From 785818fa8385fe55dab253e42a4c6728fca61333 Mon Sep 17 00:00:00 2001
From: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Date: Sat, 29 Apr 2017 11:06:43 +0200
Subject: mtd: nand: add core support for on-die ECC

A number of NAND flashes have a capability called "on-die ECC" where the
NAND chip itself is capable of detecting and correcting errors.

Linux already has support for using the ECC implementation of the NAND
controller, or a software based ECC implementation, but not for using
the ECC implementation of the NAND controller. However, such an
implementation is sometimes useful in situations where the NAND
controller provides ECC algorithms that are not strong enough for the
NAND chip used on the system. A typical case is a NAND chip that
requires a 4-bit ECC, while the NAND controller only provides a 1-bit
ECC algorithm.

This commit introduces the support for the NAND_ECC_ON_DIE ECC mode:

 - Parsing of the "on-die" value for the "nand-ecc-mode" Device Tree
   property

 - Handling NAND_ECC_ON_DIE case in nand_scan_tail(). The idea is that
   the vendor specific code for the NAND chip must implement
   ->read_page() and ->write_page(). It may optionally provide its own
   ->read_page_raw() and ->write_page_raw() as well. For OOB operation,
   we assume the standard operations are good enough, but they can be
   overridden by the vendor specific code if needed.

Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Reviewed-by: Richard Weinberger <richard@nod.at>
Signed-off-by: Boris Brezillon <boris.brezillon@free-electrons.com>
---
 include/linux/mtd/nand.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 8f67b1581683..603522097ec9 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -116,6 +116,7 @@ typedef enum {
 	NAND_ECC_HW,
 	NAND_ECC_HW_SYNDROME,
 	NAND_ECC_HW_OOB_FIRST,
+	NAND_ECC_ON_DIE,
 } nand_ecc_modes_t;
 
 enum nand_ecc_algo {
-- 
cgit v1.2.3


From cc0f51ec111266f5d255e753bf3254ad411d5c12 Mon Sep 17 00:00:00 2001
From: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Date: Sat, 29 Apr 2017 11:06:44 +0200
Subject: mtd: nand: export nand_{read,write}_page_raw()

The nand_read_page_raw() and nand_write_page_raw() functions might be
re-used by vendor-specific implementations of the read_page/write_page
functions. Instead of having vendor-specific code duplicate this code,
it is much better to export those functions and allow them to be
re-used.

Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Reviewed-by: Richard Weinberger <richard@nod.at>
Signed-off-by: Boris Brezillon <boris.brezillon@free-electrons.com>
---
 drivers/mtd/nand/nand_base.c | 10 ++++++----
 include/linux/mtd/nand.h     |  8 ++++++++
 2 files changed, 14 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index f49aecd3f1de..0b3b1a88091a 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -1524,14 +1524,15 @@ EXPORT_SYMBOL(nand_check_erased_ecc_chunk);
  *
  * Not for syndrome calculating ECC controllers, which use a special oob layout.
  */
-static int nand_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
-			      uint8_t *buf, int oob_required, int page)
+int nand_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
+		       uint8_t *buf, int oob_required, int page)
 {
 	chip->read_buf(mtd, buf, mtd->writesize);
 	if (oob_required)
 		chip->read_buf(mtd, chip->oob_poi, mtd->oobsize);
 	return 0;
 }
+EXPORT_SYMBOL(nand_read_page_raw);
 
 /**
  * nand_read_page_raw_syndrome - [INTERN] read raw page data without ecc
@@ -2469,8 +2470,8 @@ static int nand_read_oob(struct mtd_info *mtd, loff_t from,
  *
  * Not for syndrome calculating ECC controllers, which use a special oob layout.
  */
-static int nand_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
-			       const uint8_t *buf, int oob_required, int page)
+int nand_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
+			const uint8_t *buf, int oob_required, int page)
 {
 	chip->write_buf(mtd, buf, mtd->writesize);
 	if (oob_required)
@@ -2478,6 +2479,7 @@ static int nand_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
 
 	return 0;
 }
+EXPORT_SYMBOL(nand_write_page_raw);
 
 /**
  * nand_write_page_raw_syndrome - [INTERN] raw page write function
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 603522097ec9..7a01d2eb7443 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -1259,6 +1259,14 @@ int nand_read_oob_std(struct mtd_info *mtd, struct nand_chip *chip, int page);
 int nand_read_oob_syndrome(struct mtd_info *mtd, struct nand_chip *chip,
 			   int page);
 
+/* Default read_page_raw implementation */
+int nand_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
+		       uint8_t *buf, int oob_required, int page);
+
+/* Default write_page_raw implementation */
+int nand_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
+			const uint8_t *buf, int oob_required, int page);
+
 /* Reset and initialize a NAND device */
 int nand_reset(struct nand_chip *chip, int chipnr);
 
-- 
cgit v1.2.3


From c512f36b581862df20acef050c3e1a875166bd6f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 8 May 2017 09:31:19 +0200
Subject: sunrpc: properly type argument to kxdreproc_t

Pass struct rpc_request as the first argument instead of an untyped blob,
and mark the data object as const.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jeff Layton <jlayton@redhat.com>
---
 include/linux/sunrpc/xdr.h | 5 ++++-
 net/sunrpc/clnt.c          | 3 ++-
 2 files changed, 6 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 054c8cde18f3..290f189de200 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -17,6 +17,8 @@
 #include <asm/unaligned.h>
 #include <linux/scatterlist.h>
 
+struct rpc_rqst;
+
 /*
  * Buffer adjustment
  */
@@ -222,7 +224,8 @@ struct xdr_stream {
 /*
  * These are the xdr_stream style generic XDR encode and decode functions.
  */
-typedef void	(*kxdreproc_t)(void *rqstp, struct xdr_stream *xdr, void *obj);
+typedef void	(*kxdreproc_t)(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
+		const void *obj);
 typedef int	(*kxdrdproc_t)(void *rqstp, struct xdr_stream *xdr, void *obj);
 
 extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p);
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index b5cb921775a0..9fee20dc0c80 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -2476,7 +2476,8 @@ out_overflow:
 	goto out_garbage;
 }
 
-static void rpcproc_encode_null(void *rqstp, struct xdr_stream *xdr, void *obj)
+static void rpcproc_encode_null(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
+		const void *obj)
 {
 }
 
-- 
cgit v1.2.3


From 73c8dc133afb0cbe72a9234894ea72c2a0e71a73 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 8 May 2017 14:58:11 +0200
Subject: sunrpc: properly type argument to kxdrdproc_t

Pass struct rpc_request as the first argument instead of an untyped blob.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jeff Layton <jlayton@redhat.com>
Acked-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 include/linux/sunrpc/xdr.h | 3 ++-
 net/sunrpc/clnt.c          | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 290f189de200..ed0fbf0d8d0f 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -226,7 +226,8 @@ struct xdr_stream {
  */
 typedef void	(*kxdreproc_t)(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 		const void *obj);
-typedef int	(*kxdrdproc_t)(void *rqstp, struct xdr_stream *xdr, void *obj);
+typedef int	(*kxdrdproc_t)(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
+		void *obj);
 
 extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p);
 extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes);
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 9fee20dc0c80..964d5c4a1b60 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -2481,7 +2481,8 @@ static void rpcproc_encode_null(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 {
 }
 
-static int rpcproc_decode_null(void *rqstp, struct xdr_stream *xdr, void *obj)
+static int rpcproc_decode_null(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
+		void *obj)
 {
 	return 0;
 }
-- 
cgit v1.2.3


From 1c5876ddbdb401f814ef717394826e7dfb6704d4 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 8 May 2017 23:27:10 +0200
Subject: sunrpc: move p_count out of struct rpc_procinfo

p_count is the only writeable memeber of struct rpc_procinfo, which is
a good candidate to be const-ified as it contains function pointers.

This patch moves it into out out struct rpc_procinfo, and into a
separate writable array that is pointed to by struct rpc_version and
indexed by p_statidx.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/lockd/clnt4xdr.c                  |  2 ++
 fs/lockd/clntxdr.c                   |  4 ++++
 fs/lockd/mon.c                       |  4 +++-
 fs/nfs/mount_clnt.c                  |  5 ++++-
 fs/nfs/nfs2xdr.c                     |  4 +++-
 fs/nfs/nfs3xdr.c                     |  6 +++++-
 fs/nfs/nfs4xdr.c                     |  4 +++-
 fs/nfsd/nfs4callback.c               |  4 +++-
 include/linux/sunrpc/clnt.h          |  2 +-
 net/sunrpc/auth_gss/gss_rpc_upcall.c |  3 ++-
 net/sunrpc/clnt.c                    |  6 ++++--
 net/sunrpc/rpcb_clnt.c               | 12 +++++++++---
 net/sunrpc/stats.c                   |  3 +--
 13 files changed, 44 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/fs/lockd/clnt4xdr.c b/fs/lockd/clnt4xdr.c
index f0ab7a99dd23..7c255d1d7c64 100644
--- a/fs/lockd/clnt4xdr.c
+++ b/fs/lockd/clnt4xdr.c
@@ -602,8 +602,10 @@ static struct rpc_procinfo	nlm4_procedures[] = {
 	PROC(GRANTED_RES,	res,		norep),
 };
 
+static unsigned int nlm_version4_counts[ARRAY_SIZE(nlm4_procedures)];
 const struct rpc_version nlm_version4 = {
 	.number		= 4,
 	.nrprocs	= ARRAY_SIZE(nlm4_procedures),
 	.procs		= nlm4_procedures,
+	.counts		= nlm_version4_counts,
 };
diff --git a/fs/lockd/clntxdr.c b/fs/lockd/clntxdr.c
index bd8a976785ae..39500c5743a5 100644
--- a/fs/lockd/clntxdr.c
+++ b/fs/lockd/clntxdr.c
@@ -600,16 +600,20 @@ static struct rpc_procinfo	nlm_procedures[] = {
 	PROC(GRANTED_RES,	res,		norep),
 };
 
+static unsigned int nlm_version1_counts[ARRAY_SIZE(nlm_procedures)];
 static const struct rpc_version	nlm_version1 = {
 	.number		= 1,
 	.nrprocs	= ARRAY_SIZE(nlm_procedures),
 	.procs		= nlm_procedures,
+	.counts		= nlm_version1_counts,
 };
 
+static unsigned int nlm_version3_counts[ARRAY_SIZE(nlm_procedures)];
 static const struct rpc_version	nlm_version3 = {
 	.number		= 3,
 	.nrprocs	= ARRAY_SIZE(nlm_procedures),
 	.procs		= nlm_procedures,
+	.counts		= nlm_version3_counts,
 };
 
 static const struct rpc_version	*nlm_versions[] = {
diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c
index 62424e929a7f..fe4ec82764fe 100644
--- a/fs/lockd/mon.c
+++ b/fs/lockd/mon.c
@@ -552,10 +552,12 @@ static struct rpc_procinfo	nsm_procedures[] = {
 	},
 };
 
+static unsigned int nsm_version1_counts[ARRAY_SIZE(nsm_procedures)];
 static const struct rpc_version nsm_version1 = {
 	.number		= 1,
 	.nrprocs	= ARRAY_SIZE(nsm_procedures),
-	.procs		= nsm_procedures
+	.procs		= nsm_procedures,
+	.counts		= nsm_version1_counts,
 };
 
 static const struct rpc_version *nsm_version[] = {
diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c
index 806657d65074..d25914aa8bf9 100644
--- a/fs/nfs/mount_clnt.c
+++ b/fs/nfs/mount_clnt.c
@@ -504,17 +504,20 @@ static struct rpc_procinfo mnt3_procedures[] = {
 	},
 };
 
-
+static unsigned int mnt_counts[ARRAY_SIZE(mnt_procedures)];
 static const struct rpc_version mnt_version1 = {
 	.number		= 1,
 	.nrprocs	= ARRAY_SIZE(mnt_procedures),
 	.procs		= mnt_procedures,
+	.counts		= mnt_counts,
 };
 
+static unsigned int mnt3_counts[ARRAY_SIZE(mnt_procedures)];
 static const struct rpc_version mnt_version3 = {
 	.number		= 3,
 	.nrprocs	= ARRAY_SIZE(mnt3_procedures),
 	.procs		= mnt3_procedures,
+	.counts		= mnt3_counts,
 };
 
 static const struct rpc_version *mnt_version[] = {
diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c
index a299648ea321..16b4526299c1 100644
--- a/fs/nfs/nfs2xdr.c
+++ b/fs/nfs/nfs2xdr.c
@@ -1170,8 +1170,10 @@ struct rpc_procinfo	nfs_procedures[] = {
 	PROC(STATFS,	fhandle,	statfsres,	0),
 };
 
+static unsigned int nfs_version2_counts[ARRAY_SIZE(nfs_procedures)];
 const struct rpc_version nfs_version2 = {
 	.number			= 2,
 	.nrprocs		= ARRAY_SIZE(nfs_procedures),
-	.procs			= nfs_procedures
+	.procs			= nfs_procedures,
+	.counts			= nfs_version2_counts,
 };
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index cc272eb8be3e..a017ec5c7a9d 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -2578,10 +2578,12 @@ struct rpc_procinfo	nfs3_procedures[] = {
 	PROC(COMMIT,		commit,		commit,		5),
 };
 
+static unsigned int nfs_version3_counts[ARRAY_SIZE(nfs3_procedures)];
 const struct rpc_version nfs_version3 = {
 	.number			= 3,
 	.nrprocs		= ARRAY_SIZE(nfs3_procedures),
-	.procs			= nfs3_procedures
+	.procs			= nfs3_procedures,
+	.counts			= nfs_version3_counts,
 };
 
 #ifdef CONFIG_NFS_V3_ACL
@@ -2606,10 +2608,12 @@ static struct rpc_procinfo	nfs3_acl_procedures[] = {
 	},
 };
 
+static unsigned int nfs3_acl_counts[ARRAY_SIZE(nfs3_acl_procedures)];
 const struct rpc_version nfsacl_version3 = {
 	.number			= 3,
 	.nrprocs		= sizeof(nfs3_acl_procedures)/
 				  sizeof(nfs3_acl_procedures[0]),
 	.procs			= nfs3_acl_procedures,
+	.counts			= nfs3_acl_counts,
 };
 #endif  /* CONFIG_NFS_V3_ACL */
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 797f3ce75286..40cf5529e65f 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -7661,10 +7661,12 @@ struct rpc_procinfo	nfs4_procedures[] = {
 #endif /* CONFIG_NFS_V4_2 */
 };
 
+static unsigned int nfs_version4_counts[ARRAY_SIZE(nfs4_procedures)];
 const struct rpc_version nfs_version4 = {
 	.number			= 4,
 	.nrprocs		= ARRAY_SIZE(nfs4_procedures),
-	.procs			= nfs4_procedures
+	.procs			= nfs4_procedures,
+	.counts			= nfs_version4_counts,
 };
 
 /*
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index a2bedbd05b2b..afa961fe073c 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -705,6 +705,7 @@ static struct rpc_procinfo nfs4_cb_procedures[] = {
 	PROC(CB_NOTIFY_LOCK,	COMPOUND,	cb_notify_lock,	cb_notify_lock),
 };
 
+static unsigned int nfs4_cb_counts[ARRAY_SIZE(nfs4_cb_procedures)];
 static struct rpc_version nfs_cb_version4 = {
 /*
  * Note on the callback rpc program version number: despite language in rfc
@@ -715,7 +716,8 @@ static struct rpc_version nfs_cb_version4 = {
  */
 	.number			= 1,
 	.nrprocs		= ARRAY_SIZE(nfs4_cb_procedures),
-	.procs			= nfs4_cb_procedures
+	.procs			= nfs4_cb_procedures,
+	.counts			= nfs4_cb_counts,
 };
 
 static const struct rpc_version *nfs_cb_version[] = {
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 6095ecba0dde..c75ba37151fe 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -88,6 +88,7 @@ struct rpc_version {
 	u32			number;		/* version number */
 	unsigned int		nrprocs;	/* number of procs */
 	struct rpc_procinfo *	procs;		/* procedure array */
+	unsigned int		*counts;	/* call counts */
 };
 
 /*
@@ -99,7 +100,6 @@ struct rpc_procinfo {
 	kxdrdproc_t		p_decode;	/* XDR decode function */
 	unsigned int		p_arglen;	/* argument hdr length (u32) */
 	unsigned int		p_replen;	/* reply hdr length (u32) */
-	unsigned int		p_count;	/* call count */
 	unsigned int		p_timer;	/* Which RTT timer to use */
 	u32			p_statidx;	/* Which procedure to account */
 	const char *		p_name;		/* name of procedure */
diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c
index a80b8e607478..f8729b647605 100644
--- a/net/sunrpc/auth_gss/gss_rpc_upcall.c
+++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c
@@ -364,11 +364,12 @@ void gssp_free_upcall_data(struct gssp_upcall_data *data)
 /*
  * Initialization stuff
  */
-
+static unsigned int gssp_version1_counts[ARRAY_SIZE(gssp_procedures)];
 static const struct rpc_version gssp_version1 = {
 	.number		= GSSPROXY_VERS_1,
 	.nrprocs	= ARRAY_SIZE(gssp_procedures),
 	.procs		= gssp_procedures,
+	.counts		= gssp_version1_counts,
 };
 
 static const struct rpc_version *gssp_version[] = {
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 964d5c4a1b60..f2d1f971247b 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1517,14 +1517,16 @@ static void
 call_start(struct rpc_task *task)
 {
 	struct rpc_clnt	*clnt = task->tk_client;
+	int idx = task->tk_msg.rpc_proc->p_statidx;
 
 	dprintk("RPC: %5u call_start %s%d proc %s (%s)\n", task->tk_pid,
 			clnt->cl_program->name, clnt->cl_vers,
 			rpc_proc_name(task),
 			(RPC_IS_ASYNC(task) ? "async" : "sync"));
 
-	/* Increment call count */
-	task->tk_msg.rpc_proc->p_count++;
+	/* Increment call count (version might not be valid for ping) */
+	if (clnt->cl_program->version[clnt->cl_vers])
+		clnt->cl_program->version[clnt->cl_vers]->counts[idx]++;
 	clnt->cl_stats->rpccnt++;
 	task->tk_action = call_reserve;
 }
diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c
index f67b9e2897b4..9d47b9d3bbee 100644
--- a/net/sunrpc/rpcb_clnt.c
+++ b/net/sunrpc/rpcb_clnt.c
@@ -1117,22 +1117,28 @@ static const struct rpcb_info rpcb_next_version6[] = {
 	},
 };
 
+static unsigned int rpcb_version2_counts[ARRAY_SIZE(rpcb_procedures2)];
 static const struct rpc_version rpcb_version2 = {
 	.number		= RPCBVERS_2,
 	.nrprocs	= ARRAY_SIZE(rpcb_procedures2),
-	.procs		= rpcb_procedures2
+	.procs		= rpcb_procedures2,
+	.counts		= rpcb_version2_counts,
 };
 
+static unsigned int rpcb_version3_counts[ARRAY_SIZE(rpcb_procedures3)];
 static const struct rpc_version rpcb_version3 = {
 	.number		= RPCBVERS_3,
 	.nrprocs	= ARRAY_SIZE(rpcb_procedures3),
-	.procs		= rpcb_procedures3
+	.procs		= rpcb_procedures3,
+	.counts		= rpcb_version3_counts,
 };
 
+static unsigned int rpcb_version4_counts[ARRAY_SIZE(rpcb_procedures4)];
 static const struct rpc_version rpcb_version4 = {
 	.number		= RPCBVERS_4,
 	.nrprocs	= ARRAY_SIZE(rpcb_procedures4),
-	.procs		= rpcb_procedures4
+	.procs		= rpcb_procedures4,
+	.counts		= rpcb_version4_counts,
 };
 
 static const struct rpc_version *rpcb_version[] = {
diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c
index caeb01ad2b5a..91c84d18bf9a 100644
--- a/net/sunrpc/stats.c
+++ b/net/sunrpc/stats.c
@@ -55,8 +55,7 @@ static int rpc_proc_show(struct seq_file *seq, void *v) {
 		seq_printf(seq, "proc%u %u",
 					vers->number, vers->nrprocs);
 		for (j = 0; j < vers->nrprocs; j++)
-			seq_printf(seq, " %u",
-					vers->procs[j].p_count);
+			seq_printf(seq, " %u", vers->counts[j]);
 		seq_putc(seq, '\n');
 	}
 	return 0;
-- 
cgit v1.2.3


From 499b4988109e91b76f231fb1b4f1e53ec3260686 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 12 May 2017 15:36:49 +0200
Subject: sunrpc: mark all struct rpc_procinfo instances as const

struct rpc_procinfo contains function pointers, and marking it as
constant avoids it being able to be used as an attach vector for
code injections.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 fs/lockd/clnt4xdr.c                  |  2 +-
 fs/lockd/clntxdr.c                   |  2 +-
 fs/lockd/mon.c                       |  2 +-
 fs/nfs/internal.h                    |  6 +++---
 fs/nfs/mount_clnt.c                  |  4 ++--
 fs/nfs/nfs2xdr.c                     |  2 +-
 fs/nfs/nfs3xdr.c                     |  4 ++--
 fs/nfs/nfs4_fs.h                     |  2 +-
 fs/nfs/nfs4xdr.c                     |  2 +-
 fs/nfsd/nfs4callback.c               |  2 +-
 include/linux/sunrpc/clnt.h          |  4 ++--
 include/linux/sunrpc/sched.h         |  2 +-
 net/sunrpc/auth_gss/gss_rpc_upcall.c |  2 +-
 net/sunrpc/clnt.c                    |  4 ++--
 net/sunrpc/rpcb_clnt.c               | 19 ++++++++++---------
 net/sunrpc/stats.c                   |  2 +-
 16 files changed, 31 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/fs/lockd/clnt4xdr.c b/fs/lockd/clnt4xdr.c
index 7c255d1d7c64..c349fc0f9b80 100644
--- a/fs/lockd/clnt4xdr.c
+++ b/fs/lockd/clnt4xdr.c
@@ -584,7 +584,7 @@ out:
 	.p_name      = #proc,						\
 	}
 
-static struct rpc_procinfo	nlm4_procedures[] = {
+static const struct rpc_procinfo nlm4_procedures[] = {
 	PROC(TEST,		testargs,	testres),
 	PROC(LOCK,		lockargs,	res),
 	PROC(CANCEL,		cancargs,	res),
diff --git a/fs/lockd/clntxdr.c b/fs/lockd/clntxdr.c
index 39500c5743a5..3b4724a6c4ee 100644
--- a/fs/lockd/clntxdr.c
+++ b/fs/lockd/clntxdr.c
@@ -582,7 +582,7 @@ out:
 	.p_name      = #proc,						\
 	}
 
-static struct rpc_procinfo	nlm_procedures[] = {
+static const struct rpc_procinfo nlm_procedures[] = {
 	PROC(TEST,		testargs,	testres),
 	PROC(LOCK,		lockargs,	res),
 	PROC(CANCEL,		cancargs,	res),
diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c
index fe4ec82764fe..9d8166c39c54 100644
--- a/fs/lockd/mon.c
+++ b/fs/lockd/mon.c
@@ -531,7 +531,7 @@ static int nsm_xdr_dec_stat(struct rpc_rqst *rqstp,
 #define SM_monres_sz	2
 #define SM_unmonres_sz	1
 
-static struct rpc_procinfo	nsm_procedures[] = {
+static const struct rpc_procinfo nsm_procedures[] = {
 [NSMPROC_MON] = {
 		.p_proc		= NSMPROC_MON,
 		.p_encode	= nsm_xdr_enc_mon,
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index e9b4c3320e37..c21254924389 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -270,12 +270,12 @@ static inline bool nfs_match_open_context(const struct nfs_open_context *ctx1,
 }
 
 /* nfs2xdr.c */
-extern struct rpc_procinfo nfs_procedures[];
+extern const struct rpc_procinfo nfs_procedures[];
 extern int nfs2_decode_dirent(struct xdr_stream *,
 				struct nfs_entry *, int);
 
 /* nfs3xdr.c */
-extern struct rpc_procinfo nfs3_procedures[];
+extern const struct rpc_procinfo nfs3_procedures[];
 extern int nfs3_decode_dirent(struct xdr_stream *,
 				struct nfs_entry *, int);
 
@@ -292,7 +292,7 @@ extern const u32 nfs41_maxgetdevinfo_overhead;
 
 /* nfs4proc.c */
 #if IS_ENABLED(CONFIG_NFS_V4)
-extern struct rpc_procinfo nfs4_procedures[];
+extern const struct rpc_procinfo nfs4_procedures[];
 #endif
 
 #ifdef CONFIG_NFS_V4_SECURITY_LABEL
diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c
index d25914aa8bf9..3efe946672be 100644
--- a/fs/nfs/mount_clnt.c
+++ b/fs/nfs/mount_clnt.c
@@ -466,7 +466,7 @@ static int mnt_xdr_dec_mountres3(struct rpc_rqst *req,
 	return decode_auth_flavors(xdr, res);
 }
 
-static struct rpc_procinfo mnt_procedures[] = {
+static const struct rpc_procinfo mnt_procedures[] = {
 	[MOUNTPROC_MNT] = {
 		.p_proc		= MOUNTPROC_MNT,
 		.p_encode	= mnt_xdr_enc_dirpath,
@@ -485,7 +485,7 @@ static struct rpc_procinfo mnt_procedures[] = {
 	},
 };
 
-static struct rpc_procinfo mnt3_procedures[] = {
+static const struct rpc_procinfo mnt3_procedures[] = {
 	[MOUNTPROC3_MNT] = {
 		.p_proc		= MOUNTPROC3_MNT,
 		.p_encode	= mnt_xdr_enc_dirpath,
diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c
index 16b4526299c1..c8a7e98c1371 100644
--- a/fs/nfs/nfs2xdr.c
+++ b/fs/nfs/nfs2xdr.c
@@ -1152,7 +1152,7 @@ static int nfs_stat_to_errno(enum nfs_stat status)
 	.p_statidx  =  NFSPROC_##proc,					\
 	.p_name     =  #proc,						\
 	}
-struct rpc_procinfo	nfs_procedures[] = {
+const struct rpc_procinfo nfs_procedures[] = {
 	PROC(GETATTR,	fhandle,	attrstat,	1),
 	PROC(SETATTR,	sattrargs,	attrstat,	0),
 	PROC(LOOKUP,	diropargs,	diropres,	2),
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index 85ff1187e637..670eddb3ae36 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -2554,7 +2554,7 @@ static int nfs3_stat_to_errno(enum nfs_stat status)
 	.p_name      = #proc,						\
 	}
 
-struct rpc_procinfo	nfs3_procedures[] = {
+const struct rpc_procinfo nfs3_procedures[] = {
 	PROC(GETATTR,		getattr,	getattr,	1),
 	PROC(SETATTR,		setattr,	setattr,	0),
 	PROC(LOOKUP,		lookup,		lookup,		2),
@@ -2587,7 +2587,7 @@ const struct rpc_version nfs_version3 = {
 };
 
 #ifdef CONFIG_NFS_V3_ACL
-static struct rpc_procinfo	nfs3_acl_procedures[] = {
+static const struct rpc_procinfo nfs3_acl_procedures[] = {
 	[ACLPROC3_GETACL] = {
 		.p_proc = ACLPROC3_GETACL,
 		.p_encode = nfs3_xdr_enc_getacl3args,
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index af285cc27ccf..9b0cf3872722 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -493,7 +493,7 @@ static inline void nfs4_unregister_sysctl(void)
 #endif
 
 /* nfs4xdr.c */
-extern struct rpc_procinfo nfs4_procedures[];
+extern const struct rpc_procinfo nfs4_procedures[];
 
 struct nfs4_mount_data;
 
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 40cf5529e65f..0f1f290c97cd 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -7594,7 +7594,7 @@ nfs4_stat_to_errno(int stat)
 	.p_name = #proc,	\
 }
 
-struct rpc_procinfo	nfs4_procedures[] = {
+const struct rpc_procinfo nfs4_procedures[] = {
 	PROC(READ,		enc_read,		dec_read),
 	PROC(WRITE,		enc_write,		dec_write),
 	PROC(COMMIT,		enc_commit,		dec_commit),
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index afa961fe073c..ac10f78c0fb3 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -696,7 +696,7 @@ static int nfs4_xdr_dec_cb_notify_lock(struct rpc_rqst *rqstp,
 	.p_name    = #proc,						\
 }
 
-static struct rpc_procinfo nfs4_cb_procedures[] = {
+static const struct rpc_procinfo nfs4_cb_procedures[] = {
 	PROC(CB_NULL,	NULL,		cb_null,	cb_null),
 	PROC(CB_RECALL,	COMPOUND,	cb_recall,	cb_recall),
 #ifdef CONFIG_NFSD_PNFS
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index c75ba37151fe..55ef67bea06b 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -39,7 +39,7 @@ struct rpc_clnt {
 	struct list_head	cl_tasks;	/* List of tasks */
 	spinlock_t		cl_lock;	/* spinlock */
 	struct rpc_xprt __rcu *	cl_xprt;	/* transport */
-	struct rpc_procinfo *	cl_procinfo;	/* procedure info */
+	const struct rpc_procinfo *cl_procinfo;	/* procedure info */
 	u32			cl_prog,	/* RPC program number */
 				cl_vers,	/* RPC version number */
 				cl_maxproc;	/* max procedure number */
@@ -87,7 +87,7 @@ struct rpc_program {
 struct rpc_version {
 	u32			number;		/* version number */
 	unsigned int		nrprocs;	/* number of procs */
-	struct rpc_procinfo *	procs;		/* procedure array */
+	const struct rpc_procinfo *procs;	/* procedure array */
 	unsigned int		*counts;	/* call counts */
 };
 
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index 7ba040c797ec..ed60253abd0a 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -22,7 +22,7 @@
  */
 struct rpc_procinfo;
 struct rpc_message {
-	struct rpc_procinfo *	rpc_proc;	/* Procedure information */
+	const struct rpc_procinfo *rpc_proc;	/* Procedure information */
 	void *			rpc_argp;	/* Arguments */
 	void *			rpc_resp;	/* Result */
 	struct rpc_cred *	rpc_cred;	/* Credentials */
diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c
index f8729b647605..46b295e4f2b8 100644
--- a/net/sunrpc/auth_gss/gss_rpc_upcall.c
+++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c
@@ -63,7 +63,7 @@ enum {
 	.p_name   = #proc,				\
 }
 
-static struct rpc_procinfo gssp_procedures[] = {
+static const struct rpc_procinfo gssp_procedures[] = {
 	PROC(INDICATE_MECHS, indicate_mechs),
         PROC(GET_CALL_CONTEXT, get_call_context),
         PROC(IMPORT_AND_CANON_NAME, import_and_canon_name),
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index f2d1f971247b..2e49d1f892b7 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1674,7 +1674,7 @@ call_allocate(struct rpc_task *task)
 	unsigned int slack = task->tk_rqstp->rq_cred->cr_auth->au_cslack;
 	struct rpc_rqst *req = task->tk_rqstp;
 	struct rpc_xprt *xprt = req->rq_xprt;
-	struct rpc_procinfo *proc = task->tk_msg.rpc_proc;
+	const struct rpc_procinfo *proc = task->tk_msg.rpc_proc;
 	int status;
 
 	dprint_status(task);
@@ -2489,7 +2489,7 @@ static int rpcproc_decode_null(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	return 0;
 }
 
-static struct rpc_procinfo rpcproc_null = {
+static const struct rpc_procinfo rpcproc_null = {
 	.p_encode = rpcproc_encode_null,
 	.p_decode = rpcproc_decode_null,
 };
diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c
index 9d47b9d3bbee..ea0676f199c8 100644
--- a/net/sunrpc/rpcb_clnt.c
+++ b/net/sunrpc/rpcb_clnt.c
@@ -128,13 +128,13 @@ struct rpcbind_args {
 	int			r_status;
 };
 
-static struct rpc_procinfo rpcb_procedures2[];
-static struct rpc_procinfo rpcb_procedures3[];
-static struct rpc_procinfo rpcb_procedures4[];
+static const struct rpc_procinfo rpcb_procedures2[];
+static const struct rpc_procinfo rpcb_procedures3[];
+static const struct rpc_procinfo rpcb_procedures4[];
 
 struct rpcb_info {
 	u32			rpc_vers;
-	struct rpc_procinfo *	rpc_proc;
+	const struct rpc_procinfo *rpc_proc;
 };
 
 static const struct rpcb_info rpcb_next_version[];
@@ -620,7 +620,8 @@ int rpcb_v4_register(struct net *net, const u32 program, const u32 version,
 	return -EAFNOSUPPORT;
 }
 
-static struct rpc_task *rpcb_call_async(struct rpc_clnt *rpcb_clnt, struct rpcbind_args *map, struct rpc_procinfo *proc)
+static struct rpc_task *rpcb_call_async(struct rpc_clnt *rpcb_clnt,
+		struct rpcbind_args *map, const struct rpc_procinfo *proc)
 {
 	struct rpc_message msg = {
 		.rpc_proc = proc,
@@ -671,7 +672,7 @@ static struct rpc_clnt *rpcb_find_transport_owner(struct rpc_clnt *clnt)
 void rpcb_getport_async(struct rpc_task *task)
 {
 	struct rpc_clnt *clnt;
-	struct rpc_procinfo *proc;
+	const struct rpc_procinfo *proc;
 	u32 bind_version;
 	struct rpc_xprt *xprt;
 	struct rpc_clnt	*rpcb_clnt;
@@ -994,7 +995,7 @@ out_fail:
  * since the Linux kernel RPC code requires only these.
  */
 
-static struct rpc_procinfo rpcb_procedures2[] = {
+static const struct rpc_procinfo rpcb_procedures2[] = {
 	[RPCBPROC_SET] = {
 		.p_proc		= RPCBPROC_SET,
 		.p_encode	= rpcb_enc_mapping,
@@ -1027,7 +1028,7 @@ static struct rpc_procinfo rpcb_procedures2[] = {
 	},
 };
 
-static struct rpc_procinfo rpcb_procedures3[] = {
+static const struct rpc_procinfo rpcb_procedures3[] = {
 	[RPCBPROC_SET] = {
 		.p_proc		= RPCBPROC_SET,
 		.p_encode	= rpcb_enc_getaddr,
@@ -1060,7 +1061,7 @@ static struct rpc_procinfo rpcb_procedures3[] = {
 	},
 };
 
-static struct rpc_procinfo rpcb_procedures4[] = {
+static const struct rpc_procinfo rpcb_procedures4[] = {
 	[RPCBPROC_SET] = {
 		.p_proc		= RPCBPROC_SET,
 		.p_encode	= rpcb_enc_getaddr,
diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c
index 91c84d18bf9a..8b6c35ae1d57 100644
--- a/net/sunrpc/stats.c
+++ b/net/sunrpc/stats.c
@@ -191,7 +191,7 @@ void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats)
 EXPORT_SYMBOL_GPL(rpc_count_iostats);
 
 static void _print_name(struct seq_file *seq, unsigned int op,
-			struct rpc_procinfo *procs)
+			const struct rpc_procinfo *procs)
 {
 	if (procs[op].p_name)
 		seq_printf(seq, "\t%12s: ", procs[op].p_name);
-- 
cgit v1.2.3


From a6beb73272b4c0108e41bc7c7b5a447ae6c92863 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 8 May 2017 17:35:49 +0200
Subject: sunrpc: properly type pc_func callbacks

Drop the argp and resp arguments as they can trivially be derived from
the rqstp argument.  With that all functions now have the same prototype,
and we can remove the unsafe casting to svc_procfunc as well as the
svc_procfunc typedef itself.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/lockd/svc4proc.c        | 118 ++++++++++++++++++++++-------------
 fs/lockd/svcproc.c         | 118 ++++++++++++++++++++++-------------
 fs/nfs/callback_xdr.c      |   7 ++-
 fs/nfsd/nfs2acl.c          |  25 ++++----
 fs/nfsd/nfs3acl.c          |  15 ++---
 fs/nfsd/nfs3proc.c         | 151 ++++++++++++++++++++++++++-------------------
 fs/nfsd/nfs4proc.c         |   9 +--
 fs/nfsd/nfsproc.c          | 104 +++++++++++++++++--------------
 fs/nfsd/nfssvc.c           |   2 +-
 include/linux/sunrpc/svc.h |   4 +-
 net/sunrpc/svc.c           |   2 +-
 11 files changed, 328 insertions(+), 227 deletions(-)

(limited to 'include')

diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index 09c576f26c7b..3e4cba029d3d 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -62,7 +62,7 @@ no_locks:
  * NULL: Test for presence of service
  */
 static __be32
-nlm4svc_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
+nlm4svc_proc_null(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: NULL          called\n");
 	return rpc_success;
@@ -72,9 +72,9 @@ nlm4svc_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
  * TEST: Check for conflicting lock
  */
 static __be32
-nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp,
-				         struct nlm_res  *resp)
+__nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 	__be32 rc = rpc_success;
@@ -99,9 +99,15 @@ nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp,
 }
 
 static __be32
-nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp,
-				         struct nlm_res  *resp)
+nlm4svc_proc_test(struct svc_rqst *rqstp)
 {
+	return __nlm4svc_proc_test(rqstp, rqstp->rq_resp);
+}
+
+static __be32
+__nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_res *resp)
+{
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 	__be32 rc = rpc_success;
@@ -141,9 +147,15 @@ nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp,
 }
 
 static __be32
-nlm4svc_proc_cancel(struct svc_rqst *rqstp, struct nlm_args *argp,
-				           struct nlm_res  *resp)
+nlm4svc_proc_lock(struct svc_rqst *rqstp)
+{
+	return __nlm4svc_proc_lock(rqstp, rqstp->rq_resp);
+}
+
+static __be32
+__nlm4svc_proc_cancel(struct svc_rqst *rqstp, struct nlm_res *resp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 
@@ -170,13 +182,19 @@ nlm4svc_proc_cancel(struct svc_rqst *rqstp, struct nlm_args *argp,
 	return rpc_success;
 }
 
+static __be32
+nlm4svc_proc_cancel(struct svc_rqst *rqstp)
+{
+	return __nlm4svc_proc_cancel(rqstp, rqstp->rq_resp);
+}
+
 /*
  * UNLOCK: release a lock
  */
 static __be32
-nlm4svc_proc_unlock(struct svc_rqst *rqstp, struct nlm_args *argp,
-				           struct nlm_res  *resp)
+__nlm4svc_proc_unlock(struct svc_rqst *rqstp, struct nlm_res *resp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 
@@ -203,14 +221,21 @@ nlm4svc_proc_unlock(struct svc_rqst *rqstp, struct nlm_args *argp,
 	return rpc_success;
 }
 
+static __be32
+nlm4svc_proc_unlock(struct svc_rqst *rqstp)
+{
+	return __nlm4svc_proc_unlock(rqstp, rqstp->rq_resp);
+}
+
 /*
  * GRANTED: A server calls us to tell that a process' lock request
  * was granted
  */
 static __be32
-nlm4svc_proc_granted(struct svc_rqst *rqstp, struct nlm_args *argp,
-				            struct nlm_res  *resp)
+__nlm4svc_proc_granted(struct svc_rqst *rqstp, struct nlm_res *resp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
+
 	resp->cookie = argp->cookie;
 
 	dprintk("lockd: GRANTED       called\n");
@@ -219,6 +244,12 @@ nlm4svc_proc_granted(struct svc_rqst *rqstp, struct nlm_args *argp,
 	return rpc_success;
 }
 
+static __be32
+nlm4svc_proc_granted(struct svc_rqst *rqstp)
+{
+	return __nlm4svc_proc_granted(rqstp, rqstp->rq_resp);
+}
+
 /*
  * This is the generic lockd callback for async RPC calls
  */
@@ -243,9 +274,10 @@ static const struct rpc_call_ops nlm4svc_callback_ops = {
  * because we send the callback before the reply proper. I hope this
  * doesn't break any clients.
  */
-static __be32 nlm4svc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args *argp,
-		__be32 (*func)(struct svc_rqst *, struct nlm_args *, struct nlm_res  *))
+static __be32 nlm4svc_callback(struct svc_rqst *rqstp, u32 proc,
+		__be32 (*func)(struct svc_rqst *,  struct nlm_res *))
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 	struct nlm_rqst	*call;
 	__be32 stat;
@@ -261,7 +293,7 @@ static __be32 nlm4svc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args
 	if (call == NULL)
 		return rpc_system_err;
 
-	stat = func(rqstp, argp, &call->a_res);
+	stat = func(rqstp, &call->a_res);
 	if (stat != 0) {
 		nlmsvc_release_call(call);
 		return stat;
@@ -273,48 +305,44 @@ static __be32 nlm4svc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args
 	return rpc_success;
 }
 
-static __be32 nlm4svc_proc_test_msg(struct svc_rqst *rqstp, struct nlm_args *argp,
-					     void	     *resp)
+static __be32 nlm4svc_proc_test_msg(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: TEST_MSG      called\n");
-	return nlm4svc_callback(rqstp, NLMPROC_TEST_RES, argp, nlm4svc_proc_test);
+	return nlm4svc_callback(rqstp, NLMPROC_TEST_RES, __nlm4svc_proc_test);
 }
 
-static __be32 nlm4svc_proc_lock_msg(struct svc_rqst *rqstp, struct nlm_args *argp,
-					     void	     *resp)
+static __be32 nlm4svc_proc_lock_msg(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: LOCK_MSG      called\n");
-	return nlm4svc_callback(rqstp, NLMPROC_LOCK_RES, argp, nlm4svc_proc_lock);
+	return nlm4svc_callback(rqstp, NLMPROC_LOCK_RES, __nlm4svc_proc_lock);
 }
 
-static __be32 nlm4svc_proc_cancel_msg(struct svc_rqst *rqstp, struct nlm_args *argp,
-					       void	       *resp)
+static __be32 nlm4svc_proc_cancel_msg(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: CANCEL_MSG    called\n");
-	return nlm4svc_callback(rqstp, NLMPROC_CANCEL_RES, argp, nlm4svc_proc_cancel);
+	return nlm4svc_callback(rqstp, NLMPROC_CANCEL_RES, __nlm4svc_proc_cancel);
 }
 
-static __be32 nlm4svc_proc_unlock_msg(struct svc_rqst *rqstp, struct nlm_args *argp,
-                                               void            *resp)
+static __be32 nlm4svc_proc_unlock_msg(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: UNLOCK_MSG    called\n");
-	return nlm4svc_callback(rqstp, NLMPROC_UNLOCK_RES, argp, nlm4svc_proc_unlock);
+	return nlm4svc_callback(rqstp, NLMPROC_UNLOCK_RES, __nlm4svc_proc_unlock);
 }
 
-static __be32 nlm4svc_proc_granted_msg(struct svc_rqst *rqstp, struct nlm_args *argp,
-                                                void            *resp)
+static __be32 nlm4svc_proc_granted_msg(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: GRANTED_MSG   called\n");
-	return nlm4svc_callback(rqstp, NLMPROC_GRANTED_RES, argp, nlm4svc_proc_granted);
+	return nlm4svc_callback(rqstp, NLMPROC_GRANTED_RES, __nlm4svc_proc_granted);
 }
 
 /*
  * SHARE: create a DOS share or alter existing share.
  */
 static __be32
-nlm4svc_proc_share(struct svc_rqst *rqstp, struct nlm_args *argp,
-				          struct nlm_res  *resp)
+nlm4svc_proc_share(struct svc_rqst *rqstp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
+	struct nlm_res *resp = rqstp->rq_resp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 
@@ -345,9 +373,10 @@ nlm4svc_proc_share(struct svc_rqst *rqstp, struct nlm_args *argp,
  * UNSHARE: Release a DOS share.
  */
 static __be32
-nlm4svc_proc_unshare(struct svc_rqst *rqstp, struct nlm_args *argp,
-				            struct nlm_res  *resp)
+nlm4svc_proc_unshare(struct svc_rqst *rqstp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
+	struct nlm_res *resp = rqstp->rq_resp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 
@@ -378,22 +407,23 @@ nlm4svc_proc_unshare(struct svc_rqst *rqstp, struct nlm_args *argp,
  * NM_LOCK: Create an unmonitored lock
  */
 static __be32
-nlm4svc_proc_nm_lock(struct svc_rqst *rqstp, struct nlm_args *argp,
-				            struct nlm_res  *resp)
+nlm4svc_proc_nm_lock(struct svc_rqst *rqstp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
+
 	dprintk("lockd: NM_LOCK       called\n");
 
 	argp->monitor = 0;		/* just clean the monitor flag */
-	return nlm4svc_proc_lock(rqstp, argp, resp);
+	return nlm4svc_proc_lock(rqstp);
 }
 
 /*
  * FREE_ALL: Release all locks and shares held by client
  */
 static __be32
-nlm4svc_proc_free_all(struct svc_rqst *rqstp, struct nlm_args *argp,
-					     void            *resp)
+nlm4svc_proc_free_all(struct svc_rqst *rqstp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 
 	/* Obtain client */
@@ -409,9 +439,10 @@ nlm4svc_proc_free_all(struct svc_rqst *rqstp, struct nlm_args *argp,
  * SM_NOTIFY: private callback from statd (not part of official NLM proto)
  */
 static __be32
-nlm4svc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp,
-					      void	        *resp)
+nlm4svc_proc_sm_notify(struct svc_rqst *rqstp)
 {
+	struct nlm_reboot *argp = rqstp->rq_argp;
+
 	dprintk("lockd: SM_NOTIFY     called\n");
 
 	if (!nlm_privileged_requester(rqstp)) {
@@ -429,9 +460,10 @@ nlm4svc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp,
  * client sent a GRANTED_RES, let's remove the associated block
  */
 static __be32
-nlm4svc_proc_granted_res(struct svc_rqst *rqstp, struct nlm_res  *argp,
-                                                void            *resp)
+nlm4svc_proc_granted_res(struct svc_rqst *rqstp)
 {
+	struct nlm_res *argp = rqstp->rq_argp;
+
         if (!nlmsvc_ops)
                 return rpc_success;
 
@@ -463,7 +495,7 @@ nlm4svc_proc_granted_res(struct svc_rqst *rqstp, struct nlm_res  *argp,
 struct nlm_void			{ int dummy; };
 
 #define PROC(name, xargt, xrest, argt, rest, respsize)	\
- { .pc_func	= (svc_procfunc) nlm4svc_proc_##name,	\
+ { .pc_func	= nlm4svc_proc_##name,	\
    .pc_decode	= (kxdrproc_t) nlm4svc_decode_##xargt,	\
    .pc_encode	= (kxdrproc_t) nlm4svc_encode_##xrest,	\
    .pc_release	= NULL,					\
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index fb26b9f522e7..3add50661fab 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -92,7 +92,7 @@ no_locks:
  * NULL: Test for presence of service
  */
 static __be32
-nlmsvc_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
+nlmsvc_proc_null(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: NULL          called\n");
 	return rpc_success;
@@ -102,9 +102,9 @@ nlmsvc_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
  * TEST: Check for conflicting lock
  */
 static __be32
-nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp,
-				         struct nlm_res  *resp)
+__nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 	__be32 rc = rpc_success;
@@ -130,9 +130,15 @@ nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp,
 }
 
 static __be32
-nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp,
-				         struct nlm_res  *resp)
+nlmsvc_proc_test(struct svc_rqst *rqstp)
 {
+	return __nlmsvc_proc_test(rqstp, rqstp->rq_resp);
+}
+
+static __be32
+__nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_res *resp)
+{
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 	__be32 rc = rpc_success;
@@ -172,9 +178,15 @@ nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp,
 }
 
 static __be32
-nlmsvc_proc_cancel(struct svc_rqst *rqstp, struct nlm_args *argp,
-				           struct nlm_res  *resp)
+nlmsvc_proc_lock(struct svc_rqst *rqstp)
+{
+	return __nlmsvc_proc_lock(rqstp, rqstp->rq_resp);
+}
+
+static __be32
+__nlmsvc_proc_cancel(struct svc_rqst *rqstp, struct nlm_res *resp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 	struct net *net = SVC_NET(rqstp);
@@ -202,13 +214,19 @@ nlmsvc_proc_cancel(struct svc_rqst *rqstp, struct nlm_args *argp,
 	return rpc_success;
 }
 
+static __be32
+nlmsvc_proc_cancel(struct svc_rqst *rqstp)
+{
+	return __nlmsvc_proc_cancel(rqstp, rqstp->rq_resp);
+}
+
 /*
  * UNLOCK: release a lock
  */
 static __be32
-nlmsvc_proc_unlock(struct svc_rqst *rqstp, struct nlm_args *argp,
-				           struct nlm_res  *resp)
+__nlmsvc_proc_unlock(struct svc_rqst *rqstp, struct nlm_res *resp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 	struct net *net = SVC_NET(rqstp);
@@ -236,14 +254,21 @@ nlmsvc_proc_unlock(struct svc_rqst *rqstp, struct nlm_args *argp,
 	return rpc_success;
 }
 
+static __be32
+nlmsvc_proc_unlock(struct svc_rqst *rqstp)
+{
+	return __nlmsvc_proc_unlock(rqstp, rqstp->rq_resp);
+}
+
 /*
  * GRANTED: A server calls us to tell that a process' lock request
  * was granted
  */
 static __be32
-nlmsvc_proc_granted(struct svc_rqst *rqstp, struct nlm_args *argp,
-				            struct nlm_res  *resp)
+__nlmsvc_proc_granted(struct svc_rqst *rqstp, struct nlm_res *resp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
+
 	resp->cookie = argp->cookie;
 
 	dprintk("lockd: GRANTED       called\n");
@@ -252,6 +277,12 @@ nlmsvc_proc_granted(struct svc_rqst *rqstp, struct nlm_args *argp,
 	return rpc_success;
 }
 
+static __be32
+nlmsvc_proc_granted(struct svc_rqst *rqstp)
+{
+	return __nlmsvc_proc_granted(rqstp, rqstp->rq_resp);
+}
+
 /*
  * This is the generic lockd callback for async RPC calls
  */
@@ -284,9 +315,10 @@ static const struct rpc_call_ops nlmsvc_callback_ops = {
  * because we send the callback before the reply proper. I hope this
  * doesn't break any clients.
  */
-static __be32 nlmsvc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args *argp,
-		__be32 (*func)(struct svc_rqst *, struct nlm_args *, struct nlm_res  *))
+static __be32 nlmsvc_callback(struct svc_rqst *rqstp, u32 proc,
+		__be32 (*func)(struct svc_rqst *, struct nlm_res *))
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 	struct nlm_rqst	*call;
 	__be32 stat;
@@ -302,7 +334,7 @@ static __be32 nlmsvc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args
 	if (call == NULL)
 		return rpc_system_err;
 
-	stat = func(rqstp, argp, &call->a_res);
+	stat = func(rqstp, &call->a_res);
 	if (stat != 0) {
 		nlmsvc_release_call(call);
 		return stat;
@@ -314,50 +346,46 @@ static __be32 nlmsvc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args
 	return rpc_success;
 }
 
-static __be32 nlmsvc_proc_test_msg(struct svc_rqst *rqstp, struct nlm_args *argp,
-					     void	     *resp)
+static __be32 nlmsvc_proc_test_msg(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: TEST_MSG      called\n");
-	return nlmsvc_callback(rqstp, NLMPROC_TEST_RES, argp, nlmsvc_proc_test);
+	return nlmsvc_callback(rqstp, NLMPROC_TEST_RES, __nlmsvc_proc_test);
 }
 
-static __be32 nlmsvc_proc_lock_msg(struct svc_rqst *rqstp, struct nlm_args *argp,
-					     void	     *resp)
+static __be32 nlmsvc_proc_lock_msg(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: LOCK_MSG      called\n");
-	return nlmsvc_callback(rqstp, NLMPROC_LOCK_RES, argp, nlmsvc_proc_lock);
+	return nlmsvc_callback(rqstp, NLMPROC_LOCK_RES, __nlmsvc_proc_lock);
 }
 
-static __be32 nlmsvc_proc_cancel_msg(struct svc_rqst *rqstp, struct nlm_args *argp,
-					       void	       *resp)
+static __be32 nlmsvc_proc_cancel_msg(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: CANCEL_MSG    called\n");
-	return nlmsvc_callback(rqstp, NLMPROC_CANCEL_RES, argp, nlmsvc_proc_cancel);
+	return nlmsvc_callback(rqstp, NLMPROC_CANCEL_RES, __nlmsvc_proc_cancel);
 }
 
 static __be32
-nlmsvc_proc_unlock_msg(struct svc_rqst *rqstp, struct nlm_args *argp,
-                                               void            *resp)
+nlmsvc_proc_unlock_msg(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: UNLOCK_MSG    called\n");
-	return nlmsvc_callback(rqstp, NLMPROC_UNLOCK_RES, argp, nlmsvc_proc_unlock);
+	return nlmsvc_callback(rqstp, NLMPROC_UNLOCK_RES, __nlmsvc_proc_unlock);
 }
 
 static __be32
-nlmsvc_proc_granted_msg(struct svc_rqst *rqstp, struct nlm_args *argp,
-                                                void            *resp)
+nlmsvc_proc_granted_msg(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: GRANTED_MSG   called\n");
-	return nlmsvc_callback(rqstp, NLMPROC_GRANTED_RES, argp, nlmsvc_proc_granted);
+	return nlmsvc_callback(rqstp, NLMPROC_GRANTED_RES, __nlmsvc_proc_granted);
 }
 
 /*
  * SHARE: create a DOS share or alter existing share.
  */
 static __be32
-nlmsvc_proc_share(struct svc_rqst *rqstp, struct nlm_args *argp,
-				          struct nlm_res  *resp)
+nlmsvc_proc_share(struct svc_rqst *rqstp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
+	struct nlm_res *resp = rqstp->rq_resp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 
@@ -388,9 +416,10 @@ nlmsvc_proc_share(struct svc_rqst *rqstp, struct nlm_args *argp,
  * UNSHARE: Release a DOS share.
  */
 static __be32
-nlmsvc_proc_unshare(struct svc_rqst *rqstp, struct nlm_args *argp,
-				            struct nlm_res  *resp)
+nlmsvc_proc_unshare(struct svc_rqst *rqstp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
+	struct nlm_res *resp = rqstp->rq_resp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 
@@ -421,22 +450,23 @@ nlmsvc_proc_unshare(struct svc_rqst *rqstp, struct nlm_args *argp,
  * NM_LOCK: Create an unmonitored lock
  */
 static __be32
-nlmsvc_proc_nm_lock(struct svc_rqst *rqstp, struct nlm_args *argp,
-				            struct nlm_res  *resp)
+nlmsvc_proc_nm_lock(struct svc_rqst *rqstp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
+
 	dprintk("lockd: NM_LOCK       called\n");
 
 	argp->monitor = 0;		/* just clean the monitor flag */
-	return nlmsvc_proc_lock(rqstp, argp, resp);
+	return nlmsvc_proc_lock(rqstp);
 }
 
 /*
  * FREE_ALL: Release all locks and shares held by client
  */
 static __be32
-nlmsvc_proc_free_all(struct svc_rqst *rqstp, struct nlm_args *argp,
-					     void            *resp)
+nlmsvc_proc_free_all(struct svc_rqst *rqstp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 
 	/* Obtain client */
@@ -452,9 +482,10 @@ nlmsvc_proc_free_all(struct svc_rqst *rqstp, struct nlm_args *argp,
  * SM_NOTIFY: private callback from statd (not part of official NLM proto)
  */
 static __be32
-nlmsvc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp,
-					      void	        *resp)
+nlmsvc_proc_sm_notify(struct svc_rqst *rqstp)
 {
+	struct nlm_reboot *argp = rqstp->rq_argp;
+
 	dprintk("lockd: SM_NOTIFY     called\n");
 
 	if (!nlm_privileged_requester(rqstp)) {
@@ -472,9 +503,10 @@ nlmsvc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp,
  * client sent a GRANTED_RES, let's remove the associated block
  */
 static __be32
-nlmsvc_proc_granted_res(struct svc_rqst *rqstp, struct nlm_res  *argp,
-                                                void            *resp)
+nlmsvc_proc_granted_res(struct svc_rqst *rqstp)
 {
+	struct nlm_res *argp = rqstp->rq_argp;
+
 	if (!nlmsvc_ops)
 		return rpc_success;
 
@@ -505,7 +537,7 @@ nlmsvc_proc_granted_res(struct svc_rqst *rqstp, struct nlm_res  *argp,
 struct nlm_void			{ int dummy; };
 
 #define PROC(name, xargt, xrest, argt, rest, respsize)	\
- { .pc_func	= (svc_procfunc) nlmsvc_proc_##name,	\
+ { .pc_func	= nlmsvc_proc_##name,			\
    .pc_decode	= (kxdrproc_t) nlmsvc_decode_##xargt,	\
    .pc_encode	= (kxdrproc_t) nlmsvc_encode_##xrest,	\
    .pc_release	= NULL,					\
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index 287c02202b25..5a14bdaa5986 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -53,7 +53,7 @@ struct callback_op {
 
 static struct callback_op callback_ops[];
 
-static __be32 nfs4_callback_null(struct svc_rqst *rqstp, void *argp, void *resp)
+static __be32 nfs4_callback_null(struct svc_rqst *rqstp)
 {
 	return htonl(NFS4_OK);
 }
@@ -880,7 +880,7 @@ encode_hdr:
 /*
  * Decode, process and encode a COMPOUND
  */
-static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *resp)
+static __be32 nfs4_callback_compound(struct svc_rqst *rqstp)
 {
 	struct cb_compound_hdr_arg hdr_arg = { 0 };
 	struct cb_compound_hdr_res hdr_res = { NULL };
@@ -916,7 +916,8 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
 
 	while (status == 0 && nops != hdr_arg.nops) {
 		status = process_op(nops, rqstp, &xdr_in,
-				    argp, &xdr_out, resp, &cps);
+				    rqstp->rq_argp, &xdr_out, rqstp->rq_resp,
+				    &cps);
 		nops++;
 	}
 
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index 12933d07204c..4b7f84fa1fa5 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -19,7 +19,7 @@
  * NULL call.
  */
 static __be32
-nfsacld_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
+nfsacld_proc_null(struct svc_rqst *rqstp)
 {
 	return nfs_ok;
 }
@@ -27,9 +27,10 @@ nfsacld_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
 /*
  * Get the Access and/or Default ACL of a file.
  */
-static __be32 nfsacld_proc_getacl(struct svc_rqst * rqstp,
-		struct nfsd3_getaclargs *argp, struct nfsd3_getaclres *resp)
+static __be32 nfsacld_proc_getacl(struct svc_rqst *rqstp)
 {
+	struct nfsd3_getaclargs *argp = rqstp->rq_argp;
+	struct nfsd3_getaclres *resp = rqstp->rq_resp;
 	struct posix_acl *acl;
 	struct inode *inode;
 	svc_fh *fh;
@@ -87,10 +88,10 @@ fail:
 /*
  * Set the Access and/or Default ACL of a file.
  */
-static __be32 nfsacld_proc_setacl(struct svc_rqst * rqstp,
-		struct nfsd3_setaclargs *argp,
-		struct nfsd_attrstat *resp)
+static __be32 nfsacld_proc_setacl(struct svc_rqst *rqstp)
 {
+	struct nfsd3_setaclargs *argp = rqstp->rq_argp;
+	struct nfsd_attrstat *resp = rqstp->rq_resp;
 	struct inode *inode;
 	svc_fh *fh;
 	__be32 nfserr = 0;
@@ -141,9 +142,10 @@ out_errno:
 /*
  * Check file attributes
  */
-static __be32 nfsacld_proc_getattr(struct svc_rqst * rqstp,
-		struct nfsd_fhandle *argp, struct nfsd_attrstat *resp)
+static __be32 nfsacld_proc_getattr(struct svc_rqst *rqstp)
 {
+	struct nfsd_fhandle *argp = rqstp->rq_argp;
+	struct nfsd_attrstat *resp = rqstp->rq_resp;
 	__be32 nfserr;
 	dprintk("nfsd: GETATTR  %s\n", SVCFH_fmt(&argp->fh));
 
@@ -158,9 +160,10 @@ static __be32 nfsacld_proc_getattr(struct svc_rqst * rqstp,
 /*
  * Check file access
  */
-static __be32 nfsacld_proc_access(struct svc_rqst *rqstp, struct nfsd3_accessargs *argp,
-		struct nfsd3_accessres *resp)
+static __be32 nfsacld_proc_access(struct svc_rqst *rqstp)
 {
+	struct nfsd3_accessargs *argp = rqstp->rq_argp;
+	struct nfsd3_accessres *resp = rqstp->rq_resp;
 	__be32 nfserr;
 
 	dprintk("nfsd: ACCESS(2acl)   %s 0x%x\n",
@@ -347,7 +350,7 @@ struct nfsd3_voidargs { int dummy; };
 
 #define PROC(name, argt, rest, relt, cache, respsize)			\
 {									\
-	.pc_func	= (svc_procfunc) nfsacld_proc_##name,		\
+	.pc_func	= nfsacld_proc_##name,				\
 	.pc_decode	= (kxdrproc_t) nfsaclsvc_decode_##argt##args,	\
 	.pc_encode	= (kxdrproc_t) nfsaclsvc_encode_##rest##res,	\
 	.pc_release	= (kxdrproc_t) nfsaclsvc_release_##relt,	\
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index db988a229b3a..5e42004035e0 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -18,7 +18,7 @@
  * NULL call.
  */
 static __be32
-nfsd3_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
+nfsd3_proc_null(struct svc_rqst *rqstp)
 {
 	return nfs_ok;
 }
@@ -26,9 +26,10 @@ nfsd3_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
 /*
  * Get the Access and/or Default ACL of a file.
  */
-static __be32 nfsd3_proc_getacl(struct svc_rqst * rqstp,
-		struct nfsd3_getaclargs *argp, struct nfsd3_getaclres *resp)
+static __be32 nfsd3_proc_getacl(struct svc_rqst *rqstp)
 {
+	struct nfsd3_getaclargs *argp = rqstp->rq_argp;
+	struct nfsd3_getaclres *resp = rqstp->rq_resp;
 	struct posix_acl *acl;
 	struct inode *inode;
 	svc_fh *fh;
@@ -80,10 +81,10 @@ fail:
 /*
  * Set the Access and/or Default ACL of a file.
  */
-static __be32 nfsd3_proc_setacl(struct svc_rqst * rqstp,
-		struct nfsd3_setaclargs *argp,
-		struct nfsd3_attrstat *resp)
+static __be32 nfsd3_proc_setacl(struct svc_rqst *rqstp)
 {
+	struct nfsd3_setaclargs *argp = rqstp->rq_argp;
+	struct nfsd3_attrstat *resp = rqstp->rq_resp;
 	struct inode *inode;
 	svc_fh *fh;
 	__be32 nfserr = 0;
@@ -239,7 +240,7 @@ struct nfsd3_voidargs { int dummy; };
 
 #define PROC(name, argt, rest, relt, cache, respsize)			\
 {									\
-	.pc_func	= (svc_procfunc) nfsd3_proc_##name,		\
+	.pc_func	= nfsd3_proc_##name,				\
 	.pc_decode	= (kxdrproc_t) nfs3svc_decode_##argt##args,	\
 	.pc_encode	= (kxdrproc_t) nfs3svc_encode_##rest##res,	\
 	.pc_release	= (kxdrproc_t) nfs3svc_release_##relt,		\
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 24e035190770..4a2bae07cfbf 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -31,7 +31,7 @@ static int	nfs3_ftypes[] = {
  * NULL call.
  */
 static __be32
-nfsd3_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
+nfsd3_proc_null(struct svc_rqst *rqstp)
 {
 	return nfs_ok;
 }
@@ -40,9 +40,10 @@ nfsd3_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
  * Get a file's attributes
  */
 static __be32
-nfsd3_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle  *argp,
-					   struct nfsd3_attrstat *resp)
+nfsd3_proc_getattr(struct svc_rqst *rqstp)
 {
+	struct nfsd_fhandle *argp = rqstp->rq_argp;
+	struct nfsd3_attrstat *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: GETATTR(3)  %s\n",
@@ -63,9 +64,10 @@ nfsd3_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle  *argp,
  * Set a file's attributes
  */
 static __be32
-nfsd3_proc_setattr(struct svc_rqst *rqstp, struct nfsd3_sattrargs *argp,
-					   struct nfsd3_attrstat  *resp)
+nfsd3_proc_setattr(struct svc_rqst *rqstp)
 {
+	struct nfsd3_sattrargs *argp = rqstp->rq_argp;
+	struct nfsd3_attrstat *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: SETATTR(3)  %s\n",
@@ -81,9 +83,10 @@ nfsd3_proc_setattr(struct svc_rqst *rqstp, struct nfsd3_sattrargs *argp,
  * Look up a path name component
  */
 static __be32
-nfsd3_proc_lookup(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp,
-					  struct nfsd3_diropres  *resp)
+nfsd3_proc_lookup(struct svc_rqst *rqstp)
 {
+	struct nfsd3_diropargs *argp = rqstp->rq_argp;
+	struct nfsd3_diropres  *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: LOOKUP(3)   %s %.*s\n",
@@ -105,9 +108,10 @@ nfsd3_proc_lookup(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp,
  * Check file access
  */
 static __be32
-nfsd3_proc_access(struct svc_rqst *rqstp, struct nfsd3_accessargs *argp,
-					  struct nfsd3_accessres *resp)
+nfsd3_proc_access(struct svc_rqst *rqstp)
 {
+	struct nfsd3_accessargs *argp = rqstp->rq_argp;
+	struct nfsd3_accessres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: ACCESS(3)   %s 0x%x\n",
@@ -124,9 +128,10 @@ nfsd3_proc_access(struct svc_rqst *rqstp, struct nfsd3_accessargs *argp,
  * Read a symlink.
  */
 static __be32
-nfsd3_proc_readlink(struct svc_rqst *rqstp, struct nfsd3_readlinkargs *argp,
-					   struct nfsd3_readlinkres *resp)
+nfsd3_proc_readlink(struct svc_rqst *rqstp)
 {
+	struct nfsd3_readlinkargs *argp = rqstp->rq_argp;
+	struct nfsd3_readlinkres *resp = rqstp->rq_resp;
 	__be32 nfserr;
 
 	dprintk("nfsd: READLINK(3) %s\n", SVCFH_fmt(&argp->fh));
@@ -142,9 +147,10 @@ nfsd3_proc_readlink(struct svc_rqst *rqstp, struct nfsd3_readlinkargs *argp,
  * Read a portion of a file.
  */
 static __be32
-nfsd3_proc_read(struct svc_rqst *rqstp, struct nfsd3_readargs *argp,
-				        struct nfsd3_readres  *resp)
+nfsd3_proc_read(struct svc_rqst *rqstp)
 {
+	struct nfsd3_readargs *argp = rqstp->rq_argp;
+	struct nfsd3_readres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 	u32	max_blocksize = svc_max_payload(rqstp);
 	unsigned long cnt = min(argp->count, max_blocksize);
@@ -179,9 +185,10 @@ nfsd3_proc_read(struct svc_rqst *rqstp, struct nfsd3_readargs *argp,
  * Write data to a file
  */
 static __be32
-nfsd3_proc_write(struct svc_rqst *rqstp, struct nfsd3_writeargs *argp,
-					 struct nfsd3_writeres  *resp)
+nfsd3_proc_write(struct svc_rqst *rqstp)
 {
+	struct nfsd3_writeargs *argp = rqstp->rq_argp;
+	struct nfsd3_writeres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 	unsigned long cnt = argp->len;
 
@@ -206,9 +213,10 @@ nfsd3_proc_write(struct svc_rqst *rqstp, struct nfsd3_writeargs *argp,
  * first reports about SunOS compatibility problems start to pour in...
  */
 static __be32
-nfsd3_proc_create(struct svc_rqst *rqstp, struct nfsd3_createargs *argp,
-					  struct nfsd3_diropres   *resp)
+nfsd3_proc_create(struct svc_rqst *rqstp)
 {
+	struct nfsd3_createargs *argp = rqstp->rq_argp;
+	struct nfsd3_diropres *resp = rqstp->rq_resp;
 	svc_fh		*dirfhp, *newfhp = NULL;
 	struct iattr	*attr;
 	__be32		nfserr;
@@ -243,9 +251,10 @@ nfsd3_proc_create(struct svc_rqst *rqstp, struct nfsd3_createargs *argp,
  * Make directory. This operation is not idempotent.
  */
 static __be32
-nfsd3_proc_mkdir(struct svc_rqst *rqstp, struct nfsd3_createargs *argp,
-					 struct nfsd3_diropres   *resp)
+nfsd3_proc_mkdir(struct svc_rqst *rqstp)
 {
+	struct nfsd3_createargs *argp = rqstp->rq_argp;
+	struct nfsd3_diropres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: MKDIR(3)    %s %.*s\n",
@@ -263,9 +272,10 @@ nfsd3_proc_mkdir(struct svc_rqst *rqstp, struct nfsd3_createargs *argp,
 }
 
 static __be32
-nfsd3_proc_symlink(struct svc_rqst *rqstp, struct nfsd3_symlinkargs *argp,
-					   struct nfsd3_diropres    *resp)
+nfsd3_proc_symlink(struct svc_rqst *rqstp)
 {
+	struct nfsd3_symlinkargs *argp = rqstp->rq_argp;
+	struct nfsd3_diropres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: SYMLINK(3)  %s %.*s -> %.*s\n",
@@ -284,9 +294,10 @@ nfsd3_proc_symlink(struct svc_rqst *rqstp, struct nfsd3_symlinkargs *argp,
  * Make socket/fifo/device.
  */
 static __be32
-nfsd3_proc_mknod(struct svc_rqst *rqstp, struct nfsd3_mknodargs *argp,
-					 struct nfsd3_diropres  *resp)
+nfsd3_proc_mknod(struct svc_rqst *rqstp)
 {
+	struct nfsd3_mknodargs *argp = rqstp->rq_argp;
+	struct nfsd3_diropres  *resp = rqstp->rq_resp;
 	__be32	nfserr;
 	int type;
 	dev_t	rdev = 0;
@@ -321,9 +332,10 @@ nfsd3_proc_mknod(struct svc_rqst *rqstp, struct nfsd3_mknodargs *argp,
  * Remove file/fifo/socket etc.
  */
 static __be32
-nfsd3_proc_remove(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp,
-					  struct nfsd3_attrstat  *resp)
+nfsd3_proc_remove(struct svc_rqst *rqstp)
 {
+	struct nfsd3_diropargs *argp = rqstp->rq_argp;
+	struct nfsd3_attrstat *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: REMOVE(3)   %s %.*s\n",
@@ -342,9 +354,10 @@ nfsd3_proc_remove(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp,
  * Remove a directory
  */
 static __be32
-nfsd3_proc_rmdir(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp,
-					 struct nfsd3_attrstat  *resp)
+nfsd3_proc_rmdir(struct svc_rqst *rqstp)
 {
+	struct nfsd3_diropargs *argp = rqstp->rq_argp;
+	struct nfsd3_attrstat *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: RMDIR(3)    %s %.*s\n",
@@ -359,9 +372,10 @@ nfsd3_proc_rmdir(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp,
 }
 
 static __be32
-nfsd3_proc_rename(struct svc_rqst *rqstp, struct nfsd3_renameargs *argp,
-					  struct nfsd3_renameres  *resp)
+nfsd3_proc_rename(struct svc_rqst *rqstp)
 {
+	struct nfsd3_renameargs *argp = rqstp->rq_argp;
+	struct nfsd3_renameres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: RENAME(3)   %s %.*s ->\n",
@@ -381,9 +395,10 @@ nfsd3_proc_rename(struct svc_rqst *rqstp, struct nfsd3_renameargs *argp,
 }
 
 static __be32
-nfsd3_proc_link(struct svc_rqst *rqstp, struct nfsd3_linkargs *argp,
-					struct nfsd3_linkres  *resp)
+nfsd3_proc_link(struct svc_rqst *rqstp)
 {
+	struct nfsd3_linkargs *argp = rqstp->rq_argp;
+	struct nfsd3_linkres  *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: LINK(3)     %s ->\n",
@@ -404,9 +419,10 @@ nfsd3_proc_link(struct svc_rqst *rqstp, struct nfsd3_linkargs *argp,
  * Read a portion of a directory.
  */
 static __be32
-nfsd3_proc_readdir(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp,
-					   struct nfsd3_readdirres  *resp)
+nfsd3_proc_readdir(struct svc_rqst *rqstp)
 {
+	struct nfsd3_readdirargs *argp = rqstp->rq_argp;
+	struct nfsd3_readdirres  *resp = rqstp->rq_resp;
 	__be32		nfserr;
 	int		count;
 
@@ -440,9 +456,10 @@ nfsd3_proc_readdir(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp,
  * For now, we choose to ignore the dircount parameter.
  */
 static __be32
-nfsd3_proc_readdirplus(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp,
-					       struct nfsd3_readdirres  *resp)
+nfsd3_proc_readdirplus(struct svc_rqst *rqstp)
 {
+	struct nfsd3_readdirargs *argp = rqstp->rq_argp;
+	struct nfsd3_readdirres  *resp = rqstp->rq_resp;
 	__be32	nfserr;
 	int	count = 0;
 	loff_t	offset;
@@ -507,9 +524,10 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp,
  * Get file system stats
  */
 static __be32
-nfsd3_proc_fsstat(struct svc_rqst * rqstp, struct nfsd_fhandle    *argp,
-					   struct nfsd3_fsstatres *resp)
+nfsd3_proc_fsstat(struct svc_rqst *rqstp)
 {
+	struct nfsd_fhandle *argp = rqstp->rq_argp;
+	struct nfsd3_fsstatres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: FSSTAT(3)   %s\n",
@@ -524,9 +542,10 @@ nfsd3_proc_fsstat(struct svc_rqst * rqstp, struct nfsd_fhandle    *argp,
  * Get file system info
  */
 static __be32
-nfsd3_proc_fsinfo(struct svc_rqst * rqstp, struct nfsd_fhandle    *argp,
-					   struct nfsd3_fsinfores *resp)
+nfsd3_proc_fsinfo(struct svc_rqst *rqstp)
 {
+	struct nfsd_fhandle *argp = rqstp->rq_argp;
+	struct nfsd3_fsinfores *resp = rqstp->rq_resp;
 	__be32	nfserr;
 	u32	max_blocksize = svc_max_payload(rqstp);
 
@@ -567,9 +586,10 @@ nfsd3_proc_fsinfo(struct svc_rqst * rqstp, struct nfsd_fhandle    *argp,
  * Get pathconf info for the specified file
  */
 static __be32
-nfsd3_proc_pathconf(struct svc_rqst * rqstp, struct nfsd_fhandle      *argp,
-					     struct nfsd3_pathconfres *resp)
+nfsd3_proc_pathconf(struct svc_rqst *rqstp)
 {
+	struct nfsd_fhandle *argp = rqstp->rq_argp;
+	struct nfsd3_pathconfres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: PATHCONF(3) %s\n",
@@ -610,9 +630,10 @@ nfsd3_proc_pathconf(struct svc_rqst * rqstp, struct nfsd_fhandle      *argp,
  * Commit a file (range) to stable storage.
  */
 static __be32
-nfsd3_proc_commit(struct svc_rqst * rqstp, struct nfsd3_commitargs *argp,
-					   struct nfsd3_commitres  *resp)
+nfsd3_proc_commit(struct svc_rqst *rqstp)
 {
+	struct nfsd3_commitargs *argp = rqstp->rq_argp;
+	struct nfsd3_commitres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: COMMIT(3)   %s %u@%Lu\n",
@@ -655,7 +676,7 @@ struct nfsd3_voidargs { int dummy; };
 
 static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_NULL] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_null,
+		.pc_func = nfsd3_proc_null,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_voidres,
 		.pc_argsize = sizeof(struct nfsd3_voidargs),
 		.pc_ressize = sizeof(struct nfsd3_voidres),
@@ -663,7 +684,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST,
 	},
 	[NFS3PROC_GETATTR] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_getattr,
+		.pc_func = nfsd3_proc_getattr,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_attrstatres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
@@ -673,7 +694,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+AT,
 	},
 	[NFS3PROC_SETATTR] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_setattr,
+		.pc_func = nfsd3_proc_setattr,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_sattrargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
@@ -683,7 +704,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+WC,
 	},
 	[NFS3PROC_LOOKUP] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_lookup,
+		.pc_func = nfsd3_proc_lookup,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_diropres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
@@ -693,7 +714,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+FH+pAT+pAT,
 	},
 	[NFS3PROC_ACCESS] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_access,
+		.pc_func = nfsd3_proc_access,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_accessargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_accessres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
@@ -703,7 +724,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+pAT+1,
 	},
 	[NFS3PROC_READLINK] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_readlink,
+		.pc_func = nfsd3_proc_readlink,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_readlinkargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_readlinkres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
@@ -713,7 +734,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+pAT+1+NFS3_MAXPATHLEN/4,
 	},
 	[NFS3PROC_READ] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_read,
+		.pc_func = nfsd3_proc_read,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_readargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_readres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
@@ -723,7 +744,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+pAT+4+NFSSVC_MAXBLKSIZE/4,
 	},
 	[NFS3PROC_WRITE] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_write,
+		.pc_func = nfsd3_proc_write,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_writeargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_writeres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
@@ -733,7 +754,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+WC+4,
 	},
 	[NFS3PROC_CREATE] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_create,
+		.pc_func = nfsd3_proc_create,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_createargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
@@ -743,7 +764,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+(1+FH+pAT)+WC,
 	},
 	[NFS3PROC_MKDIR] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_mkdir,
+		.pc_func = nfsd3_proc_mkdir,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_mkdirargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
@@ -753,7 +774,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+(1+FH+pAT)+WC,
 	},
 	[NFS3PROC_SYMLINK] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_symlink,
+		.pc_func = nfsd3_proc_symlink,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_symlinkargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
@@ -763,7 +784,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+(1+FH+pAT)+WC,
 	},
 	[NFS3PROC_MKNOD] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_mknod,
+		.pc_func = nfsd3_proc_mknod,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_mknodargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
@@ -773,7 +794,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+(1+FH+pAT)+WC,
 	},
 	[NFS3PROC_REMOVE] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_remove,
+		.pc_func = nfsd3_proc_remove,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
@@ -783,7 +804,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+WC,
 	},
 	[NFS3PROC_RMDIR] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_rmdir,
+		.pc_func = nfsd3_proc_rmdir,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
@@ -793,7 +814,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+WC,
 	},
 	[NFS3PROC_RENAME] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_rename,
+		.pc_func = nfsd3_proc_rename,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_renameargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_renameres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
@@ -803,7 +824,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+WC+WC,
 	},
 	[NFS3PROC_LINK] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_link,
+		.pc_func = nfsd3_proc_link,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_linkargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_linkres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
@@ -813,7 +834,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+pAT+WC,
 	},
 	[NFS3PROC_READDIR] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_readdir,
+		.pc_func = nfsd3_proc_readdir,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_readdirargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
@@ -822,7 +843,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_cachetype = RC_NOCACHE,
 	},
 	[NFS3PROC_READDIRPLUS] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_readdirplus,
+		.pc_func = nfsd3_proc_readdirplus,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_readdirplusargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
@@ -831,7 +852,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_cachetype = RC_NOCACHE,
 	},
 	[NFS3PROC_FSSTAT] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_fsstat,
+		.pc_func = nfsd3_proc_fsstat,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_fsstatres,
 		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
@@ -840,7 +861,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+pAT+2*6+1,
 	},
 	[NFS3PROC_FSINFO] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_fsinfo,
+		.pc_func = nfsd3_proc_fsinfo,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_fsinfores,
 		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
@@ -849,7 +870,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+pAT+12,
 	},
 	[NFS3PROC_PATHCONF] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_pathconf,
+		.pc_func = nfsd3_proc_pathconf,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_pathconfres,
 		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
@@ -858,7 +879,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+pAT+6,
 	},
 	[NFS3PROC_COMMIT] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_commit,
+		.pc_func = nfsd3_proc_commit,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_commitargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_commitres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 695e17605b67..7a0112bc3531 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1510,7 +1510,7 @@ out:
  * NULL call.
  */
 static __be32
-nfsd4_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
+nfsd4_proc_null(struct svc_rqst *rqstp)
 {
 	return nfs_ok;
 }
@@ -1524,6 +1524,7 @@ static inline void nfsd4_increment_op_stats(u32 opnum)
 typedef __be32(*nfsd4op_func)(struct svc_rqst *, struct nfsd4_compound_state *,
 			      void *);
 typedef u32(*nfsd4op_rsize)(struct svc_rqst *, struct nfsd4_op *op);
+
 typedef void(*stateid_setter)(struct nfsd4_compound_state *, void *);
 typedef void(*stateid_getter)(struct nfsd4_compound_state *, void *);
 
@@ -1673,10 +1674,10 @@ static void svcxdr_init_encode(struct svc_rqst *rqstp,
  * COMPOUND call.
  */
 static __be32
-nfsd4_proc_compound(struct svc_rqst *rqstp, void *arg, void *res)
+nfsd4_proc_compound(struct svc_rqst *rqstp)
 {
-	struct nfsd4_compoundargs *args = arg;
-	struct nfsd4_compoundres *resp = res;
+	struct nfsd4_compoundargs *args = rqstp->rq_argp;
+	struct nfsd4_compoundres *resp = rqstp->rq_resp;
 	struct nfsd4_op	*op;
 	struct nfsd4_operation *opdesc;
 	struct nfsd4_compound_state *cstate = &resp->cstate;
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index 03a7e9da4da0..448505b939db 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -17,7 +17,7 @@ typedef struct svc_buf	svc_buf;
 
 
 static __be32
-nfsd_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
+nfsd_proc_null(struct svc_rqst *rqstp)
 {
 	return nfs_ok;
 }
@@ -39,9 +39,10 @@ nfsd_return_dirop(__be32 err, struct nfsd_diropres *resp)
  * N.B. After this call resp->fh needs an fh_put
  */
 static __be32
-nfsd_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle  *argp,
-					  struct nfsd_attrstat *resp)
+nfsd_proc_getattr(struct svc_rqst *rqstp)
 {
+	struct nfsd_fhandle *argp = rqstp->rq_argp;
+	struct nfsd_attrstat *resp = rqstp->rq_resp;
 	__be32 nfserr;
 	dprintk("nfsd: GETATTR  %s\n", SVCFH_fmt(&argp->fh));
 
@@ -56,9 +57,10 @@ nfsd_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle  *argp,
  * N.B. After this call resp->fh needs an fh_put
  */
 static __be32
-nfsd_proc_setattr(struct svc_rqst *rqstp, struct nfsd_sattrargs *argp,
-					  struct nfsd_attrstat  *resp)
+nfsd_proc_setattr(struct svc_rqst *rqstp)
 {
+	struct nfsd_sattrargs *argp = rqstp->rq_argp;
+	struct nfsd_attrstat *resp = rqstp->rq_resp;
 	struct iattr *iap = &argp->attrs;
 	struct svc_fh *fhp;
 	__be32 nfserr;
@@ -122,9 +124,10 @@ done:
  * N.B. After this call resp->fh needs an fh_put
  */
 static __be32
-nfsd_proc_lookup(struct svc_rqst *rqstp, struct nfsd_diropargs *argp,
-					 struct nfsd_diropres  *resp)
+nfsd_proc_lookup(struct svc_rqst *rqstp)
 {
+	struct nfsd_diropargs *argp = rqstp->rq_argp;
+	struct nfsd_diropres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: LOOKUP   %s %.*s\n",
@@ -142,9 +145,10 @@ nfsd_proc_lookup(struct svc_rqst *rqstp, struct nfsd_diropargs *argp,
  * Read a symlink.
  */
 static __be32
-nfsd_proc_readlink(struct svc_rqst *rqstp, struct nfsd_readlinkargs *argp,
-					   struct nfsd_readlinkres *resp)
+nfsd_proc_readlink(struct svc_rqst *rqstp)
 {
+	struct nfsd_readlinkargs *argp = rqstp->rq_argp;
+	struct nfsd_readlinkres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: READLINK %s\n", SVCFH_fmt(&argp->fh));
@@ -162,9 +166,10 @@ nfsd_proc_readlink(struct svc_rqst *rqstp, struct nfsd_readlinkargs *argp,
  * N.B. After this call resp->fh needs an fh_put
  */
 static __be32
-nfsd_proc_read(struct svc_rqst *rqstp, struct nfsd_readargs *argp,
-				       struct nfsd_readres  *resp)
+nfsd_proc_read(struct svc_rqst *rqstp)
 {
+	struct nfsd_readargs *argp = rqstp->rq_argp;
+	struct nfsd_readres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: READ    %s %d bytes at %d\n",
@@ -200,9 +205,10 @@ nfsd_proc_read(struct svc_rqst *rqstp, struct nfsd_readargs *argp,
  * N.B. After this call resp->fh needs an fh_put
  */
 static __be32
-nfsd_proc_write(struct svc_rqst *rqstp, struct nfsd_writeargs *argp,
-					struct nfsd_attrstat  *resp)
+nfsd_proc_write(struct svc_rqst *rqstp)
 {
+	struct nfsd_writeargs *argp = rqstp->rq_argp;
+	struct nfsd_attrstat *resp = rqstp->rq_resp;
 	__be32	nfserr;
 	unsigned long cnt = argp->len;
 
@@ -222,9 +228,10 @@ nfsd_proc_write(struct svc_rqst *rqstp, struct nfsd_writeargs *argp,
  * N.B. After this call _both_ argp->fh and resp->fh need an fh_put
  */
 static __be32
-nfsd_proc_create(struct svc_rqst *rqstp, struct nfsd_createargs *argp,
-					 struct nfsd_diropres   *resp)
+nfsd_proc_create(struct svc_rqst *rqstp)
 {
+	struct nfsd_createargs *argp = rqstp->rq_argp;
+	struct nfsd_diropres *resp = rqstp->rq_resp;
 	svc_fh		*dirfhp = &argp->fh;
 	svc_fh		*newfhp = &resp->fh;
 	struct iattr	*attr = &argp->attrs;
@@ -377,9 +384,9 @@ done:
 }
 
 static __be32
-nfsd_proc_remove(struct svc_rqst *rqstp, struct nfsd_diropargs *argp,
-					 void		       *resp)
+nfsd_proc_remove(struct svc_rqst *rqstp)
 {
+	struct nfsd_diropargs *argp = rqstp->rq_argp;
 	__be32	nfserr;
 
 	dprintk("nfsd: REMOVE   %s %.*s\n", SVCFH_fmt(&argp->fh),
@@ -392,9 +399,9 @@ nfsd_proc_remove(struct svc_rqst *rqstp, struct nfsd_diropargs *argp,
 }
 
 static __be32
-nfsd_proc_rename(struct svc_rqst *rqstp, struct nfsd_renameargs *argp,
-				  	 void		        *resp)
+nfsd_proc_rename(struct svc_rqst *rqstp)
 {
+	struct nfsd_renameargs *argp = rqstp->rq_argp;
 	__be32	nfserr;
 
 	dprintk("nfsd: RENAME   %s %.*s -> \n",
@@ -410,9 +417,9 @@ nfsd_proc_rename(struct svc_rqst *rqstp, struct nfsd_renameargs *argp,
 }
 
 static __be32
-nfsd_proc_link(struct svc_rqst *rqstp, struct nfsd_linkargs *argp,
-				void			    *resp)
+nfsd_proc_link(struct svc_rqst *rqstp)
 {
+	struct nfsd_linkargs *argp = rqstp->rq_argp;
 	__be32	nfserr;
 
 	dprintk("nfsd: LINK     %s ->\n",
@@ -430,9 +437,9 @@ nfsd_proc_link(struct svc_rqst *rqstp, struct nfsd_linkargs *argp,
 }
 
 static __be32
-nfsd_proc_symlink(struct svc_rqst *rqstp, struct nfsd_symlinkargs *argp,
-				          void			  *resp)
+nfsd_proc_symlink(struct svc_rqst *rqstp)
 {
+	struct nfsd_symlinkargs *argp = rqstp->rq_argp;
 	struct svc_fh	newfh;
 	__be32		nfserr;
 
@@ -460,9 +467,10 @@ nfsd_proc_symlink(struct svc_rqst *rqstp, struct nfsd_symlinkargs *argp,
  * N.B. After this call resp->fh needs an fh_put
  */
 static __be32
-nfsd_proc_mkdir(struct svc_rqst *rqstp, struct nfsd_createargs *argp,
-					struct nfsd_diropres   *resp)
+nfsd_proc_mkdir(struct svc_rqst *rqstp)
 {
+	struct nfsd_createargs *argp = rqstp->rq_argp;
+	struct nfsd_diropres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: MKDIR    %s %.*s\n", SVCFH_fmt(&argp->fh), argp->len, argp->name);
@@ -484,9 +492,9 @@ nfsd_proc_mkdir(struct svc_rqst *rqstp, struct nfsd_createargs *argp,
  * Remove a directory
  */
 static __be32
-nfsd_proc_rmdir(struct svc_rqst *rqstp, struct nfsd_diropargs *argp,
-				 	void		      *resp)
+nfsd_proc_rmdir(struct svc_rqst *rqstp)
 {
+	struct nfsd_diropargs *argp = rqstp->rq_argp;
 	__be32	nfserr;
 
 	dprintk("nfsd: RMDIR    %s %.*s\n", SVCFH_fmt(&argp->fh), argp->len, argp->name);
@@ -500,9 +508,10 @@ nfsd_proc_rmdir(struct svc_rqst *rqstp, struct nfsd_diropargs *argp,
  * Read a portion of a directory.
  */
 static __be32
-nfsd_proc_readdir(struct svc_rqst *rqstp, struct nfsd_readdirargs *argp,
-					  struct nfsd_readdirres  *resp)
+nfsd_proc_readdir(struct svc_rqst *rqstp)
 {
+	struct nfsd_readdirargs *argp = rqstp->rq_argp;
+	struct nfsd_readdirres *resp = rqstp->rq_resp;
 	int		count;
 	__be32		nfserr;
 	loff_t		offset;
@@ -540,9 +549,10 @@ nfsd_proc_readdir(struct svc_rqst *rqstp, struct nfsd_readdirargs *argp,
  * Get file system info
  */
 static __be32
-nfsd_proc_statfs(struct svc_rqst * rqstp, struct nfsd_fhandle   *argp,
-					  struct nfsd_statfsres *resp)
+nfsd_proc_statfs(struct svc_rqst *rqstp)
 {
+	struct nfsd_fhandle *argp = rqstp->rq_argp;
+	struct nfsd_statfsres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: STATFS   %s\n", SVCFH_fmt(&argp->fh));
@@ -565,7 +575,7 @@ struct nfsd_void { int dummy; };
 
 static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_NULL] = {
-		.pc_func = (svc_procfunc) nfsd_proc_null,
+		.pc_func = nfsd_proc_null,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_void,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_void),
@@ -574,7 +584,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_xdrressize = ST,
 	},
 	[NFSPROC_GETATTR] = {
-		.pc_func = (svc_procfunc) nfsd_proc_getattr,
+		.pc_func = nfsd_proc_getattr,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_fhandle,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
 		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
@@ -584,7 +594,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_xdrressize = ST+AT,
 	},
 	[NFSPROC_SETATTR] = {
-		.pc_func = (svc_procfunc) nfsd_proc_setattr,
+		.pc_func = nfsd_proc_setattr,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_sattrargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
 		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
@@ -602,7 +612,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_xdrressize = ST,
 	},
 	[NFSPROC_LOOKUP] = {
-		.pc_func = (svc_procfunc) nfsd_proc_lookup,
+		.pc_func = nfsd_proc_lookup,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_diropargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
 		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
@@ -612,7 +622,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_xdrressize = ST+FH+AT,
 	},
 	[NFSPROC_READLINK] = {
-		.pc_func = (svc_procfunc) nfsd_proc_readlink,
+		.pc_func = nfsd_proc_readlink,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_readlinkargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_readlinkres,
 		.pc_argsize = sizeof(struct nfsd_readlinkargs),
@@ -621,7 +631,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_xdrressize = ST+1+NFS_MAXPATHLEN/4,
 	},
 	[NFSPROC_READ] = {
-		.pc_func = (svc_procfunc) nfsd_proc_read,
+		.pc_func = nfsd_proc_read,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_readargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_readres,
 		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
@@ -639,7 +649,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_xdrressize = ST,
 	},
 	[NFSPROC_WRITE] = {
-		.pc_func = (svc_procfunc) nfsd_proc_write,
+		.pc_func = nfsd_proc_write,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_writeargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
 		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
@@ -649,7 +659,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_xdrressize = ST+AT,
 	},
 	[NFSPROC_CREATE] = {
-		.pc_func = (svc_procfunc) nfsd_proc_create,
+		.pc_func = nfsd_proc_create,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_createargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
 		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
@@ -659,7 +669,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_xdrressize = ST+FH+AT,
 	},
 	[NFSPROC_REMOVE] = {
-		.pc_func = (svc_procfunc) nfsd_proc_remove,
+		.pc_func = nfsd_proc_remove,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_diropargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_diropargs),
@@ -668,7 +678,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_xdrressize = ST,
 	},
 	[NFSPROC_RENAME] = {
-		.pc_func = (svc_procfunc) nfsd_proc_rename,
+		.pc_func = nfsd_proc_rename,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_renameargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_renameargs),
@@ -677,7 +687,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_xdrressize = ST,
 	},
 	[NFSPROC_LINK] = {
-		.pc_func = (svc_procfunc) nfsd_proc_link,
+		.pc_func = nfsd_proc_link,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_linkargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_linkargs),
@@ -686,7 +696,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_xdrressize = ST,
 	},
 	[NFSPROC_SYMLINK] = {
-		.pc_func = (svc_procfunc) nfsd_proc_symlink,
+		.pc_func = nfsd_proc_symlink,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_symlinkargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_symlinkargs),
@@ -695,7 +705,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_xdrressize = ST,
 	},
 	[NFSPROC_MKDIR] = {
-		.pc_func = (svc_procfunc) nfsd_proc_mkdir,
+		.pc_func = nfsd_proc_mkdir,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_createargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
 		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
@@ -705,7 +715,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_xdrressize = ST+FH+AT,
 	},
 	[NFSPROC_RMDIR] = {
-		.pc_func = (svc_procfunc) nfsd_proc_rmdir,
+		.pc_func = nfsd_proc_rmdir,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_diropargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_diropargs),
@@ -714,7 +724,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_xdrressize = ST,
 	},
 	[NFSPROC_READDIR] = {
-		.pc_func = (svc_procfunc) nfsd_proc_readdir,
+		.pc_func = nfsd_proc_readdir,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_readdirargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_readdirres,
 		.pc_argsize = sizeof(struct nfsd_readdirargs),
@@ -722,7 +732,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_cachetype = RC_NOCACHE,
 	},
 	[NFSPROC_STATFS] = {
-		.pc_func = (svc_procfunc) nfsd_proc_statfs,
+		.pc_func = nfsd_proc_statfs,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_fhandle,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_statfsres,
 		.pc_argsize = sizeof(struct nfsd_fhandle),
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 59979f0bbd4b..d64895fd8d25 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -827,7 +827,7 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 	rqstp->rq_res.head[0].iov_len += sizeof(__be32);
 
 	/* Now call the procedure handler, and encode NFS status. */
-	nfserr = proc->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp);
+	nfserr = proc->pc_func(rqstp);
 	nfserr = map_new_errors(rqstp->rq_vers, nfserr);
 	if (nfserr == nfserr_dropit || test_bit(RQ_DROPME, &rqstp->rq_flags)) {
 		dprintk("nfsd: Dropping request; may be revisited later\n");
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 94631026f79c..5c222af2db41 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -418,9 +418,9 @@ struct svc_version {
 /*
  * RPC procedure info
  */
-typedef __be32	(*svc_procfunc)(struct svc_rqst *, void *argp, void *resp);
 struct svc_procedure {
-	svc_procfunc		pc_func;	/* process the request */
+	/* process the request: */
+	__be32			(*pc_func)(struct svc_rqst *);
 	kxdrproc_t		pc_decode;	/* XDR decode args */
 	kxdrproc_t		pc_encode;	/* XDR encode result */
 	kxdrproc_t		pc_release;	/* XDR free result */
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index bc0f5a0ecbdc..95335455ad38 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1281,7 +1281,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 		if (xdr && !xdr(rqstp, argv->iov_base, rqstp->rq_argp))
 			goto err_garbage;
 
-		*statp = procp->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp);
+		*statp = procp->pc_func(rqstp);
 
 		/* Encode reply */
 		if (*statp == rpc_drop_reply ||
-- 
cgit v1.2.3


From 8537488b5a2f33980e33f654b0a515304de2b267 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 8 May 2017 18:48:24 +0200
Subject: sunrpc: properly type pc_release callbacks

Drop the p and resp arguments as they are always NULL or can trivially
be derived from the rqstp argument.  With that all functions now have the
same prototype, and we can remove the unsafe casting to kxdrproc_t.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/nfsd/nfs2acl.c          | 22 +++++++++++-----------
 fs/nfsd/nfs3acl.c          |  8 ++++----
 fs/nfsd/nfs3proc.c         | 36 ++++++++++++++++++------------------
 fs/nfsd/nfs3xdr.c          | 16 ++++++++--------
 fs/nfsd/nfs4xdr.c          |  4 +---
 fs/nfsd/nfsproc.c          | 14 +++++++-------
 fs/nfsd/nfsxdr.c           |  8 ++++----
 fs/nfsd/xdr.h              |  2 +-
 fs/nfsd/xdr3.h             |  6 ++----
 fs/nfsd/xdr4.h             |  2 +-
 include/linux/sunrpc/svc.h |  3 ++-
 net/sunrpc/svc.c           |  8 ++++----
 12 files changed, 63 insertions(+), 66 deletions(-)

(limited to 'include')

diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index 4b7f84fa1fa5..302441027f50 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -318,27 +318,27 @@ static int nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, __be32 *p,
 /*
  * XDR release functions
  */
-static int nfsaclsvc_release_getacl(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_getaclres *resp)
+static void nfsaclsvc_release_getacl(struct svc_rqst *rqstp)
 {
+	struct nfsd3_getaclres *resp = rqstp->rq_resp;
+
 	fh_put(&resp->fh);
 	posix_acl_release(resp->acl_access);
 	posix_acl_release(resp->acl_default);
-	return 1;
 }
 
-static int nfsaclsvc_release_attrstat(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd_attrstat *resp)
+static void nfsaclsvc_release_attrstat(struct svc_rqst *rqstp)
 {
+	struct nfsd_attrstat *resp = rqstp->rq_resp;
+
 	fh_put(&resp->fh);
-	return 1;
 }
 
-static int nfsaclsvc_release_access(struct svc_rqst *rqstp, __be32 *p,
-               struct nfsd3_accessres *resp)
+static void nfsaclsvc_release_access(struct svc_rqst *rqstp)
 {
-       fh_put(&resp->fh);
-       return 1;
+	struct nfsd3_accessres *resp = rqstp->rq_resp;
+
+	fh_put(&resp->fh);
 }
 
 #define nfsaclsvc_decode_voidargs	NULL
@@ -353,7 +353,7 @@ struct nfsd3_voidargs { int dummy; };
 	.pc_func	= nfsacld_proc_##name,				\
 	.pc_decode	= (kxdrproc_t) nfsaclsvc_decode_##argt##args,	\
 	.pc_encode	= (kxdrproc_t) nfsaclsvc_encode_##rest##res,	\
-	.pc_release	= (kxdrproc_t) nfsaclsvc_release_##relt,	\
+	.pc_release	= nfsaclsvc_release_##relt,	\
 	.pc_argsize	= sizeof(struct nfsd3_##argt##args),		\
 	.pc_ressize	= sizeof(struct nfsd3_##rest##res),		\
 	.pc_cachetype	= cache,					\
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index 5e42004035e0..56cdff4e954c 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -223,13 +223,13 @@ static int nfs3svc_encode_setaclres(struct svc_rqst *rqstp, __be32 *p,
 /*
  * XDR release functions
  */
-static int nfs3svc_release_getacl(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_getaclres *resp)
+static void nfs3svc_release_getacl(struct svc_rqst *rqstp)
 {
+	struct nfsd3_getaclres *resp = rqstp->rq_resp;
+
 	fh_put(&resp->fh);
 	posix_acl_release(resp->acl_access);
 	posix_acl_release(resp->acl_default);
-	return 1;
 }
 
 #define nfs3svc_decode_voidargs		NULL
@@ -243,7 +243,7 @@ struct nfsd3_voidargs { int dummy; };
 	.pc_func	= nfsd3_proc_##name,				\
 	.pc_decode	= (kxdrproc_t) nfs3svc_decode_##argt##args,	\
 	.pc_encode	= (kxdrproc_t) nfs3svc_encode_##rest##res,	\
-	.pc_release	= (kxdrproc_t) nfs3svc_release_##relt,		\
+	.pc_release	= nfs3svc_release_##relt,			\
 	.pc_argsize	= sizeof(struct nfsd3_##argt##args),		\
 	.pc_ressize	= sizeof(struct nfsd3_##rest##res),		\
 	.pc_cachetype	= cache,					\
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 4a2bae07cfbf..f0cccc0768ce 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -687,7 +687,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_getattr,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_attrstatres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
 		.pc_ressize = sizeof(struct nfsd3_attrstatres),
 		.pc_cachetype = RC_NOCACHE,
@@ -697,7 +697,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_setattr,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_sattrargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_sattrargs),
 		.pc_ressize = sizeof(struct nfsd3_wccstatres),
 		.pc_cachetype = RC_REPLBUFF,
@@ -707,7 +707,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_lookup,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_diropres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_diropargs),
 		.pc_ressize = sizeof(struct nfsd3_diropres),
 		.pc_cachetype = RC_NOCACHE,
@@ -717,7 +717,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_access,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_accessargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_accessres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_accessargs),
 		.pc_ressize = sizeof(struct nfsd3_accessres),
 		.pc_cachetype = RC_NOCACHE,
@@ -727,7 +727,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_readlink,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_readlinkargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_readlinkres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_readlinkargs),
 		.pc_ressize = sizeof(struct nfsd3_readlinkres),
 		.pc_cachetype = RC_NOCACHE,
@@ -737,7 +737,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_read,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_readargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_readres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_readargs),
 		.pc_ressize = sizeof(struct nfsd3_readres),
 		.pc_cachetype = RC_NOCACHE,
@@ -747,7 +747,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_write,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_writeargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_writeres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_writeargs),
 		.pc_ressize = sizeof(struct nfsd3_writeres),
 		.pc_cachetype = RC_REPLBUFF,
@@ -757,7 +757,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_create,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_createargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_createargs),
 		.pc_ressize = sizeof(struct nfsd3_createres),
 		.pc_cachetype = RC_REPLBUFF,
@@ -767,7 +767,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_mkdir,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_mkdirargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_mkdirargs),
 		.pc_ressize = sizeof(struct nfsd3_createres),
 		.pc_cachetype = RC_REPLBUFF,
@@ -777,7 +777,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_symlink,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_symlinkargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_symlinkargs),
 		.pc_ressize = sizeof(struct nfsd3_createres),
 		.pc_cachetype = RC_REPLBUFF,
@@ -787,7 +787,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_mknod,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_mknodargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_mknodargs),
 		.pc_ressize = sizeof(struct nfsd3_createres),
 		.pc_cachetype = RC_REPLBUFF,
@@ -797,7 +797,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_remove,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_diropargs),
 		.pc_ressize = sizeof(struct nfsd3_wccstatres),
 		.pc_cachetype = RC_REPLBUFF,
@@ -807,7 +807,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_rmdir,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_diropargs),
 		.pc_ressize = sizeof(struct nfsd3_wccstatres),
 		.pc_cachetype = RC_REPLBUFF,
@@ -817,7 +817,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_rename,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_renameargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_renameres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_renameargs),
 		.pc_ressize = sizeof(struct nfsd3_renameres),
 		.pc_cachetype = RC_REPLBUFF,
@@ -827,7 +827,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_link,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_linkargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_linkres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_linkargs),
 		.pc_ressize = sizeof(struct nfsd3_linkres),
 		.pc_cachetype = RC_REPLBUFF,
@@ -837,7 +837,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_readdir,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_readdirargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_readdirargs),
 		.pc_ressize = sizeof(struct nfsd3_readdirres),
 		.pc_cachetype = RC_NOCACHE,
@@ -846,7 +846,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_readdirplus,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_readdirplusargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_readdirplusargs),
 		.pc_ressize = sizeof(struct nfsd3_readdirres),
 		.pc_cachetype = RC_NOCACHE,
@@ -882,7 +882,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_commit,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_commitargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_commitres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_commitargs),
 		.pc_ressize = sizeof(struct nfsd3_commitres),
 		.pc_cachetype = RC_NOCACHE,
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 12feac6ee2fd..7fd361a75287 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -1114,19 +1114,19 @@ nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p,
 /*
  * XDR release functions
  */
-int
-nfs3svc_release_fhandle(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_attrstat *resp)
+void
+nfs3svc_release_fhandle(struct svc_rqst *rqstp)
 {
+	struct nfsd3_attrstat *resp = rqstp->rq_resp;
+
 	fh_put(&resp->fh);
-	return 1;
 }
 
-int
-nfs3svc_release_fhandle2(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_fhandle_pair *resp)
+void
+nfs3svc_release_fhandle2(struct svc_rqst *rqstp)
 {
+	struct nfsd3_fhandle_pair *resp = rqstp->rq_resp;
+
 	fh_put(&resp->fh1);
 	fh_put(&resp->fh2);
-	return 1;
 }
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 26780d53a6f9..5aa847bdfc63 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -4543,9 +4543,8 @@ nfs4svc_encode_voidres(struct svc_rqst *rqstp, __be32 *p, void *dummy)
         return xdr_ressize_check(rqstp, p);
 }
 
-int nfsd4_release_compoundargs(void *rq, __be32 *p, void *resp)
+void nfsd4_release_compoundargs(struct svc_rqst *rqstp)
 {
-	struct svc_rqst *rqstp = rq;
 	struct nfsd4_compoundargs *args = rqstp->rq_argp;
 
 	if (args->ops != args->iops) {
@@ -4559,7 +4558,6 @@ int nfsd4_release_compoundargs(void *rq, __be32 *p, void *resp)
 		args->to_free = tb->next;
 		kfree(tb);
 	}
-	return 1;
 }
 
 int
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index 448505b939db..dc32e0f8480d 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -587,7 +587,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_func = nfsd_proc_getattr,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_fhandle,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
-		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_fhandle),
 		.pc_ressize = sizeof(struct nfsd_attrstat),
 		.pc_cachetype = RC_NOCACHE,
@@ -597,7 +597,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_func = nfsd_proc_setattr,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_sattrargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
-		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_sattrargs),
 		.pc_ressize = sizeof(struct nfsd_attrstat),
 		.pc_cachetype = RC_REPLBUFF,
@@ -615,7 +615,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_func = nfsd_proc_lookup,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_diropargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
-		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_diropargs),
 		.pc_ressize = sizeof(struct nfsd_diropres),
 		.pc_cachetype = RC_NOCACHE,
@@ -634,7 +634,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_func = nfsd_proc_read,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_readargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_readres,
-		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_readargs),
 		.pc_ressize = sizeof(struct nfsd_readres),
 		.pc_cachetype = RC_NOCACHE,
@@ -652,7 +652,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_func = nfsd_proc_write,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_writeargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
-		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_writeargs),
 		.pc_ressize = sizeof(struct nfsd_attrstat),
 		.pc_cachetype = RC_REPLBUFF,
@@ -662,7 +662,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_func = nfsd_proc_create,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_createargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
-		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_createargs),
 		.pc_ressize = sizeof(struct nfsd_diropres),
 		.pc_cachetype = RC_REPLBUFF,
@@ -708,7 +708,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_func = nfsd_proc_mkdir,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_createargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
-		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_createargs),
 		.pc_ressize = sizeof(struct nfsd_diropres),
 		.pc_cachetype = RC_REPLBUFF,
diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c
index 6a4947a3f4fa..de7b07ee489e 100644
--- a/fs/nfsd/nfsxdr.c
+++ b/fs/nfsd/nfsxdr.c
@@ -550,10 +550,10 @@ nfssvc_encode_entry(void *ccdv, const char *name,
 /*
  * XDR release functions
  */
-int
-nfssvc_release_fhandle(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_fhandle *resp)
+void
+nfssvc_release_fhandle(struct svc_rqst *rqstp)
 {
+	struct nfsd_fhandle *resp = rqstp->rq_resp;
+
 	fh_put(&resp->fh);
-	return 1;
 }
diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h
index 4f0481d63804..2c21fa843fbf 100644
--- a/fs/nfsd/xdr.h
+++ b/fs/nfsd/xdr.h
@@ -164,7 +164,7 @@ int nfssvc_encode_readdirres(struct svc_rqst *, __be32 *, struct nfsd_readdirres
 int nfssvc_encode_entry(void *, const char *name,
 			int namlen, loff_t offset, u64 ino, unsigned int);
 
-int nfssvc_release_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *);
+void nfssvc_release_fhandle(struct svc_rqst *);
 
 /* Helper functions for NFSv2 ACL code */
 __be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, struct kstat *stat);
diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h
index 335e04aaf7db..23fe456a223b 100644
--- a/fs/nfsd/xdr3.h
+++ b/fs/nfsd/xdr3.h
@@ -330,10 +330,8 @@ int nfs3svc_encode_pathconfres(struct svc_rqst *, __be32 *,
 int nfs3svc_encode_commitres(struct svc_rqst *, __be32 *,
 				struct nfsd3_commitres *);
 
-int nfs3svc_release_fhandle(struct svc_rqst *, __be32 *,
-				struct nfsd3_attrstat *);
-int nfs3svc_release_fhandle2(struct svc_rqst *, __be32 *,
-				struct nfsd3_fhandle_pair *);
+void nfs3svc_release_fhandle(struct svc_rqst *);
+void nfs3svc_release_fhandle2(struct svc_rqst *);
 int nfs3svc_encode_entry(void *, const char *name,
 				int namlen, loff_t offset, u64 ino,
 				unsigned int);
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 8fda4abdf3b1..a158579d55a2 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -743,7 +743,7 @@ extern __be32
 nfsd4_release_lockowner(struct svc_rqst *rqstp,
 		struct nfsd4_compound_state *,
 		struct nfsd4_release_lockowner *rlockowner);
-extern int nfsd4_release_compoundargs(void *rq, __be32 *p, void *resp);
+extern void nfsd4_release_compoundargs(struct svc_rqst *rqstp);
 extern __be32 nfsd4_delegreturn(struct svc_rqst *rqstp,
 		struct nfsd4_compound_state *, struct nfsd4_delegreturn *dr);
 extern __be32 nfsd4_renew(struct svc_rqst *rqstp,
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 5c222af2db41..1381e1343640 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -423,7 +423,8 @@ struct svc_procedure {
 	__be32			(*pc_func)(struct svc_rqst *);
 	kxdrproc_t		pc_decode;	/* XDR decode args */
 	kxdrproc_t		pc_encode;	/* XDR encode result */
-	kxdrproc_t		pc_release;	/* XDR free result */
+	/* XDR free result: */
+	void			(*pc_release)(struct svc_rqst *);
 	unsigned int		pc_argsize;	/* argument struct size */
 	unsigned int		pc_ressize;	/* result struct size */
 	unsigned int		pc_count;	/* call count */
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 95335455ad38..4611cb7adc04 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1287,12 +1287,12 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 		if (*statp == rpc_drop_reply ||
 		    test_bit(RQ_DROPME, &rqstp->rq_flags)) {
 			if (procp->pc_release)
-				procp->pc_release(rqstp, NULL, rqstp->rq_resp);
+				procp->pc_release(rqstp);
 			goto dropit;
 		}
 		if (*statp == rpc_autherr_badcred) {
 			if (procp->pc_release)
-				procp->pc_release(rqstp, NULL, rqstp->rq_resp);
+				procp->pc_release(rqstp);
 			goto err_bad_auth;
 		}
 		if (*statp == rpc_success &&
@@ -1307,7 +1307,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 		if (!versp->vs_dispatch(rqstp, statp)) {
 			/* Release reply info */
 			if (procp->pc_release)
-				procp->pc_release(rqstp, NULL, rqstp->rq_resp);
+				procp->pc_release(rqstp);
 			goto dropit;
 		}
 	}
@@ -1318,7 +1318,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 
 	/* Release reply info */
 	if (procp->pc_release)
-		procp->pc_release(rqstp, NULL, rqstp->rq_resp);
+		procp->pc_release(rqstp);
 
 	if (procp->pc_encode == NULL)
 		goto dropit;
-- 
cgit v1.2.3


From 026fec7e7c4723b5f26a753bbcad69f68c8299d4 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 8 May 2017 19:01:48 +0200
Subject: sunrpc: properly type pc_decode callbacks

Drop the argp argument as it can trivially be derived from the rqstp
argument.  With that all functions now have the same prototype, and we
can remove the unsafe casting to kxdrproc_t.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/lockd/svc4proc.c        |  2 +-
 fs/lockd/svcproc.c         |  2 +-
 fs/lockd/xdr.c             | 29 ++++++++++++------
 fs/lockd/xdr4.c            | 29 ++++++++++++------
 fs/nfs/callback_xdr.c      |  4 +--
 fs/nfsd/nfs2acl.c          | 21 +++++++------
 fs/nfsd/nfs3acl.c          | 11 +++----
 fs/nfsd/nfs3proc.c         | 42 +++++++++++++-------------
 fs/nfsd/nfs3xdr.c          | 74 +++++++++++++++++++++++++++-------------------
 fs/nfsd/nfs4proc.c         |  2 +-
 fs/nfsd/nfs4xdr.c          |  4 ++-
 fs/nfsd/nfsproc.c          | 36 +++++++++++-----------
 fs/nfsd/nfssvc.c           |  5 ++--
 fs/nfsd/nfsxdr.c           | 53 ++++++++++++++++++++-------------
 fs/nfsd/xdr.h              | 34 ++++++++-------------
 fs/nfsd/xdr3.h             | 47 ++++++++++-------------------
 fs/nfsd/xdr4.h             |  3 +-
 include/linux/lockd/xdr.h  | 18 +++++------
 include/linux/lockd/xdr4.h | 18 +++++------
 include/linux/sunrpc/svc.h |  3 +-
 net/sunrpc/svc.c           |  9 ++++--
 21 files changed, 237 insertions(+), 209 deletions(-)

(limited to 'include')

diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index 3e4cba029d3d..804744f7528c 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -496,7 +496,7 @@ struct nlm_void			{ int dummy; };
 
 #define PROC(name, xargt, xrest, argt, rest, respsize)	\
  { .pc_func	= nlm4svc_proc_##name,	\
-   .pc_decode	= (kxdrproc_t) nlm4svc_decode_##xargt,	\
+   .pc_decode	= nlm4svc_decode_##xargt,	\
    .pc_encode	= (kxdrproc_t) nlm4svc_encode_##xrest,	\
    .pc_release	= NULL,					\
    .pc_argsize	= sizeof(struct nlm_##argt),		\
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index 3add50661fab..204a698f7d41 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -538,7 +538,7 @@ struct nlm_void			{ int dummy; };
 
 #define PROC(name, xargt, xrest, argt, rest, respsize)	\
  { .pc_func	= nlmsvc_proc_##name,			\
-   .pc_decode	= (kxdrproc_t) nlmsvc_decode_##xargt,	\
+   .pc_decode	= nlmsvc_decode_##xargt,		\
    .pc_encode	= (kxdrproc_t) nlmsvc_encode_##xrest,	\
    .pc_release	= NULL,					\
    .pc_argsize	= sizeof(struct nlm_##argt),		\
diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c
index 5b651daad518..b57af63fba56 100644
--- a/fs/lockd/xdr.c
+++ b/fs/lockd/xdr.c
@@ -182,8 +182,9 @@ nlm_encode_testres(__be32 *p, struct nlm_res *resp)
  * First, the server side XDR functions
  */
 int
-nlmsvc_decode_testargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
+nlmsvc_decode_testargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	u32	exclusive;
 
 	if (!(p = nlm_decode_cookie(p, &argp->cookie)))
@@ -207,8 +208,9 @@ nlmsvc_encode_testres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
 }
 
 int
-nlmsvc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
+nlmsvc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	u32	exclusive;
 
 	if (!(p = nlm_decode_cookie(p, &argp->cookie)))
@@ -227,8 +229,9 @@ nlmsvc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
 }
 
 int
-nlmsvc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
+nlmsvc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	u32	exclusive;
 
 	if (!(p = nlm_decode_cookie(p, &argp->cookie)))
@@ -243,8 +246,10 @@ nlmsvc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
 }
 
 int
-nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
+nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
+
 	if (!(p = nlm_decode_cookie(p, &argp->cookie))
 	 || !(p = nlm_decode_lock(p, &argp->lock)))
 		return 0;
@@ -253,8 +258,9 @@ nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
 }
 
 int
-nlmsvc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
+nlmsvc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_lock	*lock = &argp->lock;
 
 	memset(lock, 0, sizeof(*lock));
@@ -293,8 +299,9 @@ nlmsvc_encode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
 }
 
 int
-nlmsvc_decode_notify(struct svc_rqst *rqstp, __be32 *p, struct nlm_args *argp)
+nlmsvc_decode_notify(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_lock	*lock = &argp->lock;
 
 	if (!(p = xdr_decode_string_inplace(p, &lock->caller,
@@ -305,8 +312,10 @@ nlmsvc_decode_notify(struct svc_rqst *rqstp, __be32 *p, struct nlm_args *argp)
 }
 
 int
-nlmsvc_decode_reboot(struct svc_rqst *rqstp, __be32 *p, struct nlm_reboot *argp)
+nlmsvc_decode_reboot(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_reboot *argp = rqstp->rq_argp;
+
 	if (!(p = xdr_decode_string_inplace(p, &argp->mon, &argp->len, SM_MAXSTRLEN)))
 		return 0;
 	argp->state = ntohl(*p++);
@@ -316,8 +325,10 @@ nlmsvc_decode_reboot(struct svc_rqst *rqstp, __be32 *p, struct nlm_reboot *argp)
 }
 
 int
-nlmsvc_decode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
+nlmsvc_decode_res(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_res *resp = rqstp->rq_argp;
+
 	if (!(p = nlm_decode_cookie(p, &resp->cookie)))
 		return 0;
 	resp->status = *p++;
@@ -325,7 +336,7 @@ nlmsvc_decode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
 }
 
 int
-nlmsvc_decode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+nlmsvc_decode_void(struct svc_rqst *rqstp, __be32 *p)
 {
 	return xdr_argsize_check(rqstp, p);
 }
diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c
index dfa4789cd460..46e18598a15c 100644
--- a/fs/lockd/xdr4.c
+++ b/fs/lockd/xdr4.c
@@ -179,8 +179,9 @@ nlm4_encode_testres(__be32 *p, struct nlm_res *resp)
  * First, the server side XDR functions
  */
 int
-nlm4svc_decode_testargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
+nlm4svc_decode_testargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	u32	exclusive;
 
 	if (!(p = nlm4_decode_cookie(p, &argp->cookie)))
@@ -204,8 +205,9 @@ nlm4svc_encode_testres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
 }
 
 int
-nlm4svc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
+nlm4svc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	u32	exclusive;
 
 	if (!(p = nlm4_decode_cookie(p, &argp->cookie)))
@@ -224,8 +226,9 @@ nlm4svc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
 }
 
 int
-nlm4svc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
+nlm4svc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	u32	exclusive;
 
 	if (!(p = nlm4_decode_cookie(p, &argp->cookie)))
@@ -240,8 +243,10 @@ nlm4svc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
 }
 
 int
-nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
+nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
+
 	if (!(p = nlm4_decode_cookie(p, &argp->cookie))
 	 || !(p = nlm4_decode_lock(p, &argp->lock)))
 		return 0;
@@ -250,8 +255,9 @@ nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
 }
 
 int
-nlm4svc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
+nlm4svc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_lock	*lock = &argp->lock;
 
 	memset(lock, 0, sizeof(*lock));
@@ -290,8 +296,9 @@ nlm4svc_encode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
 }
 
 int
-nlm4svc_decode_notify(struct svc_rqst *rqstp, __be32 *p, struct nlm_args *argp)
+nlm4svc_decode_notify(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_lock	*lock = &argp->lock;
 
 	if (!(p = xdr_decode_string_inplace(p, &lock->caller,
@@ -302,8 +309,10 @@ nlm4svc_decode_notify(struct svc_rqst *rqstp, __be32 *p, struct nlm_args *argp)
 }
 
 int
-nlm4svc_decode_reboot(struct svc_rqst *rqstp, __be32 *p, struct nlm_reboot *argp)
+nlm4svc_decode_reboot(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_reboot *argp = rqstp->rq_argp;
+
 	if (!(p = xdr_decode_string_inplace(p, &argp->mon, &argp->len, SM_MAXSTRLEN)))
 		return 0;
 	argp->state = ntohl(*p++);
@@ -313,8 +322,10 @@ nlm4svc_decode_reboot(struct svc_rqst *rqstp, __be32 *p, struct nlm_reboot *argp
 }
 
 int
-nlm4svc_decode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
+nlm4svc_decode_res(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_res *resp = rqstp->rq_argp;
+
 	if (!(p = nlm4_decode_cookie(p, &resp->cookie)))
 		return 0;
 	resp->status = *p++;
@@ -322,7 +333,7 @@ nlm4svc_decode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
 }
 
 int
-nlm4svc_decode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+nlm4svc_decode_void(struct svc_rqst *rqstp, __be32 *p)
 {
 	return xdr_argsize_check(rqstp, p);
 }
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index 5a14bdaa5986..23ecbf7a40c1 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -58,7 +58,7 @@ static __be32 nfs4_callback_null(struct svc_rqst *rqstp)
 	return htonl(NFS4_OK);
 }
 
-static int nfs4_decode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+static int nfs4_decode_void(struct svc_rqst *rqstp, __be32 *p)
 {
 	return xdr_argsize_check(rqstp, p);
 }
@@ -998,7 +998,7 @@ static struct callback_op callback_ops[] = {
 static struct svc_procedure nfs4_callback_procedures1[] = {
 	[CB_NULL] = {
 		.pc_func = nfs4_callback_null,
-		.pc_decode = (kxdrproc_t)nfs4_decode_void,
+		.pc_decode = nfs4_decode_void,
 		.pc_encode = (kxdrproc_t)nfs4_encode_void,
 		.pc_xdrressize = 1,
 	},
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index 302441027f50..bcfdaa83ee6c 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -182,9 +182,10 @@ static __be32 nfsacld_proc_access(struct svc_rqst *rqstp)
 /*
  * XDR decode functions
  */
-static int nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_getaclargs *argp)
+static int nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_getaclargs *argp = rqstp->rq_argp;
+
 	p = nfs2svc_decode_fh(p, &argp->fh);
 	if (!p)
 		return 0;
@@ -194,9 +195,9 @@ static int nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 
-static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_setaclargs *argp)
+static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_setaclargs *argp = rqstp->rq_argp;
 	struct kvec *head = rqstp->rq_arg.head;
 	unsigned int base;
 	int n;
@@ -220,18 +221,20 @@ static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p,
 	return (n > 0);
 }
 
-static int nfsaclsvc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd_fhandle *argp)
+static int nfsaclsvc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_fhandle *argp = rqstp->rq_argp;
+
 	p = nfs2svc_decode_fh(p, &argp->fh);
 	if (!p)
 		return 0;
 	return xdr_argsize_check(rqstp, p);
 }
 
-static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_accessargs *argp)
+static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_accessargs *argp = rqstp->rq_argp;
+
 	p = nfs2svc_decode_fh(p, &argp->fh);
 	if (!p)
 		return 0;
@@ -351,7 +354,7 @@ struct nfsd3_voidargs { int dummy; };
 #define PROC(name, argt, rest, relt, cache, respsize)			\
 {									\
 	.pc_func	= nfsacld_proc_##name,				\
-	.pc_decode	= (kxdrproc_t) nfsaclsvc_decode_##argt##args,	\
+	.pc_decode	= nfsaclsvc_decode_##argt##args,		\
 	.pc_encode	= (kxdrproc_t) nfsaclsvc_encode_##rest##res,	\
 	.pc_release	= nfsaclsvc_release_##relt,	\
 	.pc_argsize	= sizeof(struct nfsd3_##argt##args),		\
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index 56cdff4e954c..4e68d6b5f409 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -124,9 +124,10 @@ out:
 /*
  * XDR decode functions
  */
-static int nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_getaclargs *args)
+static int nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_getaclargs *args = rqstp->rq_argp;
+
 	p = nfs3svc_decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
@@ -136,9 +137,9 @@ static int nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 
-static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_setaclargs *args)
+static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_setaclargs *args = rqstp->rq_argp;
 	struct kvec *head = rqstp->rq_arg.head;
 	unsigned int base;
 	int n;
@@ -241,7 +242,7 @@ struct nfsd3_voidargs { int dummy; };
 #define PROC(name, argt, rest, relt, cache, respsize)			\
 {									\
 	.pc_func	= nfsd3_proc_##name,				\
-	.pc_decode	= (kxdrproc_t) nfs3svc_decode_##argt##args,	\
+	.pc_decode	= nfs3svc_decode_##argt##args,			\
 	.pc_encode	= (kxdrproc_t) nfs3svc_encode_##rest##res,	\
 	.pc_release	= nfs3svc_release_##relt,			\
 	.pc_argsize	= sizeof(struct nfsd3_##argt##args),		\
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index f0cccc0768ce..ed83e8a9e7b4 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -685,7 +685,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_GETATTR] = {
 		.pc_func = nfsd3_proc_getattr,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
+		.pc_decode = nfs3svc_decode_fhandleargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_attrstatres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
@@ -695,7 +695,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_SETATTR] = {
 		.pc_func = nfsd3_proc_setattr,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_sattrargs,
+		.pc_decode = nfs3svc_decode_sattrargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_sattrargs),
@@ -705,7 +705,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_LOOKUP] = {
 		.pc_func = nfsd3_proc_lookup,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs,
+		.pc_decode = nfs3svc_decode_diropargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_diropres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_diropargs),
@@ -715,7 +715,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_ACCESS] = {
 		.pc_func = nfsd3_proc_access,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_accessargs,
+		.pc_decode = nfs3svc_decode_accessargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_accessres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_accessargs),
@@ -725,7 +725,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_READLINK] = {
 		.pc_func = nfsd3_proc_readlink,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_readlinkargs,
+		.pc_decode = nfs3svc_decode_readlinkargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_readlinkres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_readlinkargs),
@@ -735,7 +735,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_READ] = {
 		.pc_func = nfsd3_proc_read,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_readargs,
+		.pc_decode = nfs3svc_decode_readargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_readres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_readargs),
@@ -745,7 +745,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_WRITE] = {
 		.pc_func = nfsd3_proc_write,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_writeargs,
+		.pc_decode = nfs3svc_decode_writeargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_writeres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_writeargs),
@@ -755,7 +755,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_CREATE] = {
 		.pc_func = nfsd3_proc_create,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_createargs,
+		.pc_decode = nfs3svc_decode_createargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_createargs),
@@ -765,7 +765,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_MKDIR] = {
 		.pc_func = nfsd3_proc_mkdir,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_mkdirargs,
+		.pc_decode = nfs3svc_decode_mkdirargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_mkdirargs),
@@ -775,7 +775,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_SYMLINK] = {
 		.pc_func = nfsd3_proc_symlink,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_symlinkargs,
+		.pc_decode = nfs3svc_decode_symlinkargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_symlinkargs),
@@ -785,7 +785,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_MKNOD] = {
 		.pc_func = nfsd3_proc_mknod,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_mknodargs,
+		.pc_decode = nfs3svc_decode_mknodargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_mknodargs),
@@ -795,7 +795,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_REMOVE] = {
 		.pc_func = nfsd3_proc_remove,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs,
+		.pc_decode = nfs3svc_decode_diropargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_diropargs),
@@ -805,7 +805,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_RMDIR] = {
 		.pc_func = nfsd3_proc_rmdir,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs,
+		.pc_decode = nfs3svc_decode_diropargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_diropargs),
@@ -815,7 +815,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_RENAME] = {
 		.pc_func = nfsd3_proc_rename,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_renameargs,
+		.pc_decode = nfs3svc_decode_renameargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_renameres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_renameargs),
@@ -825,7 +825,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_LINK] = {
 		.pc_func = nfsd3_proc_link,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_linkargs,
+		.pc_decode = nfs3svc_decode_linkargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_linkres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_linkargs),
@@ -835,7 +835,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_READDIR] = {
 		.pc_func = nfsd3_proc_readdir,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_readdirargs,
+		.pc_decode = nfs3svc_decode_readdirargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_readdirargs),
@@ -844,7 +844,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_READDIRPLUS] = {
 		.pc_func = nfsd3_proc_readdirplus,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_readdirplusargs,
+		.pc_decode = nfs3svc_decode_readdirplusargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_readdirplusargs),
@@ -853,7 +853,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_FSSTAT] = {
 		.pc_func = nfsd3_proc_fsstat,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
+		.pc_decode = nfs3svc_decode_fhandleargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_fsstatres,
 		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
 		.pc_ressize = sizeof(struct nfsd3_fsstatres),
@@ -862,7 +862,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_FSINFO] = {
 		.pc_func = nfsd3_proc_fsinfo,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
+		.pc_decode = nfs3svc_decode_fhandleargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_fsinfores,
 		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
 		.pc_ressize = sizeof(struct nfsd3_fsinfores),
@@ -871,7 +871,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_PATHCONF] = {
 		.pc_func = nfsd3_proc_pathconf,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
+		.pc_decode = nfs3svc_decode_fhandleargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_pathconfres,
 		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
 		.pc_ressize = sizeof(struct nfsd3_pathconfres),
@@ -880,7 +880,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_COMMIT] = {
 		.pc_func = nfsd3_proc_commit,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_commitargs,
+		.pc_decode = nfs3svc_decode_commitargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_commitres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_commitargs),
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 7fd361a75287..be8bf8af9917 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -273,8 +273,10 @@ void fill_post_wcc(struct svc_fh *fhp)
  * XDR decode functions
  */
 int
-nfs3svc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *args)
+nfs3svc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_fhandle *args = rqstp->rq_argp;
+
 	p = decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
@@ -282,9 +284,10 @@ nfs3svc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *a
 }
 
 int
-nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_sattrargs *args)
+nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_sattrargs *args = rqstp->rq_argp;
+
 	p = decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
@@ -300,9 +303,10 @@ nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_diropargs *args)
+nfs3svc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_diropargs *args = rqstp->rq_argp;
+
 	if (!(p = decode_fh(p, &args->fh))
 	 || !(p = decode_filename(p, &args->name, &args->len)))
 		return 0;
@@ -311,9 +315,10 @@ nfs3svc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_accessargs *args)
+nfs3svc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_accessargs *args = rqstp->rq_argp;
+
 	p = decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
@@ -323,9 +328,9 @@ nfs3svc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_readargs *args)
+nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_readargs *args = rqstp->rq_argp;
 	unsigned int len;
 	int v;
 	u32 max_blocksize = svc_max_payload(rqstp);
@@ -356,9 +361,9 @@ nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_writeargs *args)
+nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_writeargs *args = rqstp->rq_argp;
 	unsigned int len, v, hdr, dlen;
 	u32 max_blocksize = svc_max_payload(rqstp);
 	struct kvec *head = rqstp->rq_arg.head;
@@ -416,9 +421,10 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_createargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_createargs *args)
+nfs3svc_decode_createargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_createargs *args = rqstp->rq_argp;
+
 	if (!(p = decode_fh(p, &args->fh))
 	 || !(p = decode_filename(p, &args->name, &args->len)))
 		return 0;
@@ -438,10 +444,12 @@ nfs3svc_decode_createargs(struct svc_rqst *rqstp, __be32 *p,
 
 	return xdr_argsize_check(rqstp, p);
 }
+
 int
-nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_createargs *args)
+nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_createargs *args = rqstp->rq_argp;
+
 	if (!(p = decode_fh(p, &args->fh)) ||
 	    !(p = decode_filename(p, &args->name, &args->len)))
 		return 0;
@@ -451,9 +459,9 @@ nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_symlinkargs *args)
+nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_symlinkargs *args = rqstp->rq_argp;
 	unsigned int len, avail;
 	char *old, *new;
 	struct kvec *vec;
@@ -503,9 +511,10 @@ nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_mknodargs *args)
+nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_mknodargs *args = rqstp->rq_argp;
+
 	if (!(p = decode_fh(p, &args->fh))
 	 || !(p = decode_filename(p, &args->name, &args->len)))
 		return 0;
@@ -525,9 +534,10 @@ nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_renameargs *args)
+nfs3svc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_renameargs *args = rqstp->rq_argp;
+
 	if (!(p = decode_fh(p, &args->ffh))
 	 || !(p = decode_filename(p, &args->fname, &args->flen))
 	 || !(p = decode_fh(p, &args->tfh))
@@ -538,9 +548,10 @@ nfs3svc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_readlinkargs *args)
+nfs3svc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_readlinkargs *args = rqstp->rq_argp;
+
 	p = decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
@@ -552,9 +563,10 @@ nfs3svc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_linkargs *args)
+nfs3svc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_linkargs *args = rqstp->rq_argp;
+
 	if (!(p = decode_fh(p, &args->ffh))
 	 || !(p = decode_fh(p, &args->tfh))
 	 || !(p = decode_filename(p, &args->tname, &args->tlen)))
@@ -564,9 +576,9 @@ nfs3svc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_readdirargs *args)
+nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_readdirargs *args = rqstp->rq_argp;
 	p = decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
@@ -585,9 +597,9 @@ nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_readdirargs *args)
+nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_readdirargs *args = rqstp->rq_argp;
 	int len;
 	u32 max_blocksize = svc_max_payload(rqstp);
 
@@ -613,9 +625,9 @@ nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_commitargs *args)
+nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_commitargs *args = rqstp->rq_argp;
 	p = decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 7a0112bc3531..6ff434b77a9e 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -2528,7 +2528,7 @@ static struct svc_procedure		nfsd_procedures4[2] = {
 	},
 	[NFSPROC4_COMPOUND] = {
 		.pc_func = nfsd4_proc_compound,
-		.pc_decode = (kxdrproc_t) nfs4svc_decode_compoundargs,
+		.pc_decode = nfs4svc_decode_compoundargs,
 		.pc_encode = (kxdrproc_t) nfs4svc_encode_compoundres,
 		.pc_argsize = sizeof(struct nfsd4_compoundargs),
 		.pc_ressize = sizeof(struct nfsd4_compoundres),
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 5aa847bdfc63..3a7e117bd11e 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -4561,8 +4561,10 @@ void nfsd4_release_compoundargs(struct svc_rqst *rqstp)
 }
 
 int
-nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compoundargs *args)
+nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd4_compoundargs *args = rqstp->rq_argp;
+
 	if (rqstp->rq_arg.head[0].iov_len % 4) {
 		/* client is nuts */
 		dprintk("%s: compound not properly padded! (peeraddr=%pISc xid=0x%x)",
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index dc32e0f8480d..d351d0ef6d34 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -576,7 +576,7 @@ struct nfsd_void { int dummy; };
 static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_NULL] = {
 		.pc_func = nfsd_proc_null,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_void,
+		.pc_decode = nfssvc_decode_void,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_void),
 		.pc_ressize = sizeof(struct nfsd_void),
@@ -585,7 +585,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_GETATTR] = {
 		.pc_func = nfsd_proc_getattr,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_fhandle,
+		.pc_decode = nfssvc_decode_fhandle,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
 		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_fhandle),
@@ -595,7 +595,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_SETATTR] = {
 		.pc_func = nfsd_proc_setattr,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_sattrargs,
+		.pc_decode = nfssvc_decode_sattrargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
 		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_sattrargs),
@@ -604,7 +604,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_xdrressize = ST+AT,
 	},
 	[NFSPROC_ROOT] = {
-		.pc_decode = (kxdrproc_t) nfssvc_decode_void,
+		.pc_decode = nfssvc_decode_void,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_void),
 		.pc_ressize = sizeof(struct nfsd_void),
@@ -613,7 +613,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_LOOKUP] = {
 		.pc_func = nfsd_proc_lookup,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_diropargs,
+		.pc_decode = nfssvc_decode_diropargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
 		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_diropargs),
@@ -623,7 +623,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_READLINK] = {
 		.pc_func = nfsd_proc_readlink,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_readlinkargs,
+		.pc_decode = nfssvc_decode_readlinkargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_readlinkres,
 		.pc_argsize = sizeof(struct nfsd_readlinkargs),
 		.pc_ressize = sizeof(struct nfsd_readlinkres),
@@ -632,7 +632,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_READ] = {
 		.pc_func = nfsd_proc_read,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_readargs,
+		.pc_decode = nfssvc_decode_readargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_readres,
 		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_readargs),
@@ -641,7 +641,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_xdrressize = ST+AT+1+NFSSVC_MAXBLKSIZE_V2/4,
 	},
 	[NFSPROC_WRITECACHE] = {
-		.pc_decode = (kxdrproc_t) nfssvc_decode_void,
+		.pc_decode = nfssvc_decode_void,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_void),
 		.pc_ressize = sizeof(struct nfsd_void),
@@ -650,7 +650,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_WRITE] = {
 		.pc_func = nfsd_proc_write,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_writeargs,
+		.pc_decode = nfssvc_decode_writeargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
 		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_writeargs),
@@ -660,7 +660,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_CREATE] = {
 		.pc_func = nfsd_proc_create,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_createargs,
+		.pc_decode = nfssvc_decode_createargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
 		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_createargs),
@@ -670,7 +670,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_REMOVE] = {
 		.pc_func = nfsd_proc_remove,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_diropargs,
+		.pc_decode = nfssvc_decode_diropargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_diropargs),
 		.pc_ressize = sizeof(struct nfsd_void),
@@ -679,7 +679,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_RENAME] = {
 		.pc_func = nfsd_proc_rename,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_renameargs,
+		.pc_decode = nfssvc_decode_renameargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_renameargs),
 		.pc_ressize = sizeof(struct nfsd_void),
@@ -688,7 +688,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_LINK] = {
 		.pc_func = nfsd_proc_link,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_linkargs,
+		.pc_decode = nfssvc_decode_linkargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_linkargs),
 		.pc_ressize = sizeof(struct nfsd_void),
@@ -697,7 +697,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_SYMLINK] = {
 		.pc_func = nfsd_proc_symlink,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_symlinkargs,
+		.pc_decode = nfssvc_decode_symlinkargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_symlinkargs),
 		.pc_ressize = sizeof(struct nfsd_void),
@@ -706,7 +706,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_MKDIR] = {
 		.pc_func = nfsd_proc_mkdir,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_createargs,
+		.pc_decode = nfssvc_decode_createargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
 		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_createargs),
@@ -716,7 +716,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_RMDIR] = {
 		.pc_func = nfsd_proc_rmdir,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_diropargs,
+		.pc_decode = nfssvc_decode_diropargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_diropargs),
 		.pc_ressize = sizeof(struct nfsd_void),
@@ -725,7 +725,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_READDIR] = {
 		.pc_func = nfsd_proc_readdir,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_readdirargs,
+		.pc_decode = nfssvc_decode_readdirargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_readdirres,
 		.pc_argsize = sizeof(struct nfsd_readdirargs),
 		.pc_ressize = sizeof(struct nfsd_readdirres),
@@ -733,7 +733,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_STATFS] = {
 		.pc_func = nfsd_proc_statfs,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_fhandle,
+		.pc_decode = nfssvc_decode_fhandle,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_statfsres,
 		.pc_argsize = sizeof(struct nfsd_fhandle),
 		.pc_ressize = sizeof(struct nfsd_statfsres),
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index d64895fd8d25..3e00499d7ad7 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -801,9 +801,8 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 	 */
 	rqstp->rq_cachetype = proc->pc_cachetype;
 	/* Decode arguments */
-	xdr = proc->pc_decode;
-	if (xdr && !xdr(rqstp, (__be32*)rqstp->rq_arg.head[0].iov_base,
-			rqstp->rq_argp)) {
+	if (proc->pc_decode &&
+	    !proc->pc_decode(rqstp, (__be32*)rqstp->rq_arg.head[0].iov_base)) {
 		dprintk("nfsd: failed to decode arguments!\n");
 		*statp = rpc_garbage_args;
 		return 1;
diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c
index de7b07ee489e..0957ceebe1aa 100644
--- a/fs/nfsd/nfsxdr.c
+++ b/fs/nfsd/nfsxdr.c
@@ -206,14 +206,16 @@ __be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *f
  * XDR decode functions
  */
 int
-nfssvc_decode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+nfssvc_decode_void(struct svc_rqst *rqstp, __be32 *p)
 {
 	return xdr_argsize_check(rqstp, p);
 }
 
 int
-nfssvc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *args)
+nfssvc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_fhandle *args = rqstp->rq_argp;
+
 	p = decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
@@ -221,9 +223,10 @@ nfssvc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *ar
 }
 
 int
-nfssvc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_sattrargs *args)
+nfssvc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_sattrargs *args = rqstp->rq_argp;
+
 	p = decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
@@ -233,9 +236,10 @@ nfssvc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_diropargs *args)
+nfssvc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_diropargs *args = rqstp->rq_argp;
+
 	if (!(p = decode_fh(p, &args->fh))
 	 || !(p = decode_filename(p, &args->name, &args->len)))
 		return 0;
@@ -244,9 +248,9 @@ nfssvc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_readargs *args)
+nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_readargs *args = rqstp->rq_argp;
 	unsigned int len;
 	int v;
 	p = decode_fh(p, &args->fh);
@@ -279,9 +283,9 @@ nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_writeargs *args)
+nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_writeargs *args = rqstp->rq_argp;
 	unsigned int len, hdr, dlen;
 	struct kvec *head = rqstp->rq_arg.head;
 	int v;
@@ -335,9 +339,10 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_decode_createargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_createargs *args)
+nfssvc_decode_createargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_createargs *args = rqstp->rq_argp;
+
 	if (   !(p = decode_fh(p, &args->fh))
 	    || !(p = decode_filename(p, &args->name, &args->len)))
 		return 0;
@@ -347,9 +352,10 @@ nfssvc_decode_createargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_renameargs *args)
+nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_renameargs *args = rqstp->rq_argp;
+
 	if (!(p = decode_fh(p, &args->ffh))
 	 || !(p = decode_filename(p, &args->fname, &args->flen))
 	 || !(p = decode_fh(p, &args->tfh))
@@ -360,8 +366,10 @@ nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd_readlinkargs *args)
+nfssvc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_readlinkargs *args = rqstp->rq_argp;
+
 	p = decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
@@ -373,9 +381,10 @@ nfssvc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd_readli
 }
 
 int
-nfssvc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_linkargs *args)
+nfssvc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_linkargs *args = rqstp->rq_argp;
+
 	if (!(p = decode_fh(p, &args->ffh))
 	 || !(p = decode_fh(p, &args->tfh))
 	 || !(p = decode_filename(p, &args->tname, &args->tlen)))
@@ -385,9 +394,10 @@ nfssvc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_symlinkargs *args)
+nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_symlinkargs *args = rqstp->rq_argp;
+
 	if (   !(p = decode_fh(p, &args->ffh))
 	    || !(p = decode_filename(p, &args->fname, &args->flen))
 	    || !(p = decode_pathname(p, &args->tname, &args->tlen)))
@@ -398,9 +408,10 @@ nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_readdirargs *args)
+nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_readdirargs *args = rqstp->rq_argp;
+
 	p = decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h
index 2c21fa843fbf..8eeb752cf6f8 100644
--- a/fs/nfsd/xdr.h
+++ b/fs/nfsd/xdr.h
@@ -131,28 +131,18 @@ union nfsd_xdrstore {
 #define NFS2_SVC_XDRSIZE	sizeof(union nfsd_xdrstore)
 
 
-int nfssvc_decode_void(struct svc_rqst *, __be32 *, void *);
-int nfssvc_decode_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *);
-int nfssvc_decode_sattrargs(struct svc_rqst *, __be32 *,
-				struct nfsd_sattrargs *);
-int nfssvc_decode_diropargs(struct svc_rqst *, __be32 *,
-				struct nfsd_diropargs *);
-int nfssvc_decode_readargs(struct svc_rqst *, __be32 *,
-				struct nfsd_readargs *);
-int nfssvc_decode_writeargs(struct svc_rqst *, __be32 *,
-				struct nfsd_writeargs *);
-int nfssvc_decode_createargs(struct svc_rqst *, __be32 *,
-				struct nfsd_createargs *);
-int nfssvc_decode_renameargs(struct svc_rqst *, __be32 *,
-				struct nfsd_renameargs *);
-int nfssvc_decode_readlinkargs(struct svc_rqst *, __be32 *,
-				struct nfsd_readlinkargs *);
-int nfssvc_decode_linkargs(struct svc_rqst *, __be32 *,
-				struct nfsd_linkargs *);
-int nfssvc_decode_symlinkargs(struct svc_rqst *, __be32 *,
-				struct nfsd_symlinkargs *);
-int nfssvc_decode_readdirargs(struct svc_rqst *, __be32 *,
-				struct nfsd_readdirargs *);
+int nfssvc_decode_void(struct svc_rqst *, __be32 *);
+int nfssvc_decode_fhandle(struct svc_rqst *, __be32 *);
+int nfssvc_decode_sattrargs(struct svc_rqst *, __be32 *);
+int nfssvc_decode_diropargs(struct svc_rqst *, __be32 *);
+int nfssvc_decode_readargs(struct svc_rqst *, __be32 *);
+int nfssvc_decode_writeargs(struct svc_rqst *, __be32 *);
+int nfssvc_decode_createargs(struct svc_rqst *, __be32 *);
+int nfssvc_decode_renameargs(struct svc_rqst *, __be32 *);
+int nfssvc_decode_readlinkargs(struct svc_rqst *, __be32 *);
+int nfssvc_decode_linkargs(struct svc_rqst *, __be32 *);
+int nfssvc_decode_symlinkargs(struct svc_rqst *, __be32 *);
+int nfssvc_decode_readdirargs(struct svc_rqst *, __be32 *);
 int nfssvc_encode_void(struct svc_rqst *, __be32 *, void *);
 int nfssvc_encode_attrstat(struct svc_rqst *, __be32 *, struct nfsd_attrstat *);
 int nfssvc_encode_diropres(struct svc_rqst *, __be32 *, struct nfsd_diropres *);
diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h
index 23fe456a223b..f79be4c42e4a 100644
--- a/fs/nfsd/xdr3.h
+++ b/fs/nfsd/xdr3.h
@@ -269,37 +269,22 @@ union nfsd3_xdrstore {
 
 #define NFS3_SVC_XDRSIZE		sizeof(union nfsd3_xdrstore)
 
-int nfs3svc_decode_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *);
-int nfs3svc_decode_sattrargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_sattrargs *);
-int nfs3svc_decode_diropargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_diropargs *);
-int nfs3svc_decode_accessargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_accessargs *);
-int nfs3svc_decode_readargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_readargs *);
-int nfs3svc_decode_writeargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_writeargs *);
-int nfs3svc_decode_createargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_createargs *);
-int nfs3svc_decode_mkdirargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_createargs *);
-int nfs3svc_decode_mknodargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_mknodargs *);
-int nfs3svc_decode_renameargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_renameargs *);
-int nfs3svc_decode_readlinkargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_readlinkargs *);
-int nfs3svc_decode_linkargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_linkargs *);
-int nfs3svc_decode_symlinkargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_symlinkargs *);
-int nfs3svc_decode_readdirargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_readdirargs *);
-int nfs3svc_decode_readdirplusargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_readdirargs *);
-int nfs3svc_decode_commitargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_commitargs *);
+int nfs3svc_decode_fhandle(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_sattrargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_diropargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_accessargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_readargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_writeargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_createargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_mkdirargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_mknodargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_renameargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_readlinkargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_linkargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_symlinkargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_readdirargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_readdirplusargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_commitargs(struct svc_rqst *, __be32 *);
 int nfs3svc_encode_voidres(struct svc_rqst *, __be32 *, void *);
 int nfs3svc_encode_attrstat(struct svc_rqst *, __be32 *,
 				struct nfsd3_attrstat *);
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index a158579d55a2..2a53c1233884 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -683,8 +683,7 @@ set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp)
 
 bool nfsd4_mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp);
 int nfs4svc_encode_voidres(struct svc_rqst *, __be32 *, void *);
-int nfs4svc_decode_compoundargs(struct svc_rqst *, __be32 *,
-		struct nfsd4_compoundargs *);
+int nfs4svc_decode_compoundargs(struct svc_rqst *, __be32 *);
 int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *,
 		struct nfsd4_compoundres *);
 __be32 nfsd4_check_resp_size(struct nfsd4_compoundres *, u32);
diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h
index d39ed1cc5fbf..0416600844ce 100644
--- a/include/linux/lockd/xdr.h
+++ b/include/linux/lockd/xdr.h
@@ -95,19 +95,19 @@ struct nlm_reboot {
  */
 #define NLMSVC_XDRSIZE		sizeof(struct nlm_args)
 
-int	nlmsvc_decode_testargs(struct svc_rqst *, __be32 *, struct nlm_args *);
+int	nlmsvc_decode_testargs(struct svc_rqst *, __be32 *);
 int	nlmsvc_encode_testres(struct svc_rqst *, __be32 *, struct nlm_res *);
-int	nlmsvc_decode_lockargs(struct svc_rqst *, __be32 *, struct nlm_args *);
-int	nlmsvc_decode_cancargs(struct svc_rqst *, __be32 *, struct nlm_args *);
-int	nlmsvc_decode_unlockargs(struct svc_rqst *, __be32 *, struct nlm_args *);
+int	nlmsvc_decode_lockargs(struct svc_rqst *, __be32 *);
+int	nlmsvc_decode_cancargs(struct svc_rqst *, __be32 *);
+int	nlmsvc_decode_unlockargs(struct svc_rqst *, __be32 *);
 int	nlmsvc_encode_res(struct svc_rqst *, __be32 *, struct nlm_res *);
-int	nlmsvc_decode_res(struct svc_rqst *, __be32 *, struct nlm_res *);
+int	nlmsvc_decode_res(struct svc_rqst *, __be32 *);
 int	nlmsvc_encode_void(struct svc_rqst *, __be32 *, void *);
-int	nlmsvc_decode_void(struct svc_rqst *, __be32 *, void *);
-int	nlmsvc_decode_shareargs(struct svc_rqst *, __be32 *, struct nlm_args *);
+int	nlmsvc_decode_void(struct svc_rqst *, __be32 *);
+int	nlmsvc_decode_shareargs(struct svc_rqst *, __be32 *);
 int	nlmsvc_encode_shareres(struct svc_rqst *, __be32 *, struct nlm_res *);
-int	nlmsvc_decode_notify(struct svc_rqst *, __be32 *, struct nlm_args *);
-int	nlmsvc_decode_reboot(struct svc_rqst *, __be32 *, struct nlm_reboot *);
+int	nlmsvc_decode_notify(struct svc_rqst *, __be32 *);
+int	nlmsvc_decode_reboot(struct svc_rqst *, __be32 *);
 /*
 int	nlmclt_encode_testargs(struct rpc_rqst *, u32 *, struct nlm_args *);
 int	nlmclt_encode_lockargs(struct rpc_rqst *, u32 *, struct nlm_args *);
diff --git a/include/linux/lockd/xdr4.h b/include/linux/lockd/xdr4.h
index e58c88b52ce1..951bbe31fdb8 100644
--- a/include/linux/lockd/xdr4.h
+++ b/include/linux/lockd/xdr4.h
@@ -23,19 +23,19 @@
 
 
 
-int	nlm4svc_decode_testargs(struct svc_rqst *, __be32 *, struct nlm_args *);
+int	nlm4svc_decode_testargs(struct svc_rqst *, __be32 *);
 int	nlm4svc_encode_testres(struct svc_rqst *, __be32 *, struct nlm_res *);
-int	nlm4svc_decode_lockargs(struct svc_rqst *, __be32 *, struct nlm_args *);
-int	nlm4svc_decode_cancargs(struct svc_rqst *, __be32 *, struct nlm_args *);
-int	nlm4svc_decode_unlockargs(struct svc_rqst *, __be32 *, struct nlm_args *);
+int	nlm4svc_decode_lockargs(struct svc_rqst *, __be32 *);
+int	nlm4svc_decode_cancargs(struct svc_rqst *, __be32 *);
+int	nlm4svc_decode_unlockargs(struct svc_rqst *, __be32 *);
 int	nlm4svc_encode_res(struct svc_rqst *, __be32 *, struct nlm_res *);
-int	nlm4svc_decode_res(struct svc_rqst *, __be32 *, struct nlm_res *);
+int	nlm4svc_decode_res(struct svc_rqst *, __be32 *);
 int	nlm4svc_encode_void(struct svc_rqst *, __be32 *, void *);
-int	nlm4svc_decode_void(struct svc_rqst *, __be32 *, void *);
-int	nlm4svc_decode_shareargs(struct svc_rqst *, __be32 *, struct nlm_args *);
+int	nlm4svc_decode_void(struct svc_rqst *, __be32 *);
+int	nlm4svc_decode_shareargs(struct svc_rqst *, __be32 *);
 int	nlm4svc_encode_shareres(struct svc_rqst *, __be32 *, struct nlm_res *);
-int	nlm4svc_decode_notify(struct svc_rqst *, __be32 *, struct nlm_args *);
-int	nlm4svc_decode_reboot(struct svc_rqst *, __be32 *, struct nlm_reboot *);
+int	nlm4svc_decode_notify(struct svc_rqst *, __be32 *);
+int	nlm4svc_decode_reboot(struct svc_rqst *, __be32 *);
 /*
 int	nlmclt_encode_testargs(struct rpc_rqst *, u32 *, struct nlm_args *);
 int	nlmclt_encode_lockargs(struct rpc_rqst *, u32 *, struct nlm_args *);
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 1381e1343640..047f04411dd4 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -421,7 +421,8 @@ struct svc_version {
 struct svc_procedure {
 	/* process the request: */
 	__be32			(*pc_func)(struct svc_rqst *);
-	kxdrproc_t		pc_decode;	/* XDR decode args */
+	/* XDR decode args: */
+	int			(*pc_decode)(struct svc_rqst *, __be32 *data);
 	kxdrproc_t		pc_encode;	/* XDR encode result */
 	/* XDR free result: */
 	void			(*pc_release)(struct svc_rqst *);
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 4611cb7adc04..18024c1b9b7b 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1276,9 +1276,12 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 
 	/* Call the function that processes the request. */
 	if (!versp->vs_dispatch) {
-		/* Decode arguments */
-		xdr = procp->pc_decode;
-		if (xdr && !xdr(rqstp, argv->iov_base, rqstp->rq_argp))
+		/*
+		 * Decode arguments
+		 * XXX: why do we ignore the return value?
+		 */
+		if (procp->pc_decode &&
+		    !procp->pc_decode(rqstp, argv->iov_base))
 			goto err_garbage;
 
 		*statp = procp->pc_func(rqstp);
-- 
cgit v1.2.3


From 63f8de37951a64cc24479eafd33085537e088075 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 8 May 2017 19:42:02 +0200
Subject: sunrpc: properly type pc_encode callbacks

Drop the resp argument as it can trivially be derived from the rqstp
argument.  With that all functions now have the same prototype, and we
can remove the unsafe casting to kxdrproc_t.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 fs/lockd/svc4proc.c        |  2 +-
 fs/lockd/svcproc.c         |  2 +-
 fs/lockd/xdr.c             | 14 ++++++---
 fs/lockd/xdr4.c            | 14 ++++++---
 fs/nfs/callback_xdr.c      |  6 ++--
 fs/nfsd/nfs2acl.c          | 18 ++++++-----
 fs/nfsd/nfs3acl.c          | 11 +++----
 fs/nfsd/nfs3proc.c         | 44 +++++++++++++--------------
 fs/nfsd/nfs3xdr.c          | 74 +++++++++++++++++++++++++++-------------------
 fs/nfsd/nfs4proc.c         |  4 +--
 fs/nfsd/nfs4xdr.c          |  5 ++--
 fs/nfsd/nfsproc.c          | 36 +++++++++++-----------
 fs/nfsd/nfssvc.c           |  5 +---
 fs/nfsd/nfsxdr.c           | 31 +++++++++++--------
 fs/nfsd/xdr.h              | 14 ++++-----
 fs/nfsd/xdr3.h             | 45 ++++++++++------------------
 fs/nfsd/xdr4.h             |  5 ++--
 include/linux/lockd/xdr.h  |  8 ++---
 include/linux/lockd/xdr4.h |  8 ++---
 include/linux/sunrpc/svc.h |  3 +-
 net/sunrpc/svc.c           |  6 ++--
 21 files changed, 185 insertions(+), 170 deletions(-)

(limited to 'include')

diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index 804744f7528c..fed016155791 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -497,7 +497,7 @@ struct nlm_void			{ int dummy; };
 #define PROC(name, xargt, xrest, argt, rest, respsize)	\
  { .pc_func	= nlm4svc_proc_##name,	\
    .pc_decode	= nlm4svc_decode_##xargt,	\
-   .pc_encode	= (kxdrproc_t) nlm4svc_encode_##xrest,	\
+   .pc_encode	= nlm4svc_encode_##xrest,	\
    .pc_release	= NULL,					\
    .pc_argsize	= sizeof(struct nlm_##argt),		\
    .pc_ressize	= sizeof(struct nlm_##rest),		\
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index 204a698f7d41..14648b051eba 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -539,7 +539,7 @@ struct nlm_void			{ int dummy; };
 #define PROC(name, xargt, xrest, argt, rest, respsize)	\
  { .pc_func	= nlmsvc_proc_##name,			\
    .pc_decode	= nlmsvc_decode_##xargt,		\
-   .pc_encode	= (kxdrproc_t) nlmsvc_encode_##xrest,	\
+   .pc_encode	= nlmsvc_encode_##xrest,		\
    .pc_release	= NULL,					\
    .pc_argsize	= sizeof(struct nlm_##argt),		\
    .pc_ressize	= sizeof(struct nlm_##rest),		\
diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c
index b57af63fba56..442bbd0b0b29 100644
--- a/fs/lockd/xdr.c
+++ b/fs/lockd/xdr.c
@@ -200,8 +200,10 @@ nlmsvc_decode_testargs(struct svc_rqst *rqstp, __be32 *p)
 }
 
 int
-nlmsvc_encode_testres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
+nlmsvc_encode_testres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_res *resp = rqstp->rq_resp;
+
 	if (!(p = nlm_encode_testres(p, resp)))
 		return 0;
 	return xdr_ressize_check(rqstp, p);
@@ -280,8 +282,10 @@ nlmsvc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p)
 }
 
 int
-nlmsvc_encode_shareres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
+nlmsvc_encode_shareres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_res *resp = rqstp->rq_resp;
+
 	if (!(p = nlm_encode_cookie(p, &resp->cookie)))
 		return 0;
 	*p++ = resp->status;
@@ -290,8 +294,10 @@ nlmsvc_encode_shareres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
 }
 
 int
-nlmsvc_encode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
+nlmsvc_encode_res(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_res *resp = rqstp->rq_resp;
+
 	if (!(p = nlm_encode_cookie(p, &resp->cookie)))
 		return 0;
 	*p++ = resp->status;
@@ -342,7 +348,7 @@ nlmsvc_decode_void(struct svc_rqst *rqstp, __be32 *p)
 }
 
 int
-nlmsvc_encode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+nlmsvc_encode_void(struct svc_rqst *rqstp, __be32 *p)
 {
 	return xdr_ressize_check(rqstp, p);
 }
diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c
index 46e18598a15c..2a0cd5679c49 100644
--- a/fs/lockd/xdr4.c
+++ b/fs/lockd/xdr4.c
@@ -197,8 +197,10 @@ nlm4svc_decode_testargs(struct svc_rqst *rqstp, __be32 *p)
 }
 
 int
-nlm4svc_encode_testres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
+nlm4svc_encode_testres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_res *resp = rqstp->rq_resp;
+
 	if (!(p = nlm4_encode_testres(p, resp)))
 		return 0;
 	return xdr_ressize_check(rqstp, p);
@@ -277,8 +279,10 @@ nlm4svc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p)
 }
 
 int
-nlm4svc_encode_shareres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
+nlm4svc_encode_shareres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_res *resp = rqstp->rq_resp;
+
 	if (!(p = nlm4_encode_cookie(p, &resp->cookie)))
 		return 0;
 	*p++ = resp->status;
@@ -287,8 +291,10 @@ nlm4svc_encode_shareres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
 }
 
 int
-nlm4svc_encode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
+nlm4svc_encode_res(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_res *resp = rqstp->rq_resp;
+
 	if (!(p = nlm4_encode_cookie(p, &resp->cookie)))
 		return 0;
 	*p++ = resp->status;
@@ -339,7 +345,7 @@ nlm4svc_decode_void(struct svc_rqst *rqstp, __be32 *p)
 }
 
 int
-nlm4svc_encode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+nlm4svc_encode_void(struct svc_rqst *rqstp, __be32 *p)
 {
 	return xdr_ressize_check(rqstp, p);
 }
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index 23ecbf7a40c1..acf75dc63e14 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -63,7 +63,7 @@ static int nfs4_decode_void(struct svc_rqst *rqstp, __be32 *p)
 	return xdr_argsize_check(rqstp, p);
 }
 
-static int nfs4_encode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+static int nfs4_encode_void(struct svc_rqst *rqstp, __be32 *p)
 {
 	return xdr_ressize_check(rqstp, p);
 }
@@ -999,12 +999,12 @@ static struct svc_procedure nfs4_callback_procedures1[] = {
 	[CB_NULL] = {
 		.pc_func = nfs4_callback_null,
 		.pc_decode = nfs4_decode_void,
-		.pc_encode = (kxdrproc_t)nfs4_encode_void,
+		.pc_encode = nfs4_encode_void,
 		.pc_xdrressize = 1,
 	},
 	[CB_COMPOUND] = {
 		.pc_func = nfs4_callback_compound,
-		.pc_encode = (kxdrproc_t)nfs4_encode_void,
+		.pc_encode = nfs4_encode_void,
 		.pc_argsize = 256,
 		.pc_ressize = 256,
 		.pc_xdrressize = NFS4_CALLBACK_BUFSIZE,
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index bcfdaa83ee6c..fc6b179c8fff 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -251,15 +251,15 @@ static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p)
  * There must be an encoding function for void results so svc_process
  * will work properly.
  */
-static int nfsaclsvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+static int nfsaclsvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p)
 {
 	return xdr_ressize_check(rqstp, p);
 }
 
 /* GETACL */
-static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_getaclres *resp)
+static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_getaclres *resp = rqstp->rq_resp;
 	struct dentry *dentry = resp->fh.fh_dentry;
 	struct inode *inode;
 	struct kvec *head = rqstp->rq_res.head;
@@ -302,17 +302,19 @@ static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p,
 	return (n > 0);
 }
 
-static int nfsaclsvc_encode_attrstatres(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd_attrstat *resp)
+static int nfsaclsvc_encode_attrstatres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_attrstat *resp = rqstp->rq_resp;
+
 	p = nfs2svc_encode_fattr(rqstp, p, &resp->fh, &resp->stat);
 	return xdr_ressize_check(rqstp, p);
 }
 
 /* ACCESS */
-static int nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_accessres *resp)
+static int nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_accessres *resp = rqstp->rq_resp;
+
 	p = nfs2svc_encode_fattr(rqstp, p, &resp->fh, &resp->stat);
 	*p++ = htonl(resp->access);
 	return xdr_ressize_check(rqstp, p);
@@ -355,7 +357,7 @@ struct nfsd3_voidargs { int dummy; };
 {									\
 	.pc_func	= nfsacld_proc_##name,				\
 	.pc_decode	= nfsaclsvc_decode_##argt##args,		\
-	.pc_encode	= (kxdrproc_t) nfsaclsvc_encode_##rest##res,	\
+	.pc_encode	= nfsaclsvc_encode_##rest##res,			\
 	.pc_release	= nfsaclsvc_release_##relt,	\
 	.pc_argsize	= sizeof(struct nfsd3_##argt##args),		\
 	.pc_ressize	= sizeof(struct nfsd3_##rest##res),		\
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index 4e68d6b5f409..9437b758cbfd 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -168,9 +168,9 @@ static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p)
  */
 
 /* GETACL */
-static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_getaclres *resp)
+static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_getaclres *resp = rqstp->rq_resp;
 	struct dentry *dentry = resp->fh.fh_dentry;
 
 	p = nfs3svc_encode_post_op_attr(rqstp, p, &resp->fh);
@@ -213,9 +213,10 @@ static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p,
 }
 
 /* SETACL */
-static int nfs3svc_encode_setaclres(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_attrstat *resp)
+static int nfs3svc_encode_setaclres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_attrstat *resp = rqstp->rq_resp;
+
 	p = nfs3svc_encode_post_op_attr(rqstp, p, &resp->fh);
 
 	return xdr_ressize_check(rqstp, p);
@@ -243,7 +244,7 @@ struct nfsd3_voidargs { int dummy; };
 {									\
 	.pc_func	= nfsd3_proc_##name,				\
 	.pc_decode	= nfs3svc_decode_##argt##args,			\
-	.pc_encode	= (kxdrproc_t) nfs3svc_encode_##rest##res,	\
+	.pc_encode	= nfs3svc_encode_##rest##res,			\
 	.pc_release	= nfs3svc_release_##relt,			\
 	.pc_argsize	= sizeof(struct nfsd3_##argt##args),		\
 	.pc_ressize	= sizeof(struct nfsd3_##rest##res),		\
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index ed83e8a9e7b4..17c90c41a3a6 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -677,7 +677,7 @@ struct nfsd3_voidargs { int dummy; };
 static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_NULL] = {
 		.pc_func = nfsd3_proc_null,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_voidres,
+		.pc_encode = nfs3svc_encode_voidres,
 		.pc_argsize = sizeof(struct nfsd3_voidargs),
 		.pc_ressize = sizeof(struct nfsd3_voidres),
 		.pc_cachetype = RC_NOCACHE,
@@ -686,7 +686,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_GETATTR] = {
 		.pc_func = nfsd3_proc_getattr,
 		.pc_decode = nfs3svc_decode_fhandleargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_attrstatres,
+		.pc_encode = nfs3svc_encode_attrstatres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
 		.pc_ressize = sizeof(struct nfsd3_attrstatres),
@@ -696,7 +696,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_SETATTR] = {
 		.pc_func = nfsd3_proc_setattr,
 		.pc_decode = nfs3svc_decode_sattrargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
+		.pc_encode = nfs3svc_encode_wccstatres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_sattrargs),
 		.pc_ressize = sizeof(struct nfsd3_wccstatres),
@@ -706,7 +706,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_LOOKUP] = {
 		.pc_func = nfsd3_proc_lookup,
 		.pc_decode = nfs3svc_decode_diropargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_diropres,
+		.pc_encode = nfs3svc_encode_diropres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_diropargs),
 		.pc_ressize = sizeof(struct nfsd3_diropres),
@@ -716,7 +716,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_ACCESS] = {
 		.pc_func = nfsd3_proc_access,
 		.pc_decode = nfs3svc_decode_accessargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_accessres,
+		.pc_encode = nfs3svc_encode_accessres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_accessargs),
 		.pc_ressize = sizeof(struct nfsd3_accessres),
@@ -726,7 +726,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_READLINK] = {
 		.pc_func = nfsd3_proc_readlink,
 		.pc_decode = nfs3svc_decode_readlinkargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_readlinkres,
+		.pc_encode = nfs3svc_encode_readlinkres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_readlinkargs),
 		.pc_ressize = sizeof(struct nfsd3_readlinkres),
@@ -736,7 +736,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_READ] = {
 		.pc_func = nfsd3_proc_read,
 		.pc_decode = nfs3svc_decode_readargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_readres,
+		.pc_encode = nfs3svc_encode_readres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_readargs),
 		.pc_ressize = sizeof(struct nfsd3_readres),
@@ -746,7 +746,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_WRITE] = {
 		.pc_func = nfsd3_proc_write,
 		.pc_decode = nfs3svc_decode_writeargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_writeres,
+		.pc_encode = nfs3svc_encode_writeres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_writeargs),
 		.pc_ressize = sizeof(struct nfsd3_writeres),
@@ -756,7 +756,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_CREATE] = {
 		.pc_func = nfsd3_proc_create,
 		.pc_decode = nfs3svc_decode_createargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
+		.pc_encode = nfs3svc_encode_createres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_createargs),
 		.pc_ressize = sizeof(struct nfsd3_createres),
@@ -766,7 +766,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_MKDIR] = {
 		.pc_func = nfsd3_proc_mkdir,
 		.pc_decode = nfs3svc_decode_mkdirargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
+		.pc_encode = nfs3svc_encode_createres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_mkdirargs),
 		.pc_ressize = sizeof(struct nfsd3_createres),
@@ -776,7 +776,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_SYMLINK] = {
 		.pc_func = nfsd3_proc_symlink,
 		.pc_decode = nfs3svc_decode_symlinkargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
+		.pc_encode = nfs3svc_encode_createres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_symlinkargs),
 		.pc_ressize = sizeof(struct nfsd3_createres),
@@ -786,7 +786,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_MKNOD] = {
 		.pc_func = nfsd3_proc_mknod,
 		.pc_decode = nfs3svc_decode_mknodargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
+		.pc_encode = nfs3svc_encode_createres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_mknodargs),
 		.pc_ressize = sizeof(struct nfsd3_createres),
@@ -796,7 +796,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_REMOVE] = {
 		.pc_func = nfsd3_proc_remove,
 		.pc_decode = nfs3svc_decode_diropargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
+		.pc_encode = nfs3svc_encode_wccstatres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_diropargs),
 		.pc_ressize = sizeof(struct nfsd3_wccstatres),
@@ -806,7 +806,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_RMDIR] = {
 		.pc_func = nfsd3_proc_rmdir,
 		.pc_decode = nfs3svc_decode_diropargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
+		.pc_encode = nfs3svc_encode_wccstatres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_diropargs),
 		.pc_ressize = sizeof(struct nfsd3_wccstatres),
@@ -816,7 +816,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_RENAME] = {
 		.pc_func = nfsd3_proc_rename,
 		.pc_decode = nfs3svc_decode_renameargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_renameres,
+		.pc_encode = nfs3svc_encode_renameres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_renameargs),
 		.pc_ressize = sizeof(struct nfsd3_renameres),
@@ -826,7 +826,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_LINK] = {
 		.pc_func = nfsd3_proc_link,
 		.pc_decode = nfs3svc_decode_linkargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_linkres,
+		.pc_encode = nfs3svc_encode_linkres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_linkargs),
 		.pc_ressize = sizeof(struct nfsd3_linkres),
@@ -836,7 +836,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_READDIR] = {
 		.pc_func = nfsd3_proc_readdir,
 		.pc_decode = nfs3svc_decode_readdirargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres,
+		.pc_encode = nfs3svc_encode_readdirres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_readdirargs),
 		.pc_ressize = sizeof(struct nfsd3_readdirres),
@@ -845,7 +845,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_READDIRPLUS] = {
 		.pc_func = nfsd3_proc_readdirplus,
 		.pc_decode = nfs3svc_decode_readdirplusargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres,
+		.pc_encode = nfs3svc_encode_readdirres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_readdirplusargs),
 		.pc_ressize = sizeof(struct nfsd3_readdirres),
@@ -854,7 +854,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_FSSTAT] = {
 		.pc_func = nfsd3_proc_fsstat,
 		.pc_decode = nfs3svc_decode_fhandleargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_fsstatres,
+		.pc_encode = nfs3svc_encode_fsstatres,
 		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
 		.pc_ressize = sizeof(struct nfsd3_fsstatres),
 		.pc_cachetype = RC_NOCACHE,
@@ -863,7 +863,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_FSINFO] = {
 		.pc_func = nfsd3_proc_fsinfo,
 		.pc_decode = nfs3svc_decode_fhandleargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_fsinfores,
+		.pc_encode = nfs3svc_encode_fsinfores,
 		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
 		.pc_ressize = sizeof(struct nfsd3_fsinfores),
 		.pc_cachetype = RC_NOCACHE,
@@ -872,7 +872,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_PATHCONF] = {
 		.pc_func = nfsd3_proc_pathconf,
 		.pc_decode = nfs3svc_decode_fhandleargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_pathconfres,
+		.pc_encode = nfs3svc_encode_pathconfres,
 		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
 		.pc_ressize = sizeof(struct nfsd3_pathconfres),
 		.pc_cachetype = RC_NOCACHE,
@@ -881,7 +881,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_COMMIT] = {
 		.pc_func = nfsd3_proc_commit,
 		.pc_decode = nfs3svc_decode_commitargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_commitres,
+		.pc_encode = nfs3svc_encode_commitres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_commitargs),
 		.pc_ressize = sizeof(struct nfsd3_commitres),
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index be8bf8af9917..349e355edc73 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -645,16 +645,17 @@ nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p)
  * will work properly.
  */
 int
-nfs3svc_encode_voidres(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+nfs3svc_encode_voidres(struct svc_rqst *rqstp, __be32 *p)
 {
 	return xdr_ressize_check(rqstp, p);
 }
 
 /* GETATTR */
 int
-nfs3svc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_attrstat *resp)
+nfs3svc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_attrstat *resp = rqstp->rq_resp;
+
 	if (resp->status == 0) {
 		lease_get_mtime(d_inode(resp->fh.fh_dentry),
 				&resp->stat.mtime);
@@ -665,18 +666,20 @@ nfs3svc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p,
 
 /* SETATTR, REMOVE, RMDIR */
 int
-nfs3svc_encode_wccstat(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_attrstat *resp)
+nfs3svc_encode_wccstat(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_attrstat *resp = rqstp->rq_resp;
+
 	p = encode_wcc_data(rqstp, p, &resp->fh);
 	return xdr_ressize_check(rqstp, p);
 }
 
 /* LOOKUP */
 int
-nfs3svc_encode_diropres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_diropres *resp)
+nfs3svc_encode_diropres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_diropres *resp = rqstp->rq_resp;
+
 	if (resp->status == 0) {
 		p = encode_fh(p, &resp->fh);
 		p = encode_post_op_attr(rqstp, p, &resp->fh);
@@ -687,9 +690,10 @@ nfs3svc_encode_diropres(struct svc_rqst *rqstp, __be32 *p,
 
 /* ACCESS */
 int
-nfs3svc_encode_accessres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_accessres *resp)
+nfs3svc_encode_accessres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_accessres *resp = rqstp->rq_resp;
+
 	p = encode_post_op_attr(rqstp, p, &resp->fh);
 	if (resp->status == 0)
 		*p++ = htonl(resp->access);
@@ -698,9 +702,10 @@ nfs3svc_encode_accessres(struct svc_rqst *rqstp, __be32 *p,
 
 /* READLINK */
 int
-nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_readlinkres *resp)
+nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_readlinkres *resp = rqstp->rq_resp;
+
 	p = encode_post_op_attr(rqstp, p, &resp->fh);
 	if (resp->status == 0) {
 		*p++ = htonl(resp->len);
@@ -719,9 +724,10 @@ nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p,
 
 /* READ */
 int
-nfs3svc_encode_readres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_readres *resp)
+nfs3svc_encode_readres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_readres *resp = rqstp->rq_resp;
+
 	p = encode_post_op_attr(rqstp, p, &resp->fh);
 	if (resp->status == 0) {
 		*p++ = htonl(resp->count);
@@ -743,9 +749,9 @@ nfs3svc_encode_readres(struct svc_rqst *rqstp, __be32 *p,
 
 /* WRITE */
 int
-nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_writeres *resp)
+nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_writeres *resp = rqstp->rq_resp;
 	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
 
 	p = encode_wcc_data(rqstp, p, &resp->fh);
@@ -760,9 +766,10 @@ nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p,
 
 /* CREATE, MKDIR, SYMLINK, MKNOD */
 int
-nfs3svc_encode_createres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_diropres *resp)
+nfs3svc_encode_createres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_diropres *resp = rqstp->rq_resp;
+
 	if (resp->status == 0) {
 		*p++ = xdr_one;
 		p = encode_fh(p, &resp->fh);
@@ -774,9 +781,10 @@ nfs3svc_encode_createres(struct svc_rqst *rqstp, __be32 *p,
 
 /* RENAME */
 int
-nfs3svc_encode_renameres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_renameres *resp)
+nfs3svc_encode_renameres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_renameres *resp = rqstp->rq_resp;
+
 	p = encode_wcc_data(rqstp, p, &resp->ffh);
 	p = encode_wcc_data(rqstp, p, &resp->tfh);
 	return xdr_ressize_check(rqstp, p);
@@ -784,9 +792,10 @@ nfs3svc_encode_renameres(struct svc_rqst *rqstp, __be32 *p,
 
 /* LINK */
 int
-nfs3svc_encode_linkres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_linkres *resp)
+nfs3svc_encode_linkres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_linkres *resp = rqstp->rq_resp;
+
 	p = encode_post_op_attr(rqstp, p, &resp->fh);
 	p = encode_wcc_data(rqstp, p, &resp->tfh);
 	return xdr_ressize_check(rqstp, p);
@@ -794,9 +803,10 @@ nfs3svc_encode_linkres(struct svc_rqst *rqstp, __be32 *p,
 
 /* READDIR */
 int
-nfs3svc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_readdirres *resp)
+nfs3svc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_readdirres *resp = rqstp->rq_resp;
+
 	p = encode_post_op_attr(rqstp, p, &resp->fh);
 
 	if (resp->status == 0) {
@@ -1044,9 +1054,9 @@ nfs3svc_encode_entry_plus(void *cd, const char *name,
 
 /* FSSTAT */
 int
-nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_fsstatres *resp)
+nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_fsstatres *resp = rqstp->rq_resp;
 	struct kstatfs	*s = &resp->stats;
 	u64		bs = s->f_bsize;
 
@@ -1066,9 +1076,10 @@ nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, __be32 *p,
 
 /* FSINFO */
 int
-nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_fsinfores *resp)
+nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_fsinfores *resp = rqstp->rq_resp;
+
 	*p++ = xdr_zero;	/* no post_op_attr */
 
 	if (resp->status == 0) {
@@ -1090,9 +1101,10 @@ nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, __be32 *p,
 
 /* PATHCONF */
 int
-nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_pathconfres *resp)
+nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_pathconfres *resp = rqstp->rq_resp;
+
 	*p++ = xdr_zero;	/* no post_op_attr */
 
 	if (resp->status == 0) {
@@ -1109,9 +1121,9 @@ nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, __be32 *p,
 
 /* COMMIT */
 int
-nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_commitres *resp)
+nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_commitres *resp = rqstp->rq_resp;
 	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
 
 	p = encode_wcc_data(rqstp, p, &resp->fh);
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 6ff434b77a9e..ad0622efae4e 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -2520,7 +2520,7 @@ struct nfsd4_voidargs { int dummy; };
 static struct svc_procedure		nfsd_procedures4[2] = {
 	[NFSPROC4_NULL] = {
 		.pc_func = nfsd4_proc_null,
-		.pc_encode = (kxdrproc_t) nfs4svc_encode_voidres,
+		.pc_encode = nfs4svc_encode_voidres,
 		.pc_argsize = sizeof(struct nfsd4_voidargs),
 		.pc_ressize = sizeof(struct nfsd4_voidres),
 		.pc_cachetype = RC_NOCACHE,
@@ -2529,7 +2529,7 @@ static struct svc_procedure		nfsd_procedures4[2] = {
 	[NFSPROC4_COMPOUND] = {
 		.pc_func = nfsd4_proc_compound,
 		.pc_decode = nfs4svc_decode_compoundargs,
-		.pc_encode = (kxdrproc_t) nfs4svc_encode_compoundres,
+		.pc_encode = nfs4svc_encode_compoundres,
 		.pc_argsize = sizeof(struct nfsd4_compoundargs),
 		.pc_ressize = sizeof(struct nfsd4_compoundres),
 		.pc_release = nfsd4_release_compoundargs,
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 3a7e117bd11e..54e212e3541e 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -4538,7 +4538,7 @@ nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op)
 }
 
 int
-nfs4svc_encode_voidres(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+nfs4svc_encode_voidres(struct svc_rqst *rqstp, __be32 *p)
 {
         return xdr_ressize_check(rqstp, p);
 }
@@ -4584,11 +4584,12 @@ nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, __be32 *p)
 }
 
 int
-nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compoundres *resp)
+nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p)
 {
 	/*
 	 * All that remains is to write the tag and operation count...
 	 */
+	struct nfsd4_compoundres *resp = rqstp->rq_resp;
 	struct xdr_buf *buf = resp->xdr.buf;
 
 	WARN_ON_ONCE(buf->len != buf->head[0].iov_len + buf->page_len +
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index d351d0ef6d34..0ef88d0e67d9 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -577,7 +577,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_NULL] = {
 		.pc_func = nfsd_proc_null,
 		.pc_decode = nfssvc_decode_void,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
+		.pc_encode = nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_void),
 		.pc_ressize = sizeof(struct nfsd_void),
 		.pc_cachetype = RC_NOCACHE,
@@ -586,7 +586,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_GETATTR] = {
 		.pc_func = nfsd_proc_getattr,
 		.pc_decode = nfssvc_decode_fhandle,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
+		.pc_encode = nfssvc_encode_attrstat,
 		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_fhandle),
 		.pc_ressize = sizeof(struct nfsd_attrstat),
@@ -596,7 +596,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_SETATTR] = {
 		.pc_func = nfsd_proc_setattr,
 		.pc_decode = nfssvc_decode_sattrargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
+		.pc_encode = nfssvc_encode_attrstat,
 		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_sattrargs),
 		.pc_ressize = sizeof(struct nfsd_attrstat),
@@ -605,7 +605,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_ROOT] = {
 		.pc_decode = nfssvc_decode_void,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
+		.pc_encode = nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_void),
 		.pc_ressize = sizeof(struct nfsd_void),
 		.pc_cachetype = RC_NOCACHE,
@@ -614,7 +614,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_LOOKUP] = {
 		.pc_func = nfsd_proc_lookup,
 		.pc_decode = nfssvc_decode_diropargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
+		.pc_encode = nfssvc_encode_diropres,
 		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_diropargs),
 		.pc_ressize = sizeof(struct nfsd_diropres),
@@ -624,7 +624,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_READLINK] = {
 		.pc_func = nfsd_proc_readlink,
 		.pc_decode = nfssvc_decode_readlinkargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_readlinkres,
+		.pc_encode = nfssvc_encode_readlinkres,
 		.pc_argsize = sizeof(struct nfsd_readlinkargs),
 		.pc_ressize = sizeof(struct nfsd_readlinkres),
 		.pc_cachetype = RC_NOCACHE,
@@ -633,7 +633,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_READ] = {
 		.pc_func = nfsd_proc_read,
 		.pc_decode = nfssvc_decode_readargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_readres,
+		.pc_encode = nfssvc_encode_readres,
 		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_readargs),
 		.pc_ressize = sizeof(struct nfsd_readres),
@@ -642,7 +642,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_WRITECACHE] = {
 		.pc_decode = nfssvc_decode_void,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
+		.pc_encode = nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_void),
 		.pc_ressize = sizeof(struct nfsd_void),
 		.pc_cachetype = RC_NOCACHE,
@@ -651,7 +651,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_WRITE] = {
 		.pc_func = nfsd_proc_write,
 		.pc_decode = nfssvc_decode_writeargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
+		.pc_encode = nfssvc_encode_attrstat,
 		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_writeargs),
 		.pc_ressize = sizeof(struct nfsd_attrstat),
@@ -661,7 +661,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_CREATE] = {
 		.pc_func = nfsd_proc_create,
 		.pc_decode = nfssvc_decode_createargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
+		.pc_encode = nfssvc_encode_diropres,
 		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_createargs),
 		.pc_ressize = sizeof(struct nfsd_diropres),
@@ -671,7 +671,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_REMOVE] = {
 		.pc_func = nfsd_proc_remove,
 		.pc_decode = nfssvc_decode_diropargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
+		.pc_encode = nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_diropargs),
 		.pc_ressize = sizeof(struct nfsd_void),
 		.pc_cachetype = RC_REPLSTAT,
@@ -680,7 +680,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_RENAME] = {
 		.pc_func = nfsd_proc_rename,
 		.pc_decode = nfssvc_decode_renameargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
+		.pc_encode = nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_renameargs),
 		.pc_ressize = sizeof(struct nfsd_void),
 		.pc_cachetype = RC_REPLSTAT,
@@ -689,7 +689,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_LINK] = {
 		.pc_func = nfsd_proc_link,
 		.pc_decode = nfssvc_decode_linkargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
+		.pc_encode = nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_linkargs),
 		.pc_ressize = sizeof(struct nfsd_void),
 		.pc_cachetype = RC_REPLSTAT,
@@ -698,7 +698,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_SYMLINK] = {
 		.pc_func = nfsd_proc_symlink,
 		.pc_decode = nfssvc_decode_symlinkargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
+		.pc_encode = nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_symlinkargs),
 		.pc_ressize = sizeof(struct nfsd_void),
 		.pc_cachetype = RC_REPLSTAT,
@@ -707,7 +707,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_MKDIR] = {
 		.pc_func = nfsd_proc_mkdir,
 		.pc_decode = nfssvc_decode_createargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
+		.pc_encode = nfssvc_encode_diropres,
 		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_createargs),
 		.pc_ressize = sizeof(struct nfsd_diropres),
@@ -717,7 +717,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_RMDIR] = {
 		.pc_func = nfsd_proc_rmdir,
 		.pc_decode = nfssvc_decode_diropargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
+		.pc_encode = nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_diropargs),
 		.pc_ressize = sizeof(struct nfsd_void),
 		.pc_cachetype = RC_REPLSTAT,
@@ -726,7 +726,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_READDIR] = {
 		.pc_func = nfsd_proc_readdir,
 		.pc_decode = nfssvc_decode_readdirargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_readdirres,
+		.pc_encode = nfssvc_encode_readdirres,
 		.pc_argsize = sizeof(struct nfsd_readdirargs),
 		.pc_ressize = sizeof(struct nfsd_readdirres),
 		.pc_cachetype = RC_NOCACHE,
@@ -734,7 +734,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_STATFS] = {
 		.pc_func = nfsd_proc_statfs,
 		.pc_decode = nfssvc_decode_fhandle,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_statfsres,
+		.pc_encode = nfssvc_encode_statfsres,
 		.pc_argsize = sizeof(struct nfsd_fhandle),
 		.pc_ressize = sizeof(struct nfsd_statfsres),
 		.pc_cachetype = RC_NOCACHE,
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 3e00499d7ad7..555233664124 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -782,7 +782,6 @@ int
 nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 {
 	struct svc_procedure	*proc;
-	kxdrproc_t		xdr;
 	__be32			nfserr;
 	__be32			*nfserrp;
 
@@ -841,9 +840,7 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 	 * For NFSv2, additional info is never returned in case of an error.
 	 */
 	if (!(nfserr && rqstp->rq_vers == 2)) {
-		xdr = proc->pc_encode;
-		if (xdr && !xdr(rqstp, nfserrp,
-				rqstp->rq_resp)) {
+		if (proc->pc_encode && !proc->pc_encode(rqstp, nfserrp)) {
 			/* Failed to encode result. Release cache entry */
 			dprintk("nfsd: failed to encode result!\n");
 			nfsd_cache_update(rqstp, RC_NOCACHE, NULL);
diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c
index 0957ceebe1aa..bb1998c5ae61 100644
--- a/fs/nfsd/nfsxdr.c
+++ b/fs/nfsd/nfsxdr.c
@@ -429,32 +429,35 @@ nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p)
  * XDR encode functions
  */
 int
-nfssvc_encode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+nfssvc_encode_void(struct svc_rqst *rqstp, __be32 *p)
 {
 	return xdr_ressize_check(rqstp, p);
 }
 
 int
-nfssvc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_attrstat *resp)
+nfssvc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_attrstat *resp = rqstp->rq_resp;
+
 	p = encode_fattr(rqstp, p, &resp->fh, &resp->stat);
 	return xdr_ressize_check(rqstp, p);
 }
 
 int
-nfssvc_encode_diropres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_diropres *resp)
+nfssvc_encode_diropres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_diropres *resp = rqstp->rq_resp;
+
 	p = encode_fh(p, &resp->fh);
 	p = encode_fattr(rqstp, p, &resp->fh, &resp->stat);
 	return xdr_ressize_check(rqstp, p);
 }
 
 int
-nfssvc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_readlinkres *resp)
+nfssvc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_readlinkres *resp = rqstp->rq_resp;
+
 	*p++ = htonl(resp->len);
 	xdr_ressize_check(rqstp, p);
 	rqstp->rq_res.page_len = resp->len;
@@ -468,9 +471,10 @@ nfssvc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_encode_readres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_readres *resp)
+nfssvc_encode_readres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_readres *resp = rqstp->rq_resp;
+
 	p = encode_fattr(rqstp, p, &resp->fh, &resp->stat);
 	*p++ = htonl(resp->count);
 	xdr_ressize_check(rqstp, p);
@@ -487,9 +491,10 @@ nfssvc_encode_readres(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_readdirres *resp)
+nfssvc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_readdirres *resp = rqstp->rq_resp;
+
 	xdr_ressize_check(rqstp, p);
 	p = resp->buffer;
 	*p++ = 0;			/* no more entries */
@@ -500,9 +505,9 @@ nfssvc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_encode_statfsres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_statfsres *resp)
+nfssvc_encode_statfsres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_statfsres *resp = rqstp->rq_resp;
 	struct kstatfs	*stat = &resp->stats;
 
 	*p++ = htonl(NFSSVC_MAXBLKSIZE_V2);	/* max transfer size */
diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h
index 8eeb752cf6f8..457ce45e5084 100644
--- a/fs/nfsd/xdr.h
+++ b/fs/nfsd/xdr.h
@@ -143,13 +143,13 @@ int nfssvc_decode_readlinkargs(struct svc_rqst *, __be32 *);
 int nfssvc_decode_linkargs(struct svc_rqst *, __be32 *);
 int nfssvc_decode_symlinkargs(struct svc_rqst *, __be32 *);
 int nfssvc_decode_readdirargs(struct svc_rqst *, __be32 *);
-int nfssvc_encode_void(struct svc_rqst *, __be32 *, void *);
-int nfssvc_encode_attrstat(struct svc_rqst *, __be32 *, struct nfsd_attrstat *);
-int nfssvc_encode_diropres(struct svc_rqst *, __be32 *, struct nfsd_diropres *);
-int nfssvc_encode_readlinkres(struct svc_rqst *, __be32 *, struct nfsd_readlinkres *);
-int nfssvc_encode_readres(struct svc_rqst *, __be32 *, struct nfsd_readres *);
-int nfssvc_encode_statfsres(struct svc_rqst *, __be32 *, struct nfsd_statfsres *);
-int nfssvc_encode_readdirres(struct svc_rqst *, __be32 *, struct nfsd_readdirres *);
+int nfssvc_encode_void(struct svc_rqst *, __be32 *);
+int nfssvc_encode_attrstat(struct svc_rqst *, __be32 *);
+int nfssvc_encode_diropres(struct svc_rqst *, __be32 *);
+int nfssvc_encode_readlinkres(struct svc_rqst *, __be32 *);
+int nfssvc_encode_readres(struct svc_rqst *, __be32 *);
+int nfssvc_encode_statfsres(struct svc_rqst *, __be32 *);
+int nfssvc_encode_readdirres(struct svc_rqst *, __be32 *);
 
 int nfssvc_encode_entry(void *, const char *name,
 			int namlen, loff_t offset, u64 ino, unsigned int);
diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h
index f79be4c42e4a..80d7da620e91 100644
--- a/fs/nfsd/xdr3.h
+++ b/fs/nfsd/xdr3.h
@@ -285,35 +285,22 @@ int nfs3svc_decode_symlinkargs(struct svc_rqst *, __be32 *);
 int nfs3svc_decode_readdirargs(struct svc_rqst *, __be32 *);
 int nfs3svc_decode_readdirplusargs(struct svc_rqst *, __be32 *);
 int nfs3svc_decode_commitargs(struct svc_rqst *, __be32 *);
-int nfs3svc_encode_voidres(struct svc_rqst *, __be32 *, void *);
-int nfs3svc_encode_attrstat(struct svc_rqst *, __be32 *,
-				struct nfsd3_attrstat *);
-int nfs3svc_encode_wccstat(struct svc_rqst *, __be32 *,
-				struct nfsd3_attrstat *);
-int nfs3svc_encode_diropres(struct svc_rqst *, __be32 *,
-				struct nfsd3_diropres *);
-int nfs3svc_encode_accessres(struct svc_rqst *, __be32 *,
-				struct nfsd3_accessres *);
-int nfs3svc_encode_readlinkres(struct svc_rqst *, __be32 *,
-				struct nfsd3_readlinkres *);
-int nfs3svc_encode_readres(struct svc_rqst *, __be32 *, struct nfsd3_readres *);
-int nfs3svc_encode_writeres(struct svc_rqst *, __be32 *, struct nfsd3_writeres *);
-int nfs3svc_encode_createres(struct svc_rqst *, __be32 *,
-				struct nfsd3_diropres *);
-int nfs3svc_encode_renameres(struct svc_rqst *, __be32 *,
-				struct nfsd3_renameres *);
-int nfs3svc_encode_linkres(struct svc_rqst *, __be32 *,
-				struct nfsd3_linkres *);
-int nfs3svc_encode_readdirres(struct svc_rqst *, __be32 *,
-				struct nfsd3_readdirres *);
-int nfs3svc_encode_fsstatres(struct svc_rqst *, __be32 *,
-				struct nfsd3_fsstatres *);
-int nfs3svc_encode_fsinfores(struct svc_rqst *, __be32 *,
-				struct nfsd3_fsinfores *);
-int nfs3svc_encode_pathconfres(struct svc_rqst *, __be32 *,
-				struct nfsd3_pathconfres *);
-int nfs3svc_encode_commitres(struct svc_rqst *, __be32 *,
-				struct nfsd3_commitres *);
+int nfs3svc_encode_voidres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_attrstat(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_wccstat(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_diropres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_accessres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_readlinkres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_readres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_writeres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_createres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_renameres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_linkres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_readdirres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_fsstatres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_fsinfores(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_pathconfres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_commitres(struct svc_rqst *, __be32 *);
 
 void nfs3svc_release_fhandle(struct svc_rqst *);
 void nfs3svc_release_fhandle2(struct svc_rqst *);
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 2a53c1233884..eb7f9239304f 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -682,10 +682,9 @@ set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp)
 
 
 bool nfsd4_mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp);
-int nfs4svc_encode_voidres(struct svc_rqst *, __be32 *, void *);
+int nfs4svc_encode_voidres(struct svc_rqst *, __be32 *);
 int nfs4svc_decode_compoundargs(struct svc_rqst *, __be32 *);
-int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *,
-		struct nfsd4_compoundres *);
+int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *);
 __be32 nfsd4_check_resp_size(struct nfsd4_compoundres *, u32);
 void nfsd4_encode_operation(struct nfsd4_compoundres *, struct nfsd4_op *);
 void nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op);
diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h
index 0416600844ce..7acbecc21a40 100644
--- a/include/linux/lockd/xdr.h
+++ b/include/linux/lockd/xdr.h
@@ -96,16 +96,16 @@ struct nlm_reboot {
 #define NLMSVC_XDRSIZE		sizeof(struct nlm_args)
 
 int	nlmsvc_decode_testargs(struct svc_rqst *, __be32 *);
-int	nlmsvc_encode_testres(struct svc_rqst *, __be32 *, struct nlm_res *);
+int	nlmsvc_encode_testres(struct svc_rqst *, __be32 *);
 int	nlmsvc_decode_lockargs(struct svc_rqst *, __be32 *);
 int	nlmsvc_decode_cancargs(struct svc_rqst *, __be32 *);
 int	nlmsvc_decode_unlockargs(struct svc_rqst *, __be32 *);
-int	nlmsvc_encode_res(struct svc_rqst *, __be32 *, struct nlm_res *);
+int	nlmsvc_encode_res(struct svc_rqst *, __be32 *);
 int	nlmsvc_decode_res(struct svc_rqst *, __be32 *);
-int	nlmsvc_encode_void(struct svc_rqst *, __be32 *, void *);
+int	nlmsvc_encode_void(struct svc_rqst *, __be32 *);
 int	nlmsvc_decode_void(struct svc_rqst *, __be32 *);
 int	nlmsvc_decode_shareargs(struct svc_rqst *, __be32 *);
-int	nlmsvc_encode_shareres(struct svc_rqst *, __be32 *, struct nlm_res *);
+int	nlmsvc_encode_shareres(struct svc_rqst *, __be32 *);
 int	nlmsvc_decode_notify(struct svc_rqst *, __be32 *);
 int	nlmsvc_decode_reboot(struct svc_rqst *, __be32 *);
 /*
diff --git a/include/linux/lockd/xdr4.h b/include/linux/lockd/xdr4.h
index 951bbe31fdb8..bf1645609225 100644
--- a/include/linux/lockd/xdr4.h
+++ b/include/linux/lockd/xdr4.h
@@ -24,16 +24,16 @@
 
 
 int	nlm4svc_decode_testargs(struct svc_rqst *, __be32 *);
-int	nlm4svc_encode_testres(struct svc_rqst *, __be32 *, struct nlm_res *);
+int	nlm4svc_encode_testres(struct svc_rqst *, __be32 *);
 int	nlm4svc_decode_lockargs(struct svc_rqst *, __be32 *);
 int	nlm4svc_decode_cancargs(struct svc_rqst *, __be32 *);
 int	nlm4svc_decode_unlockargs(struct svc_rqst *, __be32 *);
-int	nlm4svc_encode_res(struct svc_rqst *, __be32 *, struct nlm_res *);
+int	nlm4svc_encode_res(struct svc_rqst *, __be32 *);
 int	nlm4svc_decode_res(struct svc_rqst *, __be32 *);
-int	nlm4svc_encode_void(struct svc_rqst *, __be32 *, void *);
+int	nlm4svc_encode_void(struct svc_rqst *, __be32 *);
 int	nlm4svc_decode_void(struct svc_rqst *, __be32 *);
 int	nlm4svc_decode_shareargs(struct svc_rqst *, __be32 *);
-int	nlm4svc_encode_shareres(struct svc_rqst *, __be32 *, struct nlm_res *);
+int	nlm4svc_encode_shareres(struct svc_rqst *, __be32 *);
 int	nlm4svc_decode_notify(struct svc_rqst *, __be32 *);
 int	nlm4svc_decode_reboot(struct svc_rqst *, __be32 *);
 /*
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 047f04411dd4..6cfe41db7f31 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -423,7 +423,8 @@ struct svc_procedure {
 	__be32			(*pc_func)(struct svc_rqst *);
 	/* XDR decode args: */
 	int			(*pc_decode)(struct svc_rqst *, __be32 *data);
-	kxdrproc_t		pc_encode;	/* XDR encode result */
+	/* XDR encode result: */
+	int			(*pc_encode)(struct svc_rqst *, __be32 *data);
 	/* XDR free result: */
 	void			(*pc_release)(struct svc_rqst *);
 	unsigned int		pc_argsize;	/* argument struct size */
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 18024c1b9b7b..aa643a29fdc6 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1154,7 +1154,6 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 	struct svc_version	*versp = NULL;	/* compiler food */
 	struct svc_procedure	*procp = NULL;
 	struct svc_serv		*serv = rqstp->rq_server;
-	kxdrproc_t		xdr;
 	__be32			*statp;
 	u32			prog, vers, proc;
 	__be32			auth_stat, rpc_stat;
@@ -1298,9 +1297,8 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 				procp->pc_release(rqstp);
 			goto err_bad_auth;
 		}
-		if (*statp == rpc_success &&
-		    (xdr = procp->pc_encode) &&
-		    !xdr(rqstp, resv->iov_base+resv->iov_len, rqstp->rq_resp)) {
+		if (*statp == rpc_success && procp->pc_encode &&
+		    !procp->pc_encode(rqstp, resv->iov_base + resv->iov_len)) {
 			dprintk("svc: failed to encode reply\n");
 			/* serv->sv_stats->rpcsystemerr++; */
 			*statp = rpc_system_err;
-- 
cgit v1.2.3


From 35f297e5370bd511a171f7de0c5a31ee661f2e7e Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 8 May 2017 19:56:10 +0200
Subject: sunrpc: remove kxdrproc_t

Remove the now unused typedef.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/sunrpc/xdr.h | 7 -------
 1 file changed, 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index ed0fbf0d8d0f..261b48a2701d 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -34,13 +34,6 @@ struct xdr_netobj {
 	u8 *			data;
 };
 
-/*
- * This is the legacy generic XDR function. rqstp is either a rpc_rqst
- * (client side) or svc_rqst pointer (server side).
- * Encode functions always assume there's enough room in the buffer.
- */
-typedef int	(*kxdrproc_t)(void *rqstp, __be32 *data, void *obj);
-
 /*
  * Basic structure for transmission/reception of a client XDR message.
  * Features a header (for a linear buffer containing RPC headers
-- 
cgit v1.2.3


From 7fd38af9cae6aef1dfd28a7d1bd214eb5ddb7d53 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 8 May 2017 23:40:27 +0200
Subject: sunrpc: move pc_count out of struct svc_procinfo

pc_count is the only writeable memeber of struct svc_procinfo, which is
a good candidate to be const-ified as it contains function pointers.

This patch moves it into out out struct svc_procinfo, and into a
separate writable array that is pointed to by struct svc_version.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/lockd/svc.c             |  6 ++++++
 fs/nfs/callback_xdr.c      |  4 ++++
 fs/nfsd/nfs2acl.c          |  2 ++
 fs/nfsd/nfs3acl.c          |  2 ++
 fs/nfsd/nfs3proc.c         |  2 ++
 fs/nfsd/nfs4proc.c         |  2 ++
 fs/nfsd/nfsproc.c          |  2 ++
 include/linux/sunrpc/svc.h |  2 +-
 net/sunrpc/stats.c         | 11 ++++++-----
 net/sunrpc/svc.c           |  2 +-
 10 files changed, 28 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index 5d481e8a1b5d..cc6abe6280bc 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -739,23 +739,29 @@ module_exit(exit_nlm);
 /*
  * Define NLM program and procedures
  */
+static unsigned int nlmsvc_version1_count[17];
 static struct svc_version	nlmsvc_version1 = {
 		.vs_vers	= 1,
 		.vs_nproc	= 17,
 		.vs_proc	= nlmsvc_procedures,
+		.vs_count	= nlmsvc_version1_count,
 		.vs_xdrsize	= NLMSVC_XDRSIZE,
 };
+static unsigned int nlmsvc_version3_count[24];
 static struct svc_version	nlmsvc_version3 = {
 		.vs_vers	= 3,
 		.vs_nproc	= 24,
 		.vs_proc	= nlmsvc_procedures,
+		.vs_count	= nlmsvc_version3_count,
 		.vs_xdrsize	= NLMSVC_XDRSIZE,
 };
 #ifdef CONFIG_LOCKD_V4
+static unsigned int nlmsvc_version4_count[24];
 static struct svc_version	nlmsvc_version4 = {
 		.vs_vers	= 4,
 		.vs_nproc	= 24,
 		.vs_proc	= nlmsvc_procedures4,
+		.vs_count	= nlmsvc_version4_count,
 		.vs_xdrsize	= NLMSVC_XDRSIZE,
 };
 #endif
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index acf75dc63e14..ecd46b8c0985 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -1011,20 +1011,24 @@ static struct svc_procedure nfs4_callback_procedures1[] = {
 	}
 };
 
+static unsigned int nfs4_callback_count1[ARRAY_SIZE(nfs4_callback_procedures1)];
 struct svc_version nfs4_callback_version1 = {
 	.vs_vers = 1,
 	.vs_nproc = ARRAY_SIZE(nfs4_callback_procedures1),
 	.vs_proc = nfs4_callback_procedures1,
+	.vs_count = nfs4_callback_count1,
 	.vs_xdrsize = NFS4_CALLBACK_XDRSIZE,
 	.vs_dispatch = NULL,
 	.vs_hidden = true,
 	.vs_need_cong_ctrl = true,
 };
 
+static unsigned int nfs4_callback_count4[ARRAY_SIZE(nfs4_callback_procedures1)];
 struct svc_version nfs4_callback_version4 = {
 	.vs_vers = 4,
 	.vs_nproc = ARRAY_SIZE(nfs4_callback_procedures1),
 	.vs_proc = nfs4_callback_procedures1,
+	.vs_count = nfs4_callback_count4,
 	.vs_xdrsize = NFS4_CALLBACK_XDRSIZE,
 	.vs_dispatch = NULL,
 	.vs_hidden = true,
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index fc6b179c8fff..026edfe73fd5 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -378,10 +378,12 @@ static struct svc_procedure		nfsd_acl_procedures2[] = {
   PROC(access,	access,		access,		access,   RC_NOCACHE, ST+AT+1),
 };
 
+static unsigned int nfsd_acl_count2[ARRAY_SIZE(nfsd_acl_procedures2)];
 struct svc_version	nfsd_acl_version2 = {
 		.vs_vers	= 2,
 		.vs_nproc	= 5,
 		.vs_proc	= nfsd_acl_procedures2,
+		.vs_count	= nfsd_acl_count2,
 		.vs_dispatch	= nfsd_dispatch,
 		.vs_xdrsize	= NFS3_SVC_XDRSIZE,
 };
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index 9437b758cbfd..73c0970ccefb 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -263,10 +263,12 @@ static struct svc_procedure		nfsd_acl_procedures3[] = {
   PROC(setacl,	setacl,		setacl,		fhandle,  RC_NOCACHE, ST+pAT),
 };
 
+static unsigned int nfsd_acl_count3[ARRAY_SIZE(nfsd_acl_procedures3)];
 struct svc_version	nfsd_acl_version3 = {
 		.vs_vers	= 3,
 		.vs_nproc	= 3,
 		.vs_proc	= nfsd_acl_procedures3,
+		.vs_count	= nfsd_acl_count3,
 		.vs_dispatch	= nfsd_dispatch,
 		.vs_xdrsize	= NFS3_SVC_XDRSIZE,
 };
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 17c90c41a3a6..b5823802e278 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -890,10 +890,12 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 };
 
+static unsigned int nfsd_count3[ARRAY_SIZE(nfsd_procedures3)];
 struct svc_version	nfsd_version3 = {
 		.vs_vers	= 3,
 		.vs_nproc	= 22,
 		.vs_proc	= nfsd_procedures3,
+		.vs_count	= nfsd_count3,
 		.vs_dispatch	= nfsd_dispatch,
 		.vs_xdrsize	= NFS3_SVC_XDRSIZE,
 };
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index a947dcef5e4e..bad5fec0ebc7 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -2554,10 +2554,12 @@ static struct svc_procedure		nfsd_procedures4[2] = {
 	},
 };
 
+static unsigned int nfsd_count3[ARRAY_SIZE(nfsd_procedures4)];
 struct svc_version	nfsd_version4 = {
 	.vs_vers		= 4,
 	.vs_nproc		= 2,
 	.vs_proc		= nfsd_procedures4,
+	.vs_count		= nfsd_count3,
 	.vs_dispatch		= nfsd_dispatch,
 	.vs_xdrsize		= NFS4_SVC_XDRSIZE,
 	.vs_rpcb_optnl		= true,
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index 0ef88d0e67d9..44b157553733 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -743,10 +743,12 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 };
 
 
+static unsigned int nfsd_count2[ARRAY_SIZE(nfsd_procedures2)];
 struct svc_version	nfsd_version2 = {
 		.vs_vers	= 2,
 		.vs_nproc	= 18,
 		.vs_proc	= nfsd_procedures2,
+		.vs_count	= nfsd_count2,
 		.vs_dispatch	= nfsd_dispatch,
 		.vs_xdrsize	= NFS2_SVC_XDRSIZE,
 };
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 6cfe41db7f31..9f00384153f4 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -397,6 +397,7 @@ struct svc_version {
 	u32			vs_vers;	/* version number */
 	u32			vs_nproc;	/* number of procedures */
 	struct svc_procedure *	vs_proc;	/* per-procedure info */
+	unsigned int		*vs_count;	/* call counts */
 	u32			vs_xdrsize;	/* xdrsize needed for this version */
 
 	/* Don't register with rpcbind */
@@ -429,7 +430,6 @@ struct svc_procedure {
 	void			(*pc_release)(struct svc_rqst *);
 	unsigned int		pc_argsize;	/* argument struct size */
 	unsigned int		pc_ressize;	/* result struct size */
-	unsigned int		pc_count;	/* call count */
 	unsigned int		pc_cachetype;	/* cache info (NFS) */
 	unsigned int		pc_xdrressize;	/* maximum size of XDR reply */
 };
diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c
index 8b6c35ae1d57..1e671333c3d5 100644
--- a/net/sunrpc/stats.c
+++ b/net/sunrpc/stats.c
@@ -77,9 +77,9 @@ static const struct file_operations rpc_proc_fops = {
 /*
  * Get RPC server stats
  */
-void svc_seq_show(struct seq_file *seq, const struct svc_stat *statp) {
+void svc_seq_show(struct seq_file *seq, const struct svc_stat *statp)
+{
 	const struct svc_program *prog = statp->program;
-	const struct svc_procedure *proc;
 	const struct svc_version *vers;
 	unsigned int i, j;
 
@@ -98,11 +98,12 @@ void svc_seq_show(struct seq_file *seq, const struct svc_stat *statp) {
 			statp->rpcbadclnt);
 
 	for (i = 0; i < prog->pg_nvers; i++) {
-		if (!(vers = prog->pg_vers[i]) || !(proc = vers->vs_proc))
+		vers = prog->pg_vers[i];
+		if (!vers)
 			continue;
 		seq_printf(seq, "proc%d %u", i, vers->vs_nproc);
-		for (j = 0; j < vers->vs_nproc; j++, proc++)
-			seq_printf(seq, " %u", proc->pc_count);
+		for (j = 0; j < vers->vs_nproc; j++)
+			seq_printf(seq, " %u", vers->vs_count[j]);
 		seq_putc(seq, '\n');
 	}
 }
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index aa643a29fdc6..6452592194ac 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1261,7 +1261,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 	svc_putnl(resv, RPC_SUCCESS);
 
 	/* Bump per-procedure stats counter */
-	procp->pc_count++;
+	versp->vs_count[proc]++;
 
 	/* Initialize storage for argp and resp */
 	memset(rqstp->rq_argp, 0, procp->pc_argsize);
-- 
cgit v1.2.3


From 860bda29b99afdc072a7a796fe81185f7ae85deb Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 12 May 2017 16:11:49 +0200
Subject: sunrpc: mark all struct svc_procinfo instances as const

struct svc_procinfo contains function pointers, and marking it as
constant avoids it being able to be used as an attach vector for
code injections.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/lockd/svc4proc.c         | 2 +-
 fs/lockd/svcproc.c          | 2 +-
 fs/nfs/callback_xdr.c       | 2 +-
 fs/nfsd/nfs2acl.c           | 2 +-
 fs/nfsd/nfs3acl.c           | 2 +-
 fs/nfsd/nfs3proc.c          | 2 +-
 fs/nfsd/nfs4proc.c          | 2 +-
 fs/nfsd/nfsproc.c           | 2 +-
 fs/nfsd/nfssvc.c            | 4 ++--
 include/linux/lockd/lockd.h | 4 ++--
 include/linux/sunrpc/svc.h  | 4 ++--
 net/sunrpc/svc.c            | 2 +-
 12 files changed, 15 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index fed016155791..82925f17ec45 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -507,7 +507,7 @@ struct nlm_void			{ int dummy; };
 #define	No	(1+1024/4)				/* netobj */
 #define	St	1					/* status */
 #define	Rg	4					/* range (offset + length) */
-struct svc_procedure		nlmsvc_procedures4[] = {
+const struct svc_procedure nlmsvc_procedures4[] = {
   PROC(null,		void,		void,		void,	void, 1),
   PROC(test,		testargs,	testres,	args,	res, Ck+St+2+No+Rg),
   PROC(lock,		lockargs,	res,		args,	res, Ck+St),
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index 14648b051eba..07915162581d 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -551,7 +551,7 @@ struct nlm_void			{ int dummy; };
 #define	No	(1+1024/4)			/* Net Obj */
 #define	Rg	2				/* range - offset + size */
 
-struct svc_procedure		nlmsvc_procedures[] = {
+const struct svc_procedure nlmsvc_procedures[] = {
   PROC(null,		void,		void,		void,	void, 1),
   PROC(test,		testargs,	testres,	args,	res, Ck+St+2+No+Rg),
   PROC(lock,		lockargs,	res,		args,	res, Ck+St),
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index ecd46b8c0985..ae249f27297f 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -995,7 +995,7 @@ static struct callback_op callback_ops[] = {
 /*
  * Define NFS4 callback procedures
  */
-static struct svc_procedure nfs4_callback_procedures1[] = {
+static const struct svc_procedure nfs4_callback_procedures1[] = {
 	[CB_NULL] = {
 		.pc_func = nfs4_callback_null,
 		.pc_decode = nfs4_decode_void,
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index 026edfe73fd5..c3f6b8a6b659 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -370,7 +370,7 @@ struct nfsd3_voidargs { int dummy; };
 #define pAT (1+AT)	/* post attributes - conditional */
 #define ACL (1+NFS_ACL_MAX_ENTRIES*3)  /* Access Control List */
 
-static struct svc_procedure		nfsd_acl_procedures2[] = {
+static const struct svc_procedure nfsd_acl_procedures2[] = {
   PROC(null,	void,		void,		void,	  RC_NOCACHE, ST),
   PROC(getacl,	getacl,		getacl,		getacl,	  RC_NOCACHE, ST+1+2*(1+ACL)),
   PROC(setacl,	setacl,		attrstat,	attrstat, RC_NOCACHE, ST+AT),
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index 73c0970ccefb..1a482ac9d4e9 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -257,7 +257,7 @@ struct nfsd3_voidargs { int dummy; };
 #define pAT (1+AT)	/* post attributes - conditional */
 #define ACL (1+NFS_ACL_MAX_ENTRIES*3)  /* Access Control List */
 
-static struct svc_procedure		nfsd_acl_procedures3[] = {
+static const struct svc_procedure nfsd_acl_procedures3[] = {
   PROC(null,	void,		void,		void,	  RC_NOCACHE, ST),
   PROC(getacl,	getacl,		getacl,		getacl,	  RC_NOCACHE, ST+1+2*(1+ACL)),
   PROC(setacl,	setacl,		setacl,		fhandle,  RC_NOCACHE, ST+pAT),
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index b5823802e278..96e0e6a2af51 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -674,7 +674,7 @@ struct nfsd3_voidargs { int dummy; };
 #define pAT (1+AT)	/* post attributes - conditional */
 #define WC (7+pAT)	/* WCC attributes */
 
-static struct svc_procedure		nfsd_procedures3[22] = {
+static const struct svc_procedure nfsd_procedures3[22] = {
 	[NFS3PROC_NULL] = {
 		.pc_func = nfsd3_proc_null,
 		.pc_encode = nfs3svc_encode_voidres,
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index bad5fec0ebc7..a4d8aa3abc63 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -2533,7 +2533,7 @@ static const char *nfsd4_op_name(unsigned opnum)
 #define nfsd4_voidres			nfsd4_voidargs
 struct nfsd4_voidargs { int dummy; };
 
-static struct svc_procedure		nfsd_procedures4[2] = {
+static const struct svc_procedure nfsd_procedures4[2] = {
 	[NFSPROC4_NULL] = {
 		.pc_func = nfsd4_proc_null,
 		.pc_encode = nfs4svc_encode_voidres,
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index 44b157553733..a68b686fda12 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -573,7 +573,7 @@ struct nfsd_void { int dummy; };
 #define FH 8		/* filehandle */
 #define	AT 18		/* attributes */
 
-static struct svc_procedure		nfsd_procedures2[18] = {
+static const struct svc_procedure nfsd_procedures2[18] = {
 	[NFSPROC_NULL] = {
 		.pc_func = nfsd_proc_null,
 		.pc_decode = nfssvc_decode_void,
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 555233664124..379b310c445d 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -756,7 +756,7 @@ static __be32 map_new_errors(u32 vers, __be32 nfserr)
  * problem, we enforce these assumptions here:
  */
 static bool nfs_request_too_big(struct svc_rqst *rqstp,
-				struct svc_procedure *proc)
+				const struct svc_procedure *proc)
 {
 	/*
 	 * The ACL code has more careful bounds-checking and is not
@@ -781,7 +781,7 @@ static bool nfs_request_too_big(struct svc_rqst *rqstp,
 int
 nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 {
-	struct svc_procedure	*proc;
+	const struct svc_procedure *proc;
 	__be32			nfserr;
 	__be32			*nfserrp;
 
diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h
index 41f7b6a04d69..3eca67728366 100644
--- a/include/linux/lockd/lockd.h
+++ b/include/linux/lockd/lockd.h
@@ -192,9 +192,9 @@ struct nlm_block {
  * Global variables
  */
 extern const struct rpc_program	nlm_program;
-extern struct svc_procedure	nlmsvc_procedures[];
+extern const struct svc_procedure nlmsvc_procedures[];
 #ifdef CONFIG_LOCKD_V4
-extern struct svc_procedure	nlmsvc_procedures4[];
+extern const struct svc_procedure nlmsvc_procedures4[];
 #endif
 extern int			nlmsvc_grace_period;
 extern unsigned long		nlmsvc_timeout;
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 9f00384153f4..984e6b9c3043 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -237,7 +237,7 @@ struct svc_rqst {
 
 	struct svc_serv *	rq_server;	/* RPC service definition */
 	struct svc_pool *	rq_pool;	/* thread pool */
-	struct svc_procedure *	rq_procinfo;	/* procedure info */
+	const struct svc_procedure *rq_procinfo;/* procedure info */
 	struct auth_ops *	rq_authop;	/* authentication flavour */
 	struct svc_cred		rq_cred;	/* auth info */
 	void *			rq_xprt_ctxt;	/* transport specific context ptr */
@@ -396,7 +396,7 @@ struct svc_program {
 struct svc_version {
 	u32			vs_vers;	/* version number */
 	u32			vs_nproc;	/* number of procedures */
-	struct svc_procedure *	vs_proc;	/* per-procedure info */
+	const struct svc_procedure *vs_proc;	/* per-procedure info */
 	unsigned int		*vs_count;	/* call counts */
 	u32			vs_xdrsize;	/* xdrsize needed for this version */
 
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 6452592194ac..049963d676a7 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1152,7 +1152,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 {
 	struct svc_program	*progp;
 	struct svc_version	*versp = NULL;	/* compiler food */
-	struct svc_procedure	*procp = NULL;
+	const struct svc_procedure *procp = NULL;
 	struct svc_serv		*serv = rqstp->rq_server;
 	__be32			*statp;
 	u32			prog, vers, proc;
-- 
cgit v1.2.3


From e9679189e34b25a1b9aa77fe37d331559d1544af Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 12 May 2017 16:21:37 +0200
Subject: sunrpc: mark all struct svc_version instances as const

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 fs/lockd/svc.c             | 38 +++++++++++++++++++-------------------
 fs/nfs/callback.c          |  2 +-
 fs/nfs/callback_xdr.c      |  4 ++--
 fs/nfs/internal.h          |  4 ++--
 fs/nfs/nfs4_fs.h           |  4 ++--
 fs/nfsd/nfs2acl.c          | 14 +++++++-------
 fs/nfsd/nfs3acl.c          | 14 +++++++-------
 fs/nfsd/nfs3proc.c         | 14 +++++++-------
 fs/nfsd/nfs4proc.c         |  2 +-
 fs/nfsd/nfsd.h             |  6 +++---
 fs/nfsd/nfsproc.c          | 14 +++++++-------
 fs/nfsd/nfssvc.c           |  8 ++++----
 include/linux/sunrpc/svc.h |  2 +-
 net/sunrpc/svc.c           |  4 ++--
 14 files changed, 65 insertions(+), 65 deletions(-)

(limited to 'include')

diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index cc6abe6280bc..726b6cecf430 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -740,32 +740,32 @@ module_exit(exit_nlm);
  * Define NLM program and procedures
  */
 static unsigned int nlmsvc_version1_count[17];
-static struct svc_version	nlmsvc_version1 = {
-		.vs_vers	= 1,
-		.vs_nproc	= 17,
-		.vs_proc	= nlmsvc_procedures,
-		.vs_count	= nlmsvc_version1_count,
-		.vs_xdrsize	= NLMSVC_XDRSIZE,
+static const struct svc_version	nlmsvc_version1 = {
+	.vs_vers	= 1,
+	.vs_nproc	= 17,
+	.vs_proc	= nlmsvc_procedures,
+	.vs_count	= nlmsvc_version1_count,
+	.vs_xdrsize	= NLMSVC_XDRSIZE,
 };
 static unsigned int nlmsvc_version3_count[24];
-static struct svc_version	nlmsvc_version3 = {
-		.vs_vers	= 3,
-		.vs_nproc	= 24,
-		.vs_proc	= nlmsvc_procedures,
-		.vs_count	= nlmsvc_version3_count,
-		.vs_xdrsize	= NLMSVC_XDRSIZE,
+static const struct svc_version	nlmsvc_version3 = {
+	.vs_vers	= 3,
+	.vs_nproc	= 24,
+	.vs_proc	= nlmsvc_procedures,
+	.vs_count	= nlmsvc_version3_count,
+	.vs_xdrsize	= NLMSVC_XDRSIZE,
 };
 #ifdef CONFIG_LOCKD_V4
 static unsigned int nlmsvc_version4_count[24];
-static struct svc_version	nlmsvc_version4 = {
-		.vs_vers	= 4,
-		.vs_nproc	= 24,
-		.vs_proc	= nlmsvc_procedures4,
-		.vs_count	= nlmsvc_version4_count,
-		.vs_xdrsize	= NLMSVC_XDRSIZE,
+static const struct svc_version	nlmsvc_version4 = {
+	.vs_vers	= 4,
+	.vs_nproc	= 24,
+	.vs_proc	= nlmsvc_procedures4,
+	.vs_count	= nlmsvc_version4_count,
+	.vs_xdrsize	= NLMSVC_XDRSIZE,
 };
 #endif
-static struct svc_version *	nlmsvc_version[] = {
+static const struct svc_version *nlmsvc_version[] = {
 	[1] = &nlmsvc_version1,
 	[3] = &nlmsvc_version3,
 #ifdef CONFIG_LOCKD_V4
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index 73a1f928226c..34323877ec13 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -439,7 +439,7 @@ static int nfs_callback_authenticate(struct svc_rqst *rqstp)
 /*
  * Define NFS4 callback program
  */
-static struct svc_version *nfs4_callback_version[] = {
+static const struct svc_version *nfs4_callback_version[] = {
 	[1] = &nfs4_callback_version1,
 	[4] = &nfs4_callback_version4,
 };
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index ae249f27297f..01a430e51daa 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -1012,7 +1012,7 @@ static const struct svc_procedure nfs4_callback_procedures1[] = {
 };
 
 static unsigned int nfs4_callback_count1[ARRAY_SIZE(nfs4_callback_procedures1)];
-struct svc_version nfs4_callback_version1 = {
+const struct svc_version nfs4_callback_version1 = {
 	.vs_vers = 1,
 	.vs_nproc = ARRAY_SIZE(nfs4_callback_procedures1),
 	.vs_proc = nfs4_callback_procedures1,
@@ -1024,7 +1024,7 @@ struct svc_version nfs4_callback_version1 = {
 };
 
 static unsigned int nfs4_callback_count4[ARRAY_SIZE(nfs4_callback_procedures1)];
-struct svc_version nfs4_callback_version4 = {
+const struct svc_version nfs4_callback_version4 = {
 	.vs_vers = 4,
 	.vs_nproc = ARRAY_SIZE(nfs4_callback_procedures1),
 	.vs_proc = nfs4_callback_procedures1,
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index c21254924389..9976d8498cf3 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -225,8 +225,8 @@ static inline void nfs_fs_proc_exit(void)
 #endif
 
 /* callback_xdr.c */
-extern struct svc_version nfs4_callback_version1;
-extern struct svc_version nfs4_callback_version4;
+extern const struct svc_version nfs4_callback_version1;
+extern const struct svc_version nfs4_callback_version4;
 
 struct nfs_pageio_descriptor;
 /* pagelist.c */
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 9b0cf3872722..40bd05f05e74 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -498,8 +498,8 @@ extern const struct rpc_procinfo nfs4_procedures[];
 struct nfs4_mount_data;
 
 /* callback_xdr.c */
-extern struct svc_version nfs4_callback_version1;
-extern struct svc_version nfs4_callback_version4;
+extern const struct svc_version nfs4_callback_version1;
+extern const struct svc_version nfs4_callback_version4;
 
 static inline void nfs4_stateid_copy(nfs4_stateid *dst, const nfs4_stateid *src)
 {
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index c3f6b8a6b659..6276ec8608b0 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -379,11 +379,11 @@ static const struct svc_procedure nfsd_acl_procedures2[] = {
 };
 
 static unsigned int nfsd_acl_count2[ARRAY_SIZE(nfsd_acl_procedures2)];
-struct svc_version	nfsd_acl_version2 = {
-		.vs_vers	= 2,
-		.vs_nproc	= 5,
-		.vs_proc	= nfsd_acl_procedures2,
-		.vs_count	= nfsd_acl_count2,
-		.vs_dispatch	= nfsd_dispatch,
-		.vs_xdrsize	= NFS3_SVC_XDRSIZE,
+const struct svc_version nfsd_acl_version2 = {
+	.vs_vers	= 2,
+	.vs_nproc	= 5,
+	.vs_proc	= nfsd_acl_procedures2,
+	.vs_count	= nfsd_acl_count2,
+	.vs_dispatch	= nfsd_dispatch,
+	.vs_xdrsize	= NFS3_SVC_XDRSIZE,
 };
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index 1a482ac9d4e9..01976529f042 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -264,12 +264,12 @@ static const struct svc_procedure nfsd_acl_procedures3[] = {
 };
 
 static unsigned int nfsd_acl_count3[ARRAY_SIZE(nfsd_acl_procedures3)];
-struct svc_version	nfsd_acl_version3 = {
-		.vs_vers	= 3,
-		.vs_nproc	= 3,
-		.vs_proc	= nfsd_acl_procedures3,
-		.vs_count	= nfsd_acl_count3,
-		.vs_dispatch	= nfsd_dispatch,
-		.vs_xdrsize	= NFS3_SVC_XDRSIZE,
+const struct svc_version nfsd_acl_version3 = {
+	.vs_vers	= 3,
+	.vs_nproc	= 3,
+	.vs_proc	= nfsd_acl_procedures3,
+	.vs_count	= nfsd_acl_count3,
+	.vs_dispatch	= nfsd_dispatch,
+	.vs_xdrsize	= NFS3_SVC_XDRSIZE,
 };
 
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 96e0e6a2af51..2cb56a0d6625 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -891,11 +891,11 @@ static const struct svc_procedure nfsd_procedures3[22] = {
 };
 
 static unsigned int nfsd_count3[ARRAY_SIZE(nfsd_procedures3)];
-struct svc_version	nfsd_version3 = {
-		.vs_vers	= 3,
-		.vs_nproc	= 22,
-		.vs_proc	= nfsd_procedures3,
-		.vs_count	= nfsd_count3,
-		.vs_dispatch	= nfsd_dispatch,
-		.vs_xdrsize	= NFS3_SVC_XDRSIZE,
+const struct svc_version nfsd_version3 = {
+	.vs_vers	= 3,
+	.vs_nproc	= 22,
+	.vs_proc	= nfsd_procedures3,
+	.vs_dispatch	= nfsd_dispatch,
+	.vs_count	= nfsd_count3,
+	.vs_xdrsize	= NFS3_SVC_XDRSIZE,
 };
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index a4d8aa3abc63..e814c1946f6e 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -2555,7 +2555,7 @@ static const struct svc_procedure nfsd_procedures4[2] = {
 };
 
 static unsigned int nfsd_count3[ARRAY_SIZE(nfsd_procedures4)];
-struct svc_version	nfsd_version4 = {
+const struct svc_version nfsd_version4 = {
 	.vs_vers		= 4,
 	.vs_nproc		= 2,
 	.vs_proc		= nfsd_procedures4,
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index d96606801d47..b9c538ab7a59 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -60,7 +60,7 @@ struct readdir_cd {
 
 
 extern struct svc_program	nfsd_program;
-extern struct svc_version	nfsd_version2, nfsd_version3,
+extern const struct svc_version	nfsd_version2, nfsd_version3,
 				nfsd_version4;
 extern struct mutex		nfsd_mutex;
 extern spinlock_t		nfsd_drc_lock;
@@ -86,12 +86,12 @@ void		nfsd_destroy(struct net *net);
 
 #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
 #ifdef CONFIG_NFSD_V2_ACL
-extern struct svc_version nfsd_acl_version2;
+extern const struct svc_version nfsd_acl_version2;
 #else
 #define nfsd_acl_version2 NULL
 #endif
 #ifdef CONFIG_NFSD_V3_ACL
-extern struct svc_version nfsd_acl_version3;
+extern const struct svc_version nfsd_acl_version3;
 #else
 #define nfsd_acl_version3 NULL
 #endif
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index a68b686fda12..5076ae2b8258 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -744,13 +744,13 @@ static const struct svc_procedure nfsd_procedures2[18] = {
 
 
 static unsigned int nfsd_count2[ARRAY_SIZE(nfsd_procedures2)];
-struct svc_version	nfsd_version2 = {
-		.vs_vers	= 2,
-		.vs_nproc	= 18,
-		.vs_proc	= nfsd_procedures2,
-		.vs_count	= nfsd_count2,
-		.vs_dispatch	= nfsd_dispatch,
-		.vs_xdrsize	= NFS2_SVC_XDRSIZE,
+const struct svc_version nfsd_version2 = {
+	.vs_vers	= 2,
+	.vs_nproc	= 18,
+	.vs_proc	= nfsd_procedures2,
+	.vs_count	= nfsd_count2,
+	.vs_dispatch	= nfsd_dispatch,
+	.vs_xdrsize	= NFS2_SVC_XDRSIZE,
 };
 
 /*
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 379b310c445d..063ae7de2c12 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -68,14 +68,14 @@ unsigned long	nfsd_drc_mem_used;
 
 #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
 static struct svc_stat	nfsd_acl_svcstats;
-static struct svc_version *	nfsd_acl_version[] = {
+static const struct svc_version *nfsd_acl_version[] = {
 	[2] = &nfsd_acl_version2,
 	[3] = &nfsd_acl_version3,
 };
 
 #define NFSD_ACL_MINVERS            2
 #define NFSD_ACL_NRVERS		ARRAY_SIZE(nfsd_acl_version)
-static struct svc_version *nfsd_acl_versions[NFSD_ACL_NRVERS];
+static const struct svc_version *nfsd_acl_versions[NFSD_ACL_NRVERS];
 
 static struct svc_program	nfsd_acl_program = {
 	.pg_prog		= NFS_ACL_PROGRAM,
@@ -92,7 +92,7 @@ static struct svc_stat	nfsd_acl_svcstats = {
 };
 #endif /* defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) */
 
-static struct svc_version *	nfsd_version[] = {
+static const struct svc_version *nfsd_version[] = {
 	[2] = &nfsd_version2,
 #if defined(CONFIG_NFSD_V3)
 	[3] = &nfsd_version3,
@@ -104,7 +104,7 @@ static struct svc_version *	nfsd_version[] = {
 
 #define NFSD_MINVERS    	2
 #define NFSD_NRVERS		ARRAY_SIZE(nfsd_version)
-static struct svc_version *nfsd_versions[NFSD_NRVERS];
+static const struct svc_version *nfsd_versions[NFSD_NRVERS];
 
 struct svc_program		nfsd_program = {
 #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 984e6b9c3043..e85267899753 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -383,7 +383,7 @@ struct svc_program {
 	unsigned int		pg_lovers;	/* lowest version */
 	unsigned int		pg_hivers;	/* highest version */
 	unsigned int		pg_nvers;	/* number of versions */
-	struct svc_version **	pg_vers;	/* version array */
+	const struct svc_version **pg_vers;	/* version array */
 	char *			pg_name;	/* service name */
 	char *			pg_class;	/* class name: services sharing authentication */
 	struct svc_stat *	pg_stats;	/* rpc statistics */
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 049963d676a7..45b4f2d2e3bd 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1008,7 +1008,7 @@ int svc_register(const struct svc_serv *serv, struct net *net,
 		 const unsigned short port)
 {
 	struct svc_program	*progp;
-	struct svc_version	*vers;
+	const struct svc_version *vers;
 	unsigned int		i;
 	int			error = 0;
 
@@ -1151,7 +1151,7 @@ static int
 svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 {
 	struct svc_program	*progp;
-	struct svc_version	*versp = NULL;	/* compiler food */
+	const struct svc_version *versp = NULL;	/* compiler food */
 	const struct svc_procedure *procp = NULL;
 	struct svc_serv		*serv = rqstp->rq_server;
 	__be32			*statp;
-- 
cgit v1.2.3


From cfc5604c488ccd17936b69008af0c9ae050f4a08 Mon Sep 17 00:00:00 2001
From: Cyrille Pitchen <cyrille.pitchen@atmel.com>
Date: Tue, 25 Apr 2017 22:08:46 +0200
Subject: mtd: spi-nor: introduce SPI 1-2-2 and SPI 1-4-4 protocols

This patch changes the prototype of spi_nor_scan(): its 3rd parameter
is replaced by a 'struct spi_nor_hwcaps' pointer, which tells the spi-nor
framework about the actual hardware capabilities supported by the SPI
controller and its driver.

Besides, this patch also introduces a new 'struct spi_nor_flash_parameter'
telling the spi-nor framework about the hardware capabilities supported by
the SPI flash memory and the associated settings required to use those
hardware caps.

Then, to improve the readability of spi_nor_scan(), the discovery of the
memory settings and the memory initialization are now split into two
dedicated functions.

1 - spi_nor_init_params()

The spi_nor_init_params() function is responsible for initializing the
'struct spi_nor_flash_parameter'. Currently this structure is filled with
legacy values but further patches will allow to override some parameter
values dynamically, for instance by reading the JESD216 Serial Flash
Discoverable Parameter (SFDP) tables from the SPI memory.
The spi_nor_init_params() function only deals with the hardware
capabilities of the SPI flash memory: especially it doesn't care about
the hardware capabilities supported by the SPI controller.

2 - spi_nor_setup()

The second function is called once the 'struct spi_nor_flash_parameter'
has been initialized by spi_nor_init_params().
With both 'struct spi_nor_flash_parameter' and 'struct spi_nor_hwcaps',
the new argument of spi_nor_scan(), spi_nor_setup() computes the best
match between hardware caps supported by both the (Q)SPI memory and
controller hence selecting the relevant settings for (Fast) Read and Page
Program operations.

Signed-off-by: Cyrille Pitchen <cyrille.pitchen@atmel.com>
Reviewed-by: Marek Vasut <marek.vasut@gmail.com>
---
 drivers/mtd/devices/m25p80.c          |  21 +-
 drivers/mtd/spi-nor/aspeed-smc.c      |  23 +-
 drivers/mtd/spi-nor/atmel-quadspi.c   |  83 ++++---
 drivers/mtd/spi-nor/cadence-quadspi.c |  18 +-
 drivers/mtd/spi-nor/fsl-quadspi.c     |   6 +-
 drivers/mtd/spi-nor/hisi-sfc.c        |  31 ++-
 drivers/mtd/spi-nor/intel-spi.c       |   7 +-
 drivers/mtd/spi-nor/mtk-quadspi.c     |  15 +-
 drivers/mtd/spi-nor/nxp-spifi.c       |  22 +-
 drivers/mtd/spi-nor/spi-nor.c         | 440 ++++++++++++++++++++++++++--------
 drivers/mtd/spi-nor/stm32-quadspi.c   |  27 ++-
 include/linux/mtd/spi-nor.h           | 119 ++++++++-
 12 files changed, 613 insertions(+), 199 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c
index c4df3b1bded0..07073f4ce0bd 100644
--- a/drivers/mtd/devices/m25p80.c
+++ b/drivers/mtd/devices/m25p80.c
@@ -111,14 +111,7 @@ static ssize_t m25p80_write(struct spi_nor *nor, loff_t to, size_t len,
 
 static inline unsigned int m25p80_rx_nbits(struct spi_nor *nor)
 {
-	switch (nor->flash_read) {
-	case SPI_NOR_DUAL:
-		return 2;
-	case SPI_NOR_QUAD:
-		return 4;
-	default:
-		return 0;
-	}
+	return spi_nor_get_protocol_data_nbits(nor->read_proto);
 }
 
 /*
@@ -196,7 +189,11 @@ static int m25p_probe(struct spi_device *spi)
 	struct flash_platform_data	*data;
 	struct m25p *flash;
 	struct spi_nor *nor;
-	enum read_mode mode = SPI_NOR_NORMAL;
+	struct spi_nor_hwcaps hwcaps = {
+		.mask = SNOR_HWCAPS_READ |
+			SNOR_HWCAPS_READ_FAST |
+			SNOR_HWCAPS_PP,
+	};
 	char *flash_name;
 	int ret;
 
@@ -222,9 +219,9 @@ static int m25p_probe(struct spi_device *spi)
 	flash->spi = spi;
 
 	if (spi->mode & SPI_RX_QUAD)
-		mode = SPI_NOR_QUAD;
+		hwcaps.mask |= SNOR_HWCAPS_READ_1_1_4;
 	else if (spi->mode & SPI_RX_DUAL)
-		mode = SPI_NOR_DUAL;
+		hwcaps.mask |= SNOR_HWCAPS_READ_1_1_2;
 
 	if (data && data->name)
 		nor->mtd.name = data->name;
@@ -241,7 +238,7 @@ static int m25p_probe(struct spi_device *spi)
 	else
 		flash_name = spi->modalias;
 
-	ret = spi_nor_scan(nor, flash_name, mode);
+	ret = spi_nor_scan(nor, flash_name, &hwcaps);
 	if (ret)
 		return ret;
 
diff --git a/drivers/mtd/spi-nor/aspeed-smc.c b/drivers/mtd/spi-nor/aspeed-smc.c
index 56051d30f000..3f875c8d6339 100644
--- a/drivers/mtd/spi-nor/aspeed-smc.c
+++ b/drivers/mtd/spi-nor/aspeed-smc.c
@@ -585,14 +585,12 @@ static int aspeed_smc_chip_setup_finish(struct aspeed_smc_chip *chip)
 	 * TODO: Adjust clocks if fast read is supported and interpret
 	 * SPI-NOR flags to adjust controller settings.
 	 */
-	switch (chip->nor.flash_read) {
-	case SPI_NOR_NORMAL:
-		cmd = CONTROL_COMMAND_MODE_NORMAL;
-		break;
-	case SPI_NOR_FAST:
-		cmd = CONTROL_COMMAND_MODE_FREAD;
-		break;
-	default:
+	if (chip->nor.read_proto == SNOR_PROTO_1_1_1) {
+		if (chip->nor.read_dummy == 0)
+			cmd = CONTROL_COMMAND_MODE_NORMAL;
+		else
+			cmd = CONTROL_COMMAND_MODE_FREAD;
+	} else {
 		dev_err(chip->nor.dev, "unsupported SPI read mode\n");
 		return -EINVAL;
 	}
@@ -608,6 +606,11 @@ static int aspeed_smc_chip_setup_finish(struct aspeed_smc_chip *chip)
 static int aspeed_smc_setup_flash(struct aspeed_smc_controller *controller,
 				  struct device_node *np, struct resource *r)
 {
+	const struct spi_nor_hwcaps hwcaps = {
+		.mask = SNOR_HWCAPS_READ |
+			SNOR_HWCAPS_READ_FAST |
+			SNOR_HWCAPS_PP,
+	};
 	const struct aspeed_smc_info *info = controller->info;
 	struct device *dev = controller->dev;
 	struct device_node *child;
@@ -671,11 +674,11 @@ static int aspeed_smc_setup_flash(struct aspeed_smc_controller *controller,
 			break;
 
 		/*
-		 * TODO: Add support for SPI_NOR_QUAD and SPI_NOR_DUAL
+		 * TODO: Add support for Dual and Quad SPI protocols
 		 * attach when board support is present as determined
 		 * by of property.
 		 */
-		ret = spi_nor_scan(nor, NULL, SPI_NOR_NORMAL);
+		ret = spi_nor_scan(nor, NULL, &hwcaps);
 		if (ret)
 			break;
 
diff --git a/drivers/mtd/spi-nor/atmel-quadspi.c b/drivers/mtd/spi-nor/atmel-quadspi.c
index 47937d9beec6..ba76fa8f2031 100644
--- a/drivers/mtd/spi-nor/atmel-quadspi.c
+++ b/drivers/mtd/spi-nor/atmel-quadspi.c
@@ -275,14 +275,48 @@ static void atmel_qspi_debug_command(struct atmel_qspi *aq,
 
 static int atmel_qspi_run_command(struct atmel_qspi *aq,
 				  const struct atmel_qspi_command *cmd,
-				  u32 ifr_tfrtyp, u32 ifr_width)
+				  u32 ifr_tfrtyp, enum spi_nor_protocol proto)
 {
 	u32 iar, icr, ifr, sr;
 	int err = 0;
 
 	iar = 0;
 	icr = 0;
-	ifr = ifr_tfrtyp | ifr_width;
+	ifr = ifr_tfrtyp;
+
+	/* Set the SPI protocol */
+	switch (proto) {
+	case SNOR_PROTO_1_1_1:
+		ifr |= QSPI_IFR_WIDTH_SINGLE_BIT_SPI;
+		break;
+
+	case SNOR_PROTO_1_1_2:
+		ifr |= QSPI_IFR_WIDTH_DUAL_OUTPUT;
+		break;
+
+	case SNOR_PROTO_1_1_4:
+		ifr |= QSPI_IFR_WIDTH_QUAD_OUTPUT;
+		break;
+
+	case SNOR_PROTO_1_2_2:
+		ifr |= QSPI_IFR_WIDTH_DUAL_IO;
+		break;
+
+	case SNOR_PROTO_1_4_4:
+		ifr |= QSPI_IFR_WIDTH_QUAD_IO;
+		break;
+
+	case SNOR_PROTO_2_2_2:
+		ifr |= QSPI_IFR_WIDTH_DUAL_CMD;
+		break;
+
+	case SNOR_PROTO_4_4_4:
+		ifr |= QSPI_IFR_WIDTH_QUAD_CMD;
+		break;
+
+	default:
+		return -EINVAL;
+	}
 
 	/* Compute instruction parameters */
 	if (cmd->enable.bits.instruction) {
@@ -434,7 +468,7 @@ static int atmel_qspi_read_reg(struct spi_nor *nor, u8 opcode,
 	cmd.rx_buf = buf;
 	cmd.buf_len = len;
 	return atmel_qspi_run_command(aq, &cmd, QSPI_IFR_TFRTYP_TRSFR_READ,
-				      QSPI_IFR_WIDTH_SINGLE_BIT_SPI);
+				      nor->reg_proto);
 }
 
 static int atmel_qspi_write_reg(struct spi_nor *nor, u8 opcode,
@@ -450,7 +484,7 @@ static int atmel_qspi_write_reg(struct spi_nor *nor, u8 opcode,
 	cmd.tx_buf = buf;
 	cmd.buf_len = len;
 	return atmel_qspi_run_command(aq, &cmd, QSPI_IFR_TFRTYP_TRSFR_WRITE,
-				      QSPI_IFR_WIDTH_SINGLE_BIT_SPI);
+				      nor->reg_proto);
 }
 
 static ssize_t atmel_qspi_write(struct spi_nor *nor, loff_t to, size_t len,
@@ -469,7 +503,7 @@ static ssize_t atmel_qspi_write(struct spi_nor *nor, loff_t to, size_t len,
 	cmd.tx_buf = write_buf;
 	cmd.buf_len = len;
 	ret = atmel_qspi_run_command(aq, &cmd, QSPI_IFR_TFRTYP_TRSFR_WRITE_MEM,
-				     QSPI_IFR_WIDTH_SINGLE_BIT_SPI);
+				     nor->write_proto);
 	return (ret < 0) ? ret : len;
 }
 
@@ -484,7 +518,7 @@ static int atmel_qspi_erase(struct spi_nor *nor, loff_t offs)
 	cmd.instruction = nor->erase_opcode;
 	cmd.address = (u32)offs;
 	return atmel_qspi_run_command(aq, &cmd, QSPI_IFR_TFRTYP_TRSFR_WRITE,
-				      QSPI_IFR_WIDTH_SINGLE_BIT_SPI);
+				      nor->reg_proto);
 }
 
 static ssize_t atmel_qspi_read(struct spi_nor *nor, loff_t from, size_t len,
@@ -493,27 +527,8 @@ static ssize_t atmel_qspi_read(struct spi_nor *nor, loff_t from, size_t len,
 	struct atmel_qspi *aq = nor->priv;
 	struct atmel_qspi_command cmd;
 	u8 num_mode_cycles, num_dummy_cycles;
-	u32 ifr_width;
 	ssize_t ret;
 
-	switch (nor->flash_read) {
-	case SPI_NOR_NORMAL:
-	case SPI_NOR_FAST:
-		ifr_width = QSPI_IFR_WIDTH_SINGLE_BIT_SPI;
-		break;
-
-	case SPI_NOR_DUAL:
-		ifr_width = QSPI_IFR_WIDTH_DUAL_OUTPUT;
-		break;
-
-	case SPI_NOR_QUAD:
-		ifr_width = QSPI_IFR_WIDTH_QUAD_OUTPUT;
-		break;
-
-	default:
-		return -EINVAL;
-	}
-
 	if (nor->read_dummy >= 2) {
 		num_mode_cycles = 2;
 		num_dummy_cycles = nor->read_dummy - 2;
@@ -536,7 +551,7 @@ static ssize_t atmel_qspi_read(struct spi_nor *nor, loff_t from, size_t len,
 	cmd.rx_buf = read_buf;
 	cmd.buf_len = len;
 	ret = atmel_qspi_run_command(aq, &cmd, QSPI_IFR_TFRTYP_TRSFR_READ_MEM,
-				     ifr_width);
+				     nor->read_proto);
 	return (ret < 0) ? ret : len;
 }
 
@@ -590,6 +605,20 @@ static irqreturn_t atmel_qspi_interrupt(int irq, void *dev_id)
 
 static int atmel_qspi_probe(struct platform_device *pdev)
 {
+	const struct spi_nor_hwcaps hwcaps = {
+		.mask = SNOR_HWCAPS_READ |
+			SNOR_HWCAPS_READ_FAST |
+			SNOR_HWCAPS_READ_1_1_2 |
+			SNOR_HWCAPS_READ_1_2_2 |
+			SNOR_HWCAPS_READ_2_2_2 |
+			SNOR_HWCAPS_READ_1_1_4 |
+			SNOR_HWCAPS_READ_1_4_4 |
+			SNOR_HWCAPS_READ_4_4_4 |
+			SNOR_HWCAPS_PP |
+			SNOR_HWCAPS_PP_1_1_4 |
+			SNOR_HWCAPS_PP_1_4_4 |
+			SNOR_HWCAPS_PP_4_4_4,
+	};
 	struct device_node *child, *np = pdev->dev.of_node;
 	struct atmel_qspi *aq;
 	struct resource *res;
@@ -679,7 +708,7 @@ static int atmel_qspi_probe(struct platform_device *pdev)
 	if (err)
 		goto disable_clk;
 
-	err = spi_nor_scan(nor, NULL, SPI_NOR_QUAD);
+	err = spi_nor_scan(nor, NULL, &hwcaps);
 	if (err)
 		goto disable_clk;
 
diff --git a/drivers/mtd/spi-nor/cadence-quadspi.c b/drivers/mtd/spi-nor/cadence-quadspi.c
index 9f8102de1b16..40096d73536c 100644
--- a/drivers/mtd/spi-nor/cadence-quadspi.c
+++ b/drivers/mtd/spi-nor/cadence-quadspi.c
@@ -855,15 +855,14 @@ static int cqspi_set_protocol(struct spi_nor *nor, const int read)
 	f_pdata->data_width = CQSPI_INST_TYPE_SINGLE;
 
 	if (read) {
-		switch (nor->flash_read) {
-		case SPI_NOR_NORMAL:
-		case SPI_NOR_FAST:
+		switch (nor->read_proto) {
+		case SNOR_PROTO_1_1_1:
 			f_pdata->data_width = CQSPI_INST_TYPE_SINGLE;
 			break;
-		case SPI_NOR_DUAL:
+		case SNOR_PROTO_1_1_2:
 			f_pdata->data_width = CQSPI_INST_TYPE_DUAL;
 			break;
-		case SPI_NOR_QUAD:
+		case SNOR_PROTO_1_1_4:
 			f_pdata->data_width = CQSPI_INST_TYPE_QUAD;
 			break;
 		default:
@@ -1069,6 +1068,13 @@ static void cqspi_controller_init(struct cqspi_st *cqspi)
 
 static int cqspi_setup_flash(struct cqspi_st *cqspi, struct device_node *np)
 {
+	const struct spi_nor_hwcaps hwcaps = {
+		.mask = SNOR_HWCAPS_READ |
+			SNOR_HWCAPS_READ_FAST |
+			SNOR_HWCAPS_READ_1_1_2 |
+			SNOR_HWCAPS_READ_1_1_4 |
+			SNOR_HWCAPS_PP,
+	};
 	struct platform_device *pdev = cqspi->pdev;
 	struct device *dev = &pdev->dev;
 	struct cqspi_flash_pdata *f_pdata;
@@ -1123,7 +1129,7 @@ static int cqspi_setup_flash(struct cqspi_st *cqspi, struct device_node *np)
 			goto err;
 		}
 
-		ret = spi_nor_scan(nor, NULL, SPI_NOR_QUAD);
+		ret = spi_nor_scan(nor, NULL, &hwcaps);
 		if (ret)
 			goto err;
 
diff --git a/drivers/mtd/spi-nor/fsl-quadspi.c b/drivers/mtd/spi-nor/fsl-quadspi.c
index 1476135e0d50..f17d22435bfc 100644
--- a/drivers/mtd/spi-nor/fsl-quadspi.c
+++ b/drivers/mtd/spi-nor/fsl-quadspi.c
@@ -957,6 +957,10 @@ static void fsl_qspi_unprep(struct spi_nor *nor, enum spi_nor_ops ops)
 
 static int fsl_qspi_probe(struct platform_device *pdev)
 {
+	const struct spi_nor_hwcaps hwcaps = {
+		.mask = SNOR_HWCAPS_READ_1_1_4 |
+			SNOR_HWCAPS_PP,
+	};
 	struct device_node *np = pdev->dev.of_node;
 	struct device *dev = &pdev->dev;
 	struct fsl_qspi *q;
@@ -1065,7 +1069,7 @@ static int fsl_qspi_probe(struct platform_device *pdev)
 		/* set the chip address for READID */
 		fsl_qspi_set_base_addr(q, nor);
 
-		ret = spi_nor_scan(nor, NULL, SPI_NOR_QUAD);
+		ret = spi_nor_scan(nor, NULL, &hwcaps);
 		if (ret)
 			goto mutex_failed;
 
diff --git a/drivers/mtd/spi-nor/hisi-sfc.c b/drivers/mtd/spi-nor/hisi-sfc.c
index a286350627a6..d1106832b9d5 100644
--- a/drivers/mtd/spi-nor/hisi-sfc.c
+++ b/drivers/mtd/spi-nor/hisi-sfc.c
@@ -120,19 +120,24 @@ static inline int wait_op_finish(struct hifmc_host *host)
 		(reg & FMC_INT_OP_DONE), 0, FMC_WAIT_TIMEOUT);
 }
 
-static int get_if_type(enum read_mode flash_read)
+static int get_if_type(enum spi_nor_protocol proto)
 {
 	enum hifmc_iftype if_type;
 
-	switch (flash_read) {
-	case SPI_NOR_DUAL:
+	switch (proto) {
+	case SNOR_PROTO_1_1_2:
 		if_type = IF_TYPE_DUAL;
 		break;
-	case SPI_NOR_QUAD:
+	case SNOR_PROTO_1_2_2:
+		if_type = IF_TYPE_DIO;
+		break;
+	case SNOR_PROTO_1_1_4:
 		if_type = IF_TYPE_QUAD;
 		break;
-	case SPI_NOR_NORMAL:
-	case SPI_NOR_FAST:
+	case SNOR_PROTO_1_4_4:
+		if_type = IF_TYPE_QIO;
+		break;
+	case SNOR_PROTO_1_1_1:
 	default:
 		if_type = IF_TYPE_STD;
 		break;
@@ -253,7 +258,10 @@ static int hisi_spi_nor_dma_transfer(struct spi_nor *nor, loff_t start_off,
 	writel(FMC_DMA_LEN_SET(len), host->regbase + FMC_DMA_LEN);
 
 	reg = OP_CFG_FM_CS(priv->chipselect);
-	if_type = get_if_type(nor->flash_read);
+	if (op_type == FMC_OP_READ)
+		if_type = get_if_type(nor->read_proto);
+	else
+		if_type = get_if_type(nor->write_proto);
 	reg |= OP_CFG_MEM_IF_TYPE(if_type);
 	if (op_type == FMC_OP_READ)
 		reg |= OP_CFG_DUMMY_NUM(nor->read_dummy >> 3);
@@ -321,6 +329,13 @@ static ssize_t hisi_spi_nor_write(struct spi_nor *nor, loff_t to,
 static int hisi_spi_nor_register(struct device_node *np,
 				struct hifmc_host *host)
 {
+	const struct spi_nor_hwcaps hwcaps = {
+		.mask = SNOR_HWCAPS_READ |
+			SNOR_HWCAPS_READ_FAST |
+			SNOR_HWCAPS_READ_1_1_2 |
+			SNOR_HWCAPS_READ_1_1_4 |
+			SNOR_HWCAPS_PP,
+	};
 	struct device *dev = host->dev;
 	struct spi_nor *nor;
 	struct hifmc_priv *priv;
@@ -362,7 +377,7 @@ static int hisi_spi_nor_register(struct device_node *np,
 	nor->read = hisi_spi_nor_read;
 	nor->write = hisi_spi_nor_write;
 	nor->erase = NULL;
-	ret = spi_nor_scan(nor, NULL, SPI_NOR_QUAD);
+	ret = spi_nor_scan(nor, NULL, &hwcaps);
 	if (ret)
 		return ret;
 
diff --git a/drivers/mtd/spi-nor/intel-spi.c b/drivers/mtd/spi-nor/intel-spi.c
index 986a3d020a3a..8a596bfeddff 100644
--- a/drivers/mtd/spi-nor/intel-spi.c
+++ b/drivers/mtd/spi-nor/intel-spi.c
@@ -715,6 +715,11 @@ static void intel_spi_fill_partition(struct intel_spi *ispi,
 struct intel_spi *intel_spi_probe(struct device *dev,
 	struct resource *mem, const struct intel_spi_boardinfo *info)
 {
+	const struct spi_nor_hwcaps hwcaps = {
+		.mask = SNOR_HWCAPS_READ |
+			SNOR_HWCAPS_READ_FAST |
+			SNOR_HWCAPS_PP,
+	};
 	struct mtd_partition part;
 	struct intel_spi *ispi;
 	int ret;
@@ -746,7 +751,7 @@ struct intel_spi *intel_spi_probe(struct device *dev,
 	ispi->nor.write = intel_spi_write;
 	ispi->nor.erase = intel_spi_erase;
 
-	ret = spi_nor_scan(&ispi->nor, NULL, SPI_NOR_NORMAL);
+	ret = spi_nor_scan(&ispi->nor, NULL, &hwcaps);
 	if (ret) {
 		dev_info(dev, "failed to locate the chip\n");
 		return ERR_PTR(ret);
diff --git a/drivers/mtd/spi-nor/mtk-quadspi.c b/drivers/mtd/spi-nor/mtk-quadspi.c
index b6377707ce32..8a20ec4991c8 100644
--- a/drivers/mtd/spi-nor/mtk-quadspi.c
+++ b/drivers/mtd/spi-nor/mtk-quadspi.c
@@ -123,20 +123,20 @@ static void mt8173_nor_set_read_mode(struct mt8173_nor *mt8173_nor)
 {
 	struct spi_nor *nor = &mt8173_nor->nor;
 
-	switch (nor->flash_read) {
-	case SPI_NOR_FAST:
+	switch (nor->read_proto) {
+	case SNOR_PROTO_1_1_1:
 		writeb(nor->read_opcode, mt8173_nor->base +
 		       MTK_NOR_PRGDATA3_REG);
 		writeb(MTK_NOR_FAST_READ, mt8173_nor->base +
 		       MTK_NOR_CFG1_REG);
 		break;
-	case SPI_NOR_DUAL:
+	case SNOR_PROTO_1_1_2:
 		writeb(nor->read_opcode, mt8173_nor->base +
 		       MTK_NOR_PRGDATA3_REG);
 		writeb(MTK_NOR_DUAL_READ_EN, mt8173_nor->base +
 		       MTK_NOR_DUAL_REG);
 		break;
-	case SPI_NOR_QUAD:
+	case SNOR_PROTO_1_1_4:
 		writeb(nor->read_opcode, mt8173_nor->base +
 		       MTK_NOR_PRGDATA4_REG);
 		writeb(MTK_NOR_QUAD_READ_EN, mt8173_nor->base +
@@ -408,6 +408,11 @@ static int mt8173_nor_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf,
 static int mtk_nor_init(struct mt8173_nor *mt8173_nor,
 			struct device_node *flash_node)
 {
+	const struct spi_nor_hwcaps hwcaps = {
+		.mask = SNOR_HWCAPS_READ_FAST |
+			SNOR_HWCAPS_READ_1_1_2 |
+			SNOR_HWCAPS_PP,
+	};
 	int ret;
 	struct spi_nor *nor;
 
@@ -426,7 +431,7 @@ static int mtk_nor_init(struct mt8173_nor *mt8173_nor,
 	nor->write_reg = mt8173_nor_write_reg;
 	nor->mtd.name = "mtk_nor";
 	/* initialized with NULL */
-	ret = spi_nor_scan(nor, NULL, SPI_NOR_DUAL);
+	ret = spi_nor_scan(nor, NULL, &hwcaps);
 	if (ret)
 		return ret;
 
diff --git a/drivers/mtd/spi-nor/nxp-spifi.c b/drivers/mtd/spi-nor/nxp-spifi.c
index 73a14f40928b..15374216d4d9 100644
--- a/drivers/mtd/spi-nor/nxp-spifi.c
+++ b/drivers/mtd/spi-nor/nxp-spifi.c
@@ -240,13 +240,12 @@ static int nxp_spifi_erase(struct spi_nor *nor, loff_t offs)
 
 static int nxp_spifi_setup_memory_cmd(struct nxp_spifi *spifi)
 {
-	switch (spifi->nor.flash_read) {
-	case SPI_NOR_NORMAL:
-	case SPI_NOR_FAST:
+	switch (spifi->nor.read_proto) {
+	case SNOR_PROTO_1_1_1:
 		spifi->mcmd = SPIFI_CMD_FIELDFORM_ALL_SERIAL;
 		break;
-	case SPI_NOR_DUAL:
-	case SPI_NOR_QUAD:
+	case SNOR_PROTO_1_1_2:
+	case SNOR_PROTO_1_1_4:
 		spifi->mcmd = SPIFI_CMD_FIELDFORM_QUAD_DUAL_DATA;
 		break;
 	default:
@@ -274,7 +273,11 @@ static void nxp_spifi_dummy_id_read(struct spi_nor *nor)
 static int nxp_spifi_setup_flash(struct nxp_spifi *spifi,
 				 struct device_node *np)
 {
-	enum read_mode flash_read;
+	struct spi_nor_hwcaps hwcaps = {
+		.mask = SNOR_HWCAPS_READ |
+			SNOR_HWCAPS_READ_FAST |
+			SNOR_HWCAPS_PP,
+	};
 	u32 ctrl, property;
 	u16 mode = 0;
 	int ret;
@@ -308,13 +311,12 @@ static int nxp_spifi_setup_flash(struct nxp_spifi *spifi,
 
 	if (mode & SPI_RX_DUAL) {
 		ctrl |= SPIFI_CTRL_DUAL;
-		flash_read = SPI_NOR_DUAL;
+		hwcaps.mask |= SNOR_HWCAPS_READ_1_1_2;
 	} else if (mode & SPI_RX_QUAD) {
 		ctrl &= ~SPIFI_CTRL_DUAL;
-		flash_read = SPI_NOR_QUAD;
+		hwcaps.mask |= SNOR_HWCAPS_READ_1_1_4;
 	} else {
 		ctrl |= SPIFI_CTRL_DUAL;
-		flash_read = SPI_NOR_NORMAL;
 	}
 
 	switch (mode & (SPI_CPHA | SPI_CPOL)) {
@@ -351,7 +353,7 @@ static int nxp_spifi_setup_flash(struct nxp_spifi *spifi,
 	 */
 	nxp_spifi_dummy_id_read(&spifi->nor);
 
-	ret = spi_nor_scan(&spifi->nor, NULL, flash_read);
+	ret = spi_nor_scan(&spifi->nor, NULL, &hwcaps);
 	if (ret) {
 		dev_err(spifi->dev, "device scan failed\n");
 		return ret;
diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
index dea8c9cbadf0..e653806070a1 100644
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -149,24 +149,6 @@ static int read_cr(struct spi_nor *nor)
 	return val;
 }
 
-/*
- * Dummy Cycle calculation for different type of read.
- * It can be used to support more commands with
- * different dummy cycle requirements.
- */
-static inline int spi_nor_read_dummy_cycles(struct spi_nor *nor)
-{
-	switch (nor->flash_read) {
-	case SPI_NOR_FAST:
-	case SPI_NOR_DUAL:
-	case SPI_NOR_QUAD:
-		return 8;
-	case SPI_NOR_NORMAL:
-		return 0;
-	}
-	return 0;
-}
-
 /*
  * Write status register 1 byte
  * Returns negative if error occurred.
@@ -1460,30 +1442,6 @@ static int spansion_quad_enable(struct spi_nor *nor)
 	return 0;
 }
 
-static int set_quad_mode(struct spi_nor *nor, const struct flash_info *info)
-{
-	int status;
-
-	switch (JEDEC_MFR(info)) {
-	case SNOR_MFR_MACRONIX:
-		status = macronix_quad_enable(nor);
-		if (status) {
-			dev_err(nor->dev, "Macronix quad-read not enabled\n");
-			return -EINVAL;
-		}
-		return status;
-	case SNOR_MFR_MICRON:
-		return 0;
-	default:
-		status = spansion_quad_enable(nor);
-		if (status) {
-			dev_err(nor->dev, "Spansion quad-read not enabled\n");
-			return -EINVAL;
-		}
-		return status;
-	}
-}
-
 static int spi_nor_check(struct spi_nor *nor)
 {
 	if (!nor->dev || !nor->read || !nor->write ||
@@ -1536,8 +1494,323 @@ static int s3an_nor_scan(const struct flash_info *info, struct spi_nor *nor)
 	return 0;
 }
 
-int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode)
+struct spi_nor_read_command {
+	u8			num_mode_clocks;
+	u8			num_wait_states;
+	u8			opcode;
+	enum spi_nor_protocol	proto;
+};
+
+struct spi_nor_pp_command {
+	u8			opcode;
+	enum spi_nor_protocol	proto;
+};
+
+enum spi_nor_read_command_index {
+	SNOR_CMD_READ,
+	SNOR_CMD_READ_FAST,
+
+	/* Dual SPI */
+	SNOR_CMD_READ_1_1_2,
+	SNOR_CMD_READ_1_2_2,
+	SNOR_CMD_READ_2_2_2,
+
+	/* Quad SPI */
+	SNOR_CMD_READ_1_1_4,
+	SNOR_CMD_READ_1_4_4,
+	SNOR_CMD_READ_4_4_4,
+
+	SNOR_CMD_READ_MAX
+};
+
+enum spi_nor_pp_command_index {
+	SNOR_CMD_PP,
+
+	/* Quad SPI */
+	SNOR_CMD_PP_1_1_4,
+	SNOR_CMD_PP_1_4_4,
+	SNOR_CMD_PP_4_4_4,
+
+	SNOR_CMD_PP_MAX
+};
+
+struct spi_nor_flash_parameter {
+	u64				size;
+	u32				page_size;
+
+	struct spi_nor_hwcaps		hwcaps;
+	struct spi_nor_read_command	reads[SNOR_CMD_READ_MAX];
+	struct spi_nor_pp_command	page_programs[SNOR_CMD_PP_MAX];
+
+	int (*quad_enable)(struct spi_nor *nor);
+};
+
+static void
+spi_nor_set_read_settings(struct spi_nor_read_command *read,
+			  u8 num_mode_clocks,
+			  u8 num_wait_states,
+			  u8 opcode,
+			  enum spi_nor_protocol proto)
+{
+	read->num_mode_clocks = num_mode_clocks;
+	read->num_wait_states = num_wait_states;
+	read->opcode = opcode;
+	read->proto = proto;
+}
+
+static void
+spi_nor_set_pp_settings(struct spi_nor_pp_command *pp,
+			u8 opcode,
+			enum spi_nor_protocol proto)
+{
+	pp->opcode = opcode;
+	pp->proto = proto;
+}
+
+static int spi_nor_init_params(struct spi_nor *nor,
+			       const struct flash_info *info,
+			       struct spi_nor_flash_parameter *params)
+{
+	/* Set legacy flash parameters as default. */
+	memset(params, 0, sizeof(*params));
+
+	/* Set SPI NOR sizes. */
+	params->size = info->sector_size * info->n_sectors;
+	params->page_size = info->page_size;
+
+	/* (Fast) Read settings. */
+	params->hwcaps.mask |= SNOR_HWCAPS_READ;
+	spi_nor_set_read_settings(&params->reads[SNOR_CMD_READ],
+				  0, 0, SPINOR_OP_READ,
+				  SNOR_PROTO_1_1_1);
+
+	if (!(info->flags & SPI_NOR_NO_FR)) {
+		params->hwcaps.mask |= SNOR_HWCAPS_READ_FAST;
+		spi_nor_set_read_settings(&params->reads[SNOR_CMD_READ_FAST],
+					  0, 8, SPINOR_OP_READ_FAST,
+					  SNOR_PROTO_1_1_1);
+	}
+
+	if (info->flags & SPI_NOR_DUAL_READ) {
+		params->hwcaps.mask |= SNOR_HWCAPS_READ_1_1_2;
+		spi_nor_set_read_settings(&params->reads[SNOR_CMD_READ_1_1_2],
+					  0, 8, SPINOR_OP_READ_1_1_2,
+					  SNOR_PROTO_1_1_2);
+	}
+
+	if (info->flags & SPI_NOR_QUAD_READ) {
+		params->hwcaps.mask |= SNOR_HWCAPS_READ_1_1_4;
+		spi_nor_set_read_settings(&params->reads[SNOR_CMD_READ_1_1_4],
+					  0, 8, SPINOR_OP_READ_1_1_4,
+					  SNOR_PROTO_1_1_4);
+	}
+
+	/* Page Program settings. */
+	params->hwcaps.mask |= SNOR_HWCAPS_PP;
+	spi_nor_set_pp_settings(&params->page_programs[SNOR_CMD_PP],
+				SPINOR_OP_PP, SNOR_PROTO_1_1_1);
+
+	/* Select the procedure to set the Quad Enable bit. */
+	if (params->hwcaps.mask & (SNOR_HWCAPS_READ_QUAD |
+				   SNOR_HWCAPS_PP_QUAD)) {
+		switch (JEDEC_MFR(info)) {
+		case SNOR_MFR_MACRONIX:
+			params->quad_enable = macronix_quad_enable;
+			break;
+
+		case SNOR_MFR_MICRON:
+			break;
+
+		default:
+			params->quad_enable = spansion_quad_enable;
+			break;
+		}
+	}
+
+	return 0;
+}
+
+static int spi_nor_hwcaps2cmd(u32 hwcaps, const int table[][2], size_t size)
+{
+	size_t i;
+
+	for (i = 0; i < size; i++)
+		if (table[i][0] == (int)hwcaps)
+			return table[i][1];
+
+	return -EINVAL;
+}
+
+static int spi_nor_hwcaps_read2cmd(u32 hwcaps)
+{
+	static const int hwcaps_read2cmd[][2] = {
+		{ SNOR_HWCAPS_READ,		SNOR_CMD_READ },
+		{ SNOR_HWCAPS_READ_FAST,	SNOR_CMD_READ_FAST },
+		{ SNOR_HWCAPS_READ_1_1_2,	SNOR_CMD_READ_1_1_2 },
+		{ SNOR_HWCAPS_READ_1_2_2,	SNOR_CMD_READ_1_2_2 },
+		{ SNOR_HWCAPS_READ_2_2_2,	SNOR_CMD_READ_2_2_2 },
+		{ SNOR_HWCAPS_READ_1_1_4,	SNOR_CMD_READ_1_1_4 },
+		{ SNOR_HWCAPS_READ_1_4_4,	SNOR_CMD_READ_1_4_4 },
+		{ SNOR_HWCAPS_READ_4_4_4,	SNOR_CMD_READ_4_4_4 },
+	};
+
+	return spi_nor_hwcaps2cmd(hwcaps, hwcaps_read2cmd,
+				  ARRAY_SIZE(hwcaps_read2cmd));
+}
+
+static int spi_nor_hwcaps_pp2cmd(u32 hwcaps)
+{
+	static const int hwcaps_pp2cmd[][2] = {
+		{ SNOR_HWCAPS_PP,		SNOR_CMD_PP },
+		{ SNOR_HWCAPS_PP_1_1_4,		SNOR_CMD_PP_1_1_4 },
+		{ SNOR_HWCAPS_PP_1_4_4,		SNOR_CMD_PP_1_4_4 },
+		{ SNOR_HWCAPS_PP_4_4_4,		SNOR_CMD_PP_4_4_4 },
+	};
+
+	return spi_nor_hwcaps2cmd(hwcaps, hwcaps_pp2cmd,
+				  ARRAY_SIZE(hwcaps_pp2cmd));
+}
+
+static int spi_nor_select_read(struct spi_nor *nor,
+			       const struct spi_nor_flash_parameter *params,
+			       u32 shared_hwcaps)
+{
+	int cmd, best_match = fls(shared_hwcaps & SNOR_HWCAPS_READ_MASK) - 1;
+	const struct spi_nor_read_command *read;
+
+	if (best_match < 0)
+		return -EINVAL;
+
+	cmd = spi_nor_hwcaps_read2cmd(BIT(best_match));
+	if (cmd < 0)
+		return -EINVAL;
+
+	read = &params->reads[cmd];
+	nor->read_opcode = read->opcode;
+	nor->read_proto = read->proto;
+
+	/*
+	 * In the spi-nor framework, we don't need to make the difference
+	 * between mode clock cycles and wait state clock cycles.
+	 * Indeed, the value of the mode clock cycles is used by a QSPI
+	 * flash memory to know whether it should enter or leave its 0-4-4
+	 * (Continuous Read / XIP) mode.
+	 * eXecution In Place is out of the scope of the mtd sub-system.
+	 * Hence we choose to merge both mode and wait state clock cycles
+	 * into the so called dummy clock cycles.
+	 */
+	nor->read_dummy = read->num_mode_clocks + read->num_wait_states;
+	return 0;
+}
+
+static int spi_nor_select_pp(struct spi_nor *nor,
+			     const struct spi_nor_flash_parameter *params,
+			     u32 shared_hwcaps)
+{
+	int cmd, best_match = fls(shared_hwcaps & SNOR_HWCAPS_PP_MASK) - 1;
+	const struct spi_nor_pp_command *pp;
+
+	if (best_match < 0)
+		return -EINVAL;
+
+	cmd = spi_nor_hwcaps_pp2cmd(BIT(best_match));
+	if (cmd < 0)
+		return -EINVAL;
+
+	pp = &params->page_programs[cmd];
+	nor->program_opcode = pp->opcode;
+	nor->write_proto = pp->proto;
+	return 0;
+}
+
+static int spi_nor_select_erase(struct spi_nor *nor,
+				const struct flash_info *info)
+{
+	struct mtd_info *mtd = &nor->mtd;
+
+#ifdef CONFIG_MTD_SPI_NOR_USE_4K_SECTORS
+	/* prefer "small sector" erase if possible */
+	if (info->flags & SECT_4K) {
+		nor->erase_opcode = SPINOR_OP_BE_4K;
+		mtd->erasesize = 4096;
+	} else if (info->flags & SECT_4K_PMC) {
+		nor->erase_opcode = SPINOR_OP_BE_4K_PMC;
+		mtd->erasesize = 4096;
+	} else
+#endif
+	{
+		nor->erase_opcode = SPINOR_OP_SE;
+		mtd->erasesize = info->sector_size;
+	}
+	return 0;
+}
+
+static int spi_nor_setup(struct spi_nor *nor, const struct flash_info *info,
+			 const struct spi_nor_flash_parameter *params,
+			 const struct spi_nor_hwcaps *hwcaps)
+{
+	u32 ignored_mask, shared_mask;
+	bool enable_quad_io;
+	int err;
+
+	/*
+	 * Keep only the hardware capabilities supported by both the SPI
+	 * controller and the SPI flash memory.
+	 */
+	shared_mask = hwcaps->mask & params->hwcaps.mask;
+
+	/* SPI n-n-n protocols are not supported yet. */
+	ignored_mask = (SNOR_HWCAPS_READ_2_2_2 |
+			SNOR_HWCAPS_READ_4_4_4 |
+			SNOR_HWCAPS_PP_4_4_4);
+	if (shared_mask & ignored_mask) {
+		dev_dbg(nor->dev,
+			"SPI n-n-n protocols are not supported yet.\n");
+		shared_mask &= ~ignored_mask;
+	}
+
+	/* Select the (Fast) Read command. */
+	err = spi_nor_select_read(nor, params, shared_mask);
+	if (err) {
+		dev_err(nor->dev,
+			"can't select read settings supported by both the SPI controller and memory.\n");
+		return err;
+	}
+
+	/* Select the Page Program command. */
+	err = spi_nor_select_pp(nor, params, shared_mask);
+	if (err) {
+		dev_err(nor->dev,
+			"can't select write settings supported by both the SPI controller and memory.\n");
+		return err;
+	}
+
+	/* Select the Sector Erase command. */
+	err = spi_nor_select_erase(nor, info);
+	if (err) {
+		dev_err(nor->dev,
+			"can't select erase settings supported by both the SPI controller and memory.\n");
+		return err;
+	}
+
+	/* Enable Quad I/O if needed. */
+	enable_quad_io = (spi_nor_get_protocol_width(nor->read_proto) == 4 ||
+			  spi_nor_get_protocol_width(nor->write_proto) == 4);
+	if (enable_quad_io && params->quad_enable) {
+		err = params->quad_enable(nor);
+		if (err) {
+			dev_err(nor->dev, "quad mode not supported\n");
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+int spi_nor_scan(struct spi_nor *nor, const char *name,
+		 const struct spi_nor_hwcaps *hwcaps)
 {
+	struct spi_nor_flash_parameter params;
 	const struct flash_info *info = NULL;
 	struct device *dev = nor->dev;
 	struct mtd_info *mtd = &nor->mtd;
@@ -1549,6 +1822,11 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode)
 	if (ret)
 		return ret;
 
+	/* Reset SPI protocol for all commands. */
+	nor->reg_proto = SNOR_PROTO_1_1_1;
+	nor->read_proto = SNOR_PROTO_1_1_1;
+	nor->write_proto = SNOR_PROTO_1_1_1;
+
 	if (name)
 		info = spi_nor_match_id(name);
 	/* Try to auto-detect if chip name wasn't specified or not found */
@@ -1591,6 +1869,11 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode)
 	if (info->flags & SPI_S3AN)
 		nor->flags |=  SNOR_F_READY_XSR_RDY;
 
+	/* Parse the Serial Flash Discoverable Parameters table. */
+	ret = spi_nor_init_params(nor, info, &params);
+	if (ret)
+		return ret;
+
 	/*
 	 * Atmel, SST, Intel/Numonyx, and others serial NOR tend to power up
 	 * with the software protection bits set
@@ -1611,7 +1894,7 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode)
 	mtd->type = MTD_NORFLASH;
 	mtd->writesize = 1;
 	mtd->flags = MTD_CAP_NORFLASH;
-	mtd->size = info->sector_size * info->n_sectors;
+	mtd->size = params.size;
 	mtd->_erase = spi_nor_erase;
 	mtd->_read = spi_nor_read;
 
@@ -1642,75 +1925,38 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode)
 	if (info->flags & NO_CHIP_ERASE)
 		nor->flags |= SNOR_F_NO_OP_CHIP_ERASE;
 
-#ifdef CONFIG_MTD_SPI_NOR_USE_4K_SECTORS
-	/* prefer "small sector" erase if possible */
-	if (info->flags & SECT_4K) {
-		nor->erase_opcode = SPINOR_OP_BE_4K;
-		mtd->erasesize = 4096;
-	} else if (info->flags & SECT_4K_PMC) {
-		nor->erase_opcode = SPINOR_OP_BE_4K_PMC;
-		mtd->erasesize = 4096;
-	} else
-#endif
-	{
-		nor->erase_opcode = SPINOR_OP_SE;
-		mtd->erasesize = info->sector_size;
-	}
-
 	if (info->flags & SPI_NOR_NO_ERASE)
 		mtd->flags |= MTD_NO_ERASE;
 
 	mtd->dev.parent = dev;
-	nor->page_size = info->page_size;
+	nor->page_size = params.page_size;
 	mtd->writebufsize = nor->page_size;
 
 	if (np) {
 		/* If we were instantiated by DT, use it */
 		if (of_property_read_bool(np, "m25p,fast-read"))
-			nor->flash_read = SPI_NOR_FAST;
+			params.hwcaps.mask |= SNOR_HWCAPS_READ_FAST;
 		else
-			nor->flash_read = SPI_NOR_NORMAL;
+			params.hwcaps.mask &= ~SNOR_HWCAPS_READ_FAST;
 	} else {
 		/* If we weren't instantiated by DT, default to fast-read */
-		nor->flash_read = SPI_NOR_FAST;
+		params.hwcaps.mask |= SNOR_HWCAPS_READ_FAST;
 	}
 
 	/* Some devices cannot do fast-read, no matter what DT tells us */
 	if (info->flags & SPI_NOR_NO_FR)
-		nor->flash_read = SPI_NOR_NORMAL;
-
-	/* Quad/Dual-read mode takes precedence over fast/normal */
-	if (mode == SPI_NOR_QUAD && info->flags & SPI_NOR_QUAD_READ) {
-		ret = set_quad_mode(nor, info);
-		if (ret) {
-			dev_err(dev, "quad mode not supported\n");
-			return ret;
-		}
-		nor->flash_read = SPI_NOR_QUAD;
-	} else if (mode == SPI_NOR_DUAL && info->flags & SPI_NOR_DUAL_READ) {
-		nor->flash_read = SPI_NOR_DUAL;
-	}
-
-	/* Default commands */
-	switch (nor->flash_read) {
-	case SPI_NOR_QUAD:
-		nor->read_opcode = SPINOR_OP_READ_1_1_4;
-		break;
-	case SPI_NOR_DUAL:
-		nor->read_opcode = SPINOR_OP_READ_1_1_2;
-		break;
-	case SPI_NOR_FAST:
-		nor->read_opcode = SPINOR_OP_READ_FAST;
-		break;
-	case SPI_NOR_NORMAL:
-		nor->read_opcode = SPINOR_OP_READ;
-		break;
-	default:
-		dev_err(dev, "No Read opcode defined\n");
-		return -EINVAL;
-	}
+		params.hwcaps.mask &= ~SNOR_HWCAPS_READ_FAST;
 
-	nor->program_opcode = SPINOR_OP_PP;
+	/*
+	 * Configure the SPI memory:
+	 * - select op codes for (Fast) Read, Page Program and Sector Erase.
+	 * - set the number of dummy cycles (mode cycles + wait states).
+	 * - set the SPI protocols for register and memory accesses.
+	 * - set the Quad Enable bit if needed (required by SPI x-y-4 protos).
+	 */
+	ret = spi_nor_setup(nor, info, &params, hwcaps);
+	if (ret)
+		return ret;
 
 	if (info->addr_width)
 		nor->addr_width = info->addr_width;
@@ -1732,8 +1978,6 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode)
 		return -EINVAL;
 	}
 
-	nor->read_dummy = spi_nor_read_dummy_cycles(nor);
-
 	if (info->flags & SPI_S3AN) {
 		ret = s3an_nor_scan(info, nor);
 		if (ret)
diff --git a/drivers/mtd/spi-nor/stm32-quadspi.c b/drivers/mtd/spi-nor/stm32-quadspi.c
index ae45f81b8cd3..1056e7408d2a 100644
--- a/drivers/mtd/spi-nor/stm32-quadspi.c
+++ b/drivers/mtd/spi-nor/stm32-quadspi.c
@@ -192,15 +192,15 @@ static void stm32_qspi_set_framemode(struct spi_nor *nor,
 	cmd->framemode = CCR_IMODE_1;
 
 	if (read) {
-		switch (nor->flash_read) {
-		case SPI_NOR_NORMAL:
-		case SPI_NOR_FAST:
+		switch (nor->read_proto) {
+		default:
+		case SNOR_PROTO_1_1_1:
 			dmode = CCR_DMODE_1;
 			break;
-		case SPI_NOR_DUAL:
+		case SNOR_PROTO_1_1_2:
 			dmode = CCR_DMODE_2;
 			break;
-		case SPI_NOR_QUAD:
+		case SNOR_PROTO_1_1_4:
 			dmode = CCR_DMODE_4;
 			break;
 		}
@@ -480,7 +480,12 @@ static void stm32_qspi_unprep(struct spi_nor *nor, enum spi_nor_ops ops)
 static int stm32_qspi_flash_setup(struct stm32_qspi *qspi,
 				  struct device_node *np)
 {
-	u32 width, flash_read, presc, cs_num, max_rate = 0;
+	struct spi_nor_hwcaps hwcaps = {
+		.mask = SNOR_HWCAPS_READ |
+			SNOR_HWCAPS_READ_FAST |
+			SNOR_HWCAPS_PP,
+	};
+	u32 width, presc, cs_num, max_rate = 0;
 	struct stm32_qspi_flash *flash;
 	struct mtd_info *mtd;
 	int ret;
@@ -499,12 +504,10 @@ static int stm32_qspi_flash_setup(struct stm32_qspi *qspi,
 		width = 1;
 
 	if (width == 4)
-		flash_read = SPI_NOR_QUAD;
+		hwcaps.mask |= SNOR_HWCAPS_READ_1_1_4;
 	else if (width == 2)
-		flash_read = SPI_NOR_DUAL;
-	else if (width == 1)
-		flash_read = SPI_NOR_NORMAL;
-	else
+		hwcaps.mask |= SNOR_HWCAPS_READ_1_1_2;
+	else if (width != 1)
 		return -EINVAL;
 
 	flash = &qspi->flash[cs_num];
@@ -539,7 +542,7 @@ static int stm32_qspi_flash_setup(struct stm32_qspi *qspi,
 	 */
 	flash->fsize = FSIZE_VAL(SZ_1K);
 
-	ret = spi_nor_scan(&flash->nor, NULL, flash_read);
+	ret = spi_nor_scan(&flash->nor, NULL, &hwcaps);
 	if (ret) {
 		dev_err(qspi->dev, "device scan failed\n");
 		return ret;
diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h
index f2a718030476..60db1585f94c 100644
--- a/include/linux/mtd/spi-nor.h
+++ b/include/linux/mtd/spi-nor.h
@@ -119,13 +119,63 @@
 /* Configuration Register bits. */
 #define CR_QUAD_EN_SPAN		BIT(1)	/* Spansion Quad I/O */
 
-enum read_mode {
-	SPI_NOR_NORMAL = 0,
-	SPI_NOR_FAST,
-	SPI_NOR_DUAL,
-	SPI_NOR_QUAD,
+/* Supported SPI protocols */
+#define SNOR_PROTO_INST_MASK	GENMASK(23, 16)
+#define SNOR_PROTO_INST_SHIFT	16
+#define SNOR_PROTO_INST(_nbits)	\
+	((((unsigned long)(_nbits)) << SNOR_PROTO_INST_SHIFT) & \
+	 SNOR_PROTO_INST_MASK)
+
+#define SNOR_PROTO_ADDR_MASK	GENMASK(15, 8)
+#define SNOR_PROTO_ADDR_SHIFT	8
+#define SNOR_PROTO_ADDR(_nbits)	\
+	((((unsigned long)(_nbits)) << SNOR_PROTO_ADDR_SHIFT) & \
+	 SNOR_PROTO_ADDR_MASK)
+
+#define SNOR_PROTO_DATA_MASK	GENMASK(7, 0)
+#define SNOR_PROTO_DATA_SHIFT	0
+#define SNOR_PROTO_DATA(_nbits)	\
+	((((unsigned long)(_nbits)) << SNOR_PROTO_DATA_SHIFT) & \
+	 SNOR_PROTO_DATA_MASK)
+
+#define SNOR_PROTO_STR(_inst_nbits, _addr_nbits, _data_nbits)	\
+	(SNOR_PROTO_INST(_inst_nbits) |				\
+	 SNOR_PROTO_ADDR(_addr_nbits) |				\
+	 SNOR_PROTO_DATA(_data_nbits))
+
+enum spi_nor_protocol {
+	SNOR_PROTO_1_1_1 = SNOR_PROTO_STR(1, 1, 1),
+	SNOR_PROTO_1_1_2 = SNOR_PROTO_STR(1, 1, 2),
+	SNOR_PROTO_1_1_4 = SNOR_PROTO_STR(1, 1, 4),
+	SNOR_PROTO_1_2_2 = SNOR_PROTO_STR(1, 2, 2),
+	SNOR_PROTO_1_4_4 = SNOR_PROTO_STR(1, 4, 4),
+	SNOR_PROTO_2_2_2 = SNOR_PROTO_STR(2, 2, 2),
+	SNOR_PROTO_4_4_4 = SNOR_PROTO_STR(4, 4, 4),
 };
 
+static inline u8 spi_nor_get_protocol_inst_nbits(enum spi_nor_protocol proto)
+{
+	return ((unsigned long)(proto & SNOR_PROTO_INST_MASK)) >>
+		SNOR_PROTO_INST_SHIFT;
+}
+
+static inline u8 spi_nor_get_protocol_addr_nbits(enum spi_nor_protocol proto)
+{
+	return ((unsigned long)(proto & SNOR_PROTO_ADDR_MASK)) >>
+		SNOR_PROTO_ADDR_SHIFT;
+}
+
+static inline u8 spi_nor_get_protocol_data_nbits(enum spi_nor_protocol proto)
+{
+	return ((unsigned long)(proto & SNOR_PROTO_DATA_MASK)) >>
+		SNOR_PROTO_DATA_SHIFT;
+}
+
+static inline u8 spi_nor_get_protocol_width(enum spi_nor_protocol proto)
+{
+	return spi_nor_get_protocol_data_nbits(proto);
+}
+
 #define SPI_NOR_MAX_CMD_SIZE	8
 enum spi_nor_ops {
 	SPI_NOR_OPS_READ = 0,
@@ -154,9 +204,11 @@ enum spi_nor_option_flags {
  * @read_opcode:	the read opcode
  * @read_dummy:		the dummy needed by the read operation
  * @program_opcode:	the program opcode
- * @flash_read:		the mode of the read
  * @sst_write_second:	used by the SST write operation
  * @flags:		flag options for the current SPI-NOR (SNOR_F_*)
+ * @read_proto:		the SPI protocol for read operations
+ * @write_proto:	the SPI protocol for write operations
+ * @reg_proto		the SPI protocol for read_reg/write_reg/erase operations
  * @cmd_buf:		used by the write_reg
  * @prepare:		[OPTIONAL] do some preparations for the
  *			read/write/erase/lock/unlock operations
@@ -185,7 +237,9 @@ struct spi_nor {
 	u8			read_opcode;
 	u8			read_dummy;
 	u8			program_opcode;
-	enum read_mode		flash_read;
+	enum spi_nor_protocol	read_proto;
+	enum spi_nor_protocol	write_proto;
+	enum spi_nor_protocol	reg_proto;
 	bool			sst_write_second;
 	u32			flags;
 	u8			cmd_buf[SPI_NOR_MAX_CMD_SIZE];
@@ -219,11 +273,57 @@ static inline struct device_node *spi_nor_get_flash_node(struct spi_nor *nor)
 	return mtd_get_of_node(&nor->mtd);
 }
 
+/**
+ * struct spi_nor_hwcaps - Structure for describing the hardware capabilies
+ * supported by the SPI controller (bus master).
+ * @mask:		the bitmask listing all the supported hw capabilies
+ */
+struct spi_nor_hwcaps {
+	u32	mask;
+};
+
+/*
+ *(Fast) Read capabilities.
+ * MUST be ordered by priority: the higher bit position, the higher priority.
+ * As a matter of performances, it is relevant to use Quad SPI protocols first,
+ * then Dual SPI protocols before Fast Read and lastly (Slow) Read.
+ */
+#define SNOR_HWCAPS_READ_MASK		GENMASK(7, 0)
+#define SNOR_HWCAPS_READ		BIT(0)
+#define SNOR_HWCAPS_READ_FAST		BIT(1)
+
+#define SNOR_HWCAPS_READ_DUAL		GENMASK(4, 2)
+#define SNOR_HWCAPS_READ_1_1_2		BIT(2)
+#define SNOR_HWCAPS_READ_1_2_2		BIT(3)
+#define SNOR_HWCAPS_READ_2_2_2		BIT(4)
+
+#define SNOR_HWCAPS_READ_QUAD		GENMASK(7, 5)
+#define SNOR_HWCAPS_READ_1_1_4		BIT(5)
+#define SNOR_HWCAPS_READ_1_4_4		BIT(6)
+#define SNOR_HWCAPS_READ_4_4_4		BIT(7)
+
+/*
+ * Page Program capabilities.
+ * MUST be ordered by priority: the higher bit position, the higher priority.
+ * Like (Fast) Read capabilities, Quad SPI protocols are preferred to the
+ * legacy SPI 1-1-1 protocol.
+ * Note that Dual Page Programs are not supported because there is no existing
+ * JEDEC/SFDP standard to define them. Also at this moment no SPI flash memory
+ * implements such commands.
+ */
+#define SNOR_HWCAPS_PP_MASK	GENMASK(19, 16)
+#define SNOR_HWCAPS_PP		BIT(16)
+
+#define SNOR_HWCAPS_PP_QUAD	GENMASK(19, 17)
+#define SNOR_HWCAPS_PP_1_1_4	BIT(17)
+#define SNOR_HWCAPS_PP_1_4_4	BIT(18)
+#define SNOR_HWCAPS_PP_4_4_4	BIT(19)
+
 /**
  * spi_nor_scan() - scan the SPI NOR
  * @nor:	the spi_nor structure
  * @name:	the chip type name
- * @mode:	the read mode supported by the driver
+ * @hwcaps:	the hardware capabilities supported by the controller driver
  *
  * The drivers can use this fuction to scan the SPI NOR.
  * In the scanning, it will try to get all the necessary information to
@@ -233,6 +333,7 @@ static inline struct device_node *spi_nor_get_flash_node(struct spi_nor *nor)
  *
  * Return: 0 for success, others for failure.
  */
-int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode);
+int spi_nor_scan(struct spi_nor *nor, const char *name,
+		 const struct spi_nor_hwcaps *hwcaps);
 
 #endif
-- 
cgit v1.2.3


From 15f55331527b1422eae683477f8a31fdfae93316 Mon Sep 17 00:00:00 2001
From: Cyrille Pitchen <cyrille.pitchen@atmel.com>
Date: Tue, 25 Apr 2017 22:08:48 +0200
Subject: mtd: spi-nor: introduce Double Transfer Rate (DTR) SPI protocols

This patch introduces support to Double Transfer Rate (DTR) SPI protocols.
DTR is used only for Fast Read operations.

According to manufacturer datasheets, whatever the number of I/O lines
used during instruction (x) and address/mode/dummy (y) clock cycles, DTR
is used only during data (z) clock cycles of SPI x-y-z protocols.

Signed-off-by: Cyrille Pitchen <cyrille.pitchen@atmel.com>
Reviewed-by: Marek Vasut <marek.vasut@gmail.com>
---
 drivers/mtd/spi-nor/spi-nor.c | 10 +++++++++
 include/linux/mtd/spi-nor.h   | 48 +++++++++++++++++++++++++++++++++----------
 2 files changed, 47 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
index e653806070a1..2062a3abba72 100644
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -203,6 +203,10 @@ static inline u8 spi_nor_convert_3to4_read(u8 opcode)
 		{ SPINOR_OP_READ_1_2_2,	SPINOR_OP_READ_1_2_2_4B },
 		{ SPINOR_OP_READ_1_1_4,	SPINOR_OP_READ_1_1_4_4B },
 		{ SPINOR_OP_READ_1_4_4,	SPINOR_OP_READ_1_4_4_4B },
+
+		{ SPINOR_OP_READ_1_1_1_DTR,	SPINOR_OP_READ_1_1_1_DTR_4B },
+		{ SPINOR_OP_READ_1_2_2_DTR,	SPINOR_OP_READ_1_2_2_DTR_4B },
+		{ SPINOR_OP_READ_1_4_4_DTR,	SPINOR_OP_READ_1_4_4_DTR_4B },
 	};
 
 	return spi_nor_convert_opcode(opcode, spi_nor_3to4_read,
@@ -1509,16 +1513,19 @@ struct spi_nor_pp_command {
 enum spi_nor_read_command_index {
 	SNOR_CMD_READ,
 	SNOR_CMD_READ_FAST,
+	SNOR_CMD_READ_1_1_1_DTR,
 
 	/* Dual SPI */
 	SNOR_CMD_READ_1_1_2,
 	SNOR_CMD_READ_1_2_2,
 	SNOR_CMD_READ_2_2_2,
+	SNOR_CMD_READ_1_2_2_DTR,
 
 	/* Quad SPI */
 	SNOR_CMD_READ_1_1_4,
 	SNOR_CMD_READ_1_4_4,
 	SNOR_CMD_READ_4_4_4,
+	SNOR_CMD_READ_1_4_4_DTR,
 
 	SNOR_CMD_READ_MAX
 };
@@ -1646,12 +1653,15 @@ static int spi_nor_hwcaps_read2cmd(u32 hwcaps)
 	static const int hwcaps_read2cmd[][2] = {
 		{ SNOR_HWCAPS_READ,		SNOR_CMD_READ },
 		{ SNOR_HWCAPS_READ_FAST,	SNOR_CMD_READ_FAST },
+		{ SNOR_HWCAPS_READ_1_1_1_DTR,	SNOR_CMD_READ_1_1_1_DTR },
 		{ SNOR_HWCAPS_READ_1_1_2,	SNOR_CMD_READ_1_1_2 },
 		{ SNOR_HWCAPS_READ_1_2_2,	SNOR_CMD_READ_1_2_2 },
 		{ SNOR_HWCAPS_READ_2_2_2,	SNOR_CMD_READ_2_2_2 },
+		{ SNOR_HWCAPS_READ_1_2_2_DTR,	SNOR_CMD_READ_1_2_2_DTR },
 		{ SNOR_HWCAPS_READ_1_1_4,	SNOR_CMD_READ_1_1_4 },
 		{ SNOR_HWCAPS_READ_1_4_4,	SNOR_CMD_READ_1_4_4 },
 		{ SNOR_HWCAPS_READ_4_4_4,	SNOR_CMD_READ_4_4_4 },
+		{ SNOR_HWCAPS_READ_1_4_4_DTR,	SNOR_CMD_READ_1_4_4_DTR },
 	};
 
 	return spi_nor_hwcaps2cmd(hwcaps, hwcaps_read2cmd,
diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h
index 60db1585f94c..313dbe56f31a 100644
--- a/include/linux/mtd/spi-nor.h
+++ b/include/linux/mtd/spi-nor.h
@@ -73,6 +73,15 @@
 #define SPINOR_OP_BE_32K_4B	0x5c	/* Erase 32KiB block */
 #define SPINOR_OP_SE_4B		0xdc	/* Sector erase (usually 64KiB) */
 
+/* Double Transfer Rate opcodes - defined in JEDEC JESD216B. */
+#define SPINOR_OP_READ_1_1_1_DTR	0x0d
+#define SPINOR_OP_READ_1_2_2_DTR	0xbd
+#define SPINOR_OP_READ_1_4_4_DTR	0xed
+
+#define SPINOR_OP_READ_1_1_1_DTR_4B	0x0e
+#define SPINOR_OP_READ_1_2_2_DTR_4B	0xbe
+#define SPINOR_OP_READ_1_4_4_DTR_4B	0xee
+
 /* Used for SST flashes only. */
 #define SPINOR_OP_BP		0x02	/* Byte program */
 #define SPINOR_OP_WRDI		0x04	/* Write disable */
@@ -138,10 +147,15 @@
 	((((unsigned long)(_nbits)) << SNOR_PROTO_DATA_SHIFT) & \
 	 SNOR_PROTO_DATA_MASK)
 
+#define SNOR_PROTO_IS_DTR	BIT(24)	/* Double Transfer Rate */
+
 #define SNOR_PROTO_STR(_inst_nbits, _addr_nbits, _data_nbits)	\
 	(SNOR_PROTO_INST(_inst_nbits) |				\
 	 SNOR_PROTO_ADDR(_addr_nbits) |				\
 	 SNOR_PROTO_DATA(_data_nbits))
+#define SNOR_PROTO_DTR(_inst_nbits, _addr_nbits, _data_nbits)	\
+	(SNOR_PROTO_IS_DTR |					\
+	 SNOR_PROTO_STR(_inst_nbits, _addr_nbits, _data_nbits))
 
 enum spi_nor_protocol {
 	SNOR_PROTO_1_1_1 = SNOR_PROTO_STR(1, 1, 1),
@@ -151,8 +165,17 @@ enum spi_nor_protocol {
 	SNOR_PROTO_1_4_4 = SNOR_PROTO_STR(1, 4, 4),
 	SNOR_PROTO_2_2_2 = SNOR_PROTO_STR(2, 2, 2),
 	SNOR_PROTO_4_4_4 = SNOR_PROTO_STR(4, 4, 4),
+
+	SNOR_PROTO_1_1_1_DTR = SNOR_PROTO_DTR(1, 1, 1),
+	SNOR_PROTO_1_2_2_DTR = SNOR_PROTO_DTR(1, 2, 2),
+	SNOR_PROTO_1_4_4_DTR = SNOR_PROTO_DTR(1, 4, 4),
 };
 
+static inline bool spi_nor_protocol_is_dtr(enum spi_nor_protocol proto)
+{
+	return !!(proto & SNOR_PROTO_IS_DTR);
+}
+
 static inline u8 spi_nor_get_protocol_inst_nbits(enum spi_nor_protocol proto)
 {
 	return ((unsigned long)(proto & SNOR_PROTO_INST_MASK)) >>
@@ -288,19 +311,22 @@ struct spi_nor_hwcaps {
  * As a matter of performances, it is relevant to use Quad SPI protocols first,
  * then Dual SPI protocols before Fast Read and lastly (Slow) Read.
  */
-#define SNOR_HWCAPS_READ_MASK		GENMASK(7, 0)
+#define SNOR_HWCAPS_READ_MASK		GENMASK(10, 0)
 #define SNOR_HWCAPS_READ		BIT(0)
 #define SNOR_HWCAPS_READ_FAST		BIT(1)
-
-#define SNOR_HWCAPS_READ_DUAL		GENMASK(4, 2)
-#define SNOR_HWCAPS_READ_1_1_2		BIT(2)
-#define SNOR_HWCAPS_READ_1_2_2		BIT(3)
-#define SNOR_HWCAPS_READ_2_2_2		BIT(4)
-
-#define SNOR_HWCAPS_READ_QUAD		GENMASK(7, 5)
-#define SNOR_HWCAPS_READ_1_1_4		BIT(5)
-#define SNOR_HWCAPS_READ_1_4_4		BIT(6)
-#define SNOR_HWCAPS_READ_4_4_4		BIT(7)
+#define SNOR_HWCAPS_READ_1_1_1_DTR	BIT(2)
+
+#define SNOR_HWCAPS_READ_DUAL		GENMASK(6, 3)
+#define SNOR_HWCAPS_READ_1_1_2		BIT(3)
+#define SNOR_HWCAPS_READ_1_2_2		BIT(4)
+#define SNOR_HWCAPS_READ_2_2_2		BIT(5)
+#define SNOR_HWCAPS_READ_1_2_2_DTR	BIT(6)
+
+#define SNOR_HWCAPS_READ_QUAD		GENMASK(10, 7)
+#define SNOR_HWCAPS_READ_1_1_4		BIT(7)
+#define SNOR_HWCAPS_READ_1_4_4		BIT(8)
+#define SNOR_HWCAPS_READ_4_4_4		BIT(9)
+#define SNOR_HWCAPS_READ_1_4_4_DTR	BIT(10)
 
 /*
  * Page Program capabilities.
-- 
cgit v1.2.3


From fe488a5e48c69204c3b1ad6fa3282e12dbfaabe7 Mon Sep 17 00:00:00 2001
From: Cyrille Pitchen <cyrille.pitchen@atmel.com>
Date: Tue, 25 Apr 2017 22:08:49 +0200
Subject: mtd: spi-nor: introduce Octo SPI protocols

This patch starts adding support to Octo SPI protocols (SPI x-y-8).

Op codes for Fast Read and/or Page Program operations using Octo SPI
protocols are not known yet (no JEDEC specification has defined them yet)
but we'd rather introduce the Octo SPI protocols now so it's done as it
should be.

Signed-off-by: Cyrille Pitchen <cyrille.pitchen@atmel.com>
Reviewed-by: Marek Vasut <marek.vasut@gmail.com>
---
 drivers/mtd/spi-nor/spi-nor.c | 22 +++++++++++++++++++++-
 include/linux/mtd/spi-nor.h   | 26 +++++++++++++++++++++-----
 2 files changed, 42 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
index 2062a3abba72..060a59e716be 100644
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -1527,6 +1527,12 @@ enum spi_nor_read_command_index {
 	SNOR_CMD_READ_4_4_4,
 	SNOR_CMD_READ_1_4_4_DTR,
 
+	/* Octo SPI */
+	SNOR_CMD_READ_1_1_8,
+	SNOR_CMD_READ_1_8_8,
+	SNOR_CMD_READ_8_8_8,
+	SNOR_CMD_READ_1_8_8_DTR,
+
 	SNOR_CMD_READ_MAX
 };
 
@@ -1538,6 +1544,11 @@ enum spi_nor_pp_command_index {
 	SNOR_CMD_PP_1_4_4,
 	SNOR_CMD_PP_4_4_4,
 
+	/* Octo SPI */
+	SNOR_CMD_PP_1_1_8,
+	SNOR_CMD_PP_1_8_8,
+	SNOR_CMD_PP_8_8_8,
+
 	SNOR_CMD_PP_MAX
 };
 
@@ -1662,6 +1673,10 @@ static int spi_nor_hwcaps_read2cmd(u32 hwcaps)
 		{ SNOR_HWCAPS_READ_1_4_4,	SNOR_CMD_READ_1_4_4 },
 		{ SNOR_HWCAPS_READ_4_4_4,	SNOR_CMD_READ_4_4_4 },
 		{ SNOR_HWCAPS_READ_1_4_4_DTR,	SNOR_CMD_READ_1_4_4_DTR },
+		{ SNOR_HWCAPS_READ_1_1_8,	SNOR_CMD_READ_1_1_8 },
+		{ SNOR_HWCAPS_READ_1_8_8,	SNOR_CMD_READ_1_8_8 },
+		{ SNOR_HWCAPS_READ_8_8_8,	SNOR_CMD_READ_8_8_8 },
+		{ SNOR_HWCAPS_READ_1_8_8_DTR,	SNOR_CMD_READ_1_8_8_DTR },
 	};
 
 	return spi_nor_hwcaps2cmd(hwcaps, hwcaps_read2cmd,
@@ -1675,6 +1690,9 @@ static int spi_nor_hwcaps_pp2cmd(u32 hwcaps)
 		{ SNOR_HWCAPS_PP_1_1_4,		SNOR_CMD_PP_1_1_4 },
 		{ SNOR_HWCAPS_PP_1_4_4,		SNOR_CMD_PP_1_4_4 },
 		{ SNOR_HWCAPS_PP_4_4_4,		SNOR_CMD_PP_4_4_4 },
+		{ SNOR_HWCAPS_PP_1_1_8,		SNOR_CMD_PP_1_1_8 },
+		{ SNOR_HWCAPS_PP_1_8_8,		SNOR_CMD_PP_1_8_8 },
+		{ SNOR_HWCAPS_PP_8_8_8,		SNOR_CMD_PP_8_8_8 },
 	};
 
 	return spi_nor_hwcaps2cmd(hwcaps, hwcaps_pp2cmd,
@@ -1772,7 +1790,9 @@ static int spi_nor_setup(struct spi_nor *nor, const struct flash_info *info,
 	/* SPI n-n-n protocols are not supported yet. */
 	ignored_mask = (SNOR_HWCAPS_READ_2_2_2 |
 			SNOR_HWCAPS_READ_4_4_4 |
-			SNOR_HWCAPS_PP_4_4_4);
+			SNOR_HWCAPS_READ_8_8_8 |
+			SNOR_HWCAPS_PP_4_4_4 |
+			SNOR_HWCAPS_PP_8_8_8);
 	if (shared_mask & ignored_mask) {
 		dev_dbg(nor->dev,
 			"SPI n-n-n protocols are not supported yet.\n");
diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h
index 313dbe56f31a..55faa2f07cca 100644
--- a/include/linux/mtd/spi-nor.h
+++ b/include/linux/mtd/spi-nor.h
@@ -161,14 +161,18 @@ enum spi_nor_protocol {
 	SNOR_PROTO_1_1_1 = SNOR_PROTO_STR(1, 1, 1),
 	SNOR_PROTO_1_1_2 = SNOR_PROTO_STR(1, 1, 2),
 	SNOR_PROTO_1_1_4 = SNOR_PROTO_STR(1, 1, 4),
+	SNOR_PROTO_1_1_8 = SNOR_PROTO_STR(1, 1, 8),
 	SNOR_PROTO_1_2_2 = SNOR_PROTO_STR(1, 2, 2),
 	SNOR_PROTO_1_4_4 = SNOR_PROTO_STR(1, 4, 4),
+	SNOR_PROTO_1_8_8 = SNOR_PROTO_STR(1, 8, 8),
 	SNOR_PROTO_2_2_2 = SNOR_PROTO_STR(2, 2, 2),
 	SNOR_PROTO_4_4_4 = SNOR_PROTO_STR(4, 4, 4),
+	SNOR_PROTO_8_8_8 = SNOR_PROTO_STR(8, 8, 8),
 
 	SNOR_PROTO_1_1_1_DTR = SNOR_PROTO_DTR(1, 1, 1),
 	SNOR_PROTO_1_2_2_DTR = SNOR_PROTO_DTR(1, 2, 2),
 	SNOR_PROTO_1_4_4_DTR = SNOR_PROTO_DTR(1, 4, 4),
+	SNOR_PROTO_1_8_8_DTR = SNOR_PROTO_DTR(1, 8, 8),
 };
 
 static inline bool spi_nor_protocol_is_dtr(enum spi_nor_protocol proto)
@@ -308,10 +312,11 @@ struct spi_nor_hwcaps {
 /*
  *(Fast) Read capabilities.
  * MUST be ordered by priority: the higher bit position, the higher priority.
- * As a matter of performances, it is relevant to use Quad SPI protocols first,
- * then Dual SPI protocols before Fast Read and lastly (Slow) Read.
+ * As a matter of performances, it is relevant to use Octo SPI protocols first,
+ * then Quad SPI protocols before Dual SPI protocols, Fast Read and lastly
+ * (Slow) Read.
  */
-#define SNOR_HWCAPS_READ_MASK		GENMASK(10, 0)
+#define SNOR_HWCAPS_READ_MASK		GENMASK(14, 0)
 #define SNOR_HWCAPS_READ		BIT(0)
 #define SNOR_HWCAPS_READ_FAST		BIT(1)
 #define SNOR_HWCAPS_READ_1_1_1_DTR	BIT(2)
@@ -328,16 +333,22 @@ struct spi_nor_hwcaps {
 #define SNOR_HWCAPS_READ_4_4_4		BIT(9)
 #define SNOR_HWCAPS_READ_1_4_4_DTR	BIT(10)
 
+#define SNOR_HWCPAS_READ_OCTO		GENMASK(14, 11)
+#define SNOR_HWCAPS_READ_1_1_8		BIT(11)
+#define SNOR_HWCAPS_READ_1_8_8		BIT(12)
+#define SNOR_HWCAPS_READ_8_8_8		BIT(13)
+#define SNOR_HWCAPS_READ_1_8_8_DTR	BIT(14)
+
 /*
  * Page Program capabilities.
  * MUST be ordered by priority: the higher bit position, the higher priority.
- * Like (Fast) Read capabilities, Quad SPI protocols are preferred to the
+ * Like (Fast) Read capabilities, Octo/Quad SPI protocols are preferred to the
  * legacy SPI 1-1-1 protocol.
  * Note that Dual Page Programs are not supported because there is no existing
  * JEDEC/SFDP standard to define them. Also at this moment no SPI flash memory
  * implements such commands.
  */
-#define SNOR_HWCAPS_PP_MASK	GENMASK(19, 16)
+#define SNOR_HWCAPS_PP_MASK	GENMASK(22, 16)
 #define SNOR_HWCAPS_PP		BIT(16)
 
 #define SNOR_HWCAPS_PP_QUAD	GENMASK(19, 17)
@@ -345,6 +356,11 @@ struct spi_nor_hwcaps {
 #define SNOR_HWCAPS_PP_1_4_4	BIT(18)
 #define SNOR_HWCAPS_PP_4_4_4	BIT(19)
 
+#define SNOR_HWCAPS_PP_OCTO	GENMASK(22, 20)
+#define SNOR_HWCAPS_PP_1_1_8	BIT(20)
+#define SNOR_HWCAPS_PP_1_8_8	BIT(21)
+#define SNOR_HWCAPS_PP_8_8_8	BIT(22)
+
 /**
  * spi_nor_scan() - scan the SPI NOR
  * @nor:	the spi_nor structure
-- 
cgit v1.2.3


From 15060aba717115dc9f204c02213a7c6bf341163e Mon Sep 17 00:00:00 2001
From: CQ Tang <cq.tang@intel.com>
Date: Wed, 10 May 2017 11:39:03 -0700
Subject: iommu/vt-d: Helper function to query if a pasid has any active users

A driver would need to know if there are any active references to a
a PASID before cleaning up its resources. This function helps check
if there are any active users of a PASID before it can perform any
recovery on that device.

To: Joerg Roedel <joro@8bytes.org>
To: linux-kernel@vger.kernel.org
To: David Woodhouse <dwmw2@infradead.org>
Cc: Jean-Phillipe Brucker <jean-philippe.brucker@arm.com>
Cc: iommu@lists.linux-foundation.org

Signed-off-by: CQ Tang <cq.tang@intel.com>
Signed-off-by: Ashok Raj <ashok.raj@intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/intel-svm.c | 30 ++++++++++++++++++++++++++++++
 include/linux/intel-svm.h | 20 ++++++++++++++++++++
 2 files changed, 50 insertions(+)

(limited to 'include')

diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c
index 23c427602c55..f167c0d84ebf 100644
--- a/drivers/iommu/intel-svm.c
+++ b/drivers/iommu/intel-svm.c
@@ -489,6 +489,36 @@ int intel_svm_unbind_mm(struct device *dev, int pasid)
 }
 EXPORT_SYMBOL_GPL(intel_svm_unbind_mm);
 
+int intel_svm_is_pasid_valid(struct device *dev, int pasid)
+{
+	struct intel_iommu *iommu;
+	struct intel_svm *svm;
+	int ret = -EINVAL;
+
+	mutex_lock(&pasid_mutex);
+	iommu = intel_svm_device_to_iommu(dev);
+	if (!iommu || !iommu->pasid_table)
+		goto out;
+
+	svm = idr_find(&iommu->pasid_idr, pasid);
+	if (!svm)
+		goto out;
+
+	/* init_mm is used in this case */
+	if (!svm->mm)
+		ret = 1;
+	else if (atomic_read(&svm->mm->mm_users) > 0)
+		ret = 1;
+	else
+		ret = 0;
+
+ out:
+	mutex_unlock(&pasid_mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(intel_svm_is_pasid_valid);
+
 /* Page request queue descriptor */
 struct page_req_dsc {
 	u64 srr:1;
diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h
index 3c25794042f9..99bc5b3ae26e 100644
--- a/include/linux/intel-svm.h
+++ b/include/linux/intel-svm.h
@@ -102,6 +102,21 @@ extern int intel_svm_bind_mm(struct device *dev, int *pasid, int flags,
  */
 extern int intel_svm_unbind_mm(struct device *dev, int pasid);
 
+/**
+ * intel_svm_is_pasid_valid() - check if pasid is valid
+ * @dev:	Device for which PASID was allocated
+ * @pasid:	PASID value to be checked
+ *
+ * This function checks if the specified pasid is still valid. A
+ * valid pasid means the backing mm is still having a valid user.
+ * For kernel callers init_mm is always valid. for other mm, if mm->mm_users
+ * is non-zero, it is valid.
+ *
+ * returns -EINVAL if invalid pasid, 0 if pasid ref count is invalid
+ * 1 if pasid is valid.
+ */
+extern int intel_svm_is_pasid_valid(struct device *dev, int pasid);
+
 #else /* CONFIG_INTEL_IOMMU_SVM */
 
 static inline int intel_svm_bind_mm(struct device *dev, int *pasid,
@@ -114,6 +129,11 @@ static inline int intel_svm_unbind_mm(struct device *dev, int pasid)
 {
 	BUG();
 }
+
+static int intel_svm_is_pasid_valid(struct device *dev, int pasid)
+{
+	return -EINVAL;
+}
 #endif /* CONFIG_INTEL_IOMMU_SVM */
 
 #define intel_svm_available(dev) (!intel_svm_bind_mm((dev), NULL, 0, NULL))
-- 
cgit v1.2.3


From b9109b0e49b93b0ae663330acb36561b8f4f6905 Mon Sep 17 00:00:00 2001
From: Jaegeuk Kim <jaegeuk@kernel.org>
Date: Wed, 10 May 2017 11:28:38 -0700
Subject: f2fs: remove unnecessary read cases in merged IO flow

Merged IO flow doesn't need to care about read IOs.

f2fs_submit_merged_bio -> f2fs_submit_merged_write
f2fs_submit_merged_bios -> f2fs_submit_merged_writes
f2fs_submit_merged_bio_cond -> f2fs_submit_merged_write_cond

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/checkpoint.c        | 14 ++++++------
 fs/f2fs/data.c              | 55 ++++++++++++++++++++-------------------------
 fs/f2fs/f2fs.h              | 12 +++++-----
 fs/f2fs/gc.c                |  6 ++---
 fs/f2fs/node.c              | 11 +++++----
 fs/f2fs/segment.c           | 11 +++++----
 fs/f2fs/super.c             |  5 +----
 include/trace/events/f2fs.h |  2 +-
 8 files changed, 51 insertions(+), 65 deletions(-)

(limited to 'include')

diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 8d92f8249000..13828f63a871 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -31,7 +31,7 @@ void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io)
 	set_ckpt_flags(sbi, CP_ERROR_FLAG);
 	sbi->sb->s_flags |= MS_RDONLY;
 	if (!end_io)
-		f2fs_flush_merged_bios(sbi);
+		f2fs_flush_merged_writes(sbi);
 }
 
 /*
@@ -247,13 +247,13 @@ static int f2fs_write_meta_page(struct page *page,
 	dec_page_count(sbi, F2FS_DIRTY_META);
 
 	if (wbc->for_reclaim)
-		f2fs_submit_merged_bio_cond(sbi, page->mapping->host,
-						0, page->index, META, WRITE);
+		f2fs_submit_merged_write_cond(sbi, page->mapping->host,
+						0, page->index, META);
 
 	unlock_page(page);
 
 	if (unlikely(f2fs_cp_error(sbi)))
-		f2fs_submit_merged_bio(sbi, META, WRITE);
+		f2fs_submit_merged_write(sbi, META);
 
 	return 0;
 
@@ -356,7 +356,7 @@ continue_unlock:
 	}
 stop:
 	if (nwritten)
-		f2fs_submit_merged_bio(sbi, type, WRITE);
+		f2fs_submit_merged_write(sbi, type);
 
 	blk_finish_plug(&plug);
 
@@ -904,7 +904,7 @@ retry:
 		 * We should submit bio, since it exists several
 		 * wribacking dentry pages in the freeing inode.
 		 */
-		f2fs_submit_merged_bio(sbi, DATA, WRITE);
+		f2fs_submit_merged_write(sbi, DATA);
 		cond_resched();
 	}
 	goto retry;
@@ -1293,7 +1293,7 @@ int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish block_ops");
 
-	f2fs_flush_merged_bios(sbi);
+	f2fs_flush_merged_writes(sbi);
 
 	/* this is the case of multiple fstrims without any changes */
 	if (cpc->reason & CP_DISCARD) {
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 7c0f6bdf817d..06bb2042385e 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -291,14 +291,12 @@ static bool has_merged_page(struct f2fs_sb_info *sbi, struct inode *inode,
 	return ret;
 }
 
-static void __f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
+static void __f2fs_submit_merged_write(struct f2fs_sb_info *sbi,
 				struct inode *inode, nid_t ino, pgoff_t idx,
-				enum page_type type, int rw)
+				enum page_type type)
 {
 	enum page_type btype = PAGE_TYPE_OF_BIO(type);
-	struct f2fs_bio_info *io;
-
-	io = is_read_io(rw) ? &sbi->read_io : &sbi->write_io[btype];
+	struct f2fs_bio_info *io = &sbi->write_io[btype];
 
 	down_write(&io->io_rwsem);
 
@@ -318,25 +316,24 @@ out:
 	up_write(&io->io_rwsem);
 }
 
-void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi, enum page_type type,
-									int rw)
+void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type)
 {
-	__f2fs_submit_merged_bio(sbi, NULL, 0, 0, type, rw);
+	__f2fs_submit_merged_write(sbi, NULL, 0, 0, type);
 }
 
-void f2fs_submit_merged_bio_cond(struct f2fs_sb_info *sbi,
+void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi,
 				struct inode *inode, nid_t ino, pgoff_t idx,
-				enum page_type type, int rw)
+				enum page_type type)
 {
 	if (has_merged_page(sbi, inode, ino, idx, type))
-		__f2fs_submit_merged_bio(sbi, inode, ino, idx, type, rw);
+		__f2fs_submit_merged_write(sbi, inode, ino, idx, type);
 }
 
-void f2fs_flush_merged_bios(struct f2fs_sb_info *sbi)
+void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi)
 {
-	f2fs_submit_merged_bio(sbi, DATA, WRITE);
-	f2fs_submit_merged_bio(sbi, NODE, WRITE);
-	f2fs_submit_merged_bio(sbi, META, WRITE);
+	f2fs_submit_merged_write(sbi, DATA);
+	f2fs_submit_merged_write(sbi, NODE);
+	f2fs_submit_merged_write(sbi, META);
 }
 
 /*
@@ -368,16 +365,15 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
 	return 0;
 }
 
-int f2fs_submit_page_mbio(struct f2fs_io_info *fio)
+int f2fs_submit_page_write(struct f2fs_io_info *fio)
 {
 	struct f2fs_sb_info *sbi = fio->sbi;
 	enum page_type btype = PAGE_TYPE_OF_BIO(fio->type);
-	struct f2fs_bio_info *io;
-	bool is_read = is_read_io(fio->op);
+	struct f2fs_bio_info *io = &sbi->write_io[btype];
 	struct page *bio_page;
 	int err = 0;
 
-	io = is_read ? &sbi->read_io : &sbi->write_io[btype];
+	f2fs_bug_on(sbi, is_read_io(fio->op));
 
 	if (fio->old_blkaddr != NEW_ADDR)
 		verify_block_addr(sbi, fio->old_blkaddr);
@@ -388,8 +384,7 @@ int f2fs_submit_page_mbio(struct f2fs_io_info *fio)
 	/* set submitted = 1 as a return value */
 	fio->submitted = 1;
 
-	if (!is_read)
-		inc_page_count(sbi, WB_DATA_TYPE(bio_page));
+	inc_page_count(sbi, WB_DATA_TYPE(bio_page));
 
 	down_write(&io->io_rwsem);
 
@@ -402,12 +397,11 @@ alloc_new:
 		if ((fio->type == DATA || fio->type == NODE) &&
 				fio->new_blkaddr & F2FS_IO_SIZE_MASK(sbi)) {
 			err = -EAGAIN;
-			if (!is_read)
-				dec_page_count(sbi, WB_DATA_TYPE(bio_page));
+			dec_page_count(sbi, WB_DATA_TYPE(bio_page));
 			goto out_fail;
 		}
 		io->bio = __bio_alloc(sbi, fio->new_blkaddr,
-						BIO_MAX_PAGES, is_read);
+						BIO_MAX_PAGES, false);
 		io->fio = *fio;
 	}
 
@@ -421,7 +415,7 @@ alloc_new:
 	f2fs_trace_ios(fio, 0);
 out_fail:
 	up_write(&io->io_rwsem);
-	trace_f2fs_submit_page_mbio(fio->page, fio);
+	trace_f2fs_submit_page_write(fio->page, fio);
 	return err;
 }
 
@@ -1321,7 +1315,7 @@ retry_encrypt:
 
 	/* flush pending IOs and wait for a while in the ENOMEM case */
 	if (PTR_ERR(fio->encrypted_page) == -ENOMEM) {
-		f2fs_flush_merged_bios(fio->sbi);
+		f2fs_flush_merged_writes(fio->sbi);
 		congestion_wait(BLK_RW_ASYNC, HZ/50);
 		gfp_flags |= __GFP_NOFAIL;
 		goto retry_encrypt;
@@ -1513,8 +1507,7 @@ out:
 		ClearPageUptodate(page);
 
 	if (wbc->for_reclaim) {
-		f2fs_submit_merged_bio_cond(sbi, inode, 0, page->index,
-						DATA, WRITE);
+		f2fs_submit_merged_write_cond(sbi, inode, 0, page->index, DATA);
 		clear_inode_flag(inode, FI_HOT_DATA);
 		remove_dirty_inode(inode);
 		submitted = NULL;
@@ -1525,7 +1518,7 @@ out:
 		f2fs_balance_fs(sbi, need_balance_fs);
 
 	if (unlikely(f2fs_cp_error(sbi))) {
-		f2fs_submit_merged_bio(sbi, DATA, WRITE);
+		f2fs_submit_merged_write(sbi, DATA);
 		submitted = NULL;
 	}
 
@@ -1684,8 +1677,8 @@ continue_unlock:
 		mapping->writeback_index = done_index;
 
 	if (last_idx != ULONG_MAX)
-		f2fs_submit_merged_bio_cond(F2FS_M_SB(mapping), mapping->host,
-						0, last_idx, DATA, WRITE);
+		f2fs_submit_merged_write_cond(F2FS_M_SB(mapping), mapping->host,
+						0, last_idx, DATA);
 
 	return ret;
 }
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index e26999a74522..58697bd588fa 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -879,7 +879,6 @@ struct f2fs_sb_info {
 	struct f2fs_sm_info *sm_info;		/* segment manager */
 
 	/* for bio operations */
-	struct f2fs_bio_info read_io;			/* for read bios */
 	struct f2fs_bio_info write_io[NR_PAGE_TYPE];	/* for write bios */
 	struct mutex wio_mutex[NODE + 1];	/* bio ordering for NODE/DATA */
 	int write_io_size_bits;			/* Write IO size bits */
@@ -2325,14 +2324,13 @@ void destroy_checkpoint_caches(void);
 /*
  * data.c
  */
-void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi, enum page_type type,
-			int rw);
-void f2fs_submit_merged_bio_cond(struct f2fs_sb_info *sbi,
+void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type);
+void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi,
 				struct inode *inode, nid_t ino, pgoff_t idx,
-				enum page_type type, int rw);
-void f2fs_flush_merged_bios(struct f2fs_sb_info *sbi);
+				enum page_type type);
+void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi);
 int f2fs_submit_page_bio(struct f2fs_io_info *fio);
-int f2fs_submit_page_mbio(struct f2fs_io_info *fio);
+int f2fs_submit_page_write(struct f2fs_io_info *fio);
 struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi,
 			block_t blk_addr, struct bio *bio);
 int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr);
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 965fbf5d0a2e..67b87155bc48 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -670,7 +670,7 @@ static void move_encrypted_block(struct inode *inode, block_t bidx,
 	fio.op = REQ_OP_WRITE;
 	fio.op_flags = REQ_SYNC;
 	fio.new_blkaddr = newaddr;
-	f2fs_submit_page_mbio(&fio);
+	f2fs_submit_page_write(&fio);
 
 	f2fs_update_data_blkaddr(&dn, newaddr);
 	set_inode_flag(inode, FI_APPEND_WRITE);
@@ -936,8 +936,8 @@ next:
 	}
 
 	if (gc_type == FG_GC)
-		f2fs_submit_merged_bio(sbi,
-				(type == SUM_TYPE_NODE) ? NODE : DATA, WRITE);
+		f2fs_submit_merged_write(sbi,
+				(type == SUM_TYPE_NODE) ? NODE : DATA);
 
 	blk_finish_plug(&plug);
 
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 98351a4a4da3..41bb632ac2e0 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -1373,15 +1373,15 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
 	up_read(&sbi->node_write);
 
 	if (wbc->for_reclaim) {
-		f2fs_submit_merged_bio_cond(sbi, page->mapping->host, 0,
-						page->index, NODE, WRITE);
+		f2fs_submit_merged_write_cond(sbi, page->mapping->host, 0,
+						page->index, NODE);
 		submitted = NULL;
 	}
 
 	unlock_page(page);
 
 	if (unlikely(f2fs_cp_error(sbi))) {
-		f2fs_submit_merged_bio(sbi, NODE, WRITE);
+		f2fs_submit_merged_write(sbi, NODE);
 		submitted = NULL;
 	}
 	if (submitted)
@@ -1518,8 +1518,7 @@ continue_unlock:
 	}
 out:
 	if (last_idx != ULONG_MAX)
-		f2fs_submit_merged_bio_cond(sbi, NULL, ino, last_idx,
-							NODE, WRITE);
+		f2fs_submit_merged_write_cond(sbi, NULL, ino, last_idx, NODE);
 	return ret ? -EIO: 0;
 }
 
@@ -1625,7 +1624,7 @@ continue_unlock:
 	}
 out:
 	if (nwritten)
-		f2fs_submit_merged_bio(sbi, NODE, WRITE);
+		f2fs_submit_merged_write(sbi, NODE);
 	return ret;
 }
 
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index de31030b5041..38bb675976e2 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -328,8 +328,7 @@ static int __commit_inmem_pages(struct inode *inode,
 	}
 
 	if (last_idx != ULONG_MAX)
-		f2fs_submit_merged_bio_cond(sbi, inode, 0, last_idx,
-							DATA, WRITE);
+		f2fs_submit_merged_write_cond(sbi, inode, 0, last_idx, DATA);
 
 	if (!err)
 		__revoke_inmem_pages(inode, revoke_list, false, false);
@@ -2150,7 +2149,7 @@ reallocate:
 					&fio->new_blkaddr, sum, type);
 
 	/* writeout dirty page into bdev */
-	err = f2fs_submit_page_mbio(fio);
+	err = f2fs_submit_page_write(fio);
 	if (err == -EAGAIN) {
 		fio->old_blkaddr = fio->new_blkaddr;
 		goto reallocate;
@@ -2177,7 +2176,7 @@ void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
 		fio.op_flags &= ~REQ_META;
 
 	set_page_writeback(page);
-	f2fs_submit_page_mbio(&fio);
+	f2fs_submit_page_write(&fio);
 }
 
 void write_node_page(unsigned int nid, struct f2fs_io_info *fio)
@@ -2296,8 +2295,8 @@ void f2fs_wait_on_page_writeback(struct page *page,
 	if (PageWriteback(page)) {
 		struct f2fs_sb_info *sbi = F2FS_P_SB(page);
 
-		f2fs_submit_merged_bio_cond(sbi, page->mapping->host,
-						0, page->index, type, WRITE);
+		f2fs_submit_merged_write_cond(sbi, page->mapping->host,
+						0, page->index, type);
 		if (ordered)
 			wait_on_page_writeback(page);
 		else
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 397b1e816b36..90599397425a 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -817,7 +817,7 @@ static void f2fs_put_super(struct super_block *sb)
 	mutex_unlock(&sbi->umount_mutex);
 
 	/* our cp_error case, we can wait for any writeback page */
-	f2fs_flush_merged_bios(sbi);
+	f2fs_flush_merged_writes(sbi);
 
 	iput(sbi->node_inode);
 	iput(sbi->meta_inode);
@@ -1966,9 +1966,6 @@ try_onemore:
 	set_sbi_flag(sbi, SBI_POR_DOING);
 	spin_lock_init(&sbi->stat_lock);
 
-	init_rwsem(&sbi->read_io.io_rwsem);
-	sbi->read_io.sbi = sbi;
-	sbi->read_io.bio = NULL;
 	for (i = 0; i < NR_PAGE_TYPE; i++) {
 		init_rwsem(&sbi->write_io[i].io_rwsem);
 		sbi->write_io[i].sbi = sbi;
diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index 15da88c5c3a4..5805d92893a8 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -790,7 +790,7 @@ DEFINE_EVENT_CONDITION(f2fs__submit_page_bio, f2fs_submit_page_bio,
 	TP_CONDITION(page->mapping)
 );
 
-DEFINE_EVENT_CONDITION(f2fs__submit_page_bio, f2fs_submit_page_mbio,
+DEFINE_EVENT_CONDITION(f2fs__submit_page_bio, f2fs_submit_page_write,
 
 	TP_PROTO(struct page *page, struct f2fs_io_info *fio),
 
-- 
cgit v1.2.3


From a912b54d3aaa011266dc266e3694f782f27233cf Mon Sep 17 00:00:00 2001
From: Jaegeuk Kim <jaegeuk@kernel.org>
Date: Wed, 10 May 2017 11:18:25 -0700
Subject: f2fs: split bio cache

Split DATA/NODE type bio cache according to different temperature,
so write IOs with the same temperature can be merged in corresponding
bio cache as much as possible, otherwise, different temperature write
IOs submitting into one bio cache will always cause split of bio.

Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c              | 57 +++++++++++++++++++++++++++++++--------------
 fs/f2fs/f2fs.h              | 10 +++++++-
 fs/f2fs/gc.c                |  2 ++
 fs/f2fs/segment.c           | 24 ++++++++++++++-----
 fs/f2fs/segment.h           |  4 ++++
 fs/f2fs/super.c             | 21 ++++++++++++++---
 include/trace/events/f2fs.h | 14 ++++++++++-
 7 files changed, 103 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 06bb2042385e..4ca0899621a0 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -282,27 +282,32 @@ static bool has_merged_page(struct f2fs_sb_info *sbi, struct inode *inode,
 				nid_t ino, pgoff_t idx, enum page_type type)
 {
 	enum page_type btype = PAGE_TYPE_OF_BIO(type);
-	struct f2fs_bio_info *io = &sbi->write_io[btype];
-	bool ret;
+	enum temp_type temp;
+	struct f2fs_bio_info *io;
+	bool ret = false;
 
-	down_read(&io->io_rwsem);
-	ret = __has_merged_page(io, inode, ino, idx);
-	up_read(&io->io_rwsem);
+	for (temp = HOT; temp < NR_TEMP_TYPE; temp++) {
+		io = sbi->write_io[btype] + temp;
+
+		down_read(&io->io_rwsem);
+		ret = __has_merged_page(io, inode, ino, idx);
+		up_read(&io->io_rwsem);
+
+		/* TODO: use HOT temp only for meta pages now. */
+		if (ret || btype == META)
+			break;
+	}
 	return ret;
 }
 
 static void __f2fs_submit_merged_write(struct f2fs_sb_info *sbi,
-				struct inode *inode, nid_t ino, pgoff_t idx,
-				enum page_type type)
+				enum page_type type, enum temp_type temp)
 {
 	enum page_type btype = PAGE_TYPE_OF_BIO(type);
-	struct f2fs_bio_info *io = &sbi->write_io[btype];
+	struct f2fs_bio_info *io = sbi->write_io[btype] + temp;
 
 	down_write(&io->io_rwsem);
 
-	if (!__has_merged_page(io, inode, ino, idx))
-		goto out;
-
 	/* change META to META_FLUSH in the checkpoint procedure */
 	if (type >= META_FLUSH) {
 		io->fio.type = META_FLUSH;
@@ -312,21 +317,38 @@ static void __f2fs_submit_merged_write(struct f2fs_sb_info *sbi,
 			io->fio.op_flags |= REQ_PREFLUSH | REQ_FUA;
 	}
 	__submit_merged_bio(io);
-out:
 	up_write(&io->io_rwsem);
 }
 
+static void __submit_merged_write_cond(struct f2fs_sb_info *sbi,
+				struct inode *inode, nid_t ino, pgoff_t idx,
+				enum page_type type, bool force)
+{
+	enum temp_type temp;
+
+	if (!force && !has_merged_page(sbi, inode, ino, idx, type))
+		return;
+
+	for (temp = HOT; temp < NR_TEMP_TYPE; temp++) {
+
+		__f2fs_submit_merged_write(sbi, type, temp);
+
+		/* TODO: use HOT temp only for meta pages now. */
+		if (type >= META)
+			break;
+	}
+}
+
 void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type)
 {
-	__f2fs_submit_merged_write(sbi, NULL, 0, 0, type);
+	__submit_merged_write_cond(sbi, NULL, 0, 0, type, true);
 }
 
 void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi,
 				struct inode *inode, nid_t ino, pgoff_t idx,
 				enum page_type type)
 {
-	if (has_merged_page(sbi, inode, ino, idx, type))
-		__f2fs_submit_merged_write(sbi, inode, ino, idx, type);
+	__submit_merged_write_cond(sbi, inode, ino, idx, type, false);
 }
 
 void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi)
@@ -369,7 +391,7 @@ int f2fs_submit_page_write(struct f2fs_io_info *fio)
 {
 	struct f2fs_sb_info *sbi = fio->sbi;
 	enum page_type btype = PAGE_TYPE_OF_BIO(fio->type);
-	struct f2fs_bio_info *io = &sbi->write_io[btype];
+	struct f2fs_bio_info *io = sbi->write_io[btype] + fio->temp;
 	struct page *bio_page;
 	int err = 0;
 
@@ -405,8 +427,7 @@ alloc_new:
 		io->fio = *fio;
 	}
 
-	if (bio_add_page(io->bio, bio_page, PAGE_SIZE, 0) <
-							PAGE_SIZE) {
+	if (bio_add_page(io->bio, bio_page, PAGE_SIZE, 0) < PAGE_SIZE) {
 		__submit_merged_bio(io);
 		goto alloc_new;
 	}
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 58697bd588fa..c6643783adff 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -792,9 +792,17 @@ enum page_type {
 	OPU,
 };
 
+enum temp_type {
+	HOT = 0,	/* must be zero for meta bio */
+	WARM,
+	COLD,
+	NR_TEMP_TYPE,
+};
+
 struct f2fs_io_info {
 	struct f2fs_sb_info *sbi;	/* f2fs_sb_info pointer */
 	enum page_type type;	/* contains DATA/NODE/META/META_FLUSH */
+	enum temp_type temp;	/* contains HOT/WARM/COLD */
 	int op;			/* contains REQ_OP_ */
 	int op_flags;		/* req_flag_bits */
 	block_t new_blkaddr;	/* new block address to be written */
@@ -879,7 +887,7 @@ struct f2fs_sb_info {
 	struct f2fs_sm_info *sm_info;		/* segment manager */
 
 	/* for bio operations */
-	struct f2fs_bio_info write_io[NR_PAGE_TYPE];	/* for write bios */
+	struct f2fs_bio_info *write_io[NR_PAGE_TYPE];	/* for write bios */
 	struct mutex wio_mutex[NODE + 1];	/* bio ordering for NODE/DATA */
 	int write_io_size_bits;			/* Write IO size bits */
 	mempool_t *write_io_dummy;		/* Dummy pages */
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 67b87155bc48..e2b13558a915 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -586,6 +586,7 @@ static void move_encrypted_block(struct inode *inode, block_t bidx,
 	struct f2fs_io_info fio = {
 		.sbi = F2FS_I_SB(inode),
 		.type = DATA,
+		.temp = COLD,
 		.op = REQ_OP_READ,
 		.op_flags = 0,
 		.encrypted_page = NULL,
@@ -712,6 +713,7 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type,
 		struct f2fs_io_info fio = {
 			.sbi = F2FS_I_SB(inode),
 			.type = DATA,
+			.temp = COLD,
 			.op = REQ_OP_WRITE,
 			.op_flags = REQ_SYNC,
 			.old_blkaddr = NULL_ADDR,
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index c9f3a2faee21..fcada9d03817 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -2084,17 +2084,29 @@ static int __get_segment_type_6(struct f2fs_io_info *fio)
 
 static int __get_segment_type(struct f2fs_io_info *fio)
 {
+	int type = 0;
+
 	switch (fio->sbi->active_logs) {
 	case 2:
-		return __get_segment_type_2(fio);
+		type = __get_segment_type_2(fio);
+		break;
 	case 4:
-		return __get_segment_type_4(fio);
+		type = __get_segment_type_4(fio);
+		break;
+	case 6:
+		type = __get_segment_type_6(fio);
+		break;
+	default:
+		f2fs_bug_on(fio->sbi, true);
 	}
 
-	/* NR_CURSEG_TYPE(6) logs by default */
-	f2fs_bug_on(fio->sbi, fio->sbi->active_logs != NR_CURSEG_TYPE);
-
-	return __get_segment_type_6(fio);
+	if (IS_HOT(type))
+		fio->temp = HOT;
+	else if (IS_WARM(type))
+		fio->temp = WARM;
+	else
+		fio->temp = COLD;
+	return type;
 }
 
 void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 10bf05d4cff4..e9ba1f1d9723 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -27,6 +27,10 @@
 #define IS_DATASEG(t)	((t) <= CURSEG_COLD_DATA)
 #define IS_NODESEG(t)	((t) >= CURSEG_HOT_NODE)
 
+#define IS_HOT(t)	((t) == CURSEG_HOT_NODE || (t) == CURSEG_HOT_DATA)
+#define IS_WARM(t)	((t) == CURSEG_WARM_NODE || (t) == CURSEG_WARM_DATA)
+#define IS_COLD(t)	((t) == CURSEG_COLD_NODE || (t) == CURSEG_COLD_DATA)
+
 #define IS_CURSEG(sbi, seg)						\
 	(((seg) == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno) ||	\
 	 ((seg) == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno) ||	\
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 90599397425a..aa451ec9fb80 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -768,6 +768,7 @@ static void destroy_device_list(struct f2fs_sb_info *sbi)
 static void f2fs_put_super(struct super_block *sb)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
+	int i;
 
 	if (sbi->s_proc) {
 		remove_proc_entry("segment_info", sbi->s_proc);
@@ -838,6 +839,8 @@ static void f2fs_put_super(struct super_block *sb)
 	destroy_device_list(sbi);
 	mempool_destroy(sbi->write_io_dummy);
 	destroy_percpu_info(sbi);
+	for (i = 0; i < NR_PAGE_TYPE; i++)
+		kfree(sbi->write_io[i]);
 	kfree(sbi);
 }
 
@@ -1967,9 +1970,19 @@ try_onemore:
 	spin_lock_init(&sbi->stat_lock);
 
 	for (i = 0; i < NR_PAGE_TYPE; i++) {
-		init_rwsem(&sbi->write_io[i].io_rwsem);
-		sbi->write_io[i].sbi = sbi;
-		sbi->write_io[i].bio = NULL;
+		int n = (i == META) ? 1: NR_TEMP_TYPE;
+		int j;
+
+		sbi->write_io[i] = kmalloc(n * sizeof(struct f2fs_bio_info),
+								GFP_KERNEL);
+		if (!sbi->write_io[i])
+			goto free_options;
+
+		for (j = HOT; j < n; j++) {
+			init_rwsem(&sbi->write_io[i][j].io_rwsem);
+			sbi->write_io[i][j].sbi = sbi;
+			sbi->write_io[i][j].bio = NULL;
+		}
 	}
 
 	init_rwsem(&sbi->cp_rwsem);
@@ -2215,6 +2228,8 @@ free_meta_inode:
 free_io_dummy:
 	mempool_destroy(sbi->write_io_dummy);
 free_options:
+	for (i = 0; i < NR_PAGE_TYPE; i++)
+		kfree(sbi->write_io[i]);
 	destroy_percpu_info(sbi);
 	kfree(options);
 free_sb_buf:
diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index 5805d92893a8..6f77a2755abb 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -19,6 +19,9 @@ TRACE_DEFINE_ENUM(INMEM_INVALIDATE);
 TRACE_DEFINE_ENUM(INMEM_REVOKE);
 TRACE_DEFINE_ENUM(IPU);
 TRACE_DEFINE_ENUM(OPU);
+TRACE_DEFINE_ENUM(HOT);
+TRACE_DEFINE_ENUM(WARM);
+TRACE_DEFINE_ENUM(COLD);
 TRACE_DEFINE_ENUM(CURSEG_HOT_DATA);
 TRACE_DEFINE_ENUM(CURSEG_WARM_DATA);
 TRACE_DEFINE_ENUM(CURSEG_COLD_DATA);
@@ -59,6 +62,12 @@ TRACE_DEFINE_ENUM(CP_TRIMMED);
 		{ IPU,		"IN-PLACE" },				\
 		{ OPU,		"OUT-OF-PLACE" })
 
+#define show_block_temp(temp)						\
+	__print_symbolic(temp,						\
+		{ HOT,		"HOT" },				\
+		{ WARM,		"WARM" },				\
+		{ COLD,		"COLD" })
+
 #define F2FS_OP_FLAGS (REQ_RAHEAD | REQ_SYNC | REQ_META | REQ_PRIO |	\
 			REQ_PREFLUSH | REQ_FUA)
 #define F2FS_BIO_FLAG_MASK(t)	(t & F2FS_OP_FLAGS)
@@ -757,6 +766,7 @@ DECLARE_EVENT_CLASS(f2fs__submit_page_bio,
 		__field(block_t, new_blkaddr)
 		__field(int, op)
 		__field(int, op_flags)
+		__field(int, temp)
 		__field(int, type)
 	),
 
@@ -768,16 +778,18 @@ DECLARE_EVENT_CLASS(f2fs__submit_page_bio,
 		__entry->new_blkaddr	= fio->new_blkaddr;
 		__entry->op		= fio->op;
 		__entry->op_flags	= fio->op_flags;
+		__entry->temp		= fio->temp;
 		__entry->type		= fio->type;
 	),
 
 	TP_printk("dev = (%d,%d), ino = %lu, page_index = 0x%lx, "
-		"oldaddr = 0x%llx, newaddr = 0x%llx, rw = %s(%s), type = %s",
+		"oldaddr = 0x%llx, newaddr = 0x%llx, rw = %s(%s), type = %s_%s",
 		show_dev_ino(__entry),
 		(unsigned long)__entry->index,
 		(unsigned long long)__entry->old_blkaddr,
 		(unsigned long long)__entry->new_blkaddr,
 		show_bio_type(__entry->op, __entry->op_flags),
+		show_block_temp(__entry->temp),
 		show_block_type(__entry->type))
 );
 
-- 
cgit v1.2.3


From 3e08b2df12983159ea2d9a1aa2b2bc601093b3cb Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Tue, 25 Apr 2017 15:57:12 +0530
Subject: thermal: cpu_cooling: remove cpufreq_cooling_get_level()

There is only one user of cpufreq_cooling_get_level() and that already
has pointer to the cpufreq_cdev structure. It can directly call
get_level() instead and we can get rid of cpufreq_cooling_get_level().

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
Tested-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/thermal/cpu_cooling.c | 33 +--------------------------------
 include/linux/cpu_cooling.h   |  6 ------
 2 files changed, 1 insertion(+), 38 deletions(-)

(limited to 'include')

diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index f1e784c22c5a..1f4b6a719d05 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -135,37 +135,6 @@ static unsigned long get_level(struct cpufreq_cooling_device *cpufreq_cdev,
 	return THERMAL_CSTATE_INVALID;
 }
 
-/**
- * cpufreq_cooling_get_level - for a given cpu, return the cooling level.
- * @cpu: cpu for which the level is required
- * @freq: the frequency of interest
- *
- * This function will match the cooling level corresponding to the
- * requested @freq and return it.
- *
- * Return: The matched cooling level on success or THERMAL_CSTATE_INVALID
- * otherwise.
- */
-unsigned long cpufreq_cooling_get_level(unsigned int cpu, unsigned int freq)
-{
-	struct cpufreq_cooling_device *cpufreq_cdev;
-
-	mutex_lock(&cooling_list_lock);
-	list_for_each_entry(cpufreq_cdev, &cpufreq_cdev_list, node) {
-		if (cpumask_test_cpu(cpu, &cpufreq_cdev->allowed_cpus)) {
-			unsigned long level = get_level(cpufreq_cdev, freq);
-
-			mutex_unlock(&cooling_list_lock);
-			return level;
-		}
-	}
-	mutex_unlock(&cooling_list_lock);
-
-	pr_err("%s: cpu:%d not part of any cooling device\n", __func__, cpu);
-	return THERMAL_CSTATE_INVALID;
-}
-EXPORT_SYMBOL_GPL(cpufreq_cooling_get_level);
-
 /**
  * cpufreq_thermal_notifier - notifier callback for cpufreq policy change.
  * @nb:	struct notifier_block * with callback info.
@@ -697,7 +666,7 @@ static int cpufreq_power2state(struct thermal_cooling_device *cdev,
 	normalised_power = (dyn_power * 100) / last_load;
 	target_freq = cpu_power_to_freq(cpufreq_cdev, normalised_power);
 
-	*state = cpufreq_cooling_get_level(cpu, target_freq);
+	*state = get_level(cpufreq_cdev, target_freq);
 	if (*state == THERMAL_CSTATE_INVALID) {
 		dev_err_ratelimited(&cdev->device,
 				    "Failed to convert %dKHz for cpu %d into a cdev state\n",
diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h
index c156f5082758..96c5e4c2f9c8 100644
--- a/include/linux/cpu_cooling.h
+++ b/include/linux/cpu_cooling.h
@@ -82,7 +82,6 @@ of_cpufreq_power_cooling_register(struct device_node *np,
  */
 void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev);
 
-unsigned long cpufreq_cooling_get_level(unsigned int cpu, unsigned int freq);
 #else /* !CONFIG_CPU_THERMAL */
 static inline struct thermal_cooling_device *
 cpufreq_cooling_register(const struct cpumask *clip_cpus)
@@ -117,11 +116,6 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
 {
 	return;
 }
-static inline
-unsigned long cpufreq_cooling_get_level(unsigned int cpu, unsigned int freq)
-{
-	return THERMAL_CSTATE_INVALID;
-}
 #endif	/* CONFIG_CPU_THERMAL */
 
 #endif /* __CPU_COOLING_H__ */
-- 
cgit v1.2.3


From 4d753aa7b6279e4b7d338947a434689962f430d1 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Tue, 25 Apr 2017 15:57:14 +0530
Subject: thermal: cpu_cooling: use cpufreq_policy to register cooling device

The CPU cooling driver uses the cpufreq policy, to get clip_cpus, the
frequency table, etc. Most of the callers of CPU cooling driver's
registration routines have the cpufreq policy with them, but they only
pass the policy->related_cpus cpumask. The __cpufreq_cooling_register()
routine then gets the policy by itself and uses it.

It would be much better if the callers can pass the policy instead
directly. This also fixes a basic design flaw, where the policy can be
freed while the CPU cooling driver is still active.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
Tested-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/cpufreq/arm_big_little.c                   |  2 +-
 drivers/cpufreq/cpufreq-dt.c                       |  2 +-
 drivers/cpufreq/dbx500-cpufreq.c                   |  2 +-
 drivers/cpufreq/mt8173-cpufreq.c                   |  4 +-
 drivers/cpufreq/qoriq-cpufreq.c                    |  3 +-
 drivers/thermal/cpu_cooling.c                      | 61 ++++++++--------------
 drivers/thermal/imx_thermal.c                      | 22 ++++++--
 drivers/thermal/ti-soc-thermal/ti-thermal-common.c | 22 +++++---
 include/linux/cpu_cooling.h                        | 26 ++++-----
 9 files changed, 74 insertions(+), 70 deletions(-)

(limited to 'include')

diff --git a/drivers/cpufreq/arm_big_little.c b/drivers/cpufreq/arm_big_little.c
index 418042201e6d..ea6d62547b10 100644
--- a/drivers/cpufreq/arm_big_little.c
+++ b/drivers/cpufreq/arm_big_little.c
@@ -540,7 +540,7 @@ static void bL_cpufreq_ready(struct cpufreq_policy *policy)
 				     &power_coefficient);
 
 		cdev[cur_cluster] = of_cpufreq_power_cooling_register(np,
-				policy->related_cpus, power_coefficient, NULL);
+				policy, power_coefficient, NULL);
 		if (IS_ERR(cdev[cur_cluster])) {
 			dev_err(cpu_dev,
 				"running cpufreq without cooling device: %ld\n",
diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index c943787d761e..fef3c2160691 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -326,7 +326,7 @@ static void cpufreq_ready(struct cpufreq_policy *policy)
 				     &power_coefficient);
 
 		priv->cdev = of_cpufreq_power_cooling_register(np,
-				policy->related_cpus, power_coefficient, NULL);
+				policy, power_coefficient, NULL);
 		if (IS_ERR(priv->cdev)) {
 			dev_err(priv->cpu_dev,
 				"running cpufreq without cooling device: %ld\n",
diff --git a/drivers/cpufreq/dbx500-cpufreq.c b/drivers/cpufreq/dbx500-cpufreq.c
index 3575b82210ba..4ee0431579c1 100644
--- a/drivers/cpufreq/dbx500-cpufreq.c
+++ b/drivers/cpufreq/dbx500-cpufreq.c
@@ -43,7 +43,7 @@ static int dbx500_cpufreq_exit(struct cpufreq_policy *policy)
 
 static void dbx500_cpufreq_ready(struct cpufreq_policy *policy)
 {
-	cdev = cpufreq_cooling_register(policy->cpus);
+	cdev = cpufreq_cooling_register(policy);
 	if (IS_ERR(cdev))
 		pr_err("Failed to register cooling device %ld\n", PTR_ERR(cdev));
 	else
diff --git a/drivers/cpufreq/mt8173-cpufreq.c b/drivers/cpufreq/mt8173-cpufreq.c
index fd1886faf33a..f9f00fb4bc3a 100644
--- a/drivers/cpufreq/mt8173-cpufreq.c
+++ b/drivers/cpufreq/mt8173-cpufreq.c
@@ -320,9 +320,7 @@ static void mtk_cpufreq_ready(struct cpufreq_policy *policy)
 		of_property_read_u32(np, DYNAMIC_POWER, &capacitance);
 
 		info->cdev = of_cpufreq_power_cooling_register(np,
-						policy->related_cpus,
-						capacitance,
-						NULL);
+						policy, capacitance, NULL);
 
 		if (IS_ERR(info->cdev)) {
 			dev_err(info->cpu_dev,
diff --git a/drivers/cpufreq/qoriq-cpufreq.c b/drivers/cpufreq/qoriq-cpufreq.c
index e2ea433a5f9c..4ada55b8856e 100644
--- a/drivers/cpufreq/qoriq-cpufreq.c
+++ b/drivers/cpufreq/qoriq-cpufreq.c
@@ -278,8 +278,7 @@ static void qoriq_cpufreq_ready(struct cpufreq_policy *policy)
 	struct device_node *np = of_get_cpu_node(policy->cpu, NULL);
 
 	if (of_find_property(np, "#cooling-cells", NULL)) {
-		cpud->cdev = of_cpufreq_cooling_register(np,
-							 policy->related_cpus);
+		cpud->cdev = of_cpufreq_cooling_register(np, policy);
 
 		if (IS_ERR(cpud->cdev) && PTR_ERR(cpud->cdev) != -ENOSYS) {
 			pr_err("cpu%d is not running as cooling device: %ld\n",
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index 002b48dc6bea..58e58065b650 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -717,7 +717,7 @@ static unsigned int find_next_max(struct cpufreq_frequency_table *table,
 /**
  * __cpufreq_cooling_register - helper function to create cpufreq cooling device
  * @np: a valid struct device_node to the cooling device device tree node
- * @clip_cpus: cpumask of cpus where the frequency constraints will happen.
+ * @policy: cpufreq policy
  * Normally this should be same as cpufreq policy->related_cpus.
  * @capacitance: dynamic power coefficient for these cpus
  * @plat_static_func: function to calculate the static power consumed by these
@@ -733,45 +733,34 @@ static unsigned int find_next_max(struct cpufreq_frequency_table *table,
  */
 static struct thermal_cooling_device *
 __cpufreq_cooling_register(struct device_node *np,
-			const struct cpumask *clip_cpus, u32 capacitance,
+			struct cpufreq_policy *policy, u32 capacitance,
 			get_static_t plat_static_func)
 {
-	struct cpufreq_policy *policy;
 	struct thermal_cooling_device *cdev;
 	struct cpufreq_cooling_device *cpufreq_cdev;
 	char dev_name[THERMAL_NAME_LENGTH];
 	struct cpufreq_frequency_table *pos, *table;
-	cpumask_var_t temp_mask;
 	unsigned int freq, i, num_cpus;
 	int ret;
 	struct thermal_cooling_device_ops *cooling_ops;
 	bool first;
 
-	if (!alloc_cpumask_var(&temp_mask, GFP_KERNEL))
-		return ERR_PTR(-ENOMEM);
-
-	cpumask_and(temp_mask, clip_cpus, cpu_online_mask);
-	policy = cpufreq_cpu_get(cpumask_first(temp_mask));
-	if (!policy) {
-		pr_debug("%s: CPUFreq policy not found\n", __func__);
-		cdev = ERR_PTR(-EPROBE_DEFER);
-		goto free_cpumask;
+	if (IS_ERR_OR_NULL(policy)) {
+		pr_err("%s: cpufreq policy isn't valid: %p", __func__, policy);
+		return ERR_PTR(-EINVAL);
 	}
 
 	table = policy->freq_table;
 	if (!table) {
 		pr_debug("%s: CPUFreq table not found\n", __func__);
-		cdev = ERR_PTR(-ENODEV);
-		goto put_policy;
+		return ERR_PTR(-ENODEV);
 	}
 
 	cpufreq_cdev = kzalloc(sizeof(*cpufreq_cdev), GFP_KERNEL);
-	if (!cpufreq_cdev) {
-		cdev = ERR_PTR(-ENOMEM);
-		goto put_policy;
-	}
+	if (!cpufreq_cdev)
+		return ERR_PTR(-ENOMEM);
 
-	num_cpus = cpumask_weight(clip_cpus);
+	num_cpus = cpumask_weight(policy->related_cpus);
 	cpufreq_cdev->time_in_idle = kcalloc(num_cpus,
 					    sizeof(*cpufreq_cdev->time_in_idle),
 					    GFP_KERNEL);
@@ -802,7 +791,7 @@ __cpufreq_cooling_register(struct device_node *np,
 	/* max_level is an index, not a counter */
 	cpufreq_cdev->max_level--;
 
-	cpumask_copy(&cpufreq_cdev->allowed_cpus, clip_cpus);
+	cpumask_copy(&cpufreq_cdev->allowed_cpus, policy->related_cpus);
 
 	if (capacitance) {
 		cpufreq_cdev->plat_get_static_power = plat_static_func;
@@ -858,7 +847,7 @@ __cpufreq_cooling_register(struct device_node *np,
 		cpufreq_register_notifier(&thermal_cpufreq_notifier_block,
 					  CPUFREQ_POLICY_NOTIFIER);
 
-	goto put_policy;
+	return cdev;
 
 remove_ida:
 	ida_simple_remove(&cpufreq_ida, cpufreq_cdev->id);
@@ -872,16 +861,12 @@ free_time_in_idle:
 	kfree(cpufreq_cdev->time_in_idle);
 free_cdev:
 	kfree(cpufreq_cdev);
-put_policy:
-	cpufreq_cpu_put(policy);
-free_cpumask:
-	free_cpumask_var(temp_mask);
 	return cdev;
 }
 
 /**
  * cpufreq_cooling_register - function to create cpufreq cooling device.
- * @clip_cpus: cpumask of cpus where the frequency constraints will happen.
+ * @policy: cpufreq policy
  *
  * This interface function registers the cpufreq cooling device with the name
  * "thermal-cpufreq-%x". This api can support multiple instances of cpufreq
@@ -891,16 +876,16 @@ free_cpumask:
  * on failure, it returns a corresponding ERR_PTR().
  */
 struct thermal_cooling_device *
-cpufreq_cooling_register(const struct cpumask *clip_cpus)
+cpufreq_cooling_register(struct cpufreq_policy *policy)
 {
-	return __cpufreq_cooling_register(NULL, clip_cpus, 0, NULL);
+	return __cpufreq_cooling_register(NULL, policy, 0, NULL);
 }
 EXPORT_SYMBOL_GPL(cpufreq_cooling_register);
 
 /**
  * of_cpufreq_cooling_register - function to create cpufreq cooling device.
  * @np: a valid struct device_node to the cooling device device tree node
- * @clip_cpus: cpumask of cpus where the frequency constraints will happen.
+ * @policy: cpufreq policy
  *
  * This interface function registers the cpufreq cooling device with the name
  * "thermal-cpufreq-%x". This api can support multiple instances of cpufreq
@@ -912,18 +897,18 @@ EXPORT_SYMBOL_GPL(cpufreq_cooling_register);
  */
 struct thermal_cooling_device *
 of_cpufreq_cooling_register(struct device_node *np,
-			    const struct cpumask *clip_cpus)
+			    struct cpufreq_policy *policy)
 {
 	if (!np)
 		return ERR_PTR(-EINVAL);
 
-	return __cpufreq_cooling_register(np, clip_cpus, 0, NULL);
+	return __cpufreq_cooling_register(np, policy, 0, NULL);
 }
 EXPORT_SYMBOL_GPL(of_cpufreq_cooling_register);
 
 /**
  * cpufreq_power_cooling_register() - create cpufreq cooling device with power extensions
- * @clip_cpus:	cpumask of cpus where the frequency constraints will happen
+ * @policy:		cpufreq policy
  * @capacitance:	dynamic power coefficient for these cpus
  * @plat_static_func:	function to calculate the static power consumed by these
  *			cpus (optional)
@@ -943,10 +928,10 @@ EXPORT_SYMBOL_GPL(of_cpufreq_cooling_register);
  * on failure, it returns a corresponding ERR_PTR().
  */
 struct thermal_cooling_device *
-cpufreq_power_cooling_register(const struct cpumask *clip_cpus, u32 capacitance,
+cpufreq_power_cooling_register(struct cpufreq_policy *policy, u32 capacitance,
 			       get_static_t plat_static_func)
 {
-	return __cpufreq_cooling_register(NULL, clip_cpus, capacitance,
+	return __cpufreq_cooling_register(NULL, policy, capacitance,
 				plat_static_func);
 }
 EXPORT_SYMBOL(cpufreq_power_cooling_register);
@@ -954,7 +939,7 @@ EXPORT_SYMBOL(cpufreq_power_cooling_register);
 /**
  * of_cpufreq_power_cooling_register() - create cpufreq cooling device with power extensions
  * @np:	a valid struct device_node to the cooling device device tree node
- * @clip_cpus:	cpumask of cpus where the frequency constraints will happen
+ * @policy: cpufreq policy
  * @capacitance:	dynamic power coefficient for these cpus
  * @plat_static_func:	function to calculate the static power consumed by these
  *			cpus (optional)
@@ -976,14 +961,14 @@ EXPORT_SYMBOL(cpufreq_power_cooling_register);
  */
 struct thermal_cooling_device *
 of_cpufreq_power_cooling_register(struct device_node *np,
-				  const struct cpumask *clip_cpus,
+				  struct cpufreq_policy *policy,
 				  u32 capacitance,
 				  get_static_t plat_static_func)
 {
 	if (!np)
 		return ERR_PTR(-EINVAL);
 
-	return __cpufreq_cooling_register(np, clip_cpus, capacitance,
+	return __cpufreq_cooling_register(np, policy, capacitance,
 				plat_static_func);
 }
 EXPORT_SYMBOL(of_cpufreq_power_cooling_register);
diff --git a/drivers/thermal/imx_thermal.c b/drivers/thermal/imx_thermal.c
index fb648a45754e..f7ec39f46ee4 100644
--- a/drivers/thermal/imx_thermal.c
+++ b/drivers/thermal/imx_thermal.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/clk.h>
+#include <linux/cpufreq.h>
 #include <linux/cpu_cooling.h>
 #include <linux/delay.h>
 #include <linux/device.h>
@@ -88,6 +89,7 @@ static struct thermal_soc_data thermal_imx6sx_data = {
 };
 
 struct imx_thermal_data {
+	struct cpufreq_policy *policy;
 	struct thermal_zone_device *tz;
 	struct thermal_cooling_device *cdev;
 	enum thermal_device_mode mode;
@@ -525,13 +527,18 @@ static int imx_thermal_probe(struct platform_device *pdev)
 	regmap_write(map, MISC0 + REG_SET, MISC0_REFTOP_SELBIASOFF);
 	regmap_write(map, TEMPSENSE0 + REG_SET, TEMPSENSE0_POWER_DOWN);
 
-	data->cdev = cpufreq_cooling_register(cpu_present_mask);
+	data->policy = cpufreq_cpu_get(0);
+	if (!data->policy) {
+		pr_debug("%s: CPUFreq policy not found\n", __func__);
+		return -EPROBE_DEFER;
+	}
+
+	data->cdev = cpufreq_cooling_register(data->policy);
 	if (IS_ERR(data->cdev)) {
 		ret = PTR_ERR(data->cdev);
-		if (ret != -EPROBE_DEFER)
-			dev_err(&pdev->dev,
-				"failed to register cpufreq cooling device: %d\n",
-				ret);
+		dev_err(&pdev->dev,
+			"failed to register cpufreq cooling device: %d\n", ret);
+		cpufreq_cpu_put(data->policy);
 		return ret;
 	}
 
@@ -542,6 +549,7 @@ static int imx_thermal_probe(struct platform_device *pdev)
 			dev_err(&pdev->dev,
 				"failed to get thermal clk: %d\n", ret);
 		cpufreq_cooling_unregister(data->cdev);
+		cpufreq_cpu_put(data->policy);
 		return ret;
 	}
 
@@ -556,6 +564,7 @@ static int imx_thermal_probe(struct platform_device *pdev)
 	if (ret) {
 		dev_err(&pdev->dev, "failed to enable thermal clk: %d\n", ret);
 		cpufreq_cooling_unregister(data->cdev);
+		cpufreq_cpu_put(data->policy);
 		return ret;
 	}
 
@@ -571,6 +580,7 @@ static int imx_thermal_probe(struct platform_device *pdev)
 			"failed to register thermal zone device %d\n", ret);
 		clk_disable_unprepare(data->thermal_clk);
 		cpufreq_cooling_unregister(data->cdev);
+		cpufreq_cpu_put(data->policy);
 		return ret;
 	}
 
@@ -599,6 +609,7 @@ static int imx_thermal_probe(struct platform_device *pdev)
 		clk_disable_unprepare(data->thermal_clk);
 		thermal_zone_device_unregister(data->tz);
 		cpufreq_cooling_unregister(data->cdev);
+		cpufreq_cpu_put(data->policy);
 		return ret;
 	}
 
@@ -620,6 +631,7 @@ static int imx_thermal_remove(struct platform_device *pdev)
 
 	thermal_zone_device_unregister(data->tz);
 	cpufreq_cooling_unregister(data->cdev);
+	cpufreq_cpu_put(data->policy);
 
 	return 0;
 }
diff --git a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c
index 02790f69e26c..c211a8e4a210 100644
--- a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c
+++ b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c
@@ -28,6 +28,7 @@
 #include <linux/kernel.h>
 #include <linux/workqueue.h>
 #include <linux/thermal.h>
+#include <linux/cpufreq.h>
 #include <linux/cpumask.h>
 #include <linux/cpu_cooling.h>
 #include <linux/of.h>
@@ -37,6 +38,7 @@
 
 /* common data structures */
 struct ti_thermal_data {
+	struct cpufreq_policy *policy;
 	struct thermal_zone_device *ti_thermal;
 	struct thermal_zone_device *pcb_tz;
 	struct thermal_cooling_device *cool_dev;
@@ -247,15 +249,19 @@ int ti_thermal_register_cpu_cooling(struct ti_bandgap *bgp, int id)
 	if (!data)
 		return -EINVAL;
 
+	data->policy = cpufreq_cpu_get(0);
+	if (!data->policy) {
+		pr_debug("%s: CPUFreq policy not found\n", __func__);
+		return -EPROBE_DEFER;
+	}
+
 	/* Register cooling device */
-	data->cool_dev = cpufreq_cooling_register(cpu_present_mask);
+	data->cool_dev = cpufreq_cooling_register(data->policy);
 	if (IS_ERR(data->cool_dev)) {
 		int ret = PTR_ERR(data->cool_dev);
-
-		if (ret != -EPROBE_DEFER)
-			dev_err(bgp->dev,
-				"Failed to register cpu cooling device %d\n",
-				ret);
+		dev_err(bgp->dev, "Failed to register cpu cooling device %d\n",
+			ret);
+		cpufreq_cpu_put(data->policy);
 
 		return ret;
 	}
@@ -270,8 +276,10 @@ int ti_thermal_unregister_cpu_cooling(struct ti_bandgap *bgp, int id)
 
 	data = ti_bandgap_get_sensor_data(bgp, id);
 
-	if (data)
+	if (data) {
 		cpufreq_cooling_unregister(data->cool_dev);
+		cpufreq_cpu_put(data->policy);
+	}
 
 	return 0;
 }
diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h
index 96c5e4c2f9c8..d4292ebc5c8b 100644
--- a/include/linux/cpu_cooling.h
+++ b/include/linux/cpu_cooling.h
@@ -28,47 +28,49 @@
 #include <linux/thermal.h>
 #include <linux/cpumask.h>
 
+struct cpufreq_policy;
+
 typedef int (*get_static_t)(cpumask_t *cpumask, int interval,
 			    unsigned long voltage, u32 *power);
 
 #ifdef CONFIG_CPU_THERMAL
 /**
  * cpufreq_cooling_register - function to create cpufreq cooling device.
- * @clip_cpus: cpumask of cpus where the frequency constraints will happen
+ * @policy: cpufreq policy.
  */
 struct thermal_cooling_device *
-cpufreq_cooling_register(const struct cpumask *clip_cpus);
+cpufreq_cooling_register(struct cpufreq_policy *policy);
 
 struct thermal_cooling_device *
-cpufreq_power_cooling_register(const struct cpumask *clip_cpus,
+cpufreq_power_cooling_register(struct cpufreq_policy *policy,
 			       u32 capacitance, get_static_t plat_static_func);
 
 /**
  * of_cpufreq_cooling_register - create cpufreq cooling device based on DT.
  * @np: a valid struct device_node to the cooling device device tree node.
- * @clip_cpus: cpumask of cpus where the frequency constraints will happen
+ * @policy: cpufreq policy.
  */
 #ifdef CONFIG_THERMAL_OF
 struct thermal_cooling_device *
 of_cpufreq_cooling_register(struct device_node *np,
-			    const struct cpumask *clip_cpus);
+			    struct cpufreq_policy *policy);
 
 struct thermal_cooling_device *
 of_cpufreq_power_cooling_register(struct device_node *np,
-				  const struct cpumask *clip_cpus,
+				  struct cpufreq_policy *policy,
 				  u32 capacitance,
 				  get_static_t plat_static_func);
 #else
 static inline struct thermal_cooling_device *
 of_cpufreq_cooling_register(struct device_node *np,
-			    const struct cpumask *clip_cpus)
+			    struct cpufreq_policy *policy)
 {
 	return ERR_PTR(-ENOSYS);
 }
 
 static inline struct thermal_cooling_device *
 of_cpufreq_power_cooling_register(struct device_node *np,
-				  const struct cpumask *clip_cpus,
+				  struct cpufreq_policy *policy,
 				  u32 capacitance,
 				  get_static_t plat_static_func)
 {
@@ -84,12 +86,12 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev);
 
 #else /* !CONFIG_CPU_THERMAL */
 static inline struct thermal_cooling_device *
-cpufreq_cooling_register(const struct cpumask *clip_cpus)
+cpufreq_cooling_register(struct cpufreq_policy *policy)
 {
 	return ERR_PTR(-ENOSYS);
 }
 static inline struct thermal_cooling_device *
-cpufreq_power_cooling_register(const struct cpumask *clip_cpus,
+cpufreq_power_cooling_register(struct cpufreq_policy *policy,
 			       u32 capacitance, get_static_t plat_static_func)
 {
 	return NULL;
@@ -97,14 +99,14 @@ cpufreq_power_cooling_register(const struct cpumask *clip_cpus,
 
 static inline struct thermal_cooling_device *
 of_cpufreq_cooling_register(struct device_node *np,
-			    const struct cpumask *clip_cpus)
+			    struct cpufreq_policy *policy)
 {
 	return ERR_PTR(-ENOSYS);
 }
 
 static inline struct thermal_cooling_device *
 of_cpufreq_power_cooling_register(struct device_node *np,
-				  const struct cpumask *clip_cpus,
+				  struct cpufreq_policy *policy,
 				  u32 capacitance,
 				  get_static_t plat_static_func)
 {
-- 
cgit v1.2.3


From 55d852931319d2e3ccde86cd426405231ce6c6ac Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Tue, 25 Apr 2017 15:57:15 +0530
Subject: cpufreq: create cpufreq_table_count_valid_entries()

We need such a routine at two places already, lets create one.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
Tested-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/cpufreq/cpufreq_stats.c | 13 ++++---------
 drivers/thermal/cpu_cooling.c   | 22 +++++++++-------------
 include/linux/cpufreq.h         | 14 ++++++++++++++
 3 files changed, 27 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index f570ead62454..9c3d319dc129 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -170,11 +170,10 @@ void cpufreq_stats_create_table(struct cpufreq_policy *policy)
 	unsigned int i = 0, count = 0, ret = -ENOMEM;
 	struct cpufreq_stats *stats;
 	unsigned int alloc_size;
-	struct cpufreq_frequency_table *pos, *table;
+	struct cpufreq_frequency_table *pos;
 
-	/* We need cpufreq table for creating stats table */
-	table = policy->freq_table;
-	if (unlikely(!table))
+	count = cpufreq_table_count_valid_entries(policy);
+	if (!count)
 		return;
 
 	/* stats already initialized */
@@ -185,10 +184,6 @@ void cpufreq_stats_create_table(struct cpufreq_policy *policy)
 	if (!stats)
 		return;
 
-	/* Find total allocation size */
-	cpufreq_for_each_valid_entry(pos, table)
-		count++;
-
 	alloc_size = count * sizeof(int) + count * sizeof(u64);
 
 	alloc_size += count * count * sizeof(int);
@@ -205,7 +200,7 @@ void cpufreq_stats_create_table(struct cpufreq_policy *policy)
 	stats->max_state = count;
 
 	/* Find valid-unique entries */
-	cpufreq_for_each_valid_entry(pos, table)
+	cpufreq_for_each_valid_entry(pos, policy->freq_table)
 		if (freq_table_get_index(stats, pos->frequency) == -1)
 			stats->freq_table[i++] = pos->frequency;
 
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index 58e58065b650..55ff45c1e917 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -739,7 +739,6 @@ __cpufreq_cooling_register(struct device_node *np,
 	struct thermal_cooling_device *cdev;
 	struct cpufreq_cooling_device *cpufreq_cdev;
 	char dev_name[THERMAL_NAME_LENGTH];
-	struct cpufreq_frequency_table *pos, *table;
 	unsigned int freq, i, num_cpus;
 	int ret;
 	struct thermal_cooling_device_ops *cooling_ops;
@@ -750,9 +749,10 @@ __cpufreq_cooling_register(struct device_node *np,
 		return ERR_PTR(-EINVAL);
 	}
 
-	table = policy->freq_table;
-	if (!table) {
-		pr_debug("%s: CPUFreq table not found\n", __func__);
+	i = cpufreq_table_count_valid_entries(policy);
+	if (!i) {
+		pr_debug("%s: CPUFreq table not found or has no valid entries\n",
+			 __func__);
 		return ERR_PTR(-ENODEV);
 	}
 
@@ -777,20 +777,16 @@ __cpufreq_cooling_register(struct device_node *np,
 		goto free_time_in_idle;
 	}
 
-	/* Find max levels */
-	cpufreq_for_each_valid_entry(pos, table)
-		cpufreq_cdev->max_level++;
+	/* max_level is an index, not a counter */
+	cpufreq_cdev->max_level = i - 1;
 
-	cpufreq_cdev->freq_table = kmalloc(sizeof(*cpufreq_cdev->freq_table) *
-					  cpufreq_cdev->max_level, GFP_KERNEL);
+	cpufreq_cdev->freq_table = kmalloc(sizeof(*cpufreq_cdev->freq_table) * i,
+					  GFP_KERNEL);
 	if (!cpufreq_cdev->freq_table) {
 		cdev = ERR_PTR(-ENOMEM);
 		goto free_time_in_idle_timestamp;
 	}
 
-	/* max_level is an index, not a counter */
-	cpufreq_cdev->max_level--;
-
 	cpumask_copy(&cpufreq_cdev->allowed_cpus, policy->related_cpus);
 
 	if (capacitance) {
@@ -816,7 +812,7 @@ __cpufreq_cooling_register(struct device_node *np,
 
 	/* Fill freq-table in descending order of frequencies */
 	for (i = 0, freq = -1; i <= cpufreq_cdev->max_level; i++) {
-		freq = find_next_max(table, freq);
+		freq = find_next_max(policy->freq_table, freq);
 		cpufreq_cdev->freq_table[i] = freq;
 
 		/* Warn for duplicate entries */
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index a5ce0bbeadb5..eb9abfadaeac 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -862,6 +862,20 @@ static inline int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
 		return -EINVAL;
 	}
 }
+
+static inline int cpufreq_table_count_valid_entries(const struct cpufreq_policy *policy)
+{
+	struct cpufreq_frequency_table *pos;
+	int count = 0;
+
+	if (unlikely(!policy->freq_table))
+		return 0;
+
+	cpufreq_for_each_valid_entry(pos, policy->freq_table)
+		count++;
+
+	return count;
+}
 #else
 static inline int cpufreq_boost_trigger_state(int state)
 {
-- 
cgit v1.2.3


From 4a78cc644eed3cf2dae00c3a959910a86c140fd6 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@free-electrons.com>
Date: Fri, 26 May 2017 17:10:15 +0200
Subject: mtd: nand: Make sure drivers not supporting SET/GET_FEATURES return
 -ENOTSUPP

A lot of drivers are providing their own ->cmdfunc(), and most of the
time this implementation does not support all possible NAND operations.
But since ->cmdfunc() cannot return an error code, the core has no way
to know that the operation it requested is not supported.

This is a problem we cannot address for all kind of operations with the
current design, but we can prevent these silent failures for the
GET/SET FEATURES operation by overloading the default
->onfi_{set,get}_features() methods with one returning -ENOTSUPP.

Reported-by: Chris Packham <Chris.Packham@alliedtelesis.co.nz>
Signed-off-by: Boris Brezillon <boris.brezillon@free-electrons.com>
Tested-by: Chris Packham <Chris.Packham@alliedtelesis.co.nz>
---
 drivers/mtd/nand/bcm47xxnflash/ops_bcm4706.c  |  2 ++
 drivers/mtd/nand/cafe_nand.c                  |  2 ++
 drivers/mtd/nand/denali.c                     |  2 ++
 drivers/mtd/nand/docg4.c                      |  2 ++
 drivers/mtd/nand/fsl_elbc_nand.c              |  2 ++
 drivers/mtd/nand/fsl_ifc_nand.c               |  2 ++
 drivers/mtd/nand/hisi504_nand.c               |  2 ++
 drivers/mtd/nand/mpc5121_nfc.c                |  2 ++
 drivers/mtd/nand/nand_base.c                  | 19 +++++++++++++++++++
 drivers/mtd/nand/pxa3xx_nand.c                |  2 ++
 drivers/mtd/nand/qcom_nandc.c                 |  2 ++
 drivers/mtd/nand/sh_flctl.c                   |  2 ++
 drivers/mtd/nand/vf610_nfc.c                  |  2 ++
 drivers/staging/mt29f_spinand/mt29f_spinand.c |  2 ++
 include/linux/mtd/nand.h                      |  5 +++++
 15 files changed, 50 insertions(+)

(limited to 'include')

diff --git a/drivers/mtd/nand/bcm47xxnflash/ops_bcm4706.c b/drivers/mtd/nand/bcm47xxnflash/ops_bcm4706.c
index f1da4ea88f2c..54bac5b73f0a 100644
--- a/drivers/mtd/nand/bcm47xxnflash/ops_bcm4706.c
+++ b/drivers/mtd/nand/bcm47xxnflash/ops_bcm4706.c
@@ -392,6 +392,8 @@ int bcm47xxnflash_ops_bcm4706_init(struct bcm47xxnflash *b47n)
 	b47n->nand_chip.read_byte = bcm47xxnflash_ops_bcm4706_read_byte;
 	b47n->nand_chip.read_buf = bcm47xxnflash_ops_bcm4706_read_buf;
 	b47n->nand_chip.write_buf = bcm47xxnflash_ops_bcm4706_write_buf;
+	b47n->nand_chip.onfi_set_features = nand_onfi_get_set_features_notsupp;
+	b47n->nand_chip.onfi_get_features = nand_onfi_get_set_features_notsupp;
 
 	nand_chip->chip_delay = 50;
 	b47n->nand_chip.bbt_options = NAND_BBT_USE_FLASH;
diff --git a/drivers/mtd/nand/cafe_nand.c b/drivers/mtd/nand/cafe_nand.c
index d40c32d311d8..2fd733eba0a3 100644
--- a/drivers/mtd/nand/cafe_nand.c
+++ b/drivers/mtd/nand/cafe_nand.c
@@ -654,6 +654,8 @@ static int cafe_nand_probe(struct pci_dev *pdev,
 	cafe->nand.read_buf = cafe_read_buf;
 	cafe->nand.write_buf = cafe_write_buf;
 	cafe->nand.select_chip = cafe_select_chip;
+	cafe->nand.onfi_set_features = nand_onfi_get_set_features_notsupp;
+	cafe->nand.onfi_get_features = nand_onfi_get_set_features_notsupp;
 
 	cafe->nand.chip_delay = 0;
 
diff --git a/drivers/mtd/nand/denali.c b/drivers/mtd/nand/denali.c
index 16634df2e39a..b3c99d98fdee 100644
--- a/drivers/mtd/nand/denali.c
+++ b/drivers/mtd/nand/denali.c
@@ -1531,6 +1531,8 @@ int denali_init(struct denali_nand_info *denali)
 	chip->cmdfunc = denali_cmdfunc;
 	chip->read_byte = denali_read_byte;
 	chip->waitfunc = denali_waitfunc;
+	chip->onfi_set_features = nand_onfi_get_set_features_notsupp;
+	chip->onfi_get_features = nand_onfi_get_set_features_notsupp;
 
 	/*
 	 * scan for NAND devices attached to the controller
diff --git a/drivers/mtd/nand/docg4.c b/drivers/mtd/nand/docg4.c
index 7af2a3cd949e..a27a84fbfb84 100644
--- a/drivers/mtd/nand/docg4.c
+++ b/drivers/mtd/nand/docg4.c
@@ -1260,6 +1260,8 @@ static void __init init_mtd_structs(struct mtd_info *mtd)
 	nand->read_buf = docg4_read_buf;
 	nand->write_buf = docg4_write_buf16;
 	nand->erase = docg4_erase_block;
+	nand->onfi_set_features = nand_onfi_get_set_features_notsupp;
+	nand->onfi_get_features = nand_onfi_get_set_features_notsupp;
 	nand->ecc.read_page = docg4_read_page;
 	nand->ecc.write_page = docg4_write_page;
 	nand->ecc.read_page_raw = docg4_read_page_raw;
diff --git a/drivers/mtd/nand/fsl_elbc_nand.c b/drivers/mtd/nand/fsl_elbc_nand.c
index 113f76e59937..b9ac16f05057 100644
--- a/drivers/mtd/nand/fsl_elbc_nand.c
+++ b/drivers/mtd/nand/fsl_elbc_nand.c
@@ -775,6 +775,8 @@ static int fsl_elbc_chip_init(struct fsl_elbc_mtd *priv)
 	chip->select_chip = fsl_elbc_select_chip;
 	chip->cmdfunc = fsl_elbc_cmdfunc;
 	chip->waitfunc = fsl_elbc_wait;
+	chip->onfi_set_features = nand_onfi_get_set_features_notsupp;
+	chip->onfi_get_features = nand_onfi_get_set_features_notsupp;
 
 	chip->bbt_td = &bbt_main_descr;
 	chip->bbt_md = &bbt_mirror_descr;
diff --git a/drivers/mtd/nand/fsl_ifc_nand.c b/drivers/mtd/nand/fsl_ifc_nand.c
index d1570f512f0b..89e14daeaba6 100644
--- a/drivers/mtd/nand/fsl_ifc_nand.c
+++ b/drivers/mtd/nand/fsl_ifc_nand.c
@@ -831,6 +831,8 @@ static int fsl_ifc_chip_init(struct fsl_ifc_mtd *priv)
 	chip->select_chip = fsl_ifc_select_chip;
 	chip->cmdfunc = fsl_ifc_cmdfunc;
 	chip->waitfunc = fsl_ifc_wait;
+	chip->onfi_set_features = nand_onfi_get_set_features_notsupp;
+	chip->onfi_get_features = nand_onfi_get_set_features_notsupp;
 
 	chip->bbt_td = &bbt_main_descr;
 	chip->bbt_md = &bbt_mirror_descr;
diff --git a/drivers/mtd/nand/hisi504_nand.c b/drivers/mtd/nand/hisi504_nand.c
index e40364eeb556..530caa80b1b6 100644
--- a/drivers/mtd/nand/hisi504_nand.c
+++ b/drivers/mtd/nand/hisi504_nand.c
@@ -764,6 +764,8 @@ static int hisi_nfc_probe(struct platform_device *pdev)
 	chip->write_buf		= hisi_nfc_write_buf;
 	chip->read_buf		= hisi_nfc_read_buf;
 	chip->chip_delay	= HINFC504_CHIP_DELAY;
+	chip->onfi_set_features	= nand_onfi_get_set_features_notsupp;
+	chip->onfi_get_features	= nand_onfi_get_set_features_notsupp;
 
 	hisi_nfc_host_init(host);
 
diff --git a/drivers/mtd/nand/mpc5121_nfc.c b/drivers/mtd/nand/mpc5121_nfc.c
index 6d6eaed2d20c..0e86fb6277c3 100644
--- a/drivers/mtd/nand/mpc5121_nfc.c
+++ b/drivers/mtd/nand/mpc5121_nfc.c
@@ -708,6 +708,8 @@ static int mpc5121_nfc_probe(struct platform_device *op)
 	chip->read_buf = mpc5121_nfc_read_buf;
 	chip->write_buf = mpc5121_nfc_write_buf;
 	chip->select_chip = mpc5121_nfc_select_chip;
+	chip->onfi_set_features	= nand_onfi_get_set_features_notsupp;
+	chip->onfi_get_features	= nand_onfi_get_set_features_notsupp;
 	chip->bbt_options = NAND_BBT_USE_FLASH;
 	chip->ecc.mode = NAND_ECC_SOFT;
 	chip->ecc.algo = NAND_ECC_HAMMING;
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index 0b3b1a88091a..ed08e3946727 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -3420,6 +3420,25 @@ static int nand_onfi_get_features(struct mtd_info *mtd, struct nand_chip *chip,
 	return 0;
 }
 
+/**
+ * nand_onfi_get_set_features_notsupp - set/get features stub returning
+ *					-ENOTSUPP
+ * @mtd: MTD device structure
+ * @chip: nand chip info structure
+ * @addr: feature address.
+ * @subfeature_param: the subfeature parameters, a four bytes array.
+ *
+ * Should be used by NAND controller drivers that do not support the SET/GET
+ * FEATURES operations.
+ */
+int nand_onfi_get_set_features_notsupp(struct mtd_info *mtd,
+				       struct nand_chip *chip, int addr,
+				       u8 *subfeature_param)
+{
+	return -ENOTSUPP;
+}
+EXPORT_SYMBOL(nand_onfi_get_set_features_notsupp);
+
 /**
  * nand_suspend - [MTD Interface] Suspend the NAND flash
  * @mtd: MTD device structure
diff --git a/drivers/mtd/nand/pxa3xx_nand.c b/drivers/mtd/nand/pxa3xx_nand.c
index 649ba8200832..74dae4bbdac8 100644
--- a/drivers/mtd/nand/pxa3xx_nand.c
+++ b/drivers/mtd/nand/pxa3xx_nand.c
@@ -1812,6 +1812,8 @@ static int alloc_nand_resource(struct platform_device *pdev)
 		chip->write_buf		= pxa3xx_nand_write_buf;
 		chip->options		|= NAND_NO_SUBPAGE_WRITE;
 		chip->cmdfunc		= nand_cmdfunc;
+		chip->onfi_set_features	= nand_onfi_get_set_features_notsupp;
+		chip->onfi_get_features	= nand_onfi_get_set_features_notsupp;
 	}
 
 	nand_hw_control_init(chip->controller);
diff --git a/drivers/mtd/nand/qcom_nandc.c b/drivers/mtd/nand/qcom_nandc.c
index 57d483ac5765..88af7145a51a 100644
--- a/drivers/mtd/nand/qcom_nandc.c
+++ b/drivers/mtd/nand/qcom_nandc.c
@@ -2008,6 +2008,8 @@ static int qcom_nand_host_init(struct qcom_nand_controller *nandc,
 	chip->read_byte		= qcom_nandc_read_byte;
 	chip->read_buf		= qcom_nandc_read_buf;
 	chip->write_buf		= qcom_nandc_write_buf;
+	chip->onfi_set_features	= nand_onfi_get_set_features_notsupp;
+	chip->onfi_get_features	= nand_onfi_get_set_features_notsupp;
 
 	/*
 	 * the bad block marker is readable only when we read the last codeword
diff --git a/drivers/mtd/nand/sh_flctl.c b/drivers/mtd/nand/sh_flctl.c
index 442ce619b3b6..891ac7b99305 100644
--- a/drivers/mtd/nand/sh_flctl.c
+++ b/drivers/mtd/nand/sh_flctl.c
@@ -1183,6 +1183,8 @@ static int flctl_probe(struct platform_device *pdev)
 	nand->read_buf = flctl_read_buf;
 	nand->select_chip = flctl_select_chip;
 	nand->cmdfunc = flctl_cmdfunc;
+	nand->onfi_set_features = nand_onfi_get_set_features_notsupp;
+	nand->onfi_get_features = nand_onfi_get_set_features_notsupp;
 
 	if (pdata->flcmncr_val & SEL_16BIT)
 		nand->options |= NAND_BUSWIDTH_16;
diff --git a/drivers/mtd/nand/vf610_nfc.c b/drivers/mtd/nand/vf610_nfc.c
index 3ea4bb19e12d..744ab10e8962 100644
--- a/drivers/mtd/nand/vf610_nfc.c
+++ b/drivers/mtd/nand/vf610_nfc.c
@@ -703,6 +703,8 @@ static int vf610_nfc_probe(struct platform_device *pdev)
 	chip->read_buf = vf610_nfc_read_buf;
 	chip->write_buf = vf610_nfc_write_buf;
 	chip->select_chip = vf610_nfc_select_chip;
+	chip->onfi_set_features = nand_onfi_get_set_features_notsupp;
+	chip->onfi_get_features = nand_onfi_get_set_features_notsupp;
 
 	chip->options |= NAND_NO_SUBPAGE_WRITE;
 
diff --git a/drivers/staging/mt29f_spinand/mt29f_spinand.c b/drivers/staging/mt29f_spinand/mt29f_spinand.c
index e389009fca42..a4e3ae8f0c85 100644
--- a/drivers/staging/mt29f_spinand/mt29f_spinand.c
+++ b/drivers/staging/mt29f_spinand/mt29f_spinand.c
@@ -915,6 +915,8 @@ static int spinand_probe(struct spi_device *spi_nand)
 	chip->waitfunc	= spinand_wait;
 	chip->options	|= NAND_CACHEPRG;
 	chip->select_chip = spinand_select_chip;
+	chip->onfi_set_features = nand_onfi_get_set_features_notsupp;
+	chip->onfi_get_features = nand_onfi_get_set_features_notsupp;
 
 	mtd = nand_to_mtd(chip);
 
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 7a01d2eb7443..28f7dd9177e9 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -1259,6 +1259,11 @@ int nand_read_oob_std(struct mtd_info *mtd, struct nand_chip *chip, int page);
 int nand_read_oob_syndrome(struct mtd_info *mtd, struct nand_chip *chip,
 			   int page);
 
+/* Stub used by drivers that do not support GET/SET FEATURES operations */
+int nand_onfi_get_set_features_notsupp(struct mtd_info *mtd,
+				       struct nand_chip *chip, int addr,
+				       u8 *subfeature_param);
+
 /* Default read_page_raw implementation */
 int nand_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
 		       uint8_t *buf, int oob_required, int page);
-- 
cgit v1.2.3


From 22c78d1cce104072747023d2ae0351bf3f97d725 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa@the-dreams.de>
Date: Tue, 23 May 2017 12:27:17 +0200
Subject: i2c: break out smbus support into separate file

Break out the exported SMBus functions and the emulation layer into a
separate file. This also involved splitting up the tracing header into
an I2C and an SMBus part.

Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
---
 Documentation/driver-api/i2c.rst |   3 +
 drivers/i2c/Makefile             |   2 +-
 drivers/i2c/i2c-core-base.c      | 574 -------------------------------------
 drivers/i2c/i2c-core-smbus.c     | 594 +++++++++++++++++++++++++++++++++++++++
 include/trace/events/i2c.h       | 226 +--------------
 include/trace/events/smbus.h     | 249 ++++++++++++++++
 6 files changed, 849 insertions(+), 799 deletions(-)
 create mode 100644 drivers/i2c/i2c-core-smbus.c
 create mode 100644 include/trace/events/smbus.h

(limited to 'include')

diff --git a/Documentation/driver-api/i2c.rst b/Documentation/driver-api/i2c.rst
index e6d4808ffbab..c215503801f0 100644
--- a/Documentation/driver-api/i2c.rst
+++ b/Documentation/driver-api/i2c.rst
@@ -44,3 +44,6 @@ i2c_adapter devices which don't support those I2C operations.
 
 .. kernel-doc:: drivers/i2c/i2c-core-base.c
    :export:
+
+.. kernel-doc:: drivers/i2c/i2c-core-smbus.c
+   :export:
diff --git a/drivers/i2c/Makefile b/drivers/i2c/Makefile
index 6c54716e7f28..a6a90fe2db88 100644
--- a/drivers/i2c/Makefile
+++ b/drivers/i2c/Makefile
@@ -4,7 +4,7 @@
 
 obj-$(CONFIG_I2C_BOARDINFO)	+= i2c-boardinfo.o
 obj-$(CONFIG_I2C)		+= i2c-core.o
-i2c-core-objs 			:= i2c-core-base.o
+i2c-core-objs 			:= i2c-core-base.o i2c-core-smbus.o
 i2c-core-$(CONFIG_I2C_SLAVE) 	+= i2c-core-slave.o
 
 obj-$(CONFIG_I2C_SMBUS)		+= i2c-smbus.o
diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
index 88c0ca664a7b..70fc4624c69c 100644
--- a/drivers/i2c/i2c-core-base.c
+++ b/drivers/i2c/i2c-core-base.c
@@ -14,9 +14,6 @@
 /* ------------------------------------------------------------------------- */
 
 /* With some changes from Kyösti Mälkki <kmalkki@cc.hut.fi>.
-   All SMBus-related things are written by Frodo Looijaard <frodol@dds.nl>
-   SMBus 2.0 support by Mark Studebaker <mdsxyz123@yahoo.com> and
-   Jean Delvare <jdelvare@suse.de>
    Mux support by Rodolfo Giometti <giometti@enneenne.com> and
    Michael Lawnick <michael.lawnick.ext@nsn.com>
    OF support is copyright (c) 2008 Jochen Friedrich <jochen@scram.de>
@@ -3155,577 +3152,6 @@ void i2c_put_adapter(struct i2c_adapter *adap)
 }
 EXPORT_SYMBOL(i2c_put_adapter);
 
-/* The SMBus parts */
-
-#define POLY    (0x1070U << 3)
-static u8 crc8(u16 data)
-{
-	int i;
-
-	for (i = 0; i < 8; i++) {
-		if (data & 0x8000)
-			data = data ^ POLY;
-		data = data << 1;
-	}
-	return (u8)(data >> 8);
-}
-
-/* Incremental CRC8 over count bytes in the array pointed to by p */
-static u8 i2c_smbus_pec(u8 crc, u8 *p, size_t count)
-{
-	int i;
-
-	for (i = 0; i < count; i++)
-		crc = crc8((crc ^ p[i]) << 8);
-	return crc;
-}
-
-/* Assume a 7-bit address, which is reasonable for SMBus */
-static u8 i2c_smbus_msg_pec(u8 pec, struct i2c_msg *msg)
-{
-	/* The address will be sent first */
-	u8 addr = i2c_8bit_addr_from_msg(msg);
-	pec = i2c_smbus_pec(pec, &addr, 1);
-
-	/* The data buffer follows */
-	return i2c_smbus_pec(pec, msg->buf, msg->len);
-}
-
-/* Used for write only transactions */
-static inline void i2c_smbus_add_pec(struct i2c_msg *msg)
-{
-	msg->buf[msg->len] = i2c_smbus_msg_pec(0, msg);
-	msg->len++;
-}
-
-/* Return <0 on CRC error
-   If there was a write before this read (most cases) we need to take the
-   partial CRC from the write part into account.
-   Note that this function does modify the message (we need to decrease the
-   message length to hide the CRC byte from the caller). */
-static int i2c_smbus_check_pec(u8 cpec, struct i2c_msg *msg)
-{
-	u8 rpec = msg->buf[--msg->len];
-	cpec = i2c_smbus_msg_pec(cpec, msg);
-
-	if (rpec != cpec) {
-		pr_debug("Bad PEC 0x%02x vs. 0x%02x\n",
-			rpec, cpec);
-		return -EBADMSG;
-	}
-	return 0;
-}
-
-/**
- * i2c_smbus_read_byte - SMBus "receive byte" protocol
- * @client: Handle to slave device
- *
- * This executes the SMBus "receive byte" protocol, returning negative errno
- * else the byte received from the device.
- */
-s32 i2c_smbus_read_byte(const struct i2c_client *client)
-{
-	union i2c_smbus_data data;
-	int status;
-
-	status = i2c_smbus_xfer(client->adapter, client->addr, client->flags,
-				I2C_SMBUS_READ, 0,
-				I2C_SMBUS_BYTE, &data);
-	return (status < 0) ? status : data.byte;
-}
-EXPORT_SYMBOL(i2c_smbus_read_byte);
-
-/**
- * i2c_smbus_write_byte - SMBus "send byte" protocol
- * @client: Handle to slave device
- * @value: Byte to be sent
- *
- * This executes the SMBus "send byte" protocol, returning negative errno
- * else zero on success.
- */
-s32 i2c_smbus_write_byte(const struct i2c_client *client, u8 value)
-{
-	return i2c_smbus_xfer(client->adapter, client->addr, client->flags,
-	                      I2C_SMBUS_WRITE, value, I2C_SMBUS_BYTE, NULL);
-}
-EXPORT_SYMBOL(i2c_smbus_write_byte);
-
-/**
- * i2c_smbus_read_byte_data - SMBus "read byte" protocol
- * @client: Handle to slave device
- * @command: Byte interpreted by slave
- *
- * This executes the SMBus "read byte" protocol, returning negative errno
- * else a data byte received from the device.
- */
-s32 i2c_smbus_read_byte_data(const struct i2c_client *client, u8 command)
-{
-	union i2c_smbus_data data;
-	int status;
-
-	status = i2c_smbus_xfer(client->adapter, client->addr, client->flags,
-				I2C_SMBUS_READ, command,
-				I2C_SMBUS_BYTE_DATA, &data);
-	return (status < 0) ? status : data.byte;
-}
-EXPORT_SYMBOL(i2c_smbus_read_byte_data);
-
-/**
- * i2c_smbus_write_byte_data - SMBus "write byte" protocol
- * @client: Handle to slave device
- * @command: Byte interpreted by slave
- * @value: Byte being written
- *
- * This executes the SMBus "write byte" protocol, returning negative errno
- * else zero on success.
- */
-s32 i2c_smbus_write_byte_data(const struct i2c_client *client, u8 command,
-			      u8 value)
-{
-	union i2c_smbus_data data;
-	data.byte = value;
-	return i2c_smbus_xfer(client->adapter, client->addr, client->flags,
-			      I2C_SMBUS_WRITE, command,
-			      I2C_SMBUS_BYTE_DATA, &data);
-}
-EXPORT_SYMBOL(i2c_smbus_write_byte_data);
-
-/**
- * i2c_smbus_read_word_data - SMBus "read word" protocol
- * @client: Handle to slave device
- * @command: Byte interpreted by slave
- *
- * This executes the SMBus "read word" protocol, returning negative errno
- * else a 16-bit unsigned "word" received from the device.
- */
-s32 i2c_smbus_read_word_data(const struct i2c_client *client, u8 command)
-{
-	union i2c_smbus_data data;
-	int status;
-
-	status = i2c_smbus_xfer(client->adapter, client->addr, client->flags,
-				I2C_SMBUS_READ, command,
-				I2C_SMBUS_WORD_DATA, &data);
-	return (status < 0) ? status : data.word;
-}
-EXPORT_SYMBOL(i2c_smbus_read_word_data);
-
-/**
- * i2c_smbus_write_word_data - SMBus "write word" protocol
- * @client: Handle to slave device
- * @command: Byte interpreted by slave
- * @value: 16-bit "word" being written
- *
- * This executes the SMBus "write word" protocol, returning negative errno
- * else zero on success.
- */
-s32 i2c_smbus_write_word_data(const struct i2c_client *client, u8 command,
-			      u16 value)
-{
-	union i2c_smbus_data data;
-	data.word = value;
-	return i2c_smbus_xfer(client->adapter, client->addr, client->flags,
-			      I2C_SMBUS_WRITE, command,
-			      I2C_SMBUS_WORD_DATA, &data);
-}
-EXPORT_SYMBOL(i2c_smbus_write_word_data);
-
-/**
- * i2c_smbus_read_block_data - SMBus "block read" protocol
- * @client: Handle to slave device
- * @command: Byte interpreted by slave
- * @values: Byte array into which data will be read; big enough to hold
- *	the data returned by the slave.  SMBus allows at most 32 bytes.
- *
- * This executes the SMBus "block read" protocol, returning negative errno
- * else the number of data bytes in the slave's response.
- *
- * Note that using this function requires that the client's adapter support
- * the I2C_FUNC_SMBUS_READ_BLOCK_DATA functionality.  Not all adapter drivers
- * support this; its emulation through I2C messaging relies on a specific
- * mechanism (I2C_M_RECV_LEN) which may not be implemented.
- */
-s32 i2c_smbus_read_block_data(const struct i2c_client *client, u8 command,
-			      u8 *values)
-{
-	union i2c_smbus_data data;
-	int status;
-
-	status = i2c_smbus_xfer(client->adapter, client->addr, client->flags,
-				I2C_SMBUS_READ, command,
-				I2C_SMBUS_BLOCK_DATA, &data);
-	if (status)
-		return status;
-
-	memcpy(values, &data.block[1], data.block[0]);
-	return data.block[0];
-}
-EXPORT_SYMBOL(i2c_smbus_read_block_data);
-
-/**
- * i2c_smbus_write_block_data - SMBus "block write" protocol
- * @client: Handle to slave device
- * @command: Byte interpreted by slave
- * @length: Size of data block; SMBus allows at most 32 bytes
- * @values: Byte array which will be written.
- *
- * This executes the SMBus "block write" protocol, returning negative errno
- * else zero on success.
- */
-s32 i2c_smbus_write_block_data(const struct i2c_client *client, u8 command,
-			       u8 length, const u8 *values)
-{
-	union i2c_smbus_data data;
-
-	if (length > I2C_SMBUS_BLOCK_MAX)
-		length = I2C_SMBUS_BLOCK_MAX;
-	data.block[0] = length;
-	memcpy(&data.block[1], values, length);
-	return i2c_smbus_xfer(client->adapter, client->addr, client->flags,
-			      I2C_SMBUS_WRITE, command,
-			      I2C_SMBUS_BLOCK_DATA, &data);
-}
-EXPORT_SYMBOL(i2c_smbus_write_block_data);
-
-/* Returns the number of read bytes */
-s32 i2c_smbus_read_i2c_block_data(const struct i2c_client *client, u8 command,
-				  u8 length, u8 *values)
-{
-	union i2c_smbus_data data;
-	int status;
-
-	if (length > I2C_SMBUS_BLOCK_MAX)
-		length = I2C_SMBUS_BLOCK_MAX;
-	data.block[0] = length;
-	status = i2c_smbus_xfer(client->adapter, client->addr, client->flags,
-				I2C_SMBUS_READ, command,
-				I2C_SMBUS_I2C_BLOCK_DATA, &data);
-	if (status < 0)
-		return status;
-
-	memcpy(values, &data.block[1], data.block[0]);
-	return data.block[0];
-}
-EXPORT_SYMBOL(i2c_smbus_read_i2c_block_data);
-
-s32 i2c_smbus_write_i2c_block_data(const struct i2c_client *client, u8 command,
-				   u8 length, const u8 *values)
-{
-	union i2c_smbus_data data;
-
-	if (length > I2C_SMBUS_BLOCK_MAX)
-		length = I2C_SMBUS_BLOCK_MAX;
-	data.block[0] = length;
-	memcpy(data.block + 1, values, length);
-	return i2c_smbus_xfer(client->adapter, client->addr, client->flags,
-			      I2C_SMBUS_WRITE, command,
-			      I2C_SMBUS_I2C_BLOCK_DATA, &data);
-}
-EXPORT_SYMBOL(i2c_smbus_write_i2c_block_data);
-
-/* Simulate a SMBus command using the i2c protocol
-   No checking of parameters is done!  */
-static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr,
-				   unsigned short flags,
-				   char read_write, u8 command, int size,
-				   union i2c_smbus_data *data)
-{
-	/* So we need to generate a series of msgs. In the case of writing, we
-	  need to use only one message; when reading, we need two. We initialize
-	  most things with sane defaults, to keep the code below somewhat
-	  simpler. */
-	unsigned char msgbuf0[I2C_SMBUS_BLOCK_MAX+3];
-	unsigned char msgbuf1[I2C_SMBUS_BLOCK_MAX+2];
-	int num = read_write == I2C_SMBUS_READ ? 2 : 1;
-	int i;
-	u8 partial_pec = 0;
-	int status;
-	struct i2c_msg msg[2] = {
-		{
-			.addr = addr,
-			.flags = flags,
-			.len = 1,
-			.buf = msgbuf0,
-		}, {
-			.addr = addr,
-			.flags = flags | I2C_M_RD,
-			.len = 0,
-			.buf = msgbuf1,
-		},
-	};
-
-	msgbuf0[0] = command;
-	switch (size) {
-	case I2C_SMBUS_QUICK:
-		msg[0].len = 0;
-		/* Special case: The read/write field is used as data */
-		msg[0].flags = flags | (read_write == I2C_SMBUS_READ ?
-					I2C_M_RD : 0);
-		num = 1;
-		break;
-	case I2C_SMBUS_BYTE:
-		if (read_write == I2C_SMBUS_READ) {
-			/* Special case: only a read! */
-			msg[0].flags = I2C_M_RD | flags;
-			num = 1;
-		}
-		break;
-	case I2C_SMBUS_BYTE_DATA:
-		if (read_write == I2C_SMBUS_READ)
-			msg[1].len = 1;
-		else {
-			msg[0].len = 2;
-			msgbuf0[1] = data->byte;
-		}
-		break;
-	case I2C_SMBUS_WORD_DATA:
-		if (read_write == I2C_SMBUS_READ)
-			msg[1].len = 2;
-		else {
-			msg[0].len = 3;
-			msgbuf0[1] = data->word & 0xff;
-			msgbuf0[2] = data->word >> 8;
-		}
-		break;
-	case I2C_SMBUS_PROC_CALL:
-		num = 2; /* Special case */
-		read_write = I2C_SMBUS_READ;
-		msg[0].len = 3;
-		msg[1].len = 2;
-		msgbuf0[1] = data->word & 0xff;
-		msgbuf0[2] = data->word >> 8;
-		break;
-	case I2C_SMBUS_BLOCK_DATA:
-		if (read_write == I2C_SMBUS_READ) {
-			msg[1].flags |= I2C_M_RECV_LEN;
-			msg[1].len = 1; /* block length will be added by
-					   the underlying bus driver */
-		} else {
-			msg[0].len = data->block[0] + 2;
-			if (msg[0].len > I2C_SMBUS_BLOCK_MAX + 2) {
-				dev_err(&adapter->dev,
-					"Invalid block write size %d\n",
-					data->block[0]);
-				return -EINVAL;
-			}
-			for (i = 1; i < msg[0].len; i++)
-				msgbuf0[i] = data->block[i-1];
-		}
-		break;
-	case I2C_SMBUS_BLOCK_PROC_CALL:
-		num = 2; /* Another special case */
-		read_write = I2C_SMBUS_READ;
-		if (data->block[0] > I2C_SMBUS_BLOCK_MAX) {
-			dev_err(&adapter->dev,
-				"Invalid block write size %d\n",
-				data->block[0]);
-			return -EINVAL;
-		}
-		msg[0].len = data->block[0] + 2;
-		for (i = 1; i < msg[0].len; i++)
-			msgbuf0[i] = data->block[i-1];
-		msg[1].flags |= I2C_M_RECV_LEN;
-		msg[1].len = 1; /* block length will be added by
-				   the underlying bus driver */
-		break;
-	case I2C_SMBUS_I2C_BLOCK_DATA:
-		if (read_write == I2C_SMBUS_READ) {
-			msg[1].len = data->block[0];
-		} else {
-			msg[0].len = data->block[0] + 1;
-			if (msg[0].len > I2C_SMBUS_BLOCK_MAX + 1) {
-				dev_err(&adapter->dev,
-					"Invalid block write size %d\n",
-					data->block[0]);
-				return -EINVAL;
-			}
-			for (i = 1; i <= data->block[0]; i++)
-				msgbuf0[i] = data->block[i];
-		}
-		break;
-	default:
-		dev_err(&adapter->dev, "Unsupported transaction %d\n", size);
-		return -EOPNOTSUPP;
-	}
-
-	i = ((flags & I2C_CLIENT_PEC) && size != I2C_SMBUS_QUICK
-				      && size != I2C_SMBUS_I2C_BLOCK_DATA);
-	if (i) {
-		/* Compute PEC if first message is a write */
-		if (!(msg[0].flags & I2C_M_RD)) {
-			if (num == 1) /* Write only */
-				i2c_smbus_add_pec(&msg[0]);
-			else /* Write followed by read */
-				partial_pec = i2c_smbus_msg_pec(0, &msg[0]);
-		}
-		/* Ask for PEC if last message is a read */
-		if (msg[num-1].flags & I2C_M_RD)
-			msg[num-1].len++;
-	}
-
-	status = i2c_transfer(adapter, msg, num);
-	if (status < 0)
-		return status;
-
-	/* Check PEC if last message is a read */
-	if (i && (msg[num-1].flags & I2C_M_RD)) {
-		status = i2c_smbus_check_pec(partial_pec, &msg[num-1]);
-		if (status < 0)
-			return status;
-	}
-
-	if (read_write == I2C_SMBUS_READ)
-		switch (size) {
-		case I2C_SMBUS_BYTE:
-			data->byte = msgbuf0[0];
-			break;
-		case I2C_SMBUS_BYTE_DATA:
-			data->byte = msgbuf1[0];
-			break;
-		case I2C_SMBUS_WORD_DATA:
-		case I2C_SMBUS_PROC_CALL:
-			data->word = msgbuf1[0] | (msgbuf1[1] << 8);
-			break;
-		case I2C_SMBUS_I2C_BLOCK_DATA:
-			for (i = 0; i < data->block[0]; i++)
-				data->block[i+1] = msgbuf1[i];
-			break;
-		case I2C_SMBUS_BLOCK_DATA:
-		case I2C_SMBUS_BLOCK_PROC_CALL:
-			for (i = 0; i < msgbuf1[0] + 1; i++)
-				data->block[i] = msgbuf1[i];
-			break;
-		}
-	return 0;
-}
-
-/**
- * i2c_smbus_xfer - execute SMBus protocol operations
- * @adapter: Handle to I2C bus
- * @addr: Address of SMBus slave on that bus
- * @flags: I2C_CLIENT_* flags (usually zero or I2C_CLIENT_PEC)
- * @read_write: I2C_SMBUS_READ or I2C_SMBUS_WRITE
- * @command: Byte interpreted by slave, for protocols which use such bytes
- * @protocol: SMBus protocol operation to execute, such as I2C_SMBUS_PROC_CALL
- * @data: Data to be read or written
- *
- * This executes an SMBus protocol operation, and returns a negative
- * errno code else zero on success.
- */
-s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, unsigned short flags,
-		   char read_write, u8 command, int protocol,
-		   union i2c_smbus_data *data)
-{
-	unsigned long orig_jiffies;
-	int try;
-	s32 res;
-
-	/* If enabled, the following two tracepoints are conditional on
-	 * read_write and protocol.
-	 */
-	trace_smbus_write(adapter, addr, flags, read_write,
-			  command, protocol, data);
-	trace_smbus_read(adapter, addr, flags, read_write,
-			 command, protocol);
-
-	flags &= I2C_M_TEN | I2C_CLIENT_PEC | I2C_CLIENT_SCCB;
-
-	if (adapter->algo->smbus_xfer) {
-		i2c_lock_bus(adapter, I2C_LOCK_SEGMENT);
-
-		/* Retry automatically on arbitration loss */
-		orig_jiffies = jiffies;
-		for (res = 0, try = 0; try <= adapter->retries; try++) {
-			res = adapter->algo->smbus_xfer(adapter, addr, flags,
-							read_write, command,
-							protocol, data);
-			if (res != -EAGAIN)
-				break;
-			if (time_after(jiffies,
-				       orig_jiffies + adapter->timeout))
-				break;
-		}
-		i2c_unlock_bus(adapter, I2C_LOCK_SEGMENT);
-
-		if (res != -EOPNOTSUPP || !adapter->algo->master_xfer)
-			goto trace;
-		/*
-		 * Fall back to i2c_smbus_xfer_emulated if the adapter doesn't
-		 * implement native support for the SMBus operation.
-		 */
-	}
-
-	res = i2c_smbus_xfer_emulated(adapter, addr, flags, read_write,
-				      command, protocol, data);
-
-trace:
-	/* If enabled, the reply tracepoint is conditional on read_write. */
-	trace_smbus_reply(adapter, addr, flags, read_write,
-			  command, protocol, data);
-	trace_smbus_result(adapter, addr, flags, read_write,
-			   command, protocol, res);
-
-	return res;
-}
-EXPORT_SYMBOL(i2c_smbus_xfer);
-
-/**
- * i2c_smbus_read_i2c_block_data_or_emulated - read block or emulate
- * @client: Handle to slave device
- * @command: Byte interpreted by slave
- * @length: Size of data block; SMBus allows at most I2C_SMBUS_BLOCK_MAX bytes
- * @values: Byte array into which data will be read; big enough to hold
- *	the data returned by the slave.  SMBus allows at most
- *	I2C_SMBUS_BLOCK_MAX bytes.
- *
- * This executes the SMBus "block read" protocol if supported by the adapter.
- * If block read is not supported, it emulates it using either word or byte
- * read protocols depending on availability.
- *
- * The addresses of the I2C slave device that are accessed with this function
- * must be mapped to a linear region, so that a block read will have the same
- * effect as a byte read. Before using this function you must double-check
- * if the I2C slave does support exchanging a block transfer with a byte
- * transfer.
- */
-s32 i2c_smbus_read_i2c_block_data_or_emulated(const struct i2c_client *client,
-					      u8 command, u8 length, u8 *values)
-{
-	u8 i = 0;
-	int status;
-
-	if (length > I2C_SMBUS_BLOCK_MAX)
-		length = I2C_SMBUS_BLOCK_MAX;
-
-	if (i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_READ_I2C_BLOCK))
-		return i2c_smbus_read_i2c_block_data(client, command, length, values);
-
-	if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_READ_BYTE_DATA))
-		return -EOPNOTSUPP;
-
-	if (i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_READ_WORD_DATA)) {
-		while ((i + 2) <= length) {
-			status = i2c_smbus_read_word_data(client, command + i);
-			if (status < 0)
-				return status;
-			values[i] = status & 0xff;
-			values[i + 1] = status >> 8;
-			i += 2;
-		}
-	}
-
-	while (i < length) {
-		status = i2c_smbus_read_byte_data(client, command + i);
-		if (status < 0)
-			return status;
-		values[i] = status;
-		i++;
-	}
-
-	return i;
-}
-EXPORT_SYMBOL(i2c_smbus_read_i2c_block_data_or_emulated);
-
 MODULE_AUTHOR("Simon G. Vogl <simon@tk.uni-linz.ac.at>");
 MODULE_DESCRIPTION("I2C-Bus main module");
 MODULE_LICENSE("GPL");
diff --git a/drivers/i2c/i2c-core-smbus.c b/drivers/i2c/i2c-core-smbus.c
new file mode 100644
index 000000000000..10f00a82ec9d
--- /dev/null
+++ b/drivers/i2c/i2c-core-smbus.c
@@ -0,0 +1,594 @@
+/*
+ * Linux I2C core SMBus and SMBus emulation code
+ *
+ * This file contains the SMBus functions which are always included in the I2C
+ * core because they can be emulated via I2C. SMBus specific extensions
+ * (e.g. smbalert) are handled in a seperate i2c-smbus module.
+ *
+ * All SMBus-related things are written by Frodo Looijaard <frodol@dds.nl>
+ * SMBus 2.0 support by Mark Studebaker <mdsxyz123@yahoo.com> and
+ * Jean Delvare <jdelvare@suse.de>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/i2c.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/smbus.h>
+
+
+/* The SMBus parts */
+
+#define POLY    (0x1070U << 3)
+static u8 crc8(u16 data)
+{
+	int i;
+
+	for (i = 0; i < 8; i++) {
+		if (data & 0x8000)
+			data = data ^ POLY;
+		data = data << 1;
+	}
+	return (u8)(data >> 8);
+}
+
+/* Incremental CRC8 over count bytes in the array pointed to by p */
+static u8 i2c_smbus_pec(u8 crc, u8 *p, size_t count)
+{
+	int i;
+
+	for (i = 0; i < count; i++)
+		crc = crc8((crc ^ p[i]) << 8);
+	return crc;
+}
+
+/* Assume a 7-bit address, which is reasonable for SMBus */
+static u8 i2c_smbus_msg_pec(u8 pec, struct i2c_msg *msg)
+{
+	/* The address will be sent first */
+	u8 addr = i2c_8bit_addr_from_msg(msg);
+	pec = i2c_smbus_pec(pec, &addr, 1);
+
+	/* The data buffer follows */
+	return i2c_smbus_pec(pec, msg->buf, msg->len);
+}
+
+/* Used for write only transactions */
+static inline void i2c_smbus_add_pec(struct i2c_msg *msg)
+{
+	msg->buf[msg->len] = i2c_smbus_msg_pec(0, msg);
+	msg->len++;
+}
+
+/* Return <0 on CRC error
+   If there was a write before this read (most cases) we need to take the
+   partial CRC from the write part into account.
+   Note that this function does modify the message (we need to decrease the
+   message length to hide the CRC byte from the caller). */
+static int i2c_smbus_check_pec(u8 cpec, struct i2c_msg *msg)
+{
+	u8 rpec = msg->buf[--msg->len];
+	cpec = i2c_smbus_msg_pec(cpec, msg);
+
+	if (rpec != cpec) {
+		pr_debug("Bad PEC 0x%02x vs. 0x%02x\n",
+			rpec, cpec);
+		return -EBADMSG;
+	}
+	return 0;
+}
+
+/**
+ * i2c_smbus_read_byte - SMBus "receive byte" protocol
+ * @client: Handle to slave device
+ *
+ * This executes the SMBus "receive byte" protocol, returning negative errno
+ * else the byte received from the device.
+ */
+s32 i2c_smbus_read_byte(const struct i2c_client *client)
+{
+	union i2c_smbus_data data;
+	int status;
+
+	status = i2c_smbus_xfer(client->adapter, client->addr, client->flags,
+				I2C_SMBUS_READ, 0,
+				I2C_SMBUS_BYTE, &data);
+	return (status < 0) ? status : data.byte;
+}
+EXPORT_SYMBOL(i2c_smbus_read_byte);
+
+/**
+ * i2c_smbus_write_byte - SMBus "send byte" protocol
+ * @client: Handle to slave device
+ * @value: Byte to be sent
+ *
+ * This executes the SMBus "send byte" protocol, returning negative errno
+ * else zero on success.
+ */
+s32 i2c_smbus_write_byte(const struct i2c_client *client, u8 value)
+{
+	return i2c_smbus_xfer(client->adapter, client->addr, client->flags,
+	                      I2C_SMBUS_WRITE, value, I2C_SMBUS_BYTE, NULL);
+}
+EXPORT_SYMBOL(i2c_smbus_write_byte);
+
+/**
+ * i2c_smbus_read_byte_data - SMBus "read byte" protocol
+ * @client: Handle to slave device
+ * @command: Byte interpreted by slave
+ *
+ * This executes the SMBus "read byte" protocol, returning negative errno
+ * else a data byte received from the device.
+ */
+s32 i2c_smbus_read_byte_data(const struct i2c_client *client, u8 command)
+{
+	union i2c_smbus_data data;
+	int status;
+
+	status = i2c_smbus_xfer(client->adapter, client->addr, client->flags,
+				I2C_SMBUS_READ, command,
+				I2C_SMBUS_BYTE_DATA, &data);
+	return (status < 0) ? status : data.byte;
+}
+EXPORT_SYMBOL(i2c_smbus_read_byte_data);
+
+/**
+ * i2c_smbus_write_byte_data - SMBus "write byte" protocol
+ * @client: Handle to slave device
+ * @command: Byte interpreted by slave
+ * @value: Byte being written
+ *
+ * This executes the SMBus "write byte" protocol, returning negative errno
+ * else zero on success.
+ */
+s32 i2c_smbus_write_byte_data(const struct i2c_client *client, u8 command,
+			      u8 value)
+{
+	union i2c_smbus_data data;
+	data.byte = value;
+	return i2c_smbus_xfer(client->adapter, client->addr, client->flags,
+			      I2C_SMBUS_WRITE, command,
+			      I2C_SMBUS_BYTE_DATA, &data);
+}
+EXPORT_SYMBOL(i2c_smbus_write_byte_data);
+
+/**
+ * i2c_smbus_read_word_data - SMBus "read word" protocol
+ * @client: Handle to slave device
+ * @command: Byte interpreted by slave
+ *
+ * This executes the SMBus "read word" protocol, returning negative errno
+ * else a 16-bit unsigned "word" received from the device.
+ */
+s32 i2c_smbus_read_word_data(const struct i2c_client *client, u8 command)
+{
+	union i2c_smbus_data data;
+	int status;
+
+	status = i2c_smbus_xfer(client->adapter, client->addr, client->flags,
+				I2C_SMBUS_READ, command,
+				I2C_SMBUS_WORD_DATA, &data);
+	return (status < 0) ? status : data.word;
+}
+EXPORT_SYMBOL(i2c_smbus_read_word_data);
+
+/**
+ * i2c_smbus_write_word_data - SMBus "write word" protocol
+ * @client: Handle to slave device
+ * @command: Byte interpreted by slave
+ * @value: 16-bit "word" being written
+ *
+ * This executes the SMBus "write word" protocol, returning negative errno
+ * else zero on success.
+ */
+s32 i2c_smbus_write_word_data(const struct i2c_client *client, u8 command,
+			      u16 value)
+{
+	union i2c_smbus_data data;
+	data.word = value;
+	return i2c_smbus_xfer(client->adapter, client->addr, client->flags,
+			      I2C_SMBUS_WRITE, command,
+			      I2C_SMBUS_WORD_DATA, &data);
+}
+EXPORT_SYMBOL(i2c_smbus_write_word_data);
+
+/**
+ * i2c_smbus_read_block_data - SMBus "block read" protocol
+ * @client: Handle to slave device
+ * @command: Byte interpreted by slave
+ * @values: Byte array into which data will be read; big enough to hold
+ *	the data returned by the slave.  SMBus allows at most 32 bytes.
+ *
+ * This executes the SMBus "block read" protocol, returning negative errno
+ * else the number of data bytes in the slave's response.
+ *
+ * Note that using this function requires that the client's adapter support
+ * the I2C_FUNC_SMBUS_READ_BLOCK_DATA functionality.  Not all adapter drivers
+ * support this; its emulation through I2C messaging relies on a specific
+ * mechanism (I2C_M_RECV_LEN) which may not be implemented.
+ */
+s32 i2c_smbus_read_block_data(const struct i2c_client *client, u8 command,
+			      u8 *values)
+{
+	union i2c_smbus_data data;
+	int status;
+
+	status = i2c_smbus_xfer(client->adapter, client->addr, client->flags,
+				I2C_SMBUS_READ, command,
+				I2C_SMBUS_BLOCK_DATA, &data);
+	if (status)
+		return status;
+
+	memcpy(values, &data.block[1], data.block[0]);
+	return data.block[0];
+}
+EXPORT_SYMBOL(i2c_smbus_read_block_data);
+
+/**
+ * i2c_smbus_write_block_data - SMBus "block write" protocol
+ * @client: Handle to slave device
+ * @command: Byte interpreted by slave
+ * @length: Size of data block; SMBus allows at most 32 bytes
+ * @values: Byte array which will be written.
+ *
+ * This executes the SMBus "block write" protocol, returning negative errno
+ * else zero on success.
+ */
+s32 i2c_smbus_write_block_data(const struct i2c_client *client, u8 command,
+			       u8 length, const u8 *values)
+{
+	union i2c_smbus_data data;
+
+	if (length > I2C_SMBUS_BLOCK_MAX)
+		length = I2C_SMBUS_BLOCK_MAX;
+	data.block[0] = length;
+	memcpy(&data.block[1], values, length);
+	return i2c_smbus_xfer(client->adapter, client->addr, client->flags,
+			      I2C_SMBUS_WRITE, command,
+			      I2C_SMBUS_BLOCK_DATA, &data);
+}
+EXPORT_SYMBOL(i2c_smbus_write_block_data);
+
+/* Returns the number of read bytes */
+s32 i2c_smbus_read_i2c_block_data(const struct i2c_client *client, u8 command,
+				  u8 length, u8 *values)
+{
+	union i2c_smbus_data data;
+	int status;
+
+	if (length > I2C_SMBUS_BLOCK_MAX)
+		length = I2C_SMBUS_BLOCK_MAX;
+	data.block[0] = length;
+	status = i2c_smbus_xfer(client->adapter, client->addr, client->flags,
+				I2C_SMBUS_READ, command,
+				I2C_SMBUS_I2C_BLOCK_DATA, &data);
+	if (status < 0)
+		return status;
+
+	memcpy(values, &data.block[1], data.block[0]);
+	return data.block[0];
+}
+EXPORT_SYMBOL(i2c_smbus_read_i2c_block_data);
+
+s32 i2c_smbus_write_i2c_block_data(const struct i2c_client *client, u8 command,
+				   u8 length, const u8 *values)
+{
+	union i2c_smbus_data data;
+
+	if (length > I2C_SMBUS_BLOCK_MAX)
+		length = I2C_SMBUS_BLOCK_MAX;
+	data.block[0] = length;
+	memcpy(data.block + 1, values, length);
+	return i2c_smbus_xfer(client->adapter, client->addr, client->flags,
+			      I2C_SMBUS_WRITE, command,
+			      I2C_SMBUS_I2C_BLOCK_DATA, &data);
+}
+EXPORT_SYMBOL(i2c_smbus_write_i2c_block_data);
+
+/* Simulate a SMBus command using the i2c protocol
+   No checking of parameters is done!  */
+static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr,
+				   unsigned short flags,
+				   char read_write, u8 command, int size,
+				   union i2c_smbus_data *data)
+{
+	/* So we need to generate a series of msgs. In the case of writing, we
+	  need to use only one message; when reading, we need two. We initialize
+	  most things with sane defaults, to keep the code below somewhat
+	  simpler. */
+	unsigned char msgbuf0[I2C_SMBUS_BLOCK_MAX+3];
+	unsigned char msgbuf1[I2C_SMBUS_BLOCK_MAX+2];
+	int num = read_write == I2C_SMBUS_READ ? 2 : 1;
+	int i;
+	u8 partial_pec = 0;
+	int status;
+	struct i2c_msg msg[2] = {
+		{
+			.addr = addr,
+			.flags = flags,
+			.len = 1,
+			.buf = msgbuf0,
+		}, {
+			.addr = addr,
+			.flags = flags | I2C_M_RD,
+			.len = 0,
+			.buf = msgbuf1,
+		},
+	};
+
+	msgbuf0[0] = command;
+	switch (size) {
+	case I2C_SMBUS_QUICK:
+		msg[0].len = 0;
+		/* Special case: The read/write field is used as data */
+		msg[0].flags = flags | (read_write == I2C_SMBUS_READ ?
+					I2C_M_RD : 0);
+		num = 1;
+		break;
+	case I2C_SMBUS_BYTE:
+		if (read_write == I2C_SMBUS_READ) {
+			/* Special case: only a read! */
+			msg[0].flags = I2C_M_RD | flags;
+			num = 1;
+		}
+		break;
+	case I2C_SMBUS_BYTE_DATA:
+		if (read_write == I2C_SMBUS_READ)
+			msg[1].len = 1;
+		else {
+			msg[0].len = 2;
+			msgbuf0[1] = data->byte;
+		}
+		break;
+	case I2C_SMBUS_WORD_DATA:
+		if (read_write == I2C_SMBUS_READ)
+			msg[1].len = 2;
+		else {
+			msg[0].len = 3;
+			msgbuf0[1] = data->word & 0xff;
+			msgbuf0[2] = data->word >> 8;
+		}
+		break;
+	case I2C_SMBUS_PROC_CALL:
+		num = 2; /* Special case */
+		read_write = I2C_SMBUS_READ;
+		msg[0].len = 3;
+		msg[1].len = 2;
+		msgbuf0[1] = data->word & 0xff;
+		msgbuf0[2] = data->word >> 8;
+		break;
+	case I2C_SMBUS_BLOCK_DATA:
+		if (read_write == I2C_SMBUS_READ) {
+			msg[1].flags |= I2C_M_RECV_LEN;
+			msg[1].len = 1; /* block length will be added by
+					   the underlying bus driver */
+		} else {
+			msg[0].len = data->block[0] + 2;
+			if (msg[0].len > I2C_SMBUS_BLOCK_MAX + 2) {
+				dev_err(&adapter->dev,
+					"Invalid block write size %d\n",
+					data->block[0]);
+				return -EINVAL;
+			}
+			for (i = 1; i < msg[0].len; i++)
+				msgbuf0[i] = data->block[i-1];
+		}
+		break;
+	case I2C_SMBUS_BLOCK_PROC_CALL:
+		num = 2; /* Another special case */
+		read_write = I2C_SMBUS_READ;
+		if (data->block[0] > I2C_SMBUS_BLOCK_MAX) {
+			dev_err(&adapter->dev,
+				"Invalid block write size %d\n",
+				data->block[0]);
+			return -EINVAL;
+		}
+		msg[0].len = data->block[0] + 2;
+		for (i = 1; i < msg[0].len; i++)
+			msgbuf0[i] = data->block[i-1];
+		msg[1].flags |= I2C_M_RECV_LEN;
+		msg[1].len = 1; /* block length will be added by
+				   the underlying bus driver */
+		break;
+	case I2C_SMBUS_I2C_BLOCK_DATA:
+		if (read_write == I2C_SMBUS_READ) {
+			msg[1].len = data->block[0];
+		} else {
+			msg[0].len = data->block[0] + 1;
+			if (msg[0].len > I2C_SMBUS_BLOCK_MAX + 1) {
+				dev_err(&adapter->dev,
+					"Invalid block write size %d\n",
+					data->block[0]);
+				return -EINVAL;
+			}
+			for (i = 1; i <= data->block[0]; i++)
+				msgbuf0[i] = data->block[i];
+		}
+		break;
+	default:
+		dev_err(&adapter->dev, "Unsupported transaction %d\n", size);
+		return -EOPNOTSUPP;
+	}
+
+	i = ((flags & I2C_CLIENT_PEC) && size != I2C_SMBUS_QUICK
+				      && size != I2C_SMBUS_I2C_BLOCK_DATA);
+	if (i) {
+		/* Compute PEC if first message is a write */
+		if (!(msg[0].flags & I2C_M_RD)) {
+			if (num == 1) /* Write only */
+				i2c_smbus_add_pec(&msg[0]);
+			else /* Write followed by read */
+				partial_pec = i2c_smbus_msg_pec(0, &msg[0]);
+		}
+		/* Ask for PEC if last message is a read */
+		if (msg[num-1].flags & I2C_M_RD)
+			msg[num-1].len++;
+	}
+
+	status = i2c_transfer(adapter, msg, num);
+	if (status < 0)
+		return status;
+
+	/* Check PEC if last message is a read */
+	if (i && (msg[num-1].flags & I2C_M_RD)) {
+		status = i2c_smbus_check_pec(partial_pec, &msg[num-1]);
+		if (status < 0)
+			return status;
+	}
+
+	if (read_write == I2C_SMBUS_READ)
+		switch (size) {
+		case I2C_SMBUS_BYTE:
+			data->byte = msgbuf0[0];
+			break;
+		case I2C_SMBUS_BYTE_DATA:
+			data->byte = msgbuf1[0];
+			break;
+		case I2C_SMBUS_WORD_DATA:
+		case I2C_SMBUS_PROC_CALL:
+			data->word = msgbuf1[0] | (msgbuf1[1] << 8);
+			break;
+		case I2C_SMBUS_I2C_BLOCK_DATA:
+			for (i = 0; i < data->block[0]; i++)
+				data->block[i+1] = msgbuf1[i];
+			break;
+		case I2C_SMBUS_BLOCK_DATA:
+		case I2C_SMBUS_BLOCK_PROC_CALL:
+			for (i = 0; i < msgbuf1[0] + 1; i++)
+				data->block[i] = msgbuf1[i];
+			break;
+		}
+	return 0;
+}
+
+/**
+ * i2c_smbus_xfer - execute SMBus protocol operations
+ * @adapter: Handle to I2C bus
+ * @addr: Address of SMBus slave on that bus
+ * @flags: I2C_CLIENT_* flags (usually zero or I2C_CLIENT_PEC)
+ * @read_write: I2C_SMBUS_READ or I2C_SMBUS_WRITE
+ * @command: Byte interpreted by slave, for protocols which use such bytes
+ * @protocol: SMBus protocol operation to execute, such as I2C_SMBUS_PROC_CALL
+ * @data: Data to be read or written
+ *
+ * This executes an SMBus protocol operation, and returns a negative
+ * errno code else zero on success.
+ */
+s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, unsigned short flags,
+		   char read_write, u8 command, int protocol,
+		   union i2c_smbus_data *data)
+{
+	unsigned long orig_jiffies;
+	int try;
+	s32 res;
+
+	/* If enabled, the following two tracepoints are conditional on
+	 * read_write and protocol.
+	 */
+	trace_smbus_write(adapter, addr, flags, read_write,
+			  command, protocol, data);
+	trace_smbus_read(adapter, addr, flags, read_write,
+			 command, protocol);
+
+	flags &= I2C_M_TEN | I2C_CLIENT_PEC | I2C_CLIENT_SCCB;
+
+	if (adapter->algo->smbus_xfer) {
+		i2c_lock_bus(adapter, I2C_LOCK_SEGMENT);
+
+		/* Retry automatically on arbitration loss */
+		orig_jiffies = jiffies;
+		for (res = 0, try = 0; try <= adapter->retries; try++) {
+			res = adapter->algo->smbus_xfer(adapter, addr, flags,
+							read_write, command,
+							protocol, data);
+			if (res != -EAGAIN)
+				break;
+			if (time_after(jiffies,
+				       orig_jiffies + adapter->timeout))
+				break;
+		}
+		i2c_unlock_bus(adapter, I2C_LOCK_SEGMENT);
+
+		if (res != -EOPNOTSUPP || !adapter->algo->master_xfer)
+			goto trace;
+		/*
+		 * Fall back to i2c_smbus_xfer_emulated if the adapter doesn't
+		 * implement native support for the SMBus operation.
+		 */
+	}
+
+	res = i2c_smbus_xfer_emulated(adapter, addr, flags, read_write,
+				      command, protocol, data);
+
+trace:
+	/* If enabled, the reply tracepoint is conditional on read_write. */
+	trace_smbus_reply(adapter, addr, flags, read_write,
+			  command, protocol, data);
+	trace_smbus_result(adapter, addr, flags, read_write,
+			   command, protocol, res);
+
+	return res;
+}
+EXPORT_SYMBOL(i2c_smbus_xfer);
+
+/**
+ * i2c_smbus_read_i2c_block_data_or_emulated - read block or emulate
+ * @client: Handle to slave device
+ * @command: Byte interpreted by slave
+ * @length: Size of data block; SMBus allows at most I2C_SMBUS_BLOCK_MAX bytes
+ * @values: Byte array into which data will be read; big enough to hold
+ *	the data returned by the slave.  SMBus allows at most
+ *	I2C_SMBUS_BLOCK_MAX bytes.
+ *
+ * This executes the SMBus "block read" protocol if supported by the adapter.
+ * If block read is not supported, it emulates it using either word or byte
+ * read protocols depending on availability.
+ *
+ * The addresses of the I2C slave device that are accessed with this function
+ * must be mapped to a linear region, so that a block read will have the same
+ * effect as a byte read. Before using this function you must double-check
+ * if the I2C slave does support exchanging a block transfer with a byte
+ * transfer.
+ */
+s32 i2c_smbus_read_i2c_block_data_or_emulated(const struct i2c_client *client,
+					      u8 command, u8 length, u8 *values)
+{
+	u8 i = 0;
+	int status;
+
+	if (length > I2C_SMBUS_BLOCK_MAX)
+		length = I2C_SMBUS_BLOCK_MAX;
+
+	if (i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_READ_I2C_BLOCK))
+		return i2c_smbus_read_i2c_block_data(client, command, length, values);
+
+	if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_READ_BYTE_DATA))
+		return -EOPNOTSUPP;
+
+	if (i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_READ_WORD_DATA)) {
+		while ((i + 2) <= length) {
+			status = i2c_smbus_read_word_data(client, command + i);
+			if (status < 0)
+				return status;
+			values[i] = status & 0xff;
+			values[i + 1] = status >> 8;
+			i += 2;
+		}
+	}
+
+	while (i < length) {
+		status = i2c_smbus_read_byte_data(client, command + i);
+		if (status < 0)
+			return status;
+		values[i] = status;
+		i++;
+	}
+
+	return i;
+}
+EXPORT_SYMBOL(i2c_smbus_read_i2c_block_data_or_emulated);
diff --git a/include/trace/events/i2c.h b/include/trace/events/i2c.h
index 4abb8eab34d3..86a401190df9 100644
--- a/include/trace/events/i2c.h
+++ b/include/trace/events/i2c.h
@@ -1,4 +1,4 @@
-/* I2C and SMBUS message transfer tracepoints
+/* I2C message transfer tracepoints
  *
  * Copyright (C) 2013 Red Hat, Inc. All Rights Reserved.
  * Written by David Howells (dhowells@redhat.com)
@@ -18,7 +18,7 @@
 #include <linux/tracepoint.h>
 
 /*
- * drivers/i2c/i2c-core.c
+ * drivers/i2c/i2c-core-base.c
  */
 extern int i2c_transfer_trace_reg(void);
 extern void i2c_transfer_trace_unreg(void);
@@ -144,228 +144,6 @@ TRACE_EVENT_FN(i2c_result,
 	       i2c_transfer_trace_reg,
 	       i2c_transfer_trace_unreg);
 
-/*
- * i2c_smbus_xfer() write data or procedure call request
- */
-TRACE_EVENT_CONDITION(smbus_write,
-	TP_PROTO(const struct i2c_adapter *adap,
-		 u16 addr, unsigned short flags,
-		 char read_write, u8 command, int protocol,
-		 const union i2c_smbus_data *data),
-	TP_ARGS(adap, addr, flags, read_write, command, protocol, data),
-	TP_CONDITION(read_write == I2C_SMBUS_WRITE ||
-		     protocol == I2C_SMBUS_PROC_CALL ||
-		     protocol == I2C_SMBUS_BLOCK_PROC_CALL),
-	TP_STRUCT__entry(
-		__field(int,	adapter_nr		)
-		__field(__u16,	addr			)
-		__field(__u16,	flags			)
-		__field(__u8,	command			)
-		__field(__u8,	len			)
-		__field(__u32,	protocol		)
-		__array(__u8, buf, I2C_SMBUS_BLOCK_MAX + 2)	),
-	TP_fast_assign(
-		__entry->adapter_nr = adap->nr;
-		__entry->addr = addr;
-		__entry->flags = flags;
-		__entry->command = command;
-		__entry->protocol = protocol;
-
-		switch (protocol) {
-		case I2C_SMBUS_BYTE_DATA:
-			__entry->len = 1;
-			goto copy;
-		case I2C_SMBUS_WORD_DATA:
-		case I2C_SMBUS_PROC_CALL:
-			__entry->len = 2;
-			goto copy;
-		case I2C_SMBUS_BLOCK_DATA:
-		case I2C_SMBUS_BLOCK_PROC_CALL:
-		case I2C_SMBUS_I2C_BLOCK_DATA:
-			__entry->len = data->block[0] + 1;
-		copy:
-			memcpy(__entry->buf, data->block, __entry->len);
-			break;
-		case I2C_SMBUS_QUICK:
-		case I2C_SMBUS_BYTE:
-		case I2C_SMBUS_I2C_BLOCK_BROKEN:
-		default:
-			__entry->len = 0;
-		}
-		       ),
-	TP_printk("i2c-%d a=%03x f=%04x c=%x %s l=%u [%*phD]",
-		  __entry->adapter_nr,
-		  __entry->addr,
-		  __entry->flags,
-		  __entry->command,
-		  __print_symbolic(__entry->protocol,
-				   { I2C_SMBUS_QUICK,		"QUICK"	},
-				   { I2C_SMBUS_BYTE,		"BYTE"	},
-				   { I2C_SMBUS_BYTE_DATA,		"BYTE_DATA" },
-				   { I2C_SMBUS_WORD_DATA,		"WORD_DATA" },
-				   { I2C_SMBUS_PROC_CALL,		"PROC_CALL" },
-				   { I2C_SMBUS_BLOCK_DATA,		"BLOCK_DATA" },
-				   { I2C_SMBUS_I2C_BLOCK_BROKEN,	"I2C_BLOCK_BROKEN" },
-				   { I2C_SMBUS_BLOCK_PROC_CALL,	"BLOCK_PROC_CALL" },
-				   { I2C_SMBUS_I2C_BLOCK_DATA,	"I2C_BLOCK_DATA" }),
-		  __entry->len,
-		  __entry->len, __entry->buf
-		  ));
-
-/*
- * i2c_smbus_xfer() read data request
- */
-TRACE_EVENT_CONDITION(smbus_read,
-	TP_PROTO(const struct i2c_adapter *adap,
-		 u16 addr, unsigned short flags,
-		 char read_write, u8 command, int protocol),
-	TP_ARGS(adap, addr, flags, read_write, command, protocol),
-	TP_CONDITION(!(read_write == I2C_SMBUS_WRITE ||
-		       protocol == I2C_SMBUS_PROC_CALL ||
-		       protocol == I2C_SMBUS_BLOCK_PROC_CALL)),
-	TP_STRUCT__entry(
-		__field(int,	adapter_nr		)
-		__field(__u16,	flags			)
-		__field(__u16,	addr			)
-		__field(__u8,	command			)
-		__field(__u32,	protocol		)
-		__array(__u8, buf, I2C_SMBUS_BLOCK_MAX + 2)	),
-	TP_fast_assign(
-		__entry->adapter_nr = adap->nr;
-		__entry->addr = addr;
-		__entry->flags = flags;
-		__entry->command = command;
-		__entry->protocol = protocol;
-		       ),
-	TP_printk("i2c-%d a=%03x f=%04x c=%x %s",
-		  __entry->adapter_nr,
-		  __entry->addr,
-		  __entry->flags,
-		  __entry->command,
-		  __print_symbolic(__entry->protocol,
-				   { I2C_SMBUS_QUICK,		"QUICK"	},
-				   { I2C_SMBUS_BYTE,		"BYTE"	},
-				   { I2C_SMBUS_BYTE_DATA,		"BYTE_DATA" },
-				   { I2C_SMBUS_WORD_DATA,		"WORD_DATA" },
-				   { I2C_SMBUS_PROC_CALL,		"PROC_CALL" },
-				   { I2C_SMBUS_BLOCK_DATA,		"BLOCK_DATA" },
-				   { I2C_SMBUS_I2C_BLOCK_BROKEN,	"I2C_BLOCK_BROKEN" },
-				   { I2C_SMBUS_BLOCK_PROC_CALL,	"BLOCK_PROC_CALL" },
-				   { I2C_SMBUS_I2C_BLOCK_DATA,	"I2C_BLOCK_DATA" })
-		  ));
-
-/*
- * i2c_smbus_xfer() read data or procedure call reply
- */
-TRACE_EVENT_CONDITION(smbus_reply,
-	TP_PROTO(const struct i2c_adapter *adap,
-		 u16 addr, unsigned short flags,
-		 char read_write, u8 command, int protocol,
-		 const union i2c_smbus_data *data),
-	TP_ARGS(adap, addr, flags, read_write, command, protocol, data),
-	TP_CONDITION(read_write == I2C_SMBUS_READ),
-	TP_STRUCT__entry(
-		__field(int,	adapter_nr		)
-		__field(__u16,	addr			)
-		__field(__u16,	flags			)
-		__field(__u8,	command			)
-		__field(__u8,	len			)
-		__field(__u32,	protocol		)
-		__array(__u8, buf, I2C_SMBUS_BLOCK_MAX + 2)	),
-	TP_fast_assign(
-		__entry->adapter_nr = adap->nr;
-		__entry->addr = addr;
-		__entry->flags = flags;
-		__entry->command = command;
-		__entry->protocol = protocol;
-
-		switch (protocol) {
-		case I2C_SMBUS_BYTE:
-		case I2C_SMBUS_BYTE_DATA:
-			__entry->len = 1;
-			goto copy;
-		case I2C_SMBUS_WORD_DATA:
-		case I2C_SMBUS_PROC_CALL:
-			__entry->len = 2;
-			goto copy;
-		case I2C_SMBUS_BLOCK_DATA:
-		case I2C_SMBUS_BLOCK_PROC_CALL:
-		case I2C_SMBUS_I2C_BLOCK_DATA:
-			__entry->len = data->block[0] + 1;
-		copy:
-			memcpy(__entry->buf, data->block, __entry->len);
-			break;
-		case I2C_SMBUS_QUICK:
-		case I2C_SMBUS_I2C_BLOCK_BROKEN:
-		default:
-			__entry->len = 0;
-		}
-		       ),
-	TP_printk("i2c-%d a=%03x f=%04x c=%x %s l=%u [%*phD]",
-		  __entry->adapter_nr,
-		  __entry->addr,
-		  __entry->flags,
-		  __entry->command,
-		  __print_symbolic(__entry->protocol,
-				   { I2C_SMBUS_QUICK,		"QUICK"	},
-				   { I2C_SMBUS_BYTE,		"BYTE"	},
-				   { I2C_SMBUS_BYTE_DATA,		"BYTE_DATA" },
-				   { I2C_SMBUS_WORD_DATA,		"WORD_DATA" },
-				   { I2C_SMBUS_PROC_CALL,		"PROC_CALL" },
-				   { I2C_SMBUS_BLOCK_DATA,		"BLOCK_DATA" },
-				   { I2C_SMBUS_I2C_BLOCK_BROKEN,	"I2C_BLOCK_BROKEN" },
-				   { I2C_SMBUS_BLOCK_PROC_CALL,	"BLOCK_PROC_CALL" },
-				   { I2C_SMBUS_I2C_BLOCK_DATA,	"I2C_BLOCK_DATA" }),
-		  __entry->len,
-		  __entry->len, __entry->buf
-		  ));
-
-/*
- * i2c_smbus_xfer() result
- */
-TRACE_EVENT(smbus_result,
-	    TP_PROTO(const struct i2c_adapter *adap,
-		     u16 addr, unsigned short flags,
-		     char read_write, u8 command, int protocol,
-		     int res),
-	    TP_ARGS(adap, addr, flags, read_write, command, protocol, res),
-	    TP_STRUCT__entry(
-		    __field(int,	adapter_nr		)
-		    __field(__u16,	addr			)
-		    __field(__u16,	flags			)
-		    __field(__u8,	read_write		)
-		    __field(__u8,	command			)
-		    __field(__s16,	res			)
-		    __field(__u32,	protocol		)
-			     ),
-	    TP_fast_assign(
-		    __entry->adapter_nr = adap->nr;
-		    __entry->addr = addr;
-		    __entry->flags = flags;
-		    __entry->read_write = read_write;
-		    __entry->command = command;
-		    __entry->protocol = protocol;
-		    __entry->res = res;
-			   ),
-	    TP_printk("i2c-%d a=%03x f=%04x c=%x %s %s res=%d",
-		      __entry->adapter_nr,
-		      __entry->addr,
-		      __entry->flags,
-		      __entry->command,
-		      __print_symbolic(__entry->protocol,
-				       { I2C_SMBUS_QUICK,		"QUICK"	},
-				       { I2C_SMBUS_BYTE,		"BYTE"	},
-				       { I2C_SMBUS_BYTE_DATA,		"BYTE_DATA" },
-				       { I2C_SMBUS_WORD_DATA,		"WORD_DATA" },
-				       { I2C_SMBUS_PROC_CALL,		"PROC_CALL" },
-				       { I2C_SMBUS_BLOCK_DATA,		"BLOCK_DATA" },
-				       { I2C_SMBUS_I2C_BLOCK_BROKEN,	"I2C_BLOCK_BROKEN" },
-				       { I2C_SMBUS_BLOCK_PROC_CALL,	"BLOCK_PROC_CALL" },
-				       { I2C_SMBUS_I2C_BLOCK_DATA,	"I2C_BLOCK_DATA" }),
-		      __entry->read_write == I2C_SMBUS_WRITE ? "wr" : "rd",
-		      __entry->res
-		      ));
-
 #endif /* _TRACE_I2C_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/smbus.h b/include/trace/events/smbus.h
new file mode 100644
index 000000000000..d2fb6e1d3e10
--- /dev/null
+++ b/include/trace/events/smbus.h
@@ -0,0 +1,249 @@
+/* SMBUS message transfer tracepoints
+ *
+ * Copyright (C) 2013 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM smbus
+
+#if !defined(_TRACE_SMBUS_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_SMBUS_H
+
+#include <linux/i2c.h>
+#include <linux/tracepoint.h>
+
+/*
+ * drivers/i2c/i2c-core-smbus.c
+ */
+
+/*
+ * i2c_smbus_xfer() write data or procedure call request
+ */
+TRACE_EVENT_CONDITION(smbus_write,
+	TP_PROTO(const struct i2c_adapter *adap,
+		 u16 addr, unsigned short flags,
+		 char read_write, u8 command, int protocol,
+		 const union i2c_smbus_data *data),
+	TP_ARGS(adap, addr, flags, read_write, command, protocol, data),
+	TP_CONDITION(read_write == I2C_SMBUS_WRITE ||
+		     protocol == I2C_SMBUS_PROC_CALL ||
+		     protocol == I2C_SMBUS_BLOCK_PROC_CALL),
+	TP_STRUCT__entry(
+		__field(int,	adapter_nr		)
+		__field(__u16,	addr			)
+		__field(__u16,	flags			)
+		__field(__u8,	command			)
+		__field(__u8,	len			)
+		__field(__u32,	protocol		)
+		__array(__u8, buf, I2C_SMBUS_BLOCK_MAX + 2)	),
+	TP_fast_assign(
+		__entry->adapter_nr = adap->nr;
+		__entry->addr = addr;
+		__entry->flags = flags;
+		__entry->command = command;
+		__entry->protocol = protocol;
+
+		switch (protocol) {
+		case I2C_SMBUS_BYTE_DATA:
+			__entry->len = 1;
+			goto copy;
+		case I2C_SMBUS_WORD_DATA:
+		case I2C_SMBUS_PROC_CALL:
+			__entry->len = 2;
+			goto copy;
+		case I2C_SMBUS_BLOCK_DATA:
+		case I2C_SMBUS_BLOCK_PROC_CALL:
+		case I2C_SMBUS_I2C_BLOCK_DATA:
+			__entry->len = data->block[0] + 1;
+		copy:
+			memcpy(__entry->buf, data->block, __entry->len);
+			break;
+		case I2C_SMBUS_QUICK:
+		case I2C_SMBUS_BYTE:
+		case I2C_SMBUS_I2C_BLOCK_BROKEN:
+		default:
+			__entry->len = 0;
+		}
+		       ),
+	TP_printk("i2c-%d a=%03x f=%04x c=%x %s l=%u [%*phD]",
+		  __entry->adapter_nr,
+		  __entry->addr,
+		  __entry->flags,
+		  __entry->command,
+		  __print_symbolic(__entry->protocol,
+				   { I2C_SMBUS_QUICK,		"QUICK"	},
+				   { I2C_SMBUS_BYTE,		"BYTE"	},
+				   { I2C_SMBUS_BYTE_DATA,		"BYTE_DATA" },
+				   { I2C_SMBUS_WORD_DATA,		"WORD_DATA" },
+				   { I2C_SMBUS_PROC_CALL,		"PROC_CALL" },
+				   { I2C_SMBUS_BLOCK_DATA,		"BLOCK_DATA" },
+				   { I2C_SMBUS_I2C_BLOCK_BROKEN,	"I2C_BLOCK_BROKEN" },
+				   { I2C_SMBUS_BLOCK_PROC_CALL,	"BLOCK_PROC_CALL" },
+				   { I2C_SMBUS_I2C_BLOCK_DATA,	"I2C_BLOCK_DATA" }),
+		  __entry->len,
+		  __entry->len, __entry->buf
+		  ));
+
+/*
+ * i2c_smbus_xfer() read data request
+ */
+TRACE_EVENT_CONDITION(smbus_read,
+	TP_PROTO(const struct i2c_adapter *adap,
+		 u16 addr, unsigned short flags,
+		 char read_write, u8 command, int protocol),
+	TP_ARGS(adap, addr, flags, read_write, command, protocol),
+	TP_CONDITION(!(read_write == I2C_SMBUS_WRITE ||
+		       protocol == I2C_SMBUS_PROC_CALL ||
+		       protocol == I2C_SMBUS_BLOCK_PROC_CALL)),
+	TP_STRUCT__entry(
+		__field(int,	adapter_nr		)
+		__field(__u16,	flags			)
+		__field(__u16,	addr			)
+		__field(__u8,	command			)
+		__field(__u32,	protocol		)
+		__array(__u8, buf, I2C_SMBUS_BLOCK_MAX + 2)	),
+	TP_fast_assign(
+		__entry->adapter_nr = adap->nr;
+		__entry->addr = addr;
+		__entry->flags = flags;
+		__entry->command = command;
+		__entry->protocol = protocol;
+		       ),
+	TP_printk("i2c-%d a=%03x f=%04x c=%x %s",
+		  __entry->adapter_nr,
+		  __entry->addr,
+		  __entry->flags,
+		  __entry->command,
+		  __print_symbolic(__entry->protocol,
+				   { I2C_SMBUS_QUICK,		"QUICK"	},
+				   { I2C_SMBUS_BYTE,		"BYTE"	},
+				   { I2C_SMBUS_BYTE_DATA,		"BYTE_DATA" },
+				   { I2C_SMBUS_WORD_DATA,		"WORD_DATA" },
+				   { I2C_SMBUS_PROC_CALL,		"PROC_CALL" },
+				   { I2C_SMBUS_BLOCK_DATA,		"BLOCK_DATA" },
+				   { I2C_SMBUS_I2C_BLOCK_BROKEN,	"I2C_BLOCK_BROKEN" },
+				   { I2C_SMBUS_BLOCK_PROC_CALL,	"BLOCK_PROC_CALL" },
+				   { I2C_SMBUS_I2C_BLOCK_DATA,	"I2C_BLOCK_DATA" })
+		  ));
+
+/*
+ * i2c_smbus_xfer() read data or procedure call reply
+ */
+TRACE_EVENT_CONDITION(smbus_reply,
+	TP_PROTO(const struct i2c_adapter *adap,
+		 u16 addr, unsigned short flags,
+		 char read_write, u8 command, int protocol,
+		 const union i2c_smbus_data *data),
+	TP_ARGS(adap, addr, flags, read_write, command, protocol, data),
+	TP_CONDITION(read_write == I2C_SMBUS_READ),
+	TP_STRUCT__entry(
+		__field(int,	adapter_nr		)
+		__field(__u16,	addr			)
+		__field(__u16,	flags			)
+		__field(__u8,	command			)
+		__field(__u8,	len			)
+		__field(__u32,	protocol		)
+		__array(__u8, buf, I2C_SMBUS_BLOCK_MAX + 2)	),
+	TP_fast_assign(
+		__entry->adapter_nr = adap->nr;
+		__entry->addr = addr;
+		__entry->flags = flags;
+		__entry->command = command;
+		__entry->protocol = protocol;
+
+		switch (protocol) {
+		case I2C_SMBUS_BYTE:
+		case I2C_SMBUS_BYTE_DATA:
+			__entry->len = 1;
+			goto copy;
+		case I2C_SMBUS_WORD_DATA:
+		case I2C_SMBUS_PROC_CALL:
+			__entry->len = 2;
+			goto copy;
+		case I2C_SMBUS_BLOCK_DATA:
+		case I2C_SMBUS_BLOCK_PROC_CALL:
+		case I2C_SMBUS_I2C_BLOCK_DATA:
+			__entry->len = data->block[0] + 1;
+		copy:
+			memcpy(__entry->buf, data->block, __entry->len);
+			break;
+		case I2C_SMBUS_QUICK:
+		case I2C_SMBUS_I2C_BLOCK_BROKEN:
+		default:
+			__entry->len = 0;
+		}
+		       ),
+	TP_printk("i2c-%d a=%03x f=%04x c=%x %s l=%u [%*phD]",
+		  __entry->adapter_nr,
+		  __entry->addr,
+		  __entry->flags,
+		  __entry->command,
+		  __print_symbolic(__entry->protocol,
+				   { I2C_SMBUS_QUICK,		"QUICK"	},
+				   { I2C_SMBUS_BYTE,		"BYTE"	},
+				   { I2C_SMBUS_BYTE_DATA,		"BYTE_DATA" },
+				   { I2C_SMBUS_WORD_DATA,		"WORD_DATA" },
+				   { I2C_SMBUS_PROC_CALL,		"PROC_CALL" },
+				   { I2C_SMBUS_BLOCK_DATA,		"BLOCK_DATA" },
+				   { I2C_SMBUS_I2C_BLOCK_BROKEN,	"I2C_BLOCK_BROKEN" },
+				   { I2C_SMBUS_BLOCK_PROC_CALL,	"BLOCK_PROC_CALL" },
+				   { I2C_SMBUS_I2C_BLOCK_DATA,	"I2C_BLOCK_DATA" }),
+		  __entry->len,
+		  __entry->len, __entry->buf
+		  ));
+
+/*
+ * i2c_smbus_xfer() result
+ */
+TRACE_EVENT(smbus_result,
+	    TP_PROTO(const struct i2c_adapter *adap,
+		     u16 addr, unsigned short flags,
+		     char read_write, u8 command, int protocol,
+		     int res),
+	    TP_ARGS(adap, addr, flags, read_write, command, protocol, res),
+	    TP_STRUCT__entry(
+		    __field(int,	adapter_nr		)
+		    __field(__u16,	addr			)
+		    __field(__u16,	flags			)
+		    __field(__u8,	read_write		)
+		    __field(__u8,	command			)
+		    __field(__s16,	res			)
+		    __field(__u32,	protocol		)
+			     ),
+	    TP_fast_assign(
+		    __entry->adapter_nr = adap->nr;
+		    __entry->addr = addr;
+		    __entry->flags = flags;
+		    __entry->read_write = read_write;
+		    __entry->command = command;
+		    __entry->protocol = protocol;
+		    __entry->res = res;
+			   ),
+	    TP_printk("i2c-%d a=%03x f=%04x c=%x %s %s res=%d",
+		      __entry->adapter_nr,
+		      __entry->addr,
+		      __entry->flags,
+		      __entry->command,
+		      __print_symbolic(__entry->protocol,
+				       { I2C_SMBUS_QUICK,		"QUICK"	},
+				       { I2C_SMBUS_BYTE,		"BYTE"	},
+				       { I2C_SMBUS_BYTE_DATA,		"BYTE_DATA" },
+				       { I2C_SMBUS_WORD_DATA,		"WORD_DATA" },
+				       { I2C_SMBUS_PROC_CALL,		"PROC_CALL" },
+				       { I2C_SMBUS_BLOCK_DATA,		"BLOCK_DATA" },
+				       { I2C_SMBUS_I2C_BLOCK_BROKEN,	"I2C_BLOCK_BROKEN" },
+				       { I2C_SMBUS_BLOCK_PROC_CALL,	"BLOCK_PROC_CALL" },
+				       { I2C_SMBUS_I2C_BLOCK_DATA,	"I2C_BLOCK_DATA" }),
+		      __entry->read_write == I2C_SMBUS_WRITE ? "wr" : "rd",
+		      __entry->res
+		      ));
+
+#endif /* _TRACE_SMBUS_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
-- 
cgit v1.2.3


From 9748e1d87573c94191442d6bd0307f523e5cd8b8 Mon Sep 17 00:00:00 2001
From: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Date: Sat, 29 Apr 2017 11:06:45 +0200
Subject: mtd: nand: add support for Micron on-die ECC

Now that the core NAND subsystem has support for on-die ECC, this commit
brings the necessary code to support on-die ECC on Micron NANDs.

In micron_nand_init(), we detect if the Micron NAND chip supports on-die
ECC mode, by checking a number of conditions:

 - It must be an ONFI NAND
 - It must be a SLC NAND

 - Enabling *and* disabling on-die ECC must work

 - The on-die ECC must be correcting 4 bits per 512 bytes of data. Some
   Micron NAND chips have an on-die ECC able to correct 8 bits per 512
   bytes of data, but they work slightly differently and therefore we
   don't support them in this patch.

Then, if the on-die ECC cannot be disabled (some Micron NAND have on-die
ECC forcefully enabled), we bail out, as we don't support such
NANDs. Indeed, the implementation of raw_read()/raw_write() make the
assumption that on-die ECC can be disabled. Support for Micron NANDs
with on-die ECC forcefully enabled can easily be added, but in the
absence of such HW for testing, we preferred to simply bail out.

If the on-die ECC is supported, and requested in the Device Tree, then
it is indeed enabled, by using custom implementations of the
->read_page(), ->read_page_raw(), ->write_page() and ->write_page_raw()
operation to properly handle the on-die ECC.

In the non-raw functions, we need to enable the internal ECC engine
before issuing the NAND_CMD_READ0 or NAND_CMD_SEQIN commands, which is
why we set the NAND_ECC_CUSTOM_PAGE_ACCESS option at initialization
time (it asks the NAND core to let the NAND driver issue those
commands).

Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Signed-off-by: Boris Brezillon <boris.brezillon@free-electrons.com>
---
 drivers/mtd/nand/nand_micron.c | 216 +++++++++++++++++++++++++++++++++++++++++
 include/linux/mtd/nand.h       |   2 +
 2 files changed, 218 insertions(+)

(limited to 'include')

diff --git a/drivers/mtd/nand/nand_micron.c b/drivers/mtd/nand/nand_micron.c
index 877011069251..9993f8ead1e2 100644
--- a/drivers/mtd/nand/nand_micron.c
+++ b/drivers/mtd/nand/nand_micron.c
@@ -17,6 +17,12 @@
 
 #include <linux/mtd/nand.h>
 
+/*
+ * Special Micron status bit that indicates when the block has been
+ * corrected by on-die ECC and should be rewritten
+ */
+#define NAND_STATUS_WRITE_RECOMMENDED	BIT(3)
+
 struct nand_onfi_vendor_micron {
 	u8 two_plane_read;
 	u8 read_cache;
@@ -66,9 +72,191 @@ static int micron_nand_onfi_init(struct nand_chip *chip)
 	return 0;
 }
 
+static int micron_nand_on_die_ooblayout_ecc(struct mtd_info *mtd, int section,
+					    struct mtd_oob_region *oobregion)
+{
+	if (section >= 4)
+		return -ERANGE;
+
+	oobregion->offset = (section * 16) + 8;
+	oobregion->length = 8;
+
+	return 0;
+}
+
+static int micron_nand_on_die_ooblayout_free(struct mtd_info *mtd, int section,
+					     struct mtd_oob_region *oobregion)
+{
+	if (section >= 4)
+		return -ERANGE;
+
+	oobregion->offset = (section * 16) + 2;
+	oobregion->length = 6;
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops micron_nand_on_die_ooblayout_ops = {
+	.ecc = micron_nand_on_die_ooblayout_ecc,
+	.free = micron_nand_on_die_ooblayout_free,
+};
+
+static int micron_nand_on_die_ecc_setup(struct nand_chip *chip, bool enable)
+{
+	u8 feature[ONFI_SUBFEATURE_PARAM_LEN] = { 0, };
+
+	if (enable)
+		feature[0] |= ONFI_FEATURE_ON_DIE_ECC_EN;
+
+	return chip->onfi_set_features(nand_to_mtd(chip), chip,
+				       ONFI_FEATURE_ON_DIE_ECC, feature);
+}
+
+static int
+micron_nand_read_page_on_die_ecc(struct mtd_info *mtd, struct nand_chip *chip,
+				 uint8_t *buf, int oob_required,
+				 int page)
+{
+	int status;
+	int max_bitflips = 0;
+
+	micron_nand_on_die_ecc_setup(chip, true);
+
+	chip->cmdfunc(mtd, NAND_CMD_READ0, 0x00, page);
+	chip->cmdfunc(mtd, NAND_CMD_STATUS, -1, -1);
+	status = chip->read_byte(mtd);
+	if (status & NAND_STATUS_FAIL)
+		mtd->ecc_stats.failed++;
+	/*
+	 * The internal ECC doesn't tell us the number of bitflips
+	 * that have been corrected, but tells us if it recommends to
+	 * rewrite the block. If it's the case, then we pretend we had
+	 * a number of bitflips equal to the ECC strength, which will
+	 * hint the NAND core to rewrite the block.
+	 */
+	else if (status & NAND_STATUS_WRITE_RECOMMENDED)
+		max_bitflips = chip->ecc.strength;
+
+	chip->cmdfunc(mtd, NAND_CMD_READ0, -1, -1);
+
+	nand_read_page_raw(mtd, chip, buf, oob_required, page);
+
+	micron_nand_on_die_ecc_setup(chip, false);
+
+	return max_bitflips;
+}
+
+static int
+micron_nand_write_page_on_die_ecc(struct mtd_info *mtd, struct nand_chip *chip,
+				  const uint8_t *buf, int oob_required,
+				  int page)
+{
+	micron_nand_on_die_ecc_setup(chip, true);
+
+	chip->cmdfunc(mtd, NAND_CMD_SEQIN, 0x00, page);
+	nand_write_page_raw(mtd, chip, buf, oob_required, page);
+	chip->cmdfunc(mtd, NAND_CMD_PAGEPROG, -1, -1);
+
+	micron_nand_on_die_ecc_setup(chip, false);
+
+	return 0;
+}
+
+static int
+micron_nand_read_page_raw_on_die_ecc(struct mtd_info *mtd,
+				     struct nand_chip *chip,
+				     uint8_t *buf, int oob_required,
+				     int page)
+{
+	chip->cmdfunc(mtd, NAND_CMD_READ0, 0x00, page);
+	nand_read_page_raw(mtd, chip, buf, oob_required, page);
+
+	return 0;
+}
+
+static int
+micron_nand_write_page_raw_on_die_ecc(struct mtd_info *mtd,
+				      struct nand_chip *chip,
+				      const uint8_t *buf, int oob_required,
+				      int page)
+{
+	chip->cmdfunc(mtd, NAND_CMD_SEQIN, 0x00, page);
+	nand_write_page_raw(mtd, chip, buf, oob_required, page);
+	chip->cmdfunc(mtd, NAND_CMD_PAGEPROG, -1, -1);
+
+	return 0;
+}
+
+enum {
+	/* The NAND flash doesn't support on-die ECC */
+	MICRON_ON_DIE_UNSUPPORTED,
+
+	/*
+	 * The NAND flash supports on-die ECC and it can be
+	 * enabled/disabled by a set features command.
+	 */
+	MICRON_ON_DIE_SUPPORTED,
+
+	/*
+	 * The NAND flash supports on-die ECC, and it cannot be
+	 * disabled.
+	 */
+	MICRON_ON_DIE_MANDATORY,
+};
+
+/*
+ * Try to detect if the NAND support on-die ECC. To do this, we enable
+ * the feature, and read back if it has been enabled as expected. We
+ * also check if it can be disabled, because some Micron NANDs do not
+ * allow disabling the on-die ECC and we don't support such NANDs for
+ * now.
+ *
+ * This function also has the side effect of disabling on-die ECC if
+ * it had been left enabled by the firmware/bootloader.
+ */
+static int micron_supports_on_die_ecc(struct nand_chip *chip)
+{
+	u8 feature[ONFI_SUBFEATURE_PARAM_LEN] = { 0, };
+	int ret;
+
+	if (chip->onfi_version == 0)
+		return MICRON_ON_DIE_UNSUPPORTED;
+
+	if (chip->bits_per_cell != 1)
+		return MICRON_ON_DIE_UNSUPPORTED;
+
+	ret = micron_nand_on_die_ecc_setup(chip, true);
+	if (ret)
+		return MICRON_ON_DIE_UNSUPPORTED;
+
+	chip->onfi_get_features(nand_to_mtd(chip), chip,
+				ONFI_FEATURE_ON_DIE_ECC, feature);
+	if ((feature[0] & ONFI_FEATURE_ON_DIE_ECC_EN) == 0)
+		return MICRON_ON_DIE_UNSUPPORTED;
+
+	ret = micron_nand_on_die_ecc_setup(chip, false);
+	if (ret)
+		return MICRON_ON_DIE_UNSUPPORTED;
+
+	chip->onfi_get_features(nand_to_mtd(chip), chip,
+				ONFI_FEATURE_ON_DIE_ECC, feature);
+	if (feature[0] & ONFI_FEATURE_ON_DIE_ECC_EN)
+		return MICRON_ON_DIE_MANDATORY;
+
+	/*
+	 * Some Micron NANDs have an on-die ECC of 4/512, some other
+	 * 8/512. We only support the former.
+	 */
+	if (chip->onfi_params.ecc_bits != 4)
+		return MICRON_ON_DIE_UNSUPPORTED;
+
+	return MICRON_ON_DIE_SUPPORTED;
+}
+
 static int micron_nand_init(struct nand_chip *chip)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
+	int ondie;
 	int ret;
 
 	ret = micron_nand_onfi_init(chip);
@@ -78,6 +266,34 @@ static int micron_nand_init(struct nand_chip *chip)
 	if (mtd->writesize == 2048)
 		chip->bbt_options |= NAND_BBT_SCAN2NDPAGE;
 
+	ondie = micron_supports_on_die_ecc(chip);
+
+	if (ondie == MICRON_ON_DIE_MANDATORY) {
+		pr_err("On-die ECC forcefully enabled, not supported\n");
+		return -EINVAL;
+	}
+
+	if (chip->ecc.mode == NAND_ECC_ON_DIE) {
+		if (ondie == MICRON_ON_DIE_UNSUPPORTED) {
+			pr_err("On-die ECC selected but not supported\n");
+			return -EINVAL;
+		}
+
+		chip->ecc.options = NAND_ECC_CUSTOM_PAGE_ACCESS;
+		chip->ecc.bytes = 8;
+		chip->ecc.size = 512;
+		chip->ecc.strength = 4;
+		chip->ecc.algo = NAND_ECC_BCH;
+		chip->ecc.read_page = micron_nand_read_page_on_die_ecc;
+		chip->ecc.write_page = micron_nand_write_page_on_die_ecc;
+		chip->ecc.read_page_raw =
+			micron_nand_read_page_raw_on_die_ecc;
+		chip->ecc.write_page_raw =
+			micron_nand_write_page_raw_on_die_ecc;
+
+		mtd_set_ooblayout(mtd, &micron_nand_on_die_ooblayout_ops);
+	}
+
 	return 0;
 }
 
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 28f7dd9177e9..893d0ce08030 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -258,6 +258,8 @@ struct nand_chip;
 
 /* Vendor-specific feature address (Micron) */
 #define ONFI_FEATURE_ADDR_READ_RETRY	0x89
+#define ONFI_FEATURE_ON_DIE_ECC		0x90
+#define   ONFI_FEATURE_ON_DIE_ECC_EN	BIT(3)
 
 /* ONFI subfeature parameters length */
 #define ONFI_SUBFEATURE_PARAM_LEN	4
-- 
cgit v1.2.3


From 104e442a67cfba4d0cc982384761befb917fb6a1 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@free-electrons.com>
Date: Thu, 16 Mar 2017 09:35:58 +0100
Subject: mtd: nand: Pass the CS line to ->setup_data_interface()

Some NAND controllers can assign different NAND timings to different
CS lines. Pass the CS line information to ->setup_data_interface() so
that the NAND controller driver knows which CS line is concerned by
the setup_data_interface() request.

Signed-off-by: Boris Brezillon <boris.brezillon@free-electrons.com>
---
 drivers/mtd/nand/fsmc_nand.c  |  7 +++----
 drivers/mtd/nand/mxc_nand.c   | 12 +++++-------
 drivers/mtd/nand/nand_base.c  | 22 +++++++++++++---------
 drivers/mtd/nand/s3c2410.c    |  5 ++---
 drivers/mtd/nand/sunxi_nand.c |  7 +++----
 drivers/mtd/nand/tango_nand.c |  7 +++----
 include/linux/mtd/nand.h      | 12 ++++++++----
 7 files changed, 37 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/nand/fsmc_nand.c b/drivers/mtd/nand/fsmc_nand.c
index de57554b8c4f..9d8b051d3187 100644
--- a/drivers/mtd/nand/fsmc_nand.c
+++ b/drivers/mtd/nand/fsmc_nand.c
@@ -388,9 +388,8 @@ static int fsmc_calc_timings(struct fsmc_nand_data *host,
 	return 0;
 }
 
-static int fsmc_setup_data_interface(struct mtd_info *mtd,
-				     const struct nand_data_interface *conf,
-				     bool check_only)
+static int fsmc_setup_data_interface(struct mtd_info *mtd, int csline,
+				     const struct nand_data_interface *conf)
 {
 	struct nand_chip *nand = mtd_to_nand(mtd);
 	struct fsmc_nand_data *host = nand_get_controller_data(nand);
@@ -406,7 +405,7 @@ static int fsmc_setup_data_interface(struct mtd_info *mtd,
 	if (ret)
 		return ret;
 
-	if (check_only)
+	if (csline == NAND_DATA_IFACE_CHECK_ONLY)
 		return 0;
 
 	fsmc_nand_setup(host, &tims);
diff --git a/drivers/mtd/nand/mxc_nand.c b/drivers/mtd/nand/mxc_nand.c
index 61ca020c5272..a764d5ca7536 100644
--- a/drivers/mtd/nand/mxc_nand.c
+++ b/drivers/mtd/nand/mxc_nand.c
@@ -152,9 +152,8 @@ struct mxc_nand_devtype_data {
 	void (*select_chip)(struct mtd_info *mtd, int chip);
 	int (*correct_data)(struct mtd_info *mtd, u_char *dat,
 			u_char *read_ecc, u_char *calc_ecc);
-	int (*setup_data_interface)(struct mtd_info *mtd,
-				    const struct nand_data_interface *conf,
-				    bool check_only);
+	int (*setup_data_interface)(struct mtd_info *mtd, int csline,
+				    const struct nand_data_interface *conf);
 
 	/*
 	 * On i.MX21 the CONFIG2:INT bit cannot be read if interrupts are masked
@@ -1015,9 +1014,8 @@ static void preset_v1(struct mtd_info *mtd)
 	writew(0x4, NFC_V1_V2_WRPROT);
 }
 
-static int mxc_nand_v2_setup_data_interface(struct mtd_info *mtd,
-					const struct nand_data_interface *conf,
-					bool check_only)
+static int mxc_nand_v2_setup_data_interface(struct mtd_info *mtd, int csline,
+					const struct nand_data_interface *conf)
 {
 	struct nand_chip *nand_chip = mtd_to_nand(mtd);
 	struct mxc_nand_host *host = nand_get_controller_data(nand_chip);
@@ -1075,7 +1073,7 @@ static int mxc_nand_v2_setup_data_interface(struct mtd_info *mtd,
 		return -EINVAL;
 	}
 
-	if (check_only)
+	if (csline == NAND_DATA_IFACE_CHECK_ONLY)
 		return 0;
 
 	ret = clk_set_rate(host->clk, rate);
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index 79d98c9fa8a7..3317acf0ce04 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -1042,12 +1042,13 @@ static int nand_wait(struct mtd_info *mtd, struct nand_chip *chip)
 /**
  * nand_reset_data_interface - Reset data interface and timings
  * @chip: The NAND chip
+ * @chipnr: Internal die id
  *
  * Reset the Data interface and timings to ONFI mode 0.
  *
  * Returns 0 for success or negative error code otherwise.
  */
-static int nand_reset_data_interface(struct nand_chip *chip)
+static int nand_reset_data_interface(struct nand_chip *chip, int chipnr)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	const struct nand_data_interface *conf;
@@ -1071,7 +1072,7 @@ static int nand_reset_data_interface(struct nand_chip *chip)
 	 */
 
 	conf = nand_get_default_data_interface();
-	ret = chip->setup_data_interface(mtd, conf, false);
+	ret = chip->setup_data_interface(mtd, chipnr, conf);
 	if (ret)
 		pr_err("Failed to configure data interface to SDR timing mode 0\n");
 
@@ -1081,6 +1082,7 @@ static int nand_reset_data_interface(struct nand_chip *chip)
 /**
  * nand_setup_data_interface - Setup the best data interface and timings
  * @chip: The NAND chip
+ * @chipnr: Internal die id
  *
  * Find and configure the best data interface and NAND timings supported by
  * the chip and the driver.
@@ -1090,7 +1092,7 @@ static int nand_reset_data_interface(struct nand_chip *chip)
  *
  * Returns 0 for success or negative error code otherwise.
  */
-static int nand_setup_data_interface(struct nand_chip *chip)
+static int nand_setup_data_interface(struct nand_chip *chip, int chipnr)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	int ret;
@@ -1114,7 +1116,7 @@ static int nand_setup_data_interface(struct nand_chip *chip)
 			goto err;
 	}
 
-	ret = chip->setup_data_interface(mtd, chip->data_interface, false);
+	ret = chip->setup_data_interface(mtd, chipnr, chip->data_interface);
 err:
 	return ret;
 }
@@ -1165,8 +1167,10 @@ static int nand_init_data_interface(struct nand_chip *chip)
 		if (ret)
 			continue;
 
-		ret = chip->setup_data_interface(mtd, chip->data_interface,
-						 true);
+		/* Pass -1 to only */
+		ret = chip->setup_data_interface(mtd,
+						 NAND_DATA_IFACE_CHECK_ONLY,
+						 chip->data_interface);
 		if (!ret) {
 			chip->onfi_timing_mode_default = mode;
 			break;
@@ -1193,7 +1197,7 @@ int nand_reset(struct nand_chip *chip, int chipnr)
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	int ret;
 
-	ret = nand_reset_data_interface(chip);
+	ret = nand_reset_data_interface(chip, chipnr);
 	if (ret)
 		return ret;
 
@@ -1206,7 +1210,7 @@ int nand_reset(struct nand_chip *chip, int chipnr)
 	chip->select_chip(mtd, -1);
 
 	chip->select_chip(mtd, chipnr);
-	ret = nand_setup_data_interface(chip);
+	ret = nand_setup_data_interface(chip, chipnr);
 	chip->select_chip(mtd, -1);
 	if (ret)
 		return ret;
@@ -4396,7 +4400,7 @@ int nand_scan_ident(struct mtd_info *mtd, int maxchips,
 	 * For the other dies, nand_reset() will automatically switch to the
 	 * best mode for us.
 	 */
-	ret = nand_setup_data_interface(chip);
+	ret = nand_setup_data_interface(chip, 0);
 	if (ret)
 		return ret;
 
diff --git a/drivers/mtd/nand/s3c2410.c b/drivers/mtd/nand/s3c2410.c
index f0b030d44f71..9e0c849607b9 100644
--- a/drivers/mtd/nand/s3c2410.c
+++ b/drivers/mtd/nand/s3c2410.c
@@ -812,9 +812,8 @@ static int s3c2410_nand_add_partition(struct s3c2410_nand_info *info,
 	return -ENODEV;
 }
 
-static int s3c2410_nand_setup_data_interface(struct mtd_info *mtd,
-					const struct nand_data_interface *conf,
-					bool check_only)
+static int s3c2410_nand_setup_data_interface(struct mtd_info *mtd, int csline,
+					const struct nand_data_interface *conf)
 {
 	struct s3c2410_nand_info *info = s3c2410_nand_mtd_toinfo(mtd);
 	struct s3c2410_platform_nand *pdata = info->platform;
diff --git a/drivers/mtd/nand/sunxi_nand.c b/drivers/mtd/nand/sunxi_nand.c
index 118a26fff368..9c2dbe352c43 100644
--- a/drivers/mtd/nand/sunxi_nand.c
+++ b/drivers/mtd/nand/sunxi_nand.c
@@ -1592,9 +1592,8 @@ static int _sunxi_nand_lookup_timing(const s32 *lut, int lut_size, u32 duration,
 #define sunxi_nand_lookup_timing(l, p, c) \
 			_sunxi_nand_lookup_timing(l, ARRAY_SIZE(l), p, c)
 
-static int sunxi_nfc_setup_data_interface(struct mtd_info *mtd,
-					const struct nand_data_interface *conf,
-					bool check_only)
+static int sunxi_nfc_setup_data_interface(struct mtd_info *mtd, int csline,
+					const struct nand_data_interface *conf)
 {
 	struct nand_chip *nand = mtd_to_nand(mtd);
 	struct sunxi_nand_chip *chip = to_sunxi_nand(nand);
@@ -1707,7 +1706,7 @@ static int sunxi_nfc_setup_data_interface(struct mtd_info *mtd,
 		return tRHW;
 	}
 
-	if (check_only)
+	if (csline == NAND_DATA_IFACE_CHECK_ONLY)
 		return 0;
 
 	/*
diff --git a/drivers/mtd/nand/tango_nand.c b/drivers/mtd/nand/tango_nand.c
index 05b6e1065203..85e0d97593e8 100644
--- a/drivers/mtd/nand/tango_nand.c
+++ b/drivers/mtd/nand/tango_nand.c
@@ -476,9 +476,8 @@ static u32 to_ticks(int kHz, int ps)
 	return DIV_ROUND_UP_ULL((u64)kHz * ps, NSEC_PER_SEC);
 }
 
-static int tango_set_timings(struct mtd_info *mtd,
-			     const struct nand_data_interface *conf,
-			     bool check_only)
+static int tango_set_timings(struct mtd_info *mtd, int csline,
+			     const struct nand_data_interface *conf)
 {
 	const struct nand_sdr_timings *sdr = nand_get_sdr_timings(conf);
 	struct nand_chip *chip = mtd_to_nand(mtd);
@@ -490,7 +489,7 @@ static int tango_set_timings(struct mtd_info *mtd,
 	if (IS_ERR(sdr))
 		return PTR_ERR(sdr);
 
-	if (check_only)
+	if (csline == NAND_DATA_IFACE_CHECK_ONLY)
 		return 0;
 
 	Trdy = to_ticks(kHz, sdr->tCEA_max - sdr->tREA_max);
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 893d0ce08030..9de3686e738c 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -107,6 +107,8 @@ int nand_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len);
 #define NAND_STATUS_READY	0x40
 #define NAND_STATUS_WP		0x80
 
+#define NAND_DATA_IFACE_CHECK_ONLY	-1
+
 /*
  * Constants for ECC_MODES
  */
@@ -818,7 +820,10 @@ struct nand_manufacturer_ops {
  * @read_retries:	[INTERN] the number of read retry modes supported
  * @onfi_set_features:	[REPLACEABLE] set the features for ONFI nand
  * @onfi_get_features:	[REPLACEABLE] get the features for ONFI nand
- * @setup_data_interface: [OPTIONAL] setup the data interface and timing
+ * @setup_data_interface: [OPTIONAL] setup the data interface and timing. If
+ *			  chipnr is set to %NAND_DATA_IFACE_CHECK_ONLY this
+ *			  means the configuration should not be applied but
+ *			  only checked.
  * @bbt:		[INTERN] bad block table pointer
  * @bbt_td:		[REPLACEABLE] bad block table descriptor for flash
  *			lookup.
@@ -862,9 +867,8 @@ struct nand_chip {
 	int (*onfi_get_features)(struct mtd_info *mtd, struct nand_chip *chip,
 			int feature_addr, uint8_t *subfeature_para);
 	int (*setup_read_retry)(struct mtd_info *mtd, int retry_mode);
-	int (*setup_data_interface)(struct mtd_info *mtd,
-				    const struct nand_data_interface *conf,
-				    bool check_only);
+	int (*setup_data_interface)(struct mtd_info *mtd, int chipnr,
+				    const struct nand_data_interface *conf);
 
 
 	int chip_delay;
-- 
cgit v1.2.3


From 7d135bcced20be2b50128432c5426a7278ec4f6d Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@free-electrons.com>
Date: Sat, 6 May 2017 18:03:33 +0200
Subject: mtd: nand: Drop the ->errstat() hook

The ->errstat() hook is no longer implemented NAND controller drivers.
Get rid of it before someone starts abusing it.

Signed-off-by: Boris Brezillon <boris.brezillon@free-electrons.com>
---
 drivers/mtd/nand/nand_base.c | 16 ----------------
 include/linux/mtd/nand.h     |  5 -----
 2 files changed, 21 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index 561f70e05c88..df613125795b 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -2753,14 +2753,6 @@ static int nand_write_page(struct mtd_info *mtd, struct nand_chip *chip,
 	if (nand_standard_page_accessors(&chip->ecc))
 		chip->cmdfunc(mtd, NAND_CMD_PAGEPROG, -1, -1);
 	status = chip->waitfunc(mtd, chip);
-	/*
-	 * See if operation failed and additional status checks are
-	 * available.
-	 */
-	if ((status & NAND_STATUS_FAIL) && (chip->errstat))
-		status = chip->errstat(mtd, chip, FL_WRITING, status,
-				       page);
-
 	if (status & NAND_STATUS_FAIL)
 		return -EIO;
 
@@ -3220,14 +3212,6 @@ int nand_erase_nand(struct mtd_info *mtd, struct erase_info *instr,
 
 		status = chip->erase(mtd, page & chip->pagemask);
 
-		/*
-		 * See if operation failed and additional status checks are
-		 * available
-		 */
-		if ((status & NAND_STATUS_FAIL) && (chip->errstat))
-			status = chip->errstat(mtd, chip, FL_ERASING,
-					       status, page);
-
 		/* See if block erase succeeded */
 		if (status & NAND_STATUS_FAIL) {
 			pr_debug("%s: failed erase, page 0x%08x\n",
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 9de3686e738c..8b3607bde1b5 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -834,9 +834,6 @@ struct nand_manufacturer_ops {
  *			structure which is shared among multiple independent
  *			devices.
  * @priv:		[OPTIONAL] pointer to private chip data
- * @errstat:		[OPTIONAL] hardware specific function to perform
- *			additional error status checks (determine if errors are
- *			correctable).
  * @manufacturer:	[INTERN] Contains manufacturer information
  */
 
@@ -860,8 +857,6 @@ struct nand_chip {
 	int(*waitfunc)(struct mtd_info *mtd, struct nand_chip *this);
 	int (*erase)(struct mtd_info *mtd, int page);
 	int (*scan_bbt)(struct mtd_info *mtd);
-	int (*errstat)(struct mtd_info *mtd, struct nand_chip *this, int state,
-			int status, int page);
 	int (*onfi_set_features)(struct mtd_info *mtd, struct nand_chip *chip,
 			int feature_addr, uint8_t *subfeature_para);
 	int (*onfi_get_features)(struct mtd_info *mtd, struct nand_chip *chip,
-- 
cgit v1.2.3


From d2f31c49cf7cfe8f02b70614ae56a39b0c1d8a75 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Thu, 18 May 2017 23:11:39 +0200
Subject: i2c: sh_mobile: remove platform_data

No platform currently upstream makes use of this platform_data anymore.
The ones that did are converted to DT meanwhile. So, remove it. The old
platforms likely don't have the 'clks_per_cnt' feature, otherwise it
would have been implemented by now. And in the unlikely case they need
to setup a different bus speed, we should rather go for a generic i2c
platform data just for that.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
---
 drivers/i2c/busses/i2c-sh_mobile.c |  8 --------
 include/linux/i2c/i2c-sh_mobile.h  | 11 -----------
 2 files changed, 19 deletions(-)
 delete mode 100644 include/linux/i2c/i2c-sh_mobile.h

(limited to 'include')

diff --git a/drivers/i2c/busses/i2c-sh_mobile.c b/drivers/i2c/busses/i2c-sh_mobile.c
index 3d7559348745..d5e39eccae9b 100644
--- a/drivers/i2c/busses/i2c-sh_mobile.c
+++ b/drivers/i2c/busses/i2c-sh_mobile.c
@@ -24,7 +24,6 @@
 #include <linux/dma-mapping.h>
 #include <linux/err.h>
 #include <linux/i2c.h>
-#include <linux/i2c/i2c-sh_mobile.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
@@ -879,7 +878,6 @@ static int sh_mobile_i2c_hook_irqs(struct platform_device *dev, struct sh_mobile
 
 static int sh_mobile_i2c_probe(struct platform_device *dev)
 {
-	struct i2c_sh_mobile_platform_data *pdata = dev_get_platdata(&dev->dev);
 	struct sh_mobile_i2c_data *pd;
 	struct i2c_adapter *adap;
 	struct resource *res;
@@ -910,7 +908,6 @@ static int sh_mobile_i2c_probe(struct platform_device *dev)
 	if (IS_ERR(pd->reg))
 		return PTR_ERR(pd->reg);
 
-	/* Use platform data bus speed or STANDARD_MODE */
 	ret = of_property_read_u32(dev->dev.of_node, "clock-frequency", &bus_speed);
 	pd->bus_speed = ret ? STANDARD_MODE : bus_speed;
 
@@ -929,11 +926,6 @@ static int sh_mobile_i2c_probe(struct platform_device *dev)
 			if (config->setup)
 				config->setup(pd);
 		}
-	} else {
-		if (pdata && pdata->bus_speed)
-			pd->bus_speed = pdata->bus_speed;
-		if (pdata && pdata->clks_per_count)
-			pd->clks_per_count = pdata->clks_per_count;
 	}
 
 	/* The IIC blocks on SH-Mobile ARM processors
diff --git a/include/linux/i2c/i2c-sh_mobile.h b/include/linux/i2c/i2c-sh_mobile.h
deleted file mode 100644
index 06e3089795fb..000000000000
--- a/include/linux/i2c/i2c-sh_mobile.h
+++ /dev/null
@@ -1,11 +0,0 @@
-#ifndef __I2C_SH_MOBILE_H__
-#define __I2C_SH_MOBILE_H__
-
-#include <linux/platform_device.h>
-
-struct i2c_sh_mobile_platform_data {
-	unsigned long bus_speed;
-	unsigned int clks_per_count;
-};
-
-#endif /* __I2C_SH_MOBILE_H__ */
-- 
cgit v1.2.3


From 5c82a6ae0242416cfead597bb2b42aa3481a0ba7 Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@free-electrons.com>
Date: Fri, 2 Jun 2017 14:15:15 +0200
Subject: rtc: remove rtc_device.name

rtc->name is only used in messages were it is superfluous. Remove it
completely from the structure.

Signed-off-by: Alexandre Belloni <alexandre.belloni@free-electrons.com>
---
 drivers/rtc/class.c | 7 +++----
 include/linux/rtc.h | 1 -
 2 files changed, 3 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c
index 5fb439897fe1..543c64cd3df0 100644
--- a/drivers/rtc/class.c
+++ b/drivers/rtc/class.c
@@ -224,7 +224,6 @@ struct rtc_device *rtc_device_register(const char *name, struct device *dev,
 	rtc->pie_timer.function = rtc_pie_update_irq;
 	rtc->pie_enabled = 0;
 
-	strlcpy(rtc->name, name, RTC_DEVICE_NAME_SIZE);
 	dev_set_name(&rtc->dev, "rtc%d", id);
 
 	/* Check to see if there is an ALARM already set in hw */
@@ -238,20 +237,20 @@ struct rtc_device *rtc_device_register(const char *name, struct device *dev,
 	err = cdev_device_add(&rtc->char_dev, &rtc->dev);
 	if (err) {
 		dev_warn(&rtc->dev, "%s: failed to add char device %d:%d\n",
-			 rtc->name, MAJOR(rtc->dev.devt), rtc->id);
+			 name, MAJOR(rtc->dev.devt), rtc->id);
 
 		/* This will free both memory and the ID */
 		put_device(&rtc->dev);
 		goto exit;
 	} else {
-		dev_dbg(&rtc->dev, "%s: dev (%d:%d)\n", rtc->name,
+		dev_dbg(&rtc->dev, "%s: dev (%d:%d)\n", name,
 			MAJOR(rtc->dev.devt), rtc->id);
 	}
 
 	rtc_proc_add_device(rtc);
 
 	dev_info(dev, "rtc core: registered %s as %s\n",
-			rtc->name, dev_name(&rtc->dev));
+			name, dev_name(&rtc->dev));
 
 	return rtc;
 
diff --git a/include/linux/rtc.h b/include/linux/rtc.h
index b693adac853b..d354f56e0cf5 100644
--- a/include/linux/rtc.h
+++ b/include/linux/rtc.h
@@ -116,7 +116,6 @@ struct rtc_device {
 	struct module *owner;
 
 	int id;
-	char name[RTC_DEVICE_NAME_SIZE];
 
 	const struct rtc_class_ops *ops;
 	struct mutex ops_lock;
-- 
cgit v1.2.3


From c17cd24959cdb12c855dc61e20c36fa25f21f3d3 Mon Sep 17 00:00:00 2001
From: Nicholas Bellinger <nab@linux-iscsi.org>
Date: Thu, 1 Jun 2017 03:10:53 -0700
Subject: target/configfs: Kill se_device->dev_link_magic

Instead of using a hardcoded magic value in se_device when verifying
a target config_item symlink source during target_fabric_port_link(),
go ahead and use target_core_dev_item_ops directly instead.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_configfs.c        |  6 +++++-
 drivers/target/target_core_device.c          |  1 -
 drivers/target/target_core_fabric_configfs.c | 12 +++++++-----
 include/target/target_core_base.h            |  2 --
 4 files changed, 12 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index 0326607e5ab8..9b8abd55c21c 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -2236,7 +2236,11 @@ static void target_core_dev_release(struct config_item *item)
 	target_free_device(dev);
 }
 
-static struct configfs_item_operations target_core_dev_item_ops = {
+/*
+ * Used in target_core_fabric_configfs.c to verify valid se_device symlink
+ * within target_fabric_port_link()
+ */
+struct configfs_item_operations target_core_dev_item_ops = {
 	.release		= target_core_dev_release,
 };
 
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index a5762e601fa1..e4771cec108c 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -756,7 +756,6 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name)
 	if (!dev)
 		return NULL;
 
-	dev->dev_link_magic = SE_DEV_LINK_MAGIC;
 	dev->se_hba = hba;
 	dev->transport = hba->backend->ops;
 	dev->prot_length = sizeof(struct t10_pi_tuple);
diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c
index d1e6cab8e3d3..2cbaecd1669d 100644
--- a/drivers/target/target_core_fabric_configfs.c
+++ b/drivers/target/target_core_fabric_configfs.c
@@ -620,6 +620,8 @@ static struct configfs_attribute *target_fabric_port_attrs[] = {
 	NULL,
 };
 
+extern struct configfs_item_operations target_core_dev_item_ops;
+
 static int target_fabric_port_link(
 	struct config_item *lun_ci,
 	struct config_item *se_dev_ci)
@@ -628,16 +630,16 @@ static int target_fabric_port_link(
 	struct se_lun *lun = container_of(to_config_group(lun_ci),
 				struct se_lun, lun_group);
 	struct se_portal_group *se_tpg;
-	struct se_device *dev =
-		container_of(to_config_group(se_dev_ci), struct se_device, dev_group);
+	struct se_device *dev;
 	struct target_fabric_configfs *tf;
 	int ret;
 
-	if (dev->dev_link_magic != SE_DEV_LINK_MAGIC) {
-		pr_err("Bad dev->dev_link_magic, not a valid se_dev_ci pointer:"
-			" %p to struct se_device: %p\n", se_dev_ci, dev);
+	if (!se_dev_ci->ci_type ||
+	    se_dev_ci->ci_type->ct_item_ops != &target_core_dev_item_ops) {
+		pr_err("Bad se_dev_ci, not a valid se_dev_ci pointer: %p\n", se_dev_ci);
 		return -EFAULT;
 	}
+	dev = container_of(to_config_group(se_dev_ci), struct se_device, dev_group);
 
 	if (!(dev->dev_flags & DF_CONFIGURED)) {
 		pr_err("se_device not configured yet, cannot port link\n");
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 0c1dce2ac6f0..c3c14d053122 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -746,8 +746,6 @@ struct se_dev_stat_grps {
 };
 
 struct se_device {
-#define SE_DEV_LINK_MAGIC			0xfeeddeef
-	u32			dev_link_magic;
 	/* RELATIVE TARGET PORT IDENTIFER Counter */
 	u16			dev_rpti_counter;
 	/* Used for SAM Task Attribute ordering */
-- 
cgit v1.2.3


From 9ae0e9ade56f23765366d2cfad24e65f28df977d Mon Sep 17 00:00:00 2001
From: Nicholas Bellinger <nab@linux-iscsi.org>
Date: Thu, 1 Jun 2017 03:11:18 -0700
Subject: target/configfs: Kill se_lun->lun_link_magic

Instead of using a hardcoded magic value in se_lun when verifying
a target config_item symlink source during target_fabric_mappedlun_link(),
go ahead and use target_fabric_port_item_ops directly instead.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_fabric_configfs.c | 13 ++++++++-----
 drivers/target/target_core_tpg.c             |  1 -
 include/target/target_core_base.h            |  2 --
 3 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c
index 2cbaecd1669d..e9e917cc6441 100644
--- a/drivers/target/target_core_fabric_configfs.c
+++ b/drivers/target/target_core_fabric_configfs.c
@@ -65,6 +65,8 @@ static void target_fabric_setup_##_name##_cit(struct target_fabric_configfs *tf)
 	pr_debug("Setup generic %s\n", __stringify(_name));		\
 }
 
+static struct configfs_item_operations target_fabric_port_item_ops;
+
 /* Start of tfc_tpg_mappedlun_cit */
 
 static int target_fabric_mappedlun_link(
@@ -72,19 +74,20 @@ static int target_fabric_mappedlun_link(
 	struct config_item *lun_ci)
 {
 	struct se_dev_entry *deve;
-	struct se_lun *lun = container_of(to_config_group(lun_ci),
-			struct se_lun, lun_group);
+	struct se_lun *lun;
 	struct se_lun_acl *lacl = container_of(to_config_group(lun_acl_ci),
 			struct se_lun_acl, se_lun_group);
 	struct se_portal_group *se_tpg;
 	struct config_item *nacl_ci, *tpg_ci, *tpg_ci_s, *wwn_ci, *wwn_ci_s;
 	bool lun_access_ro;
 
-	if (lun->lun_link_magic != SE_LUN_LINK_MAGIC) {
-		pr_err("Bad lun->lun_link_magic, not a valid lun_ci pointer:"
-			" %p to struct lun: %p\n", lun_ci, lun);
+	if (!lun_ci->ci_type ||
+	    lun_ci->ci_type->ct_item_ops != &target_fabric_port_item_ops) {
+		pr_err("Bad lun_ci, not a valid lun_ci pointer: %p\n", lun_ci);
 		return -EFAULT;
 	}
+	lun = container_of(to_config_group(lun_ci), struct se_lun, lun_group);
+
 	/*
 	 * Ensure that the source port exists
 	 */
diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c
index 310d9e55c6eb..36913734c6bc 100644
--- a/drivers/target/target_core_tpg.c
+++ b/drivers/target/target_core_tpg.c
@@ -576,7 +576,6 @@ struct se_lun *core_tpg_alloc_lun(
 		return ERR_PTR(-ENOMEM);
 	}
 	lun->unpacked_lun = unpacked_lun;
-	lun->lun_link_magic = SE_LUN_LINK_MAGIC;
 	atomic_set(&lun->lun_acl_count, 0);
 	init_completion(&lun->lun_ref_comp);
 	init_completion(&lun->lun_shutdown_comp);
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index c3c14d053122..47d9f381209f 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -701,8 +701,6 @@ struct scsi_port_stats {
 
 struct se_lun {
 	u64			unpacked_lun;
-#define SE_LUN_LINK_MAGIC			0xffff7771
-	u32			lun_link_magic;
 	bool			lun_shutdown;
 	bool			lun_access_ro;
 	u32			lun_index;
-- 
cgit v1.2.3


From 2c8f8afa7f92acb07641bf95b940d384ed1d0294 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Wed, 7 Jun 2017 20:52:10 +0900
Subject: mtd: nand: add generic helpers to check, match, maximize ECC settings

Driver are responsible for setting up ECC parameters correctly.
Those include:
  - Check if ECC parameters specified (usually by DT) are valid
  - Meet the chip's ECC requirement
  - Maximize ECC strength if NAND_ECC_MAXIMIZE flag is set

The logic can be generalized by factoring out common code.

This commit adds 3 helpers to the NAND framework:
nand_check_ecc_caps - Check if preset step_size and strength are valid
nand_match_ecc_req - Match the chip's requirement
nand_maximize_ecc - Maximize the ECC strength

To use the helpers above, a driver needs to provide:
  - Data array of supported ECC step size and strength
  - A hook that calculates ECC bytes from the combination of
    step_size and strength.

By using those helpers, code duplication among drivers will be
reduced.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Boris Brezillon <boris.brezillon@free-electrons.com>
---
 drivers/mtd/nand/nand_base.c | 220 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/mtd/nand.h     |  33 +++++++
 2 files changed, 253 insertions(+)

(limited to 'include')

diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index 2404bb046b69..85edac9b2bb5 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -4523,6 +4523,226 @@ static int nand_set_ecc_soft_ops(struct mtd_info *mtd)
 	}
 }
 
+/**
+ * nand_check_ecc_caps - check the sanity of preset ECC settings
+ * @chip: nand chip info structure
+ * @caps: ECC caps info structure
+ * @oobavail: OOB size that the ECC engine can use
+ *
+ * When ECC step size and strength are already set, check if they are supported
+ * by the controller and the calculated ECC bytes fit within the chip's OOB.
+ * On success, the calculated ECC bytes is set.
+ */
+int nand_check_ecc_caps(struct nand_chip *chip,
+			const struct nand_ecc_caps *caps, int oobavail)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	const struct nand_ecc_step_info *stepinfo;
+	int preset_step = chip->ecc.size;
+	int preset_strength = chip->ecc.strength;
+	int nsteps, ecc_bytes;
+	int i, j;
+
+	if (WARN_ON(oobavail < 0))
+		return -EINVAL;
+
+	if (!preset_step || !preset_strength)
+		return -ENODATA;
+
+	nsteps = mtd->writesize / preset_step;
+
+	for (i = 0; i < caps->nstepinfos; i++) {
+		stepinfo = &caps->stepinfos[i];
+
+		if (stepinfo->stepsize != preset_step)
+			continue;
+
+		for (j = 0; j < stepinfo->nstrengths; j++) {
+			if (stepinfo->strengths[j] != preset_strength)
+				continue;
+
+			ecc_bytes = caps->calc_ecc_bytes(preset_step,
+							 preset_strength);
+			if (WARN_ON_ONCE(ecc_bytes < 0))
+				return ecc_bytes;
+
+			if (ecc_bytes * nsteps > oobavail) {
+				pr_err("ECC (step, strength) = (%d, %d) does not fit in OOB",
+				       preset_step, preset_strength);
+				return -ENOSPC;
+			}
+
+			chip->ecc.bytes = ecc_bytes;
+
+			return 0;
+		}
+	}
+
+	pr_err("ECC (step, strength) = (%d, %d) not supported on this controller",
+	       preset_step, preset_strength);
+
+	return -ENOTSUPP;
+}
+EXPORT_SYMBOL_GPL(nand_check_ecc_caps);
+
+/**
+ * nand_match_ecc_req - meet the chip's requirement with least ECC bytes
+ * @chip: nand chip info structure
+ * @caps: ECC engine caps info structure
+ * @oobavail: OOB size that the ECC engine can use
+ *
+ * If a chip's ECC requirement is provided, try to meet it with the least
+ * number of ECC bytes (i.e. with the largest number of OOB-free bytes).
+ * On success, the chosen ECC settings are set.
+ */
+int nand_match_ecc_req(struct nand_chip *chip,
+		       const struct nand_ecc_caps *caps, int oobavail)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	const struct nand_ecc_step_info *stepinfo;
+	int req_step = chip->ecc_step_ds;
+	int req_strength = chip->ecc_strength_ds;
+	int req_corr, step_size, strength, nsteps, ecc_bytes, ecc_bytes_total;
+	int best_step, best_strength, best_ecc_bytes;
+	int best_ecc_bytes_total = INT_MAX;
+	int i, j;
+
+	if (WARN_ON(oobavail < 0))
+		return -EINVAL;
+
+	/* No information provided by the NAND chip */
+	if (!req_step || !req_strength)
+		return -ENOTSUPP;
+
+	/* number of correctable bits the chip requires in a page */
+	req_corr = mtd->writesize / req_step * req_strength;
+
+	for (i = 0; i < caps->nstepinfos; i++) {
+		stepinfo = &caps->stepinfos[i];
+		step_size = stepinfo->stepsize;
+
+		for (j = 0; j < stepinfo->nstrengths; j++) {
+			strength = stepinfo->strengths[j];
+
+			/*
+			 * If both step size and strength are smaller than the
+			 * chip's requirement, it is not easy to compare the
+			 * resulted reliability.
+			 */
+			if (step_size < req_step && strength < req_strength)
+				continue;
+
+			if (mtd->writesize % step_size)
+				continue;
+
+			nsteps = mtd->writesize / step_size;
+
+			ecc_bytes = caps->calc_ecc_bytes(step_size, strength);
+			if (WARN_ON_ONCE(ecc_bytes < 0))
+				continue;
+			ecc_bytes_total = ecc_bytes * nsteps;
+
+			if (ecc_bytes_total > oobavail ||
+			    strength * nsteps < req_corr)
+				continue;
+
+			/*
+			 * We assume the best is to meet the chip's requrement
+			 * with the least number of ECC bytes.
+			 */
+			if (ecc_bytes_total < best_ecc_bytes_total) {
+				best_ecc_bytes_total = ecc_bytes_total;
+				best_step = step_size;
+				best_strength = strength;
+				best_ecc_bytes = ecc_bytes;
+			}
+		}
+	}
+
+	if (best_ecc_bytes_total == INT_MAX)
+		return -ENOTSUPP;
+
+	chip->ecc.size = best_step;
+	chip->ecc.strength = best_strength;
+	chip->ecc.bytes = best_ecc_bytes;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nand_match_ecc_req);
+
+/**
+ * nand_maximize_ecc - choose the max ECC strength available
+ * @chip: nand chip info structure
+ * @caps: ECC engine caps info structure
+ * @oobavail: OOB size that the ECC engine can use
+ *
+ * Choose the max ECC strength that is supported on the controller, and can fit
+ * within the chip's OOB.  On success, the chosen ECC settings are set.
+ */
+int nand_maximize_ecc(struct nand_chip *chip,
+		      const struct nand_ecc_caps *caps, int oobavail)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	const struct nand_ecc_step_info *stepinfo;
+	int step_size, strength, nsteps, ecc_bytes, corr;
+	int best_corr = 0;
+	int best_step = 0;
+	int best_strength, best_ecc_bytes;
+	int i, j;
+
+	if (WARN_ON(oobavail < 0))
+		return -EINVAL;
+
+	for (i = 0; i < caps->nstepinfos; i++) {
+		stepinfo = &caps->stepinfos[i];
+		step_size = stepinfo->stepsize;
+
+		/* If chip->ecc.size is already set, respect it */
+		if (chip->ecc.size && step_size != chip->ecc.size)
+			continue;
+
+		for (j = 0; j < stepinfo->nstrengths; j++) {
+			strength = stepinfo->strengths[j];
+
+			if (mtd->writesize % step_size)
+				continue;
+
+			nsteps = mtd->writesize / step_size;
+
+			ecc_bytes = caps->calc_ecc_bytes(step_size, strength);
+			if (WARN_ON_ONCE(ecc_bytes < 0))
+				continue;
+
+			if (ecc_bytes * nsteps > oobavail)
+				continue;
+
+			corr = strength * nsteps;
+
+			/*
+			 * If the number of correctable bits is the same,
+			 * bigger step_size has more reliability.
+			 */
+			if (corr > best_corr ||
+			    (corr == best_corr && step_size > best_step)) {
+				best_corr = corr;
+				best_step = step_size;
+				best_strength = strength;
+				best_ecc_bytes = ecc_bytes;
+			}
+		}
+	}
+
+	if (!best_corr)
+		return -ENOTSUPP;
+
+	chip->ecc.size = best_step;
+	chip->ecc.strength = best_strength;
+	chip->ecc.bytes = best_ecc_bytes;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nand_maximize_ecc);
+
 /*
  * Check if the chip configuration meet the datasheet requirements.
 
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 8b3607bde1b5..568f53e812cd 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -481,6 +481,30 @@ static inline void nand_hw_control_init(struct nand_hw_control *nfc)
 	init_waitqueue_head(&nfc->wq);
 }
 
+/**
+ * struct nand_ecc_step_info - ECC step information of ECC engine
+ * @stepsize: data bytes per ECC step
+ * @strengths: array of supported strengths
+ * @nstrengths: number of supported strengths
+ */
+struct nand_ecc_step_info {
+	int stepsize;
+	const int *strengths;
+	int nstrengths;
+};
+
+/**
+ * struct nand_ecc_caps - capability of ECC engine
+ * @stepinfos: array of ECC step information
+ * @nstepinfos: number of ECC step information
+ * @calc_ecc_bytes: driver's hook to calculate ECC bytes per step
+ */
+struct nand_ecc_caps {
+	const struct nand_ecc_step_info *stepinfos;
+	int nstepinfos;
+	int (*calc_ecc_bytes)(int step_size, int strength);
+};
+
 /**
  * struct nand_ecc_ctrl - Control structure for ECC
  * @mode:	ECC mode
@@ -1246,6 +1270,15 @@ int nand_check_erased_ecc_chunk(void *data, int datalen,
 				void *extraoob, int extraooblen,
 				int threshold);
 
+int nand_check_ecc_caps(struct nand_chip *chip,
+			const struct nand_ecc_caps *caps, int oobavail);
+
+int nand_match_ecc_req(struct nand_chip *chip,
+		       const struct nand_ecc_caps *caps,  int oobavail);
+
+int nand_maximize_ecc(struct nand_chip *chip,
+		      const struct nand_ecc_caps *caps, int oobavail);
+
 /* Default write_oob implementation */
 int nand_write_oob_std(struct mtd_info *mtd, struct nand_chip *chip, int page);
 
-- 
cgit v1.2.3


From a03c60178c181767ecfb26fb311a88742d228118 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Wed, 7 Jun 2017 20:52:11 +0900
Subject: mtd: nand: add a shorthand to generate nand_ecc_caps structure

struct nand_ecc_caps was designed as flexible as possible to support
multiple stepsizes (like sunxi_nand.c).

So, we need to write multiple arrays even for the simplest case.
I guess many controllers support a single stepsize, so here is a
shorthand macro for the case.

It allows to describe like ...

NAND_ECC_CAPS_SINGLE(denali_pci_ecc_caps, denali_calc_ecc_bytes, 512, 8, 15);

... instead of

static const int denali_pci_ecc_strengths[] = {8, 15};
static const struct nand_ecc_step_info denali_pci_ecc_stepinfo = {
        .stepsize = 512,
        .strengths = denali_pci_ecc_strengths,
        .nstrengths = ARRAY_SIZE(denali_pci_ecc_strengths),
};
static const struct nand_ecc_caps denali_pci_ecc_caps = {
        .stepinfos = &denali_pci_ecc_stepinfo,
        .nstepinfos = 1,
        .calc_ecc_bytes = denali_calc_ecc_bytes,
};

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Boris Brezillon <boris.brezillon@free-electrons.com>
---
 include/linux/mtd/nand.h | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

(limited to 'include')

diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 568f53e812cd..dc8fbc033442 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -505,6 +505,20 @@ struct nand_ecc_caps {
 	int (*calc_ecc_bytes)(int step_size, int strength);
 };
 
+/* a shorthand to generate struct nand_ecc_caps with only one ECC stepsize */
+#define NAND_ECC_CAPS_SINGLE(__name, __calc, __step, ...)	\
+static const int __name##_strengths[] = { __VA_ARGS__ };	\
+static const struct nand_ecc_step_info __name##_stepinfo = {	\
+	.stepsize = __step,					\
+	.strengths = __name##_strengths,			\
+	.nstrengths = ARRAY_SIZE(__name##_strengths),		\
+};								\
+static const struct nand_ecc_caps __name = {			\
+	.stepinfos = &__name##_stepinfo,			\
+	.nstepinfos = 1,					\
+	.calc_ecc_bytes = __calc,				\
+}
+
 /**
  * struct nand_ecc_ctrl - Control structure for ECC
  * @mode:	ECC mode
-- 
cgit v1.2.3


From 68c35ea25bdd4ad10445c4c02f7d48b3dccab8cc Mon Sep 17 00:00:00 2001
From: Gwendal Grignou <gwendal@chromium.org>
Date: Tue, 16 May 2017 17:46:48 +0200
Subject: mfd: cros_ec: Add helper for event notifier.

Add cros_ec_get_event() entry point to retrieve event within functions
called by the notifier.

Signed-off-by: Gwendal Grignou <gwendal@chromium.org>
Signed-off-by: Enric Balletbo i Serra <enric.balletbo@collabora.com>
Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Benson Leung <bleung@chromium.org>
---
 drivers/platform/chrome/cros_ec_proto.c | 20 ++++++++++++++++++++
 include/linux/mfd/cros_ec.h             | 10 ++++++++++
 2 files changed, 30 insertions(+)

(limited to 'include')

diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c
index ed5dee744c74..7428c2b965bb 100644
--- a/drivers/platform/chrome/cros_ec_proto.c
+++ b/drivers/platform/chrome/cros_ec_proto.c
@@ -494,3 +494,23 @@ int cros_ec_get_next_event(struct cros_ec_device *ec_dev)
 		return get_keyboard_state_event(ec_dev);
 }
 EXPORT_SYMBOL(cros_ec_get_next_event);
+
+u32 cros_ec_get_host_event(struct cros_ec_device *ec_dev)
+{
+	u32 host_event;
+
+	BUG_ON(!ec_dev->mkbp_event_supported);
+
+	if (ec_dev->event_data.event_type != EC_MKBP_EVENT_HOST_EVENT)
+		return 0;
+
+	if (ec_dev->event_size != sizeof(host_event)) {
+		dev_warn(ec_dev->dev, "Invalid host event size\n");
+		return 0;
+	}
+
+	host_event = get_unaligned_le32(&ec_dev->event_data.data.host_event);
+
+	return host_event;
+}
+EXPORT_SYMBOL(cros_ec_get_host_event);
diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h
index 28baee63eaf6..b61b2e013698 100644
--- a/include/linux/mfd/cros_ec.h
+++ b/include/linux/mfd/cros_ec.h
@@ -300,6 +300,16 @@ int cros_ec_query_all(struct cros_ec_device *ec_dev);
  */
 int cros_ec_get_next_event(struct cros_ec_device *ec_dev);
 
+/**
+ * cros_ec_get_host_event - Return a mask of event set by the EC.
+ *
+ * When MKBP is supported, when the EC raises an interrupt,
+ * We collect the events raised and call the functions in the ec notifier.
+ *
+ * This function is a helper to know which events are raised.
+ */
+u32 cros_ec_get_host_event(struct cros_ec_device *ec_dev);
+
 /* sysfs stuff */
 extern struct attribute_group cros_ec_attr_group;
 extern struct attribute_group cros_ec_lightbar_attr_group;
-- 
cgit v1.2.3


From 0aa877c558477e5c4b0faaa618cfd41f8c0b3319 Mon Sep 17 00:00:00 2001
From: Nicolas Boichat <drinkcat@chromium.org>
Date: Tue, 16 May 2017 17:46:48 +0200
Subject: mfd: cros_ec: Add EC console read structures definitions

ec_params_console_read_v1 is used to capture EC logs from kernel,
and ec_params_get_cmd_versions_v1 is used to probe whether EC
supports that command.

Signed-off-by: Nicolas Boichat <drinkcat@chromium.org>
Reviewed-by: Guenter Roeck <groeck@chromium.org>
Acked-by: Lee Jones <lee.jones@linaro.org>
Tested-by: Enric Balletbo i Serra <enric.balletbo@collabora.com>
Signed-off-by: Benson Leung <bleung@chromium.org>
---
 include/linux/mfd/cros_ec_commands.h | 21 ++++++++++++++++++++-
 1 file changed, 20 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/mfd/cros_ec_commands.h b/include/linux/mfd/cros_ec_commands.h
index c93e7e0300ef..1b19e424e1cf 100644
--- a/include/linux/mfd/cros_ec_commands.h
+++ b/include/linux/mfd/cros_ec_commands.h
@@ -625,6 +625,10 @@ struct ec_params_get_cmd_versions {
 	uint8_t cmd;      /* Command to check */
 } __packed;
 
+struct ec_params_get_cmd_versions_v1 {
+	uint16_t cmd;     /* Command to check */
+} __packed;
+
 struct ec_response_get_cmd_versions {
 	/*
 	 * Mask of supported versions; use EC_VER_MASK() to compare with a
@@ -2285,13 +2289,28 @@ struct ec_params_charge_control {
 #define EC_CMD_CONSOLE_SNAPSHOT 0x97
 
 /*
- * Read next chunk of data from saved snapshot.
+ * Read data from the saved snapshot. If the subcmd parameter is
+ * CONSOLE_READ_NEXT, this will return data starting from the beginning of
+ * the latest snapshot. If it is CONSOLE_READ_RECENT, it will start from the
+ * end of the previous snapshot.
+ *
+ * The params are only looked at in version >= 1 of this command. Prior
+ * versions will just default to CONSOLE_READ_NEXT behavior.
  *
  * Response is null-terminated string.  Empty string, if there is no more
  * remaining output.
  */
 #define EC_CMD_CONSOLE_READ 0x98
 
+enum ec_console_read_subcmd {
+	CONSOLE_READ_NEXT = 0,
+	CONSOLE_READ_RECENT
+};
+
+struct ec_params_console_read_v1 {
+	uint8_t subcmd; /* enum ec_console_read_subcmd */
+} __packed;
+
 /*****************************************************************************/
 
 /*
-- 
cgit v1.2.3


From e86264595225d2764a903965356ef59aeb7d1c47 Mon Sep 17 00:00:00 2001
From: Eric Caruso <ejcaruso@chromium.org>
Date: Tue, 16 May 2017 17:46:48 +0200
Subject: mfd: cros_ec: add debugfs, console log file

If the EC supports the new CONSOLE_READ command type, then we
place a console_log file in debugfs for that EC device which allows
us to grab EC logs. The kernel will poll every 10 seconds for the
log and keep its own buffer, but userspace should grab this and
write it out to some logs which actually get rotated.

Signed-off-by: Eric Caruso <ejcaruso@chromium.org>
Signed-off-by: Nicolas Boichat <drinkcat@chromium.org>
Acked-by: Lee Jones <lee.jones@linaro.org>
Tested-by: Enric Balletbo i Serra <enric.balletbo@collabora.com>
[bleung: restored original version of this commit, with pointer size
 issue to be fixed in next commit]
Signed-off-by: Benson Leung <bleung@chromium.org>
---
 drivers/platform/chrome/Makefile          |   3 +-
 drivers/platform/chrome/cros_ec_debugfs.c | 347 ++++++++++++++++++++++++++++++
 drivers/platform/chrome/cros_ec_debugfs.h |  27 +++
 drivers/platform/chrome/cros_ec_dev.c     |   7 +
 include/linux/mfd/cros_ec.h               |   4 +
 5 files changed, 387 insertions(+), 1 deletion(-)
 create mode 100644 drivers/platform/chrome/cros_ec_debugfs.c
 create mode 100644 drivers/platform/chrome/cros_ec_debugfs.h

(limited to 'include')

diff --git a/drivers/platform/chrome/Makefile b/drivers/platform/chrome/Makefile
index 4f3462783a3c..3870afeefcf4 100644
--- a/drivers/platform/chrome/Makefile
+++ b/drivers/platform/chrome/Makefile
@@ -2,7 +2,8 @@
 obj-$(CONFIG_CHROMEOS_LAPTOP)		+= chromeos_laptop.o
 obj-$(CONFIG_CHROMEOS_PSTORE)		+= chromeos_pstore.o
 cros_ec_devs-objs			:= cros_ec_dev.o cros_ec_sysfs.o \
-					   cros_ec_lightbar.o cros_ec_vbc.o
+					   cros_ec_lightbar.o cros_ec_vbc.o \
+					   cros_ec_debugfs.o
 obj-$(CONFIG_CROS_EC_CHARDEV)		+= cros_ec_devs.o
 obj-$(CONFIG_CROS_EC_LPC)		+= cros_ec_lpc.o
 obj-$(CONFIG_CROS_EC_PROTO)		+= cros_ec_proto.o
diff --git a/drivers/platform/chrome/cros_ec_debugfs.c b/drivers/platform/chrome/cros_ec_debugfs.c
new file mode 100644
index 000000000000..225f93631051
--- /dev/null
+++ b/drivers/platform/chrome/cros_ec_debugfs.c
@@ -0,0 +1,347 @@
+/*
+ * cros_ec_debugfs - debug logs for Chrome OS EC
+ *
+ * Copyright 2015 Google, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/circ_buf.h>
+#include <linux/debugfs.h>
+#include <linux/delay.h>
+#include <linux/fs.h>
+#include <linux/mfd/cros_ec.h>
+#include <linux/mfd/cros_ec_commands.h>
+#include <linux/mutex.h>
+#include <linux/poll.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/wait.h>
+
+#include "cros_ec_dev.h"
+#include "cros_ec_debugfs.h"
+
+#define LOG_SHIFT		14
+#define LOG_SIZE		(1 << LOG_SHIFT)
+#define LOG_POLL_SEC		10
+
+#define CIRC_ADD(idx, size, value)	(((idx) + (value)) & ((size) - 1))
+
+/* struct cros_ec_debugfs - ChromeOS EC debugging information
+ *
+ * @ec: EC device this debugfs information belongs to
+ * @dir: dentry for debugfs files
+ * @log_buffer: circular buffer for console log information
+ * @read_msg: preallocated EC command and buffer to read console log
+ * @log_mutex: mutex to protect circular buffer
+ * @log_wq: waitqueue for log readers
+ * @log_poll_work: recurring task to poll EC for new console log data
+ */
+struct cros_ec_debugfs {
+	struct cros_ec_dev *ec;
+	struct dentry *dir;
+	struct circ_buf log_buffer;
+	struct cros_ec_command *read_msg;
+	struct mutex log_mutex;
+	wait_queue_head_t log_wq;
+	struct delayed_work log_poll_work;
+};
+
+/*
+ * We need to make sure that the EC log buffer on the UART is large enough,
+ * so that it is unlikely enough to overlow within LOG_POLL_SEC.
+ */
+static void cros_ec_console_log_work(struct work_struct *__work)
+{
+	struct cros_ec_debugfs *debug_info =
+		container_of(to_delayed_work(__work),
+			     struct cros_ec_debugfs,
+			     log_poll_work);
+	struct cros_ec_dev *ec = debug_info->ec;
+	struct circ_buf *cb = &debug_info->log_buffer;
+	struct cros_ec_command snapshot_msg = {
+		.command = EC_CMD_CONSOLE_SNAPSHOT + ec->cmd_offset,
+	};
+
+	struct ec_params_console_read_v1 *read_params =
+		(struct ec_params_console_read_v1 *)debug_info->read_msg->data;
+	uint8_t *ec_buffer = (uint8_t *)debug_info->read_msg->data;
+	int idx;
+	int buf_space;
+	int ret;
+
+	ret = cros_ec_cmd_xfer(ec->ec_dev, &snapshot_msg);
+	if (ret < 0) {
+		dev_err(ec->dev, "EC communication failed\n");
+		goto resched;
+	}
+	if (snapshot_msg.result != EC_RES_SUCCESS) {
+		dev_err(ec->dev, "EC failed to snapshot the console log\n");
+		goto resched;
+	}
+
+	/* Loop until we have read everything, or there's an error. */
+	mutex_lock(&debug_info->log_mutex);
+	buf_space = CIRC_SPACE(cb->head, cb->tail, LOG_SIZE);
+
+	while (1) {
+		if (!buf_space) {
+			dev_info_once(ec->dev,
+				      "Some logs may have been dropped...\n");
+			break;
+		}
+
+		memset(read_params, '\0', sizeof(*read_params));
+		read_params->subcmd = CONSOLE_READ_RECENT;
+		ret = cros_ec_cmd_xfer(ec->ec_dev, debug_info->read_msg);
+		if (ret < 0) {
+			dev_err(ec->dev, "EC communication failed\n");
+			break;
+		}
+		if (debug_info->read_msg->result != EC_RES_SUCCESS) {
+			dev_err(ec->dev,
+				"EC failed to read the console log\n");
+			break;
+		}
+
+		/* If the buffer is empty, we're done here. */
+		if (ret == 0 || ec_buffer[0] == '\0')
+			break;
+
+		idx = 0;
+		while (idx < ret && ec_buffer[idx] != '\0' && buf_space > 0) {
+			cb->buf[cb->head] = ec_buffer[idx];
+			cb->head = CIRC_ADD(cb->head, LOG_SIZE, 1);
+			idx++;
+			buf_space--;
+		}
+
+		wake_up(&debug_info->log_wq);
+	}
+
+	mutex_unlock(&debug_info->log_mutex);
+
+resched:
+	schedule_delayed_work(&debug_info->log_poll_work,
+			      msecs_to_jiffies(LOG_POLL_SEC * 1000));
+}
+
+static int cros_ec_console_log_open(struct inode *inode, struct file *file)
+{
+	file->private_data = inode->i_private;
+
+	return nonseekable_open(inode, file);
+}
+
+static ssize_t cros_ec_console_log_read(struct file *file, char __user *buf,
+					size_t count, loff_t *ppos)
+{
+	struct cros_ec_debugfs *debug_info = file->private_data;
+	struct circ_buf *cb = &debug_info->log_buffer;
+	ssize_t ret;
+
+	mutex_lock(&debug_info->log_mutex);
+
+	while (!CIRC_CNT(cb->head, cb->tail, LOG_SIZE)) {
+		if (file->f_flags & O_NONBLOCK) {
+			ret = -EAGAIN;
+			goto error;
+		}
+
+		mutex_unlock(&debug_info->log_mutex);
+
+		ret = wait_event_interruptible(debug_info->log_wq,
+					CIRC_CNT(cb->head, cb->tail, LOG_SIZE));
+		if (ret < 0)
+			return ret;
+
+		mutex_lock(&debug_info->log_mutex);
+	}
+
+	/* Only copy until the end of the circular buffer, and let userspace
+	 * retry to get the rest of the data.
+	 */
+	ret = min_t(size_t, CIRC_CNT_TO_END(cb->head, cb->tail, LOG_SIZE),
+		    count);
+
+	if (copy_to_user(buf, cb->buf + cb->tail, ret)) {
+		ret = -EFAULT;
+		goto error;
+	}
+
+	cb->tail = CIRC_ADD(cb->tail, LOG_SIZE, ret);
+
+error:
+	mutex_unlock(&debug_info->log_mutex);
+	return ret;
+}
+
+static unsigned int cros_ec_console_log_poll(struct file *file,
+					     poll_table *wait)
+{
+	struct cros_ec_debugfs *debug_info = file->private_data;
+	unsigned int mask = 0;
+
+	poll_wait(file, &debug_info->log_wq, wait);
+
+	mutex_lock(&debug_info->log_mutex);
+	if (CIRC_CNT(debug_info->log_buffer.head,
+		     debug_info->log_buffer.tail,
+		     LOG_SIZE))
+		mask |= POLLIN | POLLRDNORM;
+	mutex_unlock(&debug_info->log_mutex);
+
+	return mask;
+}
+
+static int cros_ec_console_log_release(struct inode *inode, struct file *file)
+{
+	return 0;
+}
+
+const struct file_operations cros_ec_console_log_fops = {
+	.owner = THIS_MODULE,
+	.open = cros_ec_console_log_open,
+	.read = cros_ec_console_log_read,
+	.llseek = no_llseek,
+	.poll = cros_ec_console_log_poll,
+	.release = cros_ec_console_log_release,
+};
+
+static int ec_read_version_supported(struct cros_ec_dev *ec)
+{
+	struct ec_params_get_cmd_versions_v1 *params;
+	struct ec_response_get_cmd_versions *response;
+	int ret;
+
+	struct cros_ec_command *msg;
+
+	msg = kzalloc(sizeof(*msg) + max(sizeof(params), sizeof(response)),
+		GFP_KERNEL);
+	if (!msg)
+		return 0;
+
+	msg->command = EC_CMD_GET_CMD_VERSIONS + ec->cmd_offset;
+	msg->outsize = sizeof(params);
+	msg->insize = sizeof(response);
+
+	params = (struct ec_params_get_cmd_versions_v1 *)msg->data;
+	params->cmd = EC_CMD_CONSOLE_READ;
+	response = (struct ec_response_get_cmd_versions *)msg->data;
+
+	ret = cros_ec_cmd_xfer(ec->ec_dev, msg) >= 0 &&
+		msg->result == EC_RES_SUCCESS &&
+		(response->version_mask & EC_VER_MASK(1));
+
+	kfree(msg);
+
+	return ret;
+}
+
+static int cros_ec_create_console_log(struct cros_ec_debugfs *debug_info)
+{
+	struct cros_ec_dev *ec = debug_info->ec;
+	char *buf;
+	int read_params_size;
+	int read_response_size;
+
+	if (!ec_read_version_supported(ec)) {
+		dev_warn(ec->dev,
+			"device does not support reading the console log\n");
+		return 0;
+	}
+
+	buf = devm_kzalloc(ec->dev, LOG_SIZE, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	read_params_size = sizeof(struct ec_params_console_read_v1);
+	read_response_size = ec->ec_dev->max_response;
+	debug_info->read_msg = devm_kzalloc(ec->dev,
+		sizeof(*debug_info->read_msg) +
+			max(read_params_size, read_response_size), GFP_KERNEL);
+	if (!debug_info->read_msg)
+		return -ENOMEM;
+
+	debug_info->read_msg->version = 1;
+	debug_info->read_msg->command = EC_CMD_CONSOLE_READ + ec->cmd_offset;
+	debug_info->read_msg->outsize = read_params_size;
+	debug_info->read_msg->insize = read_response_size;
+
+	debug_info->log_buffer.buf = buf;
+	debug_info->log_buffer.head = 0;
+	debug_info->log_buffer.tail = 0;
+
+	mutex_init(&debug_info->log_mutex);
+	init_waitqueue_head(&debug_info->log_wq);
+
+	if (!debugfs_create_file("console_log",
+				 S_IFREG | S_IRUGO,
+				 debug_info->dir,
+				 debug_info,
+				 &cros_ec_console_log_fops))
+		return -ENOMEM;
+
+	INIT_DELAYED_WORK(&debug_info->log_poll_work,
+			  cros_ec_console_log_work);
+	schedule_delayed_work(&debug_info->log_poll_work, 0);
+
+	return 0;
+}
+
+static void cros_ec_cleanup_console_log(struct cros_ec_debugfs *debug_info)
+{
+	if (debug_info->log_buffer.buf) {
+		cancel_delayed_work_sync(&debug_info->log_poll_work);
+		mutex_destroy(&debug_info->log_mutex);
+	}
+}
+
+int cros_ec_debugfs_init(struct cros_ec_dev *ec)
+{
+	struct cros_ec_platform *ec_platform = dev_get_platdata(ec->dev);
+	const char *name = ec_platform->ec_name;
+	struct cros_ec_debugfs *debug_info;
+	int ret;
+
+	debug_info = devm_kzalloc(ec->dev, sizeof(*debug_info), GFP_KERNEL);
+	if (!debug_info)
+		return -ENOMEM;
+
+	debug_info->ec = ec;
+	debug_info->dir = debugfs_create_dir(name, NULL);
+	if (!debug_info->dir)
+		return -ENOMEM;
+
+	ret = cros_ec_create_console_log(debug_info);
+	if (ret)
+		goto remove_debugfs;
+
+	ec->debug_info = debug_info;
+
+	return 0;
+
+remove_debugfs:
+	debugfs_remove_recursive(debug_info->dir);
+	return ret;
+}
+
+void cros_ec_debugfs_remove(struct cros_ec_dev *ec)
+{
+	if (!ec->debug_info)
+		return;
+
+	debugfs_remove_recursive(ec->debug_info->dir);
+	cros_ec_cleanup_console_log(ec->debug_info);
+}
diff --git a/drivers/platform/chrome/cros_ec_debugfs.h b/drivers/platform/chrome/cros_ec_debugfs.h
new file mode 100644
index 000000000000..1ff3a50aa1b8
--- /dev/null
+++ b/drivers/platform/chrome/cros_ec_debugfs.h
@@ -0,0 +1,27 @@
+/*
+ * Copyright 2015 Google, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _DRV_CROS_EC_DEBUGFS_H_
+#define _DRV_CROS_EC_DEBUGFS_H_
+
+#include "cros_ec_dev.h"
+
+/* debugfs stuff */
+int cros_ec_debugfs_init(struct cros_ec_dev *ec);
+void cros_ec_debugfs_remove(struct cros_ec_dev *ec);
+
+#endif  /* _DRV_CROS_EC_DEBUGFS_H_ */
diff --git a/drivers/platform/chrome/cros_ec_dev.c b/drivers/platform/chrome/cros_ec_dev.c
index 6aa120cd0574..20ce1c23fb5c 100644
--- a/drivers/platform/chrome/cros_ec_dev.c
+++ b/drivers/platform/chrome/cros_ec_dev.c
@@ -24,6 +24,7 @@
 #include <linux/slab.h>
 #include <linux/uaccess.h>
 
+#include "cros_ec_debugfs.h"
 #include "cros_ec_dev.h"
 
 /* Device variables */
@@ -427,6 +428,9 @@ static int ec_device_probe(struct platform_device *pdev)
 		goto failed;
 	}
 
+	if (cros_ec_debugfs_init(ec))
+		dev_warn(dev, "failed to create debugfs directory\n");
+
 	/* check whether this EC is a sensor hub. */
 	if (cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE))
 		cros_ec_sensors_register(ec);
@@ -441,6 +445,9 @@ failed:
 static int ec_device_remove(struct platform_device *pdev)
 {
 	struct cros_ec_dev *ec = dev_get_drvdata(&pdev->dev);
+
+	cros_ec_debugfs_remove(ec);
+
 	cdev_del(&ec->cdev);
 	device_unregister(&ec->class_dev);
 	return 0;
diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h
index b61b2e013698..3b16c9009749 100644
--- a/include/linux/mfd/cros_ec.h
+++ b/include/linux/mfd/cros_ec.h
@@ -172,6 +172,8 @@ struct cros_ec_platform {
 	u16 cmd_offset;
 };
 
+struct cros_ec_debugfs;
+
 /*
  * struct cros_ec_dev - ChromeOS EC device entry point
  *
@@ -179,6 +181,7 @@ struct cros_ec_platform {
  * @cdev: Character device structure in /dev
  * @ec_dev: cros_ec_device structure to talk to the physical device
  * @dev: pointer to the platform device
+ * @debug_info: cros_ec_debugfs structure for debugging information
  * @cmd_offset: offset to apply for each command.
  */
 struct cros_ec_dev {
@@ -186,6 +189,7 @@ struct cros_ec_dev {
 	struct cdev cdev;
 	struct cros_ec_device *ec_dev;
 	struct device *dev;
+	struct cros_ec_debugfs *debug_info;
 	u16 cmd_offset;
 	u32 features[2];
 };
-- 
cgit v1.2.3


From e297a783e41560b44e3c14f38e420cba518113b8 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Wed, 7 Jun 2017 19:58:56 -0400
Subject: random: add wait_for_random_bytes() API

This enables users of get_random_{bytes,u32,u64,int,long} to wait until
the pool is ready before using this function, in case they actually want
to have reliable randomness.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 drivers/char/random.c  | 41 +++++++++++++++++++++++++++++++----------
 include/linux/random.h |  1 +
 2 files changed, 32 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/char/random.c b/drivers/char/random.c
index 01a260f67437..3853dd4f92e7 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -851,11 +851,6 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r)
 	}
 }
 
-static inline void crng_wait_ready(void)
-{
-	wait_event_interruptible(crng_init_wait, crng_ready());
-}
-
 static void _extract_crng(struct crng_state *crng,
 			  __u8 out[CHACHA20_BLOCK_SIZE])
 {
@@ -1477,7 +1472,10 @@ static ssize_t extract_entropy_user(struct entropy_store *r, void __user *buf,
  * number of good random numbers, suitable for key generation, seeding
  * TCP sequence numbers, etc.  It does not rely on the hardware random
  * number generator.  For random bytes direct from the hardware RNG
- * (when available), use get_random_bytes_arch().
+ * (when available), use get_random_bytes_arch(). In order to ensure
+ * that the randomness provided by this function is okay, the function
+ * wait_for_random_bytes() should be called and return 0 at least once
+ * at any point prior.
  */
 void get_random_bytes(void *buf, int nbytes)
 {
@@ -1506,6 +1504,24 @@ void get_random_bytes(void *buf, int nbytes)
 }
 EXPORT_SYMBOL(get_random_bytes);
 
+/*
+ * Wait for the urandom pool to be seeded and thus guaranteed to supply
+ * cryptographically secure random numbers. This applies to: the /dev/urandom
+ * device, the get_random_bytes function, and the get_random_{u32,u64,int,long}
+ * family of functions. Using any of these functions without first calling
+ * this function forfeits the guarantee of security.
+ *
+ * Returns: 0 if the urandom pool has been seeded.
+ *          -ERESTARTSYS if the function was interrupted by a signal.
+ */
+int wait_for_random_bytes(void)
+{
+	if (likely(crng_ready()))
+		return 0;
+	return wait_event_interruptible(crng_init_wait, crng_ready());
+}
+EXPORT_SYMBOL(wait_for_random_bytes);
+
 /*
  * Add a callback function that will be invoked when the nonblocking
  * pool is initialised.
@@ -1860,6 +1876,8 @@ const struct file_operations urandom_fops = {
 SYSCALL_DEFINE3(getrandom, char __user *, buf, size_t, count,
 		unsigned int, flags)
 {
+	int ret;
+
 	if (flags & ~(GRND_NONBLOCK|GRND_RANDOM))
 		return -EINVAL;
 
@@ -1872,9 +1890,9 @@ SYSCALL_DEFINE3(getrandom, char __user *, buf, size_t, count,
 	if (!crng_ready()) {
 		if (flags & GRND_NONBLOCK)
 			return -EAGAIN;
-		crng_wait_ready();
-		if (signal_pending(current))
-			return -ERESTARTSYS;
+		ret = wait_for_random_bytes();
+		if (unlikely(ret))
+			return ret;
 	}
 	return urandom_read(NULL, buf, count, NULL);
 }
@@ -2035,7 +2053,10 @@ static rwlock_t batched_entropy_reset_lock = __RW_LOCK_UNLOCKED(batched_entropy_
 /*
  * Get a random word for internal kernel use only. The quality of the random
  * number is either as good as RDRAND or as good as /dev/urandom, with the
- * goal of being quite fast and not depleting entropy.
+ * goal of being quite fast and not depleting entropy. In order to ensure
+ * that the randomness provided by this function is okay, the function
+ * wait_for_random_bytes() should be called and return 0 at least once
+ * at any point prior.
  */
 static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u64);
 u64 get_random_u64(void)
diff --git a/include/linux/random.h b/include/linux/random.h
index ed5c3838780d..e29929347c95 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -34,6 +34,7 @@ extern void add_input_randomness(unsigned int type, unsigned int code,
 extern void add_interrupt_randomness(int irq, int irq_flags) __latent_entropy;
 
 extern void get_random_bytes(void *buf, int nbytes);
+extern int wait_for_random_bytes(void);
 extern int add_random_ready_callback(struct random_ready_callback *rdy);
 extern void del_random_ready_callback(struct random_ready_callback *rdy);
 extern void get_random_bytes_arch(void *buf, int nbytes);
-- 
cgit v1.2.3


From da9ba564bd683374b8d319756f312821b8265b06 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Wed, 7 Jun 2017 20:05:02 -0400
Subject: random: add get_random_{bytes,u32,u64,int,long,once}_wait family

These functions are simple convenience wrappers that call
wait_for_random_bytes before calling the respective get_random_*
function.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 include/linux/net.h    |  2 ++
 include/linux/once.h   |  2 ++
 include/linux/random.h | 25 +++++++++++++++++++++++++
 3 files changed, 29 insertions(+)

(limited to 'include')

diff --git a/include/linux/net.h b/include/linux/net.h
index abcfa46a2bd9..dda2cc939a53 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -274,6 +274,8 @@ do {									\
 
 #define net_get_random_once(buf, nbytes)			\
 	get_random_once((buf), (nbytes))
+#define net_get_random_once_wait(buf, nbytes)			\
+	get_random_once_wait((buf), (nbytes))
 
 int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec,
 		   size_t num, size_t len);
diff --git a/include/linux/once.h b/include/linux/once.h
index 285f12cb40e6..9c98aaa87cbc 100644
--- a/include/linux/once.h
+++ b/include/linux/once.h
@@ -53,5 +53,7 @@ void __do_once_done(bool *done, struct static_key *once_key,
 
 #define get_random_once(buf, nbytes)					     \
 	DO_ONCE(get_random_bytes, (buf), (nbytes))
+#define get_random_once_wait(buf, nbytes)                                    \
+	DO_ONCE(get_random_bytes_wait, (buf), (nbytes))                      \
 
 #endif /* _LINUX_ONCE_H */
diff --git a/include/linux/random.h b/include/linux/random.h
index e29929347c95..4aecc339558d 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -58,6 +58,31 @@ static inline unsigned long get_random_long(void)
 #endif
 }
 
+/* Calls wait_for_random_bytes() and then calls get_random_bytes(buf, nbytes).
+ * Returns the result of the call to wait_for_random_bytes. */
+static inline int get_random_bytes_wait(void *buf, int nbytes)
+{
+	int ret = wait_for_random_bytes();
+	if (unlikely(ret))
+		return ret;
+	get_random_bytes(buf, nbytes);
+	return 0;
+}
+
+#define declare_get_random_var_wait(var) \
+	static inline int get_random_ ## var ## _wait(var *out) { \
+		int ret = wait_for_random_bytes(); \
+		if (unlikely(ret)) \
+			return ret; \
+		*out = get_random_ ## var(); \
+		return 0; \
+	}
+declare_get_random_var_wait(u32)
+declare_get_random_var_wait(u64)
+declare_get_random_var_wait(int)
+declare_get_random_var_wait(long)
+#undef declare_get_random_var
+
 unsigned long randomize_page(unsigned long start, unsigned long range);
 
 u32 prandom_u32(void);
-- 
cgit v1.2.3


From 3708184afc77bb67709a67a35d9f367ebd32cbc4 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Tue, 6 Jun 2017 12:37:37 +0300
Subject: device property: Move FW type specific functionality to FW specific
 files

The device and fwnode property API supports Devicetree, ACPI and pset
properties. The implementation of this functionality for each firmware
type was embedded in the fwnode property core. Move it out to firmware
type specific locations, making it easier to maintain.

Depends-on: ("of: Move OF property and graph API from base.c to property.c")
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/property.c |  68 ++++++++++++++++
 drivers/acpi/scan.c     |   1 +
 drivers/base/property.c | 208 +++++++++++++++++++-----------------------------
 drivers/of/property.c   |  90 +++++++++++++++++++++
 include/linux/acpi.h    |   4 +
 include/linux/fwnode.h  |  54 +++++++++++++
 include/linux/of.h      |   2 +
 7 files changed, 302 insertions(+), 125 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index 9364398204e9..14013f635db6 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -57,6 +57,7 @@ static bool acpi_nondev_subnode_extract(const union acpi_object *desc,
 
 	dn->name = link->package.elements[0].string.pointer;
 	dn->fwnode.type = FWNODE_ACPI_DATA;
+	dn->fwnode.ops = &acpi_fwnode_ops;
 	dn->parent = parent;
 	INIT_LIST_HEAD(&dn->data.subnodes);
 
@@ -1119,3 +1120,70 @@ int acpi_graph_get_remote_endpoint(struct fwnode_handle *fwnode,
 
 	return 0;
 }
+
+static bool acpi_fwnode_property_present(struct fwnode_handle *fwnode,
+					 const char *propname)
+{
+	return !acpi_node_prop_get(fwnode, propname, NULL);
+}
+
+static int acpi_fwnode_property_read_int_array(struct fwnode_handle *fwnode,
+					       const char *propname,
+					       unsigned int elem_size,
+					       void *val, size_t nval)
+{
+	enum dev_prop_type type;
+
+	switch (elem_size) {
+	case sizeof(u8):
+		type = DEV_PROP_U8;
+		break;
+	case sizeof(u16):
+		type = DEV_PROP_U16;
+		break;
+	case sizeof(u32):
+		type = DEV_PROP_U32;
+		break;
+	case sizeof(u64):
+		type = DEV_PROP_U64;
+		break;
+	default:
+		return -ENXIO;
+	}
+
+	return acpi_node_prop_read(fwnode, propname, type, val, nval);
+}
+
+static int acpi_fwnode_property_read_string_array(struct fwnode_handle *fwnode,
+						  const char *propname,
+						  const char **val, size_t nval)
+{
+	return acpi_node_prop_read(fwnode, propname, DEV_PROP_STRING,
+				   val, nval);
+}
+
+static struct fwnode_handle *
+acpi_fwnode_get_named_child_node(struct fwnode_handle *fwnode,
+				 const char *childname)
+{
+	struct fwnode_handle *child;
+
+	/*
+	 * Find first matching named child node of this fwnode.
+	 * For ACPI this will be a data only sub-node.
+	 */
+	fwnode_for_each_child_node(fwnode, child)
+		if (acpi_data_node_match(child, childname))
+			return child;
+
+	return NULL;
+}
+
+const struct fwnode_operations acpi_fwnode_ops = {
+	.property_present = acpi_fwnode_property_present,
+	.property_read_int_array = acpi_fwnode_property_read_int_array,
+	.property_read_string_array = acpi_fwnode_property_read_string_array,
+	.get_parent = acpi_node_get_parent,
+	.get_next_child_node = acpi_get_next_subnode,
+	.get_named_child_node = acpi_fwnode_get_named_child_node,
+};
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index c98f88b28948..bc2a525c495f 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1436,6 +1436,7 @@ void acpi_init_device_object(struct acpi_device *device, acpi_handle handle,
 	device->handle = handle;
 	device->parent = acpi_bus_get_parent(handle);
 	device->fwnode.type = FWNODE_ACPI;
+	device->fwnode.ops = &acpi_fwnode_ops;
 	acpi_set_device_status(device, sta);
 	acpi_device_get_busid(device);
 	acpi_set_pnp_ids(handle, &device->pnp, type);
diff --git a/drivers/base/property.c b/drivers/base/property.c
index 149de311a10e..fee0705e40e9 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -187,6 +187,50 @@ struct fwnode_handle *dev_fwnode(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(dev_fwnode);
 
+static bool pset_fwnode_property_present(struct fwnode_handle *fwnode,
+					 const char *propname)
+{
+	return !!pset_prop_get(to_pset_node(fwnode), propname);
+}
+
+static int pset_fwnode_read_int_array(struct fwnode_handle *fwnode,
+				      const char *propname,
+				      unsigned int elem_size, void *val,
+				      size_t nval)
+{
+	struct property_set *node = to_pset_node(fwnode);
+
+	if (!val)
+		return pset_prop_count_elems_of_size(node, propname, elem_size);
+
+	switch (elem_size) {
+	case sizeof(u8):
+		return pset_prop_read_u8_array(node, propname, val, nval);
+	case sizeof(u16):
+		return pset_prop_read_u16_array(node, propname, val, nval);
+	case sizeof(u32):
+		return pset_prop_read_u32_array(node, propname, val, nval);
+	case sizeof(u64):
+		return pset_prop_read_u64_array(node, propname, val, nval);
+	}
+
+	return -ENXIO;
+}
+
+static int pset_fwnode_property_read_string_array(struct fwnode_handle *fwnode,
+						  const char *propname,
+						  const char **val, size_t nval)
+{
+	return pset_prop_read_string_array(to_pset_node(fwnode), propname,
+					   val, nval);
+}
+
+static const struct fwnode_operations pset_fwnode_ops = {
+	.property_present = pset_fwnode_property_present,
+	.property_read_int_array = pset_fwnode_read_int_array,
+	.property_read_string_array = pset_fwnode_property_read_string_array,
+};
+
 /**
  * device_property_present - check if a property of a device is present
  * @dev: Device whose property is being checked
@@ -200,18 +244,6 @@ bool device_property_present(struct device *dev, const char *propname)
 }
 EXPORT_SYMBOL_GPL(device_property_present);
 
-static bool __fwnode_property_present(struct fwnode_handle *fwnode,
-				      const char *propname)
-{
-	if (is_of_node(fwnode))
-		return of_property_read_bool(to_of_node(fwnode), propname);
-	else if (is_acpi_node(fwnode))
-		return !acpi_node_prop_get(fwnode, propname, NULL);
-	else if (is_pset_node(fwnode))
-		return !!pset_prop_get(to_pset_node(fwnode), propname);
-	return false;
-}
-
 /**
  * fwnode_property_present - check if a property of a firmware node is present
  * @fwnode: Firmware node whose property to check
@@ -221,10 +253,11 @@ bool fwnode_property_present(struct fwnode_handle *fwnode, const char *propname)
 {
 	bool ret;
 
-	ret = __fwnode_property_present(fwnode, propname);
+	ret = fwnode_call_int_op(fwnode, property_present, propname);
 	if (ret == false && !IS_ERR_OR_NULL(fwnode) &&
 	    !IS_ERR_OR_NULL(fwnode->secondary))
-		ret = __fwnode_property_present(fwnode->secondary, propname);
+		ret = fwnode_call_int_op(fwnode->secondary, property_present,
+					 propname);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(fwnode_property_present);
@@ -398,42 +431,23 @@ int device_property_match_string(struct device *dev, const char *propname,
 }
 EXPORT_SYMBOL_GPL(device_property_match_string);
 
-#define OF_DEV_PROP_READ_ARRAY(node, propname, type, val, nval)				\
-	(val) ? of_property_read_##type##_array((node), (propname), (val), (nval))	\
-	      : of_property_count_elems_of_size((node), (propname), sizeof(type))
-
-#define PSET_PROP_READ_ARRAY(node, propname, type, val, nval)				\
-	(val) ? pset_prop_read_##type##_array((node), (propname), (val), (nval))	\
-	      : pset_prop_count_elems_of_size((node), (propname), sizeof(type))
-
-#define FWNODE_PROP_READ(_fwnode_, _propname_, _type_, _proptype_, _val_, _nval_)	\
-({											\
-	int _ret_;									\
-	if (is_of_node(_fwnode_))							\
-		_ret_ = OF_DEV_PROP_READ_ARRAY(to_of_node(_fwnode_), _propname_,	\
-					       _type_, _val_, _nval_);			\
-	else if (is_acpi_node(_fwnode_))						\
-		_ret_ = acpi_node_prop_read(_fwnode_, _propname_, _proptype_,		\
-					    _val_, _nval_);				\
-	else if (is_pset_node(_fwnode_)) 						\
-		_ret_ = PSET_PROP_READ_ARRAY(to_pset_node(_fwnode_), _propname_,	\
-					     _type_, _val_, _nval_);			\
-	else										\
-		_ret_ = -ENXIO;								\
-	_ret_;										\
-})
-
-#define FWNODE_PROP_READ_ARRAY(_fwnode_, _propname_, _type_, _proptype_, _val_, _nval_)	\
-({											\
-	int _ret_;									\
-	_ret_ = FWNODE_PROP_READ(_fwnode_, _propname_, _type_, _proptype_,		\
-				 _val_, _nval_);					\
-	if (_ret_ == -EINVAL && !IS_ERR_OR_NULL(_fwnode_) &&				\
-	    !IS_ERR_OR_NULL(_fwnode_->secondary))					\
-		_ret_ = FWNODE_PROP_READ(_fwnode_->secondary, _propname_, _type_,	\
-				_proptype_, _val_, _nval_);				\
-	_ret_;										\
-})
+static int fwnode_property_read_int_array(struct fwnode_handle *fwnode,
+					  const char *propname,
+					  unsigned int elem_size, void *val,
+					  size_t nval)
+{
+	int ret;
+
+	ret = fwnode_call_int_op(fwnode, property_read_int_array, propname,
+				 elem_size, val, nval);
+	if (ret == -EINVAL && !IS_ERR_OR_NULL(fwnode) &&
+	    !IS_ERR_OR_NULL(fwnode->secondary))
+		ret = fwnode_call_int_op(
+			fwnode->secondary, property_read_int_array, propname,
+			elem_size, val, nval);
+
+	return ret;
+}
 
 /**
  * fwnode_property_read_u8_array - return a u8 array property of firmware node
@@ -456,8 +470,8 @@ EXPORT_SYMBOL_GPL(device_property_match_string);
 int fwnode_property_read_u8_array(struct fwnode_handle *fwnode,
 				  const char *propname, u8 *val, size_t nval)
 {
-	return FWNODE_PROP_READ_ARRAY(fwnode, propname, u8, DEV_PROP_U8,
-				      val, nval);
+	return fwnode_property_read_int_array(fwnode, propname, sizeof(u8),
+					      val, nval);
 }
 EXPORT_SYMBOL_GPL(fwnode_property_read_u8_array);
 
@@ -482,8 +496,8 @@ EXPORT_SYMBOL_GPL(fwnode_property_read_u8_array);
 int fwnode_property_read_u16_array(struct fwnode_handle *fwnode,
 				   const char *propname, u16 *val, size_t nval)
 {
-	return FWNODE_PROP_READ_ARRAY(fwnode, propname, u16, DEV_PROP_U16,
-				      val, nval);
+	return fwnode_property_read_int_array(fwnode, propname, sizeof(u16),
+					      val, nval);
 }
 EXPORT_SYMBOL_GPL(fwnode_property_read_u16_array);
 
@@ -508,8 +522,8 @@ EXPORT_SYMBOL_GPL(fwnode_property_read_u16_array);
 int fwnode_property_read_u32_array(struct fwnode_handle *fwnode,
 				   const char *propname, u32 *val, size_t nval)
 {
-	return FWNODE_PROP_READ_ARRAY(fwnode, propname, u32, DEV_PROP_U32,
-				      val, nval);
+	return fwnode_property_read_int_array(fwnode, propname, sizeof(u32),
+					      val, nval);
 }
 EXPORT_SYMBOL_GPL(fwnode_property_read_u32_array);
 
@@ -534,29 +548,11 @@ EXPORT_SYMBOL_GPL(fwnode_property_read_u32_array);
 int fwnode_property_read_u64_array(struct fwnode_handle *fwnode,
 				   const char *propname, u64 *val, size_t nval)
 {
-	return FWNODE_PROP_READ_ARRAY(fwnode, propname, u64, DEV_PROP_U64,
-				      val, nval);
+	return fwnode_property_read_int_array(fwnode, propname, sizeof(u64),
+					      val, nval);
 }
 EXPORT_SYMBOL_GPL(fwnode_property_read_u64_array);
 
-static int __fwnode_property_read_string_array(struct fwnode_handle *fwnode,
-					       const char *propname,
-					       const char **val, size_t nval)
-{
-	if (is_of_node(fwnode))
-		return val ?
-			of_property_read_string_array(to_of_node(fwnode),
-						      propname, val, nval) :
-			of_property_count_strings(to_of_node(fwnode), propname);
-	else if (is_acpi_node(fwnode))
-		return acpi_node_prop_read(fwnode, propname, DEV_PROP_STRING,
-					   val, nval);
-	else if (is_pset_node(fwnode))
-		return pset_prop_read_string_array(to_pset_node(fwnode),
-						   propname, val, nval);
-	return -ENXIO;
-}
-
 /**
  * fwnode_property_read_string_array - return string array property of a node
  * @fwnode: Firmware node to get the property of
@@ -581,11 +577,13 @@ int fwnode_property_read_string_array(struct fwnode_handle *fwnode,
 {
 	int ret;
 
-	ret = __fwnode_property_read_string_array(fwnode, propname, val, nval);
+	ret = fwnode_call_int_op(fwnode, property_read_string_array, propname,
+				 val, nval);
 	if (ret == -EINVAL && !IS_ERR_OR_NULL(fwnode) &&
 	    !IS_ERR_OR_NULL(fwnode->secondary))
-		ret = __fwnode_property_read_string_array(fwnode->secondary,
-							  propname, val, nval);
+		ret = fwnode_call_int_op(fwnode->secondary,
+					 property_read_string_array, propname,
+					 val, nval);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(fwnode_property_read_string_array);
@@ -903,6 +901,7 @@ int device_add_properties(struct device *dev,
 		return PTR_ERR(p);
 
 	p->fwnode.type = FWNODE_PDATA;
+	p->fwnode.ops = &pset_fwnode_ops;
 	set_secondary_fwnode(dev, &p->fwnode);
 	return 0;
 }
@@ -938,19 +937,7 @@ EXPORT_SYMBOL_GPL(fwnode_get_next_parent);
  */
 struct fwnode_handle *fwnode_get_parent(struct fwnode_handle *fwnode)
 {
-	struct fwnode_handle *parent = NULL;
-
-	if (is_of_node(fwnode)) {
-		struct device_node *node;
-
-		node = of_get_parent(to_of_node(fwnode));
-		if (node)
-			parent = &node->fwnode;
-	} else if (is_acpi_node(fwnode)) {
-		parent = acpi_node_get_parent(fwnode);
-	}
-
-	return parent;
+	return fwnode_call_ptr_op(fwnode, get_parent);
 }
 EXPORT_SYMBOL_GPL(fwnode_get_parent);
 
@@ -962,18 +949,7 @@ EXPORT_SYMBOL_GPL(fwnode_get_parent);
 struct fwnode_handle *fwnode_get_next_child_node(struct fwnode_handle *fwnode,
 						 struct fwnode_handle *child)
 {
-	if (is_of_node(fwnode)) {
-		struct device_node *node;
-
-		node = of_get_next_available_child(to_of_node(fwnode),
-						   to_of_node(child));
-		if (node)
-			return &node->fwnode;
-	} else if (is_acpi_node(fwnode)) {
-		return acpi_get_next_subnode(fwnode, child);
-	}
-
-	return NULL;
+	return fwnode_call_ptr_op(fwnode, get_next_child_node, child);
 }
 EXPORT_SYMBOL_GPL(fwnode_get_next_child_node);
 
@@ -1005,23 +981,7 @@ EXPORT_SYMBOL_GPL(device_get_next_child_node);
 struct fwnode_handle *fwnode_get_named_child_node(struct fwnode_handle *fwnode,
 						  const char *childname)
 {
-	struct fwnode_handle *child;
-
-	/*
-	 * Find first matching named child node of this fwnode.
-	 * For ACPI this will be a data only sub-node.
-	 */
-	fwnode_for_each_child_node(fwnode, child) {
-		if (is_of_node(child)) {
-			if (!of_node_cmp(to_of_node(child)->name, childname))
-				return child;
-		} else if (is_acpi_data_node(child)) {
-			if (acpi_data_node_match(child, childname))
-				return child;
-		}
-	}
-
-	return NULL;
+	return fwnode_call_ptr_op(fwnode, get_named_child_node, childname);
 }
 EXPORT_SYMBOL_GPL(fwnode_get_named_child_node);
 
@@ -1043,8 +1003,7 @@ EXPORT_SYMBOL_GPL(device_get_named_child_node);
  */
 void fwnode_handle_get(struct fwnode_handle *fwnode)
 {
-	if (is_of_node(fwnode))
-		of_node_get(to_of_node(fwnode));
+	fwnode_call_void_op(fwnode, get);
 }
 EXPORT_SYMBOL_GPL(fwnode_handle_get);
 
@@ -1058,8 +1017,7 @@ EXPORT_SYMBOL_GPL(fwnode_handle_get);
  */
 void fwnode_handle_put(struct fwnode_handle *fwnode)
 {
-	if (is_of_node(fwnode))
-		of_node_put(to_of_node(fwnode));
+	fwnode_call_void_op(fwnode, put);
 }
 EXPORT_SYMBOL_GPL(fwnode_handle_put);
 
diff --git a/drivers/of/property.c b/drivers/of/property.c
index 457c313a8924..250859234fb0 100644
--- a/drivers/of/property.c
+++ b/drivers/of/property.c
@@ -764,3 +764,93 @@ struct device_node *of_graph_get_remote_node(const struct device_node *node,
 	return remote;
 }
 EXPORT_SYMBOL(of_graph_get_remote_node);
+
+static void of_fwnode_get(struct fwnode_handle *fwnode)
+{
+	of_node_get(to_of_node(fwnode));
+}
+
+static void of_fwnode_put(struct fwnode_handle *fwnode)
+{
+	of_node_put(to_of_node(fwnode));
+}
+
+static bool of_fwnode_property_present(struct fwnode_handle *fwnode,
+				       const char *propname)
+{
+	return of_property_read_bool(to_of_node(fwnode), propname);
+}
+
+static int of_fwnode_property_read_int_array(struct fwnode_handle *fwnode,
+					     const char *propname,
+					     unsigned int elem_size, void *val,
+					     size_t nval)
+{
+	struct device_node *node = to_of_node(fwnode);
+
+	if (!val)
+		return of_property_count_elems_of_size(node, propname,
+						       elem_size);
+
+	switch (elem_size) {
+	case sizeof(u8):
+		return of_property_read_u8_array(node, propname, val, nval);
+	case sizeof(u16):
+		return of_property_read_u16_array(node, propname, val, nval);
+	case sizeof(u32):
+		return of_property_read_u32_array(node, propname, val, nval);
+	case sizeof(u64):
+		return of_property_read_u64_array(node, propname, val, nval);
+	}
+
+	return -ENXIO;
+}
+
+static int of_fwnode_property_read_string_array(struct fwnode_handle *fwnode,
+						const char *propname,
+						const char **val, size_t nval)
+{
+	struct device_node *node = to_of_node(fwnode);
+
+	return val ?
+		of_property_read_string_array(node, propname, val, nval) :
+		of_property_count_strings(node, propname);
+}
+
+static struct fwnode_handle *of_fwnode_get_parent(struct fwnode_handle *fwnode)
+{
+	return of_fwnode_handle(of_get_parent(to_of_node(fwnode)));
+}
+
+static struct fwnode_handle *
+of_fwnode_get_next_child_node(struct fwnode_handle *fwnode,
+			      struct fwnode_handle *child)
+{
+	return of_fwnode_handle(of_get_next_available_child(to_of_node(fwnode),
+							    to_of_node(child)));
+}
+
+static struct fwnode_handle *
+of_fwnode_get_named_child_node(struct fwnode_handle *fwnode,
+			       const char *childname)
+{
+	struct device_node *node = to_of_node(fwnode);
+	struct device_node *child;
+
+	for_each_available_child_of_node(node, child)
+		if (!of_node_cmp(child->name, childname))
+			return of_fwnode_handle(child);
+
+	return NULL;
+}
+
+const struct fwnode_operations of_fwnode_ops = {
+	.get = of_fwnode_get,
+	.put = of_fwnode_put,
+	.property_present = of_fwnode_property_present,
+	.property_read_int_array = of_fwnode_property_read_int_array,
+	.property_read_string_array = of_fwnode_property_read_string_array,
+	.get_parent = of_fwnode_get_parent,
+	.get_next_child_node = of_fwnode_get_next_child_node,
+	.get_named_child_node = of_fwnode_get_named_child_node,
+};
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 137e4a3d89c5..b8f23c521b67 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -56,6 +56,9 @@ static inline acpi_handle acpi_device_handle(struct acpi_device *adev)
 	acpi_fwnode_handle(adev) : NULL)
 #define ACPI_HANDLE(dev)		acpi_device_handle(ACPI_COMPANION(dev))
 
+
+extern const struct fwnode_operations acpi_fwnode_ops;
+
 static inline struct fwnode_handle *acpi_alloc_fwnode_static(void)
 {
 	struct fwnode_handle *fwnode;
@@ -65,6 +68,7 @@ static inline struct fwnode_handle *acpi_alloc_fwnode_static(void)
 		return NULL;
 
 	fwnode->type = FWNODE_ACPI_STATIC;
+	fwnode->ops = &acpi_fwnode_ops;
 
 	return fwnode;
 }
diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h
index 3dff2398a5f0..8f64b3ae9c57 100644
--- a/include/linux/fwnode.h
+++ b/include/linux/fwnode.h
@@ -12,6 +12,8 @@
 #ifndef _LINUX_FWNODE_H_
 #define _LINUX_FWNODE_H_
 
+#include <linux/types.h>
+
 enum fwnode_type {
 	FWNODE_INVALID = 0,
 	FWNODE_OF,
@@ -22,9 +24,12 @@ enum fwnode_type {
 	FWNODE_IRQCHIP
 };
 
+struct fwnode_operations;
+
 struct fwnode_handle {
 	enum fwnode_type type;
 	struct fwnode_handle *secondary;
+	const struct fwnode_operations *ops;
 };
 
 /**
@@ -39,4 +44,53 @@ struct fwnode_endpoint {
 	const struct fwnode_handle *local_fwnode;
 };
 
+/**
+ * struct fwnode_operations - Operations for fwnode interface
+ * @get: Get a reference to an fwnode.
+ * @put: Put a reference to an fwnode.
+ * @property_present: Return true if a property is present.
+ * @property_read_integer_array: Read an array of integer properties. Return
+ *				 zero on success, a negative error code
+ *				 otherwise.
+ * @property_read_string_array: Read an array of string properties. Return zero
+ *				on success, a negative error code otherwise.
+ * @get_parent: Return the parent of an fwnode.
+ * @get_next_child_node: Return the next child node in an iteration.
+ * @get_named_child_node: Return a child node with a given name.
+ */
+struct fwnode_operations {
+	void (*get)(struct fwnode_handle *fwnode);
+	void (*put)(struct fwnode_handle *fwnode);
+	bool (*property_present)(struct fwnode_handle *fwnode,
+				 const char *propname);
+	int (*property_read_int_array)(struct fwnode_handle *fwnode,
+				       const char *propname,
+				       unsigned int elem_size, void *val,
+				       size_t nval);
+	int (*property_read_string_array)(struct fwnode_handle *fwnode_handle,
+					  const char *propname,
+					  const char **val, size_t nval);
+	struct fwnode_handle *(*get_parent)(struct fwnode_handle *fwnode);
+	struct fwnode_handle *
+	(*get_next_child_node)(struct fwnode_handle *fwnode,
+			       struct fwnode_handle *child);
+	struct fwnode_handle *
+	(*get_named_child_node)(struct fwnode_handle *fwnode, const char *name);
+};
+
+#define fwnode_has_op(fwnode, op)				\
+	((fwnode) && (fwnode)->ops && (fwnode)->ops->op)
+#define fwnode_call_int_op(fwnode, op, ...)				\
+	(fwnode ? (fwnode_has_op(fwnode, op) ?				\
+		   (fwnode)->ops->op(fwnode, ## __VA_ARGS__) : -ENXIO) : \
+	 -EINVAL)
+#define fwnode_call_ptr_op(fwnode, op, ...)		\
+	(fwnode_has_op(fwnode, op) ?			\
+	 (fwnode)->ops->op(fwnode, ## __VA_ARGS__) : NULL)
+#define fwnode_call_void_op(fwnode, op, ...)				\
+	do {								\
+		if (fwnode_has_op(fwnode, op))				\
+			(fwnode)->ops->op(fwnode, ## __VA_ARGS__);	\
+	} while (false)
+
 #endif
diff --git a/include/linux/of.h b/include/linux/of.h
index 29b7b738b509..cdbfa88c32cf 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -100,10 +100,12 @@ struct of_reconfig_data {
 
 /* initialize a node */
 extern struct kobj_type of_node_ktype;
+extern const struct fwnode_operations of_fwnode_ops;
 static inline void of_node_init(struct device_node *node)
 {
 	kobject_init(&node->kobj, &of_node_ktype);
 	node->fwnode.type = FWNODE_OF;
+	node->fwnode.ops = &of_fwnode_ops;
 }
 
 /* true when node is initialized */
-- 
cgit v1.2.3


From 3b27d00e7b6d7c889d87fd00df600c495b968e30 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Tue, 6 Jun 2017 12:37:38 +0300
Subject: device property: Move fwnode graph ops to firmware specific locations

Move firmware specific implementations of the fwnode graph operations to
firmware specific locations.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/property.c | 40 ++++++++++++++++++++++
 drivers/base/property.c | 91 +++++--------------------------------------------
 drivers/of/property.c   | 52 ++++++++++++++++++++++++++++
 include/linux/fwnode.h  | 14 ++++++++
 4 files changed, 114 insertions(+), 83 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index 14013f635db6..a24ca61294eb 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -1179,6 +1179,42 @@ acpi_fwnode_get_named_child_node(struct fwnode_handle *fwnode,
 	return NULL;
 }
 
+static struct fwnode_handle *
+acpi_fwnode_graph_get_next_endpoint(struct fwnode_handle *fwnode,
+				    struct fwnode_handle *prev)
+{
+	struct fwnode_handle *endpoint;
+
+	endpoint = acpi_graph_get_next_endpoint(fwnode, prev);
+	if (IS_ERR(endpoint))
+		return NULL;
+
+	return endpoint;
+}
+
+static struct fwnode_handle *
+acpi_fwnode_graph_get_remote_endpoint(struct fwnode_handle *fwnode)
+{
+	struct fwnode_handle *endpoint = NULL;
+
+	acpi_graph_get_remote_endpoint(fwnode, NULL, NULL, &endpoint);
+
+	return endpoint;
+}
+
+static int acpi_fwnode_graph_parse_endpoint(struct fwnode_handle *fwnode,
+					    struct fwnode_endpoint *endpoint)
+{
+	struct fwnode_handle *port_fwnode = fwnode_get_parent(fwnode);
+
+	endpoint->local_fwnode = fwnode;
+
+	fwnode_property_read_u32(port_fwnode, "port", &endpoint->port);
+	fwnode_property_read_u32(fwnode, "endpoint", &endpoint->id);
+
+	return 0;
+}
+
 const struct fwnode_operations acpi_fwnode_ops = {
 	.property_present = acpi_fwnode_property_present,
 	.property_read_int_array = acpi_fwnode_property_read_int_array,
@@ -1186,4 +1222,8 @@ const struct fwnode_operations acpi_fwnode_ops = {
 	.get_parent = acpi_node_get_parent,
 	.get_next_child_node = acpi_get_next_subnode,
 	.get_named_child_node = acpi_fwnode_get_named_child_node,
+	.graph_get_next_endpoint = acpi_fwnode_graph_get_next_endpoint,
+	.graph_get_remote_endpoint = acpi_fwnode_graph_get_remote_endpoint,
+	.graph_get_port_parent = acpi_node_get_parent,
+	.graph_parse_endpoint = acpi_fwnode_graph_parse_endpoint,
 };
diff --git a/drivers/base/property.c b/drivers/base/property.c
index fee0705e40e9..e1a58ac8840e 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -1156,24 +1156,7 @@ struct fwnode_handle *
 fwnode_graph_get_next_endpoint(struct fwnode_handle *fwnode,
 			       struct fwnode_handle *prev)
 {
-	struct fwnode_handle *endpoint = NULL;
-
-	if (is_of_node(fwnode)) {
-		struct device_node *node;
-
-		node = of_graph_get_next_endpoint(to_of_node(fwnode),
-						  to_of_node(prev));
-
-		if (node)
-			endpoint = &node->fwnode;
-	} else if (is_acpi_node(fwnode)) {
-		endpoint = acpi_graph_get_next_endpoint(fwnode, prev);
-		if (IS_ERR(endpoint))
-			endpoint = NULL;
-	}
-
-	return endpoint;
-
+	return fwnode_call_ptr_op(fwnode, graph_get_next_endpoint, prev);
 }
 EXPORT_SYMBOL_GPL(fwnode_graph_get_next_endpoint);
 
@@ -1186,22 +1169,12 @@ EXPORT_SYMBOL_GPL(fwnode_graph_get_next_endpoint);
 struct fwnode_handle *
 fwnode_graph_get_remote_port_parent(struct fwnode_handle *fwnode)
 {
-	struct fwnode_handle *parent = NULL;
+	struct fwnode_handle *port, *parent;
 
-	if (is_of_node(fwnode)) {
-		struct device_node *node;
+	port = fwnode_graph_get_remote_port(fwnode);
+	parent = fwnode_call_ptr_op(port, graph_get_port_parent);
 
-		node = of_graph_get_remote_port_parent(to_of_node(fwnode));
-		if (node)
-			parent = &node->fwnode;
-	} else if (is_acpi_node(fwnode)) {
-		int ret;
-
-		ret = acpi_graph_get_remote_endpoint(fwnode, &parent, NULL,
-						     NULL);
-		if (ret)
-			return NULL;
-	}
+	fwnode_handle_put(port);
 
 	return parent;
 }
@@ -1215,23 +1188,7 @@ EXPORT_SYMBOL_GPL(fwnode_graph_get_remote_port_parent);
  */
 struct fwnode_handle *fwnode_graph_get_remote_port(struct fwnode_handle *fwnode)
 {
-	struct fwnode_handle *port = NULL;
-
-	if (is_of_node(fwnode)) {
-		struct device_node *node;
-
-		node = of_graph_get_remote_port(to_of_node(fwnode));
-		if (node)
-			port = &node->fwnode;
-	} else if (is_acpi_node(fwnode)) {
-		int ret;
-
-		ret = acpi_graph_get_remote_endpoint(fwnode, NULL, &port, NULL);
-		if (ret)
-			return NULL;
-	}
-
-	return port;
+	return fwnode_get_next_parent(fwnode_graph_get_remote_endpoint(fwnode));
 }
 EXPORT_SYMBOL_GPL(fwnode_graph_get_remote_port);
 
@@ -1244,25 +1201,7 @@ EXPORT_SYMBOL_GPL(fwnode_graph_get_remote_port);
 struct fwnode_handle *
 fwnode_graph_get_remote_endpoint(struct fwnode_handle *fwnode)
 {
-	struct fwnode_handle *endpoint = NULL;
-
-	if (is_of_node(fwnode)) {
-		struct device_node *node;
-
-		node = of_parse_phandle(to_of_node(fwnode), "remote-endpoint",
-					0);
-		if (node)
-			endpoint = &node->fwnode;
-	} else if (is_acpi_node(fwnode)) {
-		int ret;
-
-		ret = acpi_graph_get_remote_endpoint(fwnode, NULL, NULL,
-						     &endpoint);
-		if (ret)
-			return NULL;
-	}
-
-	return endpoint;
+	return fwnode_call_ptr_op(fwnode, graph_get_remote_endpoint);
 }
 EXPORT_SYMBOL_GPL(fwnode_graph_get_remote_endpoint);
 
@@ -1278,22 +1217,8 @@ EXPORT_SYMBOL_GPL(fwnode_graph_get_remote_endpoint);
 int fwnode_graph_parse_endpoint(struct fwnode_handle *fwnode,
 				struct fwnode_endpoint *endpoint)
 {
-	struct fwnode_handle *port_fwnode = fwnode_get_parent(fwnode);
-
 	memset(endpoint, 0, sizeof(*endpoint));
 
-	endpoint->local_fwnode = fwnode;
-
-	if (is_acpi_node(port_fwnode)) {
-		fwnode_property_read_u32(port_fwnode, "port", &endpoint->port);
-		fwnode_property_read_u32(fwnode, "endpoint", &endpoint->id);
-	} else {
-		fwnode_property_read_u32(port_fwnode, "reg", &endpoint->port);
-		fwnode_property_read_u32(fwnode, "reg", &endpoint->id);
-	}
-
-	fwnode_handle_put(port_fwnode);
-
-	return 0;
+	return fwnode_call_int_op(fwnode, graph_parse_endpoint, endpoint);
 }
 EXPORT_SYMBOL(fwnode_graph_parse_endpoint);
diff --git a/drivers/of/property.c b/drivers/of/property.c
index 250859234fb0..e859e41e33f3 100644
--- a/drivers/of/property.c
+++ b/drivers/of/property.c
@@ -844,6 +844,54 @@ of_fwnode_get_named_child_node(struct fwnode_handle *fwnode,
 	return NULL;
 }
 
+static struct fwnode_handle *
+of_fwnode_graph_get_next_endpoint(struct fwnode_handle *fwnode,
+				  struct fwnode_handle *prev)
+{
+	return of_fwnode_handle(of_graph_get_next_endpoint(to_of_node(fwnode),
+							   to_of_node(prev)));
+}
+
+static struct fwnode_handle *
+of_fwnode_graph_get_remote_endpoint(struct fwnode_handle *fwnode)
+{
+	return of_fwnode_handle(of_parse_phandle(to_of_node(fwnode),
+						 "remote-endpoint", 0));
+}
+
+static struct fwnode_handle *
+of_fwnode_graph_get_port_parent(struct fwnode_handle *fwnode)
+{
+	struct device_node *np;
+
+	/* Get the parent of the port */
+	np = of_get_next_parent(to_of_node(fwnode));
+	if (!np)
+		return NULL;
+
+	/* Is this the "ports" node? If not, it's the port parent. */
+	if (of_node_cmp(np->name, "ports"))
+		return of_fwnode_handle(np);
+
+	return of_fwnode_handle(of_get_next_parent(np));
+}
+
+static int of_fwnode_graph_parse_endpoint(struct fwnode_handle *fwnode,
+					  struct fwnode_endpoint *endpoint)
+{
+	struct device_node *node = to_of_node(fwnode);
+	struct device_node *port_node = of_get_parent(node);
+
+	endpoint->local_fwnode = fwnode;
+
+	of_property_read_u32(port_node, "reg", &endpoint->port);
+	of_property_read_u32(node, "reg", &endpoint->id);
+
+	of_node_put(port_node);
+
+	return 0;
+}
+
 const struct fwnode_operations of_fwnode_ops = {
 	.get = of_fwnode_get,
 	.put = of_fwnode_put,
@@ -853,4 +901,8 @@ const struct fwnode_operations of_fwnode_ops = {
 	.get_parent = of_fwnode_get_parent,
 	.get_next_child_node = of_fwnode_get_next_child_node,
 	.get_named_child_node = of_fwnode_get_named_child_node,
+	.graph_get_next_endpoint = of_fwnode_graph_get_next_endpoint,
+	.graph_get_remote_endpoint = of_fwnode_graph_get_remote_endpoint,
+	.graph_get_port_parent = of_fwnode_graph_get_port_parent,
+	.graph_parse_endpoint = of_fwnode_graph_parse_endpoint,
 };
diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h
index 8f64b3ae9c57..e315d867d631 100644
--- a/include/linux/fwnode.h
+++ b/include/linux/fwnode.h
@@ -57,6 +57,11 @@ struct fwnode_endpoint {
  * @get_parent: Return the parent of an fwnode.
  * @get_next_child_node: Return the next child node in an iteration.
  * @get_named_child_node: Return a child node with a given name.
+ * @graph_get_next_endpoint: Return an endpoint node in an iteration.
+ * @graph_get_remote_endpoint: Return the remote endpoint node of a local
+ *			       endpoint node.
+ * @graph_get_port_parent: Return the parent node of a port node.
+ * @graph_parse_endpoint: Parse endpoint for port and endpoint id.
  */
 struct fwnode_operations {
 	void (*get)(struct fwnode_handle *fwnode);
@@ -76,6 +81,15 @@ struct fwnode_operations {
 			       struct fwnode_handle *child);
 	struct fwnode_handle *
 	(*get_named_child_node)(struct fwnode_handle *fwnode, const char *name);
+	struct fwnode_handle *
+	(*graph_get_next_endpoint)(struct fwnode_handle *fwnode,
+				   struct fwnode_handle *prev);
+	struct fwnode_handle *
+	(*graph_get_remote_endpoint)(struct fwnode_handle *fwnode);
+	struct fwnode_handle *
+	(*graph_get_port_parent)(struct fwnode_handle *fwnode);
+	int (*graph_parse_endpoint)(struct fwnode_handle *fwnode,
+				    struct fwnode_endpoint *endpoint);
 };
 
 #define fwnode_has_op(fwnode, op)				\
-- 
cgit v1.2.3


From 2294b3af05e9b3fe0b84a78971e709037bd7593c Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Tue, 6 Jun 2017 12:37:39 +0300
Subject: device property: Introduce fwnode_device_is_available()

Add fwnode_device_is_available() to tell whether the device corresponding
to a certain fwnode_handle is available for use.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/property.c  |  9 +++++++++
 drivers/base/property.c  | 10 ++++++++++
 drivers/of/property.c    |  6 ++++++
 include/linux/fwnode.h   |  1 +
 include/linux/property.h |  1 +
 5 files changed, 27 insertions(+)

(limited to 'include')

diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index a24ca61294eb..917c789f953d 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -1121,6 +1121,14 @@ int acpi_graph_get_remote_endpoint(struct fwnode_handle *fwnode,
 	return 0;
 }
 
+static bool acpi_fwnode_device_is_available(struct fwnode_handle *fwnode)
+{
+	if (!is_acpi_device_node(fwnode))
+		return false;
+
+	return acpi_device_is_present(to_acpi_device_node(fwnode));
+}
+
 static bool acpi_fwnode_property_present(struct fwnode_handle *fwnode,
 					 const char *propname)
 {
@@ -1216,6 +1224,7 @@ static int acpi_fwnode_graph_parse_endpoint(struct fwnode_handle *fwnode,
 }
 
 const struct fwnode_operations acpi_fwnode_ops = {
+	.device_is_available = acpi_fwnode_device_is_available,
 	.property_present = acpi_fwnode_property_present,
 	.property_read_int_array = acpi_fwnode_property_read_int_array,
 	.property_read_string_array = acpi_fwnode_property_read_string_array,
diff --git a/drivers/base/property.c b/drivers/base/property.c
index e1a58ac8840e..b979f8a2f4fb 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -1021,6 +1021,16 @@ void fwnode_handle_put(struct fwnode_handle *fwnode)
 }
 EXPORT_SYMBOL_GPL(fwnode_handle_put);
 
+/**
+ * fwnode_device_is_available - check if a device is available for use
+ * @fwnode: Pointer to the fwnode of the device.
+ */
+bool fwnode_device_is_available(struct fwnode_handle *fwnode)
+{
+	return fwnode_call_int_op(fwnode, device_is_available);
+}
+EXPORT_SYMBOL_GPL(fwnode_device_is_available);
+
 /**
  * device_get_child_node_count - return the number of child nodes for device
  * @dev: Device to cound the child nodes for
diff --git a/drivers/of/property.c b/drivers/of/property.c
index e859e41e33f3..c96389b7c6b3 100644
--- a/drivers/of/property.c
+++ b/drivers/of/property.c
@@ -775,6 +775,11 @@ static void of_fwnode_put(struct fwnode_handle *fwnode)
 	of_node_put(to_of_node(fwnode));
 }
 
+static bool of_fwnode_device_is_available(struct fwnode_handle *fwnode)
+{
+	return of_device_is_available(to_of_node(fwnode));
+}
+
 static bool of_fwnode_property_present(struct fwnode_handle *fwnode,
 				       const char *propname)
 {
@@ -895,6 +900,7 @@ static int of_fwnode_graph_parse_endpoint(struct fwnode_handle *fwnode,
 const struct fwnode_operations of_fwnode_ops = {
 	.get = of_fwnode_get,
 	.put = of_fwnode_put,
+	.device_is_available = of_fwnode_device_is_available,
 	.property_present = of_fwnode_property_present,
 	.property_read_int_array = of_fwnode_property_read_int_array,
 	.property_read_string_array = of_fwnode_property_read_string_array,
diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h
index e315d867d631..9ab375419189 100644
--- a/include/linux/fwnode.h
+++ b/include/linux/fwnode.h
@@ -66,6 +66,7 @@ struct fwnode_endpoint {
 struct fwnode_operations {
 	void (*get)(struct fwnode_handle *fwnode);
 	void (*put)(struct fwnode_handle *fwnode);
+	bool (*device_is_available)(struct fwnode_handle *fwnode);
 	bool (*property_present)(struct fwnode_handle *fwnode,
 				 const char *propname);
 	int (*property_read_int_array)(struct fwnode_handle *fwnode,
diff --git a/include/linux/property.h b/include/linux/property.h
index 2f482616a2f2..7be014af78ed 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -51,6 +51,7 @@ int device_property_read_string(struct device *dev, const char *propname,
 int device_property_match_string(struct device *dev,
 				 const char *propname, const char *string);
 
+bool fwnode_device_is_available(struct fwnode_handle *fwnode);
 bool fwnode_property_present(struct fwnode_handle *fwnode, const char *propname);
 int fwnode_property_read_u8_array(struct fwnode_handle *fwnode,
 				  const char *propname, u8 *val,
-- 
cgit v1.2.3


From 125ee6b3b0fa920c730b0991e6f083a9f5b1e4c3 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Tue, 6 Jun 2017 12:37:40 +0300
Subject: device property: Add FW type agnostic fwnode_graph_get_remote_node

Add fwnode_graph_get_remote_node() function which is equivalent to
of_graph_get_remote_node() on OF.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/property.c  | 37 +++++++++++++++++++++++++++++++++++++
 include/linux/property.h |  2 ++
 2 files changed, 39 insertions(+)

(limited to 'include')

diff --git a/drivers/base/property.c b/drivers/base/property.c
index b979f8a2f4fb..ac3590b1f93d 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -1215,6 +1215,43 @@ fwnode_graph_get_remote_endpoint(struct fwnode_handle *fwnode)
 }
 EXPORT_SYMBOL_GPL(fwnode_graph_get_remote_endpoint);
 
+/**
+ * fwnode_graph_get_remote_node - get remote parent node for given port/endpoint
+ * @fwnode: pointer to parent fwnode_handle containing graph port/endpoint
+ * @port_id: identifier of the parent port node
+ * @endpoint_id: identifier of the endpoint node
+ *
+ * Return: Remote fwnode handle associated with remote endpoint node linked
+ *	   to @node. Use fwnode_node_put() on it when done.
+ */
+struct fwnode_handle *fwnode_graph_get_remote_node(struct fwnode_handle *fwnode,
+						   u32 port_id, u32 endpoint_id)
+{
+	struct fwnode_handle *endpoint = NULL;
+
+	while ((endpoint = fwnode_graph_get_next_endpoint(fwnode, endpoint))) {
+		struct fwnode_endpoint fwnode_ep;
+		struct fwnode_handle *remote;
+		int ret;
+
+		ret = fwnode_graph_parse_endpoint(endpoint, &fwnode_ep);
+		if (ret < 0)
+			continue;
+
+		if (fwnode_ep.port != port_id || fwnode_ep.id != endpoint_id)
+			continue;
+
+		remote = fwnode_graph_get_remote_port_parent(endpoint);
+		if (!remote)
+			return NULL;
+
+		return fwnode_device_is_available(remote) ? remote : NULL;
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(fwnode_graph_get_remote_node);
+
 /**
  * fwnode_graph_parse_endpoint - parse common endpoint node properties
  * @fwnode: pointer to endpoint fwnode_handle
diff --git a/include/linux/property.h b/include/linux/property.h
index 7be014af78ed..0597a743aa66 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -281,6 +281,8 @@ struct fwnode_handle *fwnode_graph_get_remote_port(
 	struct fwnode_handle *fwnode);
 struct fwnode_handle *fwnode_graph_get_remote_endpoint(
 	struct fwnode_handle *fwnode);
+struct fwnode_handle *fwnode_graph_get_remote_node(struct fwnode_handle *fwnode,
+						   u32 port, u32 endpoint);
 
 int fwnode_graph_parse_endpoint(struct fwnode_handle *fwnode,
 				struct fwnode_endpoint *endpoint);
-- 
cgit v1.2.3


From 6a71d8d77795e0f7d887baa95bfc0d1d2bc74899 Mon Sep 17 00:00:00 2001
From: Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
Date: Tue, 6 Jun 2017 12:37:41 +0300
Subject: device property: Add fwnode_graph_get_port_parent

Provide a helper to obtain the parent device fwnode without first
parsing the remote-endpoint as per fwnode_graph_get_remote_port_parent.

Signed-off-by: Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/property.c  | 28 ++++++++++++++++++++++++----
 include/linux/property.h |  2 ++
 2 files changed, 26 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/base/property.c b/drivers/base/property.c
index ac3590b1f93d..692007e5a94b 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -1170,6 +1170,26 @@ fwnode_graph_get_next_endpoint(struct fwnode_handle *fwnode,
 }
 EXPORT_SYMBOL_GPL(fwnode_graph_get_next_endpoint);
 
+/**
+ * fwnode_graph_get_port_parent - Return the device fwnode of a port endpoint
+ * @endpoint: Endpoint firmware node of the port
+ *
+ * Return: the firmware node of the device the @endpoint belongs to.
+ */
+struct fwnode_handle *
+fwnode_graph_get_port_parent(struct fwnode_handle *endpoint)
+{
+	struct fwnode_handle *port, *parent;
+
+	port = fwnode_get_parent(endpoint);
+	parent = fwnode_call_ptr_op(port, graph_get_port_parent);
+
+	fwnode_handle_put(port);
+
+	return parent;
+}
+EXPORT_SYMBOL_GPL(fwnode_graph_get_port_parent);
+
 /**
  * fwnode_graph_get_remote_port_parent - Return fwnode of a remote device
  * @fwnode: Endpoint firmware node pointing to the remote endpoint
@@ -1179,12 +1199,12 @@ EXPORT_SYMBOL_GPL(fwnode_graph_get_next_endpoint);
 struct fwnode_handle *
 fwnode_graph_get_remote_port_parent(struct fwnode_handle *fwnode)
 {
-	struct fwnode_handle *port, *parent;
+	struct fwnode_handle *endpoint, *parent;
 
-	port = fwnode_graph_get_remote_port(fwnode);
-	parent = fwnode_call_ptr_op(port, graph_get_port_parent);
+	endpoint = fwnode_graph_get_remote_endpoint(fwnode);
+	parent = fwnode_graph_get_port_parent(endpoint);
 
-	fwnode_handle_put(port);
+	fwnode_handle_put(endpoint);
 
 	return parent;
 }
diff --git a/include/linux/property.h b/include/linux/property.h
index 0597a743aa66..7e77039e6b81 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -275,6 +275,8 @@ void *device_get_mac_address(struct device *dev, char *addr, int alen);
 
 struct fwnode_handle *fwnode_graph_get_next_endpoint(
 	struct fwnode_handle *fwnode, struct fwnode_handle *prev);
+struct fwnode_handle *
+fwnode_graph_get_port_parent(struct fwnode_handle *fwnode);
 struct fwnode_handle *fwnode_graph_get_remote_port_parent(
 	struct fwnode_handle *fwnode);
 struct fwnode_handle *fwnode_graph_get_remote_port(
-- 
cgit v1.2.3


From 1a0915be192606fee64830b9c5d70b7ed59426b6 Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <rafal@milecki.pl>
Date: Wed, 21 Jun 2017 08:26:46 +0200
Subject: mtd: partitions: add support for partition parsers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some devices have partitions that are kind of containers with extra
subpartitions / volumes instead of e.g. a simple filesystem data. To
support such cases we need to first create normal flash device
partitions and then take care of these special ones.

It's very common case for home routers. Depending on the vendor there
are formats like TRX, Seama, TP-Link, WRGG & more. All of them are used
to embed few partitions into a single one / single firmware file.

Ideally all vendors would use some well documented / standardized format
like UBI (and some probably start doing so), but there are still
countless devices on the market using these poor vendor specific
formats.

This patch extends MTD subsystem by allowing to specify list of parsers
that should be tried for a given partition. Supporting such poor formats
is highly unlikely to be the top priority so these changes try to
minimize maintenance cost to the minimum. It reuses existing code for
these new parsers and just adds a one property and one new function.

This implementation requires setting partition parsers in a flash
parser. A proper change of bcm47xxpart will follow and in the future we
will hopefully also find a solution for doing it with ofpart
("fixed-partitions").

Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 drivers/mtd/mtdpart.c          | 31 +++++++++++++++++++++++++++++++
 include/linux/mtd/partitions.h |  7 +++++++
 2 files changed, 38 insertions(+)

(limited to 'include')

diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c
index c0d464d192ee..2ad9493703f9 100644
--- a/drivers/mtd/mtdpart.c
+++ b/drivers/mtd/mtdpart.c
@@ -369,6 +369,35 @@ static inline void free_partition(struct mtd_part *p)
 	kfree(p);
 }
 
+/**
+ * mtd_parse_part - parse MTD partition looking for subpartitions
+ *
+ * @slave: part that is supposed to be a container and should be parsed
+ * @types: NULL-terminated array with names of partition parsers to try
+ *
+ * Some partitions are kind of containers with extra subpartitions (volumes).
+ * There can be various formats of such containers. This function tries to use
+ * specified parsers to analyze given partition and registers found
+ * subpartitions on success.
+ */
+static int mtd_parse_part(struct mtd_part *slave, const char *const *types)
+{
+	struct mtd_partitions parsed;
+	int err;
+
+	err = parse_mtd_partitions(&slave->mtd, types, &parsed, NULL);
+	if (err)
+		return err;
+	else if (!parsed.nr_parts)
+		return -ENOENT;
+
+	err = add_mtd_partitions(&slave->mtd, parsed.parts, parsed.nr_parts);
+
+	mtd_part_parser_cleanup(&parsed);
+
+	return err;
+}
+
 static struct mtd_part *allocate_partition(struct mtd_info *parent,
 			const struct mtd_partition *part, int partno,
 			uint64_t cur_offset)
@@ -758,6 +787,8 @@ int add_mtd_partitions(struct mtd_info *master,
 
 		add_mtd_device(&slave->mtd);
 		mtd_add_partition_attrs(slave);
+		if (parts[i].types)
+			mtd_parse_part(slave, parts[i].types);
 
 		cur_offset = slave->offset + slave->mtd.size;
 	}
diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h
index 06df1e06b6e0..c4beb70dacbd 100644
--- a/include/linux/mtd/partitions.h
+++ b/include/linux/mtd/partitions.h
@@ -20,6 +20,12 @@
  *
  * For each partition, these fields are available:
  * name: string that will be used to label the partition's MTD device.
+ * types: some partitions can be containers using specific format to describe
+ *	embedded subpartitions / volumes. E.g. many home routers use "firmware"
+ *	partition that contains at least kernel and rootfs. In such case an
+ *	extra parser is needed that will detect these dynamic partitions and
+ *	report them to the MTD subsystem. If set this property stores an array
+ *	of parser names to use when looking for subpartitions.
  * size: the partition size; if defined as MTDPART_SIZ_FULL, the partition
  * 	will extend to the end of the master MTD device.
  * offset: absolute starting position within the master MTD device; if
@@ -38,6 +44,7 @@
 
 struct mtd_partition {
 	const char *name;		/* identifier string */
+	const char *const *types;	/* names of parsers to use if any */
 	uint64_t size;			/* partition size */
 	uint64_t offset;		/* offset within the master MTD space */
 	uint32_t mask_flags;		/* master MTD flags to mask out for this partition */
-- 
cgit v1.2.3


From bce70fef7279243d62adbf5f53998b8d3d016144 Mon Sep 17 00:00:00 2001
From: Shawn Nematbakhsh <shawnn@chromium.org>
Date: Tue, 16 May 2017 17:46:48 +0200
Subject: platform/chrome: cros_ec_lpc: Add R/W helpers to LPC protocol
 variants

Call common functions for read / write to prepare support for future
LPC protocol variants which use different I/O ops than inb / outb.

Signed-off-by: Shawn Nematbakhsh <shawnn@chromium.org>
Signed-off-by: Thierry Escande <thierry.escande@collabora.com>
Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Benson Leung <bleung@chromium.org>
---
 drivers/platform/chrome/Makefile          |  3 +-
 drivers/platform/chrome/cros_ec_lpc.c     | 88 +++++++++++++------------------
 drivers/platform/chrome/cros_ec_lpc_reg.c | 64 ++++++++++++++++++++++
 include/linux/mfd/cros_ec_lpc_reg.h       | 47 +++++++++++++++++
 4 files changed, 151 insertions(+), 51 deletions(-)
 create mode 100644 drivers/platform/chrome/cros_ec_lpc_reg.c
 create mode 100644 include/linux/mfd/cros_ec_lpc_reg.h

(limited to 'include')

diff --git a/drivers/platform/chrome/Makefile b/drivers/platform/chrome/Makefile
index 3870afeefcf4..61182fd8f597 100644
--- a/drivers/platform/chrome/Makefile
+++ b/drivers/platform/chrome/Makefile
@@ -5,6 +5,7 @@ cros_ec_devs-objs			:= cros_ec_dev.o cros_ec_sysfs.o \
 					   cros_ec_lightbar.o cros_ec_vbc.o \
 					   cros_ec_debugfs.o
 obj-$(CONFIG_CROS_EC_CHARDEV)		+= cros_ec_devs.o
-obj-$(CONFIG_CROS_EC_LPC)		+= cros_ec_lpc.o
+cros_ec_lpcs-objs			:= cros_ec_lpc.o cros_ec_lpc_reg.o
+obj-$(CONFIG_CROS_EC_LPC)		+= cros_ec_lpcs.o
 obj-$(CONFIG_CROS_EC_PROTO)		+= cros_ec_proto.o
 obj-$(CONFIG_CROS_KBD_LED_BACKLIGHT)	+= cros_kbd_led_backlight.o
diff --git a/drivers/platform/chrome/cros_ec_lpc.c b/drivers/platform/chrome/cros_ec_lpc.c
index f9a245465fd0..6a782a695eb6 100644
--- a/drivers/platform/chrome/cros_ec_lpc.c
+++ b/drivers/platform/chrome/cros_ec_lpc.c
@@ -26,19 +26,22 @@
 #include <linux/io.h>
 #include <linux/mfd/cros_ec.h>
 #include <linux/mfd/cros_ec_commands.h>
+#include <linux/mfd/cros_ec_lpc_reg.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/printk.h>
 
-#define DRV_NAME "cros_ec_lpc"
+#define DRV_NAME "cros_ec_lpcs"
 
 static int ec_response_timed_out(void)
 {
 	unsigned long one_second = jiffies + HZ;
+	u8 data;
 
 	usleep_range(200, 300);
 	do {
-		if (!(inb(EC_LPC_ADDR_HOST_CMD) & EC_LPC_STATUS_BUSY_MASK))
+		if (!(cros_ec_lpc_read_bytes(EC_LPC_ADDR_HOST_CMD, 1, &data) &
+		    EC_LPC_STATUS_BUSY_MASK))
 			return 0;
 		usleep_range(100, 200);
 	} while (time_before(jiffies, one_second));
@@ -51,21 +54,20 @@ static int cros_ec_pkt_xfer_lpc(struct cros_ec_device *ec,
 {
 	struct ec_host_request *request;
 	struct ec_host_response response;
-	u8 sum = 0;
-	int i;
+	u8 sum;
 	int ret = 0;
 	u8 *dout;
 
 	ret = cros_ec_prepare_tx(ec, msg);
 
 	/* Write buffer */
-	for (i = 0; i < ret; i++)
-		outb(ec->dout[i], EC_LPC_ADDR_HOST_PACKET + i);
+	cros_ec_lpc_write_bytes(EC_LPC_ADDR_HOST_PACKET, ret, ec->dout);
 
 	request = (struct ec_host_request *)ec->dout;
 
 	/* Here we go */
-	outb(EC_COMMAND_PROTOCOL_3, EC_LPC_ADDR_HOST_CMD);
+	sum = EC_COMMAND_PROTOCOL_3;
+	cros_ec_lpc_write_bytes(EC_LPC_ADDR_HOST_CMD, 1, &sum);
 
 	if (ec_response_timed_out()) {
 		dev_warn(ec->dev, "EC responsed timed out\n");
@@ -74,17 +76,15 @@ static int cros_ec_pkt_xfer_lpc(struct cros_ec_device *ec,
 	}
 
 	/* Check result */
-	msg->result = inb(EC_LPC_ADDR_HOST_DATA);
+	msg->result = cros_ec_lpc_read_bytes(EC_LPC_ADDR_HOST_DATA, 1, &sum);
 	ret = cros_ec_check_result(ec, msg);
 	if (ret)
 		goto done;
 
 	/* Read back response */
 	dout = (u8 *)&response;
-	for (i = 0; i < sizeof(response); i++) {
-		dout[i] = inb(EC_LPC_ADDR_HOST_PACKET + i);
-		sum += dout[i];
-	}
+	sum = cros_ec_lpc_read_bytes(EC_LPC_ADDR_HOST_PACKET, sizeof(response),
+				     dout);
 
 	msg->result = response.result;
 
@@ -97,11 +97,9 @@ static int cros_ec_pkt_xfer_lpc(struct cros_ec_device *ec,
 	}
 
 	/* Read response and process checksum */
-	for (i = 0; i < response.data_len; i++) {
-		msg->data[i] =
-			inb(EC_LPC_ADDR_HOST_PACKET + sizeof(response) + i);
-		sum += msg->data[i];
-	}
+	sum += cros_ec_lpc_read_bytes(EC_LPC_ADDR_HOST_PACKET +
+				      sizeof(response), response.data_len,
+				      msg->data);
 
 	if (sum) {
 		dev_err(ec->dev,
@@ -121,8 +119,7 @@ static int cros_ec_cmd_xfer_lpc(struct cros_ec_device *ec,
 				struct cros_ec_command *msg)
 {
 	struct ec_lpc_host_args args;
-	int csum;
-	int i;
+	u8 sum;
 	int ret = 0;
 
 	if (msg->outsize > EC_PROTO2_MAX_PARAM_SIZE ||
@@ -139,24 +136,20 @@ static int cros_ec_cmd_xfer_lpc(struct cros_ec_device *ec,
 	args.data_size = msg->outsize;
 
 	/* Initialize checksum */
-	csum = msg->command + args.flags +
-		args.command_version + args.data_size;
+	sum = msg->command + args.flags + args.command_version + args.data_size;
 
 	/* Copy data and update checksum */
-	for (i = 0; i < msg->outsize; i++) {
-		outb(msg->data[i], EC_LPC_ADDR_HOST_PARAM + i);
-		csum += msg->data[i];
-	}
+	sum += cros_ec_lpc_write_bytes(EC_LPC_ADDR_HOST_PARAM, msg->outsize,
+				       msg->data);
 
 	/* Finalize checksum and write args */
-	args.checksum = csum & 0xFF;
-	outb(args.flags, EC_LPC_ADDR_HOST_ARGS);
-	outb(args.command_version, EC_LPC_ADDR_HOST_ARGS + 1);
-	outb(args.data_size, EC_LPC_ADDR_HOST_ARGS + 2);
-	outb(args.checksum, EC_LPC_ADDR_HOST_ARGS + 3);
+	args.checksum = sum;
+	cros_ec_lpc_write_bytes(EC_LPC_ADDR_HOST_ARGS, sizeof(args),
+				(u8 *)&args);
 
 	/* Here we go */
-	outb(msg->command, EC_LPC_ADDR_HOST_CMD);
+	sum = msg->command;
+	cros_ec_lpc_write_bytes(EC_LPC_ADDR_HOST_CMD, 1, &sum);
 
 	if (ec_response_timed_out()) {
 		dev_warn(ec->dev, "EC responsed timed out\n");
@@ -165,16 +158,14 @@ static int cros_ec_cmd_xfer_lpc(struct cros_ec_device *ec,
 	}
 
 	/* Check result */
-	msg->result = inb(EC_LPC_ADDR_HOST_DATA);
+	msg->result = cros_ec_lpc_read_bytes(EC_LPC_ADDR_HOST_DATA, 1, &sum);
 	ret = cros_ec_check_result(ec, msg);
 	if (ret)
 		goto done;
 
 	/* Read back args */
-	args.flags = inb(EC_LPC_ADDR_HOST_ARGS);
-	args.command_version = inb(EC_LPC_ADDR_HOST_ARGS + 1);
-	args.data_size = inb(EC_LPC_ADDR_HOST_ARGS + 2);
-	args.checksum = inb(EC_LPC_ADDR_HOST_ARGS + 3);
+	cros_ec_lpc_read_bytes(EC_LPC_ADDR_HOST_ARGS, sizeof(args),
+			       (u8 *)&args);
 
 	if (args.data_size > msg->insize) {
 		dev_err(ec->dev,
@@ -185,20 +176,17 @@ static int cros_ec_cmd_xfer_lpc(struct cros_ec_device *ec,
 	}
 
 	/* Start calculating response checksum */
-	csum = msg->command + args.flags +
-		args.command_version + args.data_size;
+	sum = msg->command + args.flags + args.command_version + args.data_size;
 
 	/* Read response and update checksum */
-	for (i = 0; i < args.data_size; i++) {
-		msg->data[i] = inb(EC_LPC_ADDR_HOST_PARAM + i);
-		csum += msg->data[i];
-	}
+	sum += cros_ec_lpc_read_bytes(EC_LPC_ADDR_HOST_PARAM, args.data_size,
+				      msg->data);
 
 	/* Verify checksum */
-	if (args.checksum != (csum & 0xFF)) {
+	if (args.checksum != sum) {
 		dev_err(ec->dev,
 			"bad packet checksum, expected %02x, got %02x\n",
-			args.checksum, csum & 0xFF);
+			args.checksum, sum);
 		ret = -EBADMSG;
 		goto done;
 	}
@@ -222,14 +210,13 @@ static int cros_ec_lpc_readmem(struct cros_ec_device *ec, unsigned int offset,
 
 	/* fixed length */
 	if (bytes) {
-		for (; cnt < bytes; i++, s++, cnt++)
-			*s = inb(EC_LPC_ADDR_MEMMAP + i);
-		return cnt;
+		cros_ec_lpc_read_bytes(EC_LPC_ADDR_MEMMAP + offset, bytes, s);
+		return bytes;
 	}
 
 	/* string */
 	for (; i < EC_MEMMAP_SIZE; i++, s++) {
-		*s = inb(EC_LPC_ADDR_MEMMAP + i);
+		cros_ec_lpc_read_bytes(EC_LPC_ADDR_MEMMAP + i, 1, s);
 		cnt++;
 		if (!*s)
 			break;
@@ -242,6 +229,7 @@ static int cros_ec_lpc_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct cros_ec_device *ec_dev;
+	u8 buf[2];
 	int ret;
 
 	if (!devm_request_region(dev, EC_LPC_ADDR_MEMMAP, EC_MEMMAP_SIZE,
@@ -250,8 +238,8 @@ static int cros_ec_lpc_probe(struct platform_device *pdev)
 		return -EBUSY;
 	}
 
-	if ((inb(EC_LPC_ADDR_MEMMAP + EC_MEMMAP_ID) != 'E') ||
-	    (inb(EC_LPC_ADDR_MEMMAP + EC_MEMMAP_ID + 1) != 'C')) {
+	cros_ec_lpc_read_bytes(EC_LPC_ADDR_MEMMAP + EC_MEMMAP_ID, 2, buf);
+	if (buf[0] != 'E' || buf[1] != 'C') {
 		dev_err(dev, "EC ID not detected\n");
 		return -ENODEV;
 	}
diff --git a/drivers/platform/chrome/cros_ec_lpc_reg.c b/drivers/platform/chrome/cros_ec_lpc_reg.c
new file mode 100644
index 000000000000..03c97813171e
--- /dev/null
+++ b/drivers/platform/chrome/cros_ec_lpc_reg.c
@@ -0,0 +1,64 @@
+/*
+ * cros_ec_lpc_reg - LPC access to the Chrome OS Embedded Controller
+ *
+ * Copyright (C) 2016 Google, Inc
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * This driver uses the Chrome OS EC byte-level message-based protocol for
+ * communicating the keyboard state (which keys are pressed) from a keyboard EC
+ * to the AP over some bus (such as i2c, lpc, spi).  The EC does debouncing,
+ * but everything else (including deghosting) is done here.  The main
+ * motivation for this is to keep the EC firmware as simple as possible, since
+ * it cannot be easily upgraded and EC flash/IRAM space is relatively
+ * expensive.
+ */
+
+#include <linux/io.h>
+#include <linux/mfd/cros_ec.h>
+#include <linux/mfd/cros_ec_commands.h>
+
+static u8 lpc_read_bytes(unsigned int offset, unsigned int length, u8 *dest)
+{
+	int i;
+	int sum = 0;
+
+	for (i = 0; i < length; ++i) {
+		dest[i] = inb(offset + i);
+		sum += dest[i];
+	}
+
+	/* Return checksum of all bytes read */
+	return sum;
+}
+
+static u8 lpc_write_bytes(unsigned int offset, unsigned int length, u8 *msg)
+{
+	int i;
+	int sum = 0;
+
+	for (i = 0; i < length; ++i) {
+		outb(msg[i], offset + i);
+		sum += msg[i];
+	}
+
+	/* Return checksum of all bytes written */
+	return sum;
+}
+
+u8 cros_ec_lpc_read_bytes(unsigned int offset, unsigned int length, u8 *dest)
+{
+	return lpc_read_bytes(offset, length, dest);
+}
+
+u8 cros_ec_lpc_write_bytes(unsigned int offset, unsigned int length, u8 *msg)
+{
+	return lpc_write_bytes(offset, length, msg);
+}
diff --git a/include/linux/mfd/cros_ec_lpc_reg.h b/include/linux/mfd/cros_ec_lpc_reg.h
new file mode 100644
index 000000000000..4089bd5c8313
--- /dev/null
+++ b/include/linux/mfd/cros_ec_lpc_reg.h
@@ -0,0 +1,47 @@
+/*
+ * cros_ec_lpc_reg - LPC access to the Chrome OS Embedded Controller
+ *
+ * Copyright (C) 2016 Google, Inc
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * This driver uses the Chrome OS EC byte-level message-based protocol for
+ * communicating the keyboard state (which keys are pressed) from a keyboard EC
+ * to the AP over some bus (such as i2c, lpc, spi).  The EC does debouncing,
+ * but everything else (including deghosting) is done here.  The main
+ * motivation for this is to keep the EC firmware as simple as possible, since
+ * it cannot be easily upgraded and EC flash/IRAM space is relatively
+ * expensive.
+ */
+
+#ifndef __LINUX_MFD_CROS_EC_REG_H
+#define __LINUX_MFD_CROS_EC_REG_H
+
+/**
+ * cros_ec_lpc_read_bytes - Read bytes from a given LPC-mapped address.
+ * Returns 8-bit checksum of all bytes read.
+ *
+ * @offset: Base read address
+ * @length: Number of bytes to read
+ * @dest: Destination buffer
+ */
+u8 cros_ec_lpc_read_bytes(unsigned int offset, unsigned int length, u8 *dest);
+
+/**
+ * cros_ec_lpc_write_bytes - Write bytes to a given LPC-mapped address.
+ * Returns 8-bit checksum of all bytes written.
+ *
+ * @offset: Base write address
+ * @length: Number of bytes to write
+ * @msg: Write data buffer
+ */
+u8 cros_ec_lpc_write_bytes(unsigned int offset, unsigned int length, u8 *msg);
+
+#endif /* __LINUX_MFD_CROS_EC_REG_H */
-- 
cgit v1.2.3


From 8d4a3dc423a2695be51ac864eefb8ba7688b1240 Mon Sep 17 00:00:00 2001
From: Shawn Nematbakhsh <shawnn@chromium.org>
Date: Tue, 16 May 2017 17:46:48 +0200
Subject: platform/chrome: cros_ec_lpc: Add support for mec1322 EC

This adds support for the ChromeOS LPC Microchip Embedded Controller
(mec1322) variant.

mec1322 accesses I/O region [800h, 9ffh] through embedded memory
interface (EMI) rather than LPC.

Signed-off-by: Shawn Nematbakhsh <shawnn@chromium.org>
Signed-off-by: Thierry Escande <thierry.escande@collabora.com>
Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Benson Leung <bleung@chromium.org>
---
 drivers/platform/chrome/Kconfig           |  12 +++
 drivers/platform/chrome/Makefile          |   1 +
 drivers/platform/chrome/cros_ec_lpc.c     |   5 ++
 drivers/platform/chrome/cros_ec_lpc_mec.c | 140 ++++++++++++++++++++++++++++++
 drivers/platform/chrome/cros_ec_lpc_reg.c |  69 +++++++++++++++
 include/linux/mfd/cros_ec_lpc_mec.h       |  90 +++++++++++++++++++
 include/linux/mfd/cros_ec_lpc_reg.h       |  14 +++
 7 files changed, 331 insertions(+)
 create mode 100644 drivers/platform/chrome/cros_ec_lpc_mec.c
 create mode 100644 include/linux/mfd/cros_ec_lpc_mec.h

(limited to 'include')

diff --git a/drivers/platform/chrome/Kconfig b/drivers/platform/chrome/Kconfig
index 76bdae1a93bb..6d80fb5076b6 100644
--- a/drivers/platform/chrome/Kconfig
+++ b/drivers/platform/chrome/Kconfig
@@ -59,6 +59,18 @@ config CROS_EC_LPC
           To compile this driver as a module, choose M here: the
           module will be called cros_ec_lpc.
 
+config CROS_EC_LPC_MEC
+	bool "ChromeOS Embedded Controller LPC Microchip EC (MEC) variant"
+	depends on CROS_EC_LPC
+	default n
+	help
+	  If you say Y here, a variant LPC protocol for the Microchip EC
+	  will be used. Note that this variant is not backward compatible
+	  with non-Microchip ECs.
+
+	  If you have a ChromeOS Embedded Controller Microchip EC variant
+	  choose Y here.
+
 config CROS_EC_PROTO
         bool
         help
diff --git a/drivers/platform/chrome/Makefile b/drivers/platform/chrome/Makefile
index 61182fd8f597..66c345ca35fc 100644
--- a/drivers/platform/chrome/Makefile
+++ b/drivers/platform/chrome/Makefile
@@ -6,6 +6,7 @@ cros_ec_devs-objs			:= cros_ec_dev.o cros_ec_sysfs.o \
 					   cros_ec_debugfs.o
 obj-$(CONFIG_CROS_EC_CHARDEV)		+= cros_ec_devs.o
 cros_ec_lpcs-objs			:= cros_ec_lpc.o cros_ec_lpc_reg.o
+cros_ec_lpcs-$(CONFIG_CROS_EC_LPC_MEC)	+= cros_ec_lpc_mec.o
 obj-$(CONFIG_CROS_EC_LPC)		+= cros_ec_lpcs.o
 obj-$(CONFIG_CROS_EC_PROTO)		+= cros_ec_proto.o
 obj-$(CONFIG_CROS_KBD_LED_BACKLIGHT)	+= cros_kbd_led_backlight.o
diff --git a/drivers/platform/chrome/cros_ec_lpc.c b/drivers/platform/chrome/cros_ec_lpc.c
index 6a782a695eb6..bc2dc6210d7b 100644
--- a/drivers/platform/chrome/cros_ec_lpc.c
+++ b/drivers/platform/chrome/cros_ec_lpc.c
@@ -346,10 +346,13 @@ static int __init cros_ec_lpc_init(void)
 		return -ENODEV;
 	}
 
+	cros_ec_lpc_reg_init();
+
 	/* Register the driver */
 	ret = platform_driver_register(&cros_ec_lpc_driver);
 	if (ret) {
 		pr_err(DRV_NAME ": can't register driver: %d\n", ret);
+		cros_ec_lpc_reg_destroy();
 		return ret;
 	}
 
@@ -358,6 +361,7 @@ static int __init cros_ec_lpc_init(void)
 	if (ret) {
 		pr_err(DRV_NAME ": can't register device: %d\n", ret);
 		platform_driver_unregister(&cros_ec_lpc_driver);
+		cros_ec_lpc_reg_destroy();
 		return ret;
 	}
 
@@ -368,6 +372,7 @@ static void __exit cros_ec_lpc_exit(void)
 {
 	platform_device_unregister(&cros_ec_lpc_device);
 	platform_driver_unregister(&cros_ec_lpc_driver);
+	cros_ec_lpc_reg_destroy();
 }
 
 module_init(cros_ec_lpc_init);
diff --git a/drivers/platform/chrome/cros_ec_lpc_mec.c b/drivers/platform/chrome/cros_ec_lpc_mec.c
new file mode 100644
index 000000000000..2eda2c2fc210
--- /dev/null
+++ b/drivers/platform/chrome/cros_ec_lpc_mec.c
@@ -0,0 +1,140 @@
+/*
+ * cros_ec_lpc_mec - LPC variant I/O for Microchip EC
+ *
+ * Copyright (C) 2016 Google, Inc
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * This driver uses the Chrome OS EC byte-level message-based protocol for
+ * communicating the keyboard state (which keys are pressed) from a keyboard EC
+ * to the AP over some bus (such as i2c, lpc, spi).  The EC does debouncing,
+ * but everything else (including deghosting) is done here.  The main
+ * motivation for this is to keep the EC firmware as simple as possible, since
+ * it cannot be easily upgraded and EC flash/IRAM space is relatively
+ * expensive.
+ */
+
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/mfd/cros_ec_commands.h>
+#include <linux/mfd/cros_ec_lpc_mec.h>
+#include <linux/mutex.h>
+#include <linux/types.h>
+
+/*
+ * This mutex must be held while accessing the EMI unit. We can't rely on the
+ * EC mutex because memmap data may be accessed without it being held.
+ */
+static struct mutex io_mutex;
+
+/*
+ * cros_ec_lpc_mec_emi_write_address
+ *
+ * Initialize EMI read / write at a given address.
+ *
+ * @addr:        Starting read / write address
+ * @access_type: Type of access, typically 32-bit auto-increment
+ */
+static void cros_ec_lpc_mec_emi_write_address(u16 addr,
+			enum cros_ec_lpc_mec_emi_access_mode access_type)
+{
+	/* Address relative to start of EMI range */
+	addr -= MEC_EMI_RANGE_START;
+	outb((addr & 0xfc) | access_type, MEC_EMI_EC_ADDRESS_B0);
+	outb((addr >> 8) & 0x7f, MEC_EMI_EC_ADDRESS_B1);
+}
+
+/*
+ * cros_ec_lpc_io_bytes_mec - Read / write bytes to MEC EMI port
+ *
+ * @io_type: MEC_IO_READ or MEC_IO_WRITE, depending on request
+ * @offset:  Base read / write address
+ * @length:  Number of bytes to read / write
+ * @buf:     Destination / source buffer
+ *
+ * @return 8-bit checksum of all bytes read / written
+ */
+u8 cros_ec_lpc_io_bytes_mec(enum cros_ec_lpc_mec_io_type io_type,
+			    unsigned int offset, unsigned int length,
+			    u8 *buf)
+{
+	int i = 0;
+	int io_addr;
+	u8 sum = 0;
+	enum cros_ec_lpc_mec_emi_access_mode access, new_access;
+
+	/*
+	 * Long access cannot be used on misaligned data since reading B0 loads
+	 * the data register and writing B3 flushes.
+	 */
+	if (offset & 0x3 || length < 4)
+		access = ACCESS_TYPE_BYTE;
+	else
+		access = ACCESS_TYPE_LONG_AUTO_INCREMENT;
+
+	mutex_lock(&io_mutex);
+
+	/* Initialize I/O at desired address */
+	cros_ec_lpc_mec_emi_write_address(offset, access);
+
+	/* Skip bytes in case of misaligned offset */
+	io_addr = MEC_EMI_EC_DATA_B0 + (offset & 0x3);
+	while (i < length) {
+		while (io_addr <= MEC_EMI_EC_DATA_B3) {
+			if (io_type == MEC_IO_READ)
+				buf[i] = inb(io_addr++);
+			else
+				outb(buf[i], io_addr++);
+
+			sum += buf[i++];
+			offset++;
+
+			/* Extra bounds check in case of misaligned length */
+			if (i == length)
+				goto done;
+		}
+
+		/*
+		 * Use long auto-increment access except for misaligned write,
+		 * since writing B3 triggers the flush.
+		 */
+		if (length - i < 4 && io_type == MEC_IO_WRITE)
+			new_access = ACCESS_TYPE_BYTE;
+		else
+			new_access = ACCESS_TYPE_LONG_AUTO_INCREMENT;
+
+		if (new_access != access ||
+		    access != ACCESS_TYPE_LONG_AUTO_INCREMENT) {
+			access = new_access;
+			cros_ec_lpc_mec_emi_write_address(offset, access);
+		}
+
+		/* Access [B0, B3] on each loop pass */
+		io_addr = MEC_EMI_EC_DATA_B0;
+	}
+
+done:
+	mutex_unlock(&io_mutex);
+
+	return sum;
+}
+EXPORT_SYMBOL(cros_ec_lpc_io_bytes_mec);
+
+void cros_ec_lpc_mec_init(void)
+{
+	mutex_init(&io_mutex);
+}
+EXPORT_SYMBOL(cros_ec_lpc_mec_init);
+
+void cros_ec_lpc_mec_destroy(void)
+{
+	mutex_destroy(&io_mutex);
+}
+EXPORT_SYMBOL(cros_ec_lpc_mec_destroy);
diff --git a/drivers/platform/chrome/cros_ec_lpc_reg.c b/drivers/platform/chrome/cros_ec_lpc_reg.c
index 03c97813171e..dcc7a3e30604 100644
--- a/drivers/platform/chrome/cros_ec_lpc_reg.c
+++ b/drivers/platform/chrome/cros_ec_lpc_reg.c
@@ -24,6 +24,7 @@
 #include <linux/io.h>
 #include <linux/mfd/cros_ec.h>
 #include <linux/mfd/cros_ec_commands.h>
+#include <linux/mfd/cros_ec_lpc_mec.h>
 
 static u8 lpc_read_bytes(unsigned int offset, unsigned int length, u8 *dest)
 {
@@ -53,12 +54,80 @@ static u8 lpc_write_bytes(unsigned int offset, unsigned int length, u8 *msg)
 	return sum;
 }
 
+#ifdef CONFIG_CROS_EC_LPC_MEC
+
 u8 cros_ec_lpc_read_bytes(unsigned int offset, unsigned int length, u8 *dest)
 {
+	if (length == 0)
+		return 0;
+
+	/* Access desired range through EMI interface */
+	if (offset >= MEC_EMI_RANGE_START && offset <= MEC_EMI_RANGE_END) {
+		/* Ensure we don't straddle EMI region */
+		if (WARN_ON(offset + length - 1 > MEC_EMI_RANGE_END))
+			return 0;
+
+		return cros_ec_lpc_io_bytes_mec(MEC_IO_READ, offset, length,
+						dest);
+	}
+
+	if (WARN_ON(offset + length > MEC_EMI_RANGE_START &&
+		    offset < MEC_EMI_RANGE_START))
+		return 0;
+
 	return lpc_read_bytes(offset, length, dest);
 }
 
 u8 cros_ec_lpc_write_bytes(unsigned int offset, unsigned int length, u8 *msg)
 {
+	if (length == 0)
+		return 0;
+
+	/* Access desired range through EMI interface */
+	if (offset >= MEC_EMI_RANGE_START && offset <= MEC_EMI_RANGE_END) {
+		/* Ensure we don't straddle EMI region */
+		if (WARN_ON(offset + length - 1 > MEC_EMI_RANGE_END))
+			return 0;
+
+		return cros_ec_lpc_io_bytes_mec(MEC_IO_WRITE, offset, length,
+						msg);
+	}
+
+	if (WARN_ON(offset + length > MEC_EMI_RANGE_START &&
+		    offset < MEC_EMI_RANGE_START))
+		return 0;
+
 	return lpc_write_bytes(offset, length, msg);
 }
+
+void cros_ec_lpc_reg_init(void)
+{
+	cros_ec_lpc_mec_init();
+}
+
+void cros_ec_lpc_reg_destroy(void)
+{
+	cros_ec_lpc_mec_destroy();
+}
+
+#else /* CONFIG_CROS_EC_LPC_MEC */
+
+u8 cros_ec_lpc_read_bytes(unsigned int offset, unsigned int length, u8 *dest)
+{
+	return lpc_read_bytes(offset, length, dest);
+}
+
+u8 cros_ec_lpc_write_bytes(unsigned int offset, unsigned int length, u8 *msg)
+{
+	return lpc_write_bytes(offset, length, msg);
+}
+
+void cros_ec_lpc_reg_init(void)
+{
+}
+
+void cros_ec_lpc_reg_destroy(void)
+{
+}
+
+#endif /* CONFIG_CROS_EC_LPC_MEC */
diff --git a/include/linux/mfd/cros_ec_lpc_mec.h b/include/linux/mfd/cros_ec_lpc_mec.h
new file mode 100644
index 000000000000..176496ddc66c
--- /dev/null
+++ b/include/linux/mfd/cros_ec_lpc_mec.h
@@ -0,0 +1,90 @@
+/*
+ * cros_ec_lpc_mec - LPC variant I/O for Microchip EC
+ *
+ * Copyright (C) 2016 Google, Inc
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * This driver uses the Chrome OS EC byte-level message-based protocol for
+ * communicating the keyboard state (which keys are pressed) from a keyboard EC
+ * to the AP over some bus (such as i2c, lpc, spi).  The EC does debouncing,
+ * but everything else (including deghosting) is done here.  The main
+ * motivation for this is to keep the EC firmware as simple as possible, since
+ * it cannot be easily upgraded and EC flash/IRAM space is relatively
+ * expensive.
+ */
+
+#ifndef __LINUX_MFD_CROS_EC_MEC_H
+#define __LINUX_MFD_CROS_EC_MEC_H
+
+#include <linux/mfd/cros_ec_commands.h>
+
+enum cros_ec_lpc_mec_emi_access_mode {
+	/* 8-bit access */
+	ACCESS_TYPE_BYTE = 0x0,
+	/* 16-bit access */
+	ACCESS_TYPE_WORD = 0x1,
+	/* 32-bit access */
+	ACCESS_TYPE_LONG = 0x2,
+	/*
+	 * 32-bit access, read or write of MEC_EMI_EC_DATA_B3 causes the
+	 * EC data register to be incremented.
+	 */
+	ACCESS_TYPE_LONG_AUTO_INCREMENT = 0x3,
+};
+
+enum cros_ec_lpc_mec_io_type {
+	MEC_IO_READ,
+	MEC_IO_WRITE,
+};
+
+/* Access IO ranges 0x800 thru 0x9ff using EMI interface instead of LPC */
+#define MEC_EMI_RANGE_START EC_HOST_CMD_REGION0
+#define MEC_EMI_RANGE_END   (EC_LPC_ADDR_MEMMAP + EC_MEMMAP_SIZE)
+
+/* EMI registers are relative to base */
+#define MEC_EMI_BASE 0x800
+#define MEC_EMI_HOST_TO_EC (MEC_EMI_BASE + 0)
+#define MEC_EMI_EC_TO_HOST (MEC_EMI_BASE + 1)
+#define MEC_EMI_EC_ADDRESS_B0 (MEC_EMI_BASE + 2)
+#define MEC_EMI_EC_ADDRESS_B1 (MEC_EMI_BASE + 3)
+#define MEC_EMI_EC_DATA_B0 (MEC_EMI_BASE + 4)
+#define MEC_EMI_EC_DATA_B1 (MEC_EMI_BASE + 5)
+#define MEC_EMI_EC_DATA_B2 (MEC_EMI_BASE + 6)
+#define MEC_EMI_EC_DATA_B3 (MEC_EMI_BASE + 7)
+
+/*
+ * cros_ec_lpc_mec_init
+ *
+ * Initialize MEC I/O.
+ */
+void cros_ec_lpc_mec_init(void);
+
+/*
+ * cros_ec_lpc_mec_destroy
+ *
+ * Cleanup MEC I/O.
+ */
+void cros_ec_lpc_mec_destroy(void);
+
+/**
+ * cros_ec_lpc_io_bytes_mec - Read / write bytes to MEC EMI port
+ *
+ * @io_type: MEC_IO_READ or MEC_IO_WRITE, depending on request
+ * @offset:  Base read / write address
+ * @length:  Number of bytes to read / write
+ * @buf:     Destination / source buffer
+ *
+ * @return 8-bit checksum of all bytes read / written
+ */
+u8 cros_ec_lpc_io_bytes_mec(enum cros_ec_lpc_mec_io_type io_type,
+			    unsigned int offset, unsigned int length, u8 *buf);
+
+#endif /* __LINUX_MFD_CROS_EC_MEC_H */
diff --git a/include/linux/mfd/cros_ec_lpc_reg.h b/include/linux/mfd/cros_ec_lpc_reg.h
index 4089bd5c8313..5560bef63c2b 100644
--- a/include/linux/mfd/cros_ec_lpc_reg.h
+++ b/include/linux/mfd/cros_ec_lpc_reg.h
@@ -44,4 +44,18 @@ u8 cros_ec_lpc_read_bytes(unsigned int offset, unsigned int length, u8 *dest);
  */
 u8 cros_ec_lpc_write_bytes(unsigned int offset, unsigned int length, u8 *msg);
 
+/**
+ * cros_ec_lpc_reg_init
+ *
+ * Initialize register I/O.
+ */
+void cros_ec_lpc_reg_init(void);
+
+/**
+ * cros_ec_lpc_reg_destroy
+ *
+ * Cleanup reg I/O.
+ */
+void cros_ec_lpc_reg_destroy(void);
+
 #endif /* __LINUX_MFD_CROS_EC_REG_H */
-- 
cgit v1.2.3


From be3ebebf4377fe924f0419f78fc82cf01a31e692 Mon Sep 17 00:00:00 2001
From: Eric Caruso <ejcaruso@chromium.org>
Date: Tue, 16 May 2017 17:46:48 +0200
Subject: platform/chrome: cros_ec_lightbar - Add lightbar program feature to
 sysfs

Add a program feature so we can upload and run programs for lightbar
sequences. We should be able to use this to shift sequences out of the
EC and save space there.

  $ cat <suitable program bin> > /sys/devices/.../cros_ec/program
  $ echo program > /sys/devices/.../cros_ec/sequence

Signed-off-by: Eric Caruso <ejcaruso@chromium.org>
Signed-off-by: Guenter Roeck <groeck@chromium.org>
Signed-off-by: Enric Balletbo i Serra <enric.balletbo@collabora.com>
Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Benson Leung <bleung@chromium.org>
---
 drivers/platform/chrome/cros_ec_lightbar.c | 69 +++++++++++++++++++++++++++++-
 include/linux/mfd/cros_ec_commands.h       | 12 +++++-
 2 files changed, 79 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/platform/chrome/cros_ec_lightbar.c b/drivers/platform/chrome/cros_ec_lightbar.c
index 8df3d447cacf..26675059707e 100644
--- a/drivers/platform/chrome/cros_ec_lightbar.c
+++ b/drivers/platform/chrome/cros_ec_lightbar.c
@@ -295,7 +295,8 @@ exit:
 
 static char const *seqname[] = {
 	"ERROR", "S5", "S3", "S0", "S5S3", "S3S0",
-	"S0S3", "S3S5", "STOP", "RUN", "PULSE", "TEST", "KONAMI",
+	"S0S3", "S3S5", "STOP", "RUN", "KONAMI",
+	"TAP", "PROGRAM",
 };
 
 static ssize_t sequence_show(struct device *dev,
@@ -390,6 +391,69 @@ exit:
 	return ret;
 }
 
+static ssize_t program_store(struct device *dev, struct device_attribute *attr,
+			     const char *buf, size_t count)
+{
+	int extra_bytes, max_size, ret;
+	struct ec_params_lightbar *param;
+	struct cros_ec_command *msg;
+	struct cros_ec_dev *ec = container_of(dev, struct cros_ec_dev,
+					      class_dev);
+
+	/*
+	 * We might need to reject the program for size reasons. The EC
+	 * enforces a maximum program size, but we also don't want to try
+	 * and send a program that is too big for the protocol. In order
+	 * to ensure the latter, we also need to ensure we have extra bytes
+	 * to represent the rest of the packet.
+	 */
+	extra_bytes = sizeof(*param) - sizeof(param->set_program.data);
+	max_size = min(EC_LB_PROG_LEN, ec->ec_dev->max_request - extra_bytes);
+	if (count > max_size) {
+		dev_err(dev, "Program is %u bytes, too long to send (max: %u)",
+			(unsigned int)count, max_size);
+
+		return -EINVAL;
+	}
+
+	msg = alloc_lightbar_cmd_msg(ec);
+	if (!msg)
+		return -ENOMEM;
+
+	ret = lb_throttle();
+	if (ret)
+		goto exit;
+
+	dev_info(dev, "Copying %zu byte program to EC", count);
+
+	param = (struct ec_params_lightbar *)msg->data;
+	param->cmd = LIGHTBAR_CMD_SET_PROGRAM;
+
+	param->set_program.size = count;
+	memcpy(param->set_program.data, buf, count);
+
+	/*
+	 * We need to set the message size manually or else it will use
+	 * EC_LB_PROG_LEN. This might be too long, and the program
+	 * is unlikely to use all of the space.
+	 */
+	msg->outsize = count + extra_bytes;
+
+	ret = cros_ec_cmd_xfer(ec->ec_dev, msg);
+	if (ret < 0)
+		goto exit;
+	if (msg->result != EC_RES_SUCCESS) {
+		ret = -EINVAL;
+		goto exit;
+	}
+
+	ret = count;
+exit:
+	kfree(msg);
+
+	return ret;
+}
+
 /* Module initialization */
 
 static DEVICE_ATTR_RW(interval_msec);
@@ -397,12 +461,15 @@ static DEVICE_ATTR_RO(version);
 static DEVICE_ATTR_WO(brightness);
 static DEVICE_ATTR_WO(led_rgb);
 static DEVICE_ATTR_RW(sequence);
+static DEVICE_ATTR_WO(program);
+
 static struct attribute *__lb_cmds_attrs[] = {
 	&dev_attr_interval_msec.attr,
 	&dev_attr_version.attr,
 	&dev_attr_brightness.attr,
 	&dev_attr_led_rgb.attr,
 	&dev_attr_sequence.attr,
+	&dev_attr_program.attr,
 	NULL,
 };
 
diff --git a/include/linux/mfd/cros_ec_commands.h b/include/linux/mfd/cros_ec_commands.h
index 1b19e424e1cf..dbea5802e83b 100644
--- a/include/linux/mfd/cros_ec_commands.h
+++ b/include/linux/mfd/cros_ec_commands.h
@@ -1162,6 +1162,13 @@ struct lightbar_params_v1 {
 	struct rgb_s color[8];			/* 0-3 are Google colors */
 } __packed;
 
+/* Lightbar program */
+#define EC_LB_PROG_LEN 192
+struct lightbar_program {
+	uint8_t size;
+	uint8_t data[EC_LB_PROG_LEN];
+};
+
 struct ec_params_lightbar {
 	uint8_t cmd;		      /* Command (see enum lightbar_command) */
 	union {
@@ -1188,6 +1195,7 @@ struct ec_params_lightbar {
 
 		struct lightbar_params_v0 set_params_v0;
 		struct lightbar_params_v1 set_params_v1;
+		struct lightbar_program set_program;
 	};
 } __packed;
 
@@ -1220,7 +1228,8 @@ struct ec_response_lightbar {
 		struct {
 			/* no return params */
 		} off, on, init, set_brightness, seq, reg, set_rgb,
-			demo, set_params_v0, set_params_v1;
+			demo, set_params_v0, set_params_v1,
+			set_program;
 	};
 } __packed;
 
@@ -1244,6 +1253,7 @@ enum lightbar_command {
 	LIGHTBAR_CMD_GET_DEMO = 15,
 	LIGHTBAR_CMD_GET_PARAMS_V1 = 16,
 	LIGHTBAR_CMD_SET_PARAMS_V1 = 17,
+	LIGHTBAR_CMD_SET_PROGRAM = 18,
 	LIGHTBAR_NUM_CMDS
 };
 
-- 
cgit v1.2.3


From 405c84308c4335ee7cb58b9304b77b85e61f7129 Mon Sep 17 00:00:00 2001
From: Eric Caruso <ejcaruso@chromium.org>
Date: Tue, 16 May 2017 17:46:48 +0200
Subject: platform/chrome: cros_ec_lightbar - Control of suspend/resume
 lightbar sequence

Don't let EC control suspend/resume sequence. If the EC controls the
lightbar and sets the sequence when it notices the chipset transitioning
between states, we can't make exceptions for cases where we don't want
to activate the lightbar. Instead, let's move the suspend/resume
notifications into the kernel so we can selectively play the sequences.

Signed-off-by: Eric Caruso <ejcaruso@chromium.org>
Signed-off-by: Guenter Roeck <groeck@chromium.org>
Signed-off-by: Enric Balletbo i Serra <enric.balletbo@collabora.com>
Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Benson Leung <bleung@chromium.org>
---
 drivers/platform/chrome/cros_ec_dev.c      | 37 +++++++++++++
 drivers/platform/chrome/cros_ec_dev.h      |  6 +++
 drivers/platform/chrome/cros_ec_lightbar.c | 85 ++++++++++++++++++++++++++++--
 include/linux/mfd/cros_ec_commands.h       | 11 +++-
 4 files changed, 134 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/platform/chrome/cros_ec_dev.c b/drivers/platform/chrome/cros_ec_dev.c
index 20ce1c23fb5c..7c2622319211 100644
--- a/drivers/platform/chrome/cros_ec_dev.c
+++ b/drivers/platform/chrome/cros_ec_dev.c
@@ -21,6 +21,7 @@
 #include <linux/mfd/core.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
 
@@ -435,6 +436,10 @@ static int ec_device_probe(struct platform_device *pdev)
 	if (cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE))
 		cros_ec_sensors_register(ec);
 
+	/* Take control of the lightbar from the EC. */
+	if (ec_has_lightbar(ec))
+		lb_manual_suspend_ctrl(ec, 1);
+
 	return 0;
 
 failed:
@@ -446,6 +451,10 @@ static int ec_device_remove(struct platform_device *pdev)
 {
 	struct cros_ec_dev *ec = dev_get_drvdata(&pdev->dev);
 
+	/* Let the EC take over the lightbar again. */
+	if (ec_has_lightbar(ec))
+		lb_manual_suspend_ctrl(ec, 0);
+
 	cros_ec_debugfs_remove(ec);
 
 	cdev_del(&ec->cdev);
@@ -459,9 +468,37 @@ static const struct platform_device_id cros_ec_id[] = {
 };
 MODULE_DEVICE_TABLE(platform, cros_ec_id);
 
+static int ec_device_suspend(struct device *dev)
+{
+	struct cros_ec_dev *ec = dev_get_drvdata(dev);
+
+	if (ec_has_lightbar(ec))
+		lb_suspend(ec);
+
+	return 0;
+}
+
+static int ec_device_resume(struct device *dev)
+{
+	struct cros_ec_dev *ec = dev_get_drvdata(dev);
+
+	if (ec_has_lightbar(ec))
+		lb_resume(ec);
+
+	return 0;
+}
+
+static const struct dev_pm_ops cros_ec_dev_pm_ops = {
+#ifdef CONFIG_PM_SLEEP
+	.suspend = ec_device_suspend,
+	.resume = ec_device_resume,
+#endif
+};
+
 static struct platform_driver cros_ec_dev_driver = {
 	.driver = {
 		.name = "cros-ec-ctl",
+		.pm = &cros_ec_dev_pm_ops,
 	},
 	.probe = ec_device_probe,
 	.remove = ec_device_remove,
diff --git a/drivers/platform/chrome/cros_ec_dev.h b/drivers/platform/chrome/cros_ec_dev.h
index bfd2c84c3571..45e9453608c5 100644
--- a/drivers/platform/chrome/cros_ec_dev.h
+++ b/drivers/platform/chrome/cros_ec_dev.h
@@ -43,4 +43,10 @@ struct cros_ec_readmem {
 #define CROS_EC_DEV_IOCXCMD   _IOWR(CROS_EC_DEV_IOC, 0, struct cros_ec_command)
 #define CROS_EC_DEV_IOCRDMEM  _IOWR(CROS_EC_DEV_IOC, 1, struct cros_ec_readmem)
 
+/* Lightbar utilities */
+extern bool ec_has_lightbar(struct cros_ec_dev *ec);
+extern int lb_manual_suspend_ctrl(struct cros_ec_dev *ec, uint8_t enable);
+extern int lb_suspend(struct cros_ec_dev *ec);
+extern int lb_resume(struct cros_ec_dev *ec);
+
 #endif /* _CROS_EC_DEV_H_ */
diff --git a/drivers/platform/chrome/cros_ec_lightbar.c b/drivers/platform/chrome/cros_ec_lightbar.c
index 26675059707e..4df379dc4bb9 100644
--- a/drivers/platform/chrome/cros_ec_lightbar.c
+++ b/drivers/platform/chrome/cros_ec_lightbar.c
@@ -341,6 +341,80 @@ exit:
 	return ret;
 }
 
+static int lb_send_empty_cmd(struct cros_ec_dev *ec, uint8_t cmd)
+{
+	struct ec_params_lightbar *param;
+	struct cros_ec_command *msg;
+	int ret;
+
+	msg = alloc_lightbar_cmd_msg(ec);
+	if (!msg)
+		return -ENOMEM;
+
+	param = (struct ec_params_lightbar *)msg->data;
+	param->cmd = cmd;
+
+	ret = lb_throttle();
+	if (ret)
+		goto error;
+
+	ret = cros_ec_cmd_xfer(ec->ec_dev, msg);
+	if (ret < 0)
+		goto error;
+	if (msg->result != EC_RES_SUCCESS) {
+		ret = -EINVAL;
+		goto error;
+	}
+	ret = 0;
+error:
+	kfree(msg);
+
+	return ret;
+}
+
+int lb_manual_suspend_ctrl(struct cros_ec_dev *ec, uint8_t enable)
+{
+	struct ec_params_lightbar *param;
+	struct cros_ec_command *msg;
+	int ret;
+
+	msg = alloc_lightbar_cmd_msg(ec);
+	if (!msg)
+		return -ENOMEM;
+
+	param = (struct ec_params_lightbar *)msg->data;
+
+	param->cmd = LIGHTBAR_CMD_MANUAL_SUSPEND_CTRL;
+	param->manual_suspend_ctrl.enable = enable;
+
+	ret = lb_throttle();
+	if (ret)
+		goto error;
+
+	ret = cros_ec_cmd_xfer(ec->ec_dev, msg);
+	if (ret < 0)
+		goto error;
+	if (msg->result != EC_RES_SUCCESS) {
+		ret = -EINVAL;
+		goto error;
+	}
+	ret = 0;
+error:
+	kfree(msg);
+
+	return ret;
+}
+
+int lb_suspend(struct cros_ec_dev *ec)
+{
+	return lb_send_empty_cmd(ec, LIGHTBAR_CMD_SUSPEND);
+}
+
+int lb_resume(struct cros_ec_dev *ec)
+{
+	return lb_send_empty_cmd(ec, LIGHTBAR_CMD_RESUME);
+}
+
 static ssize_t sequence_store(struct device *dev, struct device_attribute *attr,
 			      const char *buf, size_t count)
 {
@@ -473,6 +547,11 @@ static struct attribute *__lb_cmds_attrs[] = {
 	NULL,
 };
 
+bool ec_has_lightbar(struct cros_ec_dev *ec)
+{
+	return !!get_lightbar_version(ec, NULL, NULL);
+}
+
 static umode_t cros_ec_lightbar_attrs_are_visible(struct kobject *kobj,
 						  struct attribute *a, int n)
 {
@@ -489,10 +568,10 @@ static umode_t cros_ec_lightbar_attrs_are_visible(struct kobject *kobj,
 		return 0;
 
 	/* Only instantiate this stuff if the EC has a lightbar */
-	if (get_lightbar_version(ec, NULL, NULL))
+	if (ec_has_lightbar(ec))
 		return a->mode;
-	else
-		return 0;
+
+	return 0;
 }
 
 struct attribute_group cros_ec_lightbar_attr_group = {
diff --git a/include/linux/mfd/cros_ec_commands.h b/include/linux/mfd/cros_ec_commands.h
index dbea5802e83b..190c8f4afa02 100644
--- a/include/linux/mfd/cros_ec_commands.h
+++ b/include/linux/mfd/cros_ec_commands.h
@@ -1175,7 +1175,7 @@ struct ec_params_lightbar {
 		struct {
 			/* no args */
 		} dump, off, on, init, get_seq, get_params_v0, get_params_v1,
-			version, get_brightness, get_demo;
+			version, get_brightness, get_demo, suspend, resume;
 
 		struct {
 			uint8_t num;
@@ -1193,6 +1193,10 @@ struct ec_params_lightbar {
 			uint8_t led;
 		} get_rgb;
 
+		struct {
+			uint8_t enable;
+		} manual_suspend_ctrl;
+
 		struct lightbar_params_v0 set_params_v0;
 		struct lightbar_params_v1 set_params_v1;
 		struct lightbar_program set_program;
@@ -1229,7 +1233,7 @@ struct ec_response_lightbar {
 			/* no return params */
 		} off, on, init, set_brightness, seq, reg, set_rgb,
 			demo, set_params_v0, set_params_v1,
-			set_program;
+			set_program, manual_suspend_ctrl, suspend, resume;
 	};
 } __packed;
 
@@ -1254,6 +1258,9 @@ enum lightbar_command {
 	LIGHTBAR_CMD_GET_PARAMS_V1 = 16,
 	LIGHTBAR_CMD_SET_PARAMS_V1 = 17,
 	LIGHTBAR_CMD_SET_PROGRAM = 18,
+	LIGHTBAR_CMD_MANUAL_SUSPEND_CTRL = 19,
+	LIGHTBAR_CMD_SUSPEND = 20,
+	LIGHTBAR_CMD_RESUME = 21,
 	LIGHTBAR_NUM_CMDS
 };
 
-- 
cgit v1.2.3


From 38cb266ad1a24e037220dc563ab46364595b17b6 Mon Sep 17 00:00:00 2001
From: Jonathan Corbet <corbet@lwn.net>
Date: Fri, 23 Jun 2017 14:00:13 -0600
Subject: DRM: Fix an incorrectly formatted table

The "supported input formats" table in dw_hdmi.h was incorrectly formatted,
using "+" signs where "|" needs to be.  That, in turn, causes the PDF build
to fail.

Fixes: def23aa7e982 ("drm: bridge: dw-hdmi: Switch to V4L bus format and encodings")
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/20170623140013.0703107a@lwn.net
---
 include/drm/bridge/dw_hdmi.h | 70 ++++++++++++++++++++++----------------------
 1 file changed, 35 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/include/drm/bridge/dw_hdmi.h b/include/drm/bridge/dw_hdmi.h
index 4c8d4c81a0e8..182f83283e24 100644
--- a/include/drm/bridge/dw_hdmi.h
+++ b/include/drm/bridge/dw_hdmi.h
@@ -22,56 +22,56 @@ struct dw_hdmi;
  * 48bit bus.
  *
  * +----------------------+----------------------------------+------------------------------+
- * + Format Name          + Format Code                      + Encodings                    +
+ * | Format Name          | Format Code                      | Encodings                    |
  * +----------------------+----------------------------------+------------------------------+
- * + RGB 4:4:4 8bit       + ``MEDIA_BUS_FMT_RGB888_1X24``    + ``V4L2_YCBCR_ENC_DEFAULT``   +
+ * | RGB 4:4:4 8bit       | ``MEDIA_BUS_FMT_RGB888_1X24``    | ``V4L2_YCBCR_ENC_DEFAULT``   |
  * +----------------------+----------------------------------+------------------------------+
- * + RGB 4:4:4 10bits     + ``MEDIA_BUS_FMT_RGB101010_1X30`` + ``V4L2_YCBCR_ENC_DEFAULT``   +
+ * | RGB 4:4:4 10bits     | ``MEDIA_BUS_FMT_RGB101010_1X30`` | ``V4L2_YCBCR_ENC_DEFAULT``   |
  * +----------------------+----------------------------------+------------------------------+
- * + RGB 4:4:4 12bits     + ``MEDIA_BUS_FMT_RGB121212_1X36`` + ``V4L2_YCBCR_ENC_DEFAULT``   +
+ * | RGB 4:4:4 12bits     | ``MEDIA_BUS_FMT_RGB121212_1X36`` | ``V4L2_YCBCR_ENC_DEFAULT``   |
  * +----------------------+----------------------------------+------------------------------+
- * + RGB 4:4:4 16bits     + ``MEDIA_BUS_FMT_RGB161616_1X48`` + ``V4L2_YCBCR_ENC_DEFAULT``   +
+ * | RGB 4:4:4 16bits     | ``MEDIA_BUS_FMT_RGB161616_1X48`` | ``V4L2_YCBCR_ENC_DEFAULT``   |
  * +----------------------+----------------------------------+------------------------------+
- * + YCbCr 4:4:4 8bit     + ``MEDIA_BUS_FMT_YUV8_1X24``      + ``V4L2_YCBCR_ENC_601``       +
- * +                      +                                  + or ``V4L2_YCBCR_ENC_709``    +
- * +                      +                                  + or ``V4L2_YCBCR_ENC_XV601``  +
- * +                      +                                  + or ``V4L2_YCBCR_ENC_XV709``  +
+ * | YCbCr 4:4:4 8bit     | ``MEDIA_BUS_FMT_YUV8_1X24``      | ``V4L2_YCBCR_ENC_601``       |
+ * |                      |                                  | or ``V4L2_YCBCR_ENC_709``    |
+ * |                      |                                  | or ``V4L2_YCBCR_ENC_XV601``  |
+ * |                      |                                  | or ``V4L2_YCBCR_ENC_XV709``  |
  * +----------------------+----------------------------------+------------------------------+
- * + YCbCr 4:4:4 10bits   + ``MEDIA_BUS_FMT_YUV10_1X30``     + ``V4L2_YCBCR_ENC_601``       +
- * +                      +                                  + or ``V4L2_YCBCR_ENC_709``    +
- * +                      +                                  + or ``V4L2_YCBCR_ENC_XV601``  +
- * +                      +                                  + or ``V4L2_YCBCR_ENC_XV709``  +
+ * | YCbCr 4:4:4 10bits   | ``MEDIA_BUS_FMT_YUV10_1X30``     | ``V4L2_YCBCR_ENC_601``       |
+ * |                      |                                  | or ``V4L2_YCBCR_ENC_709``    |
+ * |                      |                                  | or ``V4L2_YCBCR_ENC_XV601``  |
+ * |                      |                                  | or ``V4L2_YCBCR_ENC_XV709``  |
  * +----------------------+----------------------------------+------------------------------+
- * + YCbCr 4:4:4 12bits   + ``MEDIA_BUS_FMT_YUV12_1X36``     + ``V4L2_YCBCR_ENC_601``       +
- * +                      +                                  + or ``V4L2_YCBCR_ENC_709``    +
- * +                      +                                  + or ``V4L2_YCBCR_ENC_XV601``  +
- * +                      +                                  + or ``V4L2_YCBCR_ENC_XV709``  +
+ * | YCbCr 4:4:4 12bits   | ``MEDIA_BUS_FMT_YUV12_1X36``     | ``V4L2_YCBCR_ENC_601``       |
+ * |                      |                                  | or ``V4L2_YCBCR_ENC_709``    |
+ * |                      |                                  | or ``V4L2_YCBCR_ENC_XV601``  |
+ * |                      |                                  | or ``V4L2_YCBCR_ENC_XV709``  |
  * +----------------------+----------------------------------+------------------------------+
- * + YCbCr 4:4:4 16bits   + ``MEDIA_BUS_FMT_YUV16_1X48``     + ``V4L2_YCBCR_ENC_601``       +
- * +                      +                                  + or ``V4L2_YCBCR_ENC_709``    +
- * +                      +                                  + or ``V4L2_YCBCR_ENC_XV601``  +
- * +                      +                                  + or ``V4L2_YCBCR_ENC_XV709``  +
+ * | YCbCr 4:4:4 16bits   | ``MEDIA_BUS_FMT_YUV16_1X48``     | ``V4L2_YCBCR_ENC_601``       |
+ * |                      |                                  | or ``V4L2_YCBCR_ENC_709``    |
+ * |                      |                                  | or ``V4L2_YCBCR_ENC_XV601``  |
+ * |                      |                                  | or ``V4L2_YCBCR_ENC_XV709``  |
  * +----------------------+----------------------------------+------------------------------+
- * + YCbCr 4:2:2 8bit     + ``MEDIA_BUS_FMT_UYVY8_1X16``     + ``V4L2_YCBCR_ENC_601``       +
- * +                      +                                  + or ``V4L2_YCBCR_ENC_709``    +
+ * | YCbCr 4:2:2 8bit     | ``MEDIA_BUS_FMT_UYVY8_1X16``     | ``V4L2_YCBCR_ENC_601``       |
+ * |                      |                                  | or ``V4L2_YCBCR_ENC_709``    |
  * +----------------------+----------------------------------+------------------------------+
- * + YCbCr 4:2:2 10bits   + ``MEDIA_BUS_FMT_UYVY10_1X20``    + ``V4L2_YCBCR_ENC_601``       +
- * +                      +                                  + or ``V4L2_YCBCR_ENC_709``    +
+ * | YCbCr 4:2:2 10bits   | ``MEDIA_BUS_FMT_UYVY10_1X20``    | ``V4L2_YCBCR_ENC_601``       |
+ * |                      |                                  | or ``V4L2_YCBCR_ENC_709``    |
  * +----------------------+----------------------------------+------------------------------+
- * + YCbCr 4:2:2 12bits   + ``MEDIA_BUS_FMT_UYVY12_1X24``    + ``V4L2_YCBCR_ENC_601``       +
- * +                      +                                  + or ``V4L2_YCBCR_ENC_709``    +
+ * | YCbCr 4:2:2 12bits   | ``MEDIA_BUS_FMT_UYVY12_1X24``    | ``V4L2_YCBCR_ENC_601``       |
+ * |                      |                                  | or ``V4L2_YCBCR_ENC_709``    |
  * +----------------------+----------------------------------+------------------------------+
- * + YCbCr 4:2:0 8bit     + ``MEDIA_BUS_FMT_UYYVYY8_0_5X24`` + ``V4L2_YCBCR_ENC_601``       +
- * +                      +                                  + or ``V4L2_YCBCR_ENC_709``    +
+ * | YCbCr 4:2:0 8bit     | ``MEDIA_BUS_FMT_UYYVYY8_0_5X24`` | ``V4L2_YCBCR_ENC_601``       |
+ * |                      |                                  | or ``V4L2_YCBCR_ENC_709``    |
  * +----------------------+----------------------------------+------------------------------+
- * + YCbCr 4:2:0 10bits   + ``MEDIA_BUS_FMT_UYYVYY10_0_5X30``+ ``V4L2_YCBCR_ENC_601``       +
- * +                      +                                  + or ``V4L2_YCBCR_ENC_709``    +
+ * | YCbCr 4:2:0 10bits   | ``MEDIA_BUS_FMT_UYYVYY10_0_5X30``| ``V4L2_YCBCR_ENC_601``       |
+ * |                      |                                  | or ``V4L2_YCBCR_ENC_709``    |
  * +----------------------+----------------------------------+------------------------------+
- * + YCbCr 4:2:0 12bits   + ``MEDIA_BUS_FMT_UYYVYY12_0_5X36``+ ``V4L2_YCBCR_ENC_601``       +
- * +                      +                                  + or ``V4L2_YCBCR_ENC_709``    +
+ * | YCbCr 4:2:0 12bits   | ``MEDIA_BUS_FMT_UYYVYY12_0_5X36``| ``V4L2_YCBCR_ENC_601``       |
+ * |                      |                                  | or ``V4L2_YCBCR_ENC_709``    |
  * +----------------------+----------------------------------+------------------------------+
- * + YCbCr 4:2:0 16bits   + ``MEDIA_BUS_FMT_UYYVYY16_0_5X48``+ ``V4L2_YCBCR_ENC_601``       +
- * +                      +                                  + or ``V4L2_YCBCR_ENC_709``    +
+ * | YCbCr 4:2:0 16bits   | ``MEDIA_BUS_FMT_UYYVYY16_0_5X48``| ``V4L2_YCBCR_ENC_601``       |
+ * |                      |                                  | or ``V4L2_YCBCR_ENC_709``    |
  * +----------------------+----------------------------------+------------------------------+
  */
 
-- 
cgit v1.2.3


From 29d99b966d60029a11d08b9b004cd84b21ce0d67 Mon Sep 17 00:00:00 2001
From: Shawn Nematbakhsh <shawnn@chromium.org>
Date: Tue, 14 Feb 2017 20:58:02 +0100
Subject: cros_ec: Don't signal wake event for non-wake host events

The subset of wake-enabled host events is defined by the EC, but the EC
may still send non-wake host events if we're in the process of
suspending. Get the mask of wake-enabled host events from the EC and
filter out non-wake events to prevent spurious aborted suspend
attempts.

Signed-off-by: Shawn Nematbakhsh <shawnn@chromium.org>
Signed-off-by: Thierry Escande <thierry.escande@collabora.com>
Acked-for-MFD-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Benson Leung <bleung@chromium.org>
---
 drivers/mfd/cros_ec.c                   | 13 ++++--
 drivers/platform/chrome/cros_ec_lpc.c   |  3 +-
 drivers/platform/chrome/cros_ec_proto.c | 76 ++++++++++++++++++++++++++++++---
 include/linux/mfd/cros_ec.h             |  5 ++-
 4 files changed, 87 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/cros_ec.c b/drivers/mfd/cros_ec.c
index d4a407e466b5..fc2569f3e7c9 100644
--- a/drivers/mfd/cros_ec.c
+++ b/drivers/mfd/cros_ec.c
@@ -54,12 +54,19 @@ static const struct mfd_cell ec_pd_cell = {
 static irqreturn_t ec_irq_thread(int irq, void *data)
 {
 	struct cros_ec_device *ec_dev = data;
+	bool wake_event = true;
 	int ret;
 
-	if (device_may_wakeup(ec_dev->dev))
+	ret = cros_ec_get_next_event(ec_dev, &wake_event);
+
+	/*
+	 * Signal only if wake host events or any interrupt if
+	 * cros_ec_get_next_event() returned an error (default value for
+	 * wake_event is true)
+	 */
+	if (wake_event && device_may_wakeup(ec_dev->dev))
 		pm_wakeup_event(ec_dev->dev, 0);
 
-	ret = cros_ec_get_next_event(ec_dev);
 	if (ret > 0)
 		blocking_notifier_call_chain(&ec_dev->event_notifier,
 					     0, ec_dev);
@@ -221,7 +228,7 @@ EXPORT_SYMBOL(cros_ec_suspend);
 
 static void cros_ec_drain_events(struct cros_ec_device *ec_dev)
 {
-	while (cros_ec_get_next_event(ec_dev) > 0)
+	while (cros_ec_get_next_event(ec_dev, NULL) > 0)
 		blocking_notifier_call_chain(&ec_dev->event_notifier,
 					     1, ec_dev);
 }
diff --git a/drivers/platform/chrome/cros_ec_lpc.c b/drivers/platform/chrome/cros_ec_lpc.c
index eeb187e558ce..2b6436d1b6a4 100644
--- a/drivers/platform/chrome/cros_ec_lpc.c
+++ b/drivers/platform/chrome/cros_ec_lpc.c
@@ -231,7 +231,8 @@ static void cros_ec_lpc_acpi_notify(acpi_handle device, u32 value, void *data)
 {
 	struct cros_ec_device *ec_dev = data;
 
-	if (ec_dev->mkbp_event_supported && cros_ec_get_next_event(ec_dev) > 0)
+	if (ec_dev->mkbp_event_supported &&
+	    cros_ec_get_next_event(ec_dev, NULL) > 0)
 		blocking_notifier_call_chain(&ec_dev->event_notifier, 0,
 					     ec_dev);
 }
diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c
index d6942a67a182..8dfa7fcb1248 100644
--- a/drivers/platform/chrome/cros_ec_proto.c
+++ b/drivers/platform/chrome/cros_ec_proto.c
@@ -150,6 +150,40 @@ int cros_ec_check_result(struct cros_ec_device *ec_dev,
 }
 EXPORT_SYMBOL(cros_ec_check_result);
 
+/*
+ * cros_ec_get_host_event_wake_mask
+ *
+ * Get the mask of host events that cause wake from suspend.
+ *
+ * @ec_dev: EC device to call
+ * @msg: message structure to use
+ * @mask: result when function returns >=0.
+ *
+ * LOCKING:
+ * the caller has ec_dev->lock mutex, or the caller knows there is
+ * no other command in progress.
+ */
+static int cros_ec_get_host_event_wake_mask(struct cros_ec_device *ec_dev,
+					    struct cros_ec_command *msg,
+					    uint32_t *mask)
+{
+	struct ec_response_host_event_mask *r;
+	int ret;
+
+	msg->command = EC_CMD_HOST_EVENT_GET_WAKE_MASK;
+	msg->version = 0;
+	msg->outsize = 0;
+	msg->insize = sizeof(*r);
+
+	ret = send_command(ec_dev, msg);
+	if (ret > 0) {
+		r = (struct ec_response_host_event_mask *)msg->data;
+		*mask = r->mask;
+	}
+
+	return ret;
+}
+
 static int cros_ec_host_command_proto_query(struct cros_ec_device *ec_dev,
 					    int devidx,
 					    struct cros_ec_command *msg)
@@ -387,6 +421,15 @@ int cros_ec_query_all(struct cros_ec_device *ec_dev)
 	else
 		ec_dev->mkbp_event_supported = 1;
 
+	/*
+	 * Get host event wake mask, assume all events are wake events
+	 * if unavailable.
+	 */
+	ret = cros_ec_get_host_event_wake_mask(ec_dev, proto_msg,
+					       &ec_dev->host_event_wake_mask);
+	if (ret < 0)
+		ec_dev->host_event_wake_mask = U32_MAX;
+
 	ret = 0;
 
 exit:
@@ -504,12 +547,35 @@ static int get_keyboard_state_event(struct cros_ec_device *ec_dev)
 	return ec_dev->event_size;
 }
 
-int cros_ec_get_next_event(struct cros_ec_device *ec_dev)
+int cros_ec_get_next_event(struct cros_ec_device *ec_dev, bool *wake_event)
 {
-	if (ec_dev->mkbp_event_supported)
-		return get_next_event(ec_dev);
-	else
-		return get_keyboard_state_event(ec_dev);
+	u32 host_event;
+	int ret;
+
+	if (!ec_dev->mkbp_event_supported) {
+		ret = get_keyboard_state_event(ec_dev);
+		if (ret < 0)
+			return ret;
+
+		if (wake_event)
+			*wake_event = true;
+
+		return ret;
+	}
+
+	ret = get_next_event(ec_dev);
+	if (ret < 0)
+		return ret;
+
+	if (wake_event) {
+		host_event = cros_ec_get_host_event(ec_dev);
+
+		/* Consider non-host_event as wake event */
+		*wake_event = !host_event ||
+			      !!(host_event & ec_dev->host_event_wake_mask);
+	}
+
+	return ret;
 }
 EXPORT_SYMBOL(cros_ec_get_next_event);
 
diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h
index 3b16c9009749..4e887ba22635 100644
--- a/include/linux/mfd/cros_ec.h
+++ b/include/linux/mfd/cros_ec.h
@@ -149,6 +149,7 @@ struct cros_ec_device {
 
 	struct ec_response_get_next_event event_data;
 	int event_size;
+	u32 host_event_wake_mask;
 };
 
 /**
@@ -299,10 +300,12 @@ int cros_ec_query_all(struct cros_ec_device *ec_dev);
  * cros_ec_get_next_event -  Fetch next event from the ChromeOS EC
  *
  * @ec_dev: Device to fetch event from
+ * @wake_event: Pointer to a bool set to true upon return if the event might be
+ *              treated as a wake event. Ignored if null.
  *
  * Returns: 0 on success, Linux error number on failure
  */
-int cros_ec_get_next_event(struct cros_ec_device *ec_dev);
+int cros_ec_get_next_event(struct cros_ec_device *ec_dev, bool *wake_event);
 
 /**
  * cros_ec_get_host_event - Return a mask of event set by the EC.
-- 
cgit v1.2.3


From a80a32341fbabd4276165a9ce4fa4c80168c0bef Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 23 Jun 2017 17:17:35 -0400
Subject: svcrdma: Remove svc_rdma_marshal.c

svc_rdma_marshal.c has one remaining exported function --
svc_rdma_xdr_decode_req -- and it has a single call site. Take
the same approach as the sendto path, and move this function
into the source file where it is called.

This is a refactoring change only.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 include/linux/sunrpc/svc_rdma.h         |   3 -
 net/sunrpc/xprtrdma/Makefile            |   4 +-
 net/sunrpc/xprtrdma/svc_rdma_marshal.c  | 168 --------------------------------
 net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 126 ++++++++++++++++++++++++
 4 files changed, 128 insertions(+), 173 deletions(-)
 delete mode 100644 net/sunrpc/xprtrdma/svc_rdma_marshal.c

(limited to 'include')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index f3787d800ba4..3ca991657889 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -185,9 +185,6 @@ extern int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt,
 				    __be32 *rdma_resp,
 				    struct xdr_buf *rcvbuf);
 
-/* svc_rdma_marshal.c */
-extern int svc_rdma_xdr_decode_req(struct xdr_buf *);
-
 /* svc_rdma_recvfrom.c */
 extern int svc_rdma_recvfrom(struct svc_rqst *);
 extern int rdma_read_chunk_lcl(struct svcxprt_rdma *, struct svc_rqst *,
diff --git a/net/sunrpc/xprtrdma/Makefile b/net/sunrpc/xprtrdma/Makefile
index c1ae8142ab73..b8213ddce2f2 100644
--- a/net/sunrpc/xprtrdma/Makefile
+++ b/net/sunrpc/xprtrdma/Makefile
@@ -3,6 +3,6 @@ obj-$(CONFIG_SUNRPC_XPRT_RDMA) += rpcrdma.o
 rpcrdma-y := transport.o rpc_rdma.o verbs.o \
 	fmr_ops.o frwr_ops.o \
 	svc_rdma.o svc_rdma_backchannel.o svc_rdma_transport.o \
-	svc_rdma_marshal.o svc_rdma_sendto.o svc_rdma_recvfrom.o \
-	svc_rdma_rw.o module.o
+	svc_rdma_sendto.o svc_rdma_recvfrom.o svc_rdma_rw.o \
+	module.o
 rpcrdma-$(CONFIG_SUNRPC_BACKCHANNEL) += backchannel.o
diff --git a/net/sunrpc/xprtrdma/svc_rdma_marshal.c b/net/sunrpc/xprtrdma/svc_rdma_marshal.c
deleted file mode 100644
index bdcf7d85a3dc..000000000000
--- a/net/sunrpc/xprtrdma/svc_rdma_marshal.c
+++ /dev/null
@@ -1,168 +0,0 @@
-/*
- * Copyright (c) 2016 Oracle. All rights reserved.
- * Copyright (c) 2005-2006 Network Appliance, Inc. All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the BSD-type
- * license below:
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- *      Redistributions of source code must retain the above copyright
- *      notice, this list of conditions and the following disclaimer.
- *
- *      Redistributions in binary form must reproduce the above
- *      copyright notice, this list of conditions and the following
- *      disclaimer in the documentation and/or other materials provided
- *      with the distribution.
- *
- *      Neither the name of the Network Appliance, Inc. nor the names of
- *      its contributors may be used to endorse or promote products
- *      derived from this software without specific prior written
- *      permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * Author: Tom Tucker <tom@opengridcomputing.com>
- */
-
-#include <linux/sunrpc/xdr.h>
-#include <linux/sunrpc/debug.h>
-#include <asm/unaligned.h>
-#include <linux/sunrpc/rpc_rdma.h>
-#include <linux/sunrpc/svc_rdma.h>
-
-#define RPCDBG_FACILITY	RPCDBG_SVCXPRT
-
-static __be32 *xdr_check_read_list(__be32 *p, __be32 *end)
-{
-	__be32 *next;
-
-	while (*p++ != xdr_zero) {
-		next = p + rpcrdma_readchunk_maxsz - 1;
-		if (next > end)
-			return NULL;
-		p = next;
-	}
-	return p;
-}
-
-static __be32 *xdr_check_write_list(__be32 *p, __be32 *end)
-{
-	__be32 *next;
-
-	while (*p++ != xdr_zero) {
-		next = p + 1 + be32_to_cpup(p) * rpcrdma_segment_maxsz;
-		if (next > end)
-			return NULL;
-		p = next;
-	}
-	return p;
-}
-
-static __be32 *xdr_check_reply_chunk(__be32 *p, __be32 *end)
-{
-	__be32 *next;
-
-	if (*p++ != xdr_zero) {
-		next = p + 1 + be32_to_cpup(p) * rpcrdma_segment_maxsz;
-		if (next > end)
-			return NULL;
-		p = next;
-	}
-	return p;
-}
-
-/**
- * svc_rdma_xdr_decode_req - Parse incoming RPC-over-RDMA header
- * @rq_arg: Receive buffer
- *
- * On entry, xdr->head[0].iov_base points to first byte in the
- * RPC-over-RDMA header.
- *
- * On successful exit, head[0] points to first byte past the
- * RPC-over-RDMA header. For RDMA_MSG, this is the RPC message.
- * The length of the RPC-over-RDMA header is returned.
- */
-int svc_rdma_xdr_decode_req(struct xdr_buf *rq_arg)
-{
-	__be32 *p, *end, *rdma_argp;
-	unsigned int hdr_len;
-
-	/* Verify that there's enough bytes for header + something */
-	if (rq_arg->len <= RPCRDMA_HDRLEN_ERR)
-		goto out_short;
-
-	rdma_argp = rq_arg->head[0].iov_base;
-	if (*(rdma_argp + 1) != rpcrdma_version)
-		goto out_version;
-
-	switch (*(rdma_argp + 3)) {
-	case rdma_msg:
-	case rdma_nomsg:
-		break;
-
-	case rdma_done:
-		goto out_drop;
-
-	case rdma_error:
-		goto out_drop;
-
-	default:
-		goto out_proc;
-	}
-
-	end = (__be32 *)((unsigned long)rdma_argp + rq_arg->len);
-	p = xdr_check_read_list(rdma_argp + 4, end);
-	if (!p)
-		goto out_inval;
-	p = xdr_check_write_list(p, end);
-	if (!p)
-		goto out_inval;
-	p = xdr_check_reply_chunk(p, end);
-	if (!p)
-		goto out_inval;
-	if (p > end)
-		goto out_inval;
-
-	rq_arg->head[0].iov_base = p;
-	hdr_len = (unsigned long)p - (unsigned long)rdma_argp;
-	rq_arg->head[0].iov_len -= hdr_len;
-	return hdr_len;
-
-out_short:
-	dprintk("svcrdma: header too short = %d\n", rq_arg->len);
-	return -EINVAL;
-
-out_version:
-	dprintk("svcrdma: bad xprt version: %u\n",
-		be32_to_cpup(rdma_argp + 1));
-	return -EPROTONOSUPPORT;
-
-out_drop:
-	dprintk("svcrdma: dropping RDMA_DONE/ERROR message\n");
-	return 0;
-
-out_proc:
-	dprintk("svcrdma: bad rdma procedure (%u)\n",
-		be32_to_cpup(rdma_argp + 3));
-	return -EINVAL;
-
-out_inval:
-	dprintk("svcrdma: failed to parse transport header\n");
-	return -EINVAL;
-}
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 27a99bf5b1a6..55ad335bbef1 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -1,4 +1,5 @@
 /*
+ * Copyright (c) 2016, 2017 Oracle. All rights reserved.
  * Copyright (c) 2014 Open Grid Computing, Inc. All rights reserved.
  * Copyright (c) 2005-2006 Network Appliance, Inc. All rights reserved.
  *
@@ -40,6 +41,7 @@
  * Author: Tom Tucker <tom@opengridcomputing.com>
  */
 
+#include <linux/sunrpc/xdr.h>
 #include <linux/sunrpc/debug.h>
 #include <linux/sunrpc/rpc_rdma.h>
 #include <linux/spinlock.h>
@@ -115,6 +117,130 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp,
 	rqstp->rq_arg.tail[0].iov_len = 0;
 }
 
+static __be32 *xdr_check_read_list(__be32 *p, __be32 *end)
+{
+	__be32 *next;
+
+	while (*p++ != xdr_zero) {
+		next = p + rpcrdma_readchunk_maxsz - 1;
+		if (next > end)
+			return NULL;
+		p = next;
+	}
+	return p;
+}
+
+static __be32 *xdr_check_write_list(__be32 *p, __be32 *end)
+{
+	__be32 *next;
+
+	while (*p++ != xdr_zero) {
+		next = p + 1 + be32_to_cpup(p) * rpcrdma_segment_maxsz;
+		if (next > end)
+			return NULL;
+		p = next;
+	}
+	return p;
+}
+
+static __be32 *xdr_check_reply_chunk(__be32 *p, __be32 *end)
+{
+	__be32 *next;
+
+	if (*p++ != xdr_zero) {
+		next = p + 1 + be32_to_cpup(p) * rpcrdma_segment_maxsz;
+		if (next > end)
+			return NULL;
+		p = next;
+	}
+	return p;
+}
+
+/* On entry, xdr->head[0].iov_base points to first byte in the
+ * RPC-over-RDMA header.
+ *
+ * On successful exit, head[0] points to first byte past the
+ * RPC-over-RDMA header. For RDMA_MSG, this is the RPC message.
+ * The length of the RPC-over-RDMA header is returned.
+ *
+ * Assumptions:
+ * - The transport header is entirely contained in the head iovec.
+ */
+static int svc_rdma_xdr_decode_req(struct xdr_buf *rq_arg)
+{
+	__be32 *p, *end, *rdma_argp;
+	unsigned int hdr_len;
+	char *proc;
+
+	/* Verify that there's enough bytes for header + something */
+	if (rq_arg->len <= RPCRDMA_HDRLEN_ERR)
+		goto out_short;
+
+	rdma_argp = rq_arg->head[0].iov_base;
+	if (*(rdma_argp + 1) != rpcrdma_version)
+		goto out_version;
+
+	switch (*(rdma_argp + 3)) {
+	case rdma_msg:
+		proc = "RDMA_MSG";
+		break;
+	case rdma_nomsg:
+		proc = "RDMA_NOMSG";
+		break;
+
+	case rdma_done:
+		goto out_drop;
+
+	case rdma_error:
+		goto out_drop;
+
+	default:
+		goto out_proc;
+	}
+
+	end = (__be32 *)((unsigned long)rdma_argp + rq_arg->len);
+	p = xdr_check_read_list(rdma_argp + 4, end);
+	if (!p)
+		goto out_inval;
+	p = xdr_check_write_list(p, end);
+	if (!p)
+		goto out_inval;
+	p = xdr_check_reply_chunk(p, end);
+	if (!p)
+		goto out_inval;
+	if (p > end)
+		goto out_inval;
+
+	rq_arg->head[0].iov_base = p;
+	hdr_len = (unsigned long)p - (unsigned long)rdma_argp;
+	rq_arg->head[0].iov_len -= hdr_len;
+	dprintk("svcrdma: received %s request for XID 0x%08x, hdr_len=%u\n",
+		proc, be32_to_cpup(rdma_argp), hdr_len);
+	return hdr_len;
+
+out_short:
+	dprintk("svcrdma: header too short = %d\n", rq_arg->len);
+	return -EINVAL;
+
+out_version:
+	dprintk("svcrdma: bad xprt version: %u\n",
+		be32_to_cpup(rdma_argp + 1));
+	return -EPROTONOSUPPORT;
+
+out_drop:
+	dprintk("svcrdma: dropping RDMA_DONE/ERROR message\n");
+	return 0;
+
+out_proc:
+	dprintk("svcrdma: bad rdma procedure (%u)\n",
+		be32_to_cpup(rdma_argp + 3));
+	return -EINVAL;
+
+out_inval:
+	dprintk("svcrdma: failed to parse transport header\n");
+	return -EINVAL;
+}
+
 /* Issue an RDMA_READ using the local lkey to map the data sink */
 int rdma_read_chunk_lcl(struct svcxprt_rdma *xprt,
 			struct svc_rqst *rqstp,
-- 
cgit v1.2.3


From 5d6dee80a1e94cc284d03e06d930e60e8d3ecf7d Mon Sep 17 00:00:00 2001
From: Alex Williamson <alex.williamson@redhat.com>
Date: Wed, 28 Jun 2017 13:50:05 -0600
Subject: vfio: New external user group/file match

At the point where the kvm-vfio pseudo device wants to release its
vfio group reference, we can't always acquire a new reference to make
that happen.  The group can be in a state where we wouldn't allow a
new reference to be added.  This new helper function allows a caller
to match a file to a group to facilitate this.  Given a file and
group, report if they match.  Thus the caller needs to already have a
group reference to match to the file.  This allows the deletion of a
group without acquiring a new reference.

Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Tested-by: Eric Auger <eric.auger@redhat.com>
Cc: stable@vger.kernel.org
---
 drivers/vfio/vfio.c  |  9 +++++++++
 include/linux/vfio.h |  2 ++
 virt/kvm/vfio.c      | 27 +++++++++++++++++++--------
 3 files changed, 30 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 54dd2fbf83d9..7597a377eb4e 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -1776,6 +1776,15 @@ void vfio_group_put_external_user(struct vfio_group *group)
 }
 EXPORT_SYMBOL_GPL(vfio_group_put_external_user);
 
+bool vfio_external_group_match_file(struct vfio_group *test_group,
+				    struct file *filep)
+{
+	struct vfio_group *group = filep->private_data;
+
+	return (filep->f_op == &vfio_group_fops) && (group == test_group);
+}
+EXPORT_SYMBOL_GPL(vfio_external_group_match_file);
+
 int vfio_external_user_iommu_id(struct vfio_group *group)
 {
 	return iommu_group_id(group->iommu_group);
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index edf9b2cad277..9b34d0af5d27 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -97,6 +97,8 @@ extern void vfio_unregister_iommu_driver(
  */
 extern struct vfio_group *vfio_group_get_external_user(struct file *filep);
 extern void vfio_group_put_external_user(struct vfio_group *group);
+extern bool vfio_external_group_match_file(struct vfio_group *group,
+					   struct file *filep);
 extern int vfio_external_user_iommu_id(struct vfio_group *group);
 extern long vfio_external_check_extension(struct vfio_group *group,
 					  unsigned long arg);
diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
index 6e002d0f3191..d99850c462a1 100644
--- a/virt/kvm/vfio.c
+++ b/virt/kvm/vfio.c
@@ -51,6 +51,22 @@ static struct vfio_group *kvm_vfio_group_get_external_user(struct file *filep)
 	return vfio_group;
 }
 
+static bool kvm_vfio_external_group_match_file(struct vfio_group *group,
+					       struct file *filep)
+{
+	bool ret, (*fn)(struct vfio_group *, struct file *);
+
+	fn = symbol_get(vfio_external_group_match_file);
+	if (!fn)
+		return false;
+
+	ret = fn(group, filep);
+
+	symbol_put(vfio_external_group_match_file);
+
+	return ret;
+}
+
 static void kvm_vfio_group_put_external_user(struct vfio_group *vfio_group)
 {
 	void (*fn)(struct vfio_group *);
@@ -231,18 +247,13 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
 		if (!f.file)
 			return -EBADF;
 
-		vfio_group = kvm_vfio_group_get_external_user(f.file);
-		fdput(f);
-
-		if (IS_ERR(vfio_group))
-			return PTR_ERR(vfio_group);
-
 		ret = -ENOENT;
 
 		mutex_lock(&kv->lock);
 
 		list_for_each_entry(kvg, &kv->group_list, node) {
-			if (kvg->vfio_group != vfio_group)
+			if (!kvm_vfio_external_group_match_file(kvg->vfio_group,
+								f.file))
 				continue;
 
 			list_del(&kvg->node);
@@ -260,7 +271,7 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
 
 		mutex_unlock(&kv->lock);
 
-		kvm_vfio_group_put_external_user(vfio_group);
+		fdput(f);
 
 		kvm_vfio_update_coherency(dev);
 
-- 
cgit v1.2.3


From 3859a271a003aba01e45b85c9d8b355eb7bf25f9 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 28 Oct 2016 01:22:25 -0700
Subject: randstruct: Mark various structs for randomization

This marks many critical kernel structures for randomization. These are
structures that have been targeted in the past in security exploits, or
contain functions pointers, pointers to function pointer tables, lists,
workqueues, ref-counters, credentials, permissions, or are otherwise
sensitive. This initial list was extracted from Brad Spengler/PaX Team's
code in the last public patch of grsecurity/PaX based on my understanding
of the code. Changes or omissions from the original code are mine and
don't reflect the original grsecurity/PaX code.

Left out of this list is task_struct, which requires special handling
and will be covered in a subsequent patch.

Signed-off-by: Kees Cook <keescook@chromium.org>
---
 arch/x86/include/asm/processor.h |  2 +-
 fs/mount.h                       |  4 ++--
 fs/namei.c                       |  2 +-
 fs/proc/internal.h               |  6 +++---
 include/linux/binfmts.h          |  4 ++--
 include/linux/cdev.h             |  2 +-
 include/linux/cred.h             |  4 ++--
 include/linux/dcache.h           |  2 +-
 include/linux/fs.h               | 17 +++++++++--------
 include/linux/fs_struct.h        |  2 +-
 include/linux/ipc.h              |  2 +-
 include/linux/ipc_namespace.h    |  2 +-
 include/linux/key-type.h         |  4 ++--
 include/linux/kmod.h             |  2 +-
 include/linux/kobject.h          |  2 +-
 include/linux/lsm_hooks.h        |  4 ++--
 include/linux/mm_types.h         |  4 ++--
 include/linux/module.h           |  4 ++--
 include/linux/mount.h            |  2 +-
 include/linux/msg.h              |  2 +-
 include/linux/path.h             |  2 +-
 include/linux/pid_namespace.h    |  2 +-
 include/linux/proc_ns.h          |  2 +-
 include/linux/sched.h            |  2 +-
 include/linux/sched/signal.h     |  2 +-
 include/linux/sem.h              |  2 +-
 include/linux/shm.h              |  2 +-
 include/linux/sysctl.h           |  2 +-
 include/linux/tty.h              |  2 +-
 include/linux/tty_driver.h       |  4 ++--
 include/linux/user_namespace.h   |  2 +-
 include/linux/utsname.h          |  2 +-
 include/net/af_unix.h            |  2 +-
 include/net/neighbour.h          |  2 +-
 include/net/net_namespace.h      |  2 +-
 include/net/sock.h               |  2 +-
 kernel/futex.c                   |  4 ++--
 security/keys/internal.h         |  2 +-
 38 files changed, 57 insertions(+), 56 deletions(-)

(limited to 'include')

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 3cada998a402..e2335edb9fc5 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -129,7 +129,7 @@ struct cpuinfo_x86 {
 	/* Index into per_cpu list: */
 	u16			cpu_index;
 	u32			microcode;
-};
+} __randomize_layout;
 
 struct cpuid_regs {
 	u32 eax, ebx, ecx, edx;
diff --git a/fs/mount.h b/fs/mount.h
index bf1fda6eed8f..e406b286fba1 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -16,7 +16,7 @@ struct mnt_namespace {
 	u64 event;
 	unsigned int		mounts; /* # of mounts in the namespace */
 	unsigned int		pending_mounts;
-};
+} __randomize_layout;
 
 struct mnt_pcp {
 	int mnt_count;
@@ -68,7 +68,7 @@ struct mount {
 	struct hlist_head mnt_pins;
 	struct fs_pin mnt_umount;
 	struct dentry *mnt_ex_mountpoint;
-};
+} __randomize_layout;
 
 #define MNT_NS_INTERNAL ERR_PTR(-EINVAL) /* distinct from any mnt_namespace */
 
diff --git a/fs/namei.c b/fs/namei.c
index 6571a5f5112e..1764620ac383 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -524,7 +524,7 @@ struct nameidata {
 	struct inode	*link_inode;
 	unsigned	root_seq;
 	int		dfd;
-};
+} __randomize_layout;
 
 static void set_nameidata(struct nameidata *p, int dfd, struct filename *name)
 {
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index c5ae09b6c726..07b16318223f 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -51,7 +51,7 @@ struct proc_dir_entry {
 	spinlock_t pde_unload_lock; /* proc_fops checks and pde_users bumps */
 	u8 namelen;
 	char name[];
-};
+} __randomize_layout;
 
 union proc_op {
 	int (*proc_get_link)(struct dentry *, struct path *);
@@ -70,7 +70,7 @@ struct proc_inode {
 	struct list_head sysctl_inodes;
 	const struct proc_ns_operations *ns_ops;
 	struct inode vfs_inode;
-};
+} __randomize_layout;
 
 /*
  * General functions
@@ -279,7 +279,7 @@ struct proc_maps_private {
 #ifdef CONFIG_NUMA
 	struct mempolicy *task_mempolicy;
 #endif
-};
+} __randomize_layout;
 
 struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode);
 
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index 05488da3aee9..3ae9013eeaaa 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -46,7 +46,7 @@ struct linux_binprm {
 	unsigned interp_flags;
 	unsigned interp_data;
 	unsigned long loader, exec;
-};
+} __randomize_layout;
 
 #define BINPRM_FLAGS_ENFORCE_NONDUMP_BIT 0
 #define BINPRM_FLAGS_ENFORCE_NONDUMP (1 << BINPRM_FLAGS_ENFORCE_NONDUMP_BIT)
@@ -81,7 +81,7 @@ struct linux_binfmt {
 	int (*load_shlib)(struct file *);
 	int (*core_dump)(struct coredump_params *cprm);
 	unsigned long min_coredump;	/* minimal dump size */
-};
+} __randomize_layout;
 
 extern void __register_binfmt(struct linux_binfmt *fmt, int insert);
 
diff --git a/include/linux/cdev.h b/include/linux/cdev.h
index 408bc09ce497..cb28eb21e3ca 100644
--- a/include/linux/cdev.h
+++ b/include/linux/cdev.h
@@ -17,7 +17,7 @@ struct cdev {
 	struct list_head list;
 	dev_t dev;
 	unsigned int count;
-};
+} __randomize_layout;
 
 void cdev_init(struct cdev *, const struct file_operations *);
 
diff --git a/include/linux/cred.h b/include/linux/cred.h
index b03e7d049a64..82c8a9e1aabb 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -31,7 +31,7 @@ struct group_info {
 	atomic_t	usage;
 	int		ngroups;
 	kgid_t		gid[0];
-};
+} __randomize_layout;
 
 /**
  * get_group_info - Get a reference to a group info structure
@@ -145,7 +145,7 @@ struct cred {
 	struct user_namespace *user_ns; /* user_ns the caps and keyrings are relative to. */
 	struct group_info *group_info;	/* supplementary groups for euid/fsgid */
 	struct rcu_head	rcu;		/* RCU deletion hook */
-};
+} __randomize_layout;
 
 extern void __put_cred(struct cred *);
 extern void exit_creds(struct task_struct *);
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index d2e38dc6172c..7eb262e13d3c 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -113,7 +113,7 @@ struct dentry {
 		struct hlist_bl_node d_in_lookup_hash;	/* only for in-lookup ones */
 	 	struct rcu_head d_rcu;
 	} d_u;
-};
+} __randomize_layout;
 
 /*
  * dentry->d_lock spinlock nesting subclasses:
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 803e5a9b2654..8f28143486c4 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -275,7 +275,7 @@ struct kiocb {
 	void (*ki_complete)(struct kiocb *iocb, long ret, long ret2);
 	void			*private;
 	int			ki_flags;
-};
+} __randomize_layout;
 
 static inline bool is_sync_kiocb(struct kiocb *kiocb)
 {
@@ -392,7 +392,7 @@ struct address_space {
 	gfp_t			gfp_mask;	/* implicit gfp mask for allocations */
 	struct list_head	private_list;	/* ditto */
 	void			*private_data;	/* ditto */
-} __attribute__((aligned(sizeof(long))));
+} __attribute__((aligned(sizeof(long)))) __randomize_layout;
 	/*
 	 * On most architectures that alignment is already the case; but
 	 * must be enforced here for CRIS, to let the least significant bit
@@ -435,7 +435,7 @@ struct block_device {
 	int			bd_fsfreeze_count;
 	/* Mutex for freeze */
 	struct mutex		bd_fsfreeze_mutex;
-};
+} __randomize_layout;
 
 /*
  * Radix-tree tags, for tagging dirty and writeback pages within the pagecache
@@ -653,7 +653,7 @@ struct inode {
 #endif
 
 	void			*i_private; /* fs or device private pointer */
-};
+} __randomize_layout;
 
 static inline unsigned int i_blocksize(const struct inode *node)
 {
@@ -868,7 +868,8 @@ struct file {
 	struct list_head	f_tfile_llink;
 #endif /* #ifdef CONFIG_EPOLL */
 	struct address_space	*f_mapping;
-} __attribute__((aligned(4)));	/* lest something weird decides that 2 is OK */
+} __randomize_layout
+  __attribute__((aligned(4)));	/* lest something weird decides that 2 is OK */
 
 struct file_handle {
 	__u32 handle_bytes;
@@ -1005,7 +1006,7 @@ struct file_lock {
 			int state;		/* state of grant or error if -ve */
 		} afs;
 	} fl_u;
-};
+} __randomize_layout;
 
 struct file_lock_context {
 	spinlock_t		flc_lock;
@@ -1404,7 +1405,7 @@ struct super_block {
 
 	spinlock_t		s_inode_wblist_lock;
 	struct list_head	s_inodes_wb;	/* writeback inodes */
-};
+} __randomize_layout;
 
 /* Helper functions so that in most cases filesystems will
  * not need to deal directly with kuid_t and kgid_t and can
@@ -1690,7 +1691,7 @@ struct file_operations {
 			u64);
 	ssize_t (*dedupe_file_range)(struct file *, u64, u64, struct file *,
 			u64);
-};
+} __randomize_layout;
 
 struct inode_operations {
 	struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h
index 0efc3e62843a..7a026240cbb1 100644
--- a/include/linux/fs_struct.h
+++ b/include/linux/fs_struct.h
@@ -12,7 +12,7 @@ struct fs_struct {
 	int umask;
 	int in_exec;
 	struct path root, pwd;
-};
+} __randomize_layout;
 
 extern struct kmem_cache *fs_cachep;
 
diff --git a/include/linux/ipc.h b/include/linux/ipc.h
index 71fd92d81b26..ea0eb0b5f98c 100644
--- a/include/linux/ipc.h
+++ b/include/linux/ipc.h
@@ -20,6 +20,6 @@ struct kern_ipc_perm {
 	umode_t		mode;
 	unsigned long	seq;
 	void		*security;
-} ____cacheline_aligned_in_smp;
+} ____cacheline_aligned_in_smp __randomize_layout;
 
 #endif /* _LINUX_IPC_H */
diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index 848e5796400e..65327ee0936b 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -61,7 +61,7 @@ struct ipc_namespace {
 	struct ucounts *ucounts;
 
 	struct ns_common ns;
-};
+} __randomize_layout;
 
 extern struct ipc_namespace init_ipc_ns;
 extern spinlock_t mq_lock;
diff --git a/include/linux/key-type.h b/include/linux/key-type.h
index 8496cf64575c..9520fc3c3b9a 100644
--- a/include/linux/key-type.h
+++ b/include/linux/key-type.h
@@ -45,7 +45,7 @@ struct key_preparsed_payload {
 	size_t		datalen;	/* Raw datalen */
 	size_t		quotalen;	/* Quota length for proposed payload */
 	time_t		expiry;		/* Expiry time of key */
-};
+} __randomize_layout;
 
 typedef int (*request_key_actor_t)(struct key_construction *key,
 				   const char *op, void *aux);
@@ -158,7 +158,7 @@ struct key_type {
 	/* internal fields */
 	struct list_head	link;		/* link in types list */
 	struct lock_class_key	lock_class;	/* key->sem lock class */
-};
+} __randomize_layout;
 
 extern struct key_type key_type_keyring;
 
diff --git a/include/linux/kmod.h b/include/linux/kmod.h
index c4e441e00db5..655082c88fd9 100644
--- a/include/linux/kmod.h
+++ b/include/linux/kmod.h
@@ -64,7 +64,7 @@ struct subprocess_info {
 	int (*init)(struct subprocess_info *info, struct cred *new);
 	void (*cleanup)(struct subprocess_info *info);
 	void *data;
-};
+} __randomize_layout;
 
 extern int
 call_usermodehelper(const char *path, char **argv, char **envp, int wait);
diff --git a/include/linux/kobject.h b/include/linux/kobject.h
index ca85cb80e99a..084513350317 100644
--- a/include/linux/kobject.h
+++ b/include/linux/kobject.h
@@ -172,7 +172,7 @@ struct kset {
 	spinlock_t list_lock;
 	struct kobject kobj;
 	const struct kset_uevent_ops *uevent_ops;
-};
+} __randomize_layout;
 
 extern void kset_init(struct kset *kset);
 extern int __must_check kset_register(struct kset *kset);
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index 080f34e66017..565163fc9ad4 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -1876,7 +1876,7 @@ struct security_hook_heads {
 	struct list_head audit_rule_match;
 	struct list_head audit_rule_free;
 #endif /* CONFIG_AUDIT */
-};
+} __randomize_layout;
 
 /*
  * Security module hook list structure.
@@ -1887,7 +1887,7 @@ struct security_hook_list {
 	struct list_head		*head;
 	union security_list_options	hook;
 	char				*lsm;
-};
+} __randomize_layout;
 
 /*
  * Initializing a security_hook_list structure takes
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 45cdb27791a3..ff151814a02d 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -342,7 +342,7 @@ struct vm_area_struct {
 	struct mempolicy *vm_policy;	/* NUMA policy for the VMA */
 #endif
 	struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
-};
+} __randomize_layout;
 
 struct core_thread {
 	struct task_struct *task;
@@ -500,7 +500,7 @@ struct mm_struct {
 	atomic_long_t hugetlb_usage;
 #endif
 	struct work_struct async_put_work;
-};
+} __randomize_layout;
 
 extern struct mm_struct init_mm;
 
diff --git a/include/linux/module.h b/include/linux/module.h
index 21f56393602f..d93111d7def6 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -45,7 +45,7 @@ struct module_kobject {
 	struct kobject *drivers_dir;
 	struct module_param_attrs *mp;
 	struct completion *kobj_completion;
-};
+} __randomize_layout;
 
 struct module_attribute {
 	struct attribute attr;
@@ -475,7 +475,7 @@ struct module {
 	ctor_fn_t *ctors;
 	unsigned int num_ctors;
 #endif
-} ____cacheline_aligned;
+} ____cacheline_aligned __randomize_layout;
 #ifndef MODULE_ARCH_INIT
 #define MODULE_ARCH_INIT {}
 #endif
diff --git a/include/linux/mount.h b/include/linux/mount.h
index 8e0352af06b7..1ce85e6fd95f 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -67,7 +67,7 @@ struct vfsmount {
 	struct dentry *mnt_root;	/* root of the mounted tree */
 	struct super_block *mnt_sb;	/* pointer to superblock */
 	int mnt_flags;
-};
+} __randomize_layout;
 
 struct file; /* forward dec */
 struct path;
diff --git a/include/linux/msg.h b/include/linux/msg.h
index f3f302f9c197..a001305f5a79 100644
--- a/include/linux/msg.h
+++ b/include/linux/msg.h
@@ -29,7 +29,7 @@ struct msg_queue {
 	struct list_head q_messages;
 	struct list_head q_receivers;
 	struct list_head q_senders;
-};
+} __randomize_layout;
 
 /* Helper routines for sys_msgsnd and sys_msgrcv */
 extern long do_msgsnd(int msqid, long mtype, void __user *mtext,
diff --git a/include/linux/path.h b/include/linux/path.h
index d1372186f431..cde895cc4af4 100644
--- a/include/linux/path.h
+++ b/include/linux/path.h
@@ -7,7 +7,7 @@ struct vfsmount;
 struct path {
 	struct vfsmount *mnt;
 	struct dentry *dentry;
-};
+} __randomize_layout;
 
 extern void path_get(const struct path *);
 extern void path_put(const struct path *);
diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h
index c2a989dee876..b09136f88cf4 100644
--- a/include/linux/pid_namespace.h
+++ b/include/linux/pid_namespace.h
@@ -52,7 +52,7 @@ struct pid_namespace {
 	int hide_pid;
 	int reboot;	/* group exit code if this pidns was rebooted */
 	struct ns_common ns;
-};
+} __randomize_layout;
 
 extern struct pid_namespace init_pid_ns;
 
diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h
index 58ab28d81fc2..06844b54dfc1 100644
--- a/include/linux/proc_ns.h
+++ b/include/linux/proc_ns.h
@@ -21,7 +21,7 @@ struct proc_ns_operations {
 	int (*install)(struct nsproxy *nsproxy, struct ns_common *ns);
 	struct user_namespace *(*owner)(struct ns_common *ns);
 	struct ns_common *(*get_parent)(struct ns_common *ns);
-};
+} __randomize_layout;
 
 extern const struct proc_ns_operations netns_operations;
 extern const struct proc_ns_operations utsns_operations;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 2b69fc650201..f833254fce00 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -408,7 +408,7 @@ struct sched_rt_entity {
 	/* rq "owned" by this entity/group: */
 	struct rt_rq			*my_q;
 #endif
-};
+} __randomize_layout;
 
 struct sched_dl_entity {
 	struct rb_node			rb_node;
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index c06d63b3a583..2a0dd40b15db 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -222,7 +222,7 @@ struct signal_struct {
 	struct mutex cred_guard_mutex;	/* guard against foreign influences on
 					 * credential calculations
 					 * (notably. ptrace) */
-};
+} __randomize_layout;
 
 /*
  * Bits in flags field of signal_struct.
diff --git a/include/linux/sem.h b/include/linux/sem.h
index 9edec926e9d9..23bcbdfad4a6 100644
--- a/include/linux/sem.h
+++ b/include/linux/sem.h
@@ -21,7 +21,7 @@ struct sem_array {
 	int			sem_nsems;	/* no. of semaphores in array */
 	int			complex_count;	/* pending complex operations */
 	unsigned int		use_global_lock;/* >0: global lock required */
-};
+} __randomize_layout;
 
 #ifdef CONFIG_SYSVIPC
 
diff --git a/include/linux/shm.h b/include/linux/shm.h
index 04e881829625..0fb7061ec54c 100644
--- a/include/linux/shm.h
+++ b/include/linux/shm.h
@@ -22,7 +22,7 @@ struct shmid_kernel /* private to the kernel */
 	/* The task created the shm object.  NULL if the task is dead. */
 	struct task_struct	*shm_creator;
 	struct list_head	shm_clist;	/* list by creator */
-};
+} __randomize_layout;
 
 /* shm_mode upper byte flags */
 #define	SHM_DEST	01000	/* segment will be destroyed on last detach */
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 80d07816def0..9ddeef2c03e2 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -117,7 +117,7 @@ struct ctl_table
 	struct ctl_table_poll *poll;
 	void *extra1;
 	void *extra2;
-};
+} __randomize_layout;
 
 struct ctl_node {
 	struct rb_node node;
diff --git a/include/linux/tty.h b/include/linux/tty.h
index d07cd2105a6c..73f8d0977bb0 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -333,7 +333,7 @@ struct tty_struct {
 	/* If the tty has a pending do_SAK, queue it here - akpm */
 	struct work_struct SAK_work;
 	struct tty_port *port;
-};
+} __randomize_layout;
 
 /* Each of a tty's open files has private_data pointing to tty_file_private */
 struct tty_file_private {
diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h
index b742b5e47cc2..00b2213f6a35 100644
--- a/include/linux/tty_driver.h
+++ b/include/linux/tty_driver.h
@@ -291,7 +291,7 @@ struct tty_operations {
 	void (*poll_put_char)(struct tty_driver *driver, int line, char ch);
 #endif
 	const struct file_operations *proc_fops;
-};
+} __randomize_layout;
 
 struct tty_driver {
 	int	magic;		/* magic number for this structure */
@@ -325,7 +325,7 @@ struct tty_driver {
 
 	const struct tty_operations *ops;
 	struct list_head tty_drivers;
-};
+} __randomize_layout;
 
 extern struct list_head tty_drivers;
 
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index 32354b4b4b2b..b3575ce29148 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -66,7 +66,7 @@ struct user_namespace {
 #endif
 	struct ucounts		*ucounts;
 	int ucount_max[UCOUNT_COUNTS];
-};
+} __randomize_layout;
 
 struct ucounts {
 	struct hlist_node node;
diff --git a/include/linux/utsname.h b/include/linux/utsname.h
index 60f0bb83b313..da826ed059cf 100644
--- a/include/linux/utsname.h
+++ b/include/linux/utsname.h
@@ -26,7 +26,7 @@ struct uts_namespace {
 	struct user_namespace *user_ns;
 	struct ucounts *ucounts;
 	struct ns_common ns;
-};
+} __randomize_layout;
 extern struct uts_namespace init_uts_ns;
 
 #ifdef CONFIG_UTS_NS
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index fd60eccb59a6..64e2a1e24a2c 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -36,7 +36,7 @@ struct unix_skb_parms {
 	u32			secid;		/* Security ID		*/
 #endif
 	u32			consumed;
-};
+} __randomize_layout;
 
 #define UNIXCB(skb) 	(*(struct unix_skb_parms *)&((skb)->cb))
 
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index e4dd3a214034..a62959d2b3f7 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -155,7 +155,7 @@ struct neighbour {
 	struct rcu_head		rcu;
 	struct net_device	*dev;
 	u8			primary_key[0];
-};
+} __randomize_layout;
 
 struct neigh_ops {
 	int			family;
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index fe80bb48ab1f..a224196d16ac 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -147,7 +147,7 @@ struct net {
 #endif
 	struct sock		*diag_nlsk;
 	atomic_t		fnhe_genid;
-};
+} __randomize_layout;
 
 #include <linux/seq_file_net.h>
 
diff --git a/include/net/sock.h b/include/net/sock.h
index f33e3d134e0b..d349297db9e9 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1113,7 +1113,7 @@ struct proto {
 	atomic_t		socks;
 #endif
 	int			(*diag_destroy)(struct sock *sk, int err);
-};
+} __randomize_layout;
 
 int proto_register(struct proto *prot, int alloc_slab);
 void proto_unregister(struct proto *prot);
diff --git a/kernel/futex.c b/kernel/futex.c
index 357348a6cf6b..5616511abf39 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -212,7 +212,7 @@ struct futex_pi_state {
 	atomic_t refcount;
 
 	union futex_key key;
-};
+} __randomize_layout;
 
 /**
  * struct futex_q - The hashed futex queue entry, one per waiting task
@@ -246,7 +246,7 @@ struct futex_q {
 	struct rt_mutex_waiter *rt_waiter;
 	union futex_key *requeue_pi_key;
 	u32 bitset;
-};
+} __randomize_layout;
 
 static const struct futex_q futex_q_init = {
 	/* list gets initialized in queue_me()*/
diff --git a/security/keys/internal.h b/security/keys/internal.h
index c0f8682eba69..6494954e9980 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -197,7 +197,7 @@ struct request_key_auth {
 	void			*callout_info;
 	size_t			callout_len;
 	pid_t			pid;
-};
+} __randomize_layout;
 
 extern struct key_type key_type_request_key_auth;
 extern struct key *request_key_auth_new(struct key *target,
-- 
cgit v1.2.3


From 29e48ce87f1eaaa4b1fe3d9af90c586ac2d1fb74 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Wed, 5 Apr 2017 22:43:33 -0700
Subject: task_struct: Allow randomized layout

This marks most of the layout of task_struct as randomizable, but leaves
thread_info and scheduler state untouched at the start, and thread_struct
untouched at the end.

Other parts of the kernel use unnamed structures, but the 0-day builder
using gcc-4.4 blows up on static initializers. Officially, it's documented
as only working on gcc 4.6 and later, which further confuses me:
	https://gcc.gnu.org/wiki/C11Status
The structure layout randomization already requires gcc 4.7, but instead
of depending on the plugin being enabled, just check the gcc versions
for wider build testing. At Linus's suggestion, the marking is hidden
in a macro to reduce how ugly it looks. Additionally, indenting is left
unchanged since it would make things harder to read.

Randomization of task_struct is modified from Brad Spengler/PaX Team's
code in the last public patch of grsecurity/PaX based on my understanding
of the code. Changes or omissions from the original code are mine and
don't reflect the original grsecurity/PaX code.

Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 include/linux/compiler-gcc.h | 13 ++++++++++++-
 include/linux/compiler.h     |  5 +++++
 include/linux/sched.h        | 14 ++++++++++++++
 3 files changed, 31 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 7deaae3dc87d..c4a66c036692 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -231,6 +231,7 @@
 #endif /* GCC_VERSION >= 40500 */
 
 #if GCC_VERSION >= 40600
+
 /*
  * When used with Link Time Optimization, gcc can optimize away C functions or
  * variables which are referenced only from assembly code.  __visible tells the
@@ -238,7 +239,17 @@
  * this.
  */
 #define __visible	__attribute__((externally_visible))
-#endif
+
+/*
+ * RANDSTRUCT_PLUGIN wants to use an anonymous struct, but it is only
+ * possible since GCC 4.6. To provide as much build testing coverage
+ * as possible, this is used for all GCC 4.6+ builds, and not just on
+ * RANDSTRUCT_PLUGIN builds.
+ */
+#define randomized_struct_fields_start	struct {
+#define randomized_struct_fields_end	} __randomize_layout;
+
+#endif /* GCC_VERSION >= 40600 */
 
 
 #if GCC_VERSION >= 40900 && !defined(__CHECKER__)
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 55ee9ee814f8..0b4ac3e8c63e 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -456,6 +456,11 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
 # define __no_randomize_layout
 #endif
 
+#ifndef randomized_struct_fields_start
+# define randomized_struct_fields_start
+# define randomized_struct_fields_end
+#endif
+
 /*
  * Tell gcc if a function is cold. The compiler will assume any path
  * directly leading to the call is unlikely.
diff --git a/include/linux/sched.h b/include/linux/sched.h
index f833254fce00..e2ad3531e7fe 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -490,6 +490,13 @@ struct task_struct {
 #endif
 	/* -1 unrunnable, 0 runnable, >0 stopped: */
 	volatile long			state;
+
+	/*
+	 * This begins the randomizable portion of task_struct. Only
+	 * scheduling-critical items should be added above here.
+	 */
+	randomized_struct_fields_start
+
 	void				*stack;
 	atomic_t			usage;
 	/* Per task flags (PF_*), defined further below: */
@@ -1051,6 +1058,13 @@ struct task_struct {
 	/* Used by LSM modules for access restriction: */
 	void				*security;
 #endif
+
+	/*
+	 * New fields for task_struct should be added above here, so that
+	 * they are included in the randomized portion of task_struct.
+	 */
+	randomized_struct_fields_end
+
 	/* CPU-specific state of this task: */
 	struct thread_struct		thread;
 
-- 
cgit v1.2.3


From 334fd34d76f237c0ee58dfc400d2c4e34d660544 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Thu, 29 Jun 2017 11:43:20 -0700
Subject: vfs: Add page_cache_seek_hole_data helper

Both ext4 and xfs implement seeking for the next hole or piece of data
in unwritten extents by scanning the page cache, and both versions share
the same bug when iterating the buffers of a page: the start offset into
the page isn't taken into account, so when a page fits more than two
filesystem blocks, things will go wrong.  For example, on a filesystem
with a block size of 1k, the following command will fail:

  xfs_io -f -c "falloc 0 4k" \
            -c "pwrite 1k 1k" \
            -c "pwrite 3k 1k" \
            -c "seek -a -r 0" foo

In this example, neither lseek(fd, 1024, SEEK_HOLE) nor lseek(fd, 2048,
SEEK_DATA) will return the correct result.

Introduce a generic vfs helper for seeking in the page cache that gets
this right.  The next commits will replace the filesystem specific
implementations.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
[hch: dropped the export]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/buffer.c                 | 124 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/buffer_head.h |   2 +
 2 files changed, 126 insertions(+)

(limited to 'include')

diff --git a/fs/buffer.c b/fs/buffer.c
index 161be58c5cb0..b3674eb7c9c0 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -3492,6 +3492,130 @@ int bh_submit_read(struct buffer_head *bh)
 }
 EXPORT_SYMBOL(bh_submit_read);
 
+/*
+ * Seek for SEEK_DATA / SEEK_HOLE within @page, starting at @lastoff.
+ *
+ * Returns the offset within the file on success, and -ENOENT otherwise.
+ */
+static loff_t
+page_seek_hole_data(struct page *page, loff_t lastoff, int whence)
+{
+	loff_t offset = page_offset(page);
+	struct buffer_head *bh, *head;
+	bool seek_data = whence == SEEK_DATA;
+
+	if (lastoff < offset)
+		lastoff = offset;
+
+	bh = head = page_buffers(page);
+	do {
+		offset += bh->b_size;
+		if (lastoff >= offset)
+			continue;
+
+		/*
+		 * Unwritten extents that have data in the page cache covering
+		 * them can be identified by the BH_Unwritten state flag.
+		 * Pages with multiple buffers might have a mix of holes, data
+		 * and unwritten extents - any buffer with valid data in it
+		 * should have BH_Uptodate flag set on it.
+		 */
+
+		if ((buffer_unwritten(bh) || buffer_uptodate(bh)) == seek_data)
+			return lastoff;
+
+		lastoff = offset;
+	} while ((bh = bh->b_this_page) != head);
+	return -ENOENT;
+}
+
+/*
+ * Seek for SEEK_DATA / SEEK_HOLE in the page cache.
+ *
+ * Within unwritten extents, the page cache determines which parts are holes
+ * and which are data: unwritten and uptodate buffer heads count as data;
+ * everything else counts as a hole.
+ *
+ * Returns the resulting offset on successs, and -ENOENT otherwise.
+ */
+loff_t
+page_cache_seek_hole_data(struct inode *inode, loff_t offset, loff_t length,
+			  int whence)
+{
+	pgoff_t index = offset >> PAGE_SHIFT;
+	pgoff_t end = DIV_ROUND_UP(offset + length, PAGE_SIZE);
+	loff_t lastoff = offset;
+	struct pagevec pvec;
+
+	if (length <= 0)
+		return -ENOENT;
+
+	pagevec_init(&pvec, 0);
+
+	do {
+		unsigned want, nr_pages, i;
+
+		want = min_t(unsigned, end - index, PAGEVEC_SIZE);
+		nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index, want);
+		if (nr_pages == 0)
+			break;
+
+		for (i = 0; i < nr_pages; i++) {
+			struct page *page = pvec.pages[i];
+
+			/*
+			 * At this point, the page may be truncated or
+			 * invalidated (changing page->mapping to NULL), or
+			 * even swizzled back from swapper_space to tmpfs file
+			 * mapping.  However, page->index will not change
+			 * because we have a reference on the page.
+                         *
+			 * If current page offset is beyond where we've ended,
+			 * we've found a hole.
+                         */
+			if (whence == SEEK_HOLE &&
+			    lastoff < page_offset(page))
+				goto check_range;
+
+			/* Searching done if the page index is out of range. */
+			if (page->index >= end)
+				goto not_found;
+
+			lock_page(page);
+			if (likely(page->mapping == inode->i_mapping) &&
+			    page_has_buffers(page)) {
+				lastoff = page_seek_hole_data(page, lastoff, whence);
+				if (lastoff >= 0) {
+					unlock_page(page);
+					goto check_range;
+				}
+			}
+			unlock_page(page);
+			lastoff = page_offset(page) + PAGE_SIZE;
+		}
+
+		/* Searching done if fewer pages returned than wanted. */
+		if (nr_pages < want)
+			break;
+
+		index = pvec.pages[i - 1]->index + 1;
+		pagevec_release(&pvec);
+	} while (index < end);
+
+	/* When no page at lastoff and we are not done, we found a hole. */
+	if (whence != SEEK_HOLE)
+		goto not_found;
+
+check_range:
+	if (lastoff < offset + length)
+		goto out;
+not_found:
+	lastoff = -ENOENT;
+out:
+	pagevec_release(&pvec);
+	return lastoff;
+}
+
 void __init buffer_init(void)
 {
 	unsigned long nrpages;
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index bd029e52ef5e..ad4e024ce17e 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -201,6 +201,8 @@ void write_boundary_block(struct block_device *bdev,
 			sector_t bblock, unsigned blocksize);
 int bh_uptodate_or_lock(struct buffer_head *bh);
 int bh_submit_read(struct buffer_head *bh);
+loff_t page_cache_seek_hole_data(struct inode *inode, loff_t offset,
+				 loff_t length, int whence);
 
 extern int buffer_heads_over_limit;
 
-- 
cgit v1.2.3


From 0ed3b0d45fd39142e418220f518c8959c1a5f596 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Thu, 29 Jun 2017 11:43:21 -0700
Subject: vfs: Add iomap_seek_hole and iomap_seek_data helpers

Filesystems can use this for implementing lseek SEEK_HOLE / SEEK_DATA
support via iomap.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
[hch: split functions, coding style cleanups]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/iomap.c            | 94 +++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/iomap.h |  4 +++
 2 files changed, 98 insertions(+)

(limited to 'include')

diff --git a/fs/iomap.c b/fs/iomap.c
index 4b10892967a5..432eed8f091f 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -584,6 +584,100 @@ int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi,
 }
 EXPORT_SYMBOL_GPL(iomap_fiemap);
 
+static loff_t
+iomap_seek_hole_actor(struct inode *inode, loff_t offset, loff_t length,
+		      void *data, struct iomap *iomap)
+{
+	switch (iomap->type) {
+	case IOMAP_UNWRITTEN:
+		offset = page_cache_seek_hole_data(inode, offset, length,
+						   SEEK_HOLE);
+		if (offset < 0)
+			return length;
+		/* fall through */
+	case IOMAP_HOLE:
+		*(loff_t *)data = offset;
+		return 0;
+	default:
+		return length;
+	}
+}
+
+loff_t
+iomap_seek_hole(struct inode *inode, loff_t offset, const struct iomap_ops *ops)
+{
+	loff_t size = i_size_read(inode);
+	loff_t length = size - offset;
+	loff_t ret;
+
+	/* Nothing to be found beyond the end of the file. */
+	if (offset >= size)
+		return -ENXIO;
+
+	while (length > 0) {
+		ret = iomap_apply(inode, offset, length, IOMAP_REPORT, ops,
+				  &offset, iomap_seek_hole_actor);
+		if (ret < 0)
+			return ret;
+		if (ret == 0)
+			break;
+
+		offset += ret;
+		length -= ret;
+	}
+
+	return offset;
+}
+EXPORT_SYMBOL_GPL(iomap_seek_hole);
+
+static loff_t
+iomap_seek_data_actor(struct inode *inode, loff_t offset, loff_t length,
+		      void *data, struct iomap *iomap)
+{
+	switch (iomap->type) {
+	case IOMAP_HOLE:
+		return length;
+	case IOMAP_UNWRITTEN:
+		offset = page_cache_seek_hole_data(inode, offset, length,
+						   SEEK_DATA);
+		if (offset < 0)
+			return length;
+		/*FALLTHRU*/
+	default:
+		*(loff_t *)data = offset;
+		return 0;
+	}
+}
+
+loff_t
+iomap_seek_data(struct inode *inode, loff_t offset, const struct iomap_ops *ops)
+{
+	loff_t size = i_size_read(inode);
+	loff_t length = size - offset;
+	loff_t ret;
+
+	/* Nothing to be found beyond the end of the file. */
+	if (offset >= size)
+		return -ENXIO;
+
+	while (length > 0) {
+		ret = iomap_apply(inode, offset, length, IOMAP_REPORT, ops,
+				  &offset, iomap_seek_data_actor);
+		if (ret < 0)
+			return ret;
+		if (ret == 0)
+			break;
+
+		offset += ret;
+		length -= ret;
+	}
+
+	if (length <= 0)
+		return -ENXIO;
+	return offset;
+}
+EXPORT_SYMBOL_GPL(iomap_seek_data);
+
 /*
  * Private flags for iomap_dio, must not overlap with the public ones in
  * iomap.h:
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index f753e788da31..8a03f5dcd89b 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -83,6 +83,10 @@ int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
 int iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops);
 int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		loff_t start, loff_t len, const struct iomap_ops *ops);
+loff_t iomap_seek_hole(struct inode *inode, loff_t offset,
+		const struct iomap_ops *ops);
+loff_t iomap_seek_data(struct inode *inode, loff_t offset,
+		const struct iomap_ops *ops);
 
 /*
  * Flags for direct I/O ->end_io:
-- 
cgit v1.2.3


From 468138d78510688fb5476f98d23f11ac6a63229a Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 2 May 2017 19:52:17 -0400
Subject: binfmt_flat: flat_{get,put}_addr_from_rp() should be able to fail

on MMU targets EFAULT is possible here.  Make both return 0 or error,
passing what used to be the return value of flat_get_addr_from_rp()
by reference.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/arm/include/asm/flat.h        | 25 +++++++++++++++++++++---
 arch/blackfin/include/asm/flat.h   | 25 ++++++++++++++----------
 arch/blackfin/kernel/flat.c        | 13 ++++++-------
 arch/c6x/include/asm/flat.h        | 15 +++++++++++++--
 arch/h8300/include/asm/flat.h      | 24 +++++++++++++++++------
 arch/m32r/include/asm/flat.h       | 19 ++++++++-----------
 arch/m68k/include/asm/flat.h       | 23 +++++++++++++++++++---
 arch/microblaze/include/asm/flat.h | 34 ++++++++++++++++-----------------
 arch/sh/include/asm/flat.h         | 15 +++++++++++++--
 arch/xtensa/include/asm/flat.h     | 15 +++++++++++++--
 fs/binfmt_flat.c                   | 39 +++++++++++++++++++++-----------------
 include/linux/flat.h               |  2 +-
 12 files changed, 168 insertions(+), 81 deletions(-)

(limited to 'include')

diff --git a/arch/arm/include/asm/flat.h b/arch/arm/include/asm/flat.h
index acf1d14b89a6..29d3a1524bce 100644
--- a/arch/arm/include/asm/flat.h
+++ b/arch/arm/include/asm/flat.h
@@ -5,12 +5,31 @@
 #ifndef __ARM_FLAT_H__
 #define __ARM_FLAT_H__
 
+#include <linux/uaccess.h>
+
 #define	flat_argvp_envp_on_stack()		1
 #define	flat_old_ram_flag(flags)		(flags)
 #define	flat_reloc_valid(reloc, size)		((reloc) <= (size))
-#define	flat_get_addr_from_rp(rp, relval, flags, persistent) \
-	({ unsigned long __val; __get_user_unaligned(__val, rp); __val; })
-#define	flat_put_addr_at_rp(rp, val, relval)	__put_user_unaligned(val, rp)
+
+static inline int flat_get_addr_from_rp(u32 __user *rp, u32 relval, u32 flags,
+					u32 *addr, u32 *persistent)
+{
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+	return copy_from_user(addr, rp, 4) ? -EFAULT : 0;
+#else
+	return get_user(*addr, rp);
+#endif
+}
+
+static inline int flat_put_addr_at_rp(u32 __user *rp, u32 addr, u32 rel)
+{
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+	return copy_to_user(rp, &addr, 4) ? -EFAULT : 0;
+#else
+	return put_user(addr, rp);
+#endif
+}
+
 #define	flat_get_relocate_addr(rel)		(rel)
 #define	flat_set_persistent(relval, p)		0
 
diff --git a/arch/blackfin/include/asm/flat.h b/arch/blackfin/include/asm/flat.h
index c1314c56dd18..296d7f56fbfd 100644
--- a/arch/blackfin/include/asm/flat.h
+++ b/arch/blackfin/include/asm/flat.h
@@ -14,23 +14,28 @@
 #define	flat_argvp_envp_on_stack()		0
 #define	flat_old_ram_flag(flags)		(flags)
 
-extern unsigned long bfin_get_addr_from_rp (unsigned long *ptr,
-					unsigned long relval,
-					unsigned long flags,
-					unsigned long *persistent);
+extern unsigned long bfin_get_addr_from_rp (u32 *ptr, u32 relval,
+					u32 flags, u32 *persistent);
 
-extern void bfin_put_addr_at_rp(unsigned long *ptr, unsigned long addr,
-		                unsigned long relval);
+extern void bfin_put_addr_at_rp(u32 *ptr, u32 addr, u32 relval);
 
 /* The amount by which a relocation can exceed the program image limits
    without being regarded as an error.  */
 
 #define	flat_reloc_valid(reloc, size)	((reloc) <= (size))
 
-#define	flat_get_addr_from_rp(rp, relval, flags, persistent)	\
-	bfin_get_addr_from_rp(rp, relval, flags, persistent)
-#define	flat_put_addr_at_rp(rp, val, relval)	\
-	bfin_put_addr_at_rp(rp, val, relval)
+static inline int flat_get_addr_from_rp(u32 __user *rp, u32 relval, u32 flags,
+					u32 *addr, u32 *persistent)
+{
+	*addr = bfin_get_addr_from_rp(rp, relval, flags, persistent);
+	return 0;
+}
+
+static inline int flat_put_addr_at_rp(u32 __user *rp, u32 val, u32 relval)
+{
+	bfin_put_addr_at_rp(rp, val, relval);
+	return 0;
+}
 
 /* Convert a relocation entry into an address.  */
 static inline unsigned long
diff --git a/arch/blackfin/kernel/flat.c b/arch/blackfin/kernel/flat.c
index b5b658449616..d29ab6a2e909 100644
--- a/arch/blackfin/kernel/flat.c
+++ b/arch/blackfin/kernel/flat.c
@@ -13,14 +13,14 @@
 #define FLAT_BFIN_RELOC_TYPE_16H_BIT 1
 #define FLAT_BFIN_RELOC_TYPE_32_BIT 2
 
-unsigned long bfin_get_addr_from_rp(unsigned long *ptr,
-		unsigned long relval,
-		unsigned long flags,
-		unsigned long *persistent)
+unsigned long bfin_get_addr_from_rp(u32 *ptr,
+		u32 relval,
+		u32 flags,
+		u32 *persistent)
 {
 	unsigned short *usptr = (unsigned short *)ptr;
 	int type = (relval >> 26) & 7;
-	unsigned long val;
+	u32 val;
 
 	switch (type) {
 	case FLAT_BFIN_RELOC_TYPE_16_BIT:
@@ -59,8 +59,7 @@ EXPORT_SYMBOL(bfin_get_addr_from_rp);
  * Insert the address ADDR into the symbol reference at RP;
  * RELVAL is the raw relocation-table entry from which RP is derived
  */
-void bfin_put_addr_at_rp(unsigned long *ptr, unsigned long addr,
-		unsigned long relval)
+void bfin_put_addr_at_rp(u32 *ptr, u32 addr, u32 relval)
 {
 	unsigned short *usptr = (unsigned short *)ptr;
 	int type = (relval >> 26) & 7;
diff --git a/arch/c6x/include/asm/flat.h b/arch/c6x/include/asm/flat.h
index a1858bd5f6c8..6f1feb00bd52 100644
--- a/arch/c6x/include/asm/flat.h
+++ b/arch/c6x/include/asm/flat.h
@@ -1,11 +1,22 @@
 #ifndef __ASM_C6X_FLAT_H
 #define __ASM_C6X_FLAT_H
 
+#include <asm/unaligned.h>
+
 #define flat_argvp_envp_on_stack()			0
 #define flat_old_ram_flag(flags)			(flags)
 #define flat_reloc_valid(reloc, size)			((reloc) <= (size))
-#define flat_get_addr_from_rp(rp, relval, flags, p)	get_unaligned(rp)
-#define flat_put_addr_at_rp(rp, val, relval)		put_unaligned(val, rp)
+static inline int flat_get_addr_from_rp(u32 __user *rp, u32 relval, u32 flags,
+					u32 *addr, u32 *persistent)
+{
+	*addr = get_unaligned((__force u32 *)rp);
+	return 0;
+}
+static inline int flat_put_addr_at_rp(u32 __user *rp, u32 addr, u32 rel)
+{
+	put_unaligned(addr, (__force u32 *)rp);
+	return 0;
+}
 #define flat_get_relocate_addr(rel)			(rel)
 #define flat_set_persistent(relval, p)			0
 
diff --git a/arch/h8300/include/asm/flat.h b/arch/h8300/include/asm/flat.h
index a4898eccf2bf..18d024251738 100644
--- a/arch/h8300/include/asm/flat.h
+++ b/arch/h8300/include/asm/flat.h
@@ -5,6 +5,8 @@
 #ifndef __H8300_FLAT_H__
 #define __H8300_FLAT_H__
 
+#include <asm/unaligned.h>
+
 #define	flat_argvp_envp_on_stack()		1
 #define	flat_old_ram_flag(flags)		1
 #define	flat_reloc_valid(reloc, size)		((reloc) <= (size))
@@ -18,11 +20,21 @@
  */
 
 #define	flat_get_relocate_addr(rel)		(rel & ~0x00000001)
-#define flat_get_addr_from_rp(rp, relval, flags, persistent) \
-	({(void)persistent; \
-		get_unaligned(rp) & (((flags) & FLAT_FLAG_GOTPIC) ?	\
-				     0xffffffff : 0x00ffffff); })
-#define flat_put_addr_at_rp(rp, addr, rel) \
-	put_unaligned(((*(char *)(rp)) << 24) | ((addr) & 0x00ffffff), (rp))
+static inline int flat_get_addr_from_rp(u32 __user *rp, u32 relval, u32 flags,
+					u32 *addr, u32 *persistent)
+{
+	u32 val = get_unaligned((__force u32 *)rp);
+	if (!(flags & FLAT_FLAG_GOTPIC)
+		val &= 0x00ffffff;
+	*addr = val;
+	return 0;
+}
+
+static inline int flat_put_addr_at_rp(u32 __user *rp, u32 addr, u32 rel)
+{
+	u32 *p = (__force u32 *)rp;
+	put_unaligned((addr & 0x00ffffff) | (*(char *)p << 24), p);
+	return 0;
+}
 
 #endif /* __H8300_FLAT_H__ */
diff --git a/arch/m32r/include/asm/flat.h b/arch/m32r/include/asm/flat.h
index 5d711c4688fb..455ce7ddbf14 100644
--- a/arch/m32r/include/asm/flat.h
+++ b/arch/m32r/include/asm/flat.h
@@ -17,11 +17,6 @@
 #define	flat_set_persistent(relval, p)		0
 #define	flat_reloc_valid(reloc, size)		\
 	(((reloc) - textlen_for_m32r_lo16_data) <= (size))
-#define flat_get_addr_from_rp(rp, relval, flags, persistent) \
-	m32r_flat_get_addr_from_rp(rp, relval, (text_len) )
-
-#define flat_put_addr_at_rp(rp, addr, relval) \
-	m32r_flat_put_addr_at_rp(rp, addr, relval)
 
 /* Convert a relocation entry into an address.  */
 static inline unsigned long
@@ -57,9 +52,9 @@ flat_get_relocate_addr (unsigned long relval)
 
 static unsigned long textlen_for_m32r_lo16_data = 0;
 
-static inline unsigned long m32r_flat_get_addr_from_rp (unsigned long *rp,
-                                                        unsigned long relval,
-						        unsigned long textlen)
+static inline unsigned long m32r_flat_get_addr_from_rp (u32 *rp,
+                                                        u32 relval,
+						        u32 textlen)
 {
         unsigned int reloc = flat_m32r_get_reloc_type (relval);
 	textlen_for_m32r_lo16_data = 0;
@@ -100,9 +95,7 @@ static inline unsigned long m32r_flat_get_addr_from_rp (unsigned long *rp,
 	return ~0;      /* bogus value */
 }
 
-static inline void m32r_flat_put_addr_at_rp (unsigned long *rp,
-					     unsigned long addr,
-                                             unsigned long relval)
+static inline void flat_put_addr_at_rp(u32 *rp, u32 addr, u32 relval)
 {
         unsigned int reloc = flat_m32r_get_reloc_type (relval);
 	if (reloc & 0xf0) {
@@ -142,4 +135,8 @@ static inline void m32r_flat_put_addr_at_rp (unsigned long *rp,
 	}
 }
 
+// kludge - text_len is a local variable in the only user.
+#define flat_get_addr_from_rp(rp, relval, flags, addr, persistent) \
+	(m32r_flat_get_addr_from_rp(rp, relval, text_len), 0)
+
 #endif /* __ASM_M32R_FLAT_H */
diff --git a/arch/m68k/include/asm/flat.h b/arch/m68k/include/asm/flat.h
index 00c392b0cabd..48b62790fe70 100644
--- a/arch/m68k/include/asm/flat.h
+++ b/arch/m68k/include/asm/flat.h
@@ -5,12 +5,29 @@
 #ifndef __M68KNOMMU_FLAT_H__
 #define __M68KNOMMU_FLAT_H__
 
+#include <linux/uaccess.h>
+
 #define	flat_argvp_envp_on_stack()		1
 #define	flat_old_ram_flag(flags)		(flags)
 #define	flat_reloc_valid(reloc, size)		((reloc) <= (size))
-#define	flat_get_addr_from_rp(rp, relval, flags, p) \
-	({ unsigned long __val; __get_user_unaligned(__val, rp); __val; })
-#define	flat_put_addr_at_rp(rp, val, relval)	__put_user_unaligned(val, rp)
+static inline int flat_get_addr_from_rp(u32 __user *rp, u32 relval, u32 flags,
+					u32 *addr, u32 *persistent)
+{
+#ifdef CONFIG_CPU_HAS_NO_UNALIGNED
+	return copy_from_user(addr, rp, 4) ? -EFAULT : 0;
+#else
+	return get_user(*addr, rp);
+#endif
+}
+
+static inline int flat_put_addr_at_rp(u32 __user *rp, u32 addr, u32 rel)
+{
+#ifdef CONFIG_CPU_HAS_NO_UNALIGNED
+	return copy_to_user(rp, &addr, 4) ? -EFAULT : 0;
+#else
+	return put_user(addr, rp);
+#endif
+}
 #define	flat_get_relocate_addr(rel)		(rel)
 
 static inline int flat_set_persistent(unsigned long relval,
diff --git a/arch/microblaze/include/asm/flat.h b/arch/microblaze/include/asm/flat.h
index 6847c1512c7b..f23c3d266bae 100644
--- a/arch/microblaze/include/asm/flat.h
+++ b/arch/microblaze/include/asm/flat.h
@@ -32,29 +32,27 @@
  * reference
  */
 
-static inline unsigned long
-flat_get_addr_from_rp(unsigned long *rp, unsigned long relval,
-			unsigned long flags, unsigned long *persistent)
+static inline int flat_get_addr_from_rp(u32 __user *rp, u32 relval, u32 flags,
+					u32 *addr, u32 *persistent)
 {
-	unsigned long addr;
-	(void)flags;
+	u32 *p = (__force u32 *)rp;
 
 	/* Is it a split 64/32 reference? */
 	if (relval & 0x80000000) {
 		/* Grab the two halves of the reference */
-		unsigned long val_hi, val_lo;
+		u32 val_hi, val_lo;
 
-		val_hi = get_unaligned(rp);
-		val_lo = get_unaligned(rp+1);
+		val_hi = get_unaligned(p);
+		val_lo = get_unaligned(p+1);
 
 		/* Crack the address out */
-		addr = ((val_hi & 0xffff) << 16) + (val_lo & 0xffff);
+		*addr = ((val_hi & 0xffff) << 16) + (val_lo & 0xffff);
 	} else {
 		/* Get the address straight out */
-		addr = get_unaligned(rp);
+		*addr = get_unaligned(p);
 	}
 
-	return addr;
+	return 0;
 }
 
 /*
@@ -63,25 +61,27 @@ flat_get_addr_from_rp(unsigned long *rp, unsigned long relval,
  */
 
 static inline void
-flat_put_addr_at_rp(unsigned long *rp, unsigned long addr, unsigned long relval)
+flat_put_addr_at_rp(u32 __user *rp, u32 addr, u32 relval)
 {
+	u32 *p = (__force u32 *)rp;
 	/* Is this a split 64/32 reloc? */
 	if (relval & 0x80000000) {
 		/* Get the two "halves" */
-		unsigned long val_hi = get_unaligned(rp);
-		unsigned long val_lo = get_unaligned(rp + 1);
+		unsigned long val_hi = get_unaligned(p);
+		unsigned long val_lo = get_unaligned(p + 1);
 
 		/* insert the address */
 		val_hi = (val_hi & 0xffff0000) | addr >> 16;
 		val_lo = (val_lo & 0xffff0000) | (addr & 0xffff);
 
 		/* store the two halves back into memory */
-		put_unaligned(val_hi, rp);
-		put_unaligned(val_lo, rp+1);
+		put_unaligned(val_hi, p);
+		put_unaligned(val_lo, p+1);
 	} else {
 		/* Put it straight in, no messing around */
-		put_unaligned(addr, rp);
+		put_unaligned(addr, p);
 	}
+	return 0;
 }
 
 #define	flat_get_relocate_addr(rel)	(rel & 0x7fffffff)
diff --git a/arch/sh/include/asm/flat.h b/arch/sh/include/asm/flat.h
index 5d84df5e27f6..275fcae23539 100644
--- a/arch/sh/include/asm/flat.h
+++ b/arch/sh/include/asm/flat.h
@@ -12,11 +12,22 @@
 #ifndef __ASM_SH_FLAT_H
 #define __ASM_SH_FLAT_H
 
+#include <asm/unaligned.h>
+
 #define	flat_argvp_envp_on_stack()		0
 #define	flat_old_ram_flag(flags)		(flags)
 #define	flat_reloc_valid(reloc, size)		((reloc) <= (size))
-#define	flat_get_addr_from_rp(rp, relval, flags, p)	get_unaligned(rp)
-#define	flat_put_addr_at_rp(rp, val, relval)	put_unaligned(val,rp)
+static inline int flat_get_addr_from_rp(u32 __user *rp, u32 relval, u32 flags,
+					u32 *addr, u32 *persistent)
+{
+	*addr = get_unaligned((__force u32 *)rp);
+	return 0;
+}
+static inline int flat_put_addr_at_rp(u32 __user *rp, u32 addr, u32 rel)
+{
+	put_unaligned(addr, (__force u32 *)rp);
+	return 0;
+}
 #define	flat_get_relocate_addr(rel)		(rel)
 #define	flat_set_persistent(relval, p)		({ (void)p; 0; })
 
diff --git a/arch/xtensa/include/asm/flat.h b/arch/xtensa/include/asm/flat.h
index 94c44abf15e4..60e0d6a45795 100644
--- a/arch/xtensa/include/asm/flat.h
+++ b/arch/xtensa/include/asm/flat.h
@@ -1,11 +1,22 @@
 #ifndef __ASM_XTENSA_FLAT_H
 #define __ASM_XTENSA_FLAT_H
 
+#include <asm/unaligned.h>
+
 #define flat_argvp_envp_on_stack()			0
 #define flat_old_ram_flag(flags)			(flags)
 #define flat_reloc_valid(reloc, size)			((reloc) <= (size))
-#define flat_get_addr_from_rp(rp, relval, flags, p)	get_unaligned(rp)
-#define flat_put_addr_at_rp(rp, val, relval	)	put_unaligned(val, rp)
+static inline int flat_get_addr_from_rp(u32 __user *rp, u32 relval, u32 flags,
+					u32 *addr, u32 *persistent)
+{
+	*addr = get_unaligned((__force u32 *)rp);
+	return 0;
+}
+static inline int flat_put_addr_at_rp(u32 __user *rp, u32 addr, u32 rel)
+{
+	put_unaligned(addr, (__force u32 *)rp);
+	return 0;
+}
 #define flat_get_relocate_addr(rel)			(rel)
 #define flat_set_persistent(relval, p)			0
 
diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index 2edcefc0a294..69ec23daa25e 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -422,9 +422,9 @@ static int load_flat_file(struct linux_binprm *bprm,
 {
 	struct flat_hdr *hdr;
 	unsigned long textpos, datapos, realdatastart;
-	unsigned long text_len, data_len, bss_len, stack_len, full_data, flags;
+	u32 text_len, data_len, bss_len, stack_len, full_data, flags;
 	unsigned long len, memp, memp_size, extra, rlim;
-	unsigned long __user *reloc, *rp;
+	u32 __user *reloc, *rp;
 	struct inode *inode;
 	int i, rev, relocs;
 	loff_t fpos;
@@ -596,13 +596,13 @@ static int load_flat_file(struct linux_binprm *bprm,
 			goto err;
 		}
 
-		reloc = (unsigned long __user *)
+		reloc = (u32 __user *)
 			(datapos + (ntohl(hdr->reloc_start) - text_len));
 		memp = realdatastart;
 		memp_size = len;
 	} else {
 
-		len = text_len + data_len + extra + MAX_SHARED_LIBS * sizeof(unsigned long);
+		len = text_len + data_len + extra + MAX_SHARED_LIBS * sizeof(u32);
 		len = PAGE_ALIGN(len);
 		textpos = vm_mmap(NULL, 0, len,
 			PROT_READ | PROT_EXEC | PROT_WRITE, MAP_PRIVATE, 0);
@@ -618,10 +618,10 @@ static int load_flat_file(struct linux_binprm *bprm,
 
 		realdatastart = textpos + ntohl(hdr->data_start);
 		datapos = ALIGN(realdatastart +
-				MAX_SHARED_LIBS * sizeof(unsigned long),
+				MAX_SHARED_LIBS * sizeof(u32),
 				FLAT_DATA_ALIGN);
 
-		reloc = (unsigned long __user *)
+		reloc = (u32 __user *)
 			(datapos + (ntohl(hdr->reloc_start) - text_len));
 		memp = textpos;
 		memp_size = len;
@@ -694,7 +694,7 @@ static int load_flat_file(struct linux_binprm *bprm,
 			ret = result;
 			pr_err("Unable to read code+data+bss, errno %d\n", ret);
 			vm_munmap(textpos, text_len + data_len + extra +
-				MAX_SHARED_LIBS * sizeof(unsigned long));
+				MAX_SHARED_LIBS * sizeof(u32));
 			goto err;
 		}
 	}
@@ -754,8 +754,8 @@ static int load_flat_file(struct linux_binprm *bprm,
 	 * image.
 	 */
 	if (flags & FLAT_FLAG_GOTPIC) {
-		for (rp = (unsigned long __user *)datapos; ; rp++) {
-			unsigned long addr, rp_val;
+		for (rp = (u32 __user *)datapos; ; rp++) {
+			u32 addr, rp_val;
 			if (get_user(rp_val, rp))
 				return -EFAULT;
 			if (rp_val == 0xffffffff)
@@ -784,9 +784,9 @@ static int load_flat_file(struct linux_binprm *bprm,
 	 * __start to address 4 so that is okay).
 	 */
 	if (rev > OLD_FLAT_VERSION) {
-		unsigned long __maybe_unused persistent = 0;
+		u32 __maybe_unused persistent = 0;
 		for (i = 0; i < relocs; i++) {
-			unsigned long addr, relval;
+			u32 addr, relval;
 
 			/*
 			 * Get the address of the pointer to be
@@ -799,15 +799,18 @@ static int load_flat_file(struct linux_binprm *bprm,
 			if (flat_set_persistent(relval, &persistent))
 				continue;
 			addr = flat_get_relocate_addr(relval);
-			rp = (unsigned long __user *)calc_reloc(addr, libinfo, id, 1);
-			if (rp == (unsigned long __user *)RELOC_FAILED) {
+			rp = (u32 __user *)calc_reloc(addr, libinfo, id, 1);
+			if (rp == (u32 __user *)RELOC_FAILED) {
 				ret = -ENOEXEC;
 				goto err;
 			}
 
 			/* Get the pointer's value.  */
-			addr = flat_get_addr_from_rp(rp, relval, flags,
-							&persistent);
+			ret = flat_get_addr_from_rp(rp, relval, flags,
+							&addr, &persistent);
+			if (unlikely(ret))
+				goto err;
+
 			if (addr != 0) {
 				/*
 				 * Do the relocation.  PIC relocs in the data section are
@@ -822,12 +825,14 @@ static int load_flat_file(struct linux_binprm *bprm,
 				}
 
 				/* Write back the relocated pointer.  */
-				flat_put_addr_at_rp(rp, addr, relval);
+				ret = flat_put_addr_at_rp(rp, addr, relval);
+				if (unlikely(ret))
+					goto err;
 			}
 		}
 	} else {
 		for (i = 0; i < relocs; i++) {
-			unsigned long relval;
+			u32 relval;
 			if (get_user(relval, reloc + i))
 				return -EFAULT;
 			relval = ntohl(relval);
diff --git a/include/linux/flat.h b/include/linux/flat.h
index 2c1eb15c4ba4..7d542dfd0def 100644
--- a/include/linux/flat.h
+++ b/include/linux/flat.h
@@ -9,8 +9,8 @@
 #ifndef _LINUX_FLAT_H
 #define _LINUX_FLAT_H
 
-#include <asm/flat.h>
 #include <uapi/linux/flat.h>
+#include <asm/flat.h>
 
 /*
  * While it would be nice to keep this header clean,  users of older
-- 
cgit v1.2.3


From 3170d8d226c2053355f3946b4b5ded4c006fe6d4 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 2 May 2017 20:06:33 -0400
Subject: kill {__,}{get,put}_user_unaligned()

no users left

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/arm/include/asm/uaccess.h          |   7 -
 arch/arm64/include/asm/uaccess.h        |   4 -
 arch/ia64/include/asm/uaccess.h         |  36 -----
 arch/m68k/include/asm/uaccess.h         |   7 -
 arch/mips/include/asm/uaccess.h         | 277 --------------------------------
 arch/parisc/include/asm/uaccess.h       |   1 -
 arch/powerpc/include/asm/uaccess.h      |   3 -
 arch/s390/include/asm/uaccess.h         |   3 -
 arch/sparc/include/asm/uaccess_64.h     |   1 -
 arch/tile/include/asm/uaccess.h         |   1 -
 arch/x86/include/asm/uaccess.h          |   3 -
 include/asm-generic/uaccess-unaligned.h |  26 ---
 12 files changed, 369 deletions(-)
 delete mode 100644 include/asm-generic/uaccess-unaligned.h

(limited to 'include')

diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 2577405d082d..0726091a8964 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -17,13 +17,6 @@
 #include <asm/unified.h>
 #include <asm/compiler.h>
 
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
-#include <asm-generic/uaccess-unaligned.h>
-#else
-#define __get_user_unaligned __get_user
-#define __put_user_unaligned __put_user
-#endif
-
 #include <asm/extable.h>
 
 /*
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 7b8a04789cef..f2b465e129de 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -254,8 +254,6 @@ do {									\
 	(void)0;							\
 })
 
-#define __get_user_unaligned __get_user
-
 #define get_user(x, ptr)						\
 ({									\
 	__typeof__(*(ptr)) __user *__p = (ptr);				\
@@ -320,8 +318,6 @@ do {									\
 	(void)0;							\
 })
 
-#define __put_user_unaligned __put_user
-
 #define put_user(x, ptr)						\
 ({									\
 	__typeof__(*(ptr)) __user *__p = (ptr);				\
diff --git a/arch/ia64/include/asm/uaccess.h b/arch/ia64/include/asm/uaccess.h
index 82a7646c4416..a217bcfe6700 100644
--- a/arch/ia64/include/asm/uaccess.h
+++ b/arch/ia64/include/asm/uaccess.h
@@ -87,42 +87,6 @@ static inline int __access_ok(const void __user *p, unsigned long size)
 #define __put_user(x, ptr)	__put_user_nocheck((__typeof__(*(ptr))) (x), (ptr), sizeof(*(ptr)))
 #define __get_user(x, ptr)	__get_user_nocheck((x), (ptr), sizeof(*(ptr)))
 
-extern long __put_user_unaligned_unknown (void);
-
-#define __put_user_unaligned(x, ptr)								\
-({												\
-	long __ret;										\
-	switch (sizeof(*(ptr))) {								\
-		case 1: __ret = __put_user((x), (ptr)); break;					\
-		case 2: __ret = (__put_user((x), (u8 __user *)(ptr)))				\
-			| (__put_user((x) >> 8, ((u8 __user *)(ptr) + 1))); break;		\
-		case 4: __ret = (__put_user((x), (u16 __user *)(ptr)))				\
-			| (__put_user((x) >> 16, ((u16 __user *)(ptr) + 1))); break;		\
-		case 8: __ret = (__put_user((x), (u32 __user *)(ptr)))				\
-			| (__put_user((x) >> 32, ((u32 __user *)(ptr) + 1))); break;		\
-		default: __ret = __put_user_unaligned_unknown();				\
-	}											\
-	__ret;											\
-})
-
-extern long __get_user_unaligned_unknown (void);
-
-#define __get_user_unaligned(x, ptr)								\
-({												\
-	long __ret;										\
-	switch (sizeof(*(ptr))) {								\
-		case 1: __ret = __get_user((x), (ptr)); break;					\
-		case 2: __ret = (__get_user((x), (u8 __user *)(ptr)))				\
-			| (__get_user((x) >> 8, ((u8 __user *)(ptr) + 1))); break;		\
-		case 4: __ret = (__get_user((x), (u16 __user *)(ptr)))				\
-			| (__get_user((x) >> 16, ((u16 __user *)(ptr) + 1))); break;		\
-		case 8: __ret = (__get_user((x), (u32 __user *)(ptr)))				\
-			| (__get_user((x) >> 32, ((u32 __user *)(ptr) + 1))); break;		\
-		default: __ret = __get_user_unaligned_unknown();				\
-	}											\
-	__ret;											\
-})
-
 #ifdef ASM_SUPPORTED
   struct __large_struct { unsigned long buf[100]; };
 # define __m(x) (*(struct __large_struct __user *)(x))
diff --git a/arch/m68k/include/asm/uaccess.h b/arch/m68k/include/asm/uaccess.h
index 67b3481d6020..63ba18e4c9a2 100644
--- a/arch/m68k/include/asm/uaccess.h
+++ b/arch/m68k/include/asm/uaccess.h
@@ -3,11 +3,4 @@
 #else
 #include <asm/uaccess_mm.h>
 #endif
-
 #include <asm/extable.h>
-#ifdef CONFIG_CPU_HAS_NO_UNALIGNED
-#include <asm-generic/uaccess-unaligned.h>
-#else
-#define __get_user_unaligned(x, ptr)	__get_user((x), (ptr))
-#define __put_user_unaligned(x, ptr)	__put_user((x), (ptr))
-#endif
diff --git a/arch/mips/include/asm/uaccess.h b/arch/mips/include/asm/uaccess.h
index 99e629a590a5..c5fc42429ce8 100644
--- a/arch/mips/include/asm/uaccess.h
+++ b/arch/mips/include/asm/uaccess.h
@@ -496,283 +496,6 @@ do {									\
 
 extern void __put_user_unknown(void);
 
-/*
- * ul{b,h,w} are macros and there are no equivalent macros for EVA.
- * EVA unaligned access is handled in the ADE exception handler.
- */
-#ifndef CONFIG_EVA
-/*
- * put_user_unaligned: - Write a simple value into user space.
- * @x:	 Value to copy to user space.
- * @ptr: Destination address, in user space.
- *
- * Context: User context only. This function may sleep if pagefaults are
- *          enabled.
- *
- * This macro copies a single simple value from kernel space to user
- * space.  It supports simple types like char and int, but not larger
- * data types like structures or arrays.
- *
- * @ptr must have pointer-to-simple-variable type, and @x must be assignable
- * to the result of dereferencing @ptr.
- *
- * Returns zero on success, or -EFAULT on error.
- */
-#define put_user_unaligned(x,ptr)	\
-	__put_user_unaligned_check((x),(ptr),sizeof(*(ptr)))
-
-/*
- * get_user_unaligned: - Get a simple variable from user space.
- * @x:	 Variable to store result.
- * @ptr: Source address, in user space.
- *
- * Context: User context only. This function may sleep if pagefaults are
- *          enabled.
- *
- * This macro copies a single simple variable from user space to kernel
- * space.  It supports simple types like char and int, but not larger
- * data types like structures or arrays.
- *
- * @ptr must have pointer-to-simple-variable type, and the result of
- * dereferencing @ptr must be assignable to @x without a cast.
- *
- * Returns zero on success, or -EFAULT on error.
- * On error, the variable @x is set to zero.
- */
-#define get_user_unaligned(x,ptr) \
-	__get_user_unaligned_check((x),(ptr),sizeof(*(ptr)))
-
-/*
- * __put_user_unaligned: - Write a simple value into user space, with less checking.
- * @x:	 Value to copy to user space.
- * @ptr: Destination address, in user space.
- *
- * Context: User context only. This function may sleep if pagefaults are
- *          enabled.
- *
- * This macro copies a single simple value from kernel space to user
- * space.  It supports simple types like char and int, but not larger
- * data types like structures or arrays.
- *
- * @ptr must have pointer-to-simple-variable type, and @x must be assignable
- * to the result of dereferencing @ptr.
- *
- * Caller must check the pointer with access_ok() before calling this
- * function.
- *
- * Returns zero on success, or -EFAULT on error.
- */
-#define __put_user_unaligned(x,ptr) \
-	__put_user_unaligned_nocheck((x),(ptr),sizeof(*(ptr)))
-
-/*
- * __get_user_unaligned: - Get a simple variable from user space, with less checking.
- * @x:	 Variable to store result.
- * @ptr: Source address, in user space.
- *
- * Context: User context only. This function may sleep if pagefaults are
- *          enabled.
- *
- * This macro copies a single simple variable from user space to kernel
- * space.  It supports simple types like char and int, but not larger
- * data types like structures or arrays.
- *
- * @ptr must have pointer-to-simple-variable type, and the result of
- * dereferencing @ptr must be assignable to @x without a cast.
- *
- * Caller must check the pointer with access_ok() before calling this
- * function.
- *
- * Returns zero on success, or -EFAULT on error.
- * On error, the variable @x is set to zero.
- */
-#define __get_user_unaligned(x,ptr) \
-	__get_user_unaligned_nocheck((x),(ptr),sizeof(*(ptr)))
-
-/*
- * Yuck.  We need two variants, one for 64bit operation and one
- * for 32 bit mode and old iron.
- */
-#ifdef CONFIG_32BIT
-#define __GET_USER_UNALIGNED_DW(val, ptr)				\
-	__get_user_unaligned_asm_ll32(val, ptr)
-#endif
-#ifdef CONFIG_64BIT
-#define __GET_USER_UNALIGNED_DW(val, ptr)				\
-	__get_user_unaligned_asm(val, "uld", ptr)
-#endif
-
-extern void __get_user_unaligned_unknown(void);
-
-#define __get_user_unaligned_common(val, size, ptr)			\
-do {									\
-	switch (size) {							\
-	case 1: __get_data_asm(val, "lb", ptr); break;			\
-	case 2: __get_data_unaligned_asm(val, "ulh", ptr); break;	\
-	case 4: __get_data_unaligned_asm(val, "ulw", ptr); break;	\
-	case 8: __GET_USER_UNALIGNED_DW(val, ptr); break;		\
-	default: __get_user_unaligned_unknown(); break;			\
-	}								\
-} while (0)
-
-#define __get_user_unaligned_nocheck(x,ptr,size)			\
-({									\
-	int __gu_err;							\
-									\
-	__get_user_unaligned_common((x), size, ptr);			\
-	__gu_err;							\
-})
-
-#define __get_user_unaligned_check(x,ptr,size)				\
-({									\
-	int __gu_err = -EFAULT;						\
-	const __typeof__(*(ptr)) __user * __gu_ptr = (ptr);		\
-									\
-	if (likely(access_ok(VERIFY_READ,  __gu_ptr, size)))		\
-		__get_user_unaligned_common((x), size, __gu_ptr);	\
-									\
-	__gu_err;							\
-})
-
-#define __get_data_unaligned_asm(val, insn, addr)			\
-{									\
-	long __gu_tmp;							\
-									\
-	__asm__ __volatile__(						\
-	"1:	" insn "	%1, %3				\n"	\
-	"2:							\n"	\
-	"	.insn						\n"	\
-	"	.section .fixup,\"ax\"				\n"	\
-	"3:	li	%0, %4					\n"	\
-	"	move	%1, $0					\n"	\
-	"	j	2b					\n"	\
-	"	.previous					\n"	\
-	"	.section __ex_table,\"a\"			\n"	\
-	"	"__UA_ADDR "\t1b, 3b				\n"	\
-	"	"__UA_ADDR "\t1b + 4, 3b			\n"	\
-	"	.previous					\n"	\
-	: "=r" (__gu_err), "=r" (__gu_tmp)				\
-	: "0" (0), "o" (__m(addr)), "i" (-EFAULT));			\
-									\
-	(val) = (__typeof__(*(addr))) __gu_tmp;				\
-}
-
-/*
- * Get a long long 64 using 32 bit registers.
- */
-#define __get_user_unaligned_asm_ll32(val, addr)			\
-{									\
-	unsigned long long __gu_tmp;					\
-									\
-	__asm__ __volatile__(						\
-	"1:	ulw	%1, (%3)				\n"	\
-	"2:	ulw	%D1, 4(%3)				\n"	\
-	"	move	%0, $0					\n"	\
-	"3:							\n"	\
-	"	.insn						\n"	\
-	"	.section	.fixup,\"ax\"			\n"	\
-	"4:	li	%0, %4					\n"	\
-	"	move	%1, $0					\n"	\
-	"	move	%D1, $0					\n"	\
-	"	j	3b					\n"	\
-	"	.previous					\n"	\
-	"	.section	__ex_table,\"a\"		\n"	\
-	"	" __UA_ADDR "	1b, 4b				\n"	\
-	"	" __UA_ADDR "	1b + 4, 4b			\n"	\
-	"	" __UA_ADDR "	2b, 4b				\n"	\
-	"	" __UA_ADDR "	2b + 4, 4b			\n"	\
-	"	.previous					\n"	\
-	: "=r" (__gu_err), "=&r" (__gu_tmp)				\
-	: "0" (0), "r" (addr), "i" (-EFAULT));				\
-	(val) = (__typeof__(*(addr))) __gu_tmp;				\
-}
-
-/*
- * Yuck.  We need two variants, one for 64bit operation and one
- * for 32 bit mode and old iron.
- */
-#ifdef CONFIG_32BIT
-#define __PUT_USER_UNALIGNED_DW(ptr) __put_user_unaligned_asm_ll32(ptr)
-#endif
-#ifdef CONFIG_64BIT
-#define __PUT_USER_UNALIGNED_DW(ptr) __put_user_unaligned_asm("usd", ptr)
-#endif
-
-#define __put_user_unaligned_common(ptr, size)				\
-do {									\
-	switch (size) {							\
-	case 1: __put_data_asm("sb", ptr); break;			\
-	case 2: __put_user_unaligned_asm("ush", ptr); break;		\
-	case 4: __put_user_unaligned_asm("usw", ptr); break;		\
-	case 8: __PUT_USER_UNALIGNED_DW(ptr); break;			\
-	default: __put_user_unaligned_unknown(); break;			\
-} while (0)
-
-#define __put_user_unaligned_nocheck(x,ptr,size)			\
-({									\
-	__typeof__(*(ptr)) __pu_val;					\
-	int __pu_err = 0;						\
-									\
-	__pu_val = (x);							\
-	__put_user_unaligned_common(ptr, size);				\
-	__pu_err;							\
-})
-
-#define __put_user_unaligned_check(x,ptr,size)				\
-({									\
-	__typeof__(*(ptr)) __user *__pu_addr = (ptr);			\
-	__typeof__(*(ptr)) __pu_val = (x);				\
-	int __pu_err = -EFAULT;						\
-									\
-	if (likely(access_ok(VERIFY_WRITE,  __pu_addr, size)))		\
-		__put_user_unaligned_common(__pu_addr, size);		\
-									\
-	__pu_err;							\
-})
-
-#define __put_user_unaligned_asm(insn, ptr)				\
-{									\
-	__asm__ __volatile__(						\
-	"1:	" insn "	%z2, %3		# __put_user_unaligned_asm\n" \
-	"2:							\n"	\
-	"	.insn						\n"	\
-	"	.section	.fixup,\"ax\"			\n"	\
-	"3:	li	%0, %4					\n"	\
-	"	j	2b					\n"	\
-	"	.previous					\n"	\
-	"	.section	__ex_table,\"a\"		\n"	\
-	"	" __UA_ADDR "	1b, 3b				\n"	\
-	"	.previous					\n"	\
-	: "=r" (__pu_err)						\
-	: "0" (0), "Jr" (__pu_val), "o" (__m(ptr)),			\
-	  "i" (-EFAULT));						\
-}
-
-#define __put_user_unaligned_asm_ll32(ptr)				\
-{									\
-	__asm__ __volatile__(						\
-	"1:	sw	%2, (%3)	# __put_user_unaligned_asm_ll32 \n" \
-	"2:	sw	%D2, 4(%3)				\n"	\
-	"3:							\n"	\
-	"	.insn						\n"	\
-	"	.section	.fixup,\"ax\"			\n"	\
-	"4:	li	%0, %4					\n"	\
-	"	j	3b					\n"	\
-	"	.previous					\n"	\
-	"	.section	__ex_table,\"a\"		\n"	\
-	"	" __UA_ADDR "	1b, 4b				\n"	\
-	"	" __UA_ADDR "	1b + 4, 4b			\n"	\
-	"	" __UA_ADDR "	2b, 4b				\n"	\
-	"	" __UA_ADDR "	2b + 4, 4b			\n"	\
-	"	.previous"						\
-	: "=r" (__pu_err)						\
-	: "0" (0), "r" (__pu_val), "r" (ptr),				\
-	  "i" (-EFAULT));						\
-}
-
-extern void __put_user_unaligned_unknown(void);
-#endif
-
 /*
  * We're generating jump to subroutines which will be outside the range of
  * jump instructions
diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h
index 6b113f39f30c..d24091e1907a 100644
--- a/arch/parisc/include/asm/uaccess.h
+++ b/arch/parisc/include/asm/uaccess.h
@@ -6,7 +6,6 @@
  */
 #include <asm/page.h>
 #include <asm/cache.h>
-#include <asm-generic/uaccess-unaligned.h>
 
 #include <linux/bug.h>
 #include <linux/string.h>
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index 5c0d8a8cdae5..9e7b08bbde5b 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -90,9 +90,6 @@
 #define __put_user_inatomic(x, ptr) \
 	__put_user_nosleep((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
 
-#define __get_user_unaligned __get_user
-#define __put_user_unaligned __put_user
-
 extern long __put_user_bad(void);
 
 /*
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index 78f3f093d143..fad9df965ec2 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -249,9 +249,6 @@ int __put_user_bad(void) __attribute__((noreturn));
 
 int __get_user_bad(void) __attribute__((noreturn));
 
-#define __put_user_unaligned __put_user
-#define __get_user_unaligned __get_user
-
 unsigned long __must_check
 raw_copy_in_user(void __user *to, const void __user *from, unsigned long n);
 
diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h
index 6096d671aa63..b5f976ee7510 100644
--- a/arch/sparc/include/asm/uaccess_64.h
+++ b/arch/sparc/include/asm/uaccess_64.h
@@ -9,7 +9,6 @@
 #include <linux/string.h>
 #include <asm/asi.h>
 #include <asm/spitfire.h>
-#include <asm-generic/uaccess-unaligned.h>
 #include <asm/extable_64.h>
 
 #include <asm/processor.h>
diff --git a/arch/tile/include/asm/uaccess.h b/arch/tile/include/asm/uaccess.h
index a803f6bb4d92..7f777411d1d6 100644
--- a/arch/tile/include/asm/uaccess.h
+++ b/arch/tile/include/asm/uaccess.h
@@ -19,7 +19,6 @@
  * User space memory access functions
  */
 #include <linux/mm.h>
-#include <asm-generic/uaccess-unaligned.h>
 #include <asm/processor.h>
 #include <asm/page.h>
 
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 68766b276d9e..fd91722315c8 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -535,9 +535,6 @@ struct __large_struct { unsigned long buf[100]; };
 #define __put_user(x, ptr)						\
 	__put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
 
-#define __get_user_unaligned __get_user
-#define __put_user_unaligned __put_user
-
 /*
  * {get|put}_user_try and catch
  *
diff --git a/include/asm-generic/uaccess-unaligned.h b/include/asm-generic/uaccess-unaligned.h
deleted file mode 100644
index 67deb898f0c5..000000000000
--- a/include/asm-generic/uaccess-unaligned.h
+++ /dev/null
@@ -1,26 +0,0 @@
-#ifndef __ASM_GENERIC_UACCESS_UNALIGNED_H
-#define __ASM_GENERIC_UACCESS_UNALIGNED_H
-
-/*
- * This macro should be used instead of __get_user() when accessing
- * values at locations that are not known to be aligned.
- */
-#define __get_user_unaligned(x, ptr)					\
-({									\
-	__typeof__ (*(ptr)) __x;					\
-	__copy_from_user(&__x, (ptr), sizeof(*(ptr))) ? -EFAULT : 0;	\
-	(x) = __x;							\
-})
-
-
-/*
- * This macro should be used instead of __put_user() when accessing
- * values at locations that are not known to be aligned.
- */
-#define __put_user_unaligned(x, ptr)					\
-({									\
-	__typeof__ (*(ptr)) __x = (x);					\
-	__copy_to_user((ptr), &__x, sizeof(*(ptr))) ? -EFAULT : 0;	\
-})
-
-#endif /* __ASM_GENERIC_UACCESS_UNALIGNED_H */
-- 
cgit v1.2.3


From fbd08e7673f950854679e5d79a30bb25e77a9d08 Mon Sep 17 00:00:00 2001
From: Dmitry Monakhov <dmonakhov@openvz.org>
Date: Thu, 29 Jun 2017 11:31:10 -0700
Subject: bio-integrity: fix interface for bio_integrity_trim

bio_integrity_trim inherent it's interface from bio_trim and accept
offset and size, but this API is error prone because data offset
must always be insync with bio's data offset. That is why we have
integrity update hook in bio_advance()

So only meaningful values are: offset == 0, sectors == bio_sectors(bio)
Let's just remove them completely.

Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio-integrity.c | 11 ++---------
 block/bio.c           |  4 ++--
 drivers/md/dm.c       |  2 +-
 include/linux/bio.h   |  5 ++---
 4 files changed, 7 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 8c2253c59edb..3a0d71199fb0 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -433,22 +433,15 @@ EXPORT_SYMBOL(bio_integrity_advance);
 /**
  * bio_integrity_trim - Trim integrity vector
  * @bio:	bio whose integrity vector to update
- * @offset:	offset to first data sector
- * @sectors:	number of data sectors
  *
  * Description: Used to trim the integrity vector in a cloned bio.
- * The ivec will be advanced corresponding to 'offset' data sectors
- * and the length will be truncated corresponding to 'len' data
- * sectors.
  */
-void bio_integrity_trim(struct bio *bio, unsigned int offset,
-			unsigned int sectors)
+void bio_integrity_trim(struct bio *bio)
 {
 	struct bio_integrity_payload *bip = bio_integrity(bio);
 	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
 
-	bio_integrity_advance(bio, offset << 9);
-	bip->bip_iter.bi_size = bio_integrity_bytes(bi, sectors);
+	bip->bip_iter.bi_size = bio_integrity_bytes(bi, bio_sectors(bio));
 }
 EXPORT_SYMBOL(bio_integrity_trim);
 
diff --git a/block/bio.c b/block/bio.c
index 5b4b32a2f8d0..a6b225324a61 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1868,7 +1868,7 @@ struct bio *bio_split(struct bio *bio, int sectors,
 	split->bi_iter.bi_size = sectors << 9;
 
 	if (bio_integrity(split))
-		bio_integrity_trim(split, 0, sectors);
+		bio_integrity_trim(split);
 
 	bio_advance(bio, split->bi_iter.bi_size);
 
@@ -1902,7 +1902,7 @@ void bio_trim(struct bio *bio, int offset, int size)
 	bio->bi_iter.bi_size = size;
 
 	if (bio_integrity(bio))
-		bio_integrity_trim(bio, 0, size);
+		bio_integrity_trim(bio);
 
 }
 EXPORT_SYMBOL_GPL(bio_trim);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 402946035308..13e714ea7a42 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1153,7 +1153,7 @@ static int clone_bio(struct dm_target_io *tio, struct bio *bio,
 	clone->bi_iter.bi_size = to_bytes(len);
 
 	if (unlikely(bio_integrity(bio) != NULL))
-		bio_integrity_trim(clone, 0, len);
+		bio_integrity_trim(clone);
 
 	return 0;
 }
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 664a27da276d..1d74f5120369 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -728,7 +728,7 @@ extern bool bio_integrity_enabled(struct bio *bio);
 extern int bio_integrity_prep(struct bio *);
 extern void bio_integrity_endio(struct bio *);
 extern void bio_integrity_advance(struct bio *, unsigned int);
-extern void bio_integrity_trim(struct bio *, unsigned int, unsigned int);
+extern void bio_integrity_trim(struct bio *);
 extern int bio_integrity_clone(struct bio *, struct bio *, gfp_t);
 extern int bioset_integrity_create(struct bio_set *, int);
 extern void bioset_integrity_free(struct bio_set *);
@@ -778,8 +778,7 @@ static inline void bio_integrity_advance(struct bio *bio,
 	return;
 }
 
-static inline void bio_integrity_trim(struct bio *bio, unsigned int offset,
-				      unsigned int sectors)
+static inline void bio_integrity_trim(struct bio *bio)
 {
 	return;
 }
-- 
cgit v1.2.3


From e23947bd76f00701f9407af23e671f4da96f5f25 Mon Sep 17 00:00:00 2001
From: Dmitry Monakhov <dmonakhov@openvz.org>
Date: Thu, 29 Jun 2017 11:31:11 -0700
Subject: bio-integrity: fold bio_integrity_enabled to bio_integrity_prep

Currently all integrity prep hooks are open-coded, and if prepare fails
we ignore it's code and fail bio with EIO. Let's return real error to
upper layer, so later caller may react accordingly.

In fact no one want to use bio_integrity_prep() w/o bio_integrity_enabled,
so it is reasonable to fold it in to one function.

Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
[hch: merged with the latest block tree,
	return bool from bio_integrity_prep]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 Documentation/block/data-integrity.txt |  6 +--
 block/bio-integrity.c                  | 88 +++++++++++++++-------------------
 block/blk-core.c                       |  5 +-
 block/blk-mq.c                         |  4 +-
 drivers/nvdimm/blk.c                   | 13 +----
 drivers/nvdimm/btt.c                   | 13 +----
 include/linux/bio.h                    | 12 ++---
 7 files changed, 50 insertions(+), 91 deletions(-)

(limited to 'include')

diff --git a/Documentation/block/data-integrity.txt b/Documentation/block/data-integrity.txt
index f56ec97f0d14..934c44ea0c57 100644
--- a/Documentation/block/data-integrity.txt
+++ b/Documentation/block/data-integrity.txt
@@ -192,7 +192,7 @@ will require extra work due to the application tag.
     supported by the block device.
 
 
-    int bio_integrity_prep(bio);
+    bool bio_integrity_prep(bio);
 
       To generate IMD for WRITE and to set up buffers for READ, the
       filesystem must call bio_integrity_prep(bio).
@@ -201,9 +201,7 @@ will require extra work due to the application tag.
       sector must be set, and the bio should have all data pages
       added.  It is up to the caller to ensure that the bio does not
       change while I/O is in progress.
-
-      bio_integrity_prep() should only be called if
-      bio_integrity_enabled() returned 1.
+      Complete bio with error if prepare failed for some reson.
 
 
 5.3 PASSING EXISTING INTEGRITY METADATA
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 3a0d71199fb0..44c4c52681c2 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -159,44 +159,6 @@ int bio_integrity_add_page(struct bio *bio, struct page *page,
 }
 EXPORT_SYMBOL(bio_integrity_add_page);
 
-/**
- * bio_integrity_enabled - Check whether integrity can be passed
- * @bio:	bio to check
- *
- * Description: Determines whether bio_integrity_prep() can be called
- * on this bio or not.	bio data direction and target device must be
- * set prior to calling.  The functions honors the write_generate and
- * read_verify flags in sysfs.
- */
-bool bio_integrity_enabled(struct bio *bio)
-{
-	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
-
-	if (bio_op(bio) != REQ_OP_READ && bio_op(bio) != REQ_OP_WRITE)
-		return false;
-
-	if (!bio_sectors(bio))
-		return false;
-
-	/* Already protected? */
-	if (bio_integrity(bio))
-		return false;
-
-	if (bi == NULL)
-		return false;
-
-	if (bio_data_dir(bio) == READ && bi->profile->verify_fn != NULL &&
-	    (bi->flags & BLK_INTEGRITY_VERIFY))
-		return true;
-
-	if (bio_data_dir(bio) == WRITE && bi->profile->generate_fn != NULL &&
-	    (bi->flags & BLK_INTEGRITY_GENERATE))
-		return true;
-
-	return false;
-}
-EXPORT_SYMBOL(bio_integrity_enabled);
-
 /**
  * bio_integrity_intervals - Return number of integrity intervals for a bio
  * @bi:		blk_integrity profile for device
@@ -262,14 +224,15 @@ static blk_status_t bio_integrity_process(struct bio *bio,
  * bio_integrity_prep - Prepare bio for integrity I/O
  * @bio:	bio to prepare
  *
- * Description: Allocates a buffer for integrity metadata, maps the
- * pages and attaches them to a bio.  The bio must have data
- * direction, target device and start sector set priot to calling.  In
- * the WRITE case, integrity metadata will be generated using the
- * block device's integrity function.  In the READ case, the buffer
+ * Description:  Checks if the bio already has an integrity payload attached.
+ * If it does, the payload has been generated by another kernel subsystem,
+ * and we just pass it through. Otherwise allocates integrity payload.
+ * The bio must have data direction, target device and start sector set priot
+ * to calling.  In the WRITE case, integrity metadata will be generated using
+ * the block device's integrity function.  In the READ case, the buffer
  * will be prepared for DMA and a suitable end_io handler set up.
  */
-int bio_integrity_prep(struct bio *bio)
+bool bio_integrity_prep(struct bio *bio)
 {
 	struct bio_integrity_payload *bip;
 	struct blk_integrity *bi;
@@ -279,20 +242,41 @@ int bio_integrity_prep(struct bio *bio)
 	unsigned int len, nr_pages;
 	unsigned int bytes, offset, i;
 	unsigned int intervals;
+	blk_status_t status;
 
 	bi = bdev_get_integrity(bio->bi_bdev);
 	q = bdev_get_queue(bio->bi_bdev);
-	BUG_ON(bi == NULL);
-	BUG_ON(bio_integrity(bio));
+	if (bio_op(bio) != REQ_OP_READ && bio_op(bio) != REQ_OP_WRITE)
+		return true;
+
+	if (!bio_sectors(bio))
+		return true;
 
+	/* Already protected? */
+	if (bio_integrity(bio))
+		return true;
+
+	if (bi == NULL)
+		return true;
+
+	if (bio_data_dir(bio) == READ) {
+		if (!bi->profile->verify_fn ||
+		    !(bi->flags & BLK_INTEGRITY_VERIFY))
+			return true;
+	} else {
+		if (!bi->profile->generate_fn ||
+		    !(bi->flags & BLK_INTEGRITY_GENERATE))
+			return true;
+	}
 	intervals = bio_integrity_intervals(bi, bio_sectors(bio));
 
 	/* Allocate kernel buffer for protection data */
 	len = intervals * bi->tuple_size;
 	buf = kmalloc(len, GFP_NOIO | q->bounce_gfp);
+	status = BLK_STS_RESOURCE;
 	if (unlikely(buf == NULL)) {
 		printk(KERN_ERR "could not allocate integrity buffer\n");
-		return -ENOMEM;
+		goto err_end_io;
 	}
 
 	end = (((unsigned long) buf) + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
@@ -304,7 +288,8 @@ int bio_integrity_prep(struct bio *bio)
 	if (IS_ERR(bip)) {
 		printk(KERN_ERR "could not allocate data integrity bioset\n");
 		kfree(buf);
-		return PTR_ERR(bip);
+		status = BLK_STS_RESOURCE;
+		goto err_end_io;
 	}
 
 	bip->bip_flags |= BIP_BLOCK_INTEGRITY;
@@ -349,8 +334,13 @@ int bio_integrity_prep(struct bio *bio)
 	/* Auto-generate integrity metadata if this is a write */
 	if (bio_data_dir(bio) == WRITE)
 		bio_integrity_process(bio, bi->profile->generate_fn);
+	return true;
+
+err_end_io:
+	bio->bi_status = status;
+	bio_endio(bio);
+	return false;
 
-	return 0;
 }
 EXPORT_SYMBOL(bio_integrity_prep);
 
diff --git a/block/blk-core.c b/block/blk-core.c
index af393d5a9680..970b9c9638c5 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1787,11 +1787,8 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 
 	blk_queue_split(q, &bio);
 
-	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
-		bio->bi_status = BLK_STS_IOERR;
-		bio_endio(bio);
+	if (!bio_integrity_prep(bio))
 		return BLK_QC_T_NONE;
-	}
 
 	if (op_is_flush(bio->bi_opf)) {
 		spin_lock_irq(q->queue_lock);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index ced2b000ca02..77617fb12661 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1550,10 +1550,8 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 
 	blk_queue_split(q, &bio);
 
-	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
-		bio_io_error(bio);
+	if (!bio_integrity_prep(bio))
 		return BLK_QC_T_NONE;
-	}
 
 	if (!is_flush_fua && !blk_queue_nomerges(q) &&
 	    blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq))
diff --git a/drivers/nvdimm/blk.c b/drivers/nvdimm/blk.c
index f12d23c49771..1a578b2a437b 100644
--- a/drivers/nvdimm/blk.c
+++ b/drivers/nvdimm/blk.c
@@ -179,16 +179,8 @@ static blk_qc_t nd_blk_make_request(struct request_queue *q, struct bio *bio)
 	int err = 0, rw;
 	bool do_acct;
 
-	/*
-	 * bio_integrity_enabled also checks if the bio already has an
-	 * integrity payload attached. If it does, we *don't* do a
-	 * bio_integrity_prep here - the payload has been generated by
-	 * another kernel subsystem, and we just pass it through.
-	 */
-	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
-		bio->bi_status = BLK_STS_IOERR;
-		goto out;
-	}
+	if (!bio_integrity_prep(bio))
+		return BLK_QC_T_NONE;
 
 	bip = bio_integrity(bio);
 	nsblk = q->queuedata;
@@ -212,7 +204,6 @@ static blk_qc_t nd_blk_make_request(struct request_queue *q, struct bio *bio)
 	if (do_acct)
 		nd_iostat_end(bio, start);
 
- out:
 	bio_endio(bio);
 	return BLK_QC_T_NONE;
 }
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index b6ba0618ea46..b5caaee78bbf 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -1203,16 +1203,8 @@ static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio)
 	int err = 0;
 	bool do_acct;
 
-	/*
-	 * bio_integrity_enabled also checks if the bio already has an
-	 * integrity payload attached. If it does, we *don't* do a
-	 * bio_integrity_prep here - the payload has been generated by
-	 * another kernel subsystem, and we just pass it through.
-	 */
-	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
-		bio->bi_status = BLK_STS_IOERR;
-		goto out;
-	}
+	if (!bio_integrity_prep(bio))
+		return BLK_QC_T_NONE;
 
 	do_acct = nd_iostat_start(bio, &start);
 	bio_for_each_segment(bvec, bio, iter) {
@@ -1239,7 +1231,6 @@ static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio)
 	if (do_acct)
 		nd_iostat_end(bio, start);
 
-out:
 	bio_endio(bio);
 	return BLK_QC_T_NONE;
 }
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 1d74f5120369..b3b5f5a89a9c 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -724,8 +724,7 @@ struct biovec_slab {
 extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, unsigned int);
 extern void bio_integrity_free(struct bio *);
 extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int);
-extern bool bio_integrity_enabled(struct bio *bio);
-extern int bio_integrity_prep(struct bio *);
+extern bool bio_integrity_prep(struct bio *);
 extern void bio_integrity_endio(struct bio *);
 extern void bio_integrity_advance(struct bio *, unsigned int);
 extern void bio_integrity_trim(struct bio *);
@@ -741,11 +740,6 @@ static inline void *bio_integrity(struct bio *bio)
 	return NULL;
 }
 
-static inline bool bio_integrity_enabled(struct bio *bio)
-{
-	return false;
-}
-
 static inline int bioset_integrity_create(struct bio_set *bs, int pool_size)
 {
 	return 0;
@@ -756,9 +750,9 @@ static inline void bioset_integrity_free (struct bio_set *bs)
 	return;
 }
 
-static inline int bio_integrity_prep(struct bio *bio)
+static inline bool bio_integrity_prep(struct bio *bio)
 {
-	return 0;
+	return true;
 }
 
 static inline void bio_integrity_free(struct bio *bio)
-- 
cgit v1.2.3


From 128b6f9fdd9ace9e56cb3a263b4bc269658f9c40 Mon Sep 17 00:00:00 2001
From: Dmitry Monakhov <dmonakhov@openvz.org>
Date: Thu, 29 Jun 2017 11:31:12 -0700
Subject: t10-pi: Move opencoded contants to common header

Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/t10-pi.c                   | 9 +++------
 drivers/scsi/lpfc/lpfc_scsi.c    | 5 +++--
 drivers/scsi/qla2xxx/qla_isr.c   | 8 ++++----
 drivers/target/target_core_sbc.c | 2 +-
 include/linux/t10-pi.h           | 2 ++
 5 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/block/t10-pi.c b/block/t10-pi.c
index 3416dadf7b15..a98db384048f 100644
--- a/block/t10-pi.c
+++ b/block/t10-pi.c
@@ -28,9 +28,6 @@
 
 typedef __be16 (csum_fn) (void *, unsigned int);
 
-static const __be16 APP_ESCAPE = (__force __be16) 0xffff;
-static const __be32 REF_ESCAPE = (__force __be32) 0xffffffff;
-
 static __be16 t10_pi_crc_fn(void *data, unsigned int len)
 {
 	return cpu_to_be16(crc_t10dif(data, len));
@@ -82,7 +79,7 @@ static blk_status_t t10_pi_verify(struct blk_integrity_iter *iter,
 		switch (type) {
 		case 1:
 		case 2:
-			if (pi->app_tag == APP_ESCAPE)
+			if (pi->app_tag == T10_PI_APP_ESCAPE)
 				goto next;
 
 			if (be32_to_cpu(pi->ref_tag) !=
@@ -95,8 +92,8 @@ static blk_status_t t10_pi_verify(struct blk_integrity_iter *iter,
 			}
 			break;
 		case 3:
-			if (pi->app_tag == APP_ESCAPE &&
-			    pi->ref_tag == REF_ESCAPE)
+			if (pi->app_tag == T10_PI_APP_ESCAPE &&
+			    pi->ref_tag == T10_PI_REF_ESCAPE)
 				goto next;
 			break;
 		}
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index 54fd0c81ceaf..99d2e990b231 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -26,6 +26,7 @@
 #include <linux/export.h>
 #include <linux/delay.h>
 #include <asm/unaligned.h>
+#include <linux/t10-pi.h>
 #include <linux/crc-t10dif.h>
 #include <net/checksum.h>
 
@@ -2934,8 +2935,8 @@ lpfc_calc_bg_err(struct lpfc_hba *phba, struct lpfc_scsi_buf *lpfc_cmd)
 				 * First check to see if a protection data
 				 * check is valid
 				 */
-				if ((src->ref_tag == 0xffffffff) ||
-				    (src->app_tag == 0xffff)) {
+				if ((src->ref_tag == T10_PI_REF_ESCAPE) ||
+				    (src->app_tag == T10_PI_APP_ESCAPE)) {
 					start_ref_tag++;
 					goto skipit;
 				}
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 2572121b765b..de031aed94f6 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -1950,9 +1950,9 @@ qla2x00_handle_dif_error(srb_t *sp, struct sts_entry_24xx *sts24)
 	 * For type     3: ref & app tag is all 'f's
 	 * For type 0,1,2: app tag is all 'f's
 	 */
-	if ((a_app_tag == 0xffff) &&
+	if ((a_app_tag == T10_PI_APP_ESCAPE) &&
 	    ((scsi_get_prot_type(cmd) != SCSI_PROT_DIF_TYPE3) ||
-	     (a_ref_tag == 0xffffffff))) {
+	     (a_ref_tag == T10_PI_REF_ESCAPE))) {
 		uint32_t blocks_done, resid;
 		sector_t lba_s = scsi_get_lba(cmd);
 
@@ -1994,9 +1994,9 @@ qla2x00_handle_dif_error(srb_t *sp, struct sts_entry_24xx *sts24)
 			spt = page_address(sg_page(sg)) + sg->offset;
 			spt += j;
 
-			spt->app_tag = 0xffff;
+			spt->app_tag = T10_PI_APP_ESCAPE;
 			if (scsi_get_prot_type(cmd) == SCSI_PROT_DIF_TYPE3)
-				spt->ref_tag = 0xffffffff;
+				spt->ref_tag = T10_PI_REF_ESCAPE;
 		}
 
 		return 0;
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index 4316f7b65fb7..dc9456e7dac9 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -1450,7 +1450,7 @@ sbc_dif_verify(struct se_cmd *cmd, sector_t start, unsigned int sectors,
 				 (unsigned long long)sector, sdt->guard_tag,
 				 sdt->app_tag, be32_to_cpu(sdt->ref_tag));
 
-			if (sdt->app_tag == cpu_to_be16(0xffff)) {
+			if (sdt->app_tag == T10_PI_APP_ESCAPE) {
 				dsg_off += block_size;
 				goto next;
 			}
diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h
index 9375d23a24e7..635a3c5706bd 100644
--- a/include/linux/t10-pi.h
+++ b/include/linux/t10-pi.h
@@ -33,6 +33,8 @@ struct t10_pi_tuple {
 	__be32 ref_tag;		/* Target LBA or indirect LBA */
 };
 
+#define T10_PI_APP_ESCAPE cpu_to_be16(0xffff)
+#define T10_PI_REF_ESCAPE cpu_to_be32(0xffffffff)
 
 extern const struct blk_integrity_profile t10_pi_type1_crc;
 extern const struct blk_integrity_profile t10_pi_type1_ip;
-- 
cgit v1.2.3


From b1fb2c52b2d85f51f36f1661409f9aeef94265ff Mon Sep 17 00:00:00 2001
From: Dmitry Monakhov <dmonakhov@openvz.org>
Date: Thu, 29 Jun 2017 11:31:13 -0700
Subject: block: guard bvec iteration logic

Currently if some one try to advance bvec beyond it's size we simply
dump WARN_ONCE and continue to iterate beyond bvec array boundaries.
This simply means that we endup dereferencing/corrupting random memory
region.

Sane reaction would be to propagate error back to calling context
But bvec_iter_advance's calling context is not always good for error
handling. For safity reason let truncate iterator size to zero which
will break external iteration loop which prevent us from unpredictable
memory range corruption. And even it caller ignores an error, it will
corrupt it's own bvecs, not others.

This patch does:
- Return error back to caller with hope that it will react on this
- Truncate iterator size

Code was added long time ago here 4550dd6c, luckily no one hit it
in real life :)

Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
[hch: switch to true/false returns instead of errno values]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/nvdimm/blk.c |  3 ++-
 drivers/nvdimm/btt.c |  3 ++-
 include/linux/bio.h  |  4 +++-
 include/linux/bvec.h | 14 +++++++++-----
 4 files changed, 16 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/nvdimm/blk.c b/drivers/nvdimm/blk.c
index 1a578b2a437b..345acca576b3 100644
--- a/drivers/nvdimm/blk.c
+++ b/drivers/nvdimm/blk.c
@@ -106,7 +106,8 @@ static int nd_blk_rw_integrity(struct nd_namespace_blk *nsblk,
 
 		len -= cur_len;
 		dev_offset += cur_len;
-		bvec_iter_advance(bip->bip_vec, &bip->bip_iter, cur_len);
+		if (!bvec_iter_advance(bip->bip_vec, &bip->bip_iter, cur_len))
+			return -EIO;
 	}
 
 	return err;
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index b5caaee78bbf..d00c10f382f0 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -985,7 +985,8 @@ static int btt_rw_integrity(struct btt *btt, struct bio_integrity_payload *bip,
 
 		len -= cur_len;
 		meta_nsoff += cur_len;
-		bvec_iter_advance(bip->bip_vec, &bip->bip_iter, cur_len);
+		if (!bvec_iter_advance(bip->bip_vec, &bip->bip_iter, cur_len))
+			return -EIO;
 	}
 
 	return ret;
diff --git a/include/linux/bio.h b/include/linux/bio.h
index b3b5f5a89a9c..d5e8689f86b8 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -167,8 +167,10 @@ static inline void bio_advance_iter(struct bio *bio, struct bvec_iter *iter,
 
 	if (bio_no_advance_iter(bio))
 		iter->bi_size -= bytes;
-	else
+	else {
 		bvec_iter_advance(bio->bi_io_vec, iter, bytes);
+		/* TODO: It is reasonable to complete bio with error here. */
+	}
 }
 
 #define __bio_for_each_segment(bvl, bio, iter, start)			\
diff --git a/include/linux/bvec.h b/include/linux/bvec.h
index 89b65b82d98f..de317b4c13c1 100644
--- a/include/linux/bvec.h
+++ b/include/linux/bvec.h
@@ -22,6 +22,7 @@
 
 #include <linux/kernel.h>
 #include <linux/bug.h>
+#include <linux/errno.h>
 
 /*
  * was unsigned short, but we might as well be ready for > 64kB I/O pages
@@ -66,12 +67,14 @@ struct bvec_iter {
 	.bv_offset	= bvec_iter_offset((bvec), (iter)),	\
 })
 
-static inline void bvec_iter_advance(const struct bio_vec *bv,
-				     struct bvec_iter *iter,
-				     unsigned bytes)
+static inline bool bvec_iter_advance(const struct bio_vec *bv,
+		struct bvec_iter *iter, unsigned bytes)
 {
-	WARN_ONCE(bytes > iter->bi_size,
-		  "Attempted to advance past end of bvec iter\n");
+	if (WARN_ONCE(bytes > iter->bi_size,
+		     "Attempted to advance past end of bvec iter\n")) {
+		iter->bi_size = 0;
+		return false;
+	}
 
 	while (bytes) {
 		unsigned iter_len = bvec_iter_len(bv, *iter);
@@ -86,6 +89,7 @@ static inline void bvec_iter_advance(const struct bio_vec *bv,
 			iter->bi_idx++;
 		}
 	}
+	return true;
 }
 
 #define for_each_bvec(bvl, bio_vec, iter, start)			\
-- 
cgit v1.2.3


From f9df1cd99ebd82f05e8f5e0aa7e38cb8d3c791d7 Mon Sep 17 00:00:00 2001
From: Dmitry Monakhov <dmonakhov@openvz.org>
Date: Thu, 29 Jun 2017 11:31:14 -0700
Subject: bio: add bvec_iter rewind API

Some ->bi_end_io handlers (for example: pi_verify or decrypt handlers)
need to know original data vector, but after bio traverse io-stack it may
be advanced, splited and relocated many times so it is hard to guess
original iterator. Let's add 'bi_done' conter which accounts number
of bytes iterator was advanced during it's evolution. Later end_io handler
may easily restore original iterator by rewinding iterator to
iter->bi_done.

Note: this change makes sizeof (struct bvec_iter) multiple to 8

Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
[hch: switched to true/false return]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/bio.h  | 19 +++++++++++++++++--
 include/linux/bvec.h | 27 +++++++++++++++++++++++++++
 2 files changed, 44 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/bio.h b/include/linux/bio.h
index d5e8689f86b8..1eba19580185 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -165,14 +165,29 @@ static inline void bio_advance_iter(struct bio *bio, struct bvec_iter *iter,
 {
 	iter->bi_sector += bytes >> 9;
 
-	if (bio_no_advance_iter(bio))
+	if (bio_no_advance_iter(bio)) {
 		iter->bi_size -= bytes;
-	else {
+		iter->bi_done += bytes;
+	} else {
 		bvec_iter_advance(bio->bi_io_vec, iter, bytes);
 		/* TODO: It is reasonable to complete bio with error here. */
 	}
 }
 
+static inline bool bio_rewind_iter(struct bio *bio, struct bvec_iter *iter,
+		unsigned int bytes)
+{
+	iter->bi_sector -= bytes >> 9;
+
+	if (bio_no_advance_iter(bio)) {
+		iter->bi_size += bytes;
+		iter->bi_done -= bytes;
+		return true;
+	}
+
+	return bvec_iter_rewind(bio->bi_io_vec, iter, bytes);
+}
+
 #define __bio_for_each_segment(bvl, bio, iter, start)			\
 	for (iter = (start);						\
 	     (iter).bi_size &&						\
diff --git a/include/linux/bvec.h b/include/linux/bvec.h
index de317b4c13c1..ec8a4d7af6bd 100644
--- a/include/linux/bvec.h
+++ b/include/linux/bvec.h
@@ -40,6 +40,8 @@ struct bvec_iter {
 
 	unsigned int		bi_idx;		/* current index into bvl_vec */
 
+	unsigned int            bi_done;	/* number of bytes completed */
+
 	unsigned int            bi_bvec_done;	/* number of bytes completed in
 						   current bvec */
 };
@@ -83,6 +85,7 @@ static inline bool bvec_iter_advance(const struct bio_vec *bv,
 		bytes -= len;
 		iter->bi_size -= len;
 		iter->bi_bvec_done += len;
+		iter->bi_done += len;
 
 		if (iter->bi_bvec_done == __bvec_iter_bvec(bv, *iter)->bv_len) {
 			iter->bi_bvec_done = 0;
@@ -92,6 +95,30 @@ static inline bool bvec_iter_advance(const struct bio_vec *bv,
 	return true;
 }
 
+static inline bool bvec_iter_rewind(const struct bio_vec *bv,
+				     struct bvec_iter *iter,
+				     unsigned int bytes)
+{
+	while (bytes) {
+		unsigned len = min(bytes, iter->bi_bvec_done);
+
+		if (iter->bi_bvec_done == 0) {
+			if (WARN_ONCE(iter->bi_idx == 0,
+				      "Attempted to rewind iter beyond "
+				      "bvec's boundaries\n")) {
+				return false;
+			}
+			iter->bi_idx--;
+			iter->bi_bvec_done = __bvec_iter_bvec(bv, *iter)->bv_len;
+			continue;
+		}
+		bytes -= len;
+		iter->bi_size += len;
+		iter->bi_bvec_done -= len;
+	}
+	return true;
+}
+
 #define for_each_bvec(bvl, bio_vec, iter, start)			\
 	for (iter = (start);						\
 	     (iter).bi_size &&						\
-- 
cgit v1.2.3


From 7c20f11680a441df09de7235206f70115fbf6290 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 3 Jul 2017 16:58:43 -0600
Subject: bio-integrity: stop abusing bi_end_io

And instead call directly into the integrity code from bio_end_io.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio-integrity.c | 39 ++++++++++++---------------------------
 block/bio.c           |  5 ++---
 block/blk.h           | 11 +++++++++++
 include/linux/bio.h   |  9 ---------
 4 files changed, 25 insertions(+), 39 deletions(-)

(limited to 'include')

diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 8df4eb103ba9..f733beab6ca2 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -102,7 +102,7 @@ EXPORT_SYMBOL(bio_integrity_alloc);
  * Description: Used to free the integrity portion of a bio. Usually
  * called from bio_free().
  */
-void bio_integrity_free(struct bio *bio)
+static void bio_integrity_free(struct bio *bio)
 {
 	struct bio_integrity_payload *bip = bio_integrity(bio);
 	struct bio_set *bs = bio->bi_pool;
@@ -120,8 +120,8 @@ void bio_integrity_free(struct bio *bio)
 	}
 
 	bio->bi_integrity = NULL;
+	bio->bi_opf &= ~REQ_INTEGRITY;
 }
-EXPORT_SYMBOL(bio_integrity_free);
 
 /**
  * bio_integrity_add_page - Attach integrity metadata
@@ -326,12 +326,6 @@ bool bio_integrity_prep(struct bio *bio)
 		offset = 0;
 	}
 
-	/* Install custom I/O completion handler if read verify is enabled */
-	if (bio_data_dir(bio) == READ) {
-		bip->bip_end_io = bio->bi_end_io;
-		bio->bi_end_io = bio_integrity_endio;
-	}
-
 	/* Auto-generate integrity metadata if this is a write */
 	if (bio_data_dir(bio) == WRITE) {
 		bio_integrity_process(bio, &bio->bi_iter,
@@ -375,13 +369,12 @@ static void bio_integrity_verify_fn(struct work_struct *work)
 		bio->bi_status = BLK_STS_IOERR;
 	}
 
-	/* Restore original bio completion handler */
-	bio->bi_end_io = bip->bip_end_io;
+	bio_integrity_free(bio);
 	bio_endio(bio);
 }
 
 /**
- * bio_integrity_endio - Integrity I/O completion function
+ * __bio_integrity_endio - Integrity I/O completion function
  * @bio:	Protected bio
  * @error:	Pointer to errno
  *
@@ -392,27 +385,19 @@ static void bio_integrity_verify_fn(struct work_struct *work)
  * in process context.	This function postpones completion
  * accordingly.
  */
-void bio_integrity_endio(struct bio *bio)
+bool __bio_integrity_endio(struct bio *bio)
 {
-	struct bio_integrity_payload *bip = bio_integrity(bio);
+	if (bio_op(bio) == REQ_OP_READ && !bio->bi_status) {
+		struct bio_integrity_payload *bip = bio_integrity(bio);
 
-	BUG_ON(bip->bip_bio != bio);
-
-	/* In case of an I/O error there is no point in verifying the
-	 * integrity metadata.  Restore original bio end_io handler
-	 * and run it.
-	 */
-	if (bio->bi_status) {
-		bio->bi_end_io = bip->bip_end_io;
-		bio_endio(bio);
-
-		return;
+		INIT_WORK(&bip->bip_work, bio_integrity_verify_fn);
+		queue_work(kintegrityd_wq, &bip->bip_work);
+		return false;
 	}
 
-	INIT_WORK(&bip->bip_work, bio_integrity_verify_fn);
-	queue_work(kintegrityd_wq, &bip->bip_work);
+	bio_integrity_free(bio);
+	return true;
 }
-EXPORT_SYMBOL(bio_integrity_endio);
 
 /**
  * bio_integrity_advance - Advance integrity vector
diff --git a/block/bio.c b/block/bio.c
index a6b225324a61..9cabf5d0be20 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -243,9 +243,6 @@ fallback:
 void bio_uninit(struct bio *bio)
 {
 	bio_disassociate_task(bio);
-
-	if (bio_integrity(bio))
-		bio_integrity_free(bio);
 }
 EXPORT_SYMBOL(bio_uninit);
 
@@ -1813,6 +1810,8 @@ void bio_endio(struct bio *bio)
 again:
 	if (!bio_remaining_done(bio))
 		return;
+	if (!bio_integrity_endio(bio))
+		return;
 
 	/*
 	 * Need to have a real endio function for chained bios, otherwise
diff --git a/block/blk.h b/block/blk.h
index 01ebb8185f6b..3a3d715bd725 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -81,10 +81,21 @@ static inline void blk_queue_enter_live(struct request_queue *q)
 
 #ifdef CONFIG_BLK_DEV_INTEGRITY
 void blk_flush_integrity(void);
+bool __bio_integrity_endio(struct bio *);
+static inline bool bio_integrity_endio(struct bio *bio)
+{
+	if (bio_integrity(bio))
+		return __bio_integrity_endio(bio);
+	return true;
+}
 #else
 static inline void blk_flush_integrity(void)
 {
 }
+static inline bool bio_integrity_endio(struct bio *bio)
+{
+	return true;
+}
 #endif
 
 void blk_timeout_work(struct work_struct *work);
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 1eba19580185..7b1cf4ba0902 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -320,8 +320,6 @@ struct bio_integrity_payload {
 
 	struct bvec_iter	bip_iter;
 
-	bio_end_io_t		*bip_end_io;	/* saved I/O completion fn */
-
 	unsigned short		bip_slab;	/* slab the bip came from */
 	unsigned short		bip_vcnt;	/* # of integrity bio_vecs */
 	unsigned short		bip_max_vcnt;	/* integrity bio_vec slots */
@@ -739,10 +737,8 @@ struct biovec_slab {
 		bip_for_each_vec(_bvl, _bio->bi_integrity, _iter)
 
 extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, unsigned int);
-extern void bio_integrity_free(struct bio *);
 extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int);
 extern bool bio_integrity_prep(struct bio *);
-extern void bio_integrity_endio(struct bio *);
 extern void bio_integrity_advance(struct bio *, unsigned int);
 extern void bio_integrity_trim(struct bio *);
 extern int bio_integrity_clone(struct bio *, struct bio *, gfp_t);
@@ -772,11 +768,6 @@ static inline bool bio_integrity_prep(struct bio *bio)
 	return true;
 }
 
-static inline void bio_integrity_free(struct bio *bio)
-{
-	return;
-}
-
 static inline int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
 				      gfp_t gfp_mask)
 {
-- 
cgit v1.2.3


From 2bece49394872d36bbc5767fd643deac05920c55 Mon Sep 17 00:00:00 2001
From: Loc Ho <lho@apm.com>
Date: Mon, 3 Jul 2017 14:33:08 -0700
Subject: ACPI: SPCR: Use access width to determine mmio usage

The current SPCR code does not check the access width of the MMIO, and
uses a default of 8bit register accesses.  This prevents devices that
only do 16 or 32bit register accesses from working.  By simply checking
this field and setting the MMIO string appropriately, this issue can be
corrected.  To prevent any legacy issues, the code will default to 8bit
accesses if the value is anything but 16 or 32.

Signed-off-by: Jon Mason <jon.mason@broadcom.com>
Signed-off-by: Loc Ho <lho@apm.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/spcr.c     | 18 ++++++++++++++++--
 include/acpi/acrestyp.h |  7 +++++++
 2 files changed, 23 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/spcr.c b/drivers/acpi/spcr.c
index 3afa8c1fa127..29050630f3da 100644
--- a/drivers/acpi/spcr.c
+++ b/drivers/acpi/spcr.c
@@ -74,8 +74,22 @@ int __init parse_spcr(bool earlycon)
 		goto done;
 	}
 
-	iotype = table->serial_port.space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY ?
-			"mmio" : "io";
+	if (table->serial_port.space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) {
+		switch (table->serial_port.access_width) {
+		default:
+			pr_err("Unexpected SPCR Access Width.  Defaulting to byte size\n");
+		case ACPI_ACCESS_SIZE_BYTE:
+			iotype = "mmio";
+			break;
+		case ACPI_ACCESS_SIZE_WORD:
+			iotype = "mmio16";
+			break;
+		case ACPI_ACCESS_SIZE_DWORD:
+			iotype = "mmio32";
+			break;
+		}
+	} else
+		iotype = "io";
 
 	switch (table->interface_type) {
 	case ACPI_DBG2_ARM_SBSA_32BIT:
diff --git a/include/acpi/acrestyp.h b/include/acpi/acrestyp.h
index f0f7403d2000..781cb555c960 100644
--- a/include/acpi/acrestyp.h
+++ b/include/acpi/acrestyp.h
@@ -372,6 +372,13 @@ struct acpi_resource_generic_register {
 	u64 address;
 };
 
+/* Generic Address Space Access Sizes */
+#define ACPI_ACCESS_SIZE_UNDEFINED		0
+#define ACPI_ACCESS_SIZE_BYTE			1
+#define ACPI_ACCESS_SIZE_WORD			2
+#define ACPI_ACCESS_SIZE_DWORD			3
+#define ACPI_ACCESS_SIZE_QWORD			4
+
 struct acpi_resource_gpio {
 	u8 revision_id;
 	u8 connection_type;
-- 
cgit v1.2.3


From ad0af7104dadccd55cd2b390271677fac142650f Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Wed, 21 Jun 2017 15:28:32 +0300
Subject: vfs: introduce inode 'inuse' lock

Added an i_state flag I_INUSE and helpers to set/clear/test the bit.

The 'inuse' lock is an 'advisory' inode lock, that can be used to extend
exclusive create protection beyond parent->i_mutex lock among cooperating
users.

This is going to be used by overlayfs to get exclusive ownership on upper
and work dirs among overlayfs mounts.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/overlayfs/overlayfs.h |  2 ++
 fs/overlayfs/util.c      | 31 +++++++++++++++++++++++++++++++
 include/linux/fs.h       |  4 ++++
 3 files changed, 37 insertions(+)

(limited to 'include')

diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index b1be3d39ac9d..5e958427463d 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -220,6 +220,8 @@ int ovl_check_setxattr(struct dentry *dentry, struct dentry *upperdentry,
 int ovl_set_impure(struct dentry *dentry, struct dentry *upperdentry);
 void ovl_set_flag(unsigned long flag, struct inode *inode);
 bool ovl_test_flag(unsigned long flag, struct inode *inode);
+bool ovl_inuse_trylock(struct dentry *dentry);
+void ovl_inuse_unlock(struct dentry *dentry);
 
 static inline bool ovl_is_impuredir(struct dentry *dentry)
 {
diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index f093fcf2b4bd..adccd74162d6 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -347,3 +347,34 @@ bool ovl_test_flag(unsigned long flag, struct inode *inode)
 {
 	return test_bit(flag, &OVL_I(inode)->flags);
 }
+
+/**
+ * Caller must hold a reference to inode to prevent it from being freed while
+ * it is marked inuse.
+ */
+bool ovl_inuse_trylock(struct dentry *dentry)
+{
+	struct inode *inode = d_inode(dentry);
+	bool locked = false;
+
+	spin_lock(&inode->i_lock);
+	if (!(inode->i_state & I_OVL_INUSE)) {
+		inode->i_state |= I_OVL_INUSE;
+		locked = true;
+	}
+	spin_unlock(&inode->i_lock);
+
+	return locked;
+}
+
+void ovl_inuse_unlock(struct dentry *dentry)
+{
+	if (dentry) {
+		struct inode *inode = d_inode(dentry);
+
+		spin_lock(&inode->i_lock);
+		WARN_ON(!(inode->i_state & I_OVL_INUSE));
+		inode->i_state &= ~I_OVL_INUSE;
+		spin_unlock(&inode->i_lock);
+	}
+}
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 3e68cabb8457..75a5fafaf096 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1930,6 +1930,9 @@ static inline bool HAS_UNMAPPED_ID(struct inode *inode)
  *			wb stat updates to grab mapping->tree_lock.  See
  *			inode_switch_wb_work_fn() for details.
  *
+ * I_OVL_INUSE		Used by overlayfs to get exclusive ownership on upper
+ *			and work dirs among overlayfs mounts.
+ *
  * Q: What is the difference between I_WILL_FREE and I_FREEING?
  */
 #define I_DIRTY_SYNC		(1 << 0)
@@ -1950,6 +1953,7 @@ static inline bool HAS_UNMAPPED_ID(struct inode *inode)
 #define __I_DIRTY_TIME_EXPIRED	12
 #define I_DIRTY_TIME_EXPIRED	(1 << __I_DIRTY_TIME_EXPIRED)
 #define I_WB_SWITCH		(1 << 13)
+#define I_OVL_INUSE			(1 << 14)
 
 #define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES)
 #define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME)
-- 
cgit v1.2.3


From f35157417215ec138c920320c746fdb3e04ef1d5 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 4 Jul 2017 17:25:02 +0100
Subject: Provide a function to create a NUL-terminated string from
 unterminated data

Provide a function, kmemdup_nul(), that will create a NUL-terminated string
from an unterminated character array where the length is known in advance.

This is better than kstrndup() in situations where we already know the
string length as the strnlen() in kstrndup() is superfluous.

Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/string.h |  1 +
 mm/util.c              | 24 ++++++++++++++++++++++++
 2 files changed, 25 insertions(+)

(limited to 'include')

diff --git a/include/linux/string.h b/include/linux/string.h
index 537918f8a98e..3dd944cfe171 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -131,6 +131,7 @@ extern char *kstrdup(const char *s, gfp_t gfp) __malloc;
 extern const char *kstrdup_const(const char *s, gfp_t gfp);
 extern char *kstrndup(const char *s, size_t len, gfp_t gfp);
 extern void *kmemdup(const void *src, size_t len, gfp_t gfp);
+extern char *kmemdup_nul(const char *s, size_t len, gfp_t gfp);
 
 extern char **argv_split(gfp_t gfp, const char *str, int *argcp);
 extern void argv_free(char **argv);
diff --git a/mm/util.c b/mm/util.c
index 26be6407abd7..21ddf90f883d 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -83,6 +83,8 @@ EXPORT_SYMBOL(kstrdup_const);
  * @s: the string to duplicate
  * @max: read at most @max chars from @s
  * @gfp: the GFP mask used in the kmalloc() call when allocating memory
+ *
+ * Note: Use kmemdup_nul() instead if the size is known exactly.
  */
 char *kstrndup(const char *s, size_t max, gfp_t gfp)
 {
@@ -120,6 +122,28 @@ void *kmemdup(const void *src, size_t len, gfp_t gfp)
 }
 EXPORT_SYMBOL(kmemdup);
 
+/**
+ * kmemdup_nul - Create a NUL-terminated string from unterminated data
+ * @s: The data to stringify
+ * @len: The size of the data
+ * @gfp: the GFP mask used in the kmalloc() call when allocating memory
+ */
+char *kmemdup_nul(const char *s, size_t len, gfp_t gfp)
+{
+	char *buf;
+
+	if (!s)
+		return NULL;
+
+	buf = kmalloc_track_caller(len + 1, gfp);
+	if (buf) {
+		memcpy(buf, s, len);
+		buf[len] = '\0';
+	}
+	return buf;
+}
+EXPORT_SYMBOL(kmemdup_nul);
+
 /**
  * memdup_user - duplicate memory region from user space
  *
-- 
cgit v1.2.3


From ee416bcdba9975065de571e09de1f7ebfde2156a Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 4 Jul 2017 17:25:16 +0100
Subject: VFS: Make get_filesystem() return the affected filesystem

Make get_filesystem() return a pointer to the filesystem on which it just
got a ref.

Suggested-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/filesystems.c   | 3 ++-
 include/linux/fs.h | 2 +-
 2 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/fs/filesystems.c b/fs/filesystems.c
index cac75547d35c..591e52d23ed4 100644
--- a/fs/filesystems.c
+++ b/fs/filesystems.c
@@ -33,9 +33,10 @@ static struct file_system_type *file_systems;
 static DEFINE_RWLOCK(file_systems_lock);
 
 /* WARNING: This can be used only if we _already_ own a reference */
-void get_filesystem(struct file_system_type *fs)
+struct file_system_type *get_filesystem(struct file_system_type *fs)
 {
 	__module_get(fs->owner);
+	return fs;
 }
 
 void put_filesystem(struct file_system_type *fs)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 803e5a9b2654..bc0c054894b9 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2956,7 +2956,7 @@ extern int generic_block_fiemap(struct inode *inode,
 				struct fiemap_extent_info *fieinfo, u64 start,
 				u64 len, get_block_t *get_block);
 
-extern void get_filesystem(struct file_system_type *fs);
+extern struct file_system_type *get_filesystem(struct file_system_type *fs);
 extern void put_filesystem(struct file_system_type *fs);
 extern struct file_system_type *get_fs_type(const char *name);
 extern struct super_block *get_super(struct block_device *);
-- 
cgit v1.2.3


From cdf01226b26e98c79c13b335fbe0cbbbe850cf44 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 4 Jul 2017 17:25:22 +0100
Subject: VFS: Provide empty name qstr

Provide an empty name (ie. "") qstr for general use.

Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/dcache.c            | 8 ++++++--
 fs/gfs2/dir.c          | 3 +--
 fs/namei.c             | 3 +--
 fs/nsfs.c              | 3 +--
 fs/pipe.c              | 3 +--
 include/linux/dcache.h | 5 +++++
 6 files changed, 15 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/fs/dcache.c b/fs/dcache.c
index a9f995f6859e..95efb7b2bf84 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -90,6 +90,11 @@ EXPORT_SYMBOL(rename_lock);
 
 static struct kmem_cache *dentry_cache __read_mostly;
 
+const struct qstr empty_name = QSTR_INIT("", 0);
+EXPORT_SYMBOL(empty_name);
+const struct qstr slash_name = QSTR_INIT("/", 1);
+EXPORT_SYMBOL(slash_name);
+
 /*
  * This is the single most critical data structure when it comes
  * to the dcache: the hashtable for lookups. Somebody should try
@@ -1578,8 +1583,7 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
 	 */
 	dentry->d_iname[DNAME_INLINE_LEN-1] = 0;
 	if (unlikely(!name)) {
-		static const struct qstr anon = QSTR_INIT("/", 1);
-		name = &anon;
+		name = &slash_name;
 		dname = dentry->d_iname;
 	} else if (name->len > DNAME_INLINE_LEN-1) {
 		size_t size = offsetof(struct external_name, name[1]);
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index 79113219be5f..a5dfff6a033e 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -872,7 +872,6 @@ static struct gfs2_leaf *new_leaf(struct inode *inode, struct buffer_head **pbh,
 	struct buffer_head *bh;
 	struct gfs2_leaf *leaf;
 	struct gfs2_dirent *dent;
-	struct qstr name = { .name = "" };
 	struct timespec tv = current_time(inode);
 
 	error = gfs2_alloc_blocks(ip, &bn, &n, 0, NULL);
@@ -896,7 +895,7 @@ static struct gfs2_leaf *new_leaf(struct inode *inode, struct buffer_head **pbh,
 	leaf->lf_sec = cpu_to_be64(tv.tv_sec);
 	memset(leaf->lf_reserved2, 0, sizeof(leaf->lf_reserved2));
 	dent = (struct gfs2_dirent *)(leaf+1);
-	gfs2_qstr2dirent(&name, bh->b_size - sizeof(struct gfs2_leaf), dent);
+	gfs2_qstr2dirent(&empty_name, bh->b_size - sizeof(struct gfs2_leaf), dent);
 	*pbh = bh;
 	return leaf;
 }
diff --git a/fs/namei.c b/fs/namei.c
index 6571a5f5112e..0d35760fee00 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3400,7 +3400,6 @@ out:
 
 struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag)
 {
-	static const struct qstr name = QSTR_INIT("/", 1);
 	struct dentry *child = NULL;
 	struct inode *dir = dentry->d_inode;
 	struct inode *inode;
@@ -3414,7 +3413,7 @@ struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag)
 	if (!dir->i_op->tmpfile)
 		goto out_err;
 	error = -ENOMEM;
-	child = d_alloc(dentry, &name);
+	child = d_alloc(dentry, &slash_name);
 	if (unlikely(!child))
 		goto out_err;
 	error = dir->i_op->tmpfile(dir, child, mode);
diff --git a/fs/nsfs.c b/fs/nsfs.c
index f3db56e83dd2..08127a2b8559 100644
--- a/fs/nsfs.c
+++ b/fs/nsfs.c
@@ -53,7 +53,6 @@ static void nsfs_evict(struct inode *inode)
 static void *__ns_get_path(struct path *path, struct ns_common *ns)
 {
 	struct vfsmount *mnt = nsfs_mnt;
-	struct qstr qname = { .name = "", };
 	struct dentry *dentry;
 	struct inode *inode;
 	unsigned long d;
@@ -85,7 +84,7 @@ slow:
 	inode->i_fop = &ns_file_operations;
 	inode->i_private = ns;
 
-	dentry = d_alloc_pseudo(mnt->mnt_sb, &qname);
+	dentry = d_alloc_pseudo(mnt->mnt_sb, &empty_name);
 	if (!dentry) {
 		iput(inode);
 		return ERR_PTR(-ENOMEM);
diff --git a/fs/pipe.c b/fs/pipe.c
index 73b84baf58f8..97e5be897753 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -739,13 +739,12 @@ int create_pipe_files(struct file **res, int flags)
 	struct inode *inode = get_pipe_inode();
 	struct file *f;
 	struct path path;
-	static struct qstr name = { .name = "" };
 
 	if (!inode)
 		return -ENFILE;
 
 	err = -ENOMEM;
-	path.dentry = d_alloc_pseudo(pipe_mnt->mnt_sb, &name);
+	path.dentry = d_alloc_pseudo(pipe_mnt->mnt_sb, &empty_name);
 	if (!path.dentry)
 		goto err_inode;
 	path.mnt = mntget(pipe_mnt);
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index d2e38dc6172c..3f65a4fa72ed 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -55,6 +55,11 @@ struct qstr {
 
 #define QSTR_INIT(n,l) { { { .len = l } }, .name = n }
 
+extern const char empty_string[];
+extern const struct qstr empty_name;
+extern const char slash_string[];
+extern const struct qstr slash_name;
+
 struct dentry_stat_t {
 	long nr_dentry;
 	long nr_unused;
-- 
cgit v1.2.3


From 4a25220d4e43bb2461823dbc7eb1502a34087958 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 5 Jul 2017 16:24:18 +0100
Subject: hugetlbfs: Implement show_options

Implement the show_options superblock op for hugetlbfs as part of a bid to
get rid of s_options and generic_show_options() to make it easier to
implement a context-based mount where the mount options can be passed
individually over a file descriptor.

Note that the uid and gid should possibly be displayed relative to the
viewer's user namespace.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Nadia Yvette Chambers <nyc@holomorphy.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/hugetlbfs/inode.c    | 70 +++++++++++++++++++++++++++++++++++++++----------
 include/linux/hugetlb.h |  3 +++
 2 files changed, 59 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index d44f5456eb9b..99b3b9836575 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -46,13 +46,13 @@ static const struct inode_operations hugetlbfs_dir_inode_operations;
 static const struct inode_operations hugetlbfs_inode_operations;
 
 struct hugetlbfs_config {
-	kuid_t   uid;
-	kgid_t   gid;
-	umode_t mode;
-	long	max_hpages;
-	long	nr_inodes;
-	struct hstate *hstate;
-	long    min_hpages;
+	struct hstate		*hstate;
+	long			max_hpages;
+	long			nr_inodes;
+	long			min_hpages;
+	kuid_t			uid;
+	kgid_t			gid;
+	umode_t			mode;
 };
 
 struct hugetlbfs_inode_info {
@@ -851,6 +851,46 @@ static int hugetlbfs_migrate_page(struct address_space *mapping,
 	return MIGRATEPAGE_SUCCESS;
 }
 
+/*
+ * Display the mount options in /proc/mounts.
+ */
+static int hugetlbfs_show_options(struct seq_file *m, struct dentry *root)
+{
+	struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(root->d_sb);
+	struct hugepage_subpool *spool = sbinfo->spool;
+	unsigned long hpage_size = huge_page_size(sbinfo->hstate);
+	unsigned hpage_shift = huge_page_shift(sbinfo->hstate);
+	char mod;
+
+	if (!uid_eq(sbinfo->uid, GLOBAL_ROOT_UID))
+		seq_printf(m, ",uid=%u",
+			   from_kuid_munged(&init_user_ns, sbinfo->uid));
+	if (!gid_eq(sbinfo->gid, GLOBAL_ROOT_GID))
+		seq_printf(m, ",gid=%u",
+			   from_kgid_munged(&init_user_ns, sbinfo->gid));
+	if (sbinfo->mode != 0755)
+		seq_printf(m, ",mode=%o", sbinfo->mode);
+	if (sbinfo->max_inodes != -1)
+		seq_printf(m, ",nr_inodes=%lu", sbinfo->max_inodes);
+
+	hpage_size /= 1024;
+	mod = 'K';
+	if (hpage_size >= 1024) {
+		hpage_size /= 1024;
+		mod = 'M';
+	}
+	seq_printf(m, ",pagesize=%lu%c", hpage_size, mod);
+	if (spool) {
+		if (spool->max_hpages != -1)
+			seq_printf(m, ",size=%llu",
+				   (unsigned long long)spool->max_hpages << hpage_shift);
+		if (spool->min_hpages != -1)
+			seq_printf(m, ",min_size=%llu",
+				   (unsigned long long)spool->min_hpages << hpage_shift);
+	}
+	return 0;
+}
+
 static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(dentry->d_sb);
@@ -1008,19 +1048,19 @@ static const struct super_operations hugetlbfs_ops = {
 	.evict_inode	= hugetlbfs_evict_inode,
 	.statfs		= hugetlbfs_statfs,
 	.put_super	= hugetlbfs_put_super,
-	.show_options	= generic_show_options,
+	.show_options	= hugetlbfs_show_options,
 };
 
-enum { NO_SIZE, SIZE_STD, SIZE_PERCENT };
+enum hugetlbfs_size_type { NO_SIZE, SIZE_STD, SIZE_PERCENT };
 
 /*
  * Convert size option passed from command line to number of huge pages
  * in the pool specified by hstate.  Size option could be in bytes
  * (val_type == SIZE_STD) or percentage of the pool (val_type == SIZE_PERCENT).
  */
-static long long
+static long
 hugetlbfs_size_to_hpages(struct hstate *h, unsigned long long size_opt,
-								int val_type)
+			 enum hugetlbfs_size_type val_type)
 {
 	if (val_type == NO_SIZE)
 		return -1;
@@ -1042,7 +1082,7 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
 	substring_t args[MAX_OPT_ARGS];
 	int option;
 	unsigned long long max_size_opt = 0, min_size_opt = 0;
-	int max_val_type = NO_SIZE, min_val_type = NO_SIZE;
+	enum hugetlbfs_size_type max_val_type = NO_SIZE, min_val_type = NO_SIZE;
 
 	if (!options)
 		return 0;
@@ -1156,8 +1196,6 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent)
 	struct hugetlbfs_config config;
 	struct hugetlbfs_sb_info *sbinfo;
 
-	save_mount_options(sb, data);
-
 	config.max_hpages = -1; /* No limit on size by default */
 	config.nr_inodes = -1; /* No limit on number of inodes by default */
 	config.uid = current_fsuid();
@@ -1178,6 +1216,10 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent)
 	sbinfo->max_inodes = config.nr_inodes;
 	sbinfo->free_inodes = config.nr_inodes;
 	sbinfo->spool = NULL;
+	sbinfo->uid = config.uid;
+	sbinfo->gid = config.gid;
+	sbinfo->mode = config.mode;
+
 	/*
 	 * Allocate and initialize subpool if maximum or minimum size is
 	 * specified.  Any needed reservations (for minimim size) are taken
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index b857fc8cc2ec..3b6eeaad2f77 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -262,6 +262,9 @@ struct hugetlbfs_sb_info {
 	spinlock_t	stat_lock;
 	struct hstate *hstate;
 	struct hugepage_subpool *spool;
+	kuid_t	uid;
+	kgid_t	gid;
+	umode_t mode;
 };
 
 static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb)
-- 
cgit v1.2.3


From 60934b200ddd62187b149a7f32cc0f160c08a7ed Mon Sep 17 00:00:00 2001
From: Serge Semin <fancer.lancer@gmail.com>
Date: Wed, 14 Dec 2016 02:49:13 +0300
Subject: NTB: Make link-state API being declared first

Since link operations are usually performed before memory window access
operations, it's logically better to declare link-related API before any
of MW/Doorbell/Scratchpad methods.

Signed-off-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
---
 include/linux/ntb.h | 137 ++++++++++++++++++++++++++--------------------------
 1 file changed, 69 insertions(+), 68 deletions(-)

(limited to 'include')

diff --git a/include/linux/ntb.h b/include/linux/ntb.h
index de87ceac110e..d7ab3e1ec88f 100644
--- a/include/linux/ntb.h
+++ b/include/linux/ntb.h
@@ -179,13 +179,13 @@ static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops)
 
 /**
  * struct ntb_ctx_ops - ntb device operations
+ * @link_is_up:		See ntb_link_is_up().
+ * @link_enable:	See ntb_link_enable().
+ * @link_disable:	See ntb_link_disable().
  * @mw_count:		See ntb_mw_count().
  * @mw_get_range:	See ntb_mw_get_range().
  * @mw_set_trans:	See ntb_mw_set_trans().
  * @mw_clear_trans:	See ntb_mw_clear_trans().
- * @link_is_up:		See ntb_link_is_up().
- * @link_enable:	See ntb_link_enable().
- * @link_disable:	See ntb_link_disable().
  * @db_is_unsafe:	See ntb_db_is_unsafe().
  * @db_valid_mask:	See ntb_db_valid_mask().
  * @db_vector_count:	See ntb_db_vector_count().
@@ -212,6 +212,12 @@ static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops)
  * @peer_spad_write:	See ntb_peer_spad_write().
  */
 struct ntb_dev_ops {
+	int (*link_is_up)(struct ntb_dev *ntb,
+			  enum ntb_speed *speed, enum ntb_width *width);
+	int (*link_enable)(struct ntb_dev *ntb,
+			   enum ntb_speed max_speed, enum ntb_width max_width);
+	int (*link_disable)(struct ntb_dev *ntb);
+
 	int (*mw_count)(struct ntb_dev *ntb);
 	int (*mw_get_range)(struct ntb_dev *ntb, int idx,
 			    phys_addr_t *base, resource_size_t *size,
@@ -220,12 +226,6 @@ struct ntb_dev_ops {
 			    dma_addr_t addr, resource_size_t size);
 	int (*mw_clear_trans)(struct ntb_dev *ntb, int idx);
 
-	int (*link_is_up)(struct ntb_dev *ntb,
-			  enum ntb_speed *speed, enum ntb_width *width);
-	int (*link_enable)(struct ntb_dev *ntb,
-			   enum ntb_speed max_speed, enum ntb_width max_width);
-	int (*link_disable)(struct ntb_dev *ntb);
-
 	int (*db_is_unsafe)(struct ntb_dev *ntb);
 	u64 (*db_valid_mask)(struct ntb_dev *ntb);
 	int (*db_vector_count)(struct ntb_dev *ntb);
@@ -265,13 +265,14 @@ static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops)
 {
 	/* commented callbacks are not required: */
 	return
+		ops->link_is_up				&&
+		ops->link_enable			&&
+		ops->link_disable			&&
 		ops->mw_count				&&
 		ops->mw_get_range			&&
 		ops->mw_set_trans			&&
 		/* ops->mw_clear_trans			&& */
-		ops->link_is_up				&&
-		ops->link_enable			&&
-		ops->link_disable			&&
+
 		/* ops->db_is_unsafe			&& */
 		ops->db_valid_mask			&&
 
@@ -440,6 +441,62 @@ void ntb_link_event(struct ntb_dev *ntb);
  */
 void ntb_db_event(struct ntb_dev *ntb, int vector);
 
+/**
+ * ntb_link_is_up() - get the current ntb link state
+ * @ntb:	NTB device context.
+ * @speed:	OUT - The link speed expressed as PCIe generation number.
+ * @width:	OUT - The link width expressed as the number of PCIe lanes.
+ *
+ * Get the current state of the ntb link.  It is recommended to query the link
+ * state once after every link event.  It is safe to query the link state in
+ * the context of the link event callback.
+ *
+ * Return: One if the link is up, zero if the link is down, otherwise a
+ *		negative value indicating the error number.
+ */
+static inline int ntb_link_is_up(struct ntb_dev *ntb,
+				 enum ntb_speed *speed, enum ntb_width *width)
+{
+	return ntb->ops->link_is_up(ntb, speed, width);
+}
+
+/**
+ * ntb_link_enable() - enable the link on the secondary side of the ntb
+ * @ntb:	NTB device context.
+ * @max_speed:	The maximum link speed expressed as PCIe generation number.
+ * @max_width:	The maximum link width expressed as the number of PCIe lanes.
+ *
+ * Enable the link on the secondary side of the ntb.  This can only be done
+ * from the primary side of the ntb in primary or b2b topology.  The ntb device
+ * should train the link to its maximum speed and width, or the requested speed
+ * and width, whichever is smaller, if supported.
+ *
+ * Return: Zero on success, otherwise an error number.
+ */
+static inline int ntb_link_enable(struct ntb_dev *ntb,
+				  enum ntb_speed max_speed,
+				  enum ntb_width max_width)
+{
+	return ntb->ops->link_enable(ntb, max_speed, max_width);
+}
+
+/**
+ * ntb_link_disable() - disable the link on the secondary side of the ntb
+ * @ntb:	NTB device context.
+ *
+ * Disable the link on the secondary side of the ntb.  This can only be
+ * done from the primary side of the ntb in primary or b2b topology.  The ntb
+ * device should disable the link.  Returning from this call must indicate that
+ * a barrier has passed, though with no more writes may pass in either
+ * direction across the link, except if this call returns an error number.
+ *
+ * Return: Zero on success, otherwise an error number.
+ */
+static inline int ntb_link_disable(struct ntb_dev *ntb)
+{
+	return ntb->ops->link_disable(ntb);
+}
+
 /**
  * ntb_mw_count() - get the number of memory windows
  * @ntb:	NTB device context.
@@ -516,62 +573,6 @@ static inline int ntb_mw_clear_trans(struct ntb_dev *ntb, int idx)
 	return ntb->ops->mw_clear_trans(ntb, idx);
 }
 
-/**
- * ntb_link_is_up() - get the current ntb link state
- * @ntb:	NTB device context.
- * @speed:	OUT - The link speed expressed as PCIe generation number.
- * @width:	OUT - The link width expressed as the number of PCIe lanes.
- *
- * Get the current state of the ntb link.  It is recommended to query the link
- * state once after every link event.  It is safe to query the link state in
- * the context of the link event callback.
- *
- * Return: One if the link is up, zero if the link is down, otherwise a
- *		negative value indicating the error number.
- */
-static inline int ntb_link_is_up(struct ntb_dev *ntb,
-				 enum ntb_speed *speed, enum ntb_width *width)
-{
-	return ntb->ops->link_is_up(ntb, speed, width);
-}
-
-/**
- * ntb_link_enable() - enable the link on the secondary side of the ntb
- * @ntb:	NTB device context.
- * @max_speed:	The maximum link speed expressed as PCIe generation number.
- * @max_width:	The maximum link width expressed as the number of PCIe lanes.
- *
- * Enable the link on the secondary side of the ntb.  This can only be done
- * from the primary side of the ntb in primary or b2b topology.  The ntb device
- * should train the link to its maximum speed and width, or the requested speed
- * and width, whichever is smaller, if supported.
- *
- * Return: Zero on success, otherwise an error number.
- */
-static inline int ntb_link_enable(struct ntb_dev *ntb,
-				  enum ntb_speed max_speed,
-				  enum ntb_width max_width)
-{
-	return ntb->ops->link_enable(ntb, max_speed, max_width);
-}
-
-/**
- * ntb_link_disable() - disable the link on the secondary side of the ntb
- * @ntb:	NTB device context.
- *
- * Disable the link on the secondary side of the ntb.  This can only be
- * done from the primary side of the ntb in primary or b2b topology.  The ntb
- * device should disable the link.  Returning from this call must indicate that
- * a barrier has passed, though with no more writes may pass in either
- * direction across the link, except if this call returns an error number.
- *
- * Return: Zero on success, otherwise an error number.
- */
-static inline int ntb_link_disable(struct ntb_dev *ntb)
-{
-	return ntb->ops->link_disable(ntb);
-}
-
 /**
  * ntb_db_is_unsafe() - check if it is safe to use hardware doorbell
  * @ntb:	NTB device context.
-- 
cgit v1.2.3


From 1e5301196a88961b02fe43c73a952f78b2c84712 Mon Sep 17 00:00:00 2001
From: Serge Semin <fancer.lancer@gmail.com>
Date: Wed, 14 Dec 2016 02:49:14 +0300
Subject: NTB: Add indexed ports NTB API

There is some NTB hardware, which can combine more than just two domains
over NTB. For instance, some IDT PCIe-switches can have NTB-functions
activated on more than two-ports. The different domains are distinguished
by ports they are connected to. So the new port-related methods are added to
the NTB API:
 ntb_port_number() - return local port
 ntb_peer_port_count() - return number of peers local port can connect to
 ntb_peer_port_number(pdix) - return port number by it index
 ntb_peer_port_idx(port) - return port index by it number

Current test-drivers aren't changed much. They still support two-ports devices
for the time being while multi-ports hardware drivers aren't added.

By default port-related API is declared for two-ports hardware.
So corresponding hardware drivers won't need to implement it.

Signed-off-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
---
 drivers/ntb/ntb.c               |  54 ++++++++++++++
 drivers/ntb/ntb_transport.c     |   6 ++
 drivers/ntb/test/ntb_perf.c     |   4 ++
 drivers/ntb/test/ntb_pingpong.c |   6 ++
 drivers/ntb/test/ntb_tool.c     |   5 ++
 include/linux/ntb.h             | 156 ++++++++++++++++++++++++++++++++++++++++
 6 files changed, 231 insertions(+)

(limited to 'include')

diff --git a/drivers/ntb/ntb.c b/drivers/ntb/ntb.c
index 2e2530743831..1e92e52813aa 100644
--- a/drivers/ntb/ntb.c
+++ b/drivers/ntb/ntb.c
@@ -191,6 +191,60 @@ void ntb_db_event(struct ntb_dev *ntb, int vector)
 }
 EXPORT_SYMBOL(ntb_db_event);
 
+int ntb_default_port_number(struct ntb_dev *ntb)
+{
+	switch (ntb->topo) {
+	case NTB_TOPO_PRI:
+	case NTB_TOPO_B2B_USD:
+		return NTB_PORT_PRI_USD;
+	case NTB_TOPO_SEC:
+	case NTB_TOPO_B2B_DSD:
+		return NTB_PORT_SEC_DSD;
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+EXPORT_SYMBOL(ntb_default_port_number);
+
+int ntb_default_peer_port_count(struct ntb_dev *ntb)
+{
+	return NTB_DEF_PEER_CNT;
+}
+EXPORT_SYMBOL(ntb_default_peer_port_count);
+
+int ntb_default_peer_port_number(struct ntb_dev *ntb, int pidx)
+{
+	if (pidx != NTB_DEF_PEER_IDX)
+		return -EINVAL;
+
+	switch (ntb->topo) {
+	case NTB_TOPO_PRI:
+	case NTB_TOPO_B2B_USD:
+		return NTB_PORT_SEC_DSD;
+	case NTB_TOPO_SEC:
+	case NTB_TOPO_B2B_DSD:
+		return NTB_PORT_PRI_USD;
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+EXPORT_SYMBOL(ntb_default_peer_port_number);
+
+int ntb_default_peer_port_idx(struct ntb_dev *ntb, int port)
+{
+	int peer_port = ntb_default_peer_port_number(ntb, NTB_DEF_PEER_IDX);
+
+	if (peer_port == -EINVAL || port != peer_port)
+		return -EINVAL;
+
+	return 0;
+}
+EXPORT_SYMBOL(ntb_default_peer_port_idx);
+
 static int ntb_probe(struct device *dev)
 {
 	struct ntb_dev *ntb;
diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index 10e5bf460139..cc6ae35109b1 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -95,6 +95,9 @@ MODULE_PARM_DESC(use_dma, "Use DMA engine to perform large data copy");
 
 static struct dentry *nt_debugfs_dir;
 
+/* Only two-ports NTB devices are supported */
+#define PIDX		NTB_DEF_PEER_IDX
+
 struct ntb_queue_entry {
 	/* ntb_queue list reference */
 	struct list_head entry;
@@ -1064,6 +1067,9 @@ static int ntb_transport_probe(struct ntb_client *self, struct ntb_dev *ndev)
 		dev_dbg(&ndev->dev,
 			"scratchpad is unsafe, proceed anyway...\n");
 
+	if (ntb_peer_port_count(ndev) != NTB_DEF_PEER_CNT)
+		dev_warn(&ndev->dev, "Multi-port NTB devices unsupported\n");
+
 	node = dev_to_node(&ndev->dev);
 
 	nt = kzalloc_node(sizeof(*nt), GFP_KERNEL, node);
diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c
index 5cab2831ce99..e52cc4eace90 100644
--- a/drivers/ntb/test/ntb_perf.c
+++ b/drivers/ntb/test/ntb_perf.c
@@ -76,6 +76,7 @@
 #define DMA_RETRIES		20
 #define SZ_4G			(1ULL << 32)
 #define MAX_SEG_ORDER		20 /* no larger than 1M for kmalloc buffer */
+#define PIDX			NTB_DEF_PEER_IDX
 
 MODULE_LICENSE(DRIVER_LICENSE);
 MODULE_VERSION(DRIVER_VERSION);
@@ -766,6 +767,9 @@ static int perf_probe(struct ntb_client *client, struct ntb_dev *ntb)
 		return -EIO;
 	}
 
+	if (ntb_peer_port_count(ntb) != NTB_DEF_PEER_CNT)
+		dev_warn(&ntb->dev, "Multi-port NTB devices unsupported\n");
+
 	node = dev_to_node(&pdev->dev);
 
 	perf = kzalloc_node(sizeof(*perf), GFP_KERNEL, node);
diff --git a/drivers/ntb/test/ntb_pingpong.c b/drivers/ntb/test/ntb_pingpong.c
index 435861189d97..12f8b40cb11a 100644
--- a/drivers/ntb/test/ntb_pingpong.c
+++ b/drivers/ntb/test/ntb_pingpong.c
@@ -90,6 +90,9 @@ static unsigned long db_init = 0x7;
 module_param(db_init, ulong, 0644);
 MODULE_PARM_DESC(db_init, "Initial doorbell bits to ring on the peer");
 
+/* Only two-ports NTB devices are supported */
+#define PIDX		NTB_DEF_PEER_IDX
+
 struct pp_ctx {
 	struct ntb_dev			*ntb;
 	u64				db_bits;
@@ -230,6 +233,9 @@ static int pp_probe(struct ntb_client *client,
 		}
 	}
 
+	if (ntb_peer_port_count(ntb) != NTB_DEF_PEER_CNT)
+		dev_warn(&ntb->dev, "multi-port NTB is unsupported\n");
+
 	pp = kmalloc(sizeof(*pp), GFP_KERNEL);
 	if (!pp) {
 		rc = -ENOMEM;
diff --git a/drivers/ntb/test/ntb_tool.c b/drivers/ntb/test/ntb_tool.c
index 61bf2ef87e0e..690862d90411 100644
--- a/drivers/ntb/test/ntb_tool.c
+++ b/drivers/ntb/test/ntb_tool.c
@@ -120,6 +120,8 @@ MODULE_AUTHOR(DRIVER_AUTHOR);
 MODULE_DESCRIPTION(DRIVER_DESCRIPTION);
 
 #define MAX_MWS 16
+/* Only two-ports devices are supported */
+#define PIDX	NTB_DEF_PEER_IDX
 
 static struct dentry *tool_dbgfs;
 
@@ -919,6 +921,9 @@ static int tool_probe(struct ntb_client *self, struct ntb_dev *ntb)
 	if (ntb_spad_is_unsafe(ntb))
 		dev_dbg(&ntb->dev, "scratchpad is unsafe\n");
 
+	if (ntb_peer_port_count(ntb) != NTB_DEF_PEER_CNT)
+		dev_warn(&ntb->dev, "multi-port NTB is unsupported\n");
+
 	tc = kzalloc(sizeof(*tc), GFP_KERNEL);
 	if (!tc) {
 		rc = -ENOMEM;
diff --git a/include/linux/ntb.h b/include/linux/ntb.h
index d7ab3e1ec88f..d23483bae6f3 100644
--- a/include/linux/ntb.h
+++ b/include/linux/ntb.h
@@ -139,6 +139,20 @@ enum ntb_width {
 	NTB_WIDTH_32 = 32,
 };
 
+/**
+ * enum ntb_default_port - NTB default port number
+ * @NTB_PORT_PRI_USD:	Default port of the NTB_TOPO_PRI/NTB_TOPO_B2B_USD
+ *			topologies
+ * @NTB_PORT_SEC_DSD:	Default port of the NTB_TOPO_SEC/NTB_TOPO_B2B_DSD
+ *			topologies
+ */
+enum ntb_default_port {
+	NTB_PORT_PRI_USD,
+	NTB_PORT_SEC_DSD
+};
+#define NTB_DEF_PEER_CNT	(1)
+#define NTB_DEF_PEER_IDX	(0)
+
 /**
  * struct ntb_client_ops - ntb client operations
  * @probe:		Notify client of a new device.
@@ -179,6 +193,10 @@ static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops)
 
 /**
  * struct ntb_ctx_ops - ntb device operations
+ * @port_number:	See ntb_port_number().
+ * @peer_port_count:	See ntb_peer_port_count().
+ * @peer_port_number:	See ntb_peer_port_number().
+ * @peer_port_idx:	See ntb_peer_port_idx().
  * @link_is_up:		See ntb_link_is_up().
  * @link_enable:	See ntb_link_enable().
  * @link_disable:	See ntb_link_disable().
@@ -212,6 +230,11 @@ static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops)
  * @peer_spad_write:	See ntb_peer_spad_write().
  */
 struct ntb_dev_ops {
+	int (*port_number)(struct ntb_dev *ntb);
+	int (*peer_port_count)(struct ntb_dev *ntb);
+	int (*peer_port_number)(struct ntb_dev *ntb, int pidx);
+	int (*peer_port_idx)(struct ntb_dev *ntb, int port);
+
 	int (*link_is_up)(struct ntb_dev *ntb,
 			  enum ntb_speed *speed, enum ntb_width *width);
 	int (*link_enable)(struct ntb_dev *ntb,
@@ -265,6 +288,9 @@ static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops)
 {
 	/* commented callbacks are not required: */
 	return
+		!ops->peer_port_count == !ops->port_number	&&
+		!ops->peer_port_number == !ops->port_number	&&
+		!ops->peer_port_idx == !ops->port_number	&&
 		ops->link_is_up				&&
 		ops->link_enable			&&
 		ops->link_disable			&&
@@ -441,6 +467,136 @@ void ntb_link_event(struct ntb_dev *ntb);
  */
 void ntb_db_event(struct ntb_dev *ntb, int vector);
 
+/**
+ * ntb_default_port_number() - get the default local port number
+ * @ntb:	NTB device context.
+ *
+ * If hardware driver doesn't specify port_number() callback method, the NTB
+ * is considered with just two ports. So this method returns default local
+ * port number in compliance with topology.
+ *
+ * NOTE Don't call this method directly. The ntb_port_number() function should
+ * be used instead.
+ *
+ * Return: the default local port number
+ */
+int ntb_default_port_number(struct ntb_dev *ntb);
+
+/**
+ * ntb_default_port_count() - get the default number of peer device ports
+ * @ntb:	NTB device context.
+ *
+ * By default hardware driver supports just one peer device.
+ *
+ * NOTE Don't call this method directly. The ntb_peer_port_count() function
+ * should be used instead.
+ *
+ * Return: the default number of peer ports
+ */
+int ntb_default_peer_port_count(struct ntb_dev *ntb);
+
+/**
+ * ntb_default_peer_port_number() - get the default peer port by given index
+ * @ntb:	NTB device context.
+ * @idx:	Peer port index (should not differ from zero).
+ *
+ * By default hardware driver supports just one peer device, so this method
+ * shall return the corresponding value from enum ntb_default_port.
+ *
+ * NOTE Don't call this method directly. The ntb_peer_port_number() function
+ * should be used instead.
+ *
+ * Return: the peer device port or negative value indicating an error
+ */
+int ntb_default_peer_port_number(struct ntb_dev *ntb, int pidx);
+
+/**
+ * ntb_default_peer_port_idx() - get the default peer device port index by
+ *				 given port number
+ * @ntb:	NTB device context.
+ * @port:	Peer port number (should be one of enum ntb_default_port).
+ *
+ * By default hardware driver supports just one peer device, so while
+ * specified port-argument indicates peer port from enum ntb_default_port,
+ * the return value shall be zero.
+ *
+ * NOTE Don't call this method directly. The ntb_peer_port_idx() function
+ * should be used instead.
+ *
+ * Return: the peer port index or negative value indicating an error
+ */
+int ntb_default_peer_port_idx(struct ntb_dev *ntb, int port);
+
+/**
+ * ntb_port_number() - get the local port number
+ * @ntb:	NTB device context.
+ *
+ * Hardware must support at least simple two-ports ntb connection
+ *
+ * Return: the local port number
+ */
+static inline int ntb_port_number(struct ntb_dev *ntb)
+{
+	if (!ntb->ops->port_number)
+		return ntb_default_port_number(ntb);
+
+	return ntb->ops->port_number(ntb);
+}
+
+/**
+ * ntb_peer_port_count() - get the number of peer device ports
+ * @ntb:	NTB device context.
+ *
+ * Hardware may support an access to memory of several remote domains
+ * over multi-port NTB devices. This method returns the number of peers,
+ * local device can have shared memory with.
+ *
+ * Return: the number of peer ports
+ */
+static inline int ntb_peer_port_count(struct ntb_dev *ntb)
+{
+	if (!ntb->ops->peer_port_count)
+		return ntb_default_peer_port_count(ntb);
+
+	return ntb->ops->peer_port_count(ntb);
+}
+
+/**
+ * ntb_peer_port_number() - get the peer port by given index
+ * @ntb:	NTB device context.
+ * @pidx:	Peer port index.
+ *
+ * Peer ports are continuously enumerated by NTB API logic, so this method
+ * lets to retrieve port real number by its index.
+ *
+ * Return: the peer device port or negative value indicating an error
+ */
+static inline int ntb_peer_port_number(struct ntb_dev *ntb, int pidx)
+{
+	if (!ntb->ops->peer_port_number)
+		return ntb_default_peer_port_number(ntb, pidx);
+
+	return ntb->ops->peer_port_number(ntb, pidx);
+}
+
+/**
+ * ntb_peer_port_idx() - get the peer device port index by given port number
+ * @ntb:	NTB device context.
+ * @port:	Peer port number.
+ *
+ * Inverse operation of ntb_peer_port_number(), so one can get port index
+ * by specified port number.
+ *
+ * Return: the peer port index or negative value indicating an error
+ */
+static inline int ntb_peer_port_idx(struct ntb_dev *ntb, int port)
+{
+	if (!ntb->ops->peer_port_idx)
+		return ntb_default_peer_port_idx(ntb, port);
+
+	return ntb->ops->peer_port_idx(ntb, port);
+}
+
 /**
  * ntb_link_is_up() - get the current ntb link state
  * @ntb:	NTB device context.
-- 
cgit v1.2.3


From 4e8c11b7fd29f70eb7af43bae908297689f2c3da Mon Sep 17 00:00:00 2001
From: Serge Semin <fancer.lancer@gmail.com>
Date: Wed, 14 Dec 2016 02:49:15 +0300
Subject: NTB: Alter link-state API to support multi-port devices

Multi-port devices permit the NTB connections between multiple domains,
so a local device can have NTB link being up with one peer and being
down with another. NTB link-state API is appropriately altered to return
a bitfield of the link-states between the local device and possible peers.

Signed-off-by: Serge Semin <fancer.lancer@gmail.com>
Acked-by: Allen Hubbe <Allen.Hubbe@dell.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
---
 drivers/ntb/hw/amd/ntb_hw_amd.c     |  2 +-
 drivers/ntb/hw/intel/ntb_hw_intel.c |  2 +-
 include/linux/ntb.h                 | 31 ++++++++++++++++---------------
 3 files changed, 18 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/ntb/hw/amd/ntb_hw_amd.c b/drivers/ntb/hw/amd/ntb_hw_amd.c
index 019a158e1128..e71ab4c1fe0e 100644
--- a/drivers/ntb/hw/amd/ntb_hw_amd.c
+++ b/drivers/ntb/hw/amd/ntb_hw_amd.c
@@ -212,7 +212,7 @@ static int amd_link_is_up(struct amd_ntb_dev *ndev)
 	return 0;
 }
 
-static int amd_ntb_link_is_up(struct ntb_dev *ntb,
+static u64 amd_ntb_link_is_up(struct ntb_dev *ntb,
 			      enum ntb_speed *speed,
 			      enum ntb_width *width)
 {
diff --git a/drivers/ntb/hw/intel/ntb_hw_intel.c b/drivers/ntb/hw/intel/ntb_hw_intel.c
index 7b3b6fd63d7d..6b25bf816f28 100644
--- a/drivers/ntb/hw/intel/ntb_hw_intel.c
+++ b/drivers/ntb/hw/intel/ntb_hw_intel.c
@@ -1171,7 +1171,7 @@ static int intel_ntb_mw_set_trans(struct ntb_dev *ntb, int idx,
 	return 0;
 }
 
-static int intel_ntb_link_is_up(struct ntb_dev *ntb,
+static u64 intel_ntb_link_is_up(struct ntb_dev *ntb,
 				enum ntb_speed *speed,
 				enum ntb_width *width)
 {
diff --git a/include/linux/ntb.h b/include/linux/ntb.h
index d23483bae6f3..b2b2924f5f43 100644
--- a/include/linux/ntb.h
+++ b/include/linux/ntb.h
@@ -235,7 +235,7 @@ struct ntb_dev_ops {
 	int (*peer_port_number)(struct ntb_dev *ntb, int pidx);
 	int (*peer_port_idx)(struct ntb_dev *ntb, int port);
 
-	int (*link_is_up)(struct ntb_dev *ntb,
+	u64 (*link_is_up)(struct ntb_dev *ntb,
 			  enum ntb_speed *speed, enum ntb_width *width);
 	int (*link_enable)(struct ntb_dev *ntb,
 			   enum ntb_speed max_speed, enum ntb_width max_width);
@@ -607,25 +607,26 @@ static inline int ntb_peer_port_idx(struct ntb_dev *ntb, int port)
  * state once after every link event.  It is safe to query the link state in
  * the context of the link event callback.
  *
- * Return: One if the link is up, zero if the link is down, otherwise a
- *		negative value indicating the error number.
+ * Return: bitfield of indexed ports link state: bit is set/cleared if the
+ *         link is up/down respectively.
  */
-static inline int ntb_link_is_up(struct ntb_dev *ntb,
+static inline u64 ntb_link_is_up(struct ntb_dev *ntb,
 				 enum ntb_speed *speed, enum ntb_width *width)
 {
 	return ntb->ops->link_is_up(ntb, speed, width);
 }
 
 /**
- * ntb_link_enable() - enable the link on the secondary side of the ntb
+ * ntb_link_enable() - enable the local port ntb connection
  * @ntb:	NTB device context.
  * @max_speed:	The maximum link speed expressed as PCIe generation number.
  * @max_width:	The maximum link width expressed as the number of PCIe lanes.
  *
- * Enable the link on the secondary side of the ntb.  This can only be done
- * from the primary side of the ntb in primary or b2b topology.  The ntb device
- * should train the link to its maximum speed and width, or the requested speed
- * and width, whichever is smaller, if supported.
+ * Enable the NTB/PCIe link on the local or remote (for bridge-to-bridge
+ * topology) side of the bridge. If it's supported the ntb device should train
+ * the link to its maximum speed and width, or the requested speed and width,
+ * whichever is smaller. Some hardware doesn't support PCIe link training, so
+ * the last two arguments will be ignored then.
  *
  * Return: Zero on success, otherwise an error number.
  */
@@ -637,14 +638,14 @@ static inline int ntb_link_enable(struct ntb_dev *ntb,
 }
 
 /**
- * ntb_link_disable() - disable the link on the secondary side of the ntb
+ * ntb_link_disable() - disable the local port ntb connection
  * @ntb:	NTB device context.
  *
- * Disable the link on the secondary side of the ntb.  This can only be
- * done from the primary side of the ntb in primary or b2b topology.  The ntb
- * device should disable the link.  Returning from this call must indicate that
- * a barrier has passed, though with no more writes may pass in either
- * direction across the link, except if this call returns an error number.
+ * Disable the link on the local or remote (for b2b topology) of the ntb.
+ * The ntb device should disable the link.  Returning from this call must
+ * indicate that a barrier has passed, though with no more writes may pass in
+ * either direction across the link, except if this call returns an error
+ * number.
  *
  * Return: Zero on success, otherwise an error number.
  */
-- 
cgit v1.2.3


From 443b9a14ecbe811071467d54d6f2f1182835cc4d Mon Sep 17 00:00:00 2001
From: Serge Semin <fancer.lancer@gmail.com>
Date: Wed, 11 Jan 2017 03:11:33 +0300
Subject: NTB: Alter MW API to support multi-ports devices

Multi-port NTB devices permit to share a memory between all accessible peers.
Memory Windows API is altered to correspondingly initialize and map memory
windows for such devices:
 ntb_mw_count(pidx); - number of inbound memory windows, which can be allocated
for shared buffer with specified peer device.
 ntb_mw_get_align(pidx, widx); - get alignment and size restriction parameters
to properly allocate inbound memory region.
 ntb_peer_mw_count(); - get number of outbound memory windows.
 ntb_peer_mw_get_addr(widx); - get mapping address of an outbound memory window

If hardware supports inbound translation configured on the local ntb port:
 ntb_mw_set_trans(pidx, widx); - set translation address of allocated inbound
memory window so a peer device could access it.
 ntb_mw_clear_trans(pidx, widx); - clear the translation address of an inbound
memory window.

If hardware supports outbound translation configured on the peer ntb port:
 ntb_peer_mw_set_trans(pidx, widx); - set translation address of a memory
window retrieved from a peer device
 ntb_peer_mw_clear_trans(pidx, widx); - clear the translation address of an
outbound memory window

Signed-off-by: Serge Semin <fancer.lancer@gmail.com>
Acked-by: Allen Hubbe <Allen.Hubbe@dell.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
---
 drivers/ntb/hw/amd/ntb_hw_amd.c     |  68 +++++++++---
 drivers/ntb/hw/intel/ntb_hw_intel.c |  90 ++++++++++++----
 drivers/ntb/ntb.c                   |   2 +
 drivers/ntb/ntb_transport.c         |  21 +++-
 drivers/ntb/test/ntb_perf.c         |  17 ++-
 drivers/ntb/test/ntb_tool.c         |  43 +++++---
 include/linux/ntb.h                 | 208 ++++++++++++++++++++++++++++--------
 7 files changed, 342 insertions(+), 107 deletions(-)

(limited to 'include')

diff --git a/drivers/ntb/hw/amd/ntb_hw_amd.c b/drivers/ntb/hw/amd/ntb_hw_amd.c
index e71ab4c1fe0e..bcefe1df9ce3 100644
--- a/drivers/ntb/hw/amd/ntb_hw_amd.c
+++ b/drivers/ntb/hw/amd/ntb_hw_amd.c
@@ -5,6 +5,7 @@
  *   GPL LICENSE SUMMARY
  *
  *   Copyright (C) 2016 Advanced Micro Devices, Inc. All Rights Reserved.
+ *   Copyright (C) 2016 T-Platforms. All Rights Reserved.
  *
  *   This program is free software; you can redistribute it and/or modify
  *   it under the terms of version 2 of the GNU General Public License as
@@ -13,6 +14,7 @@
  *   BSD LICENSE
  *
  *   Copyright (C) 2016 Advanced Micro Devices, Inc. All Rights Reserved.
+ *   Copyright (C) 2016 T-Platforms. All Rights Reserved.
  *
  *   Redistribution and use in source and binary forms, with or without
  *   modification, are permitted provided that the following conditions
@@ -79,40 +81,42 @@ static int ndev_mw_to_bar(struct amd_ntb_dev *ndev, int idx)
 	return 1 << idx;
 }
 
-static int amd_ntb_mw_count(struct ntb_dev *ntb)
+static int amd_ntb_mw_count(struct ntb_dev *ntb, int pidx)
 {
+	if (pidx != NTB_DEF_PEER_IDX)
+		return -EINVAL;
+
 	return ntb_ndev(ntb)->mw_count;
 }
 
-static int amd_ntb_mw_get_range(struct ntb_dev *ntb, int idx,
-				phys_addr_t *base,
-				resource_size_t *size,
-				resource_size_t *align,
-				resource_size_t *align_size)
+static int amd_ntb_mw_get_align(struct ntb_dev *ntb, int pidx, int idx,
+				resource_size_t *addr_align,
+				resource_size_t *size_align,
+				resource_size_t *size_max)
 {
 	struct amd_ntb_dev *ndev = ntb_ndev(ntb);
 	int bar;
 
+	if (pidx != NTB_DEF_PEER_IDX)
+		return -EINVAL;
+
 	bar = ndev_mw_to_bar(ndev, idx);
 	if (bar < 0)
 		return bar;
 
-	if (base)
-		*base = pci_resource_start(ndev->ntb.pdev, bar);
-
-	if (size)
-		*size = pci_resource_len(ndev->ntb.pdev, bar);
+	if (addr_align)
+		*addr_align = SZ_4K;
 
-	if (align)
-		*align = SZ_4K;
+	if (size_align)
+		*size_align = 1;
 
-	if (align_size)
-		*align_size = 1;
+	if (size_max)
+		*size_max = pci_resource_len(ndev->ntb.pdev, bar);
 
 	return 0;
 }
 
-static int amd_ntb_mw_set_trans(struct ntb_dev *ntb, int idx,
+static int amd_ntb_mw_set_trans(struct ntb_dev *ntb, int pidx, int idx,
 				dma_addr_t addr, resource_size_t size)
 {
 	struct amd_ntb_dev *ndev = ntb_ndev(ntb);
@@ -122,6 +126,9 @@ static int amd_ntb_mw_set_trans(struct ntb_dev *ntb, int idx,
 	u64 base_addr, limit, reg_val;
 	int bar;
 
+	if (pidx != NTB_DEF_PEER_IDX)
+		return -EINVAL;
+
 	bar = ndev_mw_to_bar(ndev, idx);
 	if (bar < 0)
 		return bar;
@@ -284,6 +291,31 @@ static int amd_ntb_link_disable(struct ntb_dev *ntb)
 	return 0;
 }
 
+static int amd_ntb_peer_mw_count(struct ntb_dev *ntb)
+{
+	/* The same as for inbound MWs */
+	return ntb_ndev(ntb)->mw_count;
+}
+
+static int amd_ntb_peer_mw_get_addr(struct ntb_dev *ntb, int idx,
+				    phys_addr_t *base, resource_size_t *size)
+{
+	struct amd_ntb_dev *ndev = ntb_ndev(ntb);
+	int bar;
+
+	bar = ndev_mw_to_bar(ndev, idx);
+	if (bar < 0)
+		return bar;
+
+	if (base)
+		*base = pci_resource_start(ndev->ntb.pdev, bar);
+
+	if (size)
+		*size = pci_resource_len(ndev->ntb.pdev, bar);
+
+	return 0;
+}
+
 static u64 amd_ntb_db_valid_mask(struct ntb_dev *ntb)
 {
 	return ntb_ndev(ntb)->db_valid_mask;
@@ -431,8 +463,10 @@ static int amd_ntb_peer_spad_write(struct ntb_dev *ntb,
 
 static const struct ntb_dev_ops amd_ntb_ops = {
 	.mw_count		= amd_ntb_mw_count,
-	.mw_get_range		= amd_ntb_mw_get_range,
+	.mw_get_align		= amd_ntb_mw_get_align,
 	.mw_set_trans		= amd_ntb_mw_set_trans,
+	.peer_mw_count		= amd_ntb_peer_mw_count,
+	.peer_mw_get_addr	= amd_ntb_peer_mw_get_addr,
 	.link_is_up		= amd_ntb_link_is_up,
 	.link_enable		= amd_ntb_link_enable,
 	.link_disable		= amd_ntb_link_disable,
diff --git a/drivers/ntb/hw/intel/ntb_hw_intel.c b/drivers/ntb/hw/intel/ntb_hw_intel.c
index 6b25bf816f28..a9b4ed4d7b52 100644
--- a/drivers/ntb/hw/intel/ntb_hw_intel.c
+++ b/drivers/ntb/hw/intel/ntb_hw_intel.c
@@ -6,6 +6,7 @@
  *
  *   Copyright(c) 2012 Intel Corporation. All rights reserved.
  *   Copyright (C) 2015 EMC Corporation. All Rights Reserved.
+ *   Copyright (C) 2016 T-Platforms. All Rights Reserved.
  *
  *   This program is free software; you can redistribute it and/or modify
  *   it under the terms of version 2 of the GNU General Public License as
@@ -15,6 +16,7 @@
  *
  *   Copyright(c) 2012 Intel Corporation. All rights reserved.
  *   Copyright (C) 2015 EMC Corporation. All Rights Reserved.
+ *   Copyright (C) 2016 T-Platforms. All Rights Reserved.
  *
  *   Redistribution and use in source and binary forms, with or without
  *   modification, are permitted provided that the following conditions
@@ -1035,20 +1037,26 @@ static void ndev_deinit_debugfs(struct intel_ntb_dev *ndev)
 	debugfs_remove_recursive(ndev->debugfs_dir);
 }
 
-static int intel_ntb_mw_count(struct ntb_dev *ntb)
+static int intel_ntb_mw_count(struct ntb_dev *ntb, int pidx)
 {
+	if (pidx != NTB_DEF_PEER_IDX)
+		return -EINVAL;
+
 	return ntb_ndev(ntb)->mw_count;
 }
 
-static int intel_ntb_mw_get_range(struct ntb_dev *ntb, int idx,
-				  phys_addr_t *base,
-				  resource_size_t *size,
-				  resource_size_t *align,
-				  resource_size_t *align_size)
+static int intel_ntb_mw_get_align(struct ntb_dev *ntb, int pidx, int idx,
+				  resource_size_t *addr_align,
+				  resource_size_t *size_align,
+				  resource_size_t *size_max)
 {
 	struct intel_ntb_dev *ndev = ntb_ndev(ntb);
+	resource_size_t bar_size, mw_size;
 	int bar;
 
+	if (pidx != NTB_DEF_PEER_IDX)
+		return -EINVAL;
+
 	if (idx >= ndev->b2b_idx && !ndev->b2b_off)
 		idx += 1;
 
@@ -1056,24 +1064,26 @@ static int intel_ntb_mw_get_range(struct ntb_dev *ntb, int idx,
 	if (bar < 0)
 		return bar;
 
-	if (base)
-		*base = pci_resource_start(ndev->ntb.pdev, bar) +
-			(idx == ndev->b2b_idx ? ndev->b2b_off : 0);
+	bar_size = pci_resource_len(ndev->ntb.pdev, bar);
 
-	if (size)
-		*size = pci_resource_len(ndev->ntb.pdev, bar) -
-			(idx == ndev->b2b_idx ? ndev->b2b_off : 0);
+	if (idx == ndev->b2b_idx)
+		mw_size = bar_size - ndev->b2b_off;
+	else
+		mw_size = bar_size;
+
+	if (addr_align)
+		*addr_align = pci_resource_len(ndev->ntb.pdev, bar);
 
-	if (align)
-		*align = pci_resource_len(ndev->ntb.pdev, bar);
+	if (size_align)
+		*size_align = 1;
 
-	if (align_size)
-		*align_size = 1;
+	if (size_max)
+		*size_max = mw_size;
 
 	return 0;
 }
 
-static int intel_ntb_mw_set_trans(struct ntb_dev *ntb, int idx,
+static int intel_ntb_mw_set_trans(struct ntb_dev *ntb, int pidx, int idx,
 				  dma_addr_t addr, resource_size_t size)
 {
 	struct intel_ntb_dev *ndev = ntb_ndev(ntb);
@@ -1083,6 +1093,9 @@ static int intel_ntb_mw_set_trans(struct ntb_dev *ntb, int idx,
 	u64 base, limit, reg_val;
 	int bar;
 
+	if (pidx != NTB_DEF_PEER_IDX)
+		return -EINVAL;
+
 	if (idx >= ndev->b2b_idx && !ndev->b2b_off)
 		idx += 1;
 
@@ -1249,6 +1262,36 @@ static int intel_ntb_link_disable(struct ntb_dev *ntb)
 	return 0;
 }
 
+static int intel_ntb_peer_mw_count(struct ntb_dev *ntb)
+{
+	/* Numbers of inbound and outbound memory windows match */
+	return ntb_ndev(ntb)->mw_count;
+}
+
+static int intel_ntb_peer_mw_get_addr(struct ntb_dev *ntb, int idx,
+				     phys_addr_t *base, resource_size_t *size)
+{
+	struct intel_ntb_dev *ndev = ntb_ndev(ntb);
+	int bar;
+
+	if (idx >= ndev->b2b_idx && !ndev->b2b_off)
+		idx += 1;
+
+	bar = ndev_mw_to_bar(ndev, idx);
+	if (bar < 0)
+		return bar;
+
+	if (base)
+		*base = pci_resource_start(ndev->ntb.pdev, bar) +
+			(idx == ndev->b2b_idx ? ndev->b2b_off : 0);
+
+	if (size)
+		*size = pci_resource_len(ndev->ntb.pdev, bar) -
+			(idx == ndev->b2b_idx ? ndev->b2b_off : 0);
+
+	return 0;
+}
+
 static int intel_ntb_db_is_unsafe(struct ntb_dev *ntb)
 {
 	return ndev_ignore_unsafe(ntb_ndev(ntb), NTB_UNSAFE_DB);
@@ -1902,7 +1945,7 @@ static int intel_ntb3_link_enable(struct ntb_dev *ntb,
 
 	return 0;
 }
-static int intel_ntb3_mw_set_trans(struct ntb_dev *ntb, int idx,
+static int intel_ntb3_mw_set_trans(struct ntb_dev *ntb, int pidx, int idx,
 				   dma_addr_t addr, resource_size_t size)
 {
 	struct intel_ntb_dev *ndev = ntb_ndev(ntb);
@@ -1912,6 +1955,9 @@ static int intel_ntb3_mw_set_trans(struct ntb_dev *ntb, int idx,
 	u64 base, limit, reg_val;
 	int bar;
 
+	if (pidx != NTB_DEF_PEER_IDX)
+		return -EINVAL;
+
 	if (idx >= ndev->b2b_idx && !ndev->b2b_off)
 		idx += 1;
 
@@ -2906,8 +2952,10 @@ static const struct intel_ntb_xlat_reg skx_sec_xlat = {
 /* operations for primary side of local ntb */
 static const struct ntb_dev_ops intel_ntb_ops = {
 	.mw_count		= intel_ntb_mw_count,
-	.mw_get_range		= intel_ntb_mw_get_range,
+	.mw_get_align		= intel_ntb_mw_get_align,
 	.mw_set_trans		= intel_ntb_mw_set_trans,
+	.peer_mw_count		= intel_ntb_peer_mw_count,
+	.peer_mw_get_addr	= intel_ntb_peer_mw_get_addr,
 	.link_is_up		= intel_ntb_link_is_up,
 	.link_enable		= intel_ntb_link_enable,
 	.link_disable		= intel_ntb_link_disable,
@@ -2932,8 +2980,10 @@ static const struct ntb_dev_ops intel_ntb_ops = {
 
 static const struct ntb_dev_ops intel_ntb3_ops = {
 	.mw_count		= intel_ntb_mw_count,
-	.mw_get_range		= intel_ntb_mw_get_range,
+	.mw_get_align		= intel_ntb_mw_get_align,
 	.mw_set_trans		= intel_ntb3_mw_set_trans,
+	.peer_mw_count		= intel_ntb_peer_mw_count,
+	.peer_mw_get_addr	= intel_ntb_peer_mw_get_addr,
 	.link_is_up		= intel_ntb_link_is_up,
 	.link_enable		= intel_ntb3_link_enable,
 	.link_disable		= intel_ntb_link_disable,
diff --git a/drivers/ntb/ntb.c b/drivers/ntb/ntb.c
index 1e92e52813aa..2551bb2ff4a4 100644
--- a/drivers/ntb/ntb.c
+++ b/drivers/ntb/ntb.c
@@ -5,6 +5,7 @@
  *   GPL LICENSE SUMMARY
  *
  *   Copyright (C) 2015 EMC Corporation. All Rights Reserved.
+ *   Copyright (C) 2016 T-Platforms. All Rights Reserved.
  *
  *   This program is free software; you can redistribute it and/or modify
  *   it under the terms of version 2 of the GNU General Public License as
@@ -18,6 +19,7 @@
  *   BSD LICENSE
  *
  *   Copyright (C) 2015 EMC Corporation. All Rights Reserved.
+ *   Copyright (C) 2016 T-Platforms. All Rights Reserved.
  *
  *   Redistribution and use in source and binary forms, with or without
  *   modification, are permitted provided that the following conditions
diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index cc6ae35109b1..771b469cebf0 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -673,7 +673,7 @@ static void ntb_free_mw(struct ntb_transport_ctx *nt, int num_mw)
 	if (!mw->virt_addr)
 		return;
 
-	ntb_mw_clear_trans(nt->ndev, num_mw);
+	ntb_mw_clear_trans(nt->ndev, PIDX, num_mw);
 	dma_free_coherent(&pdev->dev, mw->buff_size,
 			  mw->virt_addr, mw->dma_addr);
 	mw->xlat_size = 0;
@@ -730,7 +730,8 @@ static int ntb_set_mw(struct ntb_transport_ctx *nt, int num_mw,
 	}
 
 	/* Notify HW the memory location of the receive buffer */
-	rc = ntb_mw_set_trans(nt->ndev, num_mw, mw->dma_addr, mw->xlat_size);
+	rc = ntb_mw_set_trans(nt->ndev, PIDX, num_mw, mw->dma_addr,
+			      mw->xlat_size);
 	if (rc) {
 		dev_err(&pdev->dev, "Unable to set mw%d translation", num_mw);
 		ntb_free_mw(nt, num_mw);
@@ -1058,7 +1059,12 @@ static int ntb_transport_probe(struct ntb_client *self, struct ntb_dev *ndev)
 	int node;
 	int rc, i;
 
-	mw_count = ntb_mw_count(ndev);
+	mw_count = ntb_mw_count(ndev, PIDX);
+
+	if (!ndev->ops->mw_set_trans) {
+		dev_err(&ndev->dev, "Inbound MW based NTB API is required\n");
+		return -EINVAL;
+	}
 
 	if (ntb_db_is_unsafe(ndev))
 		dev_dbg(&ndev->dev,
@@ -1100,8 +1106,13 @@ static int ntb_transport_probe(struct ntb_client *self, struct ntb_dev *ndev)
 	for (i = 0; i < mw_count; i++) {
 		mw = &nt->mw_vec[i];
 
-		rc = ntb_mw_get_range(ndev, i, &mw->phys_addr, &mw->phys_size,
-				      &mw->xlat_align, &mw->xlat_align_size);
+		rc = ntb_mw_get_align(ndev, PIDX, i, &mw->xlat_align,
+				      &mw->xlat_align_size, NULL);
+		if (rc)
+			goto err1;
+
+		rc = ntb_peer_mw_get_addr(ndev, i, &mw->phys_addr,
+					  &mw->phys_size);
 		if (rc)
 			goto err1;
 
diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c
index e52cc4eace90..7f89cceaf350 100644
--- a/drivers/ntb/test/ntb_perf.c
+++ b/drivers/ntb/test/ntb_perf.c
@@ -455,7 +455,7 @@ static void perf_free_mw(struct perf_ctx *perf)
 	if (!mw->virt_addr)
 		return;
 
-	ntb_mw_clear_trans(perf->ntb, 0);
+	ntb_mw_clear_trans(perf->ntb, PIDX, 0);
 	dma_free_coherent(&pdev->dev, mw->buf_size,
 			  mw->virt_addr, mw->dma_addr);
 	mw->xlat_size = 0;
@@ -491,7 +491,7 @@ static int perf_set_mw(struct perf_ctx *perf, resource_size_t size)
 		mw->buf_size = 0;
 	}
 
-	rc = ntb_mw_set_trans(perf->ntb, 0, mw->dma_addr, mw->xlat_size);
+	rc = ntb_mw_set_trans(perf->ntb, PIDX, 0, mw->dma_addr, mw->xlat_size);
 	if (rc) {
 		dev_err(&perf->ntb->dev, "Unable to set mw0 translation\n");
 		perf_free_mw(perf);
@@ -562,8 +562,12 @@ static int perf_setup_mw(struct ntb_dev *ntb, struct perf_ctx *perf)
 
 	mw = &perf->mw;
 
-	rc = ntb_mw_get_range(ntb, 0, &mw->phys_addr, &mw->phys_size,
-			      &mw->xlat_align, &mw->xlat_align_size);
+	rc = ntb_mw_get_align(ntb, PIDX, 0, &mw->xlat_align,
+			      &mw->xlat_align_size, NULL);
+	if (rc)
+		return rc;
+
+	rc = ntb_peer_mw_get_addr(ntb, 0, &mw->phys_addr, &mw->phys_size);
 	if (rc)
 		return rc;
 
@@ -767,6 +771,11 @@ static int perf_probe(struct ntb_client *client, struct ntb_dev *ntb)
 		return -EIO;
 	}
 
+	if (!ntb->ops->mw_set_trans) {
+		dev_err(&ntb->dev, "Need inbound MW based NTB API\n");
+		return -EINVAL;
+	}
+
 	if (ntb_peer_port_count(ntb) != NTB_DEF_PEER_CNT)
 		dev_warn(&ntb->dev, "Multi-port NTB devices unsupported\n");
 
diff --git a/drivers/ntb/test/ntb_tool.c b/drivers/ntb/test/ntb_tool.c
index 690862d90411..cb692473d457 100644
--- a/drivers/ntb/test/ntb_tool.c
+++ b/drivers/ntb/test/ntb_tool.c
@@ -119,7 +119,8 @@ MODULE_VERSION(DRIVER_VERSION);
 MODULE_AUTHOR(DRIVER_AUTHOR);
 MODULE_DESCRIPTION(DRIVER_DESCRIPTION);
 
-#define MAX_MWS 16
+/* It is rare to have hadrware with greater than six MWs */
+#define MAX_MWS	6
 /* Only two-ports devices are supported */
 #define PIDX	NTB_DEF_PEER_IDX
 
@@ -670,28 +671,27 @@ static int tool_setup_mw(struct tool_ctx *tc, int idx, size_t req_size)
 {
 	int rc;
 	struct tool_mw *mw = &tc->mws[idx];
-	phys_addr_t base;
-	resource_size_t size, align, align_size;
+	resource_size_t size, align_addr, align_size;
 	char buf[16];
 
 	if (mw->peer)
 		return 0;
 
-	rc = ntb_mw_get_range(tc->ntb, idx, &base, &size, &align,
-			      &align_size);
+	rc = ntb_mw_get_align(tc->ntb, PIDX, idx, &align_addr,
+				&align_size, &size);
 	if (rc)
 		return rc;
 
 	mw->size = min_t(resource_size_t, req_size, size);
-	mw->size = round_up(mw->size, align);
+	mw->size = round_up(mw->size, align_addr);
 	mw->size = round_up(mw->size, align_size);
 	mw->peer = dma_alloc_coherent(&tc->ntb->pdev->dev, mw->size,
 				      &mw->peer_dma, GFP_KERNEL);
 
-	if (!mw->peer)
+	if (!mw->peer || !IS_ALIGNED(mw->peer_dma, align_addr))
 		return -ENOMEM;
 
-	rc = ntb_mw_set_trans(tc->ntb, idx, mw->peer_dma, mw->size);
+	rc = ntb_mw_set_trans(tc->ntb, PIDX, idx, mw->peer_dma, mw->size);
 	if (rc)
 		goto err_free_dma;
 
@@ -718,7 +718,7 @@ static void tool_free_mw(struct tool_ctx *tc, int idx)
 	struct tool_mw *mw = &tc->mws[idx];
 
 	if (mw->peer) {
-		ntb_mw_clear_trans(tc->ntb, idx);
+		ntb_mw_clear_trans(tc->ntb, PIDX, idx);
 		dma_free_coherent(&tc->ntb->pdev->dev, mw->size,
 				  mw->peer,
 				  mw->peer_dma);
@@ -744,8 +744,9 @@ static ssize_t tool_peer_mw_trans_read(struct file *filep,
 
 	phys_addr_t base;
 	resource_size_t mw_size;
-	resource_size_t align;
+	resource_size_t align_addr;
 	resource_size_t align_size;
+	resource_size_t max_size;
 
 	buf_size = min_t(size_t, size, 512);
 
@@ -753,8 +754,9 @@ static ssize_t tool_peer_mw_trans_read(struct file *filep,
 	if (!buf)
 		return -ENOMEM;
 
-	ntb_mw_get_range(mw->tc->ntb, mw->idx,
-			 &base, &mw_size, &align, &align_size);
+	ntb_mw_get_align(mw->tc->ntb, PIDX, mw->idx,
+			 &align_addr, &align_size, &max_size);
+	ntb_peer_mw_get_addr(mw->tc->ntb, mw->idx, &base, &mw_size);
 
 	off += scnprintf(buf + off, buf_size - off,
 			 "Peer MW %d Information:\n", mw->idx);
@@ -769,12 +771,16 @@ static ssize_t tool_peer_mw_trans_read(struct file *filep,
 
 	off += scnprintf(buf + off, buf_size - off,
 			 "Alignment             \t%lld\n",
-			 (unsigned long long)align);
+			 (unsigned long long)align_addr);
 
 	off += scnprintf(buf + off, buf_size - off,
 			 "Size Alignment        \t%lld\n",
 			 (unsigned long long)align_size);
 
+	off += scnprintf(buf + off, buf_size - off,
+			 "Size Max              \t%lld\n",
+			 (unsigned long long)max_size);
+
 	off += scnprintf(buf + off, buf_size - off,
 			 "Ready                 \t%c\n",
 			 (mw->peer) ? 'Y' : 'N');
@@ -829,8 +835,7 @@ static int tool_init_mw(struct tool_ctx *tc, int idx)
 	phys_addr_t base;
 	int rc;
 
-	rc = ntb_mw_get_range(tc->ntb, idx, &base, &mw->win_size,
-			      NULL, NULL);
+	rc = ntb_peer_mw_get_addr(tc->ntb, idx, &base, &mw->win_size);
 	if (rc)
 		return rc;
 
@@ -915,6 +920,12 @@ static int tool_probe(struct ntb_client *self, struct ntb_dev *ntb)
 	int rc;
 	int i;
 
+	if (!ntb->ops->mw_set_trans) {
+		dev_dbg(&ntb->dev, "need inbound MW based NTB API\n");
+		rc = -EINVAL;
+		goto err_tc;
+	}
+
 	if (ntb_db_is_unsafe(ntb))
 		dev_dbg(&ntb->dev, "doorbell is unsafe\n");
 
@@ -933,7 +944,7 @@ static int tool_probe(struct ntb_client *self, struct ntb_dev *ntb)
 	tc->ntb = ntb;
 	init_waitqueue_head(&tc->link_wq);
 
-	tc->mw_count = min(ntb_mw_count(tc->ntb), MAX_MWS);
+	tc->mw_count = min(ntb_mw_count(tc->ntb, PIDX), MAX_MWS);
 	for (i = 0; i < tc->mw_count; i++) {
 		rc = tool_init_mw(tc, i);
 		if (rc)
diff --git a/include/linux/ntb.h b/include/linux/ntb.h
index b2b2924f5f43..2ea83f91a236 100644
--- a/include/linux/ntb.h
+++ b/include/linux/ntb.h
@@ -5,6 +5,7 @@
  *   GPL LICENSE SUMMARY
  *
  *   Copyright (C) 2015 EMC Corporation. All Rights Reserved.
+ *   Copyright (C) 2016 T-Platforms. All Rights Reserved.
  *
  *   This program is free software; you can redistribute it and/or modify
  *   it under the terms of version 2 of the GNU General Public License as
@@ -18,6 +19,7 @@
  *   BSD LICENSE
  *
  *   Copyright (C) 2015 EMC Corporation. All Rights Reserved.
+ *   Copyright (C) 2016 T-Platforms. All Rights Reserved.
  *
  *   Redistribution and use in source and binary forms, with or without
  *   modification, are permitted provided that the following conditions
@@ -201,9 +203,13 @@ static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops)
  * @link_enable:	See ntb_link_enable().
  * @link_disable:	See ntb_link_disable().
  * @mw_count:		See ntb_mw_count().
- * @mw_get_range:	See ntb_mw_get_range().
+ * @mw_get_align:	See ntb_mw_get_align().
  * @mw_set_trans:	See ntb_mw_set_trans().
  * @mw_clear_trans:	See ntb_mw_clear_trans().
+ * @peer_mw_count:	See ntb_peer_mw_count().
+ * @peer_mw_get_addr:	See ntb_peer_mw_get_addr().
+ * @peer_mw_set_trans:	See ntb_peer_mw_set_trans().
+ * @peer_mw_clear_trans:See ntb_peer_mw_clear_trans().
  * @db_is_unsafe:	See ntb_db_is_unsafe().
  * @db_valid_mask:	See ntb_db_valid_mask().
  * @db_vector_count:	See ntb_db_vector_count().
@@ -241,13 +247,20 @@ struct ntb_dev_ops {
 			   enum ntb_speed max_speed, enum ntb_width max_width);
 	int (*link_disable)(struct ntb_dev *ntb);
 
-	int (*mw_count)(struct ntb_dev *ntb);
-	int (*mw_get_range)(struct ntb_dev *ntb, int idx,
-			    phys_addr_t *base, resource_size_t *size,
-			resource_size_t *align, resource_size_t *align_size);
-	int (*mw_set_trans)(struct ntb_dev *ntb, int idx,
+	int (*mw_count)(struct ntb_dev *ntb, int pidx);
+	int (*mw_get_align)(struct ntb_dev *ntb, int pidx, int widx,
+			    resource_size_t *addr_align,
+			    resource_size_t *size_align,
+			    resource_size_t *size_max);
+	int (*mw_set_trans)(struct ntb_dev *ntb, int pidx, int widx,
 			    dma_addr_t addr, resource_size_t size);
-	int (*mw_clear_trans)(struct ntb_dev *ntb, int idx);
+	int (*mw_clear_trans)(struct ntb_dev *ntb, int pidx, int widx);
+	int (*peer_mw_count)(struct ntb_dev *ntb);
+	int (*peer_mw_get_addr)(struct ntb_dev *ntb, int widx,
+				phys_addr_t *base, resource_size_t *size);
+	int (*peer_mw_set_trans)(struct ntb_dev *ntb, int pidx, int widx,
+				 u64 addr, resource_size_t size);
+	int (*peer_mw_clear_trans)(struct ntb_dev *ntb, int pidx, int widx);
 
 	int (*db_is_unsafe)(struct ntb_dev *ntb);
 	u64 (*db_valid_mask)(struct ntb_dev *ntb);
@@ -295,9 +308,13 @@ static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops)
 		ops->link_enable			&&
 		ops->link_disable			&&
 		ops->mw_count				&&
-		ops->mw_get_range			&&
-		ops->mw_set_trans			&&
+		ops->mw_get_align			&&
+		(ops->mw_set_trans			||
+		 ops->peer_mw_set_trans)		&&
 		/* ops->mw_clear_trans			&& */
+		ops->peer_mw_count			&&
+		ops->peer_mw_get_addr			&&
+		/* ops->peer_mw_clear_trans		&& */
 
 		/* ops->db_is_unsafe			&& */
 		ops->db_valid_mask			&&
@@ -655,79 +672,180 @@ static inline int ntb_link_disable(struct ntb_dev *ntb)
 }
 
 /**
- * ntb_mw_count() - get the number of memory windows
+ * ntb_mw_count() - get the number of inbound memory windows, which could
+ *                  be created for a specified peer device
  * @ntb:	NTB device context.
+ * @pidx:	Port index of peer device.
  *
  * Hardware and topology may support a different number of memory windows.
+ * Moreover different peer devices can support different number of memory
+ * windows. Simply speaking this method returns the number of possible inbound
+ * memory windows to share with specified peer device.
  *
  * Return: the number of memory windows.
  */
-static inline int ntb_mw_count(struct ntb_dev *ntb)
+static inline int ntb_mw_count(struct ntb_dev *ntb, int pidx)
 {
-	return ntb->ops->mw_count(ntb);
+	return ntb->ops->mw_count(ntb, pidx);
 }
 
 /**
- * ntb_mw_get_range() - get the range of a memory window
+ * ntb_mw_get_align() - get the restriction parameters of inbound memory window
  * @ntb:	NTB device context.
- * @idx:	Memory window number.
- * @base:	OUT - the base address for mapping the memory window
- * @size:	OUT - the size for mapping the memory window
- * @align:	OUT - the base alignment for translating the memory window
- * @align_size:	OUT - the size alignment for translating the memory window
- *
- * Get the range of a memory window.  NULL may be given for any output
- * parameter if the value is not needed.  The base and size may be used for
- * mapping the memory window, to access the peer memory.  The alignment and
- * size may be used for translating the memory window, for the peer to access
- * memory on the local system.
- *
- * Return: Zero on success, otherwise an error number.
+ * @pidx:	Port index of peer device.
+ * @widx:	Memory window index.
+ * @addr_align:	OUT - the base alignment for translating the memory window
+ * @size_align:	OUT - the size alignment for translating the memory window
+ * @size_max:	OUT - the maximum size of the memory window
+ *
+ * Get the alignments of an inbound memory window with specified index.
+ * NULL may be given for any output parameter if the value is not needed.
+ * The alignment and size parameters may be used for allocation of proper
+ * shared memory.
+ *
+ * Return: Zero on success, otherwise a negative error number.
  */
-static inline int ntb_mw_get_range(struct ntb_dev *ntb, int idx,
-				   phys_addr_t *base, resource_size_t *size,
-		resource_size_t *align, resource_size_t *align_size)
+static inline int ntb_mw_get_align(struct ntb_dev *ntb, int pidx, int widx,
+				   resource_size_t *addr_align,
+				   resource_size_t *size_align,
+				   resource_size_t *size_max)
 {
-	return ntb->ops->mw_get_range(ntb, idx, base, size,
-			align, align_size);
+	return ntb->ops->mw_get_align(ntb, pidx, widx, addr_align, size_align,
+				      size_max);
 }
 
 /**
- * ntb_mw_set_trans() - set the translation of a memory window
+ * ntb_mw_set_trans() - set the translation of an inbound memory window
  * @ntb:	NTB device context.
- * @idx:	Memory window number.
- * @addr:	The dma address local memory to expose to the peer.
+ * @pidx:	Port index of peer device.
+ * @widx:	Memory window index.
+ * @addr:	The dma address of local memory to expose to the peer.
  * @size:	The size of the local memory to expose to the peer.
  *
  * Set the translation of a memory window.  The peer may access local memory
  * through the window starting at the address, up to the size.  The address
- * must be aligned to the alignment specified by ntb_mw_get_range().  The size
- * must be aligned to the size alignment specified by ntb_mw_get_range().
+ * and size must be aligned in compliance with restrictions of
+ * ntb_mw_get_align(). The region size should not exceed the size_max parameter
+ * of that method.
+ *
+ * This method may not be implemented due to the hardware specific memory
+ * windows interface.
  *
  * Return: Zero on success, otherwise an error number.
  */
-static inline int ntb_mw_set_trans(struct ntb_dev *ntb, int idx,
+static inline int ntb_mw_set_trans(struct ntb_dev *ntb, int pidx, int widx,
 				   dma_addr_t addr, resource_size_t size)
 {
-	return ntb->ops->mw_set_trans(ntb, idx, addr, size);
+	if (!ntb->ops->mw_set_trans)
+		return 0;
+
+	return ntb->ops->mw_set_trans(ntb, pidx, widx, addr, size);
 }
 
 /**
- * ntb_mw_clear_trans() - clear the translation of a memory window
+ * ntb_mw_clear_trans() - clear the translation address of an inbound memory
+ *                        window
  * @ntb:	NTB device context.
- * @idx:	Memory window number.
+ * @pidx:	Port index of peer device.
+ * @widx:	Memory window index.
  *
- * Clear the translation of a memory window.  The peer may no longer access
- * local memory through the window.
+ * Clear the translation of an inbound memory window.  The peer may no longer
+ * access local memory through the window.
  *
  * Return: Zero on success, otherwise an error number.
  */
-static inline int ntb_mw_clear_trans(struct ntb_dev *ntb, int idx)
+static inline int ntb_mw_clear_trans(struct ntb_dev *ntb, int pidx, int widx)
 {
 	if (!ntb->ops->mw_clear_trans)
-		return ntb->ops->mw_set_trans(ntb, idx, 0, 0);
+		return ntb_mw_set_trans(ntb, pidx, widx, 0, 0);
+
+	return ntb->ops->mw_clear_trans(ntb, pidx, widx);
+}
+
+/**
+ * ntb_peer_mw_count() - get the number of outbound memory windows, which could
+ *                       be mapped to access a shared memory
+ * @ntb:	NTB device context.
+ *
+ * Hardware and topology may support a different number of memory windows.
+ * This method returns the number of outbound memory windows supported by
+ * local device.
+ *
+ * Return: the number of memory windows.
+ */
+static inline int ntb_peer_mw_count(struct ntb_dev *ntb)
+{
+	return ntb->ops->peer_mw_count(ntb);
+}
+
+/**
+ * ntb_peer_mw_get_addr() - get map address of an outbound memory window
+ * @ntb:	NTB device context.
+ * @widx:	Memory window index (within ntb_peer_mw_count() return value).
+ * @base:	OUT - the base address of mapping region.
+ * @size:	OUT - the size of mapping region.
+ *
+ * Get base and size of memory region to map.  NULL may be given for any output
+ * parameter if the value is not needed.  The base and size may be used for
+ * mapping the memory window, to access the peer memory.
+ *
+ * Return: Zero on success, otherwise a negative error number.
+ */
+static inline int ntb_peer_mw_get_addr(struct ntb_dev *ntb, int widx,
+				      phys_addr_t *base, resource_size_t *size)
+{
+	return ntb->ops->peer_mw_get_addr(ntb, widx, base, size);
+}
+
+/**
+ * ntb_peer_mw_set_trans() - set a translation address of a memory window
+ *                           retrieved from a peer device
+ * @ntb:	NTB device context.
+ * @pidx:	Port index of peer device the translation address received from.
+ * @widx:	Memory window index.
+ * @addr:	The dma address of the shared memory to access.
+ * @size:	The size of the shared memory to access.
+ *
+ * Set the translation of an outbound memory window.  The local device may
+ * access shared memory allocated by a peer device sent the address.
+ *
+ * This method may not be implemented due to the hardware specific memory
+ * windows interface, so a translation address can be only set on the side,
+ * where shared memory (inbound memory windows) is allocated.
+ *
+ * Return: Zero on success, otherwise an error number.
+ */
+static inline int ntb_peer_mw_set_trans(struct ntb_dev *ntb, int pidx, int widx,
+					u64 addr, resource_size_t size)
+{
+	if (!ntb->ops->peer_mw_set_trans)
+		return 0;
+
+	return ntb->ops->peer_mw_set_trans(ntb, pidx, widx, addr, size);
+}
+
+/**
+ * ntb_peer_mw_clear_trans() - clear the translation address of an outbound
+ *                             memory window
+ * @ntb:	NTB device context.
+ * @pidx:	Port index of peer device.
+ * @widx:	Memory window index.
+ *
+ * Clear the translation of a outbound memory window.  The local device may no
+ * longer access a shared memory through the window.
+ *
+ * This method may not be implemented due to the hardware specific memory
+ * windows interface.
+ *
+ * Return: Zero on success, otherwise an error number.
+ */
+static inline int ntb_peer_mw_clear_trans(struct ntb_dev *ntb, int pidx,
+					  int widx)
+{
+	if (!ntb->ops->peer_mw_clear_trans)
+		return ntb_peer_mw_set_trans(ntb, pidx, widx, 0, 0);
 
-	return ntb->ops->mw_clear_trans(ntb, idx);
+	return ntb->ops->peer_mw_clear_trans(ntb, pidx, widx);
 }
 
 /**
-- 
cgit v1.2.3


From d67288a39584daad11edee9b03d53264ba147453 Mon Sep 17 00:00:00 2001
From: Serge Semin <fancer.lancer@gmail.com>
Date: Wed, 11 Jan 2017 03:13:20 +0300
Subject: NTB: Alter Scratchpads API to support multi-ports devices

Even though there is no any real NTB hardware, which would have both more
than two ports and Scratchpad registers, it is logically correct to have
Scratchpad API accepting a peer port index as well. Intel/AMD drivers utilize
Primary and Secondary topology to split Scratchpad between connected root
devices. Since port-index API introduced, Intel/AMD NTB hardware drivers can
use device port to determine which Scratchpad registers actually belong to
local and peer devices. The same approach can be used if some potential
hardware in future will be multi-port and have some set of Scratchpads.
Here are the brief of changes in the API:
 ntb_spad_count() - return number of Scratchpads per each port
 ntb_peer_spad_addr(pidx, sidx) - address of Scratchpad register of the
peer device with pidx-index
 ntb_peer_spad_read(pidx, sidx) - read specified Scratchpad register of the
peer with pidx-index
 ntb_peer_spad_write(pidx, sidx) - write data to Scratchpad register of the
peer with pidx-index

Since there is hardware which doesn't support Scratchpad registers, the
corresponding API methods are now made optional.

Signed-off-by: Serge Semin <fancer.lancer@gmail.com>
Acked-by: Allen Hubbe <Allen.Hubbe@dell.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
---
 drivers/ntb/hw/amd/ntb_hw_amd.c     | 14 +++----
 drivers/ntb/hw/intel/ntb_hw_intel.c | 14 +++----
 drivers/ntb/ntb_transport.c         | 15 ++++----
 drivers/ntb/test/ntb_perf.c         |  6 +--
 drivers/ntb/test/ntb_pingpong.c     |  8 +++-
 drivers/ntb/test/ntb_tool.c         | 21 +++++++++--
 include/linux/ntb.h                 | 73 +++++++++++++++++++++++--------------
 7 files changed, 94 insertions(+), 57 deletions(-)

(limited to 'include')

diff --git a/drivers/ntb/hw/amd/ntb_hw_amd.c b/drivers/ntb/hw/amd/ntb_hw_amd.c
index bcefe1df9ce3..891beb9f26c2 100644
--- a/drivers/ntb/hw/amd/ntb_hw_amd.c
+++ b/drivers/ntb/hw/amd/ntb_hw_amd.c
@@ -432,30 +432,30 @@ static int amd_ntb_spad_write(struct ntb_dev *ntb,
 	return 0;
 }
 
-static u32 amd_ntb_peer_spad_read(struct ntb_dev *ntb, int idx)
+static u32 amd_ntb_peer_spad_read(struct ntb_dev *ntb, int pidx, int sidx)
 {
 	struct amd_ntb_dev *ndev = ntb_ndev(ntb);
 	void __iomem *mmio = ndev->self_mmio;
 	u32 offset;
 
-	if (idx < 0 || idx >= ndev->spad_count)
+	if (sidx < 0 || sidx >= ndev->spad_count)
 		return -EINVAL;
 
-	offset = ndev->peer_spad + (idx << 2);
+	offset = ndev->peer_spad + (sidx << 2);
 	return readl(mmio + AMD_SPAD_OFFSET + offset);
 }
 
-static int amd_ntb_peer_spad_write(struct ntb_dev *ntb,
-				   int idx, u32 val)
+static int amd_ntb_peer_spad_write(struct ntb_dev *ntb, int pidx,
+				   int sidx, u32 val)
 {
 	struct amd_ntb_dev *ndev = ntb_ndev(ntb);
 	void __iomem *mmio = ndev->self_mmio;
 	u32 offset;
 
-	if (idx < 0 || idx >= ndev->spad_count)
+	if (sidx < 0 || sidx >= ndev->spad_count)
 		return -EINVAL;
 
-	offset = ndev->peer_spad + (idx << 2);
+	offset = ndev->peer_spad + (sidx << 2);
 	writel(val, mmio + AMD_SPAD_OFFSET + offset);
 
 	return 0;
diff --git a/drivers/ntb/hw/intel/ntb_hw_intel.c b/drivers/ntb/hw/intel/ntb_hw_intel.c
index a9b4ed4d7b52..e00aa39a4544 100644
--- a/drivers/ntb/hw/intel/ntb_hw_intel.c
+++ b/drivers/ntb/hw/intel/ntb_hw_intel.c
@@ -1409,30 +1409,30 @@ static int intel_ntb_spad_write(struct ntb_dev *ntb,
 			       ndev->self_reg->spad);
 }
 
-static int intel_ntb_peer_spad_addr(struct ntb_dev *ntb, int idx,
+static int intel_ntb_peer_spad_addr(struct ntb_dev *ntb, int pidx, int sidx,
 				    phys_addr_t *spad_addr)
 {
 	struct intel_ntb_dev *ndev = ntb_ndev(ntb);
 
-	return ndev_spad_addr(ndev, idx, spad_addr, ndev->peer_addr,
+	return ndev_spad_addr(ndev, sidx, spad_addr, ndev->peer_addr,
 			      ndev->peer_reg->spad);
 }
 
-static u32 intel_ntb_peer_spad_read(struct ntb_dev *ntb, int idx)
+static u32 intel_ntb_peer_spad_read(struct ntb_dev *ntb, int pidx, int sidx)
 {
 	struct intel_ntb_dev *ndev = ntb_ndev(ntb);
 
-	return ndev_spad_read(ndev, idx,
+	return ndev_spad_read(ndev, sidx,
 			      ndev->peer_mmio +
 			      ndev->peer_reg->spad);
 }
 
-static int intel_ntb_peer_spad_write(struct ntb_dev *ntb,
-				     int idx, u32 val)
+static int intel_ntb_peer_spad_write(struct ntb_dev *ntb, int pidx,
+				     int sidx, u32 val)
 {
 	struct intel_ntb_dev *ndev = ntb_ndev(ntb);
 
-	return ndev_spad_write(ndev, idx, val,
+	return ndev_spad_write(ndev, sidx, val,
 			       ndev->peer_mmio +
 			       ndev->peer_reg->spad);
 }
diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index 771b469cebf0..9a03c5871efe 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -862,17 +862,17 @@ static void ntb_transport_link_work(struct work_struct *work)
 			size = max_mw_size;
 
 		spad = MW0_SZ_HIGH + (i * 2);
-		ntb_peer_spad_write(ndev, spad, upper_32_bits(size));
+		ntb_peer_spad_write(ndev, PIDX, spad, upper_32_bits(size));
 
 		spad = MW0_SZ_LOW + (i * 2);
-		ntb_peer_spad_write(ndev, spad, lower_32_bits(size));
+		ntb_peer_spad_write(ndev, PIDX, spad, lower_32_bits(size));
 	}
 
-	ntb_peer_spad_write(ndev, NUM_MWS, nt->mw_count);
+	ntb_peer_spad_write(ndev, PIDX, NUM_MWS, nt->mw_count);
 
-	ntb_peer_spad_write(ndev, NUM_QPS, nt->qp_count);
+	ntb_peer_spad_write(ndev, PIDX, NUM_QPS, nt->qp_count);
 
-	ntb_peer_spad_write(ndev, VERSION, NTB_TRANSPORT_VERSION);
+	ntb_peer_spad_write(ndev, PIDX, VERSION, NTB_TRANSPORT_VERSION);
 
 	/* Query the remote side for its info */
 	val = ntb_spad_read(ndev, VERSION);
@@ -948,7 +948,7 @@ static void ntb_qp_link_work(struct work_struct *work)
 
 	val = ntb_spad_read(nt->ndev, QP_LINKS);
 
-	ntb_peer_spad_write(nt->ndev, QP_LINKS, val | BIT(qp->qp_num));
+	ntb_peer_spad_write(nt->ndev, PIDX, QP_LINKS, val | BIT(qp->qp_num));
 
 	/* query remote spad for qp ready bits */
 	dev_dbg_ratelimited(&pdev->dev, "Remote QP link status = %x\n", val);
@@ -2108,8 +2108,7 @@ void ntb_transport_link_down(struct ntb_transport_qp *qp)
 
 	val = ntb_spad_read(qp->ndev, QP_LINKS);
 
-	ntb_peer_spad_write(qp->ndev, QP_LINKS,
-			    val & ~BIT(qp->qp_num));
+	ntb_peer_spad_write(qp->ndev, PIDX, QP_LINKS, val & ~BIT(qp->qp_num));
 
 	if (qp->link_is_up)
 		ntb_send_link_down(qp);
diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c
index 7f89cceaf350..42756a98a728 100644
--- a/drivers/ntb/test/ntb_perf.c
+++ b/drivers/ntb/test/ntb_perf.c
@@ -518,9 +518,9 @@ static void perf_link_work(struct work_struct *work)
 	if (max_mw_size && size > max_mw_size)
 		size = max_mw_size;
 
-	ntb_peer_spad_write(ndev, MW_SZ_HIGH, upper_32_bits(size));
-	ntb_peer_spad_write(ndev, MW_SZ_LOW, lower_32_bits(size));
-	ntb_peer_spad_write(ndev, VERSION, PERF_VERSION);
+	ntb_peer_spad_write(ndev, PIDX, MW_SZ_HIGH, upper_32_bits(size));
+	ntb_peer_spad_write(ndev, PIDX, MW_SZ_LOW, lower_32_bits(size));
+	ntb_peer_spad_write(ndev, PIDX, VERSION, PERF_VERSION);
 
 	/* now read what peer wrote */
 	val = ntb_spad_read(ndev, VERSION);
diff --git a/drivers/ntb/test/ntb_pingpong.c b/drivers/ntb/test/ntb_pingpong.c
index 12f8b40cb11a..938a18bcfc3f 100644
--- a/drivers/ntb/test/ntb_pingpong.c
+++ b/drivers/ntb/test/ntb_pingpong.c
@@ -138,7 +138,7 @@ static void pp_ping(unsigned long ctx)
 			"Ping bits %#llx read %#x write %#x\n",
 			db_bits, spad_rd, spad_wr);
 
-		ntb_peer_spad_write(pp->ntb, 0, spad_wr);
+		ntb_peer_spad_write(pp->ntb, PIDX, 0, spad_wr);
 		ntb_peer_db_set(pp->ntb, db_bits);
 		ntb_db_clear_mask(pp->ntb, db_mask);
 
@@ -225,6 +225,12 @@ static int pp_probe(struct ntb_client *client,
 		}
 	}
 
+	if (ntb_spad_count(ntb) < 1) {
+		dev_dbg(&ntb->dev, "no enough scratchpads\n");
+		rc = -EINVAL;
+		goto err_pp;
+	}
+
 	if (ntb_spad_is_unsafe(ntb)) {
 		dev_dbg(&ntb->dev, "scratchpad is unsafe\n");
 		if (!unsafe) {
diff --git a/drivers/ntb/test/ntb_tool.c b/drivers/ntb/test/ntb_tool.c
index cb692473d457..f002bf48a08d 100644
--- a/drivers/ntb/test/ntb_tool.c
+++ b/drivers/ntb/test/ntb_tool.c
@@ -462,13 +462,22 @@ static TOOL_FOPS_RDWR(tool_spad_fops,
 		      tool_spad_read,
 		      tool_spad_write);
 
+static u32 ntb_tool_peer_spad_read(struct ntb_dev *ntb, int sidx)
+{
+	return ntb_peer_spad_read(ntb, PIDX, sidx);
+}
+
 static ssize_t tool_peer_spad_read(struct file *filep, char __user *ubuf,
 				   size_t size, loff_t *offp)
 {
 	struct tool_ctx *tc = filep->private_data;
 
-	return tool_spadfn_read(tc, ubuf, size, offp,
-				tc->ntb->ops->peer_spad_read);
+	return tool_spadfn_read(tc, ubuf, size, offp, ntb_tool_peer_spad_read);
+}
+
+static int ntb_tool_peer_spad_write(struct ntb_dev *ntb, int sidx, u32 val)
+{
+	return ntb_peer_spad_write(ntb, PIDX, sidx, val);
 }
 
 static ssize_t tool_peer_spad_write(struct file *filep, const char __user *ubuf,
@@ -477,7 +486,7 @@ static ssize_t tool_peer_spad_write(struct file *filep, const char __user *ubuf,
 	struct tool_ctx *tc = filep->private_data;
 
 	return tool_spadfn_write(tc, ubuf, size, offp,
-				 tc->ntb->ops->peer_spad_write);
+				 ntb_tool_peer_spad_write);
 }
 
 static TOOL_FOPS_RDWR(tool_peer_spad_fops,
@@ -926,6 +935,12 @@ static int tool_probe(struct ntb_client *self, struct ntb_dev *ntb)
 		goto err_tc;
 	}
 
+	if (ntb_spad_count(ntb) < 1) {
+		dev_dbg(&ntb->dev, "no enough scratchpads\n");
+		rc = -EINVAL;
+		goto err_tc;
+	}
+
 	if (ntb_db_is_unsafe(ntb))
 		dev_dbg(&ntb->dev, "doorbell is unsafe\n");
 
diff --git a/include/linux/ntb.h b/include/linux/ntb.h
index 2ea83f91a236..4e3cd56af732 100644
--- a/include/linux/ntb.h
+++ b/include/linux/ntb.h
@@ -288,13 +288,14 @@ struct ntb_dev_ops {
 	int (*spad_is_unsafe)(struct ntb_dev *ntb);
 	int (*spad_count)(struct ntb_dev *ntb);
 
-	u32 (*spad_read)(struct ntb_dev *ntb, int idx);
-	int (*spad_write)(struct ntb_dev *ntb, int idx, u32 val);
+	u32 (*spad_read)(struct ntb_dev *ntb, int sidx);
+	int (*spad_write)(struct ntb_dev *ntb, int sidx, u32 val);
 
-	int (*peer_spad_addr)(struct ntb_dev *ntb, int idx,
+	int (*peer_spad_addr)(struct ntb_dev *ntb, int pidx, int sidx,
 			      phys_addr_t *spad_addr);
-	u32 (*peer_spad_read)(struct ntb_dev *ntb, int idx);
-	int (*peer_spad_write)(struct ntb_dev *ntb, int idx, u32 val);
+	u32 (*peer_spad_read)(struct ntb_dev *ntb, int pidx, int sidx);
+	int (*peer_spad_write)(struct ntb_dev *ntb, int pidx, int sidx,
+			       u32 val);
 };
 
 static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops)
@@ -335,13 +336,12 @@ static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops)
 		/* ops->peer_db_read_mask		&& */
 		/* ops->peer_db_set_mask		&& */
 		/* ops->peer_db_clear_mask		&& */
-		/* ops->spad_is_unsafe			&& */
-		ops->spad_count				&&
-		ops->spad_read				&&
-		ops->spad_write				&&
-		/* ops->peer_spad_addr			&& */
-		/* ops->peer_spad_read			&& */
-		ops->peer_spad_write			&&
+		/* !ops->spad_is_unsafe == !ops->spad_count	&& */
+		!ops->spad_read == !ops->spad_count		&&
+		!ops->spad_write == !ops->spad_count		&&
+		/* !ops->peer_spad_addr == !ops->spad_count	&& */
+		/* !ops->peer_spad_read == !ops->spad_count	&& */
+		!ops->peer_spad_write == !ops->spad_count	&&
 		1;
 }
 
@@ -1176,47 +1176,58 @@ static inline int ntb_spad_is_unsafe(struct ntb_dev *ntb)
  * @ntb:	NTB device context.
  *
  * Hardware and topology may support a different number of scratchpads.
+ * Although it must be the same for all ports per NTB device.
  *
  * Return: the number of scratchpads.
  */
 static inline int ntb_spad_count(struct ntb_dev *ntb)
 {
+	if (!ntb->ops->spad_count)
+		return 0;
+
 	return ntb->ops->spad_count(ntb);
 }
 
 /**
  * ntb_spad_read() - read the local scratchpad register
  * @ntb:	NTB device context.
- * @idx:	Scratchpad index.
+ * @sidx:	Scratchpad index.
  *
  * Read the local scratchpad register, and return the value.
  *
  * Return: The value of the local scratchpad register.
  */
-static inline u32 ntb_spad_read(struct ntb_dev *ntb, int idx)
+static inline u32 ntb_spad_read(struct ntb_dev *ntb, int sidx)
 {
-	return ntb->ops->spad_read(ntb, idx);
+	if (!ntb->ops->spad_read)
+		return ~(u32)0;
+
+	return ntb->ops->spad_read(ntb, sidx);
 }
 
 /**
  * ntb_spad_write() - write the local scratchpad register
  * @ntb:	NTB device context.
- * @idx:	Scratchpad index.
+ * @sidx:	Scratchpad index.
  * @val:	Scratchpad value.
  *
  * Write the value to the local scratchpad register.
  *
  * Return: Zero on success, otherwise an error number.
  */
-static inline int ntb_spad_write(struct ntb_dev *ntb, int idx, u32 val)
+static inline int ntb_spad_write(struct ntb_dev *ntb, int sidx, u32 val)
 {
-	return ntb->ops->spad_write(ntb, idx, val);
+	if (!ntb->ops->spad_write)
+		return -EINVAL;
+
+	return ntb->ops->spad_write(ntb, sidx, val);
 }
 
 /**
  * ntb_peer_spad_addr() - address of the peer scratchpad register
  * @ntb:	NTB device context.
- * @idx:	Scratchpad index.
+ * @pidx:	Port index of peer device.
+ * @sidx:	Scratchpad index.
  * @spad_addr:	OUT - The address of the peer scratchpad register.
  *
  * Return the address of the peer doorbell register.  This may be used, for
@@ -1224,45 +1235,51 @@ static inline int ntb_spad_write(struct ntb_dev *ntb, int idx, u32 val)
  *
  * Return: Zero on success, otherwise an error number.
  */
-static inline int ntb_peer_spad_addr(struct ntb_dev *ntb, int idx,
+static inline int ntb_peer_spad_addr(struct ntb_dev *ntb, int pidx, int sidx,
 				     phys_addr_t *spad_addr)
 {
 	if (!ntb->ops->peer_spad_addr)
 		return -EINVAL;
 
-	return ntb->ops->peer_spad_addr(ntb, idx, spad_addr);
+	return ntb->ops->peer_spad_addr(ntb, pidx, sidx, spad_addr);
 }
 
 /**
  * ntb_peer_spad_read() - read the peer scratchpad register
  * @ntb:	NTB device context.
- * @idx:	Scratchpad index.
+ * @pidx:	Port index of peer device.
+ * @sidx:	Scratchpad index.
  *
  * Read the peer scratchpad register, and return the value.
  *
  * Return: The value of the local scratchpad register.
  */
-static inline u32 ntb_peer_spad_read(struct ntb_dev *ntb, int idx)
+static inline u32 ntb_peer_spad_read(struct ntb_dev *ntb, int pidx, int sidx)
 {
 	if (!ntb->ops->peer_spad_read)
-		return 0;
+		return ~(u32)0;
 
-	return ntb->ops->peer_spad_read(ntb, idx);
+	return ntb->ops->peer_spad_read(ntb, pidx, sidx);
 }
 
 /**
  * ntb_peer_spad_write() - write the peer scratchpad register
  * @ntb:	NTB device context.
- * @idx:	Scratchpad index.
+ * @pidx:	Port index of peer device.
+ * @sidx:	Scratchpad index.
  * @val:	Scratchpad value.
  *
  * Write the value to the peer scratchpad register.
  *
  * Return: Zero on success, otherwise an error number.
  */
-static inline int ntb_peer_spad_write(struct ntb_dev *ntb, int idx, u32 val)
+static inline int ntb_peer_spad_write(struct ntb_dev *ntb, int pidx, int sidx,
+				      u32 val)
 {
-	return ntb->ops->peer_spad_write(ntb, idx, val);
+	if (!ntb->ops->peer_spad_write)
+		return -EINVAL;
+
+	return ntb->ops->peer_spad_write(ntb, pidx, sidx, val);
 }
 
 #endif
-- 
cgit v1.2.3


From bc3e49adc279c5505d6df8dd8c7fca45d6d3d21a Mon Sep 17 00:00:00 2001
From: Serge Semin <fancer.lancer@gmail.com>
Date: Tue, 20 Dec 2016 12:48:20 +0300
Subject: NTB: Add Messaging NTB API

Some IDT NTB-capable PCIe-switches have message registers to communicate with
peer devices. This patch adds new NTB API callback methods, which can be used
to utilize these registers functionality:
 ntb_msg_count(); - get number of message registers
 ntb_msg_inbits(); - get bitfield of inbound message registers status
 ntb_msg_outbits(); - get bitfield of outbound message registers status
 ntb_msg_read_sts(); - read the inbound and outbound message registers status
 ntb_msg_clear_sts(); - clear status bits of message registers
 ntb_msg_set_mask(); - mask interrupts raised by status bits of message
registers.
 ntb_msg_clear_mask(); - clear interrupts mask bits of message registers
 ntb_msg_read(midx, *pidx); - read message register with specified index,
additionally getting peer port index which data received from
 ntb_msg_write(midx, pidx); - write data to the specified message register
sending it to the passed peer device connected over a pidx port
 ntb_msg_event(); - notify driver context of a new message event

Of course there is hardware which doesn't support Message registers, so
this API is made optional.

Signed-off-by: Serge Semin <fancer.lancer@gmail.com>
Acked-by: Allen Hubbe <Allen.Hubbe@dell.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
---
 drivers/ntb/ntb.c   |  13 ++++
 include/linux/ntb.h | 205 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 218 insertions(+)

(limited to 'include')

diff --git a/drivers/ntb/ntb.c b/drivers/ntb/ntb.c
index 2551bb2ff4a4..03b80d89b980 100644
--- a/drivers/ntb/ntb.c
+++ b/drivers/ntb/ntb.c
@@ -193,6 +193,19 @@ void ntb_db_event(struct ntb_dev *ntb, int vector)
 }
 EXPORT_SYMBOL(ntb_db_event);
 
+void ntb_msg_event(struct ntb_dev *ntb)
+{
+	unsigned long irqflags;
+
+	spin_lock_irqsave(&ntb->ctx_lock, irqflags);
+	{
+		if (ntb->ctx_ops && ntb->ctx_ops->msg_event)
+			ntb->ctx_ops->msg_event(ntb->ctx);
+	}
+	spin_unlock_irqrestore(&ntb->ctx_lock, irqflags);
+}
+EXPORT_SYMBOL(ntb_msg_event);
+
 int ntb_default_port_number(struct ntb_dev *ntb)
 {
 	switch (ntb->topo) {
diff --git a/include/linux/ntb.h b/include/linux/ntb.h
index 4e3cd56af732..d59688f91618 100644
--- a/include/linux/ntb.h
+++ b/include/linux/ntb.h
@@ -178,10 +178,12 @@ static inline int ntb_client_ops_is_valid(const struct ntb_client_ops *ops)
  * struct ntb_ctx_ops - ntb driver context operations
  * @link_event:		See ntb_link_event().
  * @db_event:		See ntb_db_event().
+ * @msg_event:		See ntb_msg_event().
  */
 struct ntb_ctx_ops {
 	void (*link_event)(void *ctx);
 	void (*db_event)(void *ctx, int db_vector);
+	void (*msg_event)(void *ctx);
 };
 
 static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops)
@@ -190,6 +192,7 @@ static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops)
 	return
 		/* ops->link_event		&& */
 		/* ops->db_event		&& */
+		/* ops->msg_event		&& */
 		1;
 }
 
@@ -234,6 +237,15 @@ static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops)
  * @peer_spad_addr:	See ntb_peer_spad_addr().
  * @peer_spad_read:	See ntb_peer_spad_read().
  * @peer_spad_write:	See ntb_peer_spad_write().
+ * @msg_count:		See ntb_msg_count().
+ * @msg_inbits:		See ntb_msg_inbits().
+ * @msg_outbits:	See ntb_msg_outbits().
+ * @msg_read_sts:	See ntb_msg_read_sts().
+ * @msg_clear_sts:	See ntb_msg_clear_sts().
+ * @msg_set_mask:	See ntb_msg_set_mask().
+ * @msg_clear_mask:	See ntb_msg_clear_mask().
+ * @msg_read:		See ntb_msg_read().
+ * @msg_write:		See ntb_msg_write().
  */
 struct ntb_dev_ops {
 	int (*port_number)(struct ntb_dev *ntb);
@@ -296,6 +308,16 @@ struct ntb_dev_ops {
 	u32 (*peer_spad_read)(struct ntb_dev *ntb, int pidx, int sidx);
 	int (*peer_spad_write)(struct ntb_dev *ntb, int pidx, int sidx,
 			       u32 val);
+
+	int (*msg_count)(struct ntb_dev *ntb);
+	u64 (*msg_inbits)(struct ntb_dev *ntb);
+	u64 (*msg_outbits)(struct ntb_dev *ntb);
+	u64 (*msg_read_sts)(struct ntb_dev *ntb);
+	int (*msg_clear_sts)(struct ntb_dev *ntb, u64 sts_bits);
+	int (*msg_set_mask)(struct ntb_dev *ntb, u64 mask_bits);
+	int (*msg_clear_mask)(struct ntb_dev *ntb, u64 mask_bits);
+	int (*msg_read)(struct ntb_dev *ntb, int midx, int *pidx, u32 *msg);
+	int (*msg_write)(struct ntb_dev *ntb, int midx, int pidx, u32 msg);
 };
 
 static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops)
@@ -342,6 +364,15 @@ static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops)
 		/* !ops->peer_spad_addr == !ops->spad_count	&& */
 		/* !ops->peer_spad_read == !ops->spad_count	&& */
 		!ops->peer_spad_write == !ops->spad_count	&&
+
+		!ops->msg_inbits == !ops->msg_count		&&
+		!ops->msg_outbits == !ops->msg_count		&&
+		!ops->msg_read_sts == !ops->msg_count		&&
+		!ops->msg_clear_sts == !ops->msg_count		&&
+		/* !ops->msg_set_mask == !ops->msg_count	&& */
+		/* !ops->msg_clear_mask == !ops->msg_count	&& */
+		!ops->msg_read == !ops->msg_count		&&
+		!ops->msg_write == !ops->msg_count		&&
 		1;
 }
 
@@ -484,6 +515,18 @@ void ntb_link_event(struct ntb_dev *ntb);
  */
 void ntb_db_event(struct ntb_dev *ntb, int vector);
 
+/**
+ * ntb_msg_event() - notify driver context of a message event
+ * @ntb:	NTB device context.
+ *
+ * Notify the driver context of a message event.  If hardware supports
+ * message registers, this event indicates, that a new message arrived in
+ * some incoming message register or last sent message couldn't be delivered.
+ * The events can be masked/unmasked by the methods ntb_msg_set_mask() and
+ * ntb_msg_clear_mask().
+ */
+void ntb_msg_event(struct ntb_dev *ntb);
+
 /**
  * ntb_default_port_number() - get the default local port number
  * @ntb:	NTB device context.
@@ -1282,4 +1325,166 @@ static inline int ntb_peer_spad_write(struct ntb_dev *ntb, int pidx, int sidx,
 	return ntb->ops->peer_spad_write(ntb, pidx, sidx, val);
 }
 
+/**
+ * ntb_msg_count() - get the number of message registers
+ * @ntb:	NTB device context.
+ *
+ * Hardware may support a different number of message registers.
+ *
+ * Return: the number of message registers.
+ */
+static inline int ntb_msg_count(struct ntb_dev *ntb)
+{
+	if (!ntb->ops->msg_count)
+		return 0;
+
+	return ntb->ops->msg_count(ntb);
+}
+
+/**
+ * ntb_msg_inbits() - get a bitfield of inbound message registers status
+ * @ntb:	NTB device context.
+ *
+ * The method returns the bitfield of status and mask registers, which related
+ * to inbound message registers.
+ *
+ * Return: bitfield of inbound message registers.
+ */
+static inline u64 ntb_msg_inbits(struct ntb_dev *ntb)
+{
+	if (!ntb->ops->msg_inbits)
+		return 0;
+
+	return ntb->ops->msg_inbits(ntb);
+}
+
+/**
+ * ntb_msg_outbits() - get a bitfield of outbound message registers status
+ * @ntb:	NTB device context.
+ *
+ * The method returns the bitfield of status and mask registers, which related
+ * to outbound message registers.
+ *
+ * Return: bitfield of outbound message registers.
+ */
+static inline u64 ntb_msg_outbits(struct ntb_dev *ntb)
+{
+	if (!ntb->ops->msg_outbits)
+		return 0;
+
+	return ntb->ops->msg_outbits(ntb);
+}
+
+/**
+ * ntb_msg_read_sts() - read the message registers status
+ * @ntb:	NTB device context.
+ *
+ * Read the status of message register. Inbound and outbound message registers
+ * related bits can be filtered by masks retrieved from ntb_msg_inbits() and
+ * ntb_msg_outbits().
+ *
+ * Return: status bits of message registers
+ */
+static inline u64 ntb_msg_read_sts(struct ntb_dev *ntb)
+{
+	if (!ntb->ops->msg_read_sts)
+		return 0;
+
+	return ntb->ops->msg_read_sts(ntb);
+}
+
+/**
+ * ntb_msg_clear_sts() - clear status bits of message registers
+ * @ntb:	NTB device context.
+ * @sts_bits:	Status bits to clear.
+ *
+ * Clear bits in the status register.
+ *
+ * Return: Zero on success, otherwise a negative error number.
+ */
+static inline int ntb_msg_clear_sts(struct ntb_dev *ntb, u64 sts_bits)
+{
+	if (!ntb->ops->msg_clear_sts)
+		return -EINVAL;
+
+	return ntb->ops->msg_clear_sts(ntb, sts_bits);
+}
+
+/**
+ * ntb_msg_set_mask() - set mask of message register status bits
+ * @ntb:	NTB device context.
+ * @mask_bits:	Mask bits.
+ *
+ * Mask the message registers status bits from raising the message event.
+ *
+ * Return: Zero on success, otherwise a negative error number.
+ */
+static inline int ntb_msg_set_mask(struct ntb_dev *ntb, u64 mask_bits)
+{
+	if (!ntb->ops->msg_set_mask)
+		return -EINVAL;
+
+	return ntb->ops->msg_set_mask(ntb, mask_bits);
+}
+
+/**
+ * ntb_msg_clear_mask() - clear message registers mask
+ * @ntb:	NTB device context.
+ * @mask_bits:	Mask bits to clear.
+ *
+ * Clear bits in the message events mask register.
+ *
+ * Return: Zero on success, otherwise a negative error number.
+ */
+static inline int ntb_msg_clear_mask(struct ntb_dev *ntb, u64 mask_bits)
+{
+	if (!ntb->ops->msg_clear_mask)
+		return -EINVAL;
+
+	return ntb->ops->msg_clear_mask(ntb, mask_bits);
+}
+
+/**
+ * ntb_msg_read() - read message register with specified index
+ * @ntb:	NTB device context.
+ * @midx:	Message register index
+ * @pidx:	OUT - Port index of peer device a message retrieved from
+ * @msg:	OUT - Data
+ *
+ * Read data from the specified message register. Source port index of a
+ * message is retrieved as well.
+ *
+ * Return: Zero on success, otherwise a negative error number.
+ */
+static inline int ntb_msg_read(struct ntb_dev *ntb, int midx, int *pidx,
+			       u32 *msg)
+{
+	if (!ntb->ops->msg_read)
+		return -EINVAL;
+
+	return ntb->ops->msg_read(ntb, midx, pidx, msg);
+}
+
+/**
+ * ntb_msg_write() - write data to the specified message register
+ * @ntb:	NTB device context.
+ * @midx:	Message register index
+ * @pidx:	Port index of peer device a message being sent to
+ * @msg:	Data to send
+ *
+ * Send data to a specified peer device using the defined message register.
+ * Message event can be raised if the midx registers isn't empty while
+ * calling this method and the corresponding interrupt isn't masked.
+ *
+ * Return: Zero on success, otherwise a negative error number.
+ */
+static inline int ntb_msg_write(struct ntb_dev *ntb, int midx, int pidx,
+				u32 msg)
+{
+	if (!ntb->ops->msg_write)
+		return -EINVAL;
+
+	return ntb->ops->msg_write(ntb, midx, pidx, msg);
+}
+
 #endif
-- 
cgit v1.2.3


From 85dce3aaae98a8440f4a1a2404bcbab890574b46 Mon Sep 17 00:00:00 2001
From: Serge Semin <fancer.lancer@gmail.com>
Date: Wed, 14 Dec 2016 02:49:20 +0300
Subject: NTB: Add PCIe Gen4 link speed

Signed-off-by: Serge Semin <fancer.lancer@gmail.com>
Acked-by: Allen Hubbe <Allen.Hubbe@dell.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
---
 include/linux/ntb.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/ntb.h b/include/linux/ntb.h
index d59688f91618..a6f569727845 100644
--- a/include/linux/ntb.h
+++ b/include/linux/ntb.h
@@ -108,6 +108,7 @@ static inline char *ntb_topo_string(enum ntb_topo topo)
  * @NTB_SPEED_GEN1:	Link is trained to gen1 speed.
  * @NTB_SPEED_GEN2:	Link is trained to gen2 speed.
  * @NTB_SPEED_GEN3:	Link is trained to gen3 speed.
+ * @NTB_SPEED_GEN4:	Link is trained to gen4 speed.
  */
 enum ntb_speed {
 	NTB_SPEED_AUTO = -1,
@@ -115,6 +116,7 @@ enum ntb_speed {
 	NTB_SPEED_GEN1 = 1,
 	NTB_SPEED_GEN2 = 2,
 	NTB_SPEED_GEN3 = 3,
+	NTB_SPEED_GEN4 = 4
 };
 
 /**
-- 
cgit v1.2.3


From 3c69f5d6731c43a5b6b9e78b385948e8d76460be Mon Sep 17 00:00:00 2001
From: Serge Semin <fancer.lancer@gmail.com>
Date: Tue, 20 Dec 2016 12:50:09 +0300
Subject: NTB: Add ntb.h comments

Signed-off-by: Serge Semin <fancer.lancer@gmail.com>
Acked-by: Allen Hubbe <Allen.Hubbe@dell.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
---
 include/linux/ntb.h | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/ntb.h b/include/linux/ntb.h
index a6f569727845..609e232c00da 100644
--- a/include/linux/ntb.h
+++ b/include/linux/ntb.h
@@ -326,12 +326,17 @@ static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops)
 {
 	/* commented callbacks are not required: */
 	return
+		/* Port operations are required for multiport devices */
 		!ops->peer_port_count == !ops->port_number	&&
 		!ops->peer_port_number == !ops->port_number	&&
 		!ops->peer_port_idx == !ops->port_number	&&
+
+		/* Link operations are required */
 		ops->link_is_up				&&
 		ops->link_enable			&&
 		ops->link_disable			&&
+
+		/* One or both MW interfaces should be developed */
 		ops->mw_count				&&
 		ops->mw_get_align			&&
 		(ops->mw_set_trans			||
@@ -341,12 +346,11 @@ static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops)
 		ops->peer_mw_get_addr			&&
 		/* ops->peer_mw_clear_trans		&& */
 
+		/* Doorbell operations are mostly required */
 		/* ops->db_is_unsafe			&& */
 		ops->db_valid_mask			&&
-
 		/* both set, or both unset */
-		(!ops->db_vector_count == !ops->db_vector_mask) &&
-
+		(!ops->db_vector_count == !ops->db_vector_mask)	&&
 		ops->db_read				&&
 		/* ops->db_set				&& */
 		ops->db_clear				&&
@@ -360,6 +364,8 @@ static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops)
 		/* ops->peer_db_read_mask		&& */
 		/* ops->peer_db_set_mask		&& */
 		/* ops->peer_db_clear_mask		&& */
+
+		/* Scrachpads interface is optional */
 		/* !ops->spad_is_unsafe == !ops->spad_count	&& */
 		!ops->spad_read == !ops->spad_count		&&
 		!ops->spad_write == !ops->spad_count		&&
@@ -367,6 +373,7 @@ static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops)
 		/* !ops->peer_spad_read == !ops->spad_count	&& */
 		!ops->peer_spad_write == !ops->spad_count	&&
 
+		/* Messaging interface is optional */
 		!ops->msg_inbits == !ops->msg_count		&&
 		!ops->msg_outbits == !ops->msg_count		&&
 		!ops->msg_read_sts == !ops->msg_count		&&
@@ -387,13 +394,12 @@ struct ntb_client {
 	struct device_driver		drv;
 	const struct ntb_client_ops	ops;
 };
-
 #define drv_ntb_client(__drv) container_of((__drv), struct ntb_client, drv)
 
 /**
  * struct ntb_device - ntb device
  * @dev:		Linux device object.
- * @pdev:		Pci device entry of the ntb.
+ * @pdev:		PCI device entry of the ntb.
  * @topo:		Detected topology of the ntb.
  * @ops:		See &ntb_dev_ops.
  * @ctx:		See &ntb_ctx_ops.
@@ -414,7 +420,6 @@ struct ntb_dev {
 	/* block unregister until device is fully released */
 	struct completion		released;
 };
-
 #define dev_ntb(__dev) container_of((__dev), struct ntb_dev, dev)
 
 /**
@@ -511,7 +516,7 @@ void ntb_link_event(struct ntb_dev *ntb);
  * multiple interrupt vectors for doorbells, the vector number indicates which
  * vector received the interrupt.  The vector number is relative to the first
  * vector used for doorbells, starting at zero, and must be less than
- ** ntb_db_vector_count().  The driver may call ntb_db_read() to check which
+ * ntb_db_vector_count().  The driver may call ntb_db_read() to check which
  * doorbell bits need service, and ntb_db_vector_mask() to determine which of
  * those bits are associated with the vector number.
  */
-- 
cgit v1.2.3


From 5465e7d3b99bbaa823ae4f8e538543e7d6cdc530 Mon Sep 17 00:00:00 2001
From: Nicholas Bellinger <nab@linux-iscsi.org>
Date: Sat, 3 Jun 2017 06:55:50 -0700
Subject: target: Add TARGET_SCF_LOOKUP_LUN_FROM_TAG support for ABORT_TASK

This patch introduces support in target_submit_tmr() for locating a
unpacked_lun from an existing se_cmd->tag during ABORT_TASK.

When TARGET_SCF_LOOKUP_LUN_FROM_TAG is set, target_submit_tmr()
will do the extra lookup via target_lookup_lun_from_tag() and
subsequently invoke transport_lookup_tmr_lun() so a proper
percpu se_lun->lun_ref is taken before workqueue dispatch into
se_device->tmr_wq happens.

Aside from the extra target_lookup_lun_from_tag(), the existing
code-path remains unchanged.

Reviewed-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Reviewed-by: Quinn Tran <quinn.tran@cavium.com>
Cc: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_transport.c | 53 ++++++++++++++++++++++++++++------
 include/target/target_core_base.h      |  3 +-
 2 files changed, 46 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 97a01f48068b..e045803921f8 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -1594,6 +1594,29 @@ static void target_complete_tmr_failure(struct work_struct *work)
 	transport_cmd_check_stop_to_fabric(se_cmd);
 }
 
+static bool target_lookup_lun_from_tag(struct se_session *se_sess, u64 tag,
+				       u64 *unpacked_lun)
+{
+	struct se_cmd *se_cmd;
+	unsigned long flags;
+	bool ret = false;
+
+	spin_lock_irqsave(&se_sess->sess_cmd_lock, flags);
+	list_for_each_entry(se_cmd, &se_sess->sess_cmd_list, se_cmd_list) {
+		if (se_cmd->se_cmd_flags & SCF_SCSI_TMR_CDB)
+			continue;
+
+		if (se_cmd->tag == tag) {
+			*unpacked_lun = se_cmd->orig_fe_lun;
+			ret = true;
+			break;
+		}
+	}
+	spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
+
+	return ret;
+}
+
 /**
  * target_submit_tmr - lookup unpacked lun and submit uninitialized se_cmd
  *                     for TMR CDBs
@@ -1641,19 +1664,31 @@ int target_submit_tmr(struct se_cmd *se_cmd, struct se_session *se_sess,
 		core_tmr_release_req(se_cmd->se_tmr_req);
 		return ret;
 	}
+	/*
+	 * If this is ABORT_TASK with no explicit fabric provided LUN,
+	 * go ahead and search active session tags for a match to figure
+	 * out unpacked_lun for the original se_cmd.
+	 */
+	if (tm_type == TMR_ABORT_TASK && (flags & TARGET_SCF_LOOKUP_LUN_FROM_TAG)) {
+		if (!target_lookup_lun_from_tag(se_sess, tag, &unpacked_lun))
+			goto failure;
+	}
 
 	ret = transport_lookup_tmr_lun(se_cmd, unpacked_lun);
-	if (ret) {
-		/*
-		 * For callback during failure handling, push this work off
-		 * to process context with TMR_LUN_DOES_NOT_EXIST status.
-		 */
-		INIT_WORK(&se_cmd->work, target_complete_tmr_failure);
-		schedule_work(&se_cmd->work);
-		return 0;
-	}
+	if (ret)
+		goto failure;
+
 	transport_generic_handle_tmr(se_cmd);
 	return 0;
+
+	/*
+	 * For callback during failure handling, push this work off
+	 * to process context with TMR_LUN_DOES_NOT_EXIST status.
+	 */
+failure:
+	INIT_WORK(&se_cmd->work, target_complete_tmr_failure);
+	schedule_work(&se_cmd->work);
+	return 0;
 }
 EXPORT_SYMBOL(target_submit_tmr);
 
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 47d9f381209f..f835528e424e 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -188,7 +188,8 @@ enum target_sc_flags_table {
 	TARGET_SCF_BIDI_OP		= 0x01,
 	TARGET_SCF_ACK_KREF		= 0x02,
 	TARGET_SCF_UNKNOWN_SIZE		= 0x04,
-	TARGET_SCF_USE_CPUID	= 0x08,
+	TARGET_SCF_USE_CPUID		= 0x08,
+	TARGET_SCF_LOOKUP_LUN_FROM_TAG	= 0x10,
 };
 
 /* fabric independent task management function values */
-- 
cgit v1.2.3


From 9f2f342892e15f8600939ec8d06caf963ccff880 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@sandisk.com>
Date: Tue, 23 May 2017 16:48:23 -0700
Subject: target: Remove se_device.dev_list

The last user of se_device.dev_list was removed through commit
0fd97ccf45be ("target: kill struct se_subsystem_dev"). Hence
also remove se_device.dev_list.

Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Andy Grover <agrover@redhat.com>
Cc: David Disseldorp <ddiss@suse.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_device.c | 1 -
 include/target/target_core_base.h   | 2 --
 2 files changed, 3 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 6403f44e6104..1f54b397bd57 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -767,7 +767,6 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name)
 	dev->prot_length = sizeof(struct t10_pi_tuple);
 	dev->hba_index = hba->hba_index;
 
-	INIT_LIST_HEAD(&dev->dev_list);
 	INIT_LIST_HEAD(&dev->dev_sep_list);
 	INIT_LIST_HEAD(&dev->dev_tmr_list);
 	INIT_LIST_HEAD(&dev->delayed_cmd_list);
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index f835528e424e..a3af69fcf75e 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -816,8 +816,6 @@ struct se_device {
 	unsigned char		udev_path[SE_UDEV_PATH_LEN];
 	/* Pointer to template of function pointers for transport */
 	const struct target_backend_ops *transport;
-	/* Linked list for struct se_hba struct se_device list */
-	struct list_head	dev_list;
 	struct se_lun		xcopy_lun;
 	/* Protection Information */
 	int			prot_length;
-- 
cgit v1.2.3


From a85d667e58bddf73be84d1981b41eaac985ed216 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@sandisk.com>
Date: Tue, 23 May 2017 16:48:27 -0700
Subject: target: Use {get,put}_unaligned_be*() instead of open coding these
 functions

Introduce the function get_unaligned_be24(). Use {get,put}_unaligned_be*()
where appropriate. This patch does not change any functionality.

Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Cc: Andy Grover <agrover@redhat.com>
Cc: David Disseldorp <ddiss@suse.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_alua.c       |  8 +--
 drivers/target/target_core_device.c     |  8 +--
 drivers/target/target_core_fabric_lib.c |  6 +-
 drivers/target/target_core_pr.c         | 99 +++++++--------------------------
 drivers/target/target_core_pscsi.c      | 20 +++----
 drivers/target/target_core_sbc.c        | 59 +++++---------------
 drivers/target/target_core_spc.c        | 42 +++++++-------
 drivers/target/target_core_xcopy.c      |  4 +-
 include/target/target_core_backend.h    |  8 +++
 9 files changed, 83 insertions(+), 171 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c
index fc4a9c303d55..a91b7c25ffd4 100644
--- a/drivers/target/target_core_alua.c
+++ b/drivers/target/target_core_alua.c
@@ -205,8 +205,8 @@ target_emulate_report_target_port_groups(struct se_cmd *cmd)
 		/*
 		 * TARGET PORT GROUP
 		 */
-		buf[off++] = ((tg_pt_gp->tg_pt_gp_id >> 8) & 0xff);
-		buf[off++] = (tg_pt_gp->tg_pt_gp_id & 0xff);
+		put_unaligned_be16(tg_pt_gp->tg_pt_gp_id, &buf[off]);
+		off += 2;
 
 		off++; /* Skip over Reserved */
 		/*
@@ -235,8 +235,8 @@ target_emulate_report_target_port_groups(struct se_cmd *cmd)
 			/*
 			 * Set RELATIVE TARGET PORT IDENTIFIER
 			 */
-			buf[off++] = ((lun->lun_rtpi >> 8) & 0xff);
-			buf[off++] = (lun->lun_rtpi & 0xff);
+			put_unaligned_be16(lun->lun_rtpi, &buf[off]);
+			off += 2;
 			rd_len += 4;
 		}
 		spin_unlock(&tg_pt_gp->tg_pt_gp_lock);
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 1f54b397bd57..11c80c47b9d3 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -1091,19 +1091,19 @@ passthrough_parse_cdb(struct se_cmd *cmd,
 	      TRANSPORT_FLAG_PASSTHROUGH_PGR)) {
 		if (cdb[0] == PERSISTENT_RESERVE_IN) {
 			cmd->execute_cmd = target_scsi3_emulate_pr_in;
-			size = (cdb[7] << 8) + cdb[8];
+			size = get_unaligned_be16(&cdb[7]);
 			return target_cmd_size_check(cmd, size);
 		}
 		if (cdb[0] == PERSISTENT_RESERVE_OUT) {
 			cmd->execute_cmd = target_scsi3_emulate_pr_out;
-			size = (cdb[7] << 8) + cdb[8];
+			size = get_unaligned_be16(&cdb[7]);
 			return target_cmd_size_check(cmd, size);
 		}
 
 		if (cdb[0] == RELEASE || cdb[0] == RELEASE_10) {
 			cmd->execute_cmd = target_scsi2_reservation_release;
 			if (cdb[0] == RELEASE_10)
-				size = (cdb[7] << 8) | cdb[8];
+				size = get_unaligned_be16(&cdb[7]);
 			else
 				size = cmd->data_length;
 			return target_cmd_size_check(cmd, size);
@@ -1111,7 +1111,7 @@ passthrough_parse_cdb(struct se_cmd *cmd,
 		if (cdb[0] == RESERVE || cdb[0] == RESERVE_10) {
 			cmd->execute_cmd = target_scsi2_reservation_reserve;
 			if (cdb[0] == RESERVE_10)
-				size = (cdb[7] << 8) | cdb[8];
+				size = get_unaligned_be16(&cdb[7]);
 			else
 				size = cmd->data_length;
 			return target_cmd_size_check(cmd, size);
diff --git a/drivers/target/target_core_fabric_lib.c b/drivers/target/target_core_fabric_lib.c
index cb6497ce4b61..508da345b73f 100644
--- a/drivers/target/target_core_fabric_lib.c
+++ b/drivers/target/target_core_fabric_lib.c
@@ -34,6 +34,7 @@
 #include <linux/ctype.h>
 #include <linux/spinlock.h>
 #include <linux/export.h>
+#include <asm/unaligned.h>
 
 #include <scsi/scsi_proto.h>
 
@@ -216,8 +217,7 @@ static int iscsi_get_pr_transport_id(
 	if (padding != 0)
 		len += padding;
 
-	buf[2] = ((len >> 8) & 0xff);
-	buf[3] = (len & 0xff);
+	put_unaligned_be16(len, &buf[2]);
 	/*
 	 * Increment value for total payload + header length for
 	 * full status descriptor
@@ -306,7 +306,7 @@ static char *iscsi_parse_pr_out_transport_id(
 	 */
 	if (out_tid_len) {
 		/* The shift works thanks to integer promotion rules */
-		add_len = (buf[2] << 8) | buf[3];
+		add_len = get_unaligned_be16(&buf[2]);
 
 		tid_len = strlen(&buf[4]);
 		tid_len += 4; /* Add four bytes for iSCSI Transport ID header */
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index 129ca572673c..9921d4d6bb41 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -1562,10 +1562,7 @@ core_scsi3_decode_spec_i_port(
 	 * first extract TransportID Parameter Data Length, and make sure
 	 * the value matches up to the SCSI expected data transfer length.
 	 */
-	tpdl = (buf[24] & 0xff) << 24;
-	tpdl |= (buf[25] & 0xff) << 16;
-	tpdl |= (buf[26] & 0xff) << 8;
-	tpdl |= buf[27] & 0xff;
+	tpdl = get_unaligned_be32(&buf[24]);
 
 	if ((tpdl + 28) != cmd->data_length) {
 		pr_err("SPC-3 PR: Illegal tpdl: %u + 28 byte header"
@@ -3221,12 +3218,8 @@ core_scsi3_emulate_pro_register_and_move(struct se_cmd *cmd, u64 res_key,
 		goto out_put_pr_reg;
 	}
 
-	rtpi = (buf[18] & 0xff) << 8;
-	rtpi |= buf[19] & 0xff;
-	tid_len = (buf[20] & 0xff) << 24;
-	tid_len |= (buf[21] & 0xff) << 16;
-	tid_len |= (buf[22] & 0xff) << 8;
-	tid_len |= buf[23] & 0xff;
+	rtpi = get_unaligned_be16(&buf[18]);
+	tid_len = get_unaligned_be32(&buf[20]);
 	transport_kunmap_data_sg(cmd);
 	buf = NULL;
 
@@ -3552,16 +3545,6 @@ out_put_pr_reg:
 	return ret;
 }
 
-static unsigned long long core_scsi3_extract_reservation_key(unsigned char *cdb)
-{
-	unsigned int __v1, __v2;
-
-	__v1 = (cdb[0] << 24) | (cdb[1] << 16) | (cdb[2] << 8) | cdb[3];
-	__v2 = (cdb[4] << 24) | (cdb[5] << 16) | (cdb[6] << 8) | cdb[7];
-
-	return ((unsigned long long)__v2) | (unsigned long long)__v1 << 32;
-}
-
 /*
  * See spc4r17 section 6.14 Table 170
  */
@@ -3619,8 +3602,8 @@ target_scsi3_emulate_pr_out(struct se_cmd *cmd)
 	/*
 	 * From PERSISTENT_RESERVE_OUT parameter list (payload)
 	 */
-	res_key = core_scsi3_extract_reservation_key(&buf[0]);
-	sa_res_key = core_scsi3_extract_reservation_key(&buf[8]);
+	res_key = get_unaligned_be64(&buf[0]);
+	sa_res_key = get_unaligned_be64(&buf[8]);
 	/*
 	 * REGISTER_AND_MOVE uses a different SA parameter list containing
 	 * SCSI TransportIDs.
@@ -3734,10 +3717,7 @@ core_scsi3_pri_read_keys(struct se_cmd *cmd)
 	if (!buf)
 		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 
-	buf[0] = ((dev->t10_pr.pr_generation >> 24) & 0xff);
-	buf[1] = ((dev->t10_pr.pr_generation >> 16) & 0xff);
-	buf[2] = ((dev->t10_pr.pr_generation >> 8) & 0xff);
-	buf[3] = (dev->t10_pr.pr_generation & 0xff);
+	put_unaligned_be32(dev->t10_pr.pr_generation, buf);
 
 	spin_lock(&dev->t10_pr.registration_lock);
 	list_for_each_entry(pr_reg, &dev->t10_pr.registration_list,
@@ -3749,23 +3729,13 @@ core_scsi3_pri_read_keys(struct se_cmd *cmd)
 		if ((add_len + 8) > (cmd->data_length - 8))
 			break;
 
-		buf[off++] = ((pr_reg->pr_res_key >> 56) & 0xff);
-		buf[off++] = ((pr_reg->pr_res_key >> 48) & 0xff);
-		buf[off++] = ((pr_reg->pr_res_key >> 40) & 0xff);
-		buf[off++] = ((pr_reg->pr_res_key >> 32) & 0xff);
-		buf[off++] = ((pr_reg->pr_res_key >> 24) & 0xff);
-		buf[off++] = ((pr_reg->pr_res_key >> 16) & 0xff);
-		buf[off++] = ((pr_reg->pr_res_key >> 8) & 0xff);
-		buf[off++] = (pr_reg->pr_res_key & 0xff);
-
+		put_unaligned_be64(pr_reg->pr_res_key, &buf[off]);
+		off += 8;
 		add_len += 8;
 	}
 	spin_unlock(&dev->t10_pr.registration_lock);
 
-	buf[4] = ((add_len >> 24) & 0xff);
-	buf[5] = ((add_len >> 16) & 0xff);
-	buf[6] = ((add_len >> 8) & 0xff);
-	buf[7] = (add_len & 0xff);
+	put_unaligned_be32(add_len, &buf[4]);
 
 	transport_kunmap_data_sg(cmd);
 
@@ -3796,10 +3766,7 @@ core_scsi3_pri_read_reservation(struct se_cmd *cmd)
 	if (!buf)
 		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 
-	buf[0] = ((dev->t10_pr.pr_generation >> 24) & 0xff);
-	buf[1] = ((dev->t10_pr.pr_generation >> 16) & 0xff);
-	buf[2] = ((dev->t10_pr.pr_generation >> 8) & 0xff);
-	buf[3] = (dev->t10_pr.pr_generation & 0xff);
+	put_unaligned_be32(dev->t10_pr.pr_generation, &buf[0]);
 
 	spin_lock(&dev->dev_reservation_lock);
 	pr_reg = dev->dev_pr_res_holder;
@@ -3807,10 +3774,7 @@ core_scsi3_pri_read_reservation(struct se_cmd *cmd)
 		/*
 		 * Set the hardcoded Additional Length
 		 */
-		buf[4] = ((add_len >> 24) & 0xff);
-		buf[5] = ((add_len >> 16) & 0xff);
-		buf[6] = ((add_len >> 8) & 0xff);
-		buf[7] = (add_len & 0xff);
+		put_unaligned_be32(add_len, &buf[4]);
 
 		if (cmd->data_length < 22)
 			goto err;
@@ -3837,14 +3801,7 @@ core_scsi3_pri_read_reservation(struct se_cmd *cmd)
 		else
 			pr_res_key = pr_reg->pr_res_key;
 
-		buf[8] = ((pr_res_key >> 56) & 0xff);
-		buf[9] = ((pr_res_key >> 48) & 0xff);
-		buf[10] = ((pr_res_key >> 40) & 0xff);
-		buf[11] = ((pr_res_key >> 32) & 0xff);
-		buf[12] = ((pr_res_key >> 24) & 0xff);
-		buf[13] = ((pr_res_key >> 16) & 0xff);
-		buf[14] = ((pr_res_key >> 8) & 0xff);
-		buf[15] = (pr_res_key & 0xff);
+		put_unaligned_be64(pr_res_key, &buf[8]);
 		/*
 		 * Set the SCOPE and TYPE
 		 */
@@ -3882,8 +3839,7 @@ core_scsi3_pri_report_capabilities(struct se_cmd *cmd)
 	if (!buf)
 		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 
-	buf[0] = ((add_len >> 8) & 0xff);
-	buf[1] = (add_len & 0xff);
+	put_unaligned_be16(add_len, &buf[0]);
 	buf[2] |= 0x10; /* CRH: Compatible Reservation Hanlding bit. */
 	buf[2] |= 0x08; /* SIP_C: Specify Initiator Ports Capable bit */
 	buf[2] |= 0x04; /* ATP_C: All Target Ports Capable bit */
@@ -3947,10 +3903,7 @@ core_scsi3_pri_read_full_status(struct se_cmd *cmd)
 	if (!buf)
 		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 
-	buf[0] = ((dev->t10_pr.pr_generation >> 24) & 0xff);
-	buf[1] = ((dev->t10_pr.pr_generation >> 16) & 0xff);
-	buf[2] = ((dev->t10_pr.pr_generation >> 8) & 0xff);
-	buf[3] = (dev->t10_pr.pr_generation & 0xff);
+	put_unaligned_be32(dev->t10_pr.pr_generation, &buf[0]);
 
 	spin_lock(&dev->dev_reservation_lock);
 	if (dev->dev_pr_res_holder) {
@@ -3992,14 +3945,8 @@ core_scsi3_pri_read_full_status(struct se_cmd *cmd)
 		/*
 		 * Set RESERVATION KEY
 		 */
-		buf[off++] = ((pr_reg->pr_res_key >> 56) & 0xff);
-		buf[off++] = ((pr_reg->pr_res_key >> 48) & 0xff);
-		buf[off++] = ((pr_reg->pr_res_key >> 40) & 0xff);
-		buf[off++] = ((pr_reg->pr_res_key >> 32) & 0xff);
-		buf[off++] = ((pr_reg->pr_res_key >> 24) & 0xff);
-		buf[off++] = ((pr_reg->pr_res_key >> 16) & 0xff);
-		buf[off++] = ((pr_reg->pr_res_key >> 8) & 0xff);
-		buf[off++] = (pr_reg->pr_res_key & 0xff);
+		put_unaligned_be64(pr_reg->pr_res_key, &buf[off]);
+		off += 8;
 		off += 4; /* Skip Over Reserved area */
 
 		/*
@@ -4041,8 +3988,8 @@ core_scsi3_pri_read_full_status(struct se_cmd *cmd)
 		if (!pr_reg->pr_reg_all_tg_pt) {
 			u16 sep_rtpi = pr_reg->tg_pt_sep_rtpi;
 
-			buf[off++] = ((sep_rtpi >> 8) & 0xff);
-			buf[off++] = (sep_rtpi & 0xff);
+			put_unaligned_be16(sep_rtpi, &buf[off]);
+			off += 2;
 		} else
 			off += 2; /* Skip over RELATIVE TARGET PORT IDENTIFIER */
 
@@ -4062,10 +4009,7 @@ core_scsi3_pri_read_full_status(struct se_cmd *cmd)
 		/*
 		 * Set the ADDITIONAL DESCRIPTOR LENGTH
 		 */
-		buf[off++] = ((desc_len >> 24) & 0xff);
-		buf[off++] = ((desc_len >> 16) & 0xff);
-		buf[off++] = ((desc_len >> 8) & 0xff);
-		buf[off++] = (desc_len & 0xff);
+		put_unaligned_be32(desc_len, &buf[off]);
 		/*
 		 * Size of full desctipor header minus TransportID
 		 * containing $FABRIC_MOD specific) initiator device/port
@@ -4082,10 +4026,7 @@ core_scsi3_pri_read_full_status(struct se_cmd *cmd)
 	/*
 	 * Set ADDITIONAL_LENGTH
 	 */
-	buf[4] = ((add_len >> 24) & 0xff);
-	buf[5] = ((add_len >> 16) & 0xff);
-	buf[6] = ((add_len >> 8) & 0xff);
-	buf[7] = (add_len & 0xff);
+	put_unaligned_be32(add_len, &buf[4]);
 
 	transport_kunmap_data_sg(cmd);
 
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index 3e4abb13f8ea..e0be4aa38328 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -168,7 +168,7 @@ static void pscsi_tape_read_blocksize(struct se_device *dev,
 	/*
 	 * If MODE_SENSE still returns zero, set the default value to 1024.
 	 */
-	sdev->sector_size = (buf[9] << 16) | (buf[10] << 8) | (buf[11]);
+	sdev->sector_size = get_unaligned_be24(&buf[9]);
 out_free:
 	if (!sdev->sector_size)
 		sdev->sector_size = 1024;
@@ -209,8 +209,7 @@ pscsi_get_inquiry_vpd_serial(struct scsi_device *sdev, struct t10_wwn *wwn)
 	cdb[0] = INQUIRY;
 	cdb[1] = 0x01; /* Query VPD */
 	cdb[2] = 0x80; /* Unit Serial Number */
-	cdb[3] = (INQUIRY_VPD_SERIAL_LEN >> 8) & 0xff;
-	cdb[4] = (INQUIRY_VPD_SERIAL_LEN & 0xff);
+	put_unaligned_be16(INQUIRY_VPD_SERIAL_LEN, &cdb[3]);
 
 	ret = scsi_execute_req(sdev, cdb, DMA_FROM_DEVICE, buf,
 			      INQUIRY_VPD_SERIAL_LEN, NULL, HZ, 1, NULL);
@@ -245,8 +244,7 @@ pscsi_get_inquiry_vpd_device_ident(struct scsi_device *sdev,
 	cdb[0] = INQUIRY;
 	cdb[1] = 0x01; /* Query VPD */
 	cdb[2] = 0x83; /* Device Identifier */
-	cdb[3] = (INQUIRY_VPD_DEVICE_IDENTIFIER_LEN >> 8) & 0xff;
-	cdb[4] = (INQUIRY_VPD_DEVICE_IDENTIFIER_LEN & 0xff);
+	put_unaligned_be16(INQUIRY_VPD_DEVICE_IDENTIFIER_LEN, &cdb[3]);
 
 	ret = scsi_execute_req(sdev, cdb, DMA_FROM_DEVICE, buf,
 			      INQUIRY_VPD_DEVICE_IDENTIFIER_LEN,
@@ -254,7 +252,7 @@ pscsi_get_inquiry_vpd_device_ident(struct scsi_device *sdev,
 	if (ret)
 		goto out;
 
-	page_len = (buf[2] << 8) | buf[3];
+	page_len = get_unaligned_be16(&buf[2]);
 	while (page_len > 0) {
 		/* Grab a pointer to the Identification descriptor */
 		page_83 = &buf[off];
@@ -669,19 +667,17 @@ after_mode_sense:
 		}
 
 		if (cdb[0] == MODE_SELECT)
-			bdl = (buf[3]);
+			bdl = buf[3];
 		else
-			bdl = (buf[6] << 8) | (buf[7]);
+			bdl = get_unaligned_be16(&buf[6]);
 
 		if (!bdl)
 			goto after_mode_select;
 
 		if (cdb[0] == MODE_SELECT)
-			blocksize = (buf[9] << 16) | (buf[10] << 8) |
-					(buf[11]);
+			blocksize = get_unaligned_be24(&buf[9]);
 		else
-			blocksize = (buf[13] << 16) | (buf[14] << 8) |
-					(buf[15]);
+			blocksize = get_unaligned_be24(&buf[13]);
 
 		sd->sector_size = blocksize;
 	}
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index ff4a6ec30adf..ca42fba882db 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -71,14 +71,8 @@ sbc_emulate_readcapacity(struct se_cmd *cmd)
 	else
 		blocks = (u32)blocks_long;
 
-	buf[0] = (blocks >> 24) & 0xff;
-	buf[1] = (blocks >> 16) & 0xff;
-	buf[2] = (blocks >> 8) & 0xff;
-	buf[3] = blocks & 0xff;
-	buf[4] = (dev->dev_attrib.block_size >> 24) & 0xff;
-	buf[5] = (dev->dev_attrib.block_size >> 16) & 0xff;
-	buf[6] = (dev->dev_attrib.block_size >> 8) & 0xff;
-	buf[7] = dev->dev_attrib.block_size & 0xff;
+	put_unaligned_be32(blocks, &buf[0]);
+	put_unaligned_be32(dev->dev_attrib.block_size, &buf[4]);
 
 	rbuf = transport_kmap_data_sg(cmd);
 	if (rbuf) {
@@ -102,18 +96,8 @@ sbc_emulate_readcapacity_16(struct se_cmd *cmd)
 	unsigned long long blocks = dev->transport->get_blocks(dev);
 
 	memset(buf, 0, sizeof(buf));
-	buf[0] = (blocks >> 56) & 0xff;
-	buf[1] = (blocks >> 48) & 0xff;
-	buf[2] = (blocks >> 40) & 0xff;
-	buf[3] = (blocks >> 32) & 0xff;
-	buf[4] = (blocks >> 24) & 0xff;
-	buf[5] = (blocks >> 16) & 0xff;
-	buf[6] = (blocks >> 8) & 0xff;
-	buf[7] = blocks & 0xff;
-	buf[8] = (dev->dev_attrib.block_size >> 24) & 0xff;
-	buf[9] = (dev->dev_attrib.block_size >> 16) & 0xff;
-	buf[10] = (dev->dev_attrib.block_size >> 8) & 0xff;
-	buf[11] = dev->dev_attrib.block_size & 0xff;
+	put_unaligned_be64(blocks, &buf[0]);
+	put_unaligned_be32(dev->dev_attrib.block_size, &buf[8]);
 	/*
 	 * Set P_TYPE and PROT_EN bits for DIF support
 	 */
@@ -134,8 +118,8 @@ sbc_emulate_readcapacity_16(struct se_cmd *cmd)
 
 	if (dev->transport->get_alignment_offset_lbas) {
 		u16 lalba = dev->transport->get_alignment_offset_lbas(dev);
-		buf[14] = (lalba >> 8) & 0x3f;
-		buf[15] = lalba & 0xff;
+
+		put_unaligned_be16(lalba, &buf[14]);
 	}
 
 	/*
@@ -262,18 +246,17 @@ static inline u32 transport_get_sectors_6(unsigned char *cdb)
 
 static inline u32 transport_get_sectors_10(unsigned char *cdb)
 {
-	return (u32)(cdb[7] << 8) + cdb[8];
+	return get_unaligned_be16(&cdb[7]);
 }
 
 static inline u32 transport_get_sectors_12(unsigned char *cdb)
 {
-	return (u32)(cdb[6] << 24) + (cdb[7] << 16) + (cdb[8] << 8) + cdb[9];
+	return get_unaligned_be32(&cdb[6]);
 }
 
 static inline u32 transport_get_sectors_16(unsigned char *cdb)
 {
-	return (u32)(cdb[10] << 24) + (cdb[11] << 16) +
-		    (cdb[12] << 8) + cdb[13];
+	return get_unaligned_be32(&cdb[10]);
 }
 
 /*
@@ -281,29 +264,23 @@ static inline u32 transport_get_sectors_16(unsigned char *cdb)
  */
 static inline u32 transport_get_sectors_32(unsigned char *cdb)
 {
-	return (u32)(cdb[28] << 24) + (cdb[29] << 16) +
-		    (cdb[30] << 8) + cdb[31];
+	return get_unaligned_be32(&cdb[28]);
 
 }
 
 static inline u32 transport_lba_21(unsigned char *cdb)
 {
-	return ((cdb[1] & 0x1f) << 16) | (cdb[2] << 8) | cdb[3];
+	return get_unaligned_be24(&cdb[1]) & 0x1fffff;
 }
 
 static inline u32 transport_lba_32(unsigned char *cdb)
 {
-	return (cdb[2] << 24) | (cdb[3] << 16) | (cdb[4] << 8) | cdb[5];
+	return get_unaligned_be32(&cdb[2]);
 }
 
 static inline unsigned long long transport_lba_64(unsigned char *cdb)
 {
-	unsigned int __v1, __v2;
-
-	__v1 = (cdb[2] << 24) | (cdb[3] << 16) | (cdb[4] << 8) | cdb[5];
-	__v2 = (cdb[6] << 24) | (cdb[7] << 16) | (cdb[8] << 8) | cdb[9];
-
-	return ((unsigned long long)__v2) | (unsigned long long)__v1 << 32;
+	return get_unaligned_be64(&cdb[2]);
 }
 
 /*
@@ -311,12 +288,7 @@ static inline unsigned long long transport_lba_64(unsigned char *cdb)
  */
 static inline unsigned long long transport_lba_64_ext(unsigned char *cdb)
 {
-	unsigned int __v1, __v2;
-
-	__v1 = (cdb[12] << 24) | (cdb[13] << 16) | (cdb[14] << 8) | cdb[15];
-	__v2 = (cdb[16] << 24) | (cdb[17] << 16) | (cdb[18] << 8) | cdb[19];
-
-	return ((unsigned long long)__v2) | (unsigned long long)__v1 << 32;
+	return get_unaligned_be64(&cdb[12]);
 }
 
 static sense_reason_t
@@ -1051,8 +1023,7 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 				cmd->t_task_cdb[1] & 0x1f);
 			return TCM_INVALID_CDB_FIELD;
 		}
-		size = (cdb[10] << 24) | (cdb[11] << 16) |
-		       (cdb[12] << 8) | cdb[13];
+		size = get_unaligned_be32(&cdb[10]);
 		break;
 	case SYNCHRONIZE_CACHE:
 	case SYNCHRONIZE_CACHE_16:
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index 2a91ed3ef380..f59ac7671031 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -287,8 +287,8 @@ check_t10_vend_desc:
 		/* Skip over Obsolete field in RTPI payload
 		 * in Table 472 */
 		off += 2;
-		buf[off++] = ((lun->lun_rtpi >> 8) & 0xff);
-		buf[off++] = (lun->lun_rtpi & 0xff);
+		put_unaligned_be16(lun->lun_rtpi, &buf[off]);
+		off += 2;
 		len += 8; /* Header size + Designation descriptor */
 		/*
 		 * Target port group identifier, see spc4r17
@@ -316,8 +316,8 @@ check_t10_vend_desc:
 		off++; /* Skip over Reserved */
 		buf[off++] = 4; /* DESIGNATOR LENGTH */
 		off += 2; /* Skip over Reserved Field */
-		buf[off++] = ((tg_pt_gp_id >> 8) & 0xff);
-		buf[off++] = (tg_pt_gp_id & 0xff);
+		put_unaligned_be16(tg_pt_gp_id, &buf[off]);
+		off += 2;
 		len += 8; /* Header size + Designation descriptor */
 		/*
 		 * Logical Unit Group identifier, see spc4r17
@@ -343,8 +343,8 @@ check_lu_gp:
 		off++; /* Skip over Reserved */
 		buf[off++] = 4; /* DESIGNATOR LENGTH */
 		off += 2; /* Skip over Reserved Field */
-		buf[off++] = ((lu_gp_id >> 8) & 0xff);
-		buf[off++] = (lu_gp_id & 0xff);
+		put_unaligned_be16(lu_gp_id, &buf[off]);
+		off += 2;
 		len += 8; /* Header size + Designation descriptor */
 		/*
 		 * SCSI name string designator, see spc4r17
@@ -431,8 +431,7 @@ check_scsi_name:
 		/* Header size + Designation descriptor */
 		len += (scsi_target_len + 4);
 	}
-	buf[2] = ((len >> 8) & 0xff);
-	buf[3] = (len & 0xff); /* Page Length for VPD 0x83 */
+	put_unaligned_be16(len, &buf[2]); /* Page Length for VPD 0x83 */
 	return 0;
 }
 EXPORT_SYMBOL(spc_emulate_evpd_83);
@@ -1288,7 +1287,7 @@ spc_parse_cdb(struct se_cmd *cmd, unsigned int *size)
 		cmd->execute_cmd = spc_emulate_modeselect;
 		break;
 	case MODE_SELECT_10:
-		*size = (cdb[7] << 8) + cdb[8];
+		*size = get_unaligned_be16(&cdb[7]);
 		cmd->execute_cmd = spc_emulate_modeselect;
 		break;
 	case MODE_SENSE:
@@ -1296,25 +1295,25 @@ spc_parse_cdb(struct se_cmd *cmd, unsigned int *size)
 		cmd->execute_cmd = spc_emulate_modesense;
 		break;
 	case MODE_SENSE_10:
-		*size = (cdb[7] << 8) + cdb[8];
+		*size = get_unaligned_be16(&cdb[7]);
 		cmd->execute_cmd = spc_emulate_modesense;
 		break;
 	case LOG_SELECT:
 	case LOG_SENSE:
-		*size = (cdb[7] << 8) + cdb[8];
+		*size = get_unaligned_be16(&cdb[7]);
 		break;
 	case PERSISTENT_RESERVE_IN:
-		*size = (cdb[7] << 8) + cdb[8];
+		*size = get_unaligned_be16(&cdb[7]);
 		cmd->execute_cmd = target_scsi3_emulate_pr_in;
 		break;
 	case PERSISTENT_RESERVE_OUT:
-		*size = (cdb[7] << 8) + cdb[8];
+		*size = get_unaligned_be16(&cdb[7]);
 		cmd->execute_cmd = target_scsi3_emulate_pr_out;
 		break;
 	case RELEASE:
 	case RELEASE_10:
 		if (cdb[0] == RELEASE_10)
-			*size = (cdb[7] << 8) | cdb[8];
+			*size = get_unaligned_be16(&cdb[7]);
 		else
 			*size = cmd->data_length;
 
@@ -1327,7 +1326,7 @@ spc_parse_cdb(struct se_cmd *cmd, unsigned int *size)
 		 * Assume the passthrough or $FABRIC_MOD will tell us about it.
 		 */
 		if (cdb[0] == RESERVE_10)
-			*size = (cdb[7] << 8) | cdb[8];
+			*size = get_unaligned_be16(&cdb[7]);
 		else
 			*size = cmd->data_length;
 
@@ -1338,7 +1337,7 @@ spc_parse_cdb(struct se_cmd *cmd, unsigned int *size)
 		cmd->execute_cmd = spc_emulate_request_sense;
 		break;
 	case INQUIRY:
-		*size = (cdb[3] << 8) + cdb[4];
+		*size = get_unaligned_be16(&cdb[3]);
 
 		/*
 		 * Do implicit HEAD_OF_QUEUE processing for INQUIRY.
@@ -1349,7 +1348,7 @@ spc_parse_cdb(struct se_cmd *cmd, unsigned int *size)
 		break;
 	case SECURITY_PROTOCOL_IN:
 	case SECURITY_PROTOCOL_OUT:
-		*size = (cdb[6] << 24) | (cdb[7] << 16) | (cdb[8] << 8) | cdb[9];
+		*size = get_unaligned_be32(&cdb[6]);
 		break;
 	case EXTENDED_COPY:
 		*size = get_unaligned_be32(&cdb[10]);
@@ -1361,19 +1360,18 @@ spc_parse_cdb(struct se_cmd *cmd, unsigned int *size)
 		break;
 	case READ_ATTRIBUTE:
 	case WRITE_ATTRIBUTE:
-		*size = (cdb[10] << 24) | (cdb[11] << 16) |
-		       (cdb[12] << 8) | cdb[13];
+		*size = get_unaligned_be32(&cdb[10]);
 		break;
 	case RECEIVE_DIAGNOSTIC:
 	case SEND_DIAGNOSTIC:
-		*size = (cdb[3] << 8) | cdb[4];
+		*size = get_unaligned_be16(&cdb[3]);
 		break;
 	case WRITE_BUFFER:
-		*size = (cdb[6] << 16) + (cdb[7] << 8) + cdb[8];
+		*size = get_unaligned_be24(&cdb[6]);
 		break;
 	case REPORT_LUNS:
 		cmd->execute_cmd = spc_emulate_report_luns;
-		*size = (cdb[6] << 24) | (cdb[7] << 16) | (cdb[8] << 8) | cdb[9];
+		*size = get_unaligned_be32(&cdb[6]);
 		/*
 		 * Do implicit HEAD_OF_QUEUE processing for REPORT_LUNS
 		 * See spc4r17 section 5.3
diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c
index cac5a20a4de0..f12cf0c12531 100644
--- a/drivers/target/target_core_xcopy.c
+++ b/drivers/target/target_core_xcopy.c
@@ -311,9 +311,7 @@ static int target_xcopy_parse_segdesc_02(struct se_cmd *se_cmd, struct xcopy_op
 		(unsigned long long)xop->dst_lba);
 
 	if (dc != 0) {
-		xop->dbl = (desc[29] & 0xff) << 16;
-		xop->dbl |= (desc[30] & 0xff) << 8;
-		xop->dbl |= desc[31] & 0xff;
+		xop->dbl = get_unaligned_be24(&desc[29]);
 
 		pr_debug("XCOPY seg desc 0x02: DC=1 w/ dbl: %u\n", xop->dbl);
 	}
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index e475531565fd..b76071161cdc 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -2,6 +2,7 @@
 #define TARGET_CORE_BACKEND_H
 
 #include <linux/types.h>
+#include <asm/unaligned.h>
 #include <target/target_core_base.h>
 
 #define TRANSPORT_FLAG_PASSTHROUGH		0x1
@@ -109,4 +110,11 @@ sector_t target_to_linux_sector(struct se_device *dev, sector_t lb);
 bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib,
 				       struct request_queue *q);
 
+
+/* Only use get_unaligned_be24() if reading p - 1 is allowed. */
+static inline uint32_t get_unaligned_be24(const uint8_t *const p)
+{
+	return get_unaligned_be32(p - 1) & 0xffffffU;
+}
+
 #endif /* TARGET_CORE_BACKEND_H */
-- 
cgit v1.2.3


From 03db016a1bf2d35f41c08aad2ca4f4f18eeda4be Mon Sep 17 00:00:00 2001
From: Nicholas Bellinger <nab@linux-iscsi.org>
Date: Fri, 2 Jun 2017 23:33:56 -0700
Subject: iscsi-target: Kill left-over iscsi_target_do_cleanup

With commit 25cdda95fda7 in place to address the initial login
PDU asynchronous socket close OOPs, go ahead and kill off the
left-over iscsi_target_do_cleanup() and ->login_cleanup_work.

Reported-by: Mike Christie <mchristi@redhat.com>
Cc: Mike Christie <mchristi@redhat.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/iscsi/iscsi_target_nego.c | 24 ------------------------
 include/target/iscsi/iscsi_target_core.h |  1 -
 2 files changed, 25 deletions(-)

(limited to 'include')

diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c
index 6f88b31242b0..96df63f1f795 100644
--- a/drivers/target/iscsi/iscsi_target_nego.c
+++ b/drivers/target/iscsi/iscsi_target_nego.c
@@ -655,28 +655,6 @@ err:
 	iscsit_deaccess_np(np, tpg, tpg_np);
 }
 
-static void iscsi_target_do_cleanup(struct work_struct *work)
-{
-	struct iscsi_conn *conn = container_of(work,
-				struct iscsi_conn, login_cleanup_work.work);
-	struct sock *sk = conn->sock->sk;
-	struct iscsi_login *login = conn->login;
-	struct iscsi_np *np = login->np;
-	struct iscsi_portal_group *tpg = conn->tpg;
-	struct iscsi_tpg_np *tpg_np = conn->tpg_np;
-
-	pr_debug("Entering iscsi_target_do_cleanup\n");
-
-	cancel_delayed_work_sync(&conn->login_work);
-	conn->orig_state_change(sk);
-
-	iscsi_target_restore_sock_callbacks(conn);
-	iscsi_target_login_drop(conn, login);
-	iscsit_deaccess_np(np, tpg, tpg_np);
-
-	pr_debug("iscsi_target_do_cleanup done()\n");
-}
-
 static void iscsi_target_sk_state_change(struct sock *sk)
 {
 	struct iscsi_conn *conn;
@@ -1082,7 +1060,6 @@ int iscsi_target_locate_portal(
 	int sessiontype = 0, ret = 0, tag_num, tag_size;
 
 	INIT_DELAYED_WORK(&conn->login_work, iscsi_target_do_login_rx);
-	INIT_DELAYED_WORK(&conn->login_cleanup_work, iscsi_target_do_cleanup);
 	iscsi_target_set_sock_callbacks(conn);
 
 	login->np = np;
@@ -1331,7 +1308,6 @@ int iscsi_target_start_negotiation(
 
 	if (ret < 0) {
 		cancel_delayed_work_sync(&conn->login_work);
-		cancel_delayed_work_sync(&conn->login_cleanup_work);
 		iscsi_target_restore_sock_callbacks(conn);
 		iscsi_remove_failed_auth_entry(conn);
 	}
diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h
index 5f17fb770477..7948fc68286b 100644
--- a/include/target/iscsi/iscsi_target_core.h
+++ b/include/target/iscsi/iscsi_target_core.h
@@ -560,7 +560,6 @@ struct iscsi_conn {
 #define LOGIN_FLAGS_INITIAL_PDU		8
 	unsigned long		login_flags;
 	struct delayed_work	login_work;
-	struct delayed_work	login_cleanup_work;
 	struct iscsi_login	*login;
 	struct timer_list	nopin_timer;
 	struct timer_list	nopin_response_timer;
-- 
cgit v1.2.3


From c00e6220231542c6409780a3e9bfa44be7d94f3a Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@sandisk.com>
Date: Tue, 23 May 2017 16:48:28 -0700
Subject: target: Introduce a function that shows the command state

Introduce target_show_cmd() and use it where appropriate. If
transport_wait_for_tasks() takes too long, make it show the
state of the command it is waiting for.

(Add missing brackets around multi-line conditions - nab)

Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Andy Grover <agrover@redhat.com>
Cc: David Disseldorp <ddiss@suse.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_tmr.c       |  18 ++---
 drivers/target/target_core_transport.c | 122 +++++++++++++++++++++++++++++----
 include/target/target_core_fabric.h    |   1 +
 3 files changed, 114 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c
index 13f47bf4d16b..e22847bd79b9 100644
--- a/drivers/target/target_core_tmr.c
+++ b/drivers/target/target_core_tmr.c
@@ -355,20 +355,10 @@ static void core_tmr_drain_state_list(
 		cmd = list_entry(drain_task_list.next, struct se_cmd, state_list);
 		list_del_init(&cmd->state_list);
 
-		pr_debug("LUN_RESET: %s cmd: %p"
-			" ITT/CmdSN: 0x%08llx/0x%08x, i_state: %d, t_state: %d"
-			"cdb: 0x%02x\n",
-			(preempt_and_abort_list) ? "Preempt" : "", cmd,
-			cmd->tag, 0,
-			cmd->se_tfo->get_cmd_state(cmd), cmd->t_state,
-			cmd->t_task_cdb[0]);
-		pr_debug("LUN_RESET: ITT[0x%08llx] - pr_res_key: 0x%016Lx"
-			" -- CMD_T_ACTIVE: %d"
-			" CMD_T_STOP: %d CMD_T_SENT: %d\n",
-			cmd->tag, cmd->pr_res_key,
-			(cmd->transport_state & CMD_T_ACTIVE) != 0,
-			(cmd->transport_state & CMD_T_STOP) != 0,
-			(cmd->transport_state & CMD_T_SENT) != 0);
+		target_show_cmd("LUN_RESET: ", cmd);
+		pr_debug("LUN_RESET: ITT[0x%08llx] - %s pr_res_key: 0x%016Lx\n",
+			 cmd->tag, (preempt_and_abort_list) ? "preempt" : "",
+			 cmd->pr_res_key);
 
 		/*
 		 * If the command may be queued onto a workqueue cancel it now.
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index d601616b9f12..a5ecec8f3996 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -1704,15 +1704,9 @@ void transport_generic_request_failure(struct se_cmd *cmd,
 	if (transport_check_aborted_status(cmd, 1))
 		return;
 
-	pr_debug("-----[ Storage Engine Exception for cmd: %p ITT: 0x%08llx"
-		" CDB: 0x%02x\n", cmd, cmd->tag, cmd->t_task_cdb[0]);
-	pr_debug("-----[ i_state: %d t_state: %d sense_reason: %d\n",
-		cmd->se_tfo->get_cmd_state(cmd),
-		cmd->t_state, sense_reason);
-	pr_debug("-----[ CMD_T_ACTIVE: %d CMD_T_STOP: %d CMD_T_SENT: %d\n",
-		(cmd->transport_state & CMD_T_ACTIVE) != 0,
-		(cmd->transport_state & CMD_T_STOP) != 0,
-		(cmd->transport_state & CMD_T_SENT) != 0);
+	pr_debug("-----[ Storage Engine Exception; sense_reason %d\n",
+		 sense_reason);
+	target_show_cmd("-----[ ", cmd);
 
 	/*
 	 * For SAM Task Attribute emulation for failed struct se_cmd
@@ -2705,6 +2699,108 @@ int target_put_sess_cmd(struct se_cmd *se_cmd)
 }
 EXPORT_SYMBOL(target_put_sess_cmd);
 
+static const char *data_dir_name(enum dma_data_direction d)
+{
+	switch (d) {
+	case DMA_BIDIRECTIONAL:	return "BIDI";
+	case DMA_TO_DEVICE:	return "WRITE";
+	case DMA_FROM_DEVICE:	return "READ";
+	case DMA_NONE:		return "NONE";
+	}
+
+	return "(?)";
+}
+
+static const char *cmd_state_name(enum transport_state_table t)
+{
+	switch (t) {
+	case TRANSPORT_NO_STATE:	return "NO_STATE";
+	case TRANSPORT_NEW_CMD:		return "NEW_CMD";
+	case TRANSPORT_WRITE_PENDING:	return "WRITE_PENDING";
+	case TRANSPORT_PROCESSING:	return "PROCESSING";
+	case TRANSPORT_COMPLETE:	return "COMPLETE";
+	case TRANSPORT_ISTATE_PROCESSING:
+					return "ISTATE_PROCESSING";
+	case TRANSPORT_COMPLETE_QF_WP:	return "COMPLETE_QF_WP";
+	case TRANSPORT_COMPLETE_QF_OK:	return "COMPLETE_QF_OK";
+	case TRANSPORT_COMPLETE_QF_ERR:	return "COMPLETE_QF_ERR";
+	}
+
+	return "(?)";
+}
+
+static void target_append_str(char **str, const char *txt)
+{
+	char *prev = *str;
+
+	*str = *str ? kasprintf(GFP_ATOMIC, "%s,%s", *str, txt) :
+		kstrdup(txt, GFP_ATOMIC);
+	kfree(prev);
+}
+
+/*
+ * Convert a transport state bitmask into a string. The caller is
+ * responsible for freeing the returned pointer.
+ */
+static char *target_ts_to_str(u32 ts)
+{
+	char *str = NULL;
+
+	if (ts & CMD_T_ABORTED)
+		target_append_str(&str, "aborted");
+	if (ts & CMD_T_ACTIVE)
+		target_append_str(&str, "active");
+	if (ts & CMD_T_COMPLETE)
+		target_append_str(&str, "complete");
+	if (ts & CMD_T_SENT)
+		target_append_str(&str, "sent");
+	if (ts & CMD_T_STOP)
+		target_append_str(&str, "stop");
+	if (ts & CMD_T_FABRIC_STOP)
+		target_append_str(&str, "fabric_stop");
+
+	return str;
+}
+
+static const char *target_tmf_name(enum tcm_tmreq_table tmf)
+{
+	switch (tmf) {
+	case TMR_ABORT_TASK:		return "ABORT_TASK";
+	case TMR_ABORT_TASK_SET:	return "ABORT_TASK_SET";
+	case TMR_CLEAR_ACA:		return "CLEAR_ACA";
+	case TMR_CLEAR_TASK_SET:	return "CLEAR_TASK_SET";
+	case TMR_LUN_RESET:		return "LUN_RESET";
+	case TMR_TARGET_WARM_RESET:	return "TARGET_WARM_RESET";
+	case TMR_TARGET_COLD_RESET:	return "TARGET_COLD_RESET";
+	case TMR_UNKNOWN:		break;
+	}
+	return "(?)";
+}
+
+void target_show_cmd(const char *pfx, struct se_cmd *cmd)
+{
+	char *ts_str = target_ts_to_str(cmd->transport_state);
+	const u8 *cdb = cmd->t_task_cdb;
+	struct se_tmr_req *tmf = cmd->se_tmr_req;
+
+	if (!(cmd->se_cmd_flags & SCF_SCSI_TMR_CDB)) {
+		pr_debug("%scmd %#02x:%#02x with tag %#llx dir %s i_state %d t_state %s len %d refcnt %d transport_state %s\n",
+			 pfx, cdb[0], cdb[1], cmd->tag,
+			 data_dir_name(cmd->data_direction),
+			 cmd->se_tfo->get_cmd_state(cmd),
+			 cmd_state_name(cmd->t_state), cmd->data_length,
+			 kref_read(&cmd->cmd_kref), ts_str);
+	} else {
+		pr_debug("%stmf %s with tag %#llx ref_task_tag %#llx i_state %d t_state %s refcnt %d transport_state %s\n",
+			 pfx, target_tmf_name(tmf->function), cmd->tag,
+			 tmf->ref_task_tag, cmd->se_tfo->get_cmd_state(cmd),
+			 cmd_state_name(cmd->t_state),
+			 kref_read(&cmd->cmd_kref), ts_str);
+	}
+	kfree(ts_str);
+}
+EXPORT_SYMBOL(target_show_cmd);
+
 /* target_sess_cmd_list_set_waiting - Flag all commands in
  *         sess_cmd_list to complete cmd_wait_comp.  Set
  *         sess_tearing_down so no more commands are queued.
@@ -2849,13 +2945,13 @@ __transport_wait_for_tasks(struct se_cmd *cmd, bool fabric_stop,
 
 	cmd->transport_state |= CMD_T_STOP;
 
-	pr_debug("wait_for_tasks: Stopping %p ITT: 0x%08llx i_state: %d,"
-		 " t_state: %d, CMD_T_STOP\n", cmd, cmd->tag,
-		 cmd->se_tfo->get_cmd_state(cmd), cmd->t_state);
+	target_show_cmd("wait_for_tasks: Stopping ", cmd);
 
 	spin_unlock_irqrestore(&cmd->t_state_lock, *flags);
 
-	wait_for_completion(&cmd->t_transport_stop_comp);
+	while (!wait_for_completion_timeout(&cmd->t_transport_stop_comp,
+					    180 * HZ))
+		target_show_cmd("wait for tasks: ", cmd);
 
 	spin_lock_irqsave(&cmd->t_state_lock, *flags);
 	cmd->transport_state &= ~(CMD_T_ACTIVE | CMD_T_STOP);
diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h
index d7dd1427fe0d..33d2e3e5773c 100644
--- a/include/target/target_core_fabric.h
+++ b/include/target/target_core_fabric.h
@@ -160,6 +160,7 @@ int	target_get_sess_cmd(struct se_cmd *, bool);
 int	target_put_sess_cmd(struct se_cmd *);
 void	target_sess_cmd_list_set_waiting(struct se_session *);
 void	target_wait_for_sess_cmds(struct se_session *);
+void	target_show_cmd(const char *pfx, struct se_cmd *cmd);
 
 int	core_alua_check_nonop_delay(struct se_cmd *);
 
-- 
cgit v1.2.3


From 1068be7bd4b05ca41a6a8de724f52a9c87861412 Mon Sep 17 00:00:00 2001
From: "Bryant G. Ly" <bryantly@linux.vnet.ibm.com>
Date: Tue, 6 Jun 2017 09:28:49 -0500
Subject: tcmu: Add netlink for device reconfiguration

This gives tcmu the ability to handle events that can cause
reconfiguration, such as resize, path changes, write_cache, etc...

Signed-off-by: Bryant G. Ly <bryantly@linux.vnet.ibm.com>
Reviewed-By: Mike Christie <mchristi@redhat.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_user.c     | 12 ++++++++++++
 include/uapi/linux/target_core_user.h |  1 +
 2 files changed, 13 insertions(+)

(limited to 'include')

diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 0c797cc69d9e..ae918222284b 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -1562,6 +1562,7 @@ static ssize_t tcmu_emulate_write_cache_store(struct config_item *item,
 {
 	struct se_dev_attrib *da = container_of(to_config_group(item),
 					struct se_dev_attrib, da_group);
+	struct tcmu_dev *udev = TCMU_DEV(da->da_dev);
 	int val;
 	int ret;
 
@@ -1570,6 +1571,17 @@ static ssize_t tcmu_emulate_write_cache_store(struct config_item *item,
 		return ret;
 
 	da->emulate_write_cache = val;
+
+	/* Check if device has been configured before */
+	if (tcmu_dev_configured(udev)) {
+		ret = tcmu_netlink_event(TCMU_CMD_RECONFIG_DEVICE,
+					 udev->uio_info.name,
+					 udev->uio_info.uio_dev->minor);
+		if (ret) {
+			pr_err("Unable to reconfigure device\n");
+			return ret;
+		}
+	}
 	return count;
 }
 CONFIGFS_ATTR(tcmu_, emulate_write_cache);
diff --git a/include/uapi/linux/target_core_user.h b/include/uapi/linux/target_core_user.h
index af17b4154ef6..403a61faada0 100644
--- a/include/uapi/linux/target_core_user.h
+++ b/include/uapi/linux/target_core_user.h
@@ -130,6 +130,7 @@ enum tcmu_genl_cmd {
 	TCMU_CMD_UNSPEC,
 	TCMU_CMD_ADDED_DEVICE,
 	TCMU_CMD_REMOVED_DEVICE,
+	TCMU_CMD_RECONFIG_DEVICE,
 	__TCMU_CMD_MAX,
 };
 #define TCMU_CMD_MAX (__TCMU_CMD_MAX - 1)
-- 
cgit v1.2.3


From 8a45885c1514cdae2ee64b5ac03ffc00a1a8a9d7 Mon Sep 17 00:00:00 2001
From: "Bryant G. Ly" <bryantly@linux.vnet.ibm.com>
Date: Tue, 6 Jun 2017 09:28:52 -0500
Subject: tcmu: Add Type of reconfig into netlink

This patch adds more info about the attribute being changed,
so that usersapce can easily figure out what is happening.

Signed-off-by: Bryant G. Ly <bryantly@linux.vnet.ibm.com>
Reviewed-By: Mike Christie <mchristi@redhat.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_user.c     | 20 ++++++++++++++------
 include/uapi/linux/target_core_user.h |  8 ++++++++
 2 files changed, 22 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 7c6475731895..afc1fd6bacaf 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -1176,7 +1176,8 @@ static int tcmu_release(struct uio_info *info, struct inode *inode)
 	return 0;
 }
 
-static int tcmu_netlink_event(enum tcmu_genl_cmd cmd, const char *name, int minor)
+static int tcmu_netlink_event(enum tcmu_genl_cmd cmd, const char *name,
+			      int minor, int type)
 {
 	struct sk_buff *skb;
 	void *msg_header;
@@ -1198,6 +1199,10 @@ static int tcmu_netlink_event(enum tcmu_genl_cmd cmd, const char *name, int mino
 	if (ret < 0)
 		goto free_skb;
 
+	ret = nla_put_u32(skb, TCMU_ATTR_TYPE, type);
+	if (ret < 0)
+		goto free_skb;
+
 	genlmsg_end(skb, msg_header);
 
 	ret = genlmsg_multicast_allns(&tcmu_genl_family, skb, 0,
@@ -1301,7 +1306,7 @@ static int tcmu_configure_device(struct se_device *dev)
 	kref_get(&udev->kref);
 
 	ret = tcmu_netlink_event(TCMU_CMD_ADDED_DEVICE, udev->uio_info.name,
-				 udev->uio_info.uio_dev->minor);
+				 udev->uio_info.uio_dev->minor, NO_RECONFIG);
 	if (ret)
 		goto err_netlink;
 
@@ -1383,7 +1388,7 @@ static void tcmu_free_device(struct se_device *dev)
 
 	if (tcmu_dev_configured(udev)) {
 		tcmu_netlink_event(TCMU_CMD_REMOVED_DEVICE, udev->uio_info.name,
-				   udev->uio_info.uio_dev->minor);
+				   udev->uio_info.uio_dev->minor, NO_RECONFIG);
 
 		uio_unregister_device(&udev->uio_info);
 	}
@@ -1577,7 +1582,8 @@ static ssize_t tcmu_dev_path_store(struct config_item *item, const char *page,
 	if (tcmu_dev_configured(udev)) {
 		ret = tcmu_netlink_event(TCMU_CMD_RECONFIG_DEVICE,
 					 udev->uio_info.name,
-					 udev->uio_info.uio_dev->minor);
+					 udev->uio_info.uio_dev->minor,
+					 CONFIG_PATH);
 		if (ret) {
 			pr_err("Unable to reconfigure device\n");
 			return ret;
@@ -1615,7 +1621,8 @@ static ssize_t tcmu_dev_size_store(struct config_item *item, const char *page,
 	if (tcmu_dev_configured(udev)) {
 		ret = tcmu_netlink_event(TCMU_CMD_RECONFIG_DEVICE,
 					 udev->uio_info.name,
-					 udev->uio_info.uio_dev->minor);
+					 udev->uio_info.uio_dev->minor,
+					 CONFIG_SIZE);
 		if (ret) {
 			pr_err("Unable to reconfigure device\n");
 			return ret;
@@ -1654,7 +1661,8 @@ static ssize_t tcmu_emulate_write_cache_store(struct config_item *item,
 	if (tcmu_dev_configured(udev)) {
 		ret = tcmu_netlink_event(TCMU_CMD_RECONFIG_DEVICE,
 					 udev->uio_info.name,
-					 udev->uio_info.uio_dev->minor);
+					 udev->uio_info.uio_dev->minor,
+					 CONFIG_WRITECACHE);
 		if (ret) {
 			pr_err("Unable to reconfigure device\n");
 			return ret;
diff --git a/include/uapi/linux/target_core_user.h b/include/uapi/linux/target_core_user.h
index 403a61faada0..5b00e3500005 100644
--- a/include/uapi/linux/target_core_user.h
+++ b/include/uapi/linux/target_core_user.h
@@ -139,8 +139,16 @@ enum tcmu_genl_attr {
 	TCMU_ATTR_UNSPEC,
 	TCMU_ATTR_DEVICE,
 	TCMU_ATTR_MINOR,
+	TCMU_ATTR_TYPE,
 	__TCMU_ATTR_MAX,
 };
 #define TCMU_ATTR_MAX (__TCMU_ATTR_MAX - 1)
 
+enum tcmu_reconfig_types {
+	NO_RECONFIG,
+	CONFIG_PATH,
+	CONFIG_SIZE,
+	CONFIG_WRITECACHE,
+};
+
 #endif
-- 
cgit v1.2.3


From 2d76443e02f260d7a5bd0ede1851ae5534f0c68d Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Mon, 12 Jun 2017 01:34:28 -0500
Subject: tcmu: reconfigure netlink attr changes

1. TCMU_ATTR_TYPE is too generic when it describes only the
reconfiguration type, so rename to TCMU_ATTR_RECONFIG_TYPE.

2. Only return the reconfig type when it is a
TCMU_CMD_RECONFIG_DEVICE command.

3. CONFIG_* type is not needed. We can pass the value along with an
ATTR to userspace, so it does not need to read sysfs/configfs.

4. Fix leak in tcmu_dev_path_store and rename to dev_config to
reflect it is more than just a path that can be changed.

6. Don't update kernel struct value if netlink sending fails.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Reviewed-by: "Bryant G. Ly" <bryantly@linux.vnet.ibm.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_user.c     | 73 +++++++++++++++++++++--------------
 include/uapi/linux/target_core_user.h | 12 ++----
 2 files changed, 48 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 6322269d9e85..ca5b081295db 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -1177,7 +1177,8 @@ static int tcmu_release(struct uio_info *info, struct inode *inode)
 }
 
 static int tcmu_netlink_event(enum tcmu_genl_cmd cmd, const char *name,
-			      int minor, int type)
+			      int minor, int reconfig_attr,
+			      const void *reconfig_data)
 {
 	struct sk_buff *skb;
 	void *msg_header;
@@ -1199,9 +1200,27 @@ static int tcmu_netlink_event(enum tcmu_genl_cmd cmd, const char *name,
 	if (ret < 0)
 		goto free_skb;
 
-	ret = nla_put_u32(skb, TCMU_ATTR_TYPE, type);
-	if (ret < 0)
-		goto free_skb;
+	if (cmd == TCMU_CMD_RECONFIG_DEVICE) {
+		switch (reconfig_attr) {
+		case TCMU_ATTR_DEV_CFG:
+			ret = nla_put_string(skb, reconfig_attr, reconfig_data);
+			break;
+		case TCMU_ATTR_DEV_SIZE:
+			ret = nla_put_u64_64bit(skb, reconfig_attr,
+						*((u64 *)reconfig_data),
+						TCMU_ATTR_PAD);
+			break;
+		case TCMU_ATTR_WRITECACHE:
+			ret = nla_put_u8(skb, reconfig_attr,
+					  *((u8 *)reconfig_data));
+			break;
+		default:
+			BUG();
+		}
+
+		if (ret < 0)
+			goto free_skb;
+	}
 
 	genlmsg_end(skb, msg_header);
 
@@ -1306,7 +1325,7 @@ static int tcmu_configure_device(struct se_device *dev)
 	kref_get(&udev->kref);
 
 	ret = tcmu_netlink_event(TCMU_CMD_ADDED_DEVICE, udev->uio_info.name,
-				 udev->uio_info.uio_dev->minor, NO_RECONFIG);
+				 udev->uio_info.uio_dev->minor, 0, NULL);
 	if (ret)
 		goto err_netlink;
 
@@ -1388,7 +1407,7 @@ static void tcmu_free_device(struct se_device *dev)
 
 	if (tcmu_dev_configured(udev)) {
 		tcmu_netlink_event(TCMU_CMD_REMOVED_DEVICE, udev->uio_info.name,
-				   udev->uio_info.uio_dev->minor, NO_RECONFIG);
+				   udev->uio_info.uio_dev->minor, 0, NULL);
 
 		uio_unregister_device(&udev->uio_info);
 	}
@@ -1553,7 +1572,7 @@ static ssize_t tcmu_cmd_time_out_store(struct config_item *item, const char *pag
 }
 CONFIGFS_ATTR(tcmu_, cmd_time_out);
 
-static ssize_t tcmu_dev_path_show(struct config_item *item, char *page)
+static ssize_t tcmu_dev_config_show(struct config_item *item, char *page)
 {
 	struct se_dev_attrib *da = container_of(to_config_group(item),
 						struct se_dev_attrib, da_group);
@@ -1562,37 +1581,34 @@ static ssize_t tcmu_dev_path_show(struct config_item *item, char *page)
 	return snprintf(page, PAGE_SIZE, "%s\n", udev->dev_config);
 }
 
-static ssize_t tcmu_dev_path_store(struct config_item *item, const char *page,
-				   size_t count)
+static ssize_t tcmu_dev_config_store(struct config_item *item, const char *page,
+				     size_t count)
 {
 	struct se_dev_attrib *da = container_of(to_config_group(item),
 						struct se_dev_attrib, da_group);
 	struct tcmu_dev *udev = TCMU_DEV(da->da_dev);
-	char *copy = NULL;
-	int ret;
+	int ret, len;
 
-	copy = kstrdup(page, GFP_KERNEL);
-	if (!copy) {
-		kfree(copy);
+	len = strlen(page);
+	if (!len || len > TCMU_CONFIG_LEN - 1)
 		return -EINVAL;
-	}
-	strlcpy(udev->dev_config, copy, TCMU_CONFIG_LEN);
 
 	/* Check if device has been configured before */
 	if (tcmu_dev_configured(udev)) {
 		ret = tcmu_netlink_event(TCMU_CMD_RECONFIG_DEVICE,
 					 udev->uio_info.name,
 					 udev->uio_info.uio_dev->minor,
-					 CONFIG_PATH);
+					 TCMU_ATTR_DEV_CFG, page);
 		if (ret) {
 			pr_err("Unable to reconfigure device\n");
 			return ret;
 		}
 	}
+	strlcpy(udev->dev_config, page, TCMU_CONFIG_LEN);
 
 	return count;
 }
-CONFIGFS_ATTR(tcmu_, dev_path);
+CONFIGFS_ATTR(tcmu_, dev_config);
 
 static ssize_t tcmu_dev_size_show(struct config_item *item, char *page)
 {
@@ -1609,26 +1625,25 @@ static ssize_t tcmu_dev_size_store(struct config_item *item, const char *page,
 	struct se_dev_attrib *da = container_of(to_config_group(item),
 						struct se_dev_attrib, da_group);
 	struct tcmu_dev *udev = TCMU_DEV(da->da_dev);
-	unsigned long val;
+	u64 val;
 	int ret;
 
-	ret = kstrtoul(page, 0, &val);
+	ret = kstrtou64(page, 0, &val);
 	if (ret < 0)
 		return ret;
-	udev->dev_size = val;
 
 	/* Check if device has been configured before */
 	if (tcmu_dev_configured(udev)) {
 		ret = tcmu_netlink_event(TCMU_CMD_RECONFIG_DEVICE,
 					 udev->uio_info.name,
 					 udev->uio_info.uio_dev->minor,
-					 CONFIG_SIZE);
+					 TCMU_ATTR_DEV_SIZE, &val);
 		if (ret) {
 			pr_err("Unable to reconfigure device\n");
 			return ret;
 		}
 	}
-
+	udev->dev_size = val;
 	return count;
 }
 CONFIGFS_ATTR(tcmu_, dev_size);
@@ -1648,33 +1663,33 @@ static ssize_t tcmu_emulate_write_cache_store(struct config_item *item,
 	struct se_dev_attrib *da = container_of(to_config_group(item),
 					struct se_dev_attrib, da_group);
 	struct tcmu_dev *udev = TCMU_DEV(da->da_dev);
-	int val;
+	u8 val;
 	int ret;
 
-	ret = kstrtouint(page, 0, &val);
+	ret = kstrtou8(page, 0, &val);
 	if (ret < 0)
 		return ret;
 
-	da->emulate_write_cache = val;
-
 	/* Check if device has been configured before */
 	if (tcmu_dev_configured(udev)) {
 		ret = tcmu_netlink_event(TCMU_CMD_RECONFIG_DEVICE,
 					 udev->uio_info.name,
 					 udev->uio_info.uio_dev->minor,
-					 CONFIG_WRITECACHE);
+					 TCMU_ATTR_WRITECACHE, &val);
 		if (ret) {
 			pr_err("Unable to reconfigure device\n");
 			return ret;
 		}
 	}
+
+	da->emulate_write_cache = val;
 	return count;
 }
 CONFIGFS_ATTR(tcmu_, emulate_write_cache);
 
 static struct configfs_attribute *tcmu_attrib_attrs[] = {
 	&tcmu_attr_cmd_time_out,
-	&tcmu_attr_dev_path,
+	&tcmu_attr_dev_config,
 	&tcmu_attr_dev_size,
 	&tcmu_attr_emulate_write_cache,
 	NULL,
diff --git a/include/uapi/linux/target_core_user.h b/include/uapi/linux/target_core_user.h
index 5b00e3500005..4bfc9a1b635c 100644
--- a/include/uapi/linux/target_core_user.h
+++ b/include/uapi/linux/target_core_user.h
@@ -139,16 +139,12 @@ enum tcmu_genl_attr {
 	TCMU_ATTR_UNSPEC,
 	TCMU_ATTR_DEVICE,
 	TCMU_ATTR_MINOR,
-	TCMU_ATTR_TYPE,
+	TCMU_ATTR_PAD,
+	TCMU_ATTR_DEV_CFG,
+	TCMU_ATTR_DEV_SIZE,
+	TCMU_ATTR_WRITECACHE,
 	__TCMU_ATTR_MAX,
 };
 #define TCMU_ATTR_MAX (__TCMU_ATTR_MAX - 1)
 
-enum tcmu_reconfig_types {
-	NO_RECONFIG,
-	CONFIG_PATH,
-	CONFIG_SIZE,
-	CONFIG_WRITECACHE,
-};
-
 #endif
-- 
cgit v1.2.3


From 926347061ef1f4d3873829fd1960c6e4b965aa9f Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Fri, 23 Jun 2017 01:18:12 -0500
Subject: target: break up free_device callback

With this patch free_device is now used to free what is allocated in the
alloc_device callback and destroy_device tears down the resources that are
setup in the configure_device callback.

This patch will be needed in the next patch where tcmu needs
to be able to look up the device in the destroy callback.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_device.c  |  2 ++
 drivers/target/target_core_file.c    |  7 ++++++-
 drivers/target/target_core_iblock.c  |  8 ++++++--
 drivers/target/target_core_pscsi.c   |  7 ++++++-
 drivers/target/target_core_rd.c      |  7 ++++++-
 drivers/target/target_core_user.c    | 12 +++++++++---
 include/target/target_core_backend.h |  1 +
 7 files changed, 36 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 11c80c47b9d3..16a701fed66b 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -974,6 +974,8 @@ void target_free_device(struct se_device *dev)
 	if (dev->dev_flags & DF_CONFIGURED) {
 		destroy_workqueue(dev->tmr_wq);
 
+		dev->transport->destroy_device(dev);
+
 		mutex_lock(&g_device_mutex);
 		list_del(&dev->g_dev_node);
 		mutex_unlock(&g_device_mutex);
diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c
index 73b8f93a5fef..50f235580546 100644
--- a/drivers/target/target_core_file.c
+++ b/drivers/target/target_core_file.c
@@ -236,6 +236,11 @@ static void fd_dev_call_rcu(struct rcu_head *p)
 }
 
 static void fd_free_device(struct se_device *dev)
+{
+	call_rcu(&dev->rcu_head, fd_dev_call_rcu);
+}
+
+static void fd_destroy_device(struct se_device *dev)
 {
 	struct fd_dev *fd_dev = FD_DEV(dev);
 
@@ -243,7 +248,6 @@ static void fd_free_device(struct se_device *dev)
 		filp_close(fd_dev->fd_file, NULL);
 		fd_dev->fd_file = NULL;
 	}
-	call_rcu(&dev->rcu_head, fd_dev_call_rcu);
 }
 
 static int fd_do_rw(struct se_cmd *cmd, struct file *fd,
@@ -826,6 +830,7 @@ static const struct target_backend_ops fileio_ops = {
 	.detach_hba		= fd_detach_hba,
 	.alloc_device		= fd_alloc_device,
 	.configure_device	= fd_configure_device,
+	.destroy_device		= fd_destroy_device,
 	.free_device		= fd_free_device,
 	.parse_cdb		= fd_parse_cdb,
 	.set_configfs_dev_params = fd_set_configfs_dev_params,
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index b2044133d747..a5e16f715392 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -189,6 +189,11 @@ static void iblock_dev_call_rcu(struct rcu_head *p)
 }
 
 static void iblock_free_device(struct se_device *dev)
+{
+	call_rcu(&dev->rcu_head, iblock_dev_call_rcu);
+}
+
+static void iblock_destroy_device(struct se_device *dev)
 {
 	struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
 
@@ -196,8 +201,6 @@ static void iblock_free_device(struct se_device *dev)
 		blkdev_put(ib_dev->ibd_bd, FMODE_WRITE|FMODE_READ|FMODE_EXCL);
 	if (ib_dev->ibd_bio_set != NULL)
 		bioset_free(ib_dev->ibd_bio_set);
-
-	call_rcu(&dev->rcu_head, iblock_dev_call_rcu);
 }
 
 static unsigned long long iblock_emulate_read_cap_with_block_size(
@@ -858,6 +861,7 @@ static const struct target_backend_ops iblock_ops = {
 	.detach_hba		= iblock_detach_hba,
 	.alloc_device		= iblock_alloc_device,
 	.configure_device	= iblock_configure_device,
+	.destroy_device		= iblock_destroy_device,
 	.free_device		= iblock_free_device,
 	.parse_cdb		= iblock_parse_cdb,
 	.set_configfs_dev_params = iblock_set_configfs_dev_params,
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index e0be4aa38328..7d944b23aeee 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -563,6 +563,11 @@ static void pscsi_dev_call_rcu(struct rcu_head *p)
 }
 
 static void pscsi_free_device(struct se_device *dev)
+{
+	call_rcu(&dev->rcu_head, pscsi_dev_call_rcu);
+}
+
+static void pscsi_destroy_device(struct se_device *dev)
 {
 	struct pscsi_dev_virt *pdv = PSCSI_DEV(dev);
 	struct pscsi_hba_virt *phv = dev->se_hba->hba_ptr;
@@ -592,7 +597,6 @@ static void pscsi_free_device(struct se_device *dev)
 
 		pdv->pdv_sd = NULL;
 	}
-	call_rcu(&dev->rcu_head, pscsi_dev_call_rcu);
 }
 
 static void pscsi_transport_complete(struct se_cmd *cmd, struct scatterlist *sg,
@@ -1084,6 +1088,7 @@ static const struct target_backend_ops pscsi_ops = {
 	.pmode_enable_hba	= pscsi_pmode_enable_hba,
 	.alloc_device		= pscsi_alloc_device,
 	.configure_device	= pscsi_configure_device,
+	.destroy_device		= pscsi_destroy_device,
 	.free_device		= pscsi_free_device,
 	.transport_complete	= pscsi_transport_complete,
 	.parse_cdb		= pscsi_parse_cdb,
diff --git a/drivers/target/target_core_rd.c b/drivers/target/target_core_rd.c
index d12967690054..a6e8106abd6f 100644
--- a/drivers/target/target_core_rd.c
+++ b/drivers/target/target_core_rd.c
@@ -338,11 +338,15 @@ static void rd_dev_call_rcu(struct rcu_head *p)
 }
 
 static void rd_free_device(struct se_device *dev)
+{
+	call_rcu(&dev->rcu_head, rd_dev_call_rcu);
+}
+
+static void rd_destroy_device(struct se_device *dev)
 {
 	struct rd_dev *rd_dev = RD_DEV(dev);
 
 	rd_release_device_space(rd_dev);
-	call_rcu(&dev->rcu_head, rd_dev_call_rcu);
 }
 
 static struct rd_dev_sg_table *rd_get_sg_table(struct rd_dev *rd_dev, u32 page)
@@ -651,6 +655,7 @@ static const struct target_backend_ops rd_mcp_ops = {
 	.detach_hba		= rd_detach_hba,
 	.alloc_device		= rd_alloc_device,
 	.configure_device	= rd_configure_device,
+	.destroy_device		= rd_destroy_device,
 	.free_device		= rd_free_device,
 	.parse_cdb		= rd_parse_cdb,
 	.set_configfs_dev_params = rd_set_configfs_dev_params,
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index ca5b081295db..e58127b8db8a 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -1379,6 +1379,14 @@ static void tcmu_blocks_release(struct tcmu_dev *udev)
 }
 
 static void tcmu_free_device(struct se_device *dev)
+{
+	struct tcmu_dev *udev = TCMU_DEV(dev);
+
+	/* release ref from init */
+	kref_put(&udev->kref, tcmu_dev_kref_release);
+}
+
+static void tcmu_destroy_device(struct se_device *dev)
 {
 	struct tcmu_dev *udev = TCMU_DEV(dev);
 	struct tcmu_cmd *cmd;
@@ -1411,9 +1419,6 @@ static void tcmu_free_device(struct se_device *dev)
 
 		uio_unregister_device(&udev->uio_info);
 	}
-
-	/* release ref from init */
-	kref_put(&udev->kref, tcmu_dev_kref_release);
 }
 
 enum {
@@ -1705,6 +1710,7 @@ static struct target_backend_ops tcmu_ops = {
 	.detach_hba		= tcmu_detach_hba,
 	.alloc_device		= tcmu_alloc_device,
 	.configure_device	= tcmu_configure_device,
+	.destroy_device		= tcmu_destroy_device,
 	.free_device		= tcmu_free_device,
 	.parse_cdb		= tcmu_parse_cdb,
 	.set_configfs_dev_params = tcmu_set_configfs_dev_params,
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index b76071161cdc..3dbcacd7e8d7 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -30,6 +30,7 @@ struct target_backend_ops {
 
 	struct se_device *(*alloc_device)(struct se_hba *, const char *);
 	int (*configure_device)(struct se_device *);
+	void (*destroy_device)(struct se_device *);
 	void (*free_device)(struct se_device *device);
 
 	ssize_t (*set_configfs_dev_params)(struct se_device *,
-- 
cgit v1.2.3


From 0a5eee647b78e53da05e081362f42a11b4b674eb Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Fri, 23 Jun 2017 01:18:13 -0500
Subject: target: use idr for se_device dev index

In the next patches we will add tcmu netlink support that allows
userspace to send commands to target_core_user. To execute operations
on a se_device/tcmu_dev we need to be able to look up a dev by any old
id. This patch replaces the se_device->dev_index with a idr created
id.

The next patches will also remove the g_device_list and replace it with
the idr.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_device.c | 30 ++++++++++++++++++++++++++----
 include/target/target_core_base.h   |  1 -
 2 files changed, 26 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 16a701fed66b..f10dfe7b1d54 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -51,6 +51,7 @@
 
 DEFINE_MUTEX(g_device_mutex);
 LIST_HEAD(g_device_list);
+static DEFINE_IDR(devices_idr);
 
 static struct se_hba *lun0_hba;
 /* not static, needed by tpg.c */
@@ -882,7 +883,7 @@ EXPORT_SYMBOL(target_to_linux_sector);
 int target_configure_device(struct se_device *dev)
 {
 	struct se_hba *hba = dev->se_hba;
-	int ret;
+	int ret, id;
 
 	if (dev->dev_flags & DF_CONFIGURED) {
 		pr_err("se_dev->se_dev_ptr already set for storage"
@@ -890,9 +891,26 @@ int target_configure_device(struct se_device *dev)
 		return -EEXIST;
 	}
 
+	/*
+	 * Add early so modules like tcmu can use during its
+	 * configuration.
+	 */
+	mutex_lock(&g_device_mutex);
+	/*
+	 * Use cyclic to try and avoid collisions with devices
+	 * that were recently removed.
+	 */
+	id = idr_alloc_cyclic(&devices_idr, dev, 0, INT_MAX, GFP_KERNEL);
+	mutex_unlock(&g_device_mutex);
+	if (id < 0) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	dev->dev_index = id;
+
 	ret = dev->transport->configure_device(dev);
 	if (ret)
-		goto out;
+		goto out_free_index;
 	/*
 	 * XXX: there is not much point to have two different values here..
 	 */
@@ -907,12 +925,11 @@ int target_configure_device(struct se_device *dev)
 					 dev->dev_attrib.hw_block_size);
 	dev->dev_attrib.optimal_sectors = dev->dev_attrib.hw_max_sectors;
 
-	dev->dev_index = scsi_get_new_index(SCSI_DEVICE_INDEX);
 	dev->creation_time = get_jiffies_64();
 
 	ret = core_setup_alua(dev);
 	if (ret)
-		goto out;
+		goto out_free_index;
 
 	/*
 	 * Startup the struct se_device processing thread
@@ -960,6 +977,10 @@ int target_configure_device(struct se_device *dev)
 
 out_free_alua:
 	core_alua_free_lu_gp_mem(dev);
+out_free_index:
+	mutex_lock(&g_device_mutex);
+	idr_remove(&devices_idr, dev->dev_index);
+	mutex_unlock(&g_device_mutex);
 out:
 	se_release_vpd_for_dev(dev);
 	return ret;
@@ -977,6 +998,7 @@ void target_free_device(struct se_device *dev)
 		dev->transport->destroy_device(dev);
 
 		mutex_lock(&g_device_mutex);
+		idr_remove(&devices_idr, dev->dev_index);
 		list_del(&dev->g_dev_node);
 		mutex_unlock(&g_device_mutex);
 
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index a3af69fcf75e..51a92f17352c 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -219,7 +219,6 @@ enum tcm_tmrsp_table {
  */
 typedef enum {
 	SCSI_INST_INDEX,
-	SCSI_DEVICE_INDEX,
 	SCSI_AUTH_INTR_INDEX,
 	SCSI_INDEX_TYPE_MAX
 } scsi_index_t;
-- 
cgit v1.2.3


From 85441e6b8c97964a6da72135dc21f708adbdc4d8 Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Fri, 23 Jun 2017 01:18:14 -0500
Subject: target: add helper to find se_device by dev_index

This adds a helper to find a se_device by dev_index. It will
be used in the next patches so tcmu's netlink interface can
execute commands on specific devices.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_device.c  | 24 ++++++++++++++++++++++++
 include/target/target_core_backend.h |  2 ++
 2 files changed, 26 insertions(+)

(limited to 'include')

diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index f10dfe7b1d54..de1131612ddc 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -880,6 +880,30 @@ sector_t target_to_linux_sector(struct se_device *dev, sector_t lb)
 }
 EXPORT_SYMBOL(target_to_linux_sector);
 
+/**
+ * target_find_device - find a se_device by its dev_index
+ * @id: dev_index
+ * @do_depend: true if caller needs target_depend_item to be done
+ *
+ * If do_depend is true, the caller must do a target_undepend_item
+ * when finished using the device.
+ *
+ * If do_depend is false, the caller must be called in a configfs
+ * callback or during removal.
+ */
+struct se_device *target_find_device(int id, bool do_depend)
+{
+	struct se_device *dev;
+
+	mutex_lock(&g_device_mutex);
+	dev = idr_find(&devices_idr, id);
+	if (dev && do_depend && target_depend_item(&dev->dev_group.cg_item))
+		dev = NULL;
+	mutex_unlock(&g_device_mutex);
+	return dev;
+}
+EXPORT_SYMBOL(target_find_device);
+
 int target_configure_device(struct se_device *dev)
 {
 	struct se_hba *hba = dev->se_hba;
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index 3dbcacd7e8d7..1f2b7007f2df 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -106,6 +106,8 @@ bool	target_lun_is_rdonly(struct se_cmd *);
 sense_reason_t passthrough_parse_cdb(struct se_cmd *cmd,
 	sense_reason_t (*exec_cmd)(struct se_cmd *cmd));
 
+struct	se_device *target_find_device(int id, bool do_depend);
+
 bool target_sense_desc_format(struct se_device *dev);
 sector_t target_to_linux_sector(struct se_device *dev, sector_t lb);
 bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib,
-- 
cgit v1.2.3


From b3af66e24393f03ef81db17a11387d9e6174bd01 Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Fri, 23 Jun 2017 01:18:15 -0500
Subject: tcmu: perfom device add, del and reconfig synchronously

This makes the device add, del reconfig operations sync. It fixes
the issue where for add and reconfig, we do not know if userspace
successfully completely the operation, so we leave invalid kernel
structs or report incorrect status for the config/reconfig operations.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_user.c     | 213 ++++++++++++++++++++++++++++++----
 include/uapi/linux/target_core_user.h |   7 ++
 2 files changed, 200 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index e58127b8db8a..e080cd1a8fde 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -87,6 +87,8 @@
 /* Default maximum of the global data blocks(512K * PAGE_SIZE) */
 #define TCMU_GLOBAL_MAX_BLOCKS (512 * 1024)
 
+static u8 tcmu_kern_cmd_reply_supported;
+
 static struct device *tcmu_root_device;
 
 struct tcmu_hba {
@@ -95,6 +97,13 @@ struct tcmu_hba {
 
 #define TCMU_CONFIG_LEN 256
 
+struct tcmu_nl_cmd {
+	/* wake up thread waiting for reply */
+	struct completion complete;
+	int cmd;
+	int status;
+};
+
 struct tcmu_dev {
 	struct list_head node;
 	struct kref kref;
@@ -135,6 +144,11 @@ struct tcmu_dev {
 	struct timer_list timeout;
 	unsigned int cmd_time_out;
 
+	spinlock_t nl_cmd_lock;
+	struct tcmu_nl_cmd curr_nl_cmd;
+	/* wake up threads waiting on curr_nl_cmd */
+	wait_queue_head_t nl_cmd_wq;
+
 	char dev_config[TCMU_CONFIG_LEN];
 };
 
@@ -178,16 +192,128 @@ static const struct genl_multicast_group tcmu_mcgrps[] = {
 	[TCMU_MCGRP_CONFIG] = { .name = "config", },
 };
 
+static struct nla_policy tcmu_attr_policy[TCMU_ATTR_MAX+1] = {
+	[TCMU_ATTR_DEVICE]	= { .type = NLA_STRING },
+	[TCMU_ATTR_MINOR]	= { .type = NLA_U32 },
+	[TCMU_ATTR_CMD_STATUS]	= { .type = NLA_S32 },
+	[TCMU_ATTR_DEVICE_ID]	= { .type = NLA_U32 },
+	[TCMU_ATTR_SUPP_KERN_CMD_REPLY] = { .type = NLA_U8 },
+};
+
+static int tcmu_genl_cmd_done(struct genl_info *info, int completed_cmd)
+{
+	struct se_device *dev;
+	struct tcmu_dev *udev;
+	struct tcmu_nl_cmd *nl_cmd;
+	int dev_id, rc, ret = 0;
+	bool is_removed = (completed_cmd == TCMU_CMD_REMOVED_DEVICE);
+
+	if (!info->attrs[TCMU_ATTR_CMD_STATUS] ||
+	    !info->attrs[TCMU_ATTR_DEVICE_ID]) {
+		printk(KERN_ERR "TCMU_ATTR_CMD_STATUS or TCMU_ATTR_DEVICE_ID not set, doing nothing\n");
+                return -EINVAL;
+        }
+
+	dev_id = nla_get_u32(info->attrs[TCMU_ATTR_DEVICE_ID]);
+	rc = nla_get_s32(info->attrs[TCMU_ATTR_CMD_STATUS]);
+
+	dev = target_find_device(dev_id, !is_removed);
+	if (!dev) {
+		printk(KERN_ERR "tcmu nl cmd %u/%u completion could not find device with dev id %u.\n",
+		       completed_cmd, rc, dev_id);
+		return -ENODEV;
+	}
+	udev = TCMU_DEV(dev);
+
+	spin_lock(&udev->nl_cmd_lock);
+	nl_cmd = &udev->curr_nl_cmd;
+
+	pr_debug("genl cmd done got id %d curr %d done %d rc %d\n", dev_id,
+		 nl_cmd->cmd, completed_cmd, rc);
+
+	if (nl_cmd->cmd != completed_cmd) {
+		printk(KERN_ERR "Mismatched commands (Expecting reply for %d. Current %d).\n",
+		       completed_cmd, nl_cmd->cmd);
+		ret = -EINVAL;
+	} else {
+		nl_cmd->status = rc;
+	}
+
+	spin_unlock(&udev->nl_cmd_lock);
+	if (!is_removed)
+		 target_undepend_item(&dev->dev_group.cg_item);
+	if (!ret)
+		complete(&nl_cmd->complete);
+	return ret;
+}
+
+static int tcmu_genl_rm_dev_done(struct sk_buff *skb, struct genl_info *info)
+{
+	return tcmu_genl_cmd_done(info, TCMU_CMD_REMOVED_DEVICE);
+}
+
+static int tcmu_genl_add_dev_done(struct sk_buff *skb, struct genl_info *info)
+{
+	return tcmu_genl_cmd_done(info, TCMU_CMD_ADDED_DEVICE);
+}
+
+static int tcmu_genl_reconfig_dev_done(struct sk_buff *skb,
+				       struct genl_info *info)
+{
+	return tcmu_genl_cmd_done(info, TCMU_CMD_RECONFIG_DEVICE);
+}
+
+static int tcmu_genl_set_features(struct sk_buff *skb, struct genl_info *info)
+{
+	if (info->attrs[TCMU_ATTR_SUPP_KERN_CMD_REPLY]) {
+		tcmu_kern_cmd_reply_supported  =
+			nla_get_u8(info->attrs[TCMU_ATTR_SUPP_KERN_CMD_REPLY]);
+		printk(KERN_INFO "tcmu daemon: command reply support %u.\n",
+		       tcmu_kern_cmd_reply_supported);
+	}
+
+	return 0;
+}
+
+static const struct genl_ops tcmu_genl_ops[] = {
+	{
+		.cmd	= TCMU_CMD_SET_FEATURES,
+		.flags	= GENL_ADMIN_PERM,
+		.policy	= tcmu_attr_policy,
+		.doit	= tcmu_genl_set_features,
+	},
+	{
+		.cmd	= TCMU_CMD_ADDED_DEVICE_DONE,
+		.flags	= GENL_ADMIN_PERM,
+		.policy	= tcmu_attr_policy,
+		.doit	= tcmu_genl_add_dev_done,
+	},
+	{
+		.cmd	= TCMU_CMD_REMOVED_DEVICE_DONE,
+		.flags	= GENL_ADMIN_PERM,
+		.policy	= tcmu_attr_policy,
+		.doit	= tcmu_genl_rm_dev_done,
+	},
+	{
+		.cmd	= TCMU_CMD_RECONFIG_DEVICE_DONE,
+		.flags	= GENL_ADMIN_PERM,
+		.policy	= tcmu_attr_policy,
+		.doit	= tcmu_genl_reconfig_dev_done,
+	},
+};
+
 /* Our generic netlink family */
 static struct genl_family tcmu_genl_family __ro_after_init = {
 	.module = THIS_MODULE,
 	.hdrsize = 0,
 	.name = "TCM-USER",
-	.version = 1,
+	.version = 2,
 	.maxattr = TCMU_ATTR_MAX,
 	.mcgrps = tcmu_mcgrps,
 	.n_mcgrps = ARRAY_SIZE(tcmu_mcgrps),
 	.netnsok = true,
+	.ops = tcmu_genl_ops,
+	.n_ops = ARRAY_SIZE(tcmu_genl_ops),
 };
 
 #define tcmu_cmd_set_dbi_cur(cmd, index) ((cmd)->dbi_cur = (index))
@@ -989,6 +1115,9 @@ static struct se_device *tcmu_alloc_device(struct se_hba *hba, const char *name)
 	setup_timer(&udev->timeout, tcmu_device_timedout,
 		(unsigned long)udev);
 
+	init_waitqueue_head(&udev->nl_cmd_wq);
+	spin_lock_init(&udev->nl_cmd_lock);
+
 	return &udev->se_dev;
 }
 
@@ -1176,9 +1305,54 @@ static int tcmu_release(struct uio_info *info, struct inode *inode)
 	return 0;
 }
 
-static int tcmu_netlink_event(enum tcmu_genl_cmd cmd, const char *name,
-			      int minor, int reconfig_attr,
-			      const void *reconfig_data)
+static void tcmu_init_genl_cmd_reply(struct tcmu_dev *udev, int cmd)
+{
+	struct tcmu_nl_cmd *nl_cmd = &udev->curr_nl_cmd;
+
+	if (!tcmu_kern_cmd_reply_supported)
+		return;
+relock:
+	spin_lock(&udev->nl_cmd_lock);
+
+	if (nl_cmd->cmd != TCMU_CMD_UNSPEC) {
+		spin_unlock(&udev->nl_cmd_lock);
+		pr_debug("sleeping for open nl cmd\n");
+		wait_event(udev->nl_cmd_wq, (nl_cmd->cmd == TCMU_CMD_UNSPEC));
+		goto relock;
+	}
+
+	memset(nl_cmd, 0, sizeof(*nl_cmd));
+	nl_cmd->cmd = cmd;
+	init_completion(&nl_cmd->complete);
+
+	spin_unlock(&udev->nl_cmd_lock);
+}
+
+static int tcmu_wait_genl_cmd_reply(struct tcmu_dev *udev)
+{
+	struct tcmu_nl_cmd *nl_cmd = &udev->curr_nl_cmd;
+	int ret;
+	DEFINE_WAIT(__wait);
+
+	if (!tcmu_kern_cmd_reply_supported)
+		return 0;
+
+	pr_debug("sleeping for nl reply\n");
+	wait_for_completion(&nl_cmd->complete);
+
+	spin_lock(&udev->nl_cmd_lock);
+	nl_cmd->cmd = TCMU_CMD_UNSPEC;
+	ret = nl_cmd->status;
+	nl_cmd->status = 0;
+	spin_unlock(&udev->nl_cmd_lock);
+
+	wake_up_all(&udev->nl_cmd_wq);
+
+	return ret;;
+}
+
+static int tcmu_netlink_event(struct tcmu_dev *udev, enum tcmu_genl_cmd cmd,
+			      int reconfig_attr, const void *reconfig_data)
 {
 	struct sk_buff *skb;
 	void *msg_header;
@@ -1192,11 +1366,15 @@ static int tcmu_netlink_event(enum tcmu_genl_cmd cmd, const char *name,
 	if (!msg_header)
 		goto free_skb;
 
-	ret = nla_put_string(skb, TCMU_ATTR_DEVICE, name);
+	ret = nla_put_string(skb, TCMU_ATTR_DEVICE, udev->uio_info.name);
 	if (ret < 0)
 		goto free_skb;
 
-	ret = nla_put_u32(skb, TCMU_ATTR_MINOR, minor);
+	ret = nla_put_u32(skb, TCMU_ATTR_MINOR, udev->uio_info.uio_dev->minor);
+	if (ret < 0)
+		goto free_skb;
+
+	ret = nla_put_u32(skb, TCMU_ATTR_DEVICE_ID, udev->se_dev.dev_index);
 	if (ret < 0)
 		goto free_skb;
 
@@ -1224,12 +1402,15 @@ static int tcmu_netlink_event(enum tcmu_genl_cmd cmd, const char *name,
 
 	genlmsg_end(skb, msg_header);
 
+	tcmu_init_genl_cmd_reply(udev, cmd);
+
 	ret = genlmsg_multicast_allns(&tcmu_genl_family, skb, 0,
 				TCMU_MCGRP_CONFIG, GFP_KERNEL);
-
 	/* We don't care if no one is listening */
 	if (ret == -ESRCH)
 		ret = 0;
+	if (!ret)
+		ret = tcmu_wait_genl_cmd_reply(udev);
 
 	return ret;
 free_skb:
@@ -1324,8 +1505,7 @@ static int tcmu_configure_device(struct se_device *dev)
 	 */
 	kref_get(&udev->kref);
 
-	ret = tcmu_netlink_event(TCMU_CMD_ADDED_DEVICE, udev->uio_info.name,
-				 udev->uio_info.uio_dev->minor, 0, NULL);
+	ret = tcmu_netlink_event(udev, TCMU_CMD_ADDED_DEVICE, 0, NULL);
 	if (ret)
 		goto err_netlink;
 
@@ -1414,8 +1594,7 @@ static void tcmu_destroy_device(struct se_device *dev)
 	tcmu_blocks_release(udev);
 
 	if (tcmu_dev_configured(udev)) {
-		tcmu_netlink_event(TCMU_CMD_REMOVED_DEVICE, udev->uio_info.name,
-				   udev->uio_info.uio_dev->minor, 0, NULL);
+		tcmu_netlink_event(udev, TCMU_CMD_REMOVED_DEVICE, 0, NULL);
 
 		uio_unregister_device(&udev->uio_info);
 	}
@@ -1600,9 +1779,7 @@ static ssize_t tcmu_dev_config_store(struct config_item *item, const char *page,
 
 	/* Check if device has been configured before */
 	if (tcmu_dev_configured(udev)) {
-		ret = tcmu_netlink_event(TCMU_CMD_RECONFIG_DEVICE,
-					 udev->uio_info.name,
-					 udev->uio_info.uio_dev->minor,
+		ret = tcmu_netlink_event(udev, TCMU_CMD_RECONFIG_DEVICE,
 					 TCMU_ATTR_DEV_CFG, page);
 		if (ret) {
 			pr_err("Unable to reconfigure device\n");
@@ -1639,9 +1816,7 @@ static ssize_t tcmu_dev_size_store(struct config_item *item, const char *page,
 
 	/* Check if device has been configured before */
 	if (tcmu_dev_configured(udev)) {
-		ret = tcmu_netlink_event(TCMU_CMD_RECONFIG_DEVICE,
-					 udev->uio_info.name,
-					 udev->uio_info.uio_dev->minor,
+		ret = tcmu_netlink_event(udev, TCMU_CMD_RECONFIG_DEVICE,
 					 TCMU_ATTR_DEV_SIZE, &val);
 		if (ret) {
 			pr_err("Unable to reconfigure device\n");
@@ -1677,9 +1852,7 @@ static ssize_t tcmu_emulate_write_cache_store(struct config_item *item,
 
 	/* Check if device has been configured before */
 	if (tcmu_dev_configured(udev)) {
-		ret = tcmu_netlink_event(TCMU_CMD_RECONFIG_DEVICE,
-					 udev->uio_info.name,
-					 udev->uio_info.uio_dev->minor,
+		ret = tcmu_netlink_event(udev, TCMU_CMD_RECONFIG_DEVICE,
 					 TCMU_ATTR_WRITECACHE, &val);
 		if (ret) {
 			pr_err("Unable to reconfigure device\n");
diff --git a/include/uapi/linux/target_core_user.h b/include/uapi/linux/target_core_user.h
index 4bfc9a1b635c..24a1c4ec2248 100644
--- a/include/uapi/linux/target_core_user.h
+++ b/include/uapi/linux/target_core_user.h
@@ -131,6 +131,10 @@ enum tcmu_genl_cmd {
 	TCMU_CMD_ADDED_DEVICE,
 	TCMU_CMD_REMOVED_DEVICE,
 	TCMU_CMD_RECONFIG_DEVICE,
+	TCMU_CMD_ADDED_DEVICE_DONE,
+	TCMU_CMD_REMOVED_DEVICE_DONE,
+	TCMU_CMD_RECONFIG_DEVICE_DONE,
+	TCMU_CMD_SET_FEATURES,
 	__TCMU_CMD_MAX,
 };
 #define TCMU_CMD_MAX (__TCMU_CMD_MAX - 1)
@@ -143,6 +147,9 @@ enum tcmu_genl_attr {
 	TCMU_ATTR_DEV_CFG,
 	TCMU_ATTR_DEV_SIZE,
 	TCMU_ATTR_WRITECACHE,
+	TCMU_ATTR_CMD_STATUS,
+	TCMU_ATTR_DEVICE_ID,
+	TCMU_ATTR_SUPP_KERN_CMD_REPLY,
 	__TCMU_ATTR_MAX,
 };
 #define TCMU_ATTR_MAX (__TCMU_ATTR_MAX - 1)
-- 
cgit v1.2.3


From be50f538e9a5081c61a78faf58c5591c94064633 Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Fri, 23 Jun 2017 01:18:18 -0500
Subject: target: remove g_device_list

g_device_list is no longer needed because we now use the idr code
for lookups and seaches.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_device.c   | 30 ++++++++++++------------------
 drivers/target/target_core_internal.h |  3 ---
 include/target/target_core_base.h     |  1 -
 3 files changed, 12 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index bd32a0c65961..3ae8fbf01bdf 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -49,8 +49,8 @@
 #include "target_core_pr.h"
 #include "target_core_ua.h"
 
-DEFINE_MUTEX(g_device_mutex);
-LIST_HEAD(g_device_list);
+DEFINE_MUTEX(device_mutex);
+LIST_HEAD(device_list);
 static DEFINE_IDR(devices_idr);
 
 static struct se_hba *lun0_hba;
@@ -773,7 +773,6 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name)
 	INIT_LIST_HEAD(&dev->delayed_cmd_list);
 	INIT_LIST_HEAD(&dev->state_list);
 	INIT_LIST_HEAD(&dev->qf_cmd_list);
-	INIT_LIST_HEAD(&dev->g_dev_node);
 	spin_lock_init(&dev->execute_task_lock);
 	spin_lock_init(&dev->delayed_cmd_lock);
 	spin_lock_init(&dev->dev_reservation_lock);
@@ -895,11 +894,11 @@ struct se_device *target_find_device(int id, bool do_depend)
 {
 	struct se_device *dev;
 
-	mutex_lock(&g_device_mutex);
+	mutex_lock(&device_mutex);
 	dev = idr_find(&devices_idr, id);
 	if (dev && do_depend && target_depend_item(&dev->dev_group.cg_item))
 		dev = NULL;
-	mutex_unlock(&g_device_mutex);
+	mutex_unlock(&device_mutex);
 	return dev;
 }
 EXPORT_SYMBOL(target_find_device);
@@ -943,9 +942,9 @@ int target_for_each_device(int (*fn)(struct se_device *dev, void *data),
 	iter.fn = fn;
 	iter.data = data;
 
-	mutex_lock(&g_device_mutex);
+	mutex_lock(&device_mutex);
 	ret = idr_for_each(&devices_idr, target_devices_idr_iter, &iter);
-	mutex_unlock(&g_device_mutex);
+	mutex_unlock(&device_mutex);
 	return ret;
 }
 
@@ -964,13 +963,13 @@ int target_configure_device(struct se_device *dev)
 	 * Add early so modules like tcmu can use during its
 	 * configuration.
 	 */
-	mutex_lock(&g_device_mutex);
+	mutex_lock(&device_mutex);
 	/*
 	 * Use cyclic to try and avoid collisions with devices
 	 * that were recently removed.
 	 */
 	id = idr_alloc_cyclic(&devices_idr, dev, 0, INT_MAX, GFP_KERNEL);
-	mutex_unlock(&g_device_mutex);
+	mutex_unlock(&device_mutex);
 	if (id < 0) {
 		ret = -ENOMEM;
 		goto out;
@@ -1036,10 +1035,6 @@ int target_configure_device(struct se_device *dev)
 	hba->dev_count++;
 	spin_unlock(&hba->device_lock);
 
-	mutex_lock(&g_device_mutex);
-	list_add_tail(&dev->g_dev_node, &g_device_list);
-	mutex_unlock(&g_device_mutex);
-
 	dev->dev_flags |= DF_CONFIGURED;
 
 	return 0;
@@ -1047,9 +1042,9 @@ int target_configure_device(struct se_device *dev)
 out_free_alua:
 	core_alua_free_lu_gp_mem(dev);
 out_free_index:
-	mutex_lock(&g_device_mutex);
+	mutex_lock(&device_mutex);
 	idr_remove(&devices_idr, dev->dev_index);
-	mutex_unlock(&g_device_mutex);
+	mutex_unlock(&device_mutex);
 out:
 	se_release_vpd_for_dev(dev);
 	return ret;
@@ -1066,10 +1061,9 @@ void target_free_device(struct se_device *dev)
 
 		dev->transport->destroy_device(dev);
 
-		mutex_lock(&g_device_mutex);
+		mutex_lock(&device_mutex);
 		idr_remove(&devices_idr, dev->dev_index);
-		list_del(&dev->g_dev_node);
-		mutex_unlock(&g_device_mutex);
+		mutex_unlock(&device_mutex);
 
 		spin_lock(&hba->device_lock);
 		hba->dev_count--;
diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h
index 1d3ac0238568..f30e8ac13386 100644
--- a/drivers/target/target_core_internal.h
+++ b/drivers/target/target_core_internal.h
@@ -56,9 +56,6 @@ struct target_fabric_configfs {
 extern struct t10_alua_lu_gp *default_lu_gp;
 
 /* target_core_device.c */
-extern struct mutex g_device_mutex;
-extern struct list_head g_device_list;
-
 int	core_alloc_rtpi(struct se_lun *lun, struct se_device *dev);
 struct se_dev_entry *core_get_se_deve_from_rtpi(struct se_node_acl *, u16);
 void	target_pr_kref_release(struct kref *);
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 51a92f17352c..516764febeb7 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -796,7 +796,6 @@ struct se_device {
 	struct list_head	delayed_cmd_list;
 	struct list_head	state_list;
 	struct list_head	qf_cmd_list;
-	struct list_head	g_dev_node;
 	/* Pointer to associated SE HBA */
 	struct se_hba		*se_hba;
 	/* T10 Inquiry and VPD WWN Information */
-- 
cgit v1.2.3


From c6d66aba98a39cfed206c5c61f0a604ba09b26ce Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Wed, 31 May 2017 15:52:39 -0500
Subject: target: add helper to copy sense to se_cmd buffer

This adds a helper to copy sense from backend module buffer to
the se_cmd's sense buffer.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_transport.c | 18 ++++++++++++++++++
 include/target/target_core_backend.h   |  2 ++
 2 files changed, 20 insertions(+)

(limited to 'include')

diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index a8f943e325eb..341025a3cbb7 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -704,6 +704,24 @@ static unsigned char *transport_get_sense_buffer(struct se_cmd *cmd)
 	return cmd->sense_buffer;
 }
 
+void transport_copy_sense_to_cmd(struct se_cmd *cmd, unsigned char *sense)
+{
+	unsigned char *cmd_sense_buf;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	cmd_sense_buf = transport_get_sense_buffer(cmd);
+	if (!cmd_sense_buf) {
+		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+		return;
+	}
+
+	cmd->se_cmd_flags |= SCF_TRANSPORT_TASK_SENSE;
+	memcpy(cmd_sense_buf, sense, cmd->scsi_sense_length);
+	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+}
+EXPORT_SYMBOL(transport_copy_sense_to_cmd);
+
 void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status)
 {
 	struct se_device *dev = cmd->se_dev;
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index 1f2b7007f2df..3757f5f54e03 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -73,6 +73,8 @@ void	target_backend_unregister(const struct target_backend_ops *);
 void	target_complete_cmd(struct se_cmd *, u8);
 void	target_complete_cmd_with_length(struct se_cmd *, u8, int);
 
+void	transport_copy_sense_to_cmd(struct se_cmd *, unsigned char *);
+
 sense_reason_t	spc_parse_cdb(struct se_cmd *cmd, unsigned int *size);
 sense_reason_t	spc_emulate_report_luns(struct se_cmd *cmd);
 sense_reason_t	spc_emulate_inquiry_std(struct se_cmd *, unsigned char *);
-- 
cgit v1.2.3


From 1a444175486026c1a280507f8d82094909acddd2 Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Wed, 31 May 2017 15:52:42 -0500
Subject: target: remove transport_complete

transport_complete is no longer used, so drop the code.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_transport.c | 6 ------
 include/target/target_core_backend.h   | 4 ----
 2 files changed, 10 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 341025a3cbb7..b9122a56784e 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -732,12 +732,6 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status)
 
 
 	spin_lock_irqsave(&cmd->t_state_lock, flags);
-
-	if (dev && dev->transport->transport_complete) {
-		dev->transport->transport_complete(cmd,
-				cmd->t_data_sg,
-				transport_get_sense_buffer(cmd));
-	}
 	if (cmd->se_cmd_flags & SCF_TRANSPORT_TASK_SENSE)
 		success = 1;
 
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index 3757f5f54e03..e150e391878b 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -37,10 +37,6 @@ struct target_backend_ops {
 					   const char *, ssize_t);
 	ssize_t (*show_configfs_dev_params)(struct se_device *, char *);
 
-	void (*transport_complete)(struct se_cmd *cmd,
-				   struct scatterlist *,
-				   unsigned char *);
-
 	sense_reason_t (*parse_cdb)(struct se_cmd *cmd);
 	u32 (*get_device_type)(struct se_device *);
 	sector_t (*get_blocks)(struct se_device *);
-- 
cgit v1.2.3


From e5dc9a7055c98bcd7b03f9735d5f2ec2b7f0d897 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <damien.lemoal@wdc.com>
Date: Wed, 28 Jun 2017 14:58:56 +0900
Subject: target: Use macro for WRITE_VERIFY_32 operation codes

Add WRITE_VERIFY_32 definition to scsi prototypes and use this macro
definition isntead of the hard coded value.

(Drop WRITE_VERIFY_16 that's already part of another patch - nab)

Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_device.c | 2 +-
 include/scsi/scsi_proto.h           | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index bbcef3bc66c8..1c7c57a3c52e 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -1226,7 +1226,7 @@ passthrough_parse_cdb(struct se_cmd *cmd,
 		switch (get_unaligned_be16(&cdb[8])) {
 		case READ_32:
 		case WRITE_32:
-		case 0x0c: /* WRITE_VERIFY_32 */
+		case WRITE_VERIFY_32:
 		case XDWRITEREAD_32:
 			cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
 			break;
diff --git a/include/scsi/scsi_proto.h b/include/scsi/scsi_proto.h
index ce78ec8e367d..5e3fe037938e 100644
--- a/include/scsi/scsi_proto.h
+++ b/include/scsi/scsi_proto.h
@@ -161,6 +161,7 @@
 #define READ_32		      0x09
 #define VERIFY_32	      0x0a
 #define WRITE_32	      0x0b
+#define WRITE_VERIFY_32	      0x0c
 #define WRITE_SAME_32	      0x0d
 
 /* Values for T10/04-262r7 */
-- 
cgit v1.2.3


From 0e4524a5d341e719e8ee9ee7db5d58e2c5a4c10e Mon Sep 17 00:00:00 2001
From: Christian Borntraeger <borntraeger@de.ibm.com>
Date: Thu, 6 Jul 2017 14:44:28 +0200
Subject: KVM: mark vcpu->pid pointer as rcu protected

We do use rcu to protect the pid pointer. Mark it as such and
adopt all code to use the proper access methods.

This was detected by sparse.
"virt/kvm/kvm_main.c:2248:15: error: incompatible types in comparison
expression (different address spaces)"

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/kvm_host.h |  2 +-
 virt/kvm/kvm_main.c      | 15 +++++++++++----
 2 files changed, 12 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 0b50e7b35ed4..bcd37b855c66 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -234,7 +234,7 @@ struct kvm_vcpu {
 
 	int guest_fpu_loaded, guest_xcr0_loaded;
 	struct swait_queue_head wq;
-	struct pid *pid;
+	struct pid __rcu *pid;
 	int sigset_active;
 	sigset_t sigset;
 	struct kvm_vcpu_stat stat;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 19f0ecb9b93e..fc2d58312fd5 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -293,7 +293,12 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_init);
 
 void kvm_vcpu_uninit(struct kvm_vcpu *vcpu)
 {
-	put_pid(vcpu->pid);
+	/*
+	 * no need for rcu_read_lock as VCPU_RUN is the only place that
+	 * will change the vcpu->pid pointer and on uninit all file
+	 * descriptors are already gone.
+	 */
+	put_pid(rcu_dereference_protected(vcpu->pid, 1));
 	kvm_arch_vcpu_uninit(vcpu);
 	free_page((unsigned long)vcpu->run);
 }
@@ -2551,13 +2556,14 @@ static long kvm_vcpu_ioctl(struct file *filp,
 	if (r)
 		return r;
 	switch (ioctl) {
-	case KVM_RUN:
+	case KVM_RUN: {
+		struct pid *oldpid;
 		r = -EINVAL;
 		if (arg)
 			goto out;
-		if (unlikely(vcpu->pid != current->pids[PIDTYPE_PID].pid)) {
+		oldpid = rcu_access_pointer(vcpu->pid);
+		if (unlikely(oldpid != current->pids[PIDTYPE_PID].pid)) {
 			/* The thread running this VCPU changed. */
-			struct pid *oldpid = vcpu->pid;
 			struct pid *newpid = get_task_pid(current, PIDTYPE_PID);
 
 			rcu_assign_pointer(vcpu->pid, newpid);
@@ -2568,6 +2574,7 @@ static long kvm_vcpu_ioctl(struct file *filp,
 		r = kvm_arch_vcpu_ioctl_run(vcpu, vcpu->run);
 		trace_kvm_userspace_exit(vcpu->run->exit_reason, r);
 		break;
+	}
 	case KVM_GET_REGS: {
 		struct kvm_regs *kvm_regs;
 
-- 
cgit v1.2.3


From 3068a254d5519cd5116f61297462da6d1aa84c20 Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@free-electrons.com>
Date: Thu, 6 Jul 2017 11:42:00 +0200
Subject: rtc: introduce new registration method

Introduce rtc_register_device() to register an already allocated and
initialized struct rtc_device. It automatically sets up the owner and the
two steps allocation/registration will allow to remove race conditions in
the IRQ handling of some driver. It also allows to properly extend the core
without adding more arguments to rtc_device_register().

Signed-off-by: Alexandre Belloni <alexandre.belloni@free-electrons.com>
---
 drivers/rtc/class.c | 84 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/rtc.h |  7 +++++
 2 files changed, 91 insertions(+)

(limited to 'include')

diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c
index 93ce88e1b1cb..58e2a05765bb 100644
--- a/drivers/rtc/class.c
+++ b/drivers/rtc/class.c
@@ -150,6 +150,7 @@ static SIMPLE_DEV_PM_OPS(rtc_class_dev_pm_ops, rtc_suspend, rtc_resume);
 #define RTC_CLASS_DEV_PM_OPS	NULL
 #endif
 
+/* Ensure the caller will set the id before releasing the device */
 static struct rtc_device *rtc_allocate_device(void)
 {
 	struct rtc_device *rtc;
@@ -372,6 +373,89 @@ void devm_rtc_device_unregister(struct device *dev, struct rtc_device *rtc)
 }
 EXPORT_SYMBOL_GPL(devm_rtc_device_unregister);
 
+static void devm_rtc_release_device(struct device *dev, void *res)
+{
+	struct rtc_device *rtc = *(struct rtc_device **)res;
+
+	if (rtc->registered)
+		rtc_device_unregister(rtc);
+	else
+		put_device(&rtc->dev);
+}
+
+struct rtc_device *devm_rtc_allocate_device(struct device *dev)
+{
+	struct rtc_device **ptr, *rtc;
+	int id, err;
+
+	id = rtc_device_get_id(dev);
+	if (id < 0)
+		return ERR_PTR(id);
+
+	ptr = devres_alloc(devm_rtc_release_device, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr) {
+		err = -ENOMEM;
+		goto exit_ida;
+	}
+
+	rtc = rtc_allocate_device();
+	if (!rtc) {
+		err = -ENOMEM;
+		goto exit_devres;
+	}
+
+	*ptr = rtc;
+	devres_add(dev, ptr);
+
+	rtc->id = id;
+	rtc->dev.parent = dev;
+	dev_set_name(&rtc->dev, "rtc%d", id);
+
+	return rtc;
+
+exit_devres:
+	devres_free(ptr);
+exit_ida:
+	ida_simple_remove(&rtc_ida, id);
+	return ERR_PTR(err);
+}
+EXPORT_SYMBOL_GPL(devm_rtc_allocate_device);
+
+int __rtc_register_device(struct module *owner, struct rtc_device *rtc)
+{
+	struct rtc_wkalrm alrm;
+	int err;
+
+	if (!rtc->ops)
+		return -EINVAL;
+
+	rtc->owner = owner;
+
+	/* Check to see if there is an ALARM already set in hw */
+	err = __rtc_read_alarm(rtc, &alrm);
+	if (!err && !rtc_valid_tm(&alrm.time))
+		rtc_initialize_alarm(rtc, &alrm);
+
+	rtc_dev_prepare(rtc);
+
+	err = cdev_device_add(&rtc->char_dev, &rtc->dev);
+	if (err)
+		dev_warn(rtc->dev.parent, "failed to add char device %d:%d\n",
+			 MAJOR(rtc->dev.devt), rtc->id);
+	else
+		dev_dbg(rtc->dev.parent, "char device (%d:%d)\n",
+			MAJOR(rtc->dev.devt), rtc->id);
+
+	rtc_proc_add_device(rtc);
+
+	rtc->registered = true;
+	dev_info(rtc->dev.parent, "registered as %s\n",
+		 dev_name(&rtc->dev));
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__rtc_register_device);
+
 static int __init rtc_init(void)
 {
 	rtc_class = class_create(THIS_MODULE, "rtc");
diff --git a/include/linux/rtc.h b/include/linux/rtc.h
index d354f56e0cf5..8e4a5f44f59e 100644
--- a/include/linux/rtc.h
+++ b/include/linux/rtc.h
@@ -142,6 +142,8 @@ struct rtc_device {
 	/* Some hardware can't support UIE mode */
 	int uie_unsupported;
 
+	bool registered;
+
 #ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL
 	struct work_struct uie_task;
 	struct timer_list uie_timer;
@@ -163,6 +165,8 @@ extern struct rtc_device *devm_rtc_device_register(struct device *dev,
 					const char *name,
 					const struct rtc_class_ops *ops,
 					struct module *owner);
+struct rtc_device *devm_rtc_allocate_device(struct device *dev);
+int __rtc_register_device(struct module *owner, struct rtc_device *rtc);
 extern void rtc_device_unregister(struct rtc_device *rtc);
 extern void devm_rtc_device_unregister(struct device *dev,
 					struct rtc_device *rtc);
@@ -218,6 +222,9 @@ static inline bool is_leap_year(unsigned int year)
 	return (!(year % 4) && (year % 100)) || !(year % 400);
 }
 
+#define rtc_register_device(device) \
+	__rtc_register_device(THIS_MODULE, device)
+
 #ifdef CONFIG_RTC_HCTOSYS_DEVICE
 extern int rtc_hctosys_ret;
 #else
-- 
cgit v1.2.3


From 697e5a47aa12cdab6f2a8b284cc923cdf704eafc Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@free-electrons.com>
Date: Thu, 6 Jul 2017 11:42:02 +0200
Subject: rtc: add generic nvmem support

Many RTCs have an on board non volatile storage. It can be battery backed
RAM or an EEPROM. Use the nvmem subsystem to export it to both userspace
and in-kernel consumers.

This stays compatible with the previous (non documented) ABI that was using
/sys/class/rtc/rtcx/device/nvram to export that memory. But will warn about
the deprecation.

Signed-off-by: Alexandre Belloni <alexandre.belloni@free-electrons.com>
---
 Documentation/rtc.txt  |   2 +
 drivers/rtc/Kconfig    |   8 ++++
 drivers/rtc/Makefile   |   1 +
 drivers/rtc/class.c    |   4 ++
 drivers/rtc/nvmem.c    | 113 +++++++++++++++++++++++++++++++++++++++++++++++++
 drivers/rtc/rtc-core.h |   8 ++++
 include/linux/rtc.h    |   7 +++
 7 files changed, 143 insertions(+)
 create mode 100644 drivers/rtc/nvmem.c

(limited to 'include')

diff --git a/Documentation/rtc.txt b/Documentation/rtc.txt
index 47feb4414b7e..c0c977445fb9 100644
--- a/Documentation/rtc.txt
+++ b/Documentation/rtc.txt
@@ -164,6 +164,8 @@ offset		 The amount which the rtc clock has been adjusted in firmware.
 		 which are added to or removed from the rtc's base clock per
 		 billion ticks. A positive value makes a day pass more slowly,
 		 longer, and a negative value makes a day pass more quickly.
+*/nvmem		 The non volatile storage exported as a raw file, as described
+		 in Documentation/nvmem/nvmem.txt
 ================ ==============================================================
 
 IOCTL interface
diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index d0e4b4a1c2a1..72419ac2c52a 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -77,6 +77,14 @@ config RTC_DEBUG
 	  Say yes here to enable debugging support in the RTC framework
 	  and individual RTC drivers.
 
+config RTC_NVMEM
+	bool "RTC non volatile storage support"
+	select NVMEM
+	default RTC_CLASS
+	help
+	  Say yes here to add support for the non volatile (often battery
+	  backed) storage present on RTCs.
+
 comment "RTC interfaces"
 
 config RTC_INTF_SYSFS
diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile
index 4050fc8b9271..acd366b41c85 100644
--- a/drivers/rtc/Makefile
+++ b/drivers/rtc/Makefile
@@ -15,6 +15,7 @@ ifdef CONFIG_RTC_DRV_EFI
 rtc-core-y			+= rtc-efi-platform.o
 endif
 
+rtc-core-$(CONFIG_RTC_NVMEM)		+= nvmem.o
 rtc-core-$(CONFIG_RTC_INTF_DEV)		+= rtc-dev.o
 rtc-core-$(CONFIG_RTC_INTF_PROC)	+= rtc-proc.o
 rtc-core-$(CONFIG_RTC_INTF_SYSFS)	+= rtc-sysfs.o
diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c
index 58e2a05765bb..2ed970d61da1 100644
--- a/drivers/rtc/class.c
+++ b/drivers/rtc/class.c
@@ -290,6 +290,8 @@ EXPORT_SYMBOL_GPL(rtc_device_register);
  */
 void rtc_device_unregister(struct rtc_device *rtc)
 {
+	rtc_nvmem_unregister(rtc);
+
 	mutex_lock(&rtc->ops_lock);
 	/*
 	 * Remove innards of this RTC, then disable it, before
@@ -448,6 +450,8 @@ int __rtc_register_device(struct module *owner, struct rtc_device *rtc)
 
 	rtc_proc_add_device(rtc);
 
+	rtc_nvmem_register(rtc);
+
 	rtc->registered = true;
 	dev_info(rtc->dev.parent, "registered as %s\n",
 		 dev_name(&rtc->dev));
diff --git a/drivers/rtc/nvmem.c b/drivers/rtc/nvmem.c
new file mode 100644
index 000000000000..8567b4ed9ac6
--- /dev/null
+++ b/drivers/rtc/nvmem.c
@@ -0,0 +1,113 @@
+/*
+ * RTC subsystem, nvmem interface
+ *
+ * Copyright (C) 2017 Alexandre Belloni
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/err.h>
+#include <linux/types.h>
+#include <linux/nvmem-consumer.h>
+#include <linux/rtc.h>
+#include <linux/sysfs.h>
+
+#include "rtc-core.h"
+
+/*
+ * Deprecated ABI compatibility, this should be removed at some point
+ */
+
+static const char nvram_warning[] = "Deprecated ABI, please use nvmem";
+
+static ssize_t
+rtc_nvram_read(struct file *filp, struct kobject *kobj,
+	       struct bin_attribute *attr,
+	       char *buf, loff_t off, size_t count)
+{
+	struct rtc_device *rtc = attr->private;
+
+	dev_warn_once(kobj_to_dev(kobj), nvram_warning);
+
+	return nvmem_device_read(rtc->nvmem, off, count, buf);
+}
+
+static ssize_t
+rtc_nvram_write(struct file *filp, struct kobject *kobj,
+		struct bin_attribute *attr,
+		char *buf, loff_t off, size_t count)
+{
+	struct rtc_device *rtc = attr->private;
+
+	dev_warn_once(kobj_to_dev(kobj), nvram_warning);
+
+	return nvmem_device_write(rtc->nvmem, off, count, buf);
+}
+
+static int rtc_nvram_register(struct rtc_device *rtc)
+{
+	int err;
+
+	rtc->nvram = devm_kzalloc(rtc->dev.parent,
+				sizeof(struct bin_attribute),
+				GFP_KERNEL);
+	if (!rtc->nvram)
+		return -ENOMEM;
+
+	rtc->nvram->attr.name = "nvram";
+	rtc->nvram->attr.mode = 0644;
+	rtc->nvram->private = rtc;
+
+	sysfs_bin_attr_init(rtc->nvram);
+
+	rtc->nvram->read = rtc_nvram_read;
+	rtc->nvram->write = rtc_nvram_write;
+	rtc->nvram->size = rtc->nvmem_config->size;
+
+	err = sysfs_create_bin_file(&rtc->dev.parent->kobj,
+				    rtc->nvram);
+	if (err) {
+		devm_kfree(rtc->dev.parent, rtc->nvram);
+		rtc->nvram = NULL;
+	}
+
+	return err;
+}
+
+static void rtc_nvram_unregister(struct rtc_device *rtc)
+{
+	sysfs_remove_bin_file(&rtc->dev.parent->kobj, rtc->nvram);
+}
+
+/*
+ * New ABI, uses nvmem
+ */
+void rtc_nvmem_register(struct rtc_device *rtc)
+{
+	if (!rtc->nvmem_config)
+		return;
+
+	rtc->nvmem_config->dev = &rtc->dev;
+	rtc->nvmem_config->owner = rtc->owner;
+	rtc->nvmem = nvmem_register(rtc->nvmem_config);
+	if (IS_ERR_OR_NULL(rtc->nvmem))
+		return;
+
+	/* Register the old ABI */
+	if (rtc->nvram_old_abi)
+		rtc_nvram_register(rtc);
+}
+
+void rtc_nvmem_unregister(struct rtc_device *rtc)
+{
+	if (IS_ERR_OR_NULL(rtc->nvmem))
+		return;
+
+	/* unregister the old ABI */
+	if (rtc->nvram)
+		rtc_nvram_unregister(rtc);
+
+	nvmem_unregister(rtc->nvmem);
+}
diff --git a/drivers/rtc/rtc-core.h b/drivers/rtc/rtc-core.h
index 7a4ed2f7c7d7..ecab76a3207c 100644
--- a/drivers/rtc/rtc-core.h
+++ b/drivers/rtc/rtc-core.h
@@ -45,3 +45,11 @@ static inline const struct attribute_group **rtc_get_dev_attribute_groups(void)
 	return NULL;
 }
 #endif
+
+#ifdef CONFIG_RTC_NVMEM
+void rtc_nvmem_register(struct rtc_device *rtc);
+void rtc_nvmem_unregister(struct rtc_device *rtc);
+#else
+static inline void rtc_nvmem_register(struct rtc_device *rtc) {}
+static inline void rtc_nvmem_unregister(struct rtc_device *rtc) {}
+#endif
diff --git a/include/linux/rtc.h b/include/linux/rtc.h
index 8e4a5f44f59e..d53ecdc060cf 100644
--- a/include/linux/rtc.h
+++ b/include/linux/rtc.h
@@ -14,6 +14,7 @@
 
 #include <linux/types.h>
 #include <linux/interrupt.h>
+#include <linux/nvmem-provider.h>
 #include <uapi/linux/rtc.h>
 
 extern int rtc_month_days(unsigned int month, unsigned int year);
@@ -144,6 +145,12 @@ struct rtc_device {
 
 	bool registered;
 
+	struct nvmem_config *nvmem_config;
+	struct nvmem_device *nvmem;
+	/* Old ABI support */
+	bool nvram_old_abi;
+	struct bin_attribute *nvram;
+
 #ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL
 	struct work_struct uie_task;
 	struct timer_list uie_timer;
-- 
cgit v1.2.3


From 4a12f95177280a660bda99e81838919b1cc6a91a Mon Sep 17 00:00:00 2001
From: Christian Borntraeger <borntraeger@de.ibm.com>
Date: Fri, 7 Jul 2017 10:51:38 +0200
Subject: KVM: mark kvm->busses as rcu protected

mark kvm->busses as rcu protected and use the correct access
function everywhere.

found by sparse
virt/kvm/kvm_main.c:3490:15: error: incompatible types in comparison expression (different address spaces)
virt/kvm/kvm_main.c:3509:15: error: incompatible types in comparison expression (different address spaces)
virt/kvm/kvm_main.c:3561:15: error: incompatible types in comparison expression (different address spaces)
virt/kvm/kvm_main.c:3644:15: error: incompatible types in comparison expression (different address spaces)

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 include/linux/kvm_host.h |  8 +++++++-
 virt/kvm/eventfd.c       |  8 +++++---
 virt/kvm/kvm_main.c      | 17 ++++++++++-------
 3 files changed, 22 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index bcd37b855c66..6a164f9eb02c 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -404,7 +404,7 @@ struct kvm {
 	int last_boosted_vcpu;
 	struct list_head vm_list;
 	struct mutex lock;
-	struct kvm_io_bus *buses[KVM_NR_BUSES];
+	struct kvm_io_bus __rcu *buses[KVM_NR_BUSES];
 #ifdef CONFIG_HAVE_KVM_EVENTFD
 	struct {
 		spinlock_t        lock;
@@ -473,6 +473,12 @@ struct kvm {
 #define vcpu_err(vcpu, fmt, ...)					\
 	kvm_err("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__)
 
+static inline struct kvm_io_bus *kvm_get_bus(struct kvm *kvm, enum kvm_bus idx)
+{
+	return srcu_dereference_check(kvm->buses[idx], &kvm->srcu,
+				      lockdep_is_held(&kvm->slots_lock));
+}
+
 static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i)
 {
 	/* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu, in case
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index a8d540398bbd..d016aadd5fbb 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -825,7 +825,7 @@ static int kvm_assign_ioeventfd_idx(struct kvm *kvm,
 	if (ret < 0)
 		goto unlock_fail;
 
-	kvm->buses[bus_idx]->ioeventfd_count++;
+	kvm_get_bus(kvm, bus_idx)->ioeventfd_count++;
 	list_add_tail(&p->list, &kvm->ioeventfds);
 
 	mutex_unlock(&kvm->slots_lock);
@@ -848,6 +848,7 @@ kvm_deassign_ioeventfd_idx(struct kvm *kvm, enum kvm_bus bus_idx,
 {
 	struct _ioeventfd        *p, *tmp;
 	struct eventfd_ctx       *eventfd;
+	struct kvm_io_bus	 *bus;
 	int                       ret = -ENOENT;
 
 	eventfd = eventfd_ctx_fdget(args->fd);
@@ -870,8 +871,9 @@ kvm_deassign_ioeventfd_idx(struct kvm *kvm, enum kvm_bus bus_idx,
 			continue;
 
 		kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev);
-		if (kvm->buses[bus_idx])
-			kvm->buses[bus_idx]->ioeventfd_count--;
+		bus = kvm_get_bus(kvm, bus_idx);
+		if (bus)
+			bus->ioeventfd_count--;
 		ioeventfd_release(p);
 		ret = 0;
 		break;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index fc2d58312fd5..d76e822f8929 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -679,8 +679,8 @@ static struct kvm *kvm_create_vm(unsigned long type)
 	if (init_srcu_struct(&kvm->irq_srcu))
 		goto out_err_no_irq_srcu;
 	for (i = 0; i < KVM_NR_BUSES; i++) {
-		kvm->buses[i] = kzalloc(sizeof(struct kvm_io_bus),
-					GFP_KERNEL);
+		rcu_assign_pointer(kvm->buses[i],
+			kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL));
 		if (!kvm->buses[i])
 			goto out_err;
 	}
@@ -705,7 +705,7 @@ out_err_no_srcu:
 	hardware_disable_all();
 out_err_no_disable:
 	for (i = 0; i < KVM_NR_BUSES; i++)
-		kfree(kvm->buses[i]);
+		kfree(rcu_access_pointer(kvm->buses[i]));
 	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++)
 		kvm_free_memslots(kvm, kvm->memslots[i]);
 	kvm_arch_free_vm(kvm);
@@ -740,8 +740,11 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	spin_unlock(&kvm_lock);
 	kvm_free_irq_routing(kvm);
 	for (i = 0; i < KVM_NR_BUSES; i++) {
-		if (kvm->buses[i])
-			kvm_io_bus_destroy(kvm->buses[i]);
+		struct kvm_io_bus *bus;
+
+		bus = rcu_dereference_protected(kvm->buses[i], 1);
+		if (bus)
+			kvm_io_bus_destroy(bus);
 		kvm->buses[i] = NULL;
 	}
 	kvm_coalesced_mmio_free(kvm);
@@ -3570,7 +3573,7 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 {
 	struct kvm_io_bus *new_bus, *bus;
 
-	bus = kvm->buses[bus_idx];
+	bus = kvm_get_bus(kvm, bus_idx);
 	if (!bus)
 		return -ENOMEM;
 
@@ -3599,7 +3602,7 @@ void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 	int i;
 	struct kvm_io_bus *new_bus, *bus;
 
-	bus = kvm->buses[bus_idx];
+	bus = kvm_get_bus(kvm, bus_idx);
 	if (!bus)
 		return;
 
-- 
cgit v1.2.3


From a80cf7b5f4149753d5f19c872a47e66195b167d4 Mon Sep 17 00:00:00 2001
From: Christian Borntraeger <borntraeger@de.ibm.com>
Date: Thu, 6 Jul 2017 16:17:14 +0200
Subject: KVM: mark memory slots as rcu

we access the memslots array via srcu. Mark it as such and
use the right access functions also for the freeing of
memory slots.

Found by sparse:
./include/linux/kvm_host.h:565:16: error: incompatible types in
comparison expression (different address spaces)

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/kvm_host.h | 2 +-
 virt/kvm/kvm_main.c      | 6 ++++--
 2 files changed, 5 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 6a164f9eb02c..b3ca77a96b2d 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -390,7 +390,7 @@ struct kvm {
 	spinlock_t mmu_lock;
 	struct mutex slots_lock;
 	struct mm_struct *mm; /* userspace tied to this vm */
-	struct kvm_memslots *memslots[KVM_ADDRESS_SPACE_NUM];
+	struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM];
 	struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];
 
 	/*
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index d76e822f8929..6e6d4edf0e92 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -707,7 +707,8 @@ out_err_no_disable:
 	for (i = 0; i < KVM_NR_BUSES; i++)
 		kfree(rcu_access_pointer(kvm->buses[i]));
 	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++)
-		kvm_free_memslots(kvm, kvm->memslots[i]);
+		kvm_free_memslots(kvm,
+			rcu_dereference_protected(kvm->memslots[i], 1));
 	kvm_arch_free_vm(kvm);
 	mmdrop(current->mm);
 	return ERR_PTR(r);
@@ -756,7 +757,8 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	kvm_arch_destroy_vm(kvm);
 	kvm_destroy_devices(kvm);
 	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++)
-		kvm_free_memslots(kvm, kvm->memslots[i]);
+		kvm_free_memslots(kvm,
+			rcu_dereference_protected(kvm->memslots[i], 1));
 	cleanup_srcu_struct(&kvm->irq_srcu);
 	cleanup_srcu_struct(&kvm->srcu);
 	kvm_arch_free_vm(kvm);
-- 
cgit v1.2.3


From dcbbd97ccb9c6f4dad39875c1404d2643eaf110b Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Mon, 5 Jun 2017 14:44:59 +0200
Subject: libceph: remove ceph_sanitize_features() workaround

Reflects ceph.git commit ff1959282826ae6acd7134e1b1ede74ffd1cc04a.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/ceph_features.h | 21 ---------------------
 net/ceph/messenger.c               |  3 +--
 2 files changed, 1 insertion(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h
index fd8b2953c78f..4962708841b5 100644
--- a/include/linux/ceph/ceph_features.h
+++ b/include/linux/ceph/ceph_features.h
@@ -77,29 +77,8 @@
 #define CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING   (1ULL<<58) /* New, v7 encoding */
 #define CEPH_FEATURE_FS_FILE_LAYOUT_V2       (1ULL<<58) /* file_layout_t */
 
-/*
- * The introduction of CEPH_FEATURE_OSD_SNAPMAPPER caused the feature
- * vector to evaluate to 64 bit ~0.  To cope, we designate 1ULL << 63
- * to mean 33 bit ~0, and introduce a helper below to do the
- * translation.
- *
- * This was introduced by ceph.git commit
- *   9ea02b84104045c2ffd7e7f4e7af512953855ecd v0.58-657-g9ea02b8
- * and fixed by ceph.git commit
- *   4255b5c2fb54ae40c53284b3ab700fdfc7e61748 v0.65-263-g4255b5c
- */
 #define CEPH_FEATURE_RESERVED (1ULL<<63)
 
-static inline u64 ceph_sanitize_features(u64 features)
-{
-	if (features & CEPH_FEATURE_RESERVED) {
-		/* everything through OSD_SNAPMAPPER */
-		return 0x1ffffffffull;
-	} else {
-		return features;
-	}
-}
-
 /*
  * Features supported.
  */
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 588a91930051..9daed2540639 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -2033,8 +2033,7 @@ static int process_connect(struct ceph_connection *con)
 {
 	u64 sup_feat = from_msgr(con->msgr)->supported_features;
 	u64 req_feat = from_msgr(con->msgr)->required_features;
-	u64 server_feat = ceph_sanitize_features(
-				le64_to_cpu(con->in_reply.features));
+	u64 server_feat = le64_to_cpu(con->in_reply.features);
 	int ret;
 
 	dout("process_connect on %p tag %d\n", con, (int)con->in_tag);
-- 
cgit v1.2.3


From f179d3ba8cb9073c2d96315b79ff7bc658a1feee Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Mon, 5 Jun 2017 14:44:59 +0200
Subject: libceph: new features macros

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/ceph_features.h | 242 +++++++++++++++++++++++++------------
 1 file changed, 167 insertions(+), 75 deletions(-)

(limited to 'include')

diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h
index 4962708841b5..7fce9ed44af0 100644
--- a/include/linux/ceph/ceph_features.h
+++ b/include/linux/ceph/ceph_features.h
@@ -2,82 +2,174 @@
 #define __CEPH_FEATURES
 
 /*
- * feature bits
+ * Each time we reclaim bits for reuse we need to specify another bit
+ * that, if present, indicates we have the new incarnation of that
+ * feature.  Base case is 1 (first use).
  */
-#define CEPH_FEATURE_UID            (1ULL<<0)
-#define CEPH_FEATURE_NOSRCADDR      (1ULL<<1)
-#define CEPH_FEATURE_MONCLOCKCHECK  (1ULL<<2)
-#define CEPH_FEATURE_FLOCK          (1ULL<<3)
-#define CEPH_FEATURE_SUBSCRIBE2     (1ULL<<4)
-#define CEPH_FEATURE_MONNAMES       (1ULL<<5)
-#define CEPH_FEATURE_RECONNECT_SEQ  (1ULL<<6)
-#define CEPH_FEATURE_DIRLAYOUTHASH  (1ULL<<7)
-#define CEPH_FEATURE_OBJECTLOCATOR  (1ULL<<8)
-#define CEPH_FEATURE_PGID64         (1ULL<<9)
-#define CEPH_FEATURE_INCSUBOSDMAP   (1ULL<<10)
-#define CEPH_FEATURE_PGPOOL3        (1ULL<<11)
-#define CEPH_FEATURE_OSDREPLYMUX    (1ULL<<12)
-#define CEPH_FEATURE_OSDENC         (1ULL<<13)
-#define CEPH_FEATURE_OMAP           (1ULL<<14)
-#define CEPH_FEATURE_MONENC         (1ULL<<15)
-#define CEPH_FEATURE_QUERY_T        (1ULL<<16)
-#define CEPH_FEATURE_INDEP_PG_MAP   (1ULL<<17)
-#define CEPH_FEATURE_CRUSH_TUNABLES (1ULL<<18)
-#define CEPH_FEATURE_CHUNKY_SCRUB   (1ULL<<19)
-#define CEPH_FEATURE_MON_NULLROUTE  (1ULL<<20)
-#define CEPH_FEATURE_MON_GV         (1ULL<<21)
-#define CEPH_FEATURE_BACKFILL_RESERVATION (1ULL<<22)
-#define CEPH_FEATURE_MSG_AUTH	    (1ULL<<23)
-#define CEPH_FEATURE_RECOVERY_RESERVATION (1ULL<<24)
-#define CEPH_FEATURE_CRUSH_TUNABLES2 (1ULL<<25)
-#define CEPH_FEATURE_CREATEPOOLID   (1ULL<<26)
-#define CEPH_FEATURE_REPLY_CREATE_INODE   (1ULL<<27)
-#define CEPH_FEATURE_OSD_HBMSGS     (1ULL<<28)
-#define CEPH_FEATURE_MDSENC         (1ULL<<29)
-#define CEPH_FEATURE_OSDHASHPSPOOL  (1ULL<<30)
-#define CEPH_FEATURE_MON_SINGLE_PAXOS (1ULL<<31)
-#define CEPH_FEATURE_OSD_SNAPMAPPER (1ULL<<32)
-#define CEPH_FEATURE_MON_SCRUB      (1ULL<<33)
-#define CEPH_FEATURE_OSD_PACKED_RECOVERY (1ULL<<34)
-#define CEPH_FEATURE_OSD_CACHEPOOL (1ULL<<35)
-#define CEPH_FEATURE_CRUSH_V2      (1ULL<<36)  /* new indep; SET_* steps */
-#define CEPH_FEATURE_EXPORT_PEER   (1ULL<<37)
-#define CEPH_FEATURE_OSD_ERASURE_CODES (1ULL<<38)
-#define CEPH_FEATURE_OSD_TMAP2OMAP (1ULL<<38)   /* overlap with EC */
-/* The process supports new-style OSDMap encoding. Monitors also use
-   this bit to determine if peers support NAK messages. */
-#define CEPH_FEATURE_OSDMAP_ENC    (1ULL<<39)
-#define CEPH_FEATURE_MDS_INLINE_DATA     (1ULL<<40)
-#define CEPH_FEATURE_CRUSH_TUNABLES3     (1ULL<<41)
-#define CEPH_FEATURE_OSD_PRIMARY_AFFINITY (1ULL<<41)  /* overlap w/ tunables3 */
-#define CEPH_FEATURE_MSGR_KEEPALIVE2   (1ULL<<42)
-#define CEPH_FEATURE_OSD_POOLRESEND    (1ULL<<43)
-#define CEPH_FEATURE_ERASURE_CODE_PLUGINS_V2 (1ULL<<44)
-#define CEPH_FEATURE_OSD_SET_ALLOC_HINT (1ULL<<45)
-#define CEPH_FEATURE_OSD_FADVISE_FLAGS (1ULL<<46)
-#define CEPH_FEATURE_OSD_REPOP         (1ULL<<46)   /* overlap with fadvise */
-#define CEPH_FEATURE_OSD_OBJECT_DIGEST  (1ULL<<46)  /* overlap with fadvise */
-#define CEPH_FEATURE_OSD_TRANSACTION_MAY_LAYOUT (1ULL<<46) /* overlap w/ fadvise */
-#define CEPH_FEATURE_MDS_QUOTA      (1ULL<<47)
-#define CEPH_FEATURE_CRUSH_V4      (1ULL<<48)  /* straw2 buckets */
-#define CEPH_FEATURE_OSD_MIN_SIZE_RECOVERY (1ULL<<49)
-// duplicated since it was introduced at the same time as MIN_SIZE_RECOVERY
-#define CEPH_FEATURE_OSD_PROXY_FEATURES (1ULL<<49)  /* overlap w/ above */
-#define CEPH_FEATURE_MON_METADATA (1ULL<<50)
-#define CEPH_FEATURE_OSD_BITWISE_HOBJ_SORT (1ULL<<51) /* can sort objs bitwise */
-#define CEPH_FEATURE_OSD_PROXY_WRITE_FEATURES (1ULL<<52)
-#define CEPH_FEATURE_ERASURE_CODE_PLUGINS_V3 (1ULL<<53)
-#define CEPH_FEATURE_OSD_HITSET_GMT (1ULL<<54)
-#define CEPH_FEATURE_HAMMER_0_94_4 (1ULL<<55)
-#define CEPH_FEATURE_NEW_OSDOP_ENCODING   (1ULL<<56) /* New, v7 encoding */
-#define CEPH_FEATURE_MON_STATEFUL_SUB (1ULL<<57) /* stateful mon subscription */
-#define CEPH_FEATURE_MON_ROUTE_OSDMAP (1ULL<<57) /* peon sends osdmaps */
-#define CEPH_FEATURE_CRUSH_TUNABLES5	(1ULL<<58) /* chooseleaf stable mode */
-// duplicated since it was introduced at the same time as CEPH_FEATURE_CRUSH_TUNABLES5
-#define CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING   (1ULL<<58) /* New, v7 encoding */
-#define CEPH_FEATURE_FS_FILE_LAYOUT_V2       (1ULL<<58) /* file_layout_t */
-
-#define CEPH_FEATURE_RESERVED (1ULL<<63)
+#define CEPH_FEATURE_INCARNATION_1 (0ull)
+#define CEPH_FEATURE_INCARNATION_2 (1ull<<57) // CEPH_FEATURE_SERVER_JEWEL
+
+#define DEFINE_CEPH_FEATURE(bit, incarnation, name)			\
+	const static uint64_t CEPH_FEATURE_##name = (1ULL<<bit);		\
+	const static uint64_t CEPH_FEATUREMASK_##name =			\
+		(1ULL<<bit | CEPH_FEATURE_INCARNATION_##incarnation);
+
+/* this bit is ignored but still advertised by release *when* */
+#define DEFINE_CEPH_FEATURE_DEPRECATED(bit, incarnation, name, when) \
+	const static uint64_t DEPRECATED_CEPH_FEATURE_##name = (1ULL<<bit); \
+	const static uint64_t DEPRECATED_CEPH_FEATUREMASK_##name =		\
+		(1ULL<<bit | CEPH_FEATURE_INCARNATION_##incarnation);
+
+/*
+ * this bit is ignored by release *unused* and not advertised by
+ * release *unadvertised*
+ */
+#define DEFINE_CEPH_FEATURE_RETIRED(bit, inc, name, unused, unadvertised)
+
+
+/*
+ * test for a feature.  this test is safer than a typical mask against
+ * the bit because it ensures that we have the bit AND the marker for the
+ * bit's incarnation.  this must be used in any case where the features
+ * bits may include an old meaning of the bit.
+ */
+#define CEPH_HAVE_FEATURE(x, name)			\
+	(((x) & (CEPH_FEATUREMASK_##name)) == (CEPH_FEATUREMASK_##name))
+
+
+/*
+ * Notes on deprecation:
+ *
+ * A *major* release is a release through which all upgrades must pass
+ * (e.g., jewel).  For example, no pre-jewel server will ever talk to
+ * a post-jewel server (mon, osd, etc).
+ *
+ * For feature bits used *only* on the server-side:
+ *
+ *  - In the first phase we indicate that a feature is DEPRECATED as of
+ *    a particular release.  This is the first major release X (say,
+ *    jewel) that does not depend on its peers advertising the feature.
+ *    That is, it safely assumes its peers all have the feature.  We
+ *    indicate this with the DEPRECATED macro.  For example,
+ *
+ *      DEFINE_CEPH_FEATURE_DEPRECATED( 2, 1, MONCLOCKCHECK, JEWEL)
+ *
+ *    because 10.2.z (jewel) did not care if its peers advertised this
+ *    feature bit.
+ *
+ *  - In the second phase we stop advertising the the bit and call it
+ *    RETIRED.  This can normally be done in the *next* major release
+ *    following the one in which we marked the feature DEPRECATED.  In
+ *    the above example, for 12.0.z (luminous) we can say:
+ *
+ *      DEFINE_CEPH_FEATURE_RETIRED( 2, 1, MONCLOCKCHECK, JEWEL, LUMINOUS)
+ *
+ *  - The bit can be reused in the first post-luminous release, 13.0.z
+ *    (m).
+ *
+ * This ensures that no two versions who have different meanings for
+ * the bit ever speak to each other.
+ */
+
+DEFINE_CEPH_FEATURE( 0, 1, UID)
+DEFINE_CEPH_FEATURE( 1, 1, NOSRCADDR)
+DEFINE_CEPH_FEATURE_RETIRED( 2, 1, MONCLOCKCHECK, JEWEL, LUMINOUS)
+
+DEFINE_CEPH_FEATURE( 3, 1, FLOCK)
+DEFINE_CEPH_FEATURE( 4, 1, SUBSCRIBE2)
+DEFINE_CEPH_FEATURE( 5, 1, MONNAMES)
+DEFINE_CEPH_FEATURE( 6, 1, RECONNECT_SEQ)
+DEFINE_CEPH_FEATURE( 7, 1, DIRLAYOUTHASH)
+DEFINE_CEPH_FEATURE( 8, 1, OBJECTLOCATOR)
+DEFINE_CEPH_FEATURE( 9, 1, PGID64)
+DEFINE_CEPH_FEATURE(10, 1, INCSUBOSDMAP)
+DEFINE_CEPH_FEATURE(11, 1, PGPOOL3)
+DEFINE_CEPH_FEATURE(12, 1, OSDREPLYMUX)
+DEFINE_CEPH_FEATURE(13, 1, OSDENC)
+DEFINE_CEPH_FEATURE_RETIRED(14, 1, OMAP, HAMMER, JEWEL)
+DEFINE_CEPH_FEATURE(14, 2, SERVER_KRAKEN)
+DEFINE_CEPH_FEATURE(15, 1, MONENC)
+DEFINE_CEPH_FEATURE_RETIRED(16, 1, QUERY_T, JEWEL, LUMINOUS)
+
+DEFINE_CEPH_FEATURE_RETIRED(17, 1, INDEP_PG_MAP, JEWEL, LUMINOUS)
+
+DEFINE_CEPH_FEATURE(18, 1, CRUSH_TUNABLES)
+DEFINE_CEPH_FEATURE_RETIRED(19, 1, CHUNKY_SCRUB, JEWEL, LUMINOUS)
+
+DEFINE_CEPH_FEATURE_RETIRED(20, 1, MON_NULLROUTE, JEWEL, LUMINOUS)
+
+DEFINE_CEPH_FEATURE_RETIRED(21, 1, MON_GV, HAMMER, JEWEL)
+DEFINE_CEPH_FEATURE(21, 2, SERVER_LUMINOUS)
+DEFINE_CEPH_FEATURE(21, 2, RESEND_ON_SPLIT)  // overlap
+DEFINE_CEPH_FEATURE(21, 2, RADOS_BACKOFF)    // overlap
+DEFINE_CEPH_FEATURE(21, 2, OSDMAP_PG_UPMAP)  // overlap
+DEFINE_CEPH_FEATURE(21, 2, CRUSH_CHOOSE_ARGS) // overlap
+DEFINE_CEPH_FEATURE_RETIRED(22, 1, BACKFILL_RESERVATION, JEWEL, LUMINOUS)
+
+DEFINE_CEPH_FEATURE(23, 1, MSG_AUTH)
+DEFINE_CEPH_FEATURE_RETIRED(24, 1, RECOVERY_RESERVATION, JEWEL, LUNINOUS)
+
+DEFINE_CEPH_FEATURE(25, 1, CRUSH_TUNABLES2)
+DEFINE_CEPH_FEATURE(26, 1, CREATEPOOLID)
+DEFINE_CEPH_FEATURE(27, 1, REPLY_CREATE_INODE)
+DEFINE_CEPH_FEATURE_RETIRED(28, 1, OSD_HBMSGS, HAMMER, JEWEL)
+DEFINE_CEPH_FEATURE(28, 2, SERVER_M)
+DEFINE_CEPH_FEATURE(29, 1, MDSENC)
+DEFINE_CEPH_FEATURE(30, 1, OSDHASHPSPOOL)
+DEFINE_CEPH_FEATURE(31, 1, MON_SINGLE_PAXOS)  // deprecate me
+DEFINE_CEPH_FEATURE_RETIRED(32, 1, OSD_SNAPMAPPER, JEWEL, LUMINOUS)
+
+DEFINE_CEPH_FEATURE_RETIRED(33, 1, MON_SCRUB, JEWEL, LUMINOUS)
+
+DEFINE_CEPH_FEATURE_RETIRED(34, 1, OSD_PACKED_RECOVERY, JEWEL, LUMINOUS)
+
+DEFINE_CEPH_FEATURE(35, 1, OSD_CACHEPOOL)
+DEFINE_CEPH_FEATURE(36, 1, CRUSH_V2)
+DEFINE_CEPH_FEATURE(37, 1, EXPORT_PEER)
+DEFINE_CEPH_FEATURE(38, 1, OSD_ERASURE_CODES)
+DEFINE_CEPH_FEATURE(38, 1, OSD_OSD_TMAP2OMAP) // overlap
+DEFINE_CEPH_FEATURE(39, 1, OSDMAP_ENC)
+DEFINE_CEPH_FEATURE(40, 1, MDS_INLINE_DATA)
+DEFINE_CEPH_FEATURE(41, 1, CRUSH_TUNABLES3)
+DEFINE_CEPH_FEATURE(41, 1, OSD_PRIMARY_AFFINITY) // overlap
+DEFINE_CEPH_FEATURE(42, 1, MSGR_KEEPALIVE2)
+DEFINE_CEPH_FEATURE(43, 1, OSD_POOLRESEND)
+DEFINE_CEPH_FEATURE(44, 1, ERASURE_CODE_PLUGINS_V2)
+DEFINE_CEPH_FEATURE_RETIRED(45, 1, OSD_SET_ALLOC_HINT, JEWEL, LUMINOUS)
+
+DEFINE_CEPH_FEATURE(46, 1, OSD_FADVISE_FLAGS)
+DEFINE_CEPH_FEATURE_RETIRED(46, 1, OSD_REPOP, JEWEL, LUMINOUS) // overlap
+DEFINE_CEPH_FEATURE_RETIRED(46, 1, OSD_OBJECT_DIGEST, JEWEL, LUMINOUS) // overlap
+DEFINE_CEPH_FEATURE_RETIRED(46, 1, OSD_TRANSACTION_MAY_LAYOUT, JEWEL, LUMINOUS) // overlap
+
+DEFINE_CEPH_FEATURE(47, 1, MDS_QUOTA)
+DEFINE_CEPH_FEATURE(48, 1, CRUSH_V4)
+DEFINE_CEPH_FEATURE_RETIRED(49, 1, OSD_MIN_SIZE_RECOVERY, JEWEL, LUMINOUS)
+DEFINE_CEPH_FEATURE_RETIRED(49, 1, OSD_PROXY_FEATURES, JEWEL, LUMINOUS) // overlap
+
+DEFINE_CEPH_FEATURE(50, 1, MON_METADATA)
+DEFINE_CEPH_FEATURE(51, 1, OSD_BITWISE_HOBJ_SORT)
+DEFINE_CEPH_FEATURE(52, 1, OSD_PROXY_WRITE_FEATURES)
+DEFINE_CEPH_FEATURE(53, 1, ERASURE_CODE_PLUGINS_V3)
+DEFINE_CEPH_FEATURE(54, 1, OSD_HITSET_GMT)
+DEFINE_CEPH_FEATURE(55, 1, HAMMER_0_94_4)
+DEFINE_CEPH_FEATURE(56, 1, NEW_OSDOP_ENCODING)
+DEFINE_CEPH_FEATURE(57, 1, MON_STATEFUL_SUB)
+DEFINE_CEPH_FEATURE(57, 1, MON_ROUTE_OSDMAP) // overlap
+DEFINE_CEPH_FEATURE(57, 1, OSDSUBOP_NO_SNAPCONTEXT) // overlap
+DEFINE_CEPH_FEATURE(57, 1, SERVER_JEWEL) // overlap
+DEFINE_CEPH_FEATURE(58, 1, CRUSH_TUNABLES5)
+DEFINE_CEPH_FEATURE(58, 1, NEW_OSDOPREPLY_ENCODING) // overlap
+DEFINE_CEPH_FEATURE(58, 1, FS_FILE_LAYOUT_V2) // overlap
+DEFINE_CEPH_FEATURE(59, 1, FS_BTIME)
+DEFINE_CEPH_FEATURE(59, 1, FS_CHANGE_ATTR) // overlap
+DEFINE_CEPH_FEATURE(59, 1, MSG_ADDR2) // overlap
+DEFINE_CEPH_FEATURE(60, 1, BLKIN_TRACING)  // *do not share this bit*
+
+DEFINE_CEPH_FEATURE(61, 1, RESERVED2)          // unused, but slow down!
+DEFINE_CEPH_FEATURE(62, 1, RESERVED)           // do not use; used as a sentinal
+DEFINE_CEPH_FEATURE_DEPRECATED(63, 1, RESERVED_BROKEN, LUMINOUS) // client-facing
+
 
 /*
  * Features supported.
-- 
cgit v1.2.3


From 2d7522e0bda17eb3c7af0ffe74f03dd6c3cca443 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Mon, 5 Jun 2017 14:45:00 +0200
Subject: libceph: advertise support for OSD_POOLRESEND

The code has been in place since commit 63244fa123a7 ("libceph:
introduce ceph_osd_request_target, calc_target()"), and, with the
ceph_{oloc,oid}_copy() issue fixed in the previous commit, is now
in working order.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/ceph_features.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h
index 7fce9ed44af0..89c68af48539 100644
--- a/include/linux/ceph/ceph_features.h
+++ b/include/linux/ceph/ceph_features.h
@@ -197,6 +197,7 @@ DEFINE_CEPH_FEATURE_DEPRECATED(63, 1, RESERVED_BROKEN, LUMINOUS) // client-facin
 	 CEPH_FEATURE_CRUSH_TUNABLES3 |		\
 	 CEPH_FEATURE_OSD_PRIMARY_AFFINITY |	\
 	 CEPH_FEATURE_MSGR_KEEPALIVE2 |		\
+	 CEPH_FEATURE_OSD_POOLRESEND |		\
 	 CEPH_FEATURE_CRUSH_V4 |		\
 	 CEPH_FEATURE_CRUSH_TUNABLES5 |		\
 	 CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING)
-- 
cgit v1.2.3


From 220abf5aa7ba5f544f1b589bde33761c60bbf9a0 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Mon, 5 Jun 2017 14:45:00 +0200
Subject: libceph: support SERVER_JEWEL feature bits

Only MON_STATEFUL_SUB, really.  MON_ROUTE_OSDMAP and
OSDSUBOP_NO_SNAPCONTEXT are irrelevant.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/ceph_features.h | 2 ++
 net/ceph/mon_client.c              | 8 +++++++-
 2 files changed, 9 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h
index 89c68af48539..78a58770e6e9 100644
--- a/include/linux/ceph/ceph_features.h
+++ b/include/linux/ceph/ceph_features.h
@@ -199,6 +199,8 @@ DEFINE_CEPH_FEATURE_DEPRECATED(63, 1, RESERVED_BROKEN, LUMINOUS) // client-facin
 	 CEPH_FEATURE_MSGR_KEEPALIVE2 |		\
 	 CEPH_FEATURE_OSD_POOLRESEND |		\
 	 CEPH_FEATURE_CRUSH_V4 |		\
+	 CEPH_FEATURE_SERVER_JEWEL |		\
+	 CEPH_FEATURE_MON_STATEFUL_SUB |	\
 	 CEPH_FEATURE_CRUSH_TUNABLES5 |		\
 	 CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING)
 
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index 250f11f78609..875675765531 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -6,6 +6,7 @@
 #include <linux/random.h>
 #include <linux/sched.h>
 
+#include <linux/ceph/ceph_features.h>
 #include <linux/ceph/mon_client.h>
 #include <linux/ceph/libceph.h>
 #include <linux/ceph/debugfs.h>
@@ -297,6 +298,10 @@ static void handle_subscribe_ack(struct ceph_mon_client *monc,
 
 	mutex_lock(&monc->mutex);
 	if (monc->sub_renew_sent) {
+		/*
+		 * This is only needed for legacy (infernalis or older)
+		 * MONs -- see delayed_work().
+		 */
 		monc->sub_renew_after = monc->sub_renew_sent +
 					    (seconds >> 1) * HZ - 1;
 		dout("%s sent %lu duration %d renew after %lu\n", __func__,
@@ -955,7 +960,8 @@ static void delayed_work(struct work_struct *work)
 			__validate_auth(monc);
 		}
 
-		if (is_auth) {
+		if (is_auth &&
+		    !(monc->con.peer_features & CEPH_FEATURE_MON_STATEFUL_SUB)) {
 			unsigned long now = jiffies;
 
 			dout("%s renew subs? now %lu renew after %lu\n",
-- 
cgit v1.2.3


From dc93e0e2831de2f80817b89aae4864b88332fcce Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Mon, 5 Jun 2017 14:45:00 +0200
Subject: libceph: fold [l]req->last_force_resend into ceph_osd_request_target

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/osd_client.h |  4 ++--
 net/ceph/osd_client.c           | 21 ++++++++++-----------
 2 files changed, 12 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 85650b415e73..ef630ebd1169 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -148,6 +148,8 @@ struct ceph_osd_request_target {
 	unsigned int flags;                /* CEPH_OSD_FLAG_* */
 	bool paused;
 
+	u32 last_force_resend;
+
 	int osd;
 };
 
@@ -193,7 +195,6 @@ struct ceph_osd_request {
 	unsigned long r_stamp;                /* jiffies, send or check time */
 	unsigned long r_start_stamp;          /* jiffies */
 	int r_attempts;
-	u32 r_last_force_resend;
 	u32 r_map_dne_bound;
 
 	struct ceph_osd_req_op r_ops[];
@@ -221,7 +222,6 @@ struct ceph_osd_linger_request {
 	struct list_head pending_lworks;
 
 	struct ceph_osd_request_target t;
-	u32 last_force_resend;
 	u32 map_dne_bound;
 
 	struct timespec mtime;
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 924f07c36ddb..aca6319b99b6 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -384,6 +384,8 @@ static void target_copy(struct ceph_osd_request_target *dest,
 	dest->flags = src->flags;
 	dest->paused = src->paused;
 
+	dest->last_force_resend = src->last_force_resend;
+
 	dest->osd = src->osd;
 }
 
@@ -1311,7 +1313,6 @@ enum calc_target_result {
 
 static enum calc_target_result calc_target(struct ceph_osd_client *osdc,
 					   struct ceph_osd_request_target *t,
-					   u32 *last_force_resend,
 					   bool any_change)
 {
 	struct ceph_pg_pool_info *pi;
@@ -1332,11 +1333,10 @@ static enum calc_target_result calc_target(struct ceph_osd_client *osdc,
 	}
 
 	if (osdc->osdmap->epoch == pi->last_force_request_resend) {
-		if (last_force_resend &&
-		    *last_force_resend < pi->last_force_request_resend) {
-			*last_force_resend = pi->last_force_request_resend;
+		if (t->last_force_resend < pi->last_force_request_resend) {
+			t->last_force_resend = pi->last_force_request_resend;
 			force_resend = true;
-		} else if (!last_force_resend) {
+		} else if (t->last_force_resend == 0) {
 			force_resend = true;
 		}
 	}
@@ -1645,7 +1645,7 @@ static void __submit_request(struct ceph_osd_request *req, bool wrlocked)
 	dout("%s req %p wrlocked %d\n", __func__, req, wrlocked);
 
 again:
-	ct_res = calc_target(osdc, &req->r_t, &req->r_last_force_resend, false);
+	ct_res = calc_target(osdc, &req->r_t, false);
 	if (ct_res == CALC_TARGET_POOL_DNE && !wrlocked)
 		goto promote;
 
@@ -2441,7 +2441,7 @@ static void linger_submit(struct ceph_osd_linger_request *lreq)
 	struct ceph_osd_client *osdc = lreq->osdc;
 	struct ceph_osd *osd;
 
-	calc_target(osdc, &lreq->t, &lreq->last_force_resend, false);
+	calc_target(osdc, &lreq->t, false);
 	osd = lookup_create_osd(osdc, lreq->t.osd, true);
 	link_linger(osd, lreq);
 
@@ -3059,7 +3059,7 @@ recalc_linger_target(struct ceph_osd_linger_request *lreq)
 	struct ceph_osd_client *osdc = lreq->osdc;
 	enum calc_target_result ct_res;
 
-	ct_res = calc_target(osdc, &lreq->t, &lreq->last_force_resend, true);
+	ct_res = calc_target(osdc, &lreq->t, true);
 	if (ct_res == CALC_TARGET_NEED_RESEND) {
 		struct ceph_osd *osd;
 
@@ -3130,8 +3130,7 @@ static void scan_requests(struct ceph_osd *osd,
 		n = rb_next(n); /* unlink_request(), check_pool_dne() */
 
 		dout("%s req %p tid %llu\n", __func__, req, req->r_tid);
-		ct_res = calc_target(osdc, &req->r_t,
-				     &req->r_last_force_resend, false);
+		ct_res = calc_target(osdc, &req->r_t, false);
 		switch (ct_res) {
 		case CALC_TARGET_NO_ACTION:
 			force_resend_writes = cleared_full ||
@@ -3240,7 +3239,7 @@ static void kick_requests(struct ceph_osd_client *osdc,
 		erase_request(need_resend, req); /* before link_request() */
 
 		WARN_ON(req->r_osd);
-		calc_target(osdc, &req->r_t, NULL, false);
+		calc_target(osdc, &req->r_t, false);
 		osd = lookup_create_osd(osdc, req->r_t.osd, true);
 		link_request(osd, req);
 		if (!req->r_linger) {
-- 
cgit v1.2.3


From dc98ff7230e5ccf11c621dff0d590e83574a7184 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Thu, 15 Jun 2017 16:30:53 +0200
Subject: libceph: introduce ceph_spg, ceph_pg_to_primary_shard()

Store both raw pgid and actual spgid in ceph_osd_request_target.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/osd_client.h |  3 ++-
 include/linux/ceph/osdmap.h     | 10 ++++++++++
 net/ceph/debugfs.c              | 11 ++++++++++-
 net/ceph/osd_client.c           |  7 +++++--
 net/ceph/osdmap.c               | 33 +++++++++++++++++++++++++++++++++
 5 files changed, 60 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index ef630ebd1169..6114f7b02135 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -136,7 +136,8 @@ struct ceph_osd_request_target {
 	struct ceph_object_id target_oid;
 	struct ceph_object_locator target_oloc;
 
-	struct ceph_pg pgid;
+	struct ceph_pg pgid;               /* last raw pg we mapped to */
+	struct ceph_spg spgid;             /* last actual spg we mapped to */
 	u32 pg_num;
 	u32 pg_num_mask;
 	struct ceph_osds acting;
diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index 938656f70807..7ae5b416b4b6 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -24,6 +24,13 @@ struct ceph_pg {
 	uint32_t seed;
 };
 
+#define CEPH_SPG_NOSHARD	-1
+
+struct ceph_spg {
+	struct ceph_pg pgid;
+	s8 shard;
+};
+
 int ceph_pg_compare(const struct ceph_pg *lhs, const struct ceph_pg *rhs);
 
 #define CEPH_POOL_FLAG_HASHPSPOOL	(1ULL << 0) /* hash pg seed and pool id
@@ -271,6 +278,9 @@ void ceph_pg_to_up_acting_osds(struct ceph_osdmap *osdmap,
 			       const struct ceph_pg *raw_pgid,
 			       struct ceph_osds *up,
 			       struct ceph_osds *acting);
+bool ceph_pg_to_primary_shard(struct ceph_osdmap *osdmap,
+			      const struct ceph_pg *raw_pgid,
+			      struct ceph_spg *spgid);
 int ceph_pg_to_acting_primary(struct ceph_osdmap *osdmap,
 			      const struct ceph_pg *raw_pgid);
 
diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c
index 71ba13927b3d..50ab1bdb16e2 100644
--- a/net/ceph/debugfs.c
+++ b/net/ceph/debugfs.c
@@ -147,11 +147,20 @@ static int monc_show(struct seq_file *s, void *p)
 	return 0;
 }
 
+static void dump_spgid(struct seq_file *s, const struct ceph_spg *spgid)
+{
+	seq_printf(s, "%llu.%x", spgid->pgid.pool, spgid->pgid.seed);
+	if (spgid->shard != CEPH_SPG_NOSHARD)
+		seq_printf(s, "s%d", spgid->shard);
+}
+
 static void dump_target(struct seq_file *s, struct ceph_osd_request_target *t)
 {
 	int i;
 
-	seq_printf(s, "osd%d\t%llu.%x\t[", t->osd, t->pgid.pool, t->pgid.seed);
+	seq_printf(s, "osd%d\t%llu.%x\t", t->osd, t->pgid.pool, t->pgid.seed);
+	dump_spgid(s, &t->spgid);
+	seq_puts(s, "\t[");
 	for (i = 0; i < t->up.size; i++)
 		seq_printf(s, "%s%d", (!i ? "" : ","), t->up.osds[i]);
 	seq_printf(s, "]/%d\t[", t->up.primary);
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index aca6319b99b6..66509414f4c8 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -373,6 +373,7 @@ static void target_copy(struct ceph_osd_request_target *dest,
 	ceph_oloc_copy(&dest->target_oloc, &src->target_oloc);
 
 	dest->pgid = src->pgid; /* struct */
+	dest->spgid = src->spgid; /* struct */
 	dest->pg_num = src->pg_num;
 	dest->pg_num_mask = src->pg_num_mask;
 	ceph_osds_copy(&dest->acting, &src->acting);
@@ -1394,6 +1395,7 @@ static enum calc_target_result calc_target(struct ceph_osd_client *osdc,
 	    ceph_osds_changed(&t->acting, &acting, any_change) ||
 	    force_resend) {
 		t->pgid = pgid; /* struct */
+		ceph_pg_to_primary_shard(osdc->osdmap, &pgid, &t->spgid);
 		ceph_osds_copy(&t->acting, &acting);
 		ceph_osds_copy(&t->up, &up);
 		t->size = pi->size;
@@ -1595,9 +1597,10 @@ static void send_request(struct ceph_osd_request *req)
 
 	encode_request(req, req->r_request);
 
-	dout("%s req %p tid %llu to pg %llu.%x osd%d flags 0x%x attempt %d\n",
+	dout("%s req %p tid %llu to pgid %llu.%x spgid %llu.%xs%d osd%d flags 0x%x attempt %d\n",
 	     __func__, req, req->r_tid, req->r_t.pgid.pool, req->r_t.pgid.seed,
-	     req->r_t.osd, req->r_flags, req->r_attempts);
+	     req->r_t.spgid.pgid.pool, req->r_t.spgid.pgid.seed,
+	     req->r_t.spgid.shard, osd->o_osd, req->r_flags, req->r_attempts);
 
 	req->r_t.paused = false;
 	req->r_stamp = jiffies;
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 710ee3dc01b9..a4155620eace 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -2265,6 +2265,39 @@ out:
 	WARN_ON(!osds_valid(up) || !osds_valid(acting));
 }
 
+bool ceph_pg_to_primary_shard(struct ceph_osdmap *osdmap,
+			      const struct ceph_pg *raw_pgid,
+			      struct ceph_spg *spgid)
+{
+	struct ceph_pg_pool_info *pi;
+	struct ceph_pg pgid;
+	struct ceph_osds up, acting;
+	int i;
+
+	pi = ceph_pg_pool_by_id(osdmap, raw_pgid->pool);
+	if (!pi)
+		return false;
+
+	raw_pg_to_pg(pi, raw_pgid, &pgid);
+
+	if (ceph_can_shift_osds(pi)) {
+		spgid->pgid = pgid; /* struct */
+		spgid->shard = CEPH_SPG_NOSHARD;
+		return true;
+	}
+
+	ceph_pg_to_up_acting_osds(osdmap, &pgid, &up, &acting);
+	for (i = 0; i < acting.size; i++) {
+		if (acting.osds[i] == acting.primary) {
+			spgid->pgid = pgid; /* struct */
+			spgid->shard = i;
+			return true;
+		}
+	}
+
+	return false;
+}
+
 /*
  * Return acting primary for given PG, or -1 if none.
  */
-- 
cgit v1.2.3


From 98ad5ebd1505eb903ae8bc27e94c1ab0d1c3e651 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Thu, 15 Jun 2017 16:30:54 +0200
Subject: libceph: ceph_connection_operations::reencode_message() method

Give upper layers a chance to reencode the message after the connection
is negotiated and ->peer_features is set.  OSD client will use this to
support both luminous and pre-luminous OSDs (in a single cluster): the
former need MOSDOp v8; the latter will continue to be sent MOSDOp v4.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/messenger.h | 2 ++
 net/ceph/messenger.c           | 7 +++++--
 2 files changed, 7 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index c5c4c713e00f..fbd94d9fa5dd 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -44,6 +44,8 @@ struct ceph_connection_operations {
 					struct ceph_msg_header *hdr,
 					int *skip);
 
+	void (*reencode_message) (struct ceph_msg *msg);
+
 	int (*sign_message) (struct ceph_msg *msg);
 	int (*check_message_signature) (struct ceph_msg *msg);
 };
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 9daed2540639..0c31035bbfee 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -1288,13 +1288,16 @@ static void prepare_write_message(struct ceph_connection *con)
 		m->hdr.seq = cpu_to_le64(++con->out_seq);
 		m->needs_out_seq = false;
 	}
-	WARN_ON(m->data_length != le32_to_cpu(m->hdr.data_len));
+
+	if (con->ops->reencode_message)
+		con->ops->reencode_message(m);
 
 	dout("prepare_write_message %p seq %lld type %d len %d+%d+%zd\n",
 	     m, con->out_seq, le16_to_cpu(m->hdr.type),
 	     le32_to_cpu(m->hdr.front_len), le32_to_cpu(m->hdr.middle_len),
 	     m->data_length);
-	BUG_ON(le32_to_cpu(m->hdr.front_len) != m->front.iov_len);
+	WARN_ON(m->front.iov_len != le32_to_cpu(m->hdr.front_len));
+	WARN_ON(m->data_length != le32_to_cpu(m->hdr.data_len));
 
 	/* tag + hdr + front + middle */
 	con_out_kvec_add(con, sizeof (tag_msg), &tag_msg);
-- 
cgit v1.2.3


From 8cb441c0545dfd4dafeedc1e2d7157e1072413ac Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Thu, 15 Jun 2017 16:30:54 +0200
Subject: libceph: MOSDOp v8 encoding (actual spgid + full hash)

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/osd_client.h |  17 +++++
 include/linux/ceph/osdmap.h     |   4 +-
 net/ceph/osd_client.c           | 153 +++++++++++++++++++++++++++++++++++-----
 3 files changed, 154 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 6114f7b02135..bca2718ac253 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -205,6 +205,23 @@ struct ceph_request_redirect {
 	struct ceph_object_locator oloc;
 };
 
+/*
+ * osd request identifier
+ *
+ * caller name + incarnation# + tid to unique identify this request
+ */
+struct ceph_osd_reqid {
+	struct ceph_entity_name name;
+	__le64 tid;
+	__le32 inc;
+} __packed;
+
+struct ceph_blkin_trace_info {
+	__le64 trace_id;
+	__le64 span_id;
+	__le64 parent_span_id;
+} __packed;
+
 typedef void (*rados_watchcb2_t)(void *arg, u64 notify_id, u64 cookie,
 				 u64 notifier_id, void *data, size_t data_len);
 typedef void (*rados_watcherrcb_t)(void *arg, u64 cookie, int err);
diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index 7ae5b416b4b6..66447fc7f334 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -205,11 +205,13 @@ static inline struct ceph_entity_addr *ceph_osd_addr(struct ceph_osdmap *map,
 	return &map->osd_addr[osd];
 }
 
+#define CEPH_PGID_ENCODING_LEN		(1 + 8 + 4 + 4)
+
 static inline int ceph_decode_pgid(void **p, void *end, struct ceph_pg *pgid)
 {
 	__u8 version;
 
-	if (!ceph_has_room(p, end, 1 + 8 + 4 + 4)) {
+	if (!ceph_has_room(p, end, CEPH_PGID_ENCODING_LEN)) {
 		pr_warn("incomplete pg encoding\n");
 		return -EINVAL;
 	}
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index b0298c3681b6..eaaf17e7c37b 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -12,6 +12,7 @@
 #include <linux/bio.h>
 #endif
 
+#include <linux/ceph/ceph_features.h>
 #include <linux/ceph/libceph.h>
 #include <linux/ceph/osd_client.h>
 #include <linux/ceph/messenger.h>
@@ -555,17 +556,21 @@ int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp)
 	WARN_ON(ceph_oloc_empty(&req->r_base_oloc));
 
 	/* create request message */
-	msg_size = 4 + 4 + 4; /* client_inc, osdmap_epoch, flags */
-	msg_size += 4 + 4 + 4 + 8; /* mtime, reassert_version */
+	msg_size = CEPH_ENCODING_START_BLK_LEN +
+			CEPH_PGID_ENCODING_LEN + 1; /* spgid */
+	msg_size += 4 + 4 + 4; /* hash, osdmap_epoch, flags */
+	msg_size += CEPH_ENCODING_START_BLK_LEN +
+			sizeof(struct ceph_osd_reqid); /* reqid */
+	msg_size += sizeof(struct ceph_blkin_trace_info); /* trace */
+	msg_size += 4 + sizeof(struct ceph_timespec); /* client_inc, mtime */
 	msg_size += CEPH_ENCODING_START_BLK_LEN +
 			ceph_oloc_encoding_size(&req->r_base_oloc); /* oloc */
-	msg_size += 1 + 8 + 4 + 4; /* pgid */
 	msg_size += 4 + req->r_base_oid.name_len; /* oid */
 	msg_size += 2 + req->r_num_ops * sizeof(struct ceph_osd_op);
 	msg_size += 8; /* snapid */
 	msg_size += 8; /* snap_seq */
 	msg_size += 4 + 8 * (req->r_snapc ? req->r_snapc->num_snaps : 0);
-	msg_size += 4; /* retry_attempt */
+	msg_size += 4 + 8; /* retry_attempt, features */
 
 	if (req->r_mempool)
 		msg = ceph_msgpool_get(&osdc->msgpool_op, 0);
@@ -1493,6 +1498,13 @@ static void encode_pgid(void **p, const struct ceph_pg *pgid)
 	ceph_encode_32(p, -1); /* preferred */
 }
 
+static void encode_spgid(void **p, const struct ceph_spg *spgid)
+{
+	ceph_start_encoding(p, 1, 1, CEPH_PGID_ENCODING_LEN + 1);
+	encode_pgid(p, &spgid->pgid);
+	ceph_encode_8(p, spgid->shard);
+}
+
 static void encode_oloc(void **p, void *end,
 			const struct ceph_object_locator *oloc)
 {
@@ -1507,7 +1519,8 @@ static void encode_oloc(void **p, void *end,
 		ceph_encode_32(p, 0);
 }
 
-static void encode_request(struct ceph_osd_request *req, struct ceph_msg *msg)
+static void encode_request_partial(struct ceph_osd_request *req,
+				   struct ceph_msg *msg)
 {
 	void *p = msg->front.iov_base;
 	void *const end = p + msg->front_alloc_len;
@@ -1524,18 +1537,25 @@ static void encode_request(struct ceph_osd_request *req, struct ceph_msg *msg)
 
 	setup_request_data(req, msg);
 
-	ceph_encode_32(&p, 1); /* client_inc, always 1 */
+	encode_spgid(&p, &req->r_t.spgid); /* actual spg */
+	ceph_encode_32(&p, req->r_t.pgid.seed); /* raw hash */
 	ceph_encode_32(&p, req->r_osdc->osdmap->epoch);
 	ceph_encode_32(&p, req->r_flags);
+
+	/* reqid */
+	ceph_start_encoding(&p, 2, 2, sizeof(struct ceph_osd_reqid));
+	memset(p, 0, sizeof(struct ceph_osd_reqid));
+	p += sizeof(struct ceph_osd_reqid);
+
+	/* trace */
+	memset(p, 0, sizeof(struct ceph_blkin_trace_info));
+	p += sizeof(struct ceph_blkin_trace_info);
+
+	ceph_encode_32(&p, 0); /* client_inc, always 0 */
 	ceph_encode_timespec(p, &req->r_mtime);
 	p += sizeof(struct ceph_timespec);
 
-	/* reassert_version */
-	memset(p, 0, sizeof(struct ceph_eversion));
-	p += sizeof(struct ceph_eversion);
-
 	encode_oloc(&p, end, &req->r_t.target_oloc);
-	encode_pgid(&p, &req->r_t.pgid);
 	ceph_encode_string(&p, end, req->r_t.target_oid.name,
 			   req->r_t.target_oid.name_len);
 
@@ -1558,11 +1578,10 @@ static void encode_request(struct ceph_osd_request *req, struct ceph_msg *msg)
 	}
 
 	ceph_encode_32(&p, req->r_attempts); /* retry_attempt */
+	BUG_ON(p != end - 8); /* space for features */
 
-	BUG_ON(p > end);
-	msg->front.iov_len = p - msg->front.iov_base;
-	msg->hdr.version = cpu_to_le16(4); /* MOSDOp v4 */
-	msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
+	msg->hdr.version = cpu_to_le16(8); /* MOSDOp v8 */
+	/* front_len is finalized in encode_request_finish() */
 	msg->hdr.data_len = cpu_to_le32(data_len);
 	/*
 	 * The header "data_off" is a hint to the receiver allowing it
@@ -1571,9 +1590,99 @@ static void encode_request(struct ceph_osd_request *req, struct ceph_msg *msg)
 	 */
 	msg->hdr.data_off = cpu_to_le16(req->r_data_offset);
 
-	dout("%s req %p oid %s oid_len %d front %zu data %u\n", __func__,
-	     req, req->r_t.target_oid.name, req->r_t.target_oid.name_len,
-	     msg->front.iov_len, data_len);
+	dout("%s req %p msg %p oid %s oid_len %d\n", __func__, req, msg,
+	     req->r_t.target_oid.name, req->r_t.target_oid.name_len);
+}
+
+static void encode_request_finish(struct ceph_msg *msg)
+{
+	void *p = msg->front.iov_base;
+	void *const end = p + msg->front_alloc_len;
+
+	if (CEPH_HAVE_FEATURE(msg->con->peer_features, RESEND_ON_SPLIT)) {
+		/* luminous OSD -- encode features and be done */
+		p = end - 8;
+		ceph_encode_64(&p, msg->con->peer_features);
+	} else {
+		struct {
+			char spgid[CEPH_ENCODING_START_BLK_LEN +
+				   CEPH_PGID_ENCODING_LEN + 1];
+			__le32 hash;
+			__le32 epoch;
+			__le32 flags;
+			char reqid[CEPH_ENCODING_START_BLK_LEN +
+				   sizeof(struct ceph_osd_reqid)];
+			char trace[sizeof(struct ceph_blkin_trace_info)];
+			__le32 client_inc;
+			struct ceph_timespec mtime;
+		} __packed head;
+		struct ceph_pg pgid;
+		void *oloc, *oid, *tail;
+		int oloc_len, oid_len, tail_len;
+		int len;
+
+		/*
+		 * Pre-luminous OSD -- reencode v8 into v4 using @head
+		 * as a temporary buffer.  Encode the raw PG; the rest
+		 * is just a matter of moving oloc, oid and tail blobs
+		 * around.
+		 */
+		memcpy(&head, p, sizeof(head));
+		p += sizeof(head);
+
+		oloc = p;
+		p += CEPH_ENCODING_START_BLK_LEN;
+		pgid.pool = ceph_decode_64(&p);
+		p += 4 + 4; /* preferred, key len */
+		len = ceph_decode_32(&p);
+		p += len;   /* nspace */
+		oloc_len = p - oloc;
+
+		oid = p;
+		len = ceph_decode_32(&p);
+		p += len;
+		oid_len = p - oid;
+
+		tail = p;
+		tail_len = (end - p) - 8;
+
+		p = msg->front.iov_base;
+		ceph_encode_copy(&p, &head.client_inc, sizeof(head.client_inc));
+		ceph_encode_copy(&p, &head.epoch, sizeof(head.epoch));
+		ceph_encode_copy(&p, &head.flags, sizeof(head.flags));
+		ceph_encode_copy(&p, &head.mtime, sizeof(head.mtime));
+
+		/* reassert_version */
+		memset(p, 0, sizeof(struct ceph_eversion));
+		p += sizeof(struct ceph_eversion);
+
+		BUG_ON(p >= oloc);
+		memmove(p, oloc, oloc_len);
+		p += oloc_len;
+
+		pgid.seed = le32_to_cpu(head.hash);
+		encode_pgid(&p, &pgid); /* raw pg */
+
+		BUG_ON(p >= oid);
+		memmove(p, oid, oid_len);
+		p += oid_len;
+
+		/* tail -- ops, snapid, snapc, retry_attempt */
+		BUG_ON(p >= tail);
+		memmove(p, tail, tail_len);
+		p += tail_len;
+
+		msg->hdr.version = cpu_to_le16(4); /* MOSDOp v4 */
+	}
+
+	BUG_ON(p > end);
+	msg->front.iov_len = p - msg->front.iov_base;
+	msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
+
+	dout("%s msg %p tid %llu %u+%u+%u v%d\n", __func__, msg,
+	     le64_to_cpu(msg->hdr.tid), le32_to_cpu(msg->hdr.front_len),
+	     le32_to_cpu(msg->hdr.middle_len), le32_to_cpu(msg->hdr.data_len),
+	     le16_to_cpu(msg->hdr.version));
 }
 
 /*
@@ -1599,7 +1708,7 @@ static void send_request(struct ceph_osd_request *req)
 	else
 		WARN_ON(req->r_flags & CEPH_OSD_FLAG_RETRY);
 
-	encode_request(req, req->r_request);
+	encode_request_partial(req, req->r_request);
 
 	dout("%s req %p tid %llu to pgid %llu.%x spgid %llu.%xs%d osd%d flags 0x%x attempt %d\n",
 	     __func__, req, req->r_tid, req->r_t.pgid.pool, req->r_t.pgid.seed,
@@ -4577,6 +4686,11 @@ static int invalidate_authorizer(struct ceph_connection *con)
 	return ceph_monc_validate_auth(&osdc->client->monc);
 }
 
+static void osd_reencode_message(struct ceph_msg *msg)
+{
+	encode_request_finish(msg);
+}
+
 static int osd_sign_message(struct ceph_msg *msg)
 {
 	struct ceph_osd *o = msg->con->private;
@@ -4601,6 +4715,7 @@ static const struct ceph_connection_operations osd_con_ops = {
 	.verify_authorizer_reply = verify_authorizer_reply,
 	.invalidate_authorizer = invalidate_authorizer,
 	.alloc_msg = alloc_msg,
+	.reencode_message = osd_reencode_message,
 	.sign_message = osd_sign_message,
 	.check_message_signature = osd_check_message_signature,
 	.fault = osd_fault,
-- 
cgit v1.2.3


From 7de030d6b10a56e991312a978ace6be3c090097c Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Thu, 15 Jun 2017 16:30:54 +0200
Subject: libceph: resend on PG splits if OSD has RESEND_ON_SPLIT

Note that ceph_osd_request_target fields are updated regardless of
RESEND_ON_SPLIT.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/osdmap.h |  2 ++
 net/ceph/osd_client.c       | 21 ++++++++++++++-------
 net/ceph/osdmap.c           |  7 +++----
 3 files changed, 19 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index 66447fc7f334..63fb073a3355 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -249,6 +249,8 @@ static inline void ceph_osds_init(struct ceph_osds *set)
 
 void ceph_osds_copy(struct ceph_osds *dest, const struct ceph_osds *src);
 
+bool ceph_pg_is_split(const struct ceph_pg *pgid, u32 old_pg_num,
+		      u32 new_pg_num);
 bool ceph_is_new_interval(const struct ceph_osds *old_acting,
 			  const struct ceph_osds *new_acting,
 			  const struct ceph_osds *old_up,
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 4143f73590f3..518dbac599d0 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1319,6 +1319,7 @@ enum calc_target_result {
 
 static enum calc_target_result calc_target(struct ceph_osd_client *osdc,
 					   struct ceph_osd_request_target *t,
+					   struct ceph_connection *con,
 					   bool any_change)
 {
 	struct ceph_pg_pool_info *pi;
@@ -1327,6 +1328,7 @@ static enum calc_target_result calc_target(struct ceph_osd_client *osdc,
 	bool force_resend = false;
 	bool unpaused = false;
 	bool legacy_change;
+	bool split = false;
 	bool need_check_tiering = false;
 	bool sort_bitwise = ceph_osdmap_flag(osdc, CEPH_OSDMAP_SORTBITWISE);
 	enum calc_target_result ct_res;
@@ -1398,8 +1400,10 @@ static enum calc_target_result calc_target(struct ceph_osd_client *osdc,
 	}
 	legacy_change = ceph_pg_compare(&t->pgid, &pgid) ||
 			ceph_osds_changed(&t->acting, &acting, any_change);
+	if (t->pg_num)
+		split = ceph_pg_is_split(&last_pgid, t->pg_num, pi->pg_num);
 
-	if (legacy_change || force_resend) {
+	if (legacy_change || force_resend || split) {
 		t->pgid = pgid; /* struct */
 		ceph_pg_to_primary_shard(osdc->osdmap, &pgid, &t->spgid);
 		ceph_osds_copy(&t->acting, &acting);
@@ -1413,7 +1417,9 @@ static enum calc_target_result calc_target(struct ceph_osd_client *osdc,
 		t->osd = acting.primary;
 	}
 
-	if (unpaused || legacy_change || force_resend)
+	if (unpaused || legacy_change || force_resend ||
+	    (split && con && CEPH_HAVE_FEATURE(con->peer_features,
+					       RESEND_ON_SPLIT)))
 		ct_res = CALC_TARGET_NEED_RESEND;
 	else
 		ct_res = CALC_TARGET_NO_ACTION;
@@ -1765,7 +1771,7 @@ static void __submit_request(struct ceph_osd_request *req, bool wrlocked)
 	dout("%s req %p wrlocked %d\n", __func__, req, wrlocked);
 
 again:
-	ct_res = calc_target(osdc, &req->r_t, false);
+	ct_res = calc_target(osdc, &req->r_t, NULL, false);
 	if (ct_res == CALC_TARGET_POOL_DNE && !wrlocked)
 		goto promote;
 
@@ -2561,7 +2567,7 @@ static void linger_submit(struct ceph_osd_linger_request *lreq)
 	struct ceph_osd_client *osdc = lreq->osdc;
 	struct ceph_osd *osd;
 
-	calc_target(osdc, &lreq->t, false);
+	calc_target(osdc, &lreq->t, NULL, false);
 	osd = lookup_create_osd(osdc, lreq->t.osd, true);
 	link_linger(osd, lreq);
 
@@ -3179,7 +3185,7 @@ recalc_linger_target(struct ceph_osd_linger_request *lreq)
 	struct ceph_osd_client *osdc = lreq->osdc;
 	enum calc_target_result ct_res;
 
-	ct_res = calc_target(osdc, &lreq->t, true);
+	ct_res = calc_target(osdc, &lreq->t, NULL, true);
 	if (ct_res == CALC_TARGET_NEED_RESEND) {
 		struct ceph_osd *osd;
 
@@ -3250,7 +3256,8 @@ static void scan_requests(struct ceph_osd *osd,
 		n = rb_next(n); /* unlink_request(), check_pool_dne() */
 
 		dout("%s req %p tid %llu\n", __func__, req, req->r_tid);
-		ct_res = calc_target(osdc, &req->r_t, false);
+		ct_res = calc_target(osdc, &req->r_t, &req->r_osd->o_con,
+				     false);
 		switch (ct_res) {
 		case CALC_TARGET_NO_ACTION:
 			force_resend_writes = cleared_full ||
@@ -3359,7 +3366,7 @@ static void kick_requests(struct ceph_osd_client *osdc,
 		erase_request(need_resend, req); /* before link_request() */
 
 		WARN_ON(req->r_osd);
-		calc_target(osdc, &req->r_t, false);
+		calc_target(osdc, &req->r_t, NULL, false);
 		osd = lookup_create_osd(osdc, req->r_t.osd, true);
 		link_request(osd, req);
 		if (!req->r_linger) {
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index a4155620eace..367879afed58 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -1753,9 +1753,8 @@ void ceph_osds_copy(struct ceph_osds *dest, const struct ceph_osds *src)
 	dest->primary = src->primary;
 }
 
-static bool is_split(const struct ceph_pg *pgid,
-		     u32 old_pg_num,
-		     u32 new_pg_num)
+bool ceph_pg_is_split(const struct ceph_pg *pgid, u32 old_pg_num,
+		      u32 new_pg_num)
 {
 	int old_bits = calc_bits_of(old_pg_num);
 	int old_mask = (1 << old_bits) - 1;
@@ -1800,7 +1799,7 @@ bool ceph_is_new_interval(const struct ceph_osds *old_acting,
 	       !osds_equal(old_up, new_up) ||
 	       old_size != new_size ||
 	       old_min_size != new_min_size ||
-	       is_split(pgid, old_pg_num, new_pg_num) ||
+	       ceph_pg_is_split(pgid, old_pg_num, new_pg_num) ||
 	       old_sort_bitwise != new_sort_bitwise;
 }
 
-- 
cgit v1.2.3


From 04c7d789e269c2b82bbd08106049a5a979cdb3fd Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Thu, 15 Jun 2017 16:30:55 +0200
Subject: libceph: make sure need_resend targets reflect latest map

Otherwise we may miss events like PG splits, pool deletions, etc when
we get multiple incremental maps at once.  Because check_pool_dne() can
now be fed an unlinked request, finish_request() needed to be taught to
handle unlinked requests.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/osd_client.h |  1 +
 net/ceph/debugfs.c              |  2 +-
 net/ceph/osd_client.c           | 33 +++++++++++++++++++++++++--------
 3 files changed, 27 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index bca2718ac253..62c672bcbb31 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -149,6 +149,7 @@ struct ceph_osd_request_target {
 	unsigned int flags;                /* CEPH_OSD_FLAG_* */
 	bool paused;
 
+	u32 epoch;
 	u32 last_force_resend;
 
 	int osd;
diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c
index 50ab1bdb16e2..c0089f8ccaeb 100644
--- a/net/ceph/debugfs.c
+++ b/net/ceph/debugfs.c
@@ -166,7 +166,7 @@ static void dump_target(struct seq_file *s, struct ceph_osd_request_target *t)
 	seq_printf(s, "]/%d\t[", t->up.primary);
 	for (i = 0; i < t->acting.size; i++)
 		seq_printf(s, "%s%d", (!i ? "" : ","), t->acting.osds[i]);
-	seq_printf(s, "]/%d\t", t->acting.primary);
+	seq_printf(s, "]/%d\te%u\t", t->acting.primary, t->epoch);
 	if (t->target_oloc.pool_ns) {
 		seq_printf(s, "%*pE/%*pE\t0x%x",
 			(int)t->target_oloc.pool_ns->len,
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 576101b635ef..173ab9c68eb6 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -386,6 +386,7 @@ static void target_copy(struct ceph_osd_request_target *dest,
 	dest->flags = src->flags;
 	dest->paused = src->paused;
 
+	dest->epoch = src->epoch;
 	dest->last_force_resend = src->last_force_resend;
 
 	dest->osd = src->osd;
@@ -1334,6 +1335,7 @@ static enum calc_target_result calc_target(struct ceph_osd_client *osdc,
 	enum calc_target_result ct_res;
 	int ret;
 
+	t->epoch = osdc->osdmap->epoch;
 	pi = ceph_pg_pool_by_id(osdc->osdmap, t->base_oloc.pool);
 	if (!pi) {
 		t->osd = CEPH_HOMELESS_OSD;
@@ -1720,10 +1722,11 @@ static void send_request(struct ceph_osd_request *req)
 
 	encode_request_partial(req, req->r_request);
 
-	dout("%s req %p tid %llu to pgid %llu.%x spgid %llu.%xs%d osd%d flags 0x%x attempt %d\n",
+	dout("%s req %p tid %llu to pgid %llu.%x spgid %llu.%xs%d osd%d e%u flags 0x%x attempt %d\n",
 	     __func__, req, req->r_tid, req->r_t.pgid.pool, req->r_t.pgid.seed,
 	     req->r_t.spgid.pgid.pool, req->r_t.spgid.pgid.seed,
-	     req->r_t.spgid.shard, osd->o_osd, req->r_flags, req->r_attempts);
+	     req->r_t.spgid.shard, osd->o_osd, req->r_t.epoch, req->r_flags,
+	     req->r_attempts);
 
 	req->r_t.paused = false;
 	req->r_stamp = jiffies;
@@ -1863,13 +1866,12 @@ static void submit_request(struct ceph_osd_request *req, bool wrlocked)
 static void finish_request(struct ceph_osd_request *req)
 {
 	struct ceph_osd_client *osdc = req->r_osdc;
-	struct ceph_osd *osd = req->r_osd;
 
-	verify_osd_locked(osd);
+	WARN_ON(lookup_request_mc(&osdc->map_checks, req->r_tid));
 	dout("%s req %p tid %llu\n", __func__, req, req->r_tid);
 
-	WARN_ON(lookup_request_mc(&osdc->map_checks, req->r_tid));
-	unlink_request(osd, req);
+	if (req->r_osd)
+		unlink_request(req->r_osd, req);
 	atomic_dec(&osdc->num_requests);
 
 	/*
@@ -3356,8 +3358,25 @@ static void kick_requests(struct ceph_osd_client *osdc,
 			  struct list_head *need_resend_linger)
 {
 	struct ceph_osd_linger_request *lreq, *nlreq;
+	enum calc_target_result ct_res;
 	struct rb_node *n;
 
+	/* make sure need_resend targets reflect latest map */
+	for (n = rb_first(need_resend); n; ) {
+		struct ceph_osd_request *req =
+		    rb_entry(n, struct ceph_osd_request, r_node);
+
+		n = rb_next(n);
+
+		if (req->r_t.epoch < osdc->osdmap->epoch) {
+			ct_res = calc_target(osdc, &req->r_t, NULL, false);
+			if (ct_res == CALC_TARGET_POOL_DNE) {
+				erase_request(need_resend, req);
+				check_pool_dne(req);
+			}
+		}
+	}
+
 	for (n = rb_first(need_resend); n; ) {
 		struct ceph_osd_request *req =
 		    rb_entry(n, struct ceph_osd_request, r_node);
@@ -3366,8 +3385,6 @@ static void kick_requests(struct ceph_osd_client *osdc,
 		n = rb_next(n);
 		erase_request(need_resend, req); /* before link_request() */
 
-		WARN_ON(req->r_osd);
-		calc_target(osdc, &req->r_t, NULL, false);
 		osd = lookup_create_osd(osdc, req->r_t.osd, true);
 		link_request(osd, req);
 		if (!req->r_linger) {
-- 
cgit v1.2.3


From df28152d53b449a72258000f592472215fc9371e Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Thu, 15 Jun 2017 16:30:56 +0200
Subject: libceph: avoid unnecessary pi lookups in calc_target()

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/osdmap.h | 10 +++++++--
 net/ceph/osd_client.c       |  8 +++----
 net/ceph/osdmap.c           | 54 +++++++++++++++++++++++++--------------------
 3 files changed, 42 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index 63fb073a3355..060d059acbf8 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -273,16 +273,22 @@ extern int ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
 					 u64 off, u64 len,
 					 u64 *bno, u64 *oxoff, u64 *oxlen);
 
+int __ceph_object_locator_to_pg(struct ceph_pg_pool_info *pi,
+				const struct ceph_object_id *oid,
+				const struct ceph_object_locator *oloc,
+				struct ceph_pg *raw_pgid);
 int ceph_object_locator_to_pg(struct ceph_osdmap *osdmap,
-			      struct ceph_object_id *oid,
-			      struct ceph_object_locator *oloc,
+			      const struct ceph_object_id *oid,
+			      const struct ceph_object_locator *oloc,
 			      struct ceph_pg *raw_pgid);
 
 void ceph_pg_to_up_acting_osds(struct ceph_osdmap *osdmap,
+			       struct ceph_pg_pool_info *pi,
 			       const struct ceph_pg *raw_pgid,
 			       struct ceph_osds *up,
 			       struct ceph_osds *acting);
 bool ceph_pg_to_primary_shard(struct ceph_osdmap *osdmap,
+			      struct ceph_pg_pool_info *pi,
 			      const struct ceph_pg *raw_pgid,
 			      struct ceph_spg *spgid);
 int ceph_pg_to_acting_primary(struct ceph_osdmap *osdmap,
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index ce0055dc7544..620aa43a6a0a 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1368,8 +1368,8 @@ static enum calc_target_result calc_target(struct ceph_osd_client *osdc,
 		}
 	}
 
-	ret = ceph_object_locator_to_pg(osdc->osdmap, &t->target_oid,
-					&t->target_oloc, &pgid);
+	ret = __ceph_object_locator_to_pg(pi, &t->target_oid, &t->target_oloc,
+					  &pgid);
 	if (ret) {
 		WARN_ON(ret != -ENOENT);
 		t->osd = CEPH_HOMELESS_OSD;
@@ -1379,7 +1379,7 @@ static enum calc_target_result calc_target(struct ceph_osd_client *osdc,
 	last_pgid.pool = pgid.pool;
 	last_pgid.seed = ceph_stable_mod(pgid.seed, t->pg_num, t->pg_num_mask);
 
-	ceph_pg_to_up_acting_osds(osdc->osdmap, &pgid, &up, &acting);
+	ceph_pg_to_up_acting_osds(osdc->osdmap, pi, &pgid, &up, &acting);
 	if (any_change &&
 	    ceph_is_new_interval(&t->acting,
 				 &acting,
@@ -1407,7 +1407,7 @@ static enum calc_target_result calc_target(struct ceph_osd_client *osdc,
 
 	if (legacy_change || force_resend || split) {
 		t->pgid = pgid; /* struct */
-		ceph_pg_to_primary_shard(osdc->osdmap, &pgid, &t->spgid);
+		ceph_pg_to_primary_shard(osdc->osdmap, pi, &pgid, &t->spgid);
 		ceph_osds_copy(&t->acting, &acting);
 		ceph_osds_copy(&t->up, &up);
 		t->size = pi->size;
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 367879afed58..1e2e190a4c2a 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -1923,16 +1923,12 @@ EXPORT_SYMBOL(ceph_calc_file_object_mapping);
  * Should only be called with target_oid and target_oloc (as opposed to
  * base_oid and base_oloc), since tiering isn't taken into account.
  */
-int ceph_object_locator_to_pg(struct ceph_osdmap *osdmap,
-			      struct ceph_object_id *oid,
-			      struct ceph_object_locator *oloc,
-			      struct ceph_pg *raw_pgid)
+int __ceph_object_locator_to_pg(struct ceph_pg_pool_info *pi,
+				const struct ceph_object_id *oid,
+				const struct ceph_object_locator *oloc,
+				struct ceph_pg *raw_pgid)
 {
-	struct ceph_pg_pool_info *pi;
-
-	pi = ceph_pg_pool_by_id(osdmap, oloc->pool);
-	if (!pi)
-		return -ENOENT;
+	WARN_ON(pi->id != oloc->pool);
 
 	if (!oloc->pool_ns) {
 		raw_pgid->pool = oloc->pool;
@@ -1964,6 +1960,20 @@ int ceph_object_locator_to_pg(struct ceph_osdmap *osdmap,
 	}
 	return 0;
 }
+
+int ceph_object_locator_to_pg(struct ceph_osdmap *osdmap,
+			      const struct ceph_object_id *oid,
+			      const struct ceph_object_locator *oloc,
+			      struct ceph_pg *raw_pgid)
+{
+	struct ceph_pg_pool_info *pi;
+
+	pi = ceph_pg_pool_by_id(osdmap, oloc->pool);
+	if (!pi)
+		return -ENOENT;
+
+	return __ceph_object_locator_to_pg(pi, oid, oloc, raw_pgid);
+}
 EXPORT_SYMBOL(ceph_object_locator_to_pg);
 
 /*
@@ -2236,19 +2246,14 @@ static void get_temp_osds(struct ceph_osdmap *osdmap,
  * resend a request.
  */
 void ceph_pg_to_up_acting_osds(struct ceph_osdmap *osdmap,
+			       struct ceph_pg_pool_info *pi,
 			       const struct ceph_pg *raw_pgid,
 			       struct ceph_osds *up,
 			       struct ceph_osds *acting)
 {
-	struct ceph_pg_pool_info *pi;
 	u32 pps;
 
-	pi = ceph_pg_pool_by_id(osdmap, raw_pgid->pool);
-	if (!pi) {
-		ceph_osds_init(up);
-		ceph_osds_init(acting);
-		goto out;
-	}
+	WARN_ON(pi->id != raw_pgid->pool);
 
 	pg_to_raw_osds(osdmap, pi, raw_pgid, up, &pps);
 	raw_to_up_osds(osdmap, pi, up);
@@ -2260,23 +2265,19 @@ void ceph_pg_to_up_acting_osds(struct ceph_osdmap *osdmap,
 		if (acting->primary == -1)
 			acting->primary = up->primary;
 	}
-out:
 	WARN_ON(!osds_valid(up) || !osds_valid(acting));
 }
 
 bool ceph_pg_to_primary_shard(struct ceph_osdmap *osdmap,
+			      struct ceph_pg_pool_info *pi,
 			      const struct ceph_pg *raw_pgid,
 			      struct ceph_spg *spgid)
 {
-	struct ceph_pg_pool_info *pi;
 	struct ceph_pg pgid;
 	struct ceph_osds up, acting;
 	int i;
 
-	pi = ceph_pg_pool_by_id(osdmap, raw_pgid->pool);
-	if (!pi)
-		return false;
-
+	WARN_ON(pi->id != raw_pgid->pool);
 	raw_pg_to_pg(pi, raw_pgid, &pgid);
 
 	if (ceph_can_shift_osds(pi)) {
@@ -2285,7 +2286,7 @@ bool ceph_pg_to_primary_shard(struct ceph_osdmap *osdmap,
 		return true;
 	}
 
-	ceph_pg_to_up_acting_osds(osdmap, &pgid, &up, &acting);
+	ceph_pg_to_up_acting_osds(osdmap, pi, &pgid, &up, &acting);
 	for (i = 0; i < acting.size; i++) {
 		if (acting.osds[i] == acting.primary) {
 			spgid->pgid = pgid; /* struct */
@@ -2303,9 +2304,14 @@ bool ceph_pg_to_primary_shard(struct ceph_osdmap *osdmap,
 int ceph_pg_to_acting_primary(struct ceph_osdmap *osdmap,
 			      const struct ceph_pg *raw_pgid)
 {
+	struct ceph_pg_pool_info *pi;
 	struct ceph_osds up, acting;
 
-	ceph_pg_to_up_acting_osds(osdmap, raw_pgid, &up, &acting);
+	pi = ceph_pg_pool_by_id(osdmap, raw_pgid->pool);
+	if (!pi)
+		return -1;
+
+	ceph_pg_to_up_acting_osds(osdmap, pi, raw_pgid, &up, &acting);
 	return acting.primary;
 }
 EXPORT_SYMBOL(ceph_pg_to_acting_primary);
-- 
cgit v1.2.3


From 76f827a7b1faaaebc53f89d184e95ea3a0b8dd71 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Mon, 19 Jun 2017 12:18:05 +0200
Subject: libceph: make DEFINE_RB_* helpers more general

Initially for ceph_pg_mapping, ceph_spg_mapping and ceph_hobject_id,
compared with ceph_pg_compare(), ceph_spg_compare() and hoid_compare()
respectively.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/libceph.h | 49 +++++++++++++++++++++++++++++++++-----------
 1 file changed, 37 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index 3229ae6c7846..8a79587e1317 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -184,10 +184,11 @@ static inline int calc_pages_for(u64 off, u64 len)
 		(off >> PAGE_SHIFT);
 }
 
-/*
- * These are not meant to be generic - an integer key is assumed.
- */
-#define DEFINE_RB_INSDEL_FUNCS(name, type, keyfld, nodefld)		\
+#define RB_BYVAL(a)      (a)
+#define RB_BYPTR(a)      (&(a))
+#define RB_CMP3WAY(a, b) ((a) < (b) ? -1 : (a) > (b))
+
+#define DEFINE_RB_INSDEL_FUNCS2(name, type, keyfld, cmpexp, keyexp, nodefld) \
 static void insert_##name(struct rb_root *root, type *t)		\
 {									\
 	struct rb_node **n = &root->rb_node;				\
@@ -197,11 +198,13 @@ static void insert_##name(struct rb_root *root, type *t)		\
 									\
 	while (*n) {							\
 		type *cur = rb_entry(*n, type, nodefld);		\
+		int cmp;						\
 									\
 		parent = *n;						\
-		if (t->keyfld < cur->keyfld)				\
+		cmp = cmpexp(keyexp(t->keyfld), keyexp(cur->keyfld));	\
+		if (cmp < 0)						\
 			n = &(*n)->rb_left;				\
-		else if (t->keyfld > cur->keyfld)			\
+		else if (cmp > 0)					\
 			n = &(*n)->rb_right;				\
 		else							\
 			BUG();						\
@@ -217,19 +220,24 @@ static void erase_##name(struct rb_root *root, type *t)			\
 	RB_CLEAR_NODE(&t->nodefld);					\
 }
 
-#define DEFINE_RB_LOOKUP_FUNC(name, type, keyfld, nodefld)		\
-extern type __lookup_##name##_key;					\
-static type *lookup_##name(struct rb_root *root,			\
-			   typeof(__lookup_##name##_key.keyfld) key)	\
+/*
+ * @lookup_param_type is a parameter and not constructed from (@type,
+ * @keyfld) with typeof() because adding const is too unwieldy.
+ */
+#define DEFINE_RB_LOOKUP_FUNC2(name, type, keyfld, cmpexp, keyexp,	\
+			       lookup_param_type, nodefld)		\
+static type *lookup_##name(struct rb_root *root, lookup_param_type key)	\
 {									\
 	struct rb_node *n = root->rb_node;				\
 									\
 	while (n) {							\
 		type *cur = rb_entry(n, type, nodefld);			\
+		int cmp;						\
 									\
-		if (key < cur->keyfld)					\
+		cmp = cmpexp(key, keyexp(cur->keyfld));			\
+		if (cmp < 0)						\
 			n = n->rb_left;					\
-		else if (key > cur->keyfld)				\
+		else if (cmp > 0)					\
 			n = n->rb_right;				\
 		else							\
 			return cur;					\
@@ -238,6 +246,23 @@ static type *lookup_##name(struct rb_root *root,			\
 	return NULL;							\
 }
 
+#define DEFINE_RB_FUNCS2(name, type, keyfld, cmpexp, keyexp,		\
+			 lookup_param_type, nodefld)			\
+DEFINE_RB_INSDEL_FUNCS2(name, type, keyfld, cmpexp, keyexp, nodefld)	\
+DEFINE_RB_LOOKUP_FUNC2(name, type, keyfld, cmpexp, keyexp,		\
+		       lookup_param_type, nodefld)
+
+/*
+ * Shorthands for integer keys.
+ */
+#define DEFINE_RB_INSDEL_FUNCS(name, type, keyfld, nodefld)		\
+DEFINE_RB_INSDEL_FUNCS2(name, type, keyfld, RB_CMP3WAY, RB_BYVAL, nodefld)
+
+#define DEFINE_RB_LOOKUP_FUNC(name, type, keyfld, nodefld)		\
+extern type __lookup_##name##_key;					\
+DEFINE_RB_LOOKUP_FUNC2(name, type, keyfld, RB_CMP3WAY, RB_BYVAL,	\
+		       typeof(__lookup_##name##_key.keyfld), nodefld)
+
 #define DEFINE_RB_FUNCS(name, type, keyfld, nodefld)			\
 DEFINE_RB_INSDEL_FUNCS(name, type, keyfld, nodefld)			\
 DEFINE_RB_LOOKUP_FUNC(name, type, keyfld, nodefld)
-- 
cgit v1.2.3


From a02a946dfe9633d7e0202359836f6b5217a62824 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Mon, 19 Jun 2017 12:18:05 +0200
Subject: libceph: respect RADOS_BACKOFF backoffs

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/ceph_fs.h    |   1 +
 include/linux/ceph/osd_client.h |  45 +++
 include/linux/ceph/osdmap.h     |   1 +
 include/linux/ceph/rados.h      |   6 +
 net/ceph/ceph_common.c          |   1 +
 net/ceph/debugfs.c              |  74 +++++
 net/ceph/osd_client.c           | 593 ++++++++++++++++++++++++++++++++++++++++
 net/ceph/osdmap.c               |  16 ++
 8 files changed, 737 insertions(+)

(limited to 'include')

diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index ad078ebe25d6..edf5b04b918a 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -147,6 +147,7 @@ struct ceph_dir_layout {
 #define CEPH_MSG_OSD_OP                 42
 #define CEPH_MSG_OSD_OPREPLY            43
 #define CEPH_MSG_WATCH_NOTIFY           44
+#define CEPH_MSG_OSD_BACKOFF            61
 
 
 /* watch-notify operations */
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 62c672bcbb31..c6d96a5f46fd 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -1,6 +1,7 @@
 #ifndef _FS_CEPH_OSD_CLIENT_H
 #define _FS_CEPH_OSD_CLIENT_H
 
+#include <linux/bitrev.h>
 #include <linux/completion.h>
 #include <linux/kref.h>
 #include <linux/mempool.h>
@@ -36,6 +37,8 @@ struct ceph_osd {
 	struct ceph_connection o_con;
 	struct rb_root o_requests;
 	struct rb_root o_linger_requests;
+	struct rb_root o_backoff_mappings;
+	struct rb_root o_backoffs_by_id;
 	struct list_head o_osd_lru;
 	struct ceph_auth_handshake o_auth;
 	unsigned long lru_ttl;
@@ -275,6 +278,48 @@ struct ceph_watch_item {
 	struct ceph_entity_addr addr;
 };
 
+struct ceph_spg_mapping {
+	struct rb_node node;
+	struct ceph_spg spgid;
+
+	struct rb_root backoffs;
+};
+
+struct ceph_hobject_id {
+	void *key;
+	size_t key_len;
+	void *oid;
+	size_t oid_len;
+	u64 snapid;
+	u32 hash;
+	u8 is_max;
+	void *nspace;
+	size_t nspace_len;
+	s64 pool;
+
+	/* cache */
+	u32 hash_reverse_bits;
+};
+
+static inline void ceph_hoid_build_hash_cache(struct ceph_hobject_id *hoid)
+{
+	hoid->hash_reverse_bits = bitrev32(hoid->hash);
+}
+
+/*
+ * PG-wide backoff: [begin, end)
+ * per-object backoff: begin == end
+ */
+struct ceph_osd_backoff {
+	struct rb_node spg_node;
+	struct rb_node id_node;
+
+	struct ceph_spg spgid;
+	u64 id;
+	struct ceph_hobject_id *begin;
+	struct ceph_hobject_id *end;
+};
+
 #define CEPH_LINGER_ID_START	0xffff000000000000ULL
 
 struct ceph_osd_client {
diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index 060d059acbf8..fe6d189bdd30 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -32,6 +32,7 @@ struct ceph_spg {
 };
 
 int ceph_pg_compare(const struct ceph_pg *lhs, const struct ceph_pg *rhs);
+int ceph_spg_compare(const struct ceph_spg *lhs, const struct ceph_spg *rhs);
 
 #define CEPH_POOL_FLAG_HASHPSPOOL	(1ULL << 0) /* hash pg seed and pool id
 						       together */
diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h
index 5d0018782d50..385db08bb8b2 100644
--- a/include/linux/ceph/rados.h
+++ b/include/linux/ceph/rados.h
@@ -439,6 +439,12 @@ enum {
 
 const char *ceph_osd_watch_op_name(int o);
 
+enum {
+	CEPH_OSD_BACKOFF_OP_BLOCK = 1,
+	CEPH_OSD_BACKOFF_OP_ACK_BLOCK = 2,
+	CEPH_OSD_BACKOFF_OP_UNBLOCK = 3,
+};
+
 /*
  * an individual object operation.  each may be accompanied by some data
  * payload
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index 47e94b560ba0..3d265c5cb6d0 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -85,6 +85,7 @@ const char *ceph_msg_type_name(int type)
 	case CEPH_MSG_OSD_OP: return "osd_op";
 	case CEPH_MSG_OSD_OPREPLY: return "osd_opreply";
 	case CEPH_MSG_WATCH_NOTIFY: return "watch_notify";
+	case CEPH_MSG_OSD_BACKOFF: return "osd_backoff";
 	default: return "unknown";
 	}
 }
diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c
index c0089f8ccaeb..017f15c575f8 100644
--- a/net/ceph/debugfs.c
+++ b/net/ceph/debugfs.c
@@ -243,6 +243,73 @@ static void dump_linger_requests(struct seq_file *s, struct ceph_osd *osd)
 	mutex_unlock(&osd->lock);
 }
 
+static void dump_snapid(struct seq_file *s, u64 snapid)
+{
+	if (snapid == CEPH_NOSNAP)
+		seq_puts(s, "head");
+	else if (snapid == CEPH_SNAPDIR)
+		seq_puts(s, "snapdir");
+	else
+		seq_printf(s, "%llx", snapid);
+}
+
+static void dump_name_escaped(struct seq_file *s, unsigned char *name,
+			      size_t len)
+{
+	size_t i;
+
+	for (i = 0; i < len; i++) {
+		if (name[i] == '%' || name[i] == ':' || name[i] == '/' ||
+		    name[i] < 32 || name[i] >= 127) {
+			seq_printf(s, "%%%02x", name[i]);
+		} else {
+			seq_putc(s, name[i]);
+		}
+	}
+}
+
+static void dump_hoid(struct seq_file *s, const struct ceph_hobject_id *hoid)
+{
+	if (hoid->snapid == 0 && hoid->hash == 0 && !hoid->is_max &&
+	    hoid->pool == S64_MIN) {
+		seq_puts(s, "MIN");
+		return;
+	}
+	if (hoid->is_max) {
+		seq_puts(s, "MAX");
+		return;
+	}
+	seq_printf(s, "%lld:%08x:", hoid->pool, hoid->hash_reverse_bits);
+	dump_name_escaped(s, hoid->nspace, hoid->nspace_len);
+	seq_putc(s, ':');
+	dump_name_escaped(s, hoid->key, hoid->key_len);
+	seq_putc(s, ':');
+	dump_name_escaped(s, hoid->oid, hoid->oid_len);
+	seq_putc(s, ':');
+	dump_snapid(s, hoid->snapid);
+}
+
+static void dump_backoffs(struct seq_file *s, struct ceph_osd *osd)
+{
+	struct rb_node *n;
+
+	mutex_lock(&osd->lock);
+	for (n = rb_first(&osd->o_backoffs_by_id); n; n = rb_next(n)) {
+		struct ceph_osd_backoff *backoff =
+		    rb_entry(n, struct ceph_osd_backoff, id_node);
+
+		seq_printf(s, "osd%d\t", osd->o_osd);
+		dump_spgid(s, &backoff->spgid);
+		seq_printf(s, "\t%llu\t", backoff->id);
+		dump_hoid(s, backoff->begin);
+		seq_putc(s, '\t');
+		dump_hoid(s, backoff->end);
+		seq_putc(s, '\n');
+	}
+
+	mutex_unlock(&osd->lock);
+}
+
 static int osdc_show(struct seq_file *s, void *pp)
 {
 	struct ceph_client *client = s->private;
@@ -268,6 +335,13 @@ static int osdc_show(struct seq_file *s, void *pp)
 	}
 	dump_linger_requests(s, &osdc->homeless_osd);
 
+	seq_puts(s, "BACKOFFS\n");
+	for (n = rb_first(&osdc->osds); n; n = rb_next(n)) {
+		struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node);
+
+		dump_backoffs(s, osd);
+	}
+
 	up_read(&osdc->lock);
 	return 0;
 }
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 620aa43a6a0a..86a9737d8e3f 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -50,6 +50,7 @@ static void link_linger(struct ceph_osd *osd,
 			struct ceph_osd_linger_request *lreq);
 static void unlink_linger(struct ceph_osd *osd,
 			  struct ceph_osd_linger_request *lreq);
+static void clear_backoffs(struct ceph_osd *osd);
 
 #if 1
 static inline bool rwsem_is_wrlocked(struct rw_semaphore *sem)
@@ -1019,6 +1020,8 @@ static void osd_init(struct ceph_osd *osd)
 	RB_CLEAR_NODE(&osd->o_node);
 	osd->o_requests = RB_ROOT;
 	osd->o_linger_requests = RB_ROOT;
+	osd->o_backoff_mappings = RB_ROOT;
+	osd->o_backoffs_by_id = RB_ROOT;
 	INIT_LIST_HEAD(&osd->o_osd_lru);
 	INIT_LIST_HEAD(&osd->o_keepalive_item);
 	osd->o_incarnation = 1;
@@ -1030,6 +1033,8 @@ static void osd_cleanup(struct ceph_osd *osd)
 	WARN_ON(!RB_EMPTY_NODE(&osd->o_node));
 	WARN_ON(!RB_EMPTY_ROOT(&osd->o_requests));
 	WARN_ON(!RB_EMPTY_ROOT(&osd->o_linger_requests));
+	WARN_ON(!RB_EMPTY_ROOT(&osd->o_backoff_mappings));
+	WARN_ON(!RB_EMPTY_ROOT(&osd->o_backoffs_by_id));
 	WARN_ON(!list_empty(&osd->o_osd_lru));
 	WARN_ON(!list_empty(&osd->o_keepalive_item));
 
@@ -1150,6 +1155,7 @@ static void close_osd(struct ceph_osd *osd)
 		unlink_linger(osd, lreq);
 		link_linger(&osdc->homeless_osd, lreq);
 	}
+	clear_backoffs(osd);
 
 	__remove_osd_from_lru(osd);
 	erase_osd(&osdc->osds, osd);
@@ -1431,6 +1437,328 @@ out:
 	return ct_res;
 }
 
+static struct ceph_spg_mapping *alloc_spg_mapping(void)
+{
+	struct ceph_spg_mapping *spg;
+
+	spg = kmalloc(sizeof(*spg), GFP_NOIO);
+	if (!spg)
+		return NULL;
+
+	RB_CLEAR_NODE(&spg->node);
+	spg->backoffs = RB_ROOT;
+	return spg;
+}
+
+static void free_spg_mapping(struct ceph_spg_mapping *spg)
+{
+	WARN_ON(!RB_EMPTY_NODE(&spg->node));
+	WARN_ON(!RB_EMPTY_ROOT(&spg->backoffs));
+
+	kfree(spg);
+}
+
+/*
+ * rbtree of ceph_spg_mapping for handling map<spg_t, ...>, similar to
+ * ceph_pg_mapping.  Used to track OSD backoffs -- a backoff [range] is
+ * defined only within a specific spgid; it does not pass anything to
+ * children on split, or to another primary.
+ */
+DEFINE_RB_FUNCS2(spg_mapping, struct ceph_spg_mapping, spgid, ceph_spg_compare,
+		 RB_BYPTR, const struct ceph_spg *, node)
+
+static u64 hoid_get_bitwise_key(const struct ceph_hobject_id *hoid)
+{
+	return hoid->is_max ? 0x100000000ull : hoid->hash_reverse_bits;
+}
+
+static void hoid_get_effective_key(const struct ceph_hobject_id *hoid,
+				   void **pkey, size_t *pkey_len)
+{
+	if (hoid->key_len) {
+		*pkey = hoid->key;
+		*pkey_len = hoid->key_len;
+	} else {
+		*pkey = hoid->oid;
+		*pkey_len = hoid->oid_len;
+	}
+}
+
+static int compare_names(const void *name1, size_t name1_len,
+			 const void *name2, size_t name2_len)
+{
+	int ret;
+
+	ret = memcmp(name1, name2, min(name1_len, name2_len));
+	if (!ret) {
+		if (name1_len < name2_len)
+			ret = -1;
+		else if (name1_len > name2_len)
+			ret = 1;
+	}
+	return ret;
+}
+
+static int hoid_compare(const struct ceph_hobject_id *lhs,
+			const struct ceph_hobject_id *rhs)
+{
+	void *effective_key1, *effective_key2;
+	size_t effective_key1_len, effective_key2_len;
+	int ret;
+
+	if (lhs->is_max < rhs->is_max)
+		return -1;
+	if (lhs->is_max > rhs->is_max)
+		return 1;
+
+	if (lhs->pool < rhs->pool)
+		return -1;
+	if (lhs->pool > rhs->pool)
+		return 1;
+
+	if (hoid_get_bitwise_key(lhs) < hoid_get_bitwise_key(rhs))
+		return -1;
+	if (hoid_get_bitwise_key(lhs) > hoid_get_bitwise_key(rhs))
+		return 1;
+
+	ret = compare_names(lhs->nspace, lhs->nspace_len,
+			    rhs->nspace, rhs->nspace_len);
+	if (ret)
+		return ret;
+
+	hoid_get_effective_key(lhs, &effective_key1, &effective_key1_len);
+	hoid_get_effective_key(rhs, &effective_key2, &effective_key2_len);
+	ret = compare_names(effective_key1, effective_key1_len,
+			    effective_key2, effective_key2_len);
+	if (ret)
+		return ret;
+
+	ret = compare_names(lhs->oid, lhs->oid_len, rhs->oid, rhs->oid_len);
+	if (ret)
+		return ret;
+
+	if (lhs->snapid < rhs->snapid)
+		return -1;
+	if (lhs->snapid > rhs->snapid)
+		return 1;
+
+	return 0;
+}
+
+/*
+ * For decoding ->begin and ->end of MOSDBackoff only -- no MIN/MAX
+ * compat stuff here.
+ *
+ * Assumes @hoid is zero-initialized.
+ */
+static int decode_hoid(void **p, void *end, struct ceph_hobject_id *hoid)
+{
+	u8 struct_v;
+	u32 struct_len;
+	int ret;
+
+	ret = ceph_start_decoding(p, end, 4, "hobject_t", &struct_v,
+				  &struct_len);
+	if (ret)
+		return ret;
+
+	if (struct_v < 4) {
+		pr_err("got struct_v %d < 4 of hobject_t\n", struct_v);
+		goto e_inval;
+	}
+
+	hoid->key = ceph_extract_encoded_string(p, end, &hoid->key_len,
+						GFP_NOIO);
+	if (IS_ERR(hoid->key)) {
+		ret = PTR_ERR(hoid->key);
+		hoid->key = NULL;
+		return ret;
+	}
+
+	hoid->oid = ceph_extract_encoded_string(p, end, &hoid->oid_len,
+						GFP_NOIO);
+	if (IS_ERR(hoid->oid)) {
+		ret = PTR_ERR(hoid->oid);
+		hoid->oid = NULL;
+		return ret;
+	}
+
+	ceph_decode_64_safe(p, end, hoid->snapid, e_inval);
+	ceph_decode_32_safe(p, end, hoid->hash, e_inval);
+	ceph_decode_8_safe(p, end, hoid->is_max, e_inval);
+
+	hoid->nspace = ceph_extract_encoded_string(p, end, &hoid->nspace_len,
+						   GFP_NOIO);
+	if (IS_ERR(hoid->nspace)) {
+		ret = PTR_ERR(hoid->nspace);
+		hoid->nspace = NULL;
+		return ret;
+	}
+
+	ceph_decode_64_safe(p, end, hoid->pool, e_inval);
+
+	ceph_hoid_build_hash_cache(hoid);
+	return 0;
+
+e_inval:
+	return -EINVAL;
+}
+
+static int hoid_encoding_size(const struct ceph_hobject_id *hoid)
+{
+	return 8 + 4 + 1 + 8 + /* snapid, hash, is_max, pool */
+	       4 + hoid->key_len + 4 + hoid->oid_len + 4 + hoid->nspace_len;
+}
+
+static void encode_hoid(void **p, void *end, const struct ceph_hobject_id *hoid)
+{
+	ceph_start_encoding(p, 4, 3, hoid_encoding_size(hoid));
+	ceph_encode_string(p, end, hoid->key, hoid->key_len);
+	ceph_encode_string(p, end, hoid->oid, hoid->oid_len);
+	ceph_encode_64(p, hoid->snapid);
+	ceph_encode_32(p, hoid->hash);
+	ceph_encode_8(p, hoid->is_max);
+	ceph_encode_string(p, end, hoid->nspace, hoid->nspace_len);
+	ceph_encode_64(p, hoid->pool);
+}
+
+static void free_hoid(struct ceph_hobject_id *hoid)
+{
+	if (hoid) {
+		kfree(hoid->key);
+		kfree(hoid->oid);
+		kfree(hoid->nspace);
+		kfree(hoid);
+	}
+}
+
+static struct ceph_osd_backoff *alloc_backoff(void)
+{
+	struct ceph_osd_backoff *backoff;
+
+	backoff = kzalloc(sizeof(*backoff), GFP_NOIO);
+	if (!backoff)
+		return NULL;
+
+	RB_CLEAR_NODE(&backoff->spg_node);
+	RB_CLEAR_NODE(&backoff->id_node);
+	return backoff;
+}
+
+static void free_backoff(struct ceph_osd_backoff *backoff)
+{
+	WARN_ON(!RB_EMPTY_NODE(&backoff->spg_node));
+	WARN_ON(!RB_EMPTY_NODE(&backoff->id_node));
+
+	free_hoid(backoff->begin);
+	free_hoid(backoff->end);
+	kfree(backoff);
+}
+
+/*
+ * Within a specific spgid, backoffs are managed by ->begin hoid.
+ */
+DEFINE_RB_INSDEL_FUNCS2(backoff, struct ceph_osd_backoff, begin, hoid_compare,
+			RB_BYVAL, spg_node);
+
+static struct ceph_osd_backoff *lookup_containing_backoff(struct rb_root *root,
+					    const struct ceph_hobject_id *hoid)
+{
+	struct rb_node *n = root->rb_node;
+
+	while (n) {
+		struct ceph_osd_backoff *cur =
+		    rb_entry(n, struct ceph_osd_backoff, spg_node);
+		int cmp;
+
+		cmp = hoid_compare(hoid, cur->begin);
+		if (cmp < 0) {
+			n = n->rb_left;
+		} else if (cmp > 0) {
+			if (hoid_compare(hoid, cur->end) < 0)
+				return cur;
+
+			n = n->rb_right;
+		} else {
+			return cur;
+		}
+	}
+
+	return NULL;
+}
+
+/*
+ * Each backoff has a unique id within its OSD session.
+ */
+DEFINE_RB_FUNCS(backoff_by_id, struct ceph_osd_backoff, id, id_node)
+
+static void clear_backoffs(struct ceph_osd *osd)
+{
+	while (!RB_EMPTY_ROOT(&osd->o_backoff_mappings)) {
+		struct ceph_spg_mapping *spg =
+		    rb_entry(rb_first(&osd->o_backoff_mappings),
+			     struct ceph_spg_mapping, node);
+
+		while (!RB_EMPTY_ROOT(&spg->backoffs)) {
+			struct ceph_osd_backoff *backoff =
+			    rb_entry(rb_first(&spg->backoffs),
+				     struct ceph_osd_backoff, spg_node);
+
+			erase_backoff(&spg->backoffs, backoff);
+			erase_backoff_by_id(&osd->o_backoffs_by_id, backoff);
+			free_backoff(backoff);
+		}
+		erase_spg_mapping(&osd->o_backoff_mappings, spg);
+		free_spg_mapping(spg);
+	}
+}
+
+/*
+ * Set up a temporary, non-owning view into @t.
+ */
+static void hoid_fill_from_target(struct ceph_hobject_id *hoid,
+				  const struct ceph_osd_request_target *t)
+{
+	hoid->key = NULL;
+	hoid->key_len = 0;
+	hoid->oid = t->target_oid.name;
+	hoid->oid_len = t->target_oid.name_len;
+	hoid->snapid = CEPH_NOSNAP;
+	hoid->hash = t->pgid.seed;
+	hoid->is_max = false;
+	if (t->target_oloc.pool_ns) {
+		hoid->nspace = t->target_oloc.pool_ns->str;
+		hoid->nspace_len = t->target_oloc.pool_ns->len;
+	} else {
+		hoid->nspace = NULL;
+		hoid->nspace_len = 0;
+	}
+	hoid->pool = t->target_oloc.pool;
+	ceph_hoid_build_hash_cache(hoid);
+}
+
+static bool should_plug_request(struct ceph_osd_request *req)
+{
+	struct ceph_osd *osd = req->r_osd;
+	struct ceph_spg_mapping *spg;
+	struct ceph_osd_backoff *backoff;
+	struct ceph_hobject_id hoid;
+
+	spg = lookup_spg_mapping(&osd->o_backoff_mappings, &req->r_t.spgid);
+	if (!spg)
+		return false;
+
+	hoid_fill_from_target(&hoid, &req->r_t);
+	backoff = lookup_containing_backoff(&spg->backoffs, &hoid);
+	if (!backoff)
+		return false;
+
+	dout("%s req %p tid %llu backoff osd%d spgid %llu.%xs%d id %llu\n",
+	     __func__, req, req->r_tid, osd->o_osd, backoff->spgid.pgid.pool,
+	     backoff->spgid.pgid.seed, backoff->spgid.shard, backoff->id);
+	return true;
+}
+
 static void setup_request_data(struct ceph_osd_request *req,
 			       struct ceph_msg *msg)
 {
@@ -1707,6 +2035,10 @@ static void send_request(struct ceph_osd_request *req)
 	verify_osd_locked(osd);
 	WARN_ON(osd->o_osd != req->r_t.osd);
 
+	/* backoff? */
+	if (should_plug_request(req))
+		return;
+
 	/*
 	 * We may have a previously queued request message hanging
 	 * around.  Cancel it to avoid corrupting the msgr.
@@ -3527,6 +3859,8 @@ static void kick_osd_requests(struct ceph_osd *osd)
 {
 	struct rb_node *n;
 
+	clear_backoffs(osd);
+
 	for (n = rb_first(&osd->o_requests); n; ) {
 		struct ceph_osd_request *req =
 		    rb_entry(n, struct ceph_osd_request, r_node);
@@ -3572,6 +3906,261 @@ out_unlock:
 	up_write(&osdc->lock);
 }
 
+struct MOSDBackoff {
+	struct ceph_spg spgid;
+	u32 map_epoch;
+	u8 op;
+	u64 id;
+	struct ceph_hobject_id *begin;
+	struct ceph_hobject_id *end;
+};
+
+static int decode_MOSDBackoff(const struct ceph_msg *msg, struct MOSDBackoff *m)
+{
+	void *p = msg->front.iov_base;
+	void *const end = p + msg->front.iov_len;
+	u8 struct_v;
+	u32 struct_len;
+	int ret;
+
+	ret = ceph_start_decoding(&p, end, 1, "spg_t", &struct_v, &struct_len);
+	if (ret)
+		return ret;
+
+	ret = ceph_decode_pgid(&p, end, &m->spgid.pgid);
+	if (ret)
+		return ret;
+
+	ceph_decode_8_safe(&p, end, m->spgid.shard, e_inval);
+	ceph_decode_32_safe(&p, end, m->map_epoch, e_inval);
+	ceph_decode_8_safe(&p, end, m->op, e_inval);
+	ceph_decode_64_safe(&p, end, m->id, e_inval);
+
+	m->begin = kzalloc(sizeof(*m->begin), GFP_NOIO);
+	if (!m->begin)
+		return -ENOMEM;
+
+	ret = decode_hoid(&p, end, m->begin);
+	if (ret) {
+		free_hoid(m->begin);
+		return ret;
+	}
+
+	m->end = kzalloc(sizeof(*m->end), GFP_NOIO);
+	if (!m->end) {
+		free_hoid(m->begin);
+		return -ENOMEM;
+	}
+
+	ret = decode_hoid(&p, end, m->end);
+	if (ret) {
+		free_hoid(m->begin);
+		free_hoid(m->end);
+		return ret;
+	}
+
+	return 0;
+
+e_inval:
+	return -EINVAL;
+}
+
+static struct ceph_msg *create_backoff_message(
+				const struct ceph_osd_backoff *backoff,
+				u32 map_epoch)
+{
+	struct ceph_msg *msg;
+	void *p, *end;
+	int msg_size;
+
+	msg_size = CEPH_ENCODING_START_BLK_LEN +
+			CEPH_PGID_ENCODING_LEN + 1; /* spgid */
+	msg_size += 4 + 1 + 8; /* map_epoch, op, id */
+	msg_size += CEPH_ENCODING_START_BLK_LEN +
+			hoid_encoding_size(backoff->begin);
+	msg_size += CEPH_ENCODING_START_BLK_LEN +
+			hoid_encoding_size(backoff->end);
+
+	msg = ceph_msg_new(CEPH_MSG_OSD_BACKOFF, msg_size, GFP_NOIO, true);
+	if (!msg)
+		return NULL;
+
+	p = msg->front.iov_base;
+	end = p + msg->front_alloc_len;
+
+	encode_spgid(&p, &backoff->spgid);
+	ceph_encode_32(&p, map_epoch);
+	ceph_encode_8(&p, CEPH_OSD_BACKOFF_OP_ACK_BLOCK);
+	ceph_encode_64(&p, backoff->id);
+	encode_hoid(&p, end, backoff->begin);
+	encode_hoid(&p, end, backoff->end);
+	BUG_ON(p != end);
+
+	msg->front.iov_len = p - msg->front.iov_base;
+	msg->hdr.version = cpu_to_le16(1); /* MOSDBackoff v1 */
+	msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
+
+	return msg;
+}
+
+static void handle_backoff_block(struct ceph_osd *osd, struct MOSDBackoff *m)
+{
+	struct ceph_spg_mapping *spg;
+	struct ceph_osd_backoff *backoff;
+	struct ceph_msg *msg;
+
+	dout("%s osd%d spgid %llu.%xs%d id %llu\n", __func__, osd->o_osd,
+	     m->spgid.pgid.pool, m->spgid.pgid.seed, m->spgid.shard, m->id);
+
+	spg = lookup_spg_mapping(&osd->o_backoff_mappings, &m->spgid);
+	if (!spg) {
+		spg = alloc_spg_mapping();
+		if (!spg) {
+			pr_err("%s failed to allocate spg\n", __func__);
+			return;
+		}
+		spg->spgid = m->spgid; /* struct */
+		insert_spg_mapping(&osd->o_backoff_mappings, spg);
+	}
+
+	backoff = alloc_backoff();
+	if (!backoff) {
+		pr_err("%s failed to allocate backoff\n", __func__);
+		return;
+	}
+	backoff->spgid = m->spgid; /* struct */
+	backoff->id = m->id;
+	backoff->begin = m->begin;
+	m->begin = NULL; /* backoff now owns this */
+	backoff->end = m->end;
+	m->end = NULL;   /* ditto */
+
+	insert_backoff(&spg->backoffs, backoff);
+	insert_backoff_by_id(&osd->o_backoffs_by_id, backoff);
+
+	/*
+	 * Ack with original backoff's epoch so that the OSD can
+	 * discard this if there was a PG split.
+	 */
+	msg = create_backoff_message(backoff, m->map_epoch);
+	if (!msg) {
+		pr_err("%s failed to allocate msg\n", __func__);
+		return;
+	}
+	ceph_con_send(&osd->o_con, msg);
+}
+
+static bool target_contained_by(const struct ceph_osd_request_target *t,
+				const struct ceph_hobject_id *begin,
+				const struct ceph_hobject_id *end)
+{
+	struct ceph_hobject_id hoid;
+	int cmp;
+
+	hoid_fill_from_target(&hoid, t);
+	cmp = hoid_compare(&hoid, begin);
+	return !cmp || (cmp > 0 && hoid_compare(&hoid, end) < 0);
+}
+
+static void handle_backoff_unblock(struct ceph_osd *osd,
+				   const struct MOSDBackoff *m)
+{
+	struct ceph_spg_mapping *spg;
+	struct ceph_osd_backoff *backoff;
+	struct rb_node *n;
+
+	dout("%s osd%d spgid %llu.%xs%d id %llu\n", __func__, osd->o_osd,
+	     m->spgid.pgid.pool, m->spgid.pgid.seed, m->spgid.shard, m->id);
+
+	backoff = lookup_backoff_by_id(&osd->o_backoffs_by_id, m->id);
+	if (!backoff) {
+		pr_err("%s osd%d spgid %llu.%xs%d id %llu backoff dne\n",
+		       __func__, osd->o_osd, m->spgid.pgid.pool,
+		       m->spgid.pgid.seed, m->spgid.shard, m->id);
+		return;
+	}
+
+	if (hoid_compare(backoff->begin, m->begin) &&
+	    hoid_compare(backoff->end, m->end)) {
+		pr_err("%s osd%d spgid %llu.%xs%d id %llu bad range?\n",
+		       __func__, osd->o_osd, m->spgid.pgid.pool,
+		       m->spgid.pgid.seed, m->spgid.shard, m->id);
+		/* unblock it anyway... */
+	}
+
+	spg = lookup_spg_mapping(&osd->o_backoff_mappings, &backoff->spgid);
+	BUG_ON(!spg);
+
+	erase_backoff(&spg->backoffs, backoff);
+	erase_backoff_by_id(&osd->o_backoffs_by_id, backoff);
+	free_backoff(backoff);
+
+	if (RB_EMPTY_ROOT(&spg->backoffs)) {
+		erase_spg_mapping(&osd->o_backoff_mappings, spg);
+		free_spg_mapping(spg);
+	}
+
+	for (n = rb_first(&osd->o_requests); n; n = rb_next(n)) {
+		struct ceph_osd_request *req =
+		    rb_entry(n, struct ceph_osd_request, r_node);
+
+		if (!ceph_spg_compare(&req->r_t.spgid, &m->spgid)) {
+			/*
+			 * Match against @m, not @backoff -- the PG may
+			 * have split on the OSD.
+			 */
+			if (target_contained_by(&req->r_t, m->begin, m->end)) {
+				/*
+				 * If no other installed backoff applies,
+				 * resend.
+				 */
+				send_request(req);
+			}
+		}
+	}
+}
+
+static void handle_backoff(struct ceph_osd *osd, struct ceph_msg *msg)
+{
+	struct ceph_osd_client *osdc = osd->o_osdc;
+	struct MOSDBackoff m;
+	int ret;
+
+	down_read(&osdc->lock);
+	if (!osd_registered(osd)) {
+		dout("%s osd%d unknown\n", __func__, osd->o_osd);
+		up_read(&osdc->lock);
+		return;
+	}
+	WARN_ON(osd->o_osd != le64_to_cpu(msg->hdr.src.num));
+
+	mutex_lock(&osd->lock);
+	ret = decode_MOSDBackoff(msg, &m);
+	if (ret) {
+		pr_err("failed to decode MOSDBackoff: %d\n", ret);
+		ceph_msg_dump(msg);
+		goto out_unlock;
+	}
+
+	switch (m.op) {
+	case CEPH_OSD_BACKOFF_OP_BLOCK:
+		handle_backoff_block(osd, &m);
+		break;
+	case CEPH_OSD_BACKOFF_OP_UNBLOCK:
+		handle_backoff_unblock(osd, &m);
+		break;
+	default:
+		pr_err("%s osd%d unknown op %d\n", __func__, osd->o_osd, m.op);
+	}
+
+	free_hoid(m.begin);
+	free_hoid(m.end);
+
+out_unlock:
+	mutex_unlock(&osd->lock);
+	up_read(&osdc->lock);
+}
+
 /*
  * Process osd watch notifications
  */
@@ -4509,6 +5098,9 @@ static void dispatch(struct ceph_connection *con, struct ceph_msg *msg)
 	case CEPH_MSG_OSD_OPREPLY:
 		handle_reply(osd, msg);
 		break;
+	case CEPH_MSG_OSD_BACKOFF:
+		handle_backoff(osd, msg);
+		break;
 	case CEPH_MSG_WATCH_NOTIFY:
 		handle_watch_notify(osdc, msg);
 		break;
@@ -4631,6 +5223,7 @@ static struct ceph_msg *alloc_msg(struct ceph_connection *con,
 	*skip = 0;
 	switch (type) {
 	case CEPH_MSG_OSD_MAP:
+	case CEPH_MSG_OSD_BACKOFF:
 	case CEPH_MSG_WATCH_NOTIFY:
 		return alloc_msg_with_page_vector(hdr);
 	case CEPH_MSG_OSD_OPREPLY:
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 1e2e190a4c2a..1d87a736221b 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -418,6 +418,22 @@ int ceph_pg_compare(const struct ceph_pg *lhs, const struct ceph_pg *rhs)
 	return 0;
 }
 
+int ceph_spg_compare(const struct ceph_spg *lhs, const struct ceph_spg *rhs)
+{
+	int ret;
+
+	ret = ceph_pg_compare(&lhs->pgid, &rhs->pgid);
+	if (ret)
+		return ret;
+
+	if (lhs->shard < rhs->shard)
+		return -1;
+	if (lhs->shard > rhs->shard)
+		return 1;
+
+	return 0;
+}
+
 /*
  * rbtree of pg_mapping for handling pg_temp (explicit mapping of pgid
  * to a set of osds) and primary_temp (explicit primary setting)
-- 
cgit v1.2.3


From 278b1d709c6acc6f7d138fed775c76695b068e43 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Wed, 21 Jun 2017 17:27:17 +0200
Subject: libceph: ceph_decode_skip_* helpers

Some of these won't be as efficient as they could be (e.g.
ceph_decode_skip_set(... 32 ...) could advance by len * sizeof(u32)
once instead of advancing by sizeof(u32) len times), but that's fine
and not worth a bunch of extra macro code.

Replace skip_name_map() with ceph_decode_skip_map as an example.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/decode.h | 60 +++++++++++++++++++++++++++++++++++++++++++++
 net/ceph/osdmap.c           | 25 +++----------------
 2 files changed, 63 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h
index f990f2cc907a..14af9b70d301 100644
--- a/include/linux/ceph/decode.h
+++ b/include/linux/ceph/decode.h
@@ -132,6 +132,66 @@ bad:
 	return ERR_PTR(-ERANGE);
 }
 
+/*
+ * skip helpers
+ */
+#define ceph_decode_skip_n(p, end, n, bad)			\
+	do {							\
+		ceph_decode_need(p, end, n, bad);		\
+                *p += n;					\
+	} while (0)
+
+#define ceph_decode_skip_64(p, end, bad)			\
+ceph_decode_skip_n(p, end, sizeof(u64), bad)
+
+#define ceph_decode_skip_32(p, end, bad)			\
+ceph_decode_skip_n(p, end, sizeof(u32), bad)
+
+#define ceph_decode_skip_16(p, end, bad)			\
+ceph_decode_skip_n(p, end, sizeof(u16), bad)
+
+#define ceph_decode_skip_8(p, end, bad)				\
+ceph_decode_skip_n(p, end, sizeof(u8), bad)
+
+#define ceph_decode_skip_string(p, end, bad)			\
+	do {							\
+		u32 len;					\
+								\
+		ceph_decode_32_safe(p, end, len, bad);		\
+		ceph_decode_skip_n(p, end, len, bad);		\
+	} while (0)
+
+#define ceph_decode_skip_set(p, end, type, bad)			\
+	do {							\
+		u32 len;					\
+								\
+		ceph_decode_32_safe(p, end, len, bad);		\
+		while (len--)					\
+			ceph_decode_skip_##type(p, end, bad);	\
+	} while (0)
+
+#define ceph_decode_skip_map(p, end, ktype, vtype, bad)		\
+	do {							\
+		u32 len;					\
+								\
+		ceph_decode_32_safe(p, end, len, bad);		\
+		while (len--) {					\
+			ceph_decode_skip_##ktype(p, end, bad);	\
+			ceph_decode_skip_##vtype(p, end, bad);	\
+		}						\
+	} while (0)
+
+#define ceph_decode_skip_map_of_map(p, end, ktype1, ktype2, vtype2, bad) \
+	do {							\
+		u32 len;					\
+								\
+		ceph_decode_32_safe(p, end, len, bad);		\
+		while (len--) {					\
+			ceph_decode_skip_##ktype1(p, end, bad);	\
+			ceph_decode_skip_map(p, end, ktype2, vtype2, bad); \
+		}						\
+	} while (0)
+
 /*
  * struct ceph_timespec <-> struct timespec
  */
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 423747714017..f6d561edd511 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -138,21 +138,6 @@ bad:
 	return -EINVAL;
 }
 
-static int skip_name_map(void **p, void *end)
-{
-        int len;
-        ceph_decode_32_safe(p, end, len ,bad);
-        while (len--) {
-                int strlen;
-                *p += sizeof(u32);
-                ceph_decode_32_safe(p, end, strlen, bad);
-                *p += strlen;
-}
-        return 0;
-bad:
-        return -EINVAL;
-}
-
 static void crush_finalize(struct crush_map *c)
 {
 	__s32 b;
@@ -187,7 +172,6 @@ static struct crush_map *crush_decode(void *pbyval, void *end)
 	void **p = &pbyval;
 	void *start = pbyval;
 	u32 magic;
-	u32 num_name_maps;
 
 	dout("crush_decode %p to %p len %d\n", *p, end, (int)(end - *p));
 
@@ -353,12 +337,9 @@ static struct crush_map *crush_decode(void *pbyval, void *end)
 		}
 	}
 
-	/* ignore trailing name maps. */
-        for (num_name_maps = 0; num_name_maps < 3; num_name_maps++) {
-                err = skip_name_map(p, end);
-                if (err < 0)
-                        goto done;
-        }
+	ceph_decode_skip_map(p, end, 32, string, bad); /* type_map */
+	ceph_decode_skip_map(p, end, 32, string, bad); /* name_map */
+	ceph_decode_skip_map(p, end, 32, string, bad); /* rule_name_map */
 
         /* tunables */
         ceph_decode_need(p, end, 3*sizeof(u32), done);
-- 
cgit v1.2.3


From 6f428df47dae2c8ea31fd4c0c74a12a8a5ac2d1d Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Wed, 21 Jun 2017 17:27:18 +0200
Subject: libceph: pg_upmap[_items] infrastructure

pg_temp and pg_upmap encodings are the same (PG -> array of osds),
except for the incremental remove: it's an empty mapping in new_pg_temp
for pg_temp and a separate old_pg_upmap set for pg_upmap.  (This isn't
to allow for empty pg_upmap mappings -- apparently, pg_temp just wasn't
looked at as an example for pg_upmap encoding.)

Reuse __decode_pg_temp() for decoding pg_upmap and new_pg_upmap.
__decode_pg_temp() stores into pg_temp union member, but since pg_upmap
union member is identical, reading through pg_upmap later is OK.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/osdmap.h |  10 +++-
 net/ceph/debugfs.c          |  23 ++++++++
 net/ceph/osdmap.c           | 135 +++++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 164 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index fe6d189bdd30..c612cff81f5c 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -143,10 +143,14 @@ struct ceph_pg_mapping {
 		struct {
 			int len;
 			int osds[];
-		} pg_temp;
+		} pg_temp, pg_upmap;
 		struct {
 			int osd;
 		} primary_temp;
+		struct {
+			int len;
+			int from_to[][2];
+		} pg_upmap_items;
 	};
 };
 
@@ -165,6 +169,10 @@ struct ceph_osdmap {
 	struct rb_root pg_temp;
 	struct rb_root primary_temp;
 
+	/* remap (post-CRUSH, pre-up) */
+	struct rb_root pg_upmap;	/* PG := raw set */
+	struct rb_root pg_upmap_items;	/* from -> to within raw set */
+
 	u32 *osd_primary_affinity;
 
 	struct rb_root pg_pools;
diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c
index 017f15c575f8..4f57d5bcaba2 100644
--- a/net/ceph/debugfs.c
+++ b/net/ceph/debugfs.c
@@ -104,6 +104,29 @@ static int osdmap_show(struct seq_file *s, void *p)
 		seq_printf(s, "primary_temp %llu.%x %d\n", pg->pgid.pool,
 			   pg->pgid.seed, pg->primary_temp.osd);
 	}
+	for (n = rb_first(&map->pg_upmap); n; n = rb_next(n)) {
+		struct ceph_pg_mapping *pg =
+			rb_entry(n, struct ceph_pg_mapping, node);
+
+		seq_printf(s, "pg_upmap %llu.%x [", pg->pgid.pool,
+			   pg->pgid.seed);
+		for (i = 0; i < pg->pg_upmap.len; i++)
+			seq_printf(s, "%s%d", (i == 0 ? "" : ","),
+				   pg->pg_upmap.osds[i]);
+		seq_printf(s, "]\n");
+	}
+	for (n = rb_first(&map->pg_upmap_items); n; n = rb_next(n)) {
+		struct ceph_pg_mapping *pg =
+			rb_entry(n, struct ceph_pg_mapping, node);
+
+		seq_printf(s, "pg_upmap_items %llu.%x [", pg->pgid.pool,
+			   pg->pgid.seed);
+		for (i = 0; i < pg->pg_upmap_items.len; i++)
+			seq_printf(s, "%s%d->%d", (i == 0 ? "" : ","),
+				   pg->pg_upmap_items.from_to[i][0],
+				   pg->pg_upmap_items.from_to[i][1]);
+		seq_printf(s, "]\n");
+	}
 
 	up_read(&osdc->lock);
 	return 0;
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index f6d561edd511..a3f60d0bfd13 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -735,6 +735,8 @@ struct ceph_osdmap *ceph_osdmap_alloc(void)
 	map->pool_max = -1;
 	map->pg_temp = RB_ROOT;
 	map->primary_temp = RB_ROOT;
+	map->pg_upmap = RB_ROOT;
+	map->pg_upmap_items = RB_ROOT;
 	mutex_init(&map->crush_workspace_mutex);
 
 	return map;
@@ -759,6 +761,20 @@ void ceph_osdmap_destroy(struct ceph_osdmap *map)
 		erase_pg_mapping(&map->primary_temp, pg);
 		free_pg_mapping(pg);
 	}
+	while (!RB_EMPTY_ROOT(&map->pg_upmap)) {
+		struct ceph_pg_mapping *pg =
+			rb_entry(rb_first(&map->pg_upmap),
+				 struct ceph_pg_mapping, node);
+		rb_erase(&pg->node, &map->pg_upmap);
+		kfree(pg);
+	}
+	while (!RB_EMPTY_ROOT(&map->pg_upmap_items)) {
+		struct ceph_pg_mapping *pg =
+			rb_entry(rb_first(&map->pg_upmap_items),
+				 struct ceph_pg_mapping, node);
+		rb_erase(&pg->node, &map->pg_upmap_items);
+		kfree(pg);
+	}
 	while (!RB_EMPTY_ROOT(&map->pg_pools)) {
 		struct ceph_pg_pool_info *pi =
 			rb_entry(rb_first(&map->pg_pools),
@@ -1161,6 +1177,75 @@ e_inval:
 	return -EINVAL;
 }
 
+static struct ceph_pg_mapping *__decode_pg_upmap(void **p, void *end,
+						 bool __unused)
+{
+	return __decode_pg_temp(p, end, false);
+}
+
+static int decode_pg_upmap(void **p, void *end, struct ceph_osdmap *map)
+{
+	return decode_pg_mapping(p, end, &map->pg_upmap, __decode_pg_upmap,
+				 false);
+}
+
+static int decode_new_pg_upmap(void **p, void *end, struct ceph_osdmap *map)
+{
+	return decode_pg_mapping(p, end, &map->pg_upmap, __decode_pg_upmap,
+				 true);
+}
+
+static int decode_old_pg_upmap(void **p, void *end, struct ceph_osdmap *map)
+{
+	return decode_pg_mapping(p, end, &map->pg_upmap, NULL, true);
+}
+
+static struct ceph_pg_mapping *__decode_pg_upmap_items(void **p, void *end,
+						       bool __unused)
+{
+	struct ceph_pg_mapping *pg;
+	u32 len, i;
+
+	ceph_decode_32_safe(p, end, len, e_inval);
+	if (len > (SIZE_MAX - sizeof(*pg)) / (2 * sizeof(u32)))
+		return ERR_PTR(-EINVAL);
+
+	ceph_decode_need(p, end, 2 * len * sizeof(u32), e_inval);
+	pg = kzalloc(sizeof(*pg) + 2 * len * sizeof(u32), GFP_NOIO);
+	if (!pg)
+		return ERR_PTR(-ENOMEM);
+
+	pg->pg_upmap_items.len = len;
+	for (i = 0; i < len; i++) {
+		pg->pg_upmap_items.from_to[i][0] = ceph_decode_32(p);
+		pg->pg_upmap_items.from_to[i][1] = ceph_decode_32(p);
+	}
+
+	return pg;
+
+e_inval:
+	return ERR_PTR(-EINVAL);
+}
+
+static int decode_pg_upmap_items(void **p, void *end, struct ceph_osdmap *map)
+{
+	return decode_pg_mapping(p, end, &map->pg_upmap_items,
+				 __decode_pg_upmap_items, false);
+}
+
+static int decode_new_pg_upmap_items(void **p, void *end,
+				     struct ceph_osdmap *map)
+{
+	return decode_pg_mapping(p, end, &map->pg_upmap_items,
+				 __decode_pg_upmap_items, true);
+}
+
+static int decode_old_pg_upmap_items(void **p, void *end,
+				     struct ceph_osdmap *map)
+{
+	return decode_pg_mapping(p, end, &map->pg_upmap_items, NULL, true);
+}
+
 /*
  * decode a full map.
  */
@@ -1250,9 +1335,7 @@ static int osdmap_decode(void **p, void *end, struct ceph_osdmap *map)
 		if (err)
 			goto bad;
 	} else {
-		/* XXX can this happen? */
-		kfree(map->osd_primary_affinity);
-		map->osd_primary_affinity = NULL;
+		WARN_ON(map->osd_primary_affinity);
 	}
 
 	/* crush */
@@ -1261,6 +1344,26 @@ static int osdmap_decode(void **p, void *end, struct ceph_osdmap *map)
 	if (err)
 		goto bad;
 
+	*p += len;
+	if (struct_v >= 3) {
+		/* erasure_code_profiles */
+		ceph_decode_skip_map_of_map(p, end, string, string, string,
+					    bad);
+	}
+
+	if (struct_v >= 4) {
+		err = decode_pg_upmap(p, end, map);
+		if (err)
+			goto bad;
+
+		err = decode_pg_upmap_items(p, end, map);
+		if (err)
+			goto bad;
+	} else {
+		WARN_ON(!RB_EMPTY_ROOT(&map->pg_upmap));
+		WARN_ON(!RB_EMPTY_ROOT(&map->pg_upmap_items));
+	}
+
 	/* ignore the rest */
 	*p = end;
 
@@ -1520,6 +1623,32 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 			goto bad;
 	}
 
+	if (struct_v >= 3) {
+		/* new_erasure_code_profiles */
+		ceph_decode_skip_map_of_map(p, end, string, string, string,
+					    bad);
+		/* old_erasure_code_profiles */
+		ceph_decode_skip_set(p, end, string, bad);
+	}
+
+	if (struct_v >= 4) {
+		err = decode_new_pg_upmap(p, end, map);
+		if (err)
+			goto bad;
+
+		err = decode_old_pg_upmap(p, end, map);
+		if (err)
+			goto bad;
+
+		err = decode_new_pg_upmap_items(p, end, map);
+		if (err)
+			goto bad;
+
+		err = decode_old_pg_upmap_items(p, end, map);
+		if (err)
+			goto bad;
+	}
+
 	/* ignore the rest */
 	*p = end;
 
-- 
cgit v1.2.3


From 069f3222ca96acfe8c59937e98c401bda5475b48 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Thu, 22 Jun 2017 19:44:05 +0200
Subject: crush: implement weight and id overrides for straw2

bucket_straw2_choose needs to use weights that may be different from
weight_items. For instance to compensate for an uneven distribution
caused by a low number of values. Or to fix the probability biais
introduced by conditional probabilities (see
http://tracker.ceph.com/issues/15653 for more information).

We introduce a weight_set for each straw2 bucket to set the desired
weight for a given item at a given position. The weight of a given item
when picking the first replica (first position) may be different from
the weight the second replica (second position). For instance the weight
matrix for a given bucket containing items 3, 7 and 13 could be as
follows:

          position 0   position 1

item 3     0x10000      0x100000
item 7     0x40000       0x10000
item 13    0x40000       0x10000

When crush_do_rule picks the first of two replicas (position 0), item 7,
3 are four times more likely to be choosen by bucket_straw2_choose than
item 13. When choosing the second replica (position 1), item 3 is ten
times more likely to be choosen than item 7, 13.

By default the weight_set of each bucket exactly matches the content of
item_weights for each position to ensure backward compatibility.

bucket_straw2_choose compares items by using their id. The same ids are
also used to index buckets and they must be unique. For each item in a
bucket an array of ids can be provided for placement purposes and they
are used instead of the ids. If no replacement ids are provided, the
legacy behavior is preserved.

Reflects ceph.git commit 19537a450fd5c5a0bb8b7830947507a76db2ceca.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/crush/crush.h  | 58 ++++++++++++++++++++++++++++++++++
 include/linux/crush/mapper.h |  9 +++---
 net/ceph/crush/mapper.c      | 74 +++++++++++++++++++++++++++++++++-----------
 net/ceph/osdmap.c            |  2 +-
 4 files changed, 119 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h
index fbecbd089d75..d8676e56fa23 100644
--- a/include/linux/crush/crush.h
+++ b/include/linux/crush/crush.h
@@ -137,6 +137,64 @@ struct crush_bucket {
 
 };
 
+/** @ingroup API
+ *
+ * Replacement weights for each item in a bucket. The size of the
+ * array must be exactly the size of the straw2 bucket, just as the
+ * item_weights array.
+ *
+ */
+struct crush_weight_set {
+	__u32 *weights; /*!< 16.16 fixed point weights
+                             in the same order as items */
+	__u32 size;     /*!< size of the __weights__ array */
+};
+
+/** @ingroup API
+ *
+ * Replacement weights and ids for a given straw2 bucket, for
+ * placement purposes.
+ *
+ * When crush_do_rule() chooses the Nth item from a straw2 bucket, the
+ * replacement weights found at __weight_set[N]__ are used instead of
+ * the weights from __item_weights__. If __N__ is greater than
+ * __weight_set_size__, the weights found at __weight_set_size-1__ are
+ * used instead. For instance if __weight_set__ is:
+ *
+ *    [ [ 0x10000, 0x20000 ],   // position 0
+ *      [ 0x20000, 0x40000 ] ]  // position 1
+ *
+ * choosing the 0th item will use position 0 weights [ 0x10000, 0x20000 ]
+ * choosing the 1th item will use position 1 weights [ 0x20000, 0x40000 ]
+ * choosing the 2th item will use position 1 weights [ 0x20000, 0x40000 ]
+ * etc.
+ *
+ */
+struct crush_choose_arg {
+	__s32 *ids;            /*!< values to use instead of items */
+	__u32 ids_size;        /*!< size of the __ids__ array */
+	struct crush_weight_set *weight_set; /*!< weight replacements for
+                                                  a given position */
+	__u32 weight_set_size; /*!< size of the __weight_set__ array */
+};
+
+/** @ingroup API
+ *
+ * Replacement weights and ids for each bucket in the crushmap. The
+ * __size__ of the __args__ array must be exactly the same as the
+ * __map->max_buckets__.
+ *
+ * The __crush_choose_arg__ at index N will be used when choosing
+ * an item from the bucket __map->buckets[N]__ bucket, provided it
+ * is a straw2 bucket.
+ *
+ */
+struct crush_choose_arg_map {
+	struct crush_choose_arg *args; /*!< replacement for each bucket
+                                            in the crushmap */
+	__u32 size;                    /*!< size of the __args__ array */
+};
+
 struct crush_bucket_uniform {
 	struct crush_bucket h;
 	__u32 item_weight;  /* 16-bit fixed point; all items equally weighted */
diff --git a/include/linux/crush/mapper.h b/include/linux/crush/mapper.h
index c95e19e1ff11..141edabb947e 100644
--- a/include/linux/crush/mapper.h
+++ b/include/linux/crush/mapper.h
@@ -11,11 +11,10 @@
 #include "crush.h"
 
 extern int crush_find_rule(const struct crush_map *map, int ruleset, int type, int size);
-extern int crush_do_rule(const struct crush_map *map,
-			 int ruleno,
-			 int x, int *result, int result_max,
-			 const __u32 *weights, int weight_max,
-			 void *cwin);
+int crush_do_rule(const struct crush_map *map,
+		  int ruleno, int x, int *result, int result_max,
+		  const __u32 *weight, int weight_max,
+		  void *cwin, const struct crush_choose_arg *choose_args);
 
 /*
  * Returns the exact amount of workspace that will need to be used
diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c
index b5cd8c21bfdf..0b2646a9cc50 100644
--- a/net/ceph/crush/mapper.c
+++ b/net/ceph/crush/mapper.c
@@ -302,19 +302,42 @@ static __u64 crush_ln(unsigned int xin)
  *
  */
 
+static __u32 *get_choose_arg_weights(const struct crush_bucket_straw2 *bucket,
+				     const struct crush_choose_arg *arg,
+				     int position)
+{
+	if (!arg || !arg->weight_set || arg->weight_set_size == 0)
+		return bucket->item_weights;
+
+	if (position >= arg->weight_set_size)
+		position = arg->weight_set_size - 1;
+	return arg->weight_set[position].weights;
+}
+
+static __s32 *get_choose_arg_ids(const struct crush_bucket_straw2 *bucket,
+				 const struct crush_choose_arg *arg)
+{
+	if (!arg || !arg->ids)
+		return bucket->h.items;
+
+	return arg->ids;
+}
+
 static int bucket_straw2_choose(const struct crush_bucket_straw2 *bucket,
-				int x, int r)
+				int x, int r,
+				const struct crush_choose_arg *arg,
+				int position)
 {
 	unsigned int i, high = 0;
 	unsigned int u;
-	unsigned int w;
 	__s64 ln, draw, high_draw = 0;
+	__u32 *weights = get_choose_arg_weights(bucket, arg, position);
+	__s32 *ids = get_choose_arg_ids(bucket, arg);
 
 	for (i = 0; i < bucket->h.size; i++) {
-		w = bucket->item_weights[i];
-		if (w) {
-			u = crush_hash32_3(bucket->h.hash, x,
-					   bucket->h.items[i], r);
+		dprintk("weight 0x%x item %d\n", weights[i], ids[i]);
+		if (weights[i]) {
+			u = crush_hash32_3(bucket->h.hash, x, ids[i], r);
 			u &= 0xffff;
 
 			/*
@@ -335,7 +358,7 @@ static int bucket_straw2_choose(const struct crush_bucket_straw2 *bucket,
 			 * weight means a larger (less negative) value
 			 * for draw.
 			 */
-			draw = div64_s64(ln, w);
+			draw = div64_s64(ln, weights[i]);
 		} else {
 			draw = S64_MIN;
 		}
@@ -352,7 +375,9 @@ static int bucket_straw2_choose(const struct crush_bucket_straw2 *bucket,
 
 static int crush_bucket_choose(const struct crush_bucket *in,
 			       struct crush_work_bucket *work,
-			       int x, int r)
+			       int x, int r,
+			       const struct crush_choose_arg *arg,
+			       int position)
 {
 	dprintk(" crush_bucket_choose %d x=%d r=%d\n", in->id, x, r);
 	BUG_ON(in->size == 0);
@@ -374,7 +399,7 @@ static int crush_bucket_choose(const struct crush_bucket *in,
 	case CRUSH_BUCKET_STRAW2:
 		return bucket_straw2_choose(
 			(const struct crush_bucket_straw2 *)in,
-			x, r);
+			x, r, arg, position);
 	default:
 		dprintk("unknown bucket %d alg %d\n", in->id, in->alg);
 		return in->items[0];
@@ -436,7 +461,8 @@ static int crush_choose_firstn(const struct crush_map *map,
 			       unsigned int vary_r,
 			       unsigned int stable,
 			       int *out2,
-			       int parent_r)
+			       int parent_r,
+			       const struct crush_choose_arg *choose_args)
 {
 	int rep;
 	unsigned int ftotal, flocal;
@@ -486,7 +512,10 @@ static int crush_choose_firstn(const struct crush_map *map,
 				else
 					item = crush_bucket_choose(
 						in, work->work[-1-in->id],
-						x, r);
+						x, r,
+						(choose_args ?
+						 &choose_args[-1-in->id] : 0),
+						outpos);
 				if (item >= map->max_devices) {
 					dprintk("   bad item %d\n", item);
 					skip_rep = 1;
@@ -543,7 +572,8 @@ static int crush_choose_firstn(const struct crush_map *map,
 							    vary_r,
 							    stable,
 							    NULL,
-							    sub_r) <= outpos)
+							    sub_r,
+							    choose_args) <= outpos)
 							/* didn't get leaf */
 							reject = 1;
 					} else {
@@ -620,7 +650,8 @@ static void crush_choose_indep(const struct crush_map *map,
 			       unsigned int recurse_tries,
 			       int recurse_to_leaf,
 			       int *out2,
-			       int parent_r)
+			       int parent_r,
+			       const struct crush_choose_arg *choose_args)
 {
 	const struct crush_bucket *in = bucket;
 	int endpos = outpos + left;
@@ -692,7 +723,10 @@ static void crush_choose_indep(const struct crush_map *map,
 
 				item = crush_bucket_choose(
 					in, work->work[-1-in->id],
-					x, r);
+					x, r,
+					(choose_args ?
+					 &choose_args[-1-in->id] : 0),
+					outpos);
 				if (item >= map->max_devices) {
 					dprintk("   bad item %d\n", item);
 					out[rep] = CRUSH_ITEM_NONE;
@@ -746,7 +780,8 @@ static void crush_choose_indep(const struct crush_map *map,
 							x, 1, numrep, 0,
 							out2, rep,
 							recurse_tries, 0,
-							0, NULL, r);
+							0, NULL, r,
+							choose_args);
 						if (out2[rep] == CRUSH_ITEM_NONE) {
 							/* placed nothing; no leaf */
 							break;
@@ -854,11 +889,12 @@ void crush_init_workspace(const struct crush_map *map, void *v)
  * @weight: weight vector (for map leaves)
  * @weight_max: size of weight vector
  * @cwin: pointer to at least crush_work_size() bytes of memory
+ * @choose_args: weights and ids for each known bucket
  */
 int crush_do_rule(const struct crush_map *map,
 		  int ruleno, int x, int *result, int result_max,
 		  const __u32 *weight, int weight_max,
-		  void *cwin)
+		  void *cwin, const struct crush_choose_arg *choose_args)
 {
 	int result_len;
 	struct crush_work *cw = cwin;
@@ -1013,7 +1049,8 @@ int crush_do_rule(const struct crush_map *map,
 						vary_r,
 						stable,
 						c+osize,
-						0);
+						0,
+						choose_args);
 				} else {
 					out_size = ((numrep < (result_max-osize)) ?
 						    numrep : (result_max-osize));
@@ -1030,7 +1067,8 @@ int crush_do_rule(const struct crush_map *map,
 						   choose_leaf_tries : 1,
 						recurse_to_leaf,
 						c+osize,
-						0);
+						0,
+						choose_args);
 					osize += out_size;
 				}
 			}
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 93baa69407c5..9da0ee61aca5 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -2111,7 +2111,7 @@ static int do_crush(struct ceph_osdmap *map, int ruleno, int x,
 
 	mutex_lock(&map->crush_workspace_mutex);
 	r = crush_do_rule(map->crush, ruleno, x, result, result_max,
-			  weight, weight_max, map->crush_workspace);
+			  weight, weight_max, map->crush_workspace, NULL);
 	mutex_unlock(&map->crush_workspace_mutex);
 
 	return r;
-- 
cgit v1.2.3


From 5cf9c4a9959b6273675310d14a834ef14fbca37c Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Thu, 22 Jun 2017 19:44:05 +0200
Subject: libceph, crush: per-pool crush_choose_arg_map for crush_do_rule()

If there is no crush_choose_arg_map for a given pool, a NULL pointer is
passed to preserve existing crush_do_rule() behavior.

Reflects ceph.git commits 55fb91d64071552ea1bc65ab4ea84d3c8b73ab4b,
                          dbe36e08be00c6519a8c89718dd47b0219c20516.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/crush/crush.h |   8 ++
 net/ceph/crush/crush.c      |   3 +
 net/ceph/osdmap.c           | 200 +++++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 208 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h
index d8676e56fa23..92e165d417a6 100644
--- a/include/linux/crush/crush.h
+++ b/include/linux/crush/crush.h
@@ -2,6 +2,7 @@
 #define CEPH_CRUSH_CRUSH_H
 
 #ifdef __KERNEL__
+# include <linux/rbtree.h>
 # include <linux/types.h>
 #else
 # include "crush_compat.h"
@@ -190,6 +191,10 @@ struct crush_choose_arg {
  *
  */
 struct crush_choose_arg_map {
+#ifdef __KERNEL__
+	struct rb_node node;
+	u64 choose_args_index;
+#endif
 	struct crush_choose_arg *args; /*!< replacement for each bucket
                                             in the crushmap */
 	__u32 size;                    /*!< size of the __args__ array */
@@ -294,6 +299,9 @@ struct crush_map {
 	__u32 allowed_bucket_algs;
 
 	__u32 *choose_tries;
+#else
+	/* CrushWrapper::choose_args */
+	struct rb_root choose_args;
 #endif
 };
 
diff --git a/net/ceph/crush/crush.c b/net/ceph/crush/crush.c
index 5bf94c04f645..4b428f46a8ca 100644
--- a/net/ceph/crush/crush.c
+++ b/net/ceph/crush/crush.c
@@ -1,6 +1,7 @@
 #ifdef __KERNEL__
 # include <linux/slab.h>
 # include <linux/crush/crush.h>
+void clear_choose_args(struct crush_map *c);
 #else
 # include "crush_compat.h"
 # include "crush.h"
@@ -127,6 +128,8 @@ void crush_destroy(struct crush_map *map)
 
 #ifndef __KERNEL__
 	kfree(map->choose_tries);
+#else
+	clear_choose_args(map);
 #endif
 	kfree(map);
 }
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 9da0ee61aca5..f630d1072299 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -138,6 +138,177 @@ bad:
 	return -EINVAL;
 }
 
+static struct crush_choose_arg_map *alloc_choose_arg_map(void)
+{
+	struct crush_choose_arg_map *arg_map;
+
+	arg_map = kzalloc(sizeof(*arg_map), GFP_NOIO);
+	if (!arg_map)
+		return NULL;
+
+	RB_CLEAR_NODE(&arg_map->node);
+	return arg_map;
+}
+
+static void free_choose_arg_map(struct crush_choose_arg_map *arg_map)
+{
+	if (arg_map) {
+		int i, j;
+
+		WARN_ON(!RB_EMPTY_NODE(&arg_map->node));
+
+		for (i = 0; i < arg_map->size; i++) {
+			struct crush_choose_arg *arg = &arg_map->args[i];
+
+			for (j = 0; j < arg->weight_set_size; j++)
+				kfree(arg->weight_set[j].weights);
+			kfree(arg->weight_set);
+			kfree(arg->ids);
+		}
+		kfree(arg_map->args);
+		kfree(arg_map);
+	}
+}
+
+DEFINE_RB_FUNCS(choose_arg_map, struct crush_choose_arg_map, choose_args_index,
+		node);
+
+void clear_choose_args(struct crush_map *c)
+{
+	while (!RB_EMPTY_ROOT(&c->choose_args)) {
+		struct crush_choose_arg_map *arg_map =
+		    rb_entry(rb_first(&c->choose_args),
+			     struct crush_choose_arg_map, node);
+
+		erase_choose_arg_map(&c->choose_args, arg_map);
+		free_choose_arg_map(arg_map);
+	}
+}
+
+static u32 *decode_array_32_alloc(void **p, void *end, u32 *plen)
+{
+	u32 *a = NULL;
+	u32 len;
+	int ret;
+
+	ceph_decode_32_safe(p, end, len, e_inval);
+	if (len) {
+		u32 i;
+
+		a = kmalloc_array(len, sizeof(u32), GFP_NOIO);
+		if (!a) {
+			ret = -ENOMEM;
+			goto fail;
+		}
+
+		ceph_decode_need(p, end, len * sizeof(u32), e_inval);
+		for (i = 0; i < len; i++)
+			a[i] = ceph_decode_32(p);
+	}
+
+	*plen = len;
+	return a;
+
+e_inval:
+	ret = -EINVAL;
+fail:
+	kfree(a);
+	return ERR_PTR(ret);
+}
+
+/*
+ * Assumes @arg is zero-initialized.
+ */
+static int decode_choose_arg(void **p, void *end, struct crush_choose_arg *arg)
+{
+	int ret;
+
+	ceph_decode_32_safe(p, end, arg->weight_set_size, e_inval);
+	if (arg->weight_set_size) {
+		u32 i;
+
+		arg->weight_set = kmalloc_array(arg->weight_set_size,
+						sizeof(*arg->weight_set),
+						GFP_NOIO);
+		if (!arg->weight_set)
+			return -ENOMEM;
+
+		for (i = 0; i < arg->weight_set_size; i++) {
+			struct crush_weight_set *w = &arg->weight_set[i];
+
+			w->weights = decode_array_32_alloc(p, end, &w->size);
+			if (IS_ERR(w->weights)) {
+				ret = PTR_ERR(w->weights);
+				w->weights = NULL;
+				return ret;
+			}
+		}
+	}
+
+	arg->ids = decode_array_32_alloc(p, end, &arg->ids_size);
+	if (IS_ERR(arg->ids)) {
+		ret = PTR_ERR(arg->ids);
+		arg->ids = NULL;
+		return ret;
+	}
+
+	return 0;
+
+e_inval:
+	return -EINVAL;
+}
+
+static int decode_choose_args(void **p, void *end, struct crush_map *c)
+{
+	struct crush_choose_arg_map *arg_map = NULL;
+	u32 num_choose_arg_maps, num_buckets;
+	int ret;
+
+	ceph_decode_32_safe(p, end, num_choose_arg_maps, e_inval);
+	while (num_choose_arg_maps--) {
+		arg_map = alloc_choose_arg_map();
+		if (!arg_map) {
+			ret = -ENOMEM;
+			goto fail;
+		}
+
+		ceph_decode_64_safe(p, end, arg_map->choose_args_index,
+				    e_inval);
+		arg_map->size = c->max_buckets;
+		arg_map->args = kcalloc(arg_map->size, sizeof(*arg_map->args),
+					GFP_NOIO);
+		if (!arg_map->args) {
+			ret = -ENOMEM;
+			goto fail;
+		}
+
+		ceph_decode_32_safe(p, end, num_buckets, e_inval);
+		while (num_buckets--) {
+			struct crush_choose_arg *arg;
+			u32 bucket_index;
+
+			ceph_decode_32_safe(p, end, bucket_index, e_inval);
+			if (bucket_index >= arg_map->size)
+				goto e_inval;
+
+			arg = &arg_map->args[bucket_index];
+			ret = decode_choose_arg(p, end, arg);
+			if (ret)
+				goto fail;
+		}
+
+		insert_choose_arg_map(&c->choose_args, arg_map);
+	}
+
+	return 0;
+
+e_inval:
+	ret = -EINVAL;
+fail:
+	free_choose_arg_map(arg_map);
+	return ret;
+}
+
 static void crush_finalize(struct crush_map *c)
 {
 	__s32 b;
@@ -179,6 +350,8 @@ static struct crush_map *crush_decode(void *pbyval, void *end)
 	if (c == NULL)
 		return ERR_PTR(-ENOMEM);
 
+	c->choose_args = RB_ROOT;
+
         /* set tunables to default values */
         c->choose_local_tries = 2;
         c->choose_local_fallback_tries = 5;
@@ -372,6 +545,21 @@ static struct crush_map *crush_decode(void *pbyval, void *end)
 	dout("crush decode tunable chooseleaf_stable = %d\n",
 	     c->chooseleaf_stable);
 
+	if (*p != end) {
+		/* class_map */
+		ceph_decode_skip_map(p, end, 32, 32, bad);
+		/* class_name */
+		ceph_decode_skip_map(p, end, 32, string, bad);
+		/* class_bucket */
+		ceph_decode_skip_map_of_map(p, end, 32, 32, 32, bad);
+	}
+
+	if (*p != end) {
+		err = decode_choose_args(p, end, c);
+		if (err)
+			goto bad;
+	}
+
 done:
 	crush_finalize(c);
 	dout("crush_decode success\n");
@@ -2103,15 +2291,21 @@ static u32 raw_pg_to_pps(struct ceph_pg_pool_info *pi,
 
 static int do_crush(struct ceph_osdmap *map, int ruleno, int x,
 		    int *result, int result_max,
-		    const __u32 *weight, int weight_max)
+		    const __u32 *weight, int weight_max,
+		    u64 choose_args_index)
 {
+	struct crush_choose_arg_map *arg_map;
 	int r;
 
 	BUG_ON(result_max > CEPH_PG_MAX_SIZE);
 
+	arg_map = lookup_choose_arg_map(&map->crush->choose_args,
+					choose_args_index);
+
 	mutex_lock(&map->crush_workspace_mutex);
 	r = crush_do_rule(map->crush, ruleno, x, result, result_max,
-			  weight, weight_max, map->crush_workspace, NULL);
+			  weight, weight_max, map->crush_workspace,
+			  arg_map ? arg_map->args : NULL);
 	mutex_unlock(&map->crush_workspace_mutex);
 
 	return r;
@@ -2181,7 +2375,7 @@ static void pg_to_raw_osds(struct ceph_osdmap *osdmap,
 	}
 
 	len = do_crush(osdmap, ruleno, pps, raw->osds, pi->size,
-		       osdmap->osd_weight, osdmap->max_osd);
+		       osdmap->osd_weight, osdmap->max_osd, pi->id);
 	if (len < 0) {
 		pr_err("error %d from crush rule %d: pool %lld ruleset %d type %d size %d\n",
 		       len, ruleno, pi->id, pi->crush_ruleset, pi->type,
-- 
cgit v1.2.3


From 0bb05da2ec57163b7a25efef001ed8f52b18b070 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Thu, 22 Jun 2017 19:44:06 +0200
Subject: libceph: osd_state is 32 bits wide in luminous

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/osdmap.h |  4 ++--
 net/ceph/debugfs.c          |  2 +-
 net/ceph/osdmap.c           | 29 ++++++++++++++++++++---------
 3 files changed, 23 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index c612cff81f5c..a0996cb9faed 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -162,7 +162,7 @@ struct ceph_osdmap {
 	u32 flags;         /* CEPH_OSDMAP_* */
 
 	u32 max_osd;       /* size of osd_state, _offload, _addr arrays */
-	u8 *osd_state;     /* CEPH_OSD_* */
+	u32 *osd_state;    /* CEPH_OSD_* */
 	u32 *osd_weight;   /* 0 = failed, 0x10000 = 100% normal */
 	struct ceph_entity_addr *osd_addr;
 
@@ -203,7 +203,7 @@ static inline bool ceph_osd_is_down(struct ceph_osdmap *map, int osd)
 	return !ceph_osd_is_up(map, osd);
 }
 
-extern char *ceph_osdmap_state_str(char *str, int len, int state);
+char *ceph_osdmap_state_str(char *str, int len, u32 state);
 extern u32 ceph_get_primary_affinity(struct ceph_osdmap *map, int osd);
 
 static inline struct ceph_entity_addr *ceph_osd_addr(struct ceph_osdmap *map,
diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c
index 4f57d5bcaba2..fa5233e0d01c 100644
--- a/net/ceph/debugfs.c
+++ b/net/ceph/debugfs.c
@@ -77,7 +77,7 @@ static int osdmap_show(struct seq_file *s, void *p)
 	}
 	for (i = 0; i < map->max_osd; i++) {
 		struct ceph_entity_addr *addr = &map->osd_addr[i];
-		int state = map->osd_state[i];
+		u32 state = map->osd_state[i];
 		char sb[64];
 
 		seq_printf(s, "osd%d\t%s\t%3d%%\t(%s)\t%3d%%\n",
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index f630d1072299..864789c5974e 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -11,7 +11,7 @@
 #include <linux/crush/hash.h>
 #include <linux/crush/mapper.h>
 
-char *ceph_osdmap_state_str(char *str, int len, int state)
+char *ceph_osdmap_state_str(char *str, int len, u32 state)
 {
 	if (!len)
 		return str;
@@ -984,7 +984,7 @@ void ceph_osdmap_destroy(struct ceph_osdmap *map)
  */
 static int osdmap_set_max_osd(struct ceph_osdmap *map, int max)
 {
-	u8 *state;
+	u32 *state;
 	u32 *weight;
 	struct ceph_entity_addr *addr;
 	int i;
@@ -1484,13 +1484,21 @@ static int osdmap_decode(void **p, void *end, struct ceph_osdmap *map)
 
 	/* osd_state, osd_weight, osd_addrs->client_addr */
 	ceph_decode_need(p, end, 3*sizeof(u32) +
-			 map->max_osd*(1 + sizeof(*map->osd_weight) +
+			 map->max_osd*((struct_v >= 5 ? sizeof(u32) :
+							sizeof(u8)) +
+				       sizeof(*map->osd_weight) +
 				       sizeof(*map->osd_addr)), e_inval);
 
 	if (ceph_decode_32(p) != map->max_osd)
 		goto e_inval;
 
-	ceph_decode_copy(p, map->osd_state, map->max_osd);
+	if (struct_v >= 5) {
+		for (i = 0; i < map->max_osd; i++)
+			map->osd_state[i] = ceph_decode_32(p);
+	} else {
+		for (i = 0; i < map->max_osd; i++)
+			map->osd_state[i] = ceph_decode_8(p);
+	}
 
 	if (ceph_decode_32(p) != map->max_osd)
 		goto e_inval;
@@ -1598,7 +1606,7 @@ struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end)
  *     new_up_client: { osd=6, addr=... } # set osd_state and addr
  *     new_state: { osd=6, xorstate=EXISTS } # clear osd_state
  */
-static int decode_new_up_state_weight(void **p, void *end,
+static int decode_new_up_state_weight(void **p, void *end, u8 struct_v,
 				      struct ceph_osdmap *map)
 {
 	void *new_up_client;
@@ -1614,7 +1622,7 @@ static int decode_new_up_state_weight(void **p, void *end,
 
 	new_state = *p;
 	ceph_decode_32_safe(p, end, len, e_inval);
-	len *= sizeof(u32) + sizeof(u8);
+	len *= sizeof(u32) + (struct_v >= 5 ? sizeof(u32) : sizeof(u8));
 	ceph_decode_need(p, end, len, e_inval);
 	*p += len;
 
@@ -1650,11 +1658,14 @@ static int decode_new_up_state_weight(void **p, void *end,
 	len = ceph_decode_32(p);
 	while (len--) {
 		s32 osd;
-		u8 xorstate;
+		u32 xorstate;
 		int ret;
 
 		osd = ceph_decode_32(p);
-		xorstate = ceph_decode_8(p);
+		if (struct_v >= 5)
+			xorstate = ceph_decode_32(p);
+		else
+			xorstate = ceph_decode_8(p);
 		if (xorstate == 0)
 			xorstate = CEPH_OSD_UP;
 		BUG_ON(osd >= map->max_osd);
@@ -1788,7 +1799,7 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 	}
 
 	/* new_up_client, new_state, new_weight */
-	err = decode_new_up_state_weight(p, end, map);
+	err = decode_new_up_state_weight(p, end, struct_v, map);
 	if (err)
 		goto bad;
 
-- 
cgit v1.2.3


From 33e9c8dbfbcef8e4cda8e43a445e692ab7e0d8c0 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Mon, 26 Jun 2017 12:05:55 +0200
Subject: libceph: advertise support for NEW_OSDOP_ENCODING and SERVER_LUMINOUS

All four SERVER_LUMINOUS feature bits are implemented, switch it on!

NEW_OSDOP_ENCODING doesn't mean much for the client (it signifies
support for MOSDOp v6) but needs to be enabled in order to get the
latest (currently v25) pg_pool_t.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Acked-by: Sage Weil <sage@redhat.com>
---
 include/linux/ceph/ceph_features.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include')

diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h
index 78a58770e6e9..f0f6c537b64c 100644
--- a/include/linux/ceph/ceph_features.h
+++ b/include/linux/ceph/ceph_features.h
@@ -184,6 +184,11 @@ DEFINE_CEPH_FEATURE_DEPRECATED(63, 1, RESERVED_BROKEN, LUMINOUS) // client-facin
 	 CEPH_FEATURE_PGPOOL3 |			\
 	 CEPH_FEATURE_OSDENC |			\
 	 CEPH_FEATURE_CRUSH_TUNABLES |		\
+	 CEPH_FEATURE_SERVER_LUMINOUS |		\
+	 CEPH_FEATURE_RESEND_ON_SPLIT |		\
+	 CEPH_FEATURE_RADOS_BACKOFF |		\
+	 CEPH_FEATURE_OSDMAP_PG_UPMAP |		\
+	 CEPH_FEATURE_CRUSH_CHOOSE_ARGS |	\
 	 CEPH_FEATURE_MSG_AUTH |		\
 	 CEPH_FEATURE_CRUSH_TUNABLES2 |		\
 	 CEPH_FEATURE_REPLY_CREATE_INODE |	\
@@ -199,6 +204,7 @@ DEFINE_CEPH_FEATURE_DEPRECATED(63, 1, RESERVED_BROKEN, LUMINOUS) // client-facin
 	 CEPH_FEATURE_MSGR_KEEPALIVE2 |		\
 	 CEPH_FEATURE_OSD_POOLRESEND |		\
 	 CEPH_FEATURE_CRUSH_V4 |		\
+	 CEPH_FEATURE_NEW_OSDOP_ENCODING |	\
 	 CEPH_FEATURE_SERVER_JEWEL |		\
 	 CEPH_FEATURE_MON_STATEFUL_SUB |	\
 	 CEPH_FEATURE_CRUSH_TUNABLES5 |		\
-- 
cgit v1.2.3


From 8f1a357d41a22009150cf404b5aa5876efdb59b1 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 6 Jul 2017 20:26:17 +0300
Subject: i2c: Provide a stub for i2c_detect_slave_mode()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Drivers would like to call i2c_detect_slave_mode() even if !I2C_SLAVE.
Give them what they want to,

Otherwise kernel will not compile:
drivers/i2c/busses/i2c-designware-platdrv.c: In function ‘dw_i2c_plat_probe’:
drivers/i2c/busses/i2c-designware-platdrv.c:331:6: error: implicit declaration of function ‘i2c_detect_slave_mode’ [-Werror=implicit-function-declaration]
  if (i2c_detect_slave_mode(&pdev->dev))
      ^~~~~~~~~~~~~~~~~~~~~
cc1: some warnings being treated as errors

Fixes: 6e38cf3b4421 ("i2c: designware: Let slave adapter support be optional")
Reported-by: Abdul Haleem <abdhalee@linux.vnet.ibm.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
---
 include/linux/i2c.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index 72d0ece70ed3..00ca5b86a753 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -295,6 +295,8 @@ static inline int i2c_slave_event(struct i2c_client *client,
 {
 	return client->slave_cb(client, event, val);
 }
+#else
+static inline bool i2c_detect_slave_mode(struct device *dev) { return false; }
 #endif
 
 /**
-- 
cgit v1.2.3


From d1438ad8f3eec7207618b8e01f9f3eec7b6f67c4 Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Fri, 7 Jul 2017 18:08:25 -0700
Subject: nvme_fc/nvmet_fc: revise Create Association descriptor length

Revises the Create Association LS for the amount of pad expected in 1.16.

Add defines for the minimum lengths that a target can accept (e.g. variable
pad lengths)

Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
---
 include/linux/nvme-fc.h | 23 ++++++++++++++++++++++-
 1 file changed, 22 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/nvme-fc.h b/include/linux/nvme-fc.h
index bc711a10be05..21c37e39e41a 100644
--- a/include/linux/nvme-fc.h
+++ b/include/linux/nvme-fc.h
@@ -17,6 +17,7 @@
 
 /*
  * This file contains definitions relative to FC-NVME r1.14 (16-020vB).
+ * The fcnvme_lsdesc_cr_assoc_cmd struct reflects expected r1.16 content.
  */
 
 #ifndef _NVME_FC_H
@@ -193,9 +194,21 @@ struct fcnvme_lsdesc_cr_assoc_cmd {
 	uuid_t	hostid;
 	u8	hostnqn[FCNVME_ASSOC_HOSTNQN_LEN];
 	u8	subnqn[FCNVME_ASSOC_SUBNQN_LEN];
-	u8	rsvd632[384];
+	__be32	rsvd584[108];		/* pad to 1016 bytes,
+					 * which makes overall LS rqst
+					 * payload 1024 bytes
+					 */
 };
 
+#define FCNVME_LSDESC_CRA_CMD_DESC_MINLEN	\
+		offsetof(struct fcnvme_lsdesc_cr_assoc_cmd, rsvd584)
+
+#define FCNVME_LSDESC_CRA_CMD_DESC_MIN_DESCLEN	\
+		(FCNVME_LSDESC_CRA_CMD_DESC_MINLEN - \
+		 offsetof(struct fcnvme_lsdesc_cr_assoc_cmd, ersp_ratio))
+
+
+
 /* FCNVME_LSDESC_CREATE_CONN_CMD */
 struct fcnvme_lsdesc_cr_conn_cmd {
 	__be32	desc_tag;		/* FCNVME_LSDESC_xxx */
@@ -273,6 +286,14 @@ struct fcnvme_ls_cr_assoc_rqst {
 	struct fcnvme_lsdesc_cr_assoc_cmd	assoc_cmd;
 };
 
+#define FCNVME_LSDESC_CRA_RQST_MINLEN	\
+		(offsetof(struct fcnvme_ls_cr_assoc_rqst, assoc_cmd) + \
+			FCNVME_LSDESC_CRA_CMD_DESC_MINLEN)
+
+#define FCNVME_LSDESC_CRA_RQST_MIN_LISTLEN	\
+		FCNVME_LSDESC_CRA_CMD_DESC_MINLEN
+
+
 struct fcnvme_ls_cr_assoc_acc {
 	struct fcnvme_ls_acc_hdr		hdr;
 	struct fcnvme_lsdesc_assoc_id		associd;
-- 
cgit v1.2.3


From 7e988b103d0d52190244517edc76e649071284bb Mon Sep 17 00:00:00 2001
From: Christian Borntraeger <borntraeger@de.ibm.com>
Date: Fri, 7 Jul 2017 15:49:00 +0200
Subject: KVM: use correct accessor function for __kvm_memslots

kvm memslots are protected by srcu and not by rcu. We must use
srcu_dereference_check instead of rcu_dereference_check.

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/kvm_host.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index b3ca77a96b2d..648b34cabb38 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -568,9 +568,8 @@ void kvm_put_kvm(struct kvm *kvm);
 
 static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id)
 {
-	return rcu_dereference_check(kvm->memslots[as_id],
-			srcu_read_lock_held(&kvm->srcu)
-			|| lockdep_is_held(&kvm->slots_lock));
+	return srcu_dereference_check(kvm->memslots[as_id], &kvm->srcu,
+			lockdep_is_held(&kvm->slots_lock));
 }
 
 static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm)
-- 
cgit v1.2.3


From c43aeb198048f64abda8655fdcdebe71cf1877ba Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 10 Jul 2017 07:40:49 -0400
Subject: fix brown paperbag bug in inlined copy_..._iter()

"copied nothing" == "return 0", not "return full size".

Fixes: aa28de275a24 "iov_iter/hardening: move object size checks to inlined part"
Spotted-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/uio.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/uio.h b/include/linux/uio.h
index 342d2dc225b9..8a642cda641c 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -103,7 +103,7 @@ static __always_inline __must_check
 size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
 {
 	if (unlikely(!check_copy_size(addr, bytes, true)))
-		return bytes;
+		return 0;
 	else
 		return _copy_to_iter(addr, bytes, i);
 }
@@ -112,7 +112,7 @@ static __always_inline __must_check
 size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
 {
 	if (unlikely(!check_copy_size(addr, bytes, false)))
-		return bytes;
+		return 0;
 	else
 		return _copy_from_iter(addr, bytes, i);
 }
@@ -130,7 +130,7 @@ static __always_inline __must_check
 size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i)
 {
 	if (unlikely(!check_copy_size(addr, bytes, false)))
-		return bytes;
+		return 0;
 	else
 		return _copy_from_iter_nocache(addr, bytes, i);
 }
@@ -160,7 +160,7 @@ static __always_inline __must_check
 size_t copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i)
 {
 	if (unlikely(!check_copy_size(addr, bytes, false)))
-		return bytes;
+		return 0;
 	else
 		return _copy_from_iter_flushcache(addr, bytes, i);
 }
-- 
cgit v1.2.3


From 42a6e0996084972574e0a2b23e7326b78b0f64c5 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 10 Jul 2017 13:22:50 +0200
Subject: nvmem: include linux/err.h from header

The new support for nvmem devices from the rtc layer caused a build
error in some configurations:

include/linux/nvmem-provider.h: In function 'nvmem_register':
include/linux/nvmem-provider.h:51:9: error: implicit declaration of function 'ERR_PTR' [-Werror=implicit-function-declaration]

This adds the missing include to ensure we can always include
the header.

Fixes: 697e5a47aa12 ("rtc: add generic nvmem support")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Signed-off-by: Alexandre Belloni <alexandre.belloni@free-electrons.com>
---
 include/linux/nvmem-provider.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h
index cd93416d762e..497706f5adca 100644
--- a/include/linux/nvmem-provider.h
+++ b/include/linux/nvmem-provider.h
@@ -12,6 +12,9 @@
 #ifndef _LINUX_NVMEM_PROVIDER_H
 #define _LINUX_NVMEM_PROVIDER_H
 
+#include <linux/err.h>
+#include <linux/errno.h>
+
 struct nvmem_device;
 struct nvmem_cell_info;
 typedef int (*nvmem_reg_read_t)(void *priv, unsigned int offset,
-- 
cgit v1.2.3


From 7cee9384cb3e25de33d75ecdbf08bb15b4ea9fa5 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Mon, 10 Jul 2017 11:40:19 -0700
Subject: Fix up over-eager 'wait_queue_t' renaming

Commit ac6424b981bc ("sched/wait: Rename wait_queue_t =>
wait_queue_entry_t") had scripted the renaming incorrectly, and didn't
actually check that the 'wait_queue_t' was a full token.

As a result, it also triggered on 'wait_queue_token', and renamed that
to 'wait_queue_entry_token' entry in the autofs4 packet structure
definition too.  That was entirely incorrect, and not intended.

The end result built fine when building just the kernel - because
everything had been renamed consistently there - but caused problems in
user space because the "struct autofs_packet_missing" type is exported
as part of the uapi.

This scripts it all back again:

    git grep -lw wait_queue_entry_token |
        xargs sed -i 's/wait_queue_entry_token/wait_queue_token/g'

and checks the end result.

Reported-by: Florian Fainelli <f.fainelli@gmail.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Fixes: ac6424b981bc ("sched/wait: Rename wait_queue_t => wait_queue_entry_t")
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/filesystems/autofs4.txt | 12 ++++++------
 fs/autofs4/autofs_i.h                 |  2 +-
 fs/autofs4/waitq.c                    | 18 +++++++++---------
 include/uapi/linux/auto_fs.h          |  4 ++--
 include/uapi/linux/auto_fs4.h         |  4 ++--
 5 files changed, 20 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/Documentation/filesystems/autofs4.txt b/Documentation/filesystems/autofs4.txt
index 8444dc3d57e8..f10dd590f69f 100644
--- a/Documentation/filesystems/autofs4.txt
+++ b/Documentation/filesystems/autofs4.txt
@@ -316,7 +316,7 @@ For version 5, the format of the message is:
         struct autofs_v5_packet {
                 int proto_version;                /* Protocol version */
                 int type;                        /* Type of packet */
-                autofs_wqt_t wait_queue_entry_token;
+                autofs_wqt_t wait_queue_token;
                 __u32 dev;
                 __u64 ino;
                 __u32 uid;
@@ -341,12 +341,12 @@ The pipe will be set to "packet mode" (equivalent to passing
 `O_DIRECT`) to _pipe2(2)_ so that a read from the pipe will return at
 most one packet, and any unread portion of a packet will be discarded.
 
-The `wait_queue_entry_token` is a unique number which can identify a
+The `wait_queue_token` is a unique number which can identify a
 particular request to be acknowledged.  When a message is sent over
 the pipe the affected dentry is marked as either "active" or
 "expiring" and other accesses to it block until the message is
 acknowledged using one of the ioctls below and the relevant
-`wait_queue_entry_token`.
+`wait_queue_token`.
 
 Communicating with autofs: root directory ioctls
 ------------------------------------------------
@@ -358,7 +358,7 @@ capability, or must be the automount daemon.
 The available ioctl commands are:
 
 - **AUTOFS_IOC_READY**: a notification has been handled.  The argument
-    to the ioctl command is the "wait_queue_entry_token" number
+    to the ioctl command is the "wait_queue_token" number
     corresponding to the notification being acknowledged.
 - **AUTOFS_IOC_FAIL**: similar to above, but indicates failure with
     the error code `ENOENT`.
@@ -382,14 +382,14 @@ The available ioctl commands are:
         struct autofs_packet_expire_multi {
                 int proto_version;              /* Protocol version */
                 int type;                       /* Type of packet */
-                autofs_wqt_t wait_queue_entry_token;
+                autofs_wqt_t wait_queue_token;
                 int len;
                 char name[NAME_MAX+1];
         };
 
      is required.  This is filled in with the name of something
      that can be unmounted or removed.  If nothing can be expired,
-     `errno` is set to `EAGAIN`.  Even though a `wait_queue_entry_token`
+     `errno` is set to `EAGAIN`.  Even though a `wait_queue_token`
      is present in the structure, no "wait queue" is established
      and no acknowledgment is needed.
 - **AUTOFS_IOC_EXPIRE_MULTI**:  This is similar to
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index 974f5346458a..beef981aa54f 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -83,7 +83,7 @@ struct autofs_info {
 struct autofs_wait_queue {
 	wait_queue_head_t queue;
 	struct autofs_wait_queue *next;
-	autofs_wqt_t wait_queue_entry_token;
+	autofs_wqt_t wait_queue_token;
 	/* We use the following to see what we are waiting for */
 	struct qstr name;
 	u32 dev;
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index 7071895b0678..24a58bf9ca72 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -104,7 +104,7 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
 	size_t pktsz;
 
 	pr_debug("wait id = 0x%08lx, name = %.*s, type=%d\n",
-		 (unsigned long) wq->wait_queue_entry_token,
+		 (unsigned long) wq->wait_queue_token,
 		 wq->name.len, wq->name.name, type);
 
 	memset(&pkt, 0, sizeof(pkt)); /* For security reasons */
@@ -120,7 +120,7 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
 
 		pktsz = sizeof(*mp);
 
-		mp->wait_queue_entry_token = wq->wait_queue_entry_token;
+		mp->wait_queue_token = wq->wait_queue_token;
 		mp->len = wq->name.len;
 		memcpy(mp->name, wq->name.name, wq->name.len);
 		mp->name[wq->name.len] = '\0';
@@ -133,7 +133,7 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
 
 		pktsz = sizeof(*ep);
 
-		ep->wait_queue_entry_token = wq->wait_queue_entry_token;
+		ep->wait_queue_token = wq->wait_queue_token;
 		ep->len = wq->name.len;
 		memcpy(ep->name, wq->name.name, wq->name.len);
 		ep->name[wq->name.len] = '\0';
@@ -153,7 +153,7 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
 
 		pktsz = sizeof(*packet);
 
-		packet->wait_queue_entry_token = wq->wait_queue_entry_token;
+		packet->wait_queue_token = wq->wait_queue_token;
 		packet->len = wq->name.len;
 		memcpy(packet->name, wq->name.name, wq->name.len);
 		packet->name[wq->name.len] = '\0';
@@ -428,7 +428,7 @@ int autofs4_wait(struct autofs_sb_info *sbi,
 			return -ENOMEM;
 		}
 
-		wq->wait_queue_entry_token = autofs4_next_wait_queue;
+		wq->wait_queue_token = autofs4_next_wait_queue;
 		if (++autofs4_next_wait_queue == 0)
 			autofs4_next_wait_queue = 1;
 		wq->next = sbi->queues;
@@ -461,7 +461,7 @@ int autofs4_wait(struct autofs_sb_info *sbi,
 		}
 
 		pr_debug("new wait id = 0x%08lx, name = %.*s, nfy=%d\n",
-			 (unsigned long) wq->wait_queue_entry_token, wq->name.len,
+			 (unsigned long) wq->wait_queue_token, wq->name.len,
 			 wq->name.name, notify);
 
 		/*
@@ -471,7 +471,7 @@ int autofs4_wait(struct autofs_sb_info *sbi,
 	} else {
 		wq->wait_ctr++;
 		pr_debug("existing wait id = 0x%08lx, name = %.*s, nfy=%d\n",
-			 (unsigned long) wq->wait_queue_entry_token, wq->name.len,
+			 (unsigned long) wq->wait_queue_token, wq->name.len,
 			 wq->name.name, notify);
 		mutex_unlock(&sbi->wq_mutex);
 		kfree(qstr.name);
@@ -550,13 +550,13 @@ int autofs4_wait(struct autofs_sb_info *sbi,
 }
 
 
-int autofs4_wait_release(struct autofs_sb_info *sbi, autofs_wqt_t wait_queue_entry_token, int status)
+int autofs4_wait_release(struct autofs_sb_info *sbi, autofs_wqt_t wait_queue_token, int status)
 {
 	struct autofs_wait_queue *wq, **wql;
 
 	mutex_lock(&sbi->wq_mutex);
 	for (wql = &sbi->queues; (wq = *wql) != NULL; wql = &wq->next) {
-		if (wq->wait_queue_entry_token == wait_queue_entry_token)
+		if (wq->wait_queue_token == wait_queue_token)
 			break;
 	}
 
diff --git a/include/uapi/linux/auto_fs.h b/include/uapi/linux/auto_fs.h
index 1953f8d6063b..aa63451ef20a 100644
--- a/include/uapi/linux/auto_fs.h
+++ b/include/uapi/linux/auto_fs.h
@@ -26,7 +26,7 @@
 #define AUTOFS_MIN_PROTO_VERSION	AUTOFS_PROTO_VERSION
 
 /*
- * The wait_queue_entry_token (autofs_wqt_t) is part of a structure which is passed
+ * The wait_queue_token (autofs_wqt_t) is part of a structure which is passed
  * back to the kernel via ioctl from userspace. On architectures where 32- and
  * 64-bit userspace binaries can be executed it's important that the size of
  * autofs_wqt_t stays constant between 32- and 64-bit Linux kernels so that we
@@ -49,7 +49,7 @@ struct autofs_packet_hdr {
 
 struct autofs_packet_missing {
 	struct autofs_packet_hdr hdr;
-	autofs_wqt_t wait_queue_entry_token;
+	autofs_wqt_t wait_queue_token;
 	int len;
 	char name[NAME_MAX+1];
 };	
diff --git a/include/uapi/linux/auto_fs4.h b/include/uapi/linux/auto_fs4.h
index 65b72d0222e7..7c6da423d54e 100644
--- a/include/uapi/linux/auto_fs4.h
+++ b/include/uapi/linux/auto_fs4.h
@@ -108,7 +108,7 @@ enum autofs_notify {
 /* v4 multi expire (via pipe) */
 struct autofs_packet_expire_multi {
 	struct autofs_packet_hdr hdr;
-	autofs_wqt_t wait_queue_entry_token;
+	autofs_wqt_t wait_queue_token;
 	int len;
 	char name[NAME_MAX+1];
 };
@@ -123,7 +123,7 @@ union autofs_packet_union {
 /* autofs v5 common packet struct */
 struct autofs_v5_packet {
 	struct autofs_packet_hdr hdr;
-	autofs_wqt_t wait_queue_entry_token;
+	autofs_wqt_t wait_queue_token;
 	__u32 dev;
 	__u64 ino;
 	__u32 uid;
-- 
cgit v1.2.3


From 23955622ff8d231bcc9650b3d06583f117a6e3ba Mon Sep 17 00:00:00 2001
From: Shaohua Li <shli@fb.com>
Date: Mon, 10 Jul 2017 15:47:11 -0700
Subject: swap: add block io poll in swapin path

For fast flash disk, async IO could introduce overhead because of
context switch.  block-mq now supports IO poll, which improves
performance and latency a lot.  swapin is a good place to use this
technique, because the task is waiting for the swapin page to continue
execution.

In my virtual machine, directly read 4k data from a NVMe with iopoll is
about 60% better than that without poll.  With iopoll support in swapin
patch, my microbenchmark (a task does random memory write) is about
10%~25% faster.  CPU utilization increases a lot though, 2x and even 3x
CPU utilization.  This will depend on disk speed.

While iopoll in swapin isn't intended for all usage cases, it's a win
for latency sensistive workloads with high speed swap disk.  block layer
has knob to control poll in runtime.  If poll isn't enabled in block
layer, there should be no noticeable change in swapin.

I got a chance to run the same test in a NVMe with DRAM as the media.
In simple fio IO test, blkpoll boosts 50% performance in single thread
test and ~20% in 8 threads test.  So this is the base line.  In above
swap test, blkpoll boosts ~27% performance in single thread test.
blkpoll uses 2x CPU time though.

If we enable hybid polling, the performance gain has very slight drop
but CPU time is only 50% worse than that without blkpoll.  Also we can
adjust parameter of hybid poll, with it, the CPU time penality is
reduced further.  In 8 threads test, blkpoll doesn't help though.  The
performance is similar to that without blkpoll, but cpu utilization is
similar too.  There is lock contention in swap path.  The cpu time
spending on blkpoll isn't high.  So overall, blkpoll swapin isn't worse
than that without it.

The swapin readahead might read several pages in in the same time and
form a big IO request.  Since the IO will take longer time, it doesn't
make sense to do poll, so the patch only does iopoll for single page
swapin.

[akpm@linux-foundation.org: coding-style fixes]
Link: http://lkml.kernel.org/r/070c3c3e40b711e7b1390002c991e86a-b5408f0@7511894063d3764ff01ea8111f5a004d7dd700ed078797c204a24e620ddb965c
Signed-off-by: Shaohua Li <shli@fb.com>
Cc: Tim Chen <tim.c.chen@intel.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Jens Axboe <axboe@fb.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/swap.h |  5 +++--
 mm/madvise.c         |  4 ++--
 mm/page_io.c         | 23 +++++++++++++++++++++--
 mm/swap_state.c      | 10 ++++++----
 mm/swapfile.c        |  2 +-
 5 files changed, 33 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 5ab1c98c7d27..61e7180cee21 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -331,7 +331,7 @@ extern void kswapd_stop(int nid);
 #include <linux/blk_types.h> /* for bio_end_io_t */
 
 /* linux/mm/page_io.c */
-extern int swap_readpage(struct page *);
+extern int swap_readpage(struct page *page, bool do_poll);
 extern int swap_writepage(struct page *page, struct writeback_control *wbc);
 extern void end_swap_bio_write(struct bio *bio);
 extern int __swap_writepage(struct page *page, struct writeback_control *wbc,
@@ -362,7 +362,8 @@ extern void free_page_and_swap_cache(struct page *);
 extern void free_pages_and_swap_cache(struct page **, int);
 extern struct page *lookup_swap_cache(swp_entry_t);
 extern struct page *read_swap_cache_async(swp_entry_t, gfp_t,
-			struct vm_area_struct *vma, unsigned long addr);
+			struct vm_area_struct *vma, unsigned long addr,
+			bool do_poll);
 extern struct page *__read_swap_cache_async(swp_entry_t, gfp_t,
 			struct vm_area_struct *vma, unsigned long addr,
 			bool *new_page_allocated);
diff --git a/mm/madvise.c b/mm/madvise.c
index 25b78ee4fc2c..8eda1841c576 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -205,7 +205,7 @@ static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start,
 			continue;
 
 		page = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE,
-								vma, index);
+							vma, index, false);
 		if (page)
 			put_page(page);
 	}
@@ -246,7 +246,7 @@ static void force_shm_swapin_readahead(struct vm_area_struct *vma,
 		}
 		swap = radix_to_swp_entry(page);
 		page = read_swap_cache_async(swap, GFP_HIGHUSER_MOVABLE,
-								NULL, 0);
+							NULL, 0, false);
 		if (page)
 			put_page(page);
 	}
diff --git a/mm/page_io.c b/mm/page_io.c
index 2da71e627812..b6c4ac388209 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -117,6 +117,7 @@ static void swap_slot_free_notify(struct page *page)
 static void end_swap_bio_read(struct bio *bio)
 {
 	struct page *page = bio->bi_io_vec[0].bv_page;
+	struct task_struct *waiter = bio->bi_private;
 
 	if (bio->bi_status) {
 		SetPageError(page);
@@ -132,7 +133,9 @@ static void end_swap_bio_read(struct bio *bio)
 	swap_slot_free_notify(page);
 out:
 	unlock_page(page);
+	WRITE_ONCE(bio->bi_private, NULL);
 	bio_put(bio);
+	wake_up_process(waiter);
 }
 
 int generic_swapfile_activate(struct swap_info_struct *sis,
@@ -329,11 +332,13 @@ out:
 	return ret;
 }
 
-int swap_readpage(struct page *page)
+int swap_readpage(struct page *page, bool do_poll)
 {
 	struct bio *bio;
 	int ret = 0;
 	struct swap_info_struct *sis = page_swap_info(page);
+	blk_qc_t qc;
+	struct block_device *bdev;
 
 	VM_BUG_ON_PAGE(!PageSwapCache(page), page);
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
@@ -372,9 +377,23 @@ int swap_readpage(struct page *page)
 		ret = -ENOMEM;
 		goto out;
 	}
+	bdev = bio->bi_bdev;
+	bio->bi_private = current;
 	bio_set_op_attrs(bio, REQ_OP_READ, 0);
 	count_vm_event(PSWPIN);
-	submit_bio(bio);
+	bio_get(bio);
+	qc = submit_bio(bio);
+	while (do_poll) {
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		if (!READ_ONCE(bio->bi_private))
+			break;
+
+		if (!blk_mq_poll(bdev_get_queue(bdev), qc))
+			break;
+	}
+	__set_current_state(TASK_RUNNING);
+	bio_put(bio);
+
 out:
 	return ret;
 }
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 9c71b6b2562f..b68c93014f50 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -412,14 +412,14 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
  * the swap entry is no longer in use.
  */
 struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
-			struct vm_area_struct *vma, unsigned long addr)
+		struct vm_area_struct *vma, unsigned long addr, bool do_poll)
 {
 	bool page_was_allocated;
 	struct page *retpage = __read_swap_cache_async(entry, gfp_mask,
 			vma, addr, &page_was_allocated);
 
 	if (page_was_allocated)
-		swap_readpage(retpage);
+		swap_readpage(retpage, do_poll);
 
 	return retpage;
 }
@@ -496,11 +496,13 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
 	unsigned long start_offset, end_offset;
 	unsigned long mask;
 	struct blk_plug plug;
+	bool do_poll = true;
 
 	mask = swapin_nr_pages(offset) - 1;
 	if (!mask)
 		goto skip;
 
+	do_poll = false;
 	/* Read a page_cluster sized and aligned cluster around offset. */
 	start_offset = offset & ~mask;
 	end_offset = offset | mask;
@@ -511,7 +513,7 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
 	for (offset = start_offset; offset <= end_offset ; offset++) {
 		/* Ok, do the async read-ahead now */
 		page = read_swap_cache_async(swp_entry(swp_type(entry), offset),
-						gfp_mask, vma, addr);
+						gfp_mask, vma, addr, false);
 		if (!page)
 			continue;
 		if (offset != entry_offset && likely(!PageTransCompound(page)))
@@ -522,7 +524,7 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
 
 	lru_add_drain();	/* Push any new pages onto the LRU now */
 skip:
-	return read_swap_cache_async(entry, gfp_mask, vma, addr);
+	return read_swap_cache_async(entry, gfp_mask, vma, addr, do_poll);
 }
 
 int init_swap_address_space(unsigned int type, unsigned long nr_pages)
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 811d90e1c929..6ba4aab2db0b 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1868,7 +1868,7 @@ int try_to_unuse(unsigned int type, bool frontswap,
 		swap_map = &si->swap_map[i];
 		entry = swp_entry(type, i);
 		page = read_swap_cache_async(entry,
-					GFP_HIGHUSER_MOVABLE, NULL, 0);
+					GFP_HIGHUSER_MOVABLE, NULL, 0, false);
 		if (!page) {
 			/*
 			 * Either swap_duplicate() failed because entry
-- 
cgit v1.2.3


From b37ff71cc626a0c1b5e098ff9a0b723815f6aaeb Mon Sep 17 00:00:00 2001
From: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Date: Mon, 10 Jul 2017 15:47:38 -0700
Subject: mm: hwpoison: change PageHWPoison behavior on hugetlb pages

We'd like to narrow down the error region in memory error on hugetlb
pages.  However, currently we set PageHWPoison flags on all subpages in
the error hugepage and add # of subpages to num_hwpoison_pages, which
doesn't fit our purpose.

So this patch changes the behavior and we only set PageHWPoison on the
head page then increase num_hwpoison_pages only by 1.  This is a
preparation for narrow-down part which comes in later patches.

Link: http://lkml.kernel.org/r/1496305019-5493-4-git-send-email-n-horiguchi@ah.jp.nec.com
Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: Anshuman Khandual <khandual@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/swapops.h |  9 -----
 mm/memory-failure.c     | 87 ++++++++++++++-----------------------------------
 2 files changed, 24 insertions(+), 72 deletions(-)

(limited to 'include')

diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index 5c3a5f3e7eec..c5ff7b217ee6 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -196,15 +196,6 @@ static inline void num_poisoned_pages_dec(void)
 	atomic_long_dec(&num_poisoned_pages);
 }
 
-static inline void num_poisoned_pages_add(long num)
-{
-	atomic_long_add(num, &num_poisoned_pages);
-}
-
-static inline void num_poisoned_pages_sub(long num)
-{
-	atomic_long_sub(num, &num_poisoned_pages);
-}
 #else
 
 static inline swp_entry_t make_hwpoison_entry(struct page *page)
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index e3bf6432ed25..a9ddb0e72f5b 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1009,22 +1009,6 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	return unmap_success;
 }
 
-static void set_page_hwpoison_huge_page(struct page *hpage)
-{
-	int i;
-	int nr_pages = 1 << compound_order(hpage);
-	for (i = 0; i < nr_pages; i++)
-		SetPageHWPoison(hpage + i);
-}
-
-static void clear_page_hwpoison_huge_page(struct page *hpage)
-{
-	int i;
-	int nr_pages = 1 << compound_order(hpage);
-	for (i = 0; i < nr_pages; i++)
-		ClearPageHWPoison(hpage + i);
-}
-
 /**
  * memory_failure - Handle memory failure of a page.
  * @pfn: Page Number of the corrupted page
@@ -1050,7 +1034,6 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	struct page *hpage;
 	struct page *orig_head;
 	int res;
-	unsigned int nr_pages;
 	unsigned long page_flags;
 
 	if (!sysctl_memory_failure_recovery)
@@ -1064,24 +1047,23 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 
 	p = pfn_to_page(pfn);
 	orig_head = hpage = compound_head(p);
+
+	/* tmporary check code, to be updated in later patches */
+	if (PageHuge(p)) {
+		if (TestSetPageHWPoison(hpage)) {
+			pr_err("Memory failure: %#lx: already hardware poisoned\n", pfn);
+			return 0;
+		}
+		goto tmp;
+	}
 	if (TestSetPageHWPoison(p)) {
 		pr_err("Memory failure: %#lx: already hardware poisoned\n",
 			pfn);
 		return 0;
 	}
 
-	/*
-	 * Currently errors on hugetlbfs pages are measured in hugepage units,
-	 * so nr_pages should be 1 << compound_order.  OTOH when errors are on
-	 * transparent hugepages, they are supposed to be split and error
-	 * measurement is done in normal page units.  So nr_pages should be one
-	 * in this case.
-	 */
-	if (PageHuge(p))
-		nr_pages = 1 << compound_order(hpage);
-	else /* normal page or thp */
-		nr_pages = 1;
-	num_poisoned_pages_add(nr_pages);
+tmp:
+	num_poisoned_pages_inc();
 
 	/*
 	 * We need/can do nothing about count=0 pages.
@@ -1109,12 +1091,11 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 			if (PageHWPoison(hpage)) {
 				if ((hwpoison_filter(p) && TestClearPageHWPoison(p))
 				    || (p != hpage && TestSetPageHWPoison(hpage))) {
-					num_poisoned_pages_sub(nr_pages);
+					num_poisoned_pages_dec();
 					unlock_page(hpage);
 					return 0;
 				}
 			}
-			set_page_hwpoison_huge_page(hpage);
 			res = dequeue_hwpoisoned_huge_page(hpage);
 			action_result(pfn, MF_MSG_FREE_HUGE,
 				      res ? MF_IGNORED : MF_DELAYED);
@@ -1137,7 +1118,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 				pr_err("Memory failure: %#lx: thp split failed\n",
 					pfn);
 			if (TestClearPageHWPoison(p))
-				num_poisoned_pages_sub(nr_pages);
+				num_poisoned_pages_dec();
 			put_hwpoison_page(p);
 			return -EBUSY;
 		}
@@ -1193,14 +1174,14 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	 */
 	if (!PageHWPoison(p)) {
 		pr_err("Memory failure: %#lx: just unpoisoned\n", pfn);
-		num_poisoned_pages_sub(nr_pages);
+		num_poisoned_pages_dec();
 		unlock_page(hpage);
 		put_hwpoison_page(hpage);
 		return 0;
 	}
 	if (hwpoison_filter(p)) {
 		if (TestClearPageHWPoison(p))
-			num_poisoned_pages_sub(nr_pages);
+			num_poisoned_pages_dec();
 		unlock_page(hpage);
 		put_hwpoison_page(hpage);
 		return 0;
@@ -1219,14 +1200,6 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 		put_hwpoison_page(hpage);
 		return 0;
 	}
-	/*
-	 * Set PG_hwpoison on all pages in an error hugepage,
-	 * because containment is done in hugepage unit for now.
-	 * Since we have done TestSetPageHWPoison() for the head page with
-	 * page lock held, we can safely set PG_hwpoison bits on tail pages.
-	 */
-	if (PageHuge(p))
-		set_page_hwpoison_huge_page(hpage);
 
 	/*
 	 * It's very difficult to mess with pages currently under IO
@@ -1397,7 +1370,6 @@ int unpoison_memory(unsigned long pfn)
 	struct page *page;
 	struct page *p;
 	int freeit = 0;
-	unsigned int nr_pages;
 	static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL,
 					DEFAULT_RATELIMIT_BURST);
 
@@ -1442,8 +1414,6 @@ int unpoison_memory(unsigned long pfn)
 		return 0;
 	}
 
-	nr_pages = 1 << compound_order(page);
-
 	if (!get_hwpoison_page(p)) {
 		/*
 		 * Since HWPoisoned hugepage should have non-zero refcount,
@@ -1473,10 +1443,8 @@ int unpoison_memory(unsigned long pfn)
 	if (TestClearPageHWPoison(page)) {
 		unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n",
 				 pfn, &unpoison_rs);
-		num_poisoned_pages_sub(nr_pages);
+		num_poisoned_pages_dec();
 		freeit = 1;
-		if (PageHuge(page))
-			clear_page_hwpoison_huge_page(page);
 	}
 	unlock_page(page);
 
@@ -1608,14 +1576,10 @@ static int soft_offline_huge_page(struct page *page, int flags)
 			ret = -EIO;
 	} else {
 		/* overcommit hugetlb page will be freed to buddy */
-		if (PageHuge(page)) {
-			set_page_hwpoison_huge_page(hpage);
+		SetPageHWPoison(page);
+		if (PageHuge(page))
 			dequeue_hwpoisoned_huge_page(hpage);
-			num_poisoned_pages_add(1 << compound_order(hpage));
-		} else {
-			SetPageHWPoison(page);
-			num_poisoned_pages_inc();
-		}
+		num_poisoned_pages_inc();
 	}
 	return ret;
 }
@@ -1731,15 +1695,12 @@ static int soft_offline_in_use_page(struct page *page, int flags)
 
 static void soft_offline_free_page(struct page *page)
 {
-	if (PageHuge(page)) {
-		struct page *hpage = compound_head(page);
+	struct page *head = compound_head(page);
 
-		set_page_hwpoison_huge_page(hpage);
-		if (!dequeue_hwpoisoned_huge_page(hpage))
-			num_poisoned_pages_add(1 << compound_order(hpage));
-	} else {
-		if (!TestSetPageHWPoison(page))
-			num_poisoned_pages_inc();
+	if (!TestSetPageHWPoison(head)) {
+		num_poisoned_pages_inc();
+		if (PageHuge(head))
+			dequeue_hwpoisoned_huge_page(head);
 	}
 }
 
-- 
cgit v1.2.3


From c3114a84f7f96c9d5c73c8bfa7e21ff42fda97e2 Mon Sep 17 00:00:00 2001
From: Anshuman Khandual <khandual@linux.vnet.ibm.com>
Date: Mon, 10 Jul 2017 15:47:41 -0700
Subject: mm: hugetlb: soft-offline: dissolve source hugepage after successful
 migration

Currently hugepage migrated by soft-offline (i.e.  due to correctable
memory errors) is contained as a hugepage, which means many non-error
pages in it are unreusable, i.e.  wasted.

This patch solves this issue by dissolving source hugepages into buddy.
As done in previous patch, PageHWPoison is set only on a head page of
the error hugepage.  Then in dissoliving we move the PageHWPoison flag
to the raw error page so that all healthy subpages return back to buddy.

[arnd@arndb.de: fix warnings: replace some macros with inline functions]
  Link: http://lkml.kernel.org/r/20170609102544.2947326-1-arnd@arndb.de
Link: http://lkml.kernel.org/r/1496305019-5493-5-git-send-email-n-horiguchi@ah.jp.nec.com
Signed-off-by: Anshuman Khandual <khandual@linux.vnet.ibm.com>
Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/hugetlb.h | 31 +++++++++++++++++++++++++++----
 mm/hugetlb.c            | 10 +++++++++-
 mm/memory-failure.c     |  5 +----
 mm/migrate.c            |  2 ++
 4 files changed, 39 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 46bfb702e7d6..668ab1742ef6 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -472,6 +472,7 @@ static inline pgoff_t basepage_index(struct page *page)
 	return __basepage_index(page);
 }
 
+extern int dissolve_free_huge_page(struct page *page);
 extern int dissolve_free_huge_pages(unsigned long start_pfn,
 				    unsigned long end_pfn);
 static inline bool hugepage_migration_supported(struct hstate *h)
@@ -550,15 +551,37 @@ static inline unsigned int pages_per_huge_page(struct hstate *h)
 {
 	return 1;
 }
-#define hstate_index_to_shift(index) 0
-#define hstate_index(h) 0
+
+static inline unsigned hstate_index_to_shift(unsigned index)
+{
+	return 0;
+}
+
+static inline int hstate_index(struct hstate *h)
+{
+	return 0;
+}
 
 static inline pgoff_t basepage_index(struct page *page)
 {
 	return page->index;
 }
-#define dissolve_free_huge_pages(s, e)	0
-#define hugepage_migration_supported(h)	false
+
+static inline int dissolve_free_huge_page(struct page *page)
+{
+	return 0;
+}
+
+static inline int dissolve_free_huge_pages(unsigned long start_pfn,
+					   unsigned long end_pfn)
+{
+	return 0;
+}
+
+static inline bool hugepage_migration_supported(struct hstate *h)
+{
+	return false;
+}
 
 static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
 					   struct mm_struct *mm, pte_t *pte)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 41a1b48cefbf..b2d44363837a 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1459,7 +1459,7 @@ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
  * number of free hugepages would be reduced below the number of reserved
  * hugepages.
  */
-static int dissolve_free_huge_page(struct page *page)
+int dissolve_free_huge_page(struct page *page)
 {
 	int rc = 0;
 
@@ -1472,6 +1472,14 @@ static int dissolve_free_huge_page(struct page *page)
 			rc = -EBUSY;
 			goto out;
 		}
+		/*
+		 * Move PageHWPoison flag from head page to the raw error page,
+		 * which makes any subpages rather than the error page reusable.
+		 */
+		if (PageHWPoison(head) && page != head) {
+			SetPageHWPoison(page);
+			ClearPageHWPoison(head);
+		}
 		list_del(&head->lru);
 		h->free_huge_pages--;
 		h->free_huge_pages_node[nid]--;
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index a9ddb0e72f5b..42c5803e6275 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1575,11 +1575,8 @@ static int soft_offline_huge_page(struct page *page, int flags)
 		if (ret > 0)
 			ret = -EIO;
 	} else {
-		/* overcommit hugetlb page will be freed to buddy */
-		SetPageHWPoison(page);
 		if (PageHuge(page))
-			dequeue_hwpoisoned_huge_page(hpage);
-		num_poisoned_pages_inc();
+			dissolve_free_huge_page(page);
 	}
 	return ret;
 }
diff --git a/mm/migrate.c b/mm/migrate.c
index 051cc1555d36..8935cbe362ce 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1252,6 +1252,8 @@ put_anon:
 out:
 	if (rc != -EAGAIN)
 		putback_active_hugepage(hpage);
+	if (reason == MR_MEMORY_FAILURE && !test_set_page_hwpoison(hpage))
+		num_poisoned_pages_inc();
 
 	/*
 	 * If migration was not successful and there's a freeing callback, use
-- 
cgit v1.2.3


From ddd40d8a2c4ef8f2152ea6d227e11475cf7e5bfa Mon Sep 17 00:00:00 2001
From: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Date: Mon, 10 Jul 2017 15:47:53 -0700
Subject: mm: hugetlb: delete dequeue_hwpoisoned_huge_page()

dequeue_hwpoisoned_huge_page() is no longer used, so let's remove it.

Link: http://lkml.kernel.org/r/1496305019-5493-9-git-send-email-n-horiguchi@ah.jp.nec.com
Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/hugetlb.h |  5 -----
 mm/hugetlb.c            | 34 ----------------------------------
 mm/memory-failure.c     | 11 -----------
 3 files changed, 50 deletions(-)

(limited to 'include')

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 668ab1742ef6..57f700ac127e 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -116,7 +116,6 @@ int hugetlb_reserve_pages(struct inode *inode, long from, long to,
 						vm_flags_t vm_flags);
 long hugetlb_unreserve_pages(struct inode *inode, long start, long end,
 						long freed);
-int dequeue_hwpoisoned_huge_page(struct page *page);
 bool isolate_huge_page(struct page *page, struct list_head *list);
 void putback_active_hugepage(struct page *page);
 void free_huge_page(struct page *page);
@@ -192,10 +191,6 @@ static inline void hugetlb_show_meminfo(void)
 #define hugetlb_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, dst_addr, \
 				src_addr, pagep)	({ BUG(); 0; })
 #define huge_pte_offset(mm, address, sz)	0
-static inline int dequeue_hwpoisoned_huge_page(struct page *page)
-{
-	return 0;
-}
 
 static inline bool isolate_huge_page(struct page *page, struct list_head *list)
 {
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index b2d44363837a..8254e8f6db6b 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4746,40 +4746,6 @@ follow_huge_pgd(struct mm_struct *mm, unsigned long address, pgd_t *pgd, int fla
 	return pte_page(*(pte_t *)pgd) + ((address & ~PGDIR_MASK) >> PAGE_SHIFT);
 }
 
-#ifdef CONFIG_MEMORY_FAILURE
-
-/*
- * This function is called from memory failure code.
- */
-int dequeue_hwpoisoned_huge_page(struct page *hpage)
-{
-	struct hstate *h = page_hstate(hpage);
-	int nid = page_to_nid(hpage);
-	int ret = -EBUSY;
-
-	spin_lock(&hugetlb_lock);
-	/*
-	 * Just checking !page_huge_active is not enough, because that could be
-	 * an isolated/hwpoisoned hugepage (which have >0 refcount).
-	 */
-	if (!page_huge_active(hpage) && !page_count(hpage)) {
-		/*
-		 * Hwpoisoned hugepage isn't linked to activelist or freelist,
-		 * but dangling hpage->lru can trigger list-debug warnings
-		 * (this happens when we call unpoison_memory() on it),
-		 * so let it point to itself with list_del_init().
-		 */
-		list_del_init(&hpage->lru);
-		set_page_refcounted(hpage);
-		h->free_huge_pages--;
-		h->free_huge_pages_node[nid]--;
-		ret = 0;
-	}
-	spin_unlock(&hugetlb_lock);
-	return ret;
-}
-#endif
-
 bool isolate_huge_page(struct page *page, struct list_head *list)
 {
 	bool ret = true;
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 6f8f69f4a986..2aec57c07652 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1458,17 +1458,6 @@ int unpoison_memory(unsigned long pfn)
 	}
 
 	if (!get_hwpoison_page(p)) {
-		/*
-		 * Since HWPoisoned hugepage should have non-zero refcount,
-		 * race between memory failure and unpoison seems to happen.
-		 * In such case unpoison fails and memory failure runs
-		 * to the end.
-		 */
-		if (PageHuge(page)) {
-			unpoison_pr_info("Unpoison: Memory failure is now running on free hugepage %#lx\n",
-					 pfn, &unpoison_rs);
-			return 0;
-		}
 		if (TestClearPageHWPoison(p))
 			num_poisoned_pages_dec();
 		unpoison_pr_info("Unpoison: Software-unpoisoned free page %#lx\n",
-- 
cgit v1.2.3


From 1860033237d4be09c5d7382585f0c7229367a534 Mon Sep 17 00:00:00 2001
From: Michal Hocko <mhocko@suse.com>
Date: Mon, 10 Jul 2017 15:48:02 -0700
Subject: mm: make PR_SET_THP_DISABLE immediately active

PR_SET_THP_DISABLE has a rather subtle semantic.  It doesn't affect any
existing mapping because it only updated mm->def_flags which is a
template for new mappings.

The mappings created after prctl(PR_SET_THP_DISABLE) have VM_NOHUGEPAGE
flag set.  This can be quite surprising for all those applications which
do not do prctl(); fork() & exec() and want to control their own THP
behavior.

Another usecase when the immediate semantic of the prctl might be useful
is a combination of pre- and post-copy migration of containers with
CRIU.  In this case CRIU populates a part of a memory region with data
that was saved during the pre-copy stage.  Afterwards, the region is
registered with userfaultfd and CRIU expects to get page faults for the
parts of the region that were not yet populated.  However, khugepaged
collapses the pages and the expected page faults do not occur.

In more general case, the prctl(PR_SET_THP_DISABLE) could be used as a
temporary mechanism for enabling/disabling THP process wide.

Implementation wise, a new MMF_DISABLE_THP flag is added.  This flag is
tested when decision whether to use huge pages is taken either during
page fault of at the time of THP collapse.

It should be noted, that the new implementation makes PR_SET_THP_DISABLE
master override to any per-VMA setting, which was not the case
previously.

Fixes: a0715cc22601 ("mm, thp: add VM_INIT_DEF_MASK and PRCTL_THP_DISABLE")
Link: http://lkml.kernel.org/r/1496415802-30944-1-git-send-email-rppt@linux.vnet.ibm.com
Signed-off-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Pavel Emelyanov <xemul@virtuozzo.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/huge_mm.h        | 1 +
 include/linux/khugepaged.h     | 3 ++-
 include/linux/sched/coredump.h | 5 ++++-
 kernel/sys.c                   | 6 +++---
 mm/khugepaged.c                | 3 ++-
 mm/shmem.c                     | 8 +++++---
 6 files changed, 17 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index d3b3e8fcc717..40d7b7dd2653 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -92,6 +92,7 @@ extern bool is_vma_temporary_stack(struct vm_area_struct *vma);
 	   (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG) &&			\
 	   ((__vma)->vm_flags & VM_HUGEPAGE))) &&			\
 	 !((__vma)->vm_flags & VM_NOHUGEPAGE) &&			\
+	 !test_bit(MMF_DISABLE_THP, &(__vma)->vm_mm->flags) &&		\
 	 !is_vma_temporary_stack(__vma))
 #define transparent_hugepage_use_zero_page()				\
 	(transparent_hugepage_flags &					\
diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h
index 5d9a400af509..f0d7335336cd 100644
--- a/include/linux/khugepaged.h
+++ b/include/linux/khugepaged.h
@@ -48,7 +48,8 @@ static inline int khugepaged_enter(struct vm_area_struct *vma,
 	if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags))
 		if ((khugepaged_always() ||
 		     (khugepaged_req_madv() && (vm_flags & VM_HUGEPAGE))) &&
-		    !(vm_flags & VM_NOHUGEPAGE))
+		    !(vm_flags & VM_NOHUGEPAGE) &&
+		    !test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))
 			if (__khugepaged_enter(vma->vm_mm))
 				return -ENOMEM;
 	return 0;
diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h
index 69eedcef8f03..98ae0d05aa32 100644
--- a/include/linux/sched/coredump.h
+++ b/include/linux/sched/coredump.h
@@ -68,7 +68,10 @@ static inline int get_dumpable(struct mm_struct *mm)
 #define MMF_OOM_SKIP		21	/* mm is of no interest for the OOM killer */
 #define MMF_UNSTABLE		22	/* mm is unstable for copy_from_user */
 #define MMF_HUGE_ZERO_PAGE	23      /* mm has ever used the global huge zero page */
+#define MMF_DISABLE_THP		24	/* disable THP for all VMAs */
+#define MMF_DISABLE_THP_MASK	(1 << MMF_DISABLE_THP)
 
-#define MMF_INIT_MASK		(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK)
+#define MMF_INIT_MASK		(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\
+				 MMF_DISABLE_THP_MASK)
 
 #endif /* _LINUX_SCHED_COREDUMP_H */
diff --git a/kernel/sys.c b/kernel/sys.c
index 47d901586b4e..73fc0af147d0 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2360,7 +2360,7 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 	case PR_GET_THP_DISABLE:
 		if (arg2 || arg3 || arg4 || arg5)
 			return -EINVAL;
-		error = !!(me->mm->def_flags & VM_NOHUGEPAGE);
+		error = !!test_bit(MMF_DISABLE_THP, &me->mm->flags);
 		break;
 	case PR_SET_THP_DISABLE:
 		if (arg3 || arg4 || arg5)
@@ -2368,9 +2368,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 		if (down_write_killable(&me->mm->mmap_sem))
 			return -EINTR;
 		if (arg2)
-			me->mm->def_flags |= VM_NOHUGEPAGE;
+			set_bit(MMF_DISABLE_THP, &me->mm->flags);
 		else
-			me->mm->def_flags &= ~VM_NOHUGEPAGE;
+			clear_bit(MMF_DISABLE_THP, &me->mm->flags);
 		up_write(&me->mm->mmap_sem);
 		break;
 	case PR_MPX_ENABLE_MANAGEMENT:
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index df4ebdb2b10a..c01f177a1120 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -816,7 +816,8 @@ khugepaged_alloc_page(struct page **hpage, gfp_t gfp, int node)
 static bool hugepage_vma_check(struct vm_area_struct *vma)
 {
 	if ((!(vma->vm_flags & VM_HUGEPAGE) && !khugepaged_always()) ||
-	    (vma->vm_flags & VM_NOHUGEPAGE))
+	    (vma->vm_flags & VM_NOHUGEPAGE) ||
+	    test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))
 		return false;
 	if (shmem_file(vma->vm_file)) {
 		if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE))
diff --git a/mm/shmem.c b/mm/shmem.c
index 9418f5a9bc46..b0aa6075d164 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1977,10 +1977,12 @@ static int shmem_fault(struct vm_fault *vmf)
 	}
 
 	sgp = SGP_CACHE;
-	if (vma->vm_flags & VM_HUGEPAGE)
-		sgp = SGP_HUGE;
-	else if (vma->vm_flags & VM_NOHUGEPAGE)
+
+	if ((vma->vm_flags & VM_NOHUGEPAGE) ||
+	    test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))
 		sgp = SGP_NOHUGE;
+	else if (vma->vm_flags & VM_HUGEPAGE)
+		sgp = SGP_HUGE;
 
 	error = shmem_getpage_gfp(inode, vmf->pgoff, &vmf->page, sgp,
 				  gfp, vma, vmf, &ret);
-- 
cgit v1.2.3


From 7ab0e50ad0831e714dcdc3de44a7fe3887732b7c Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Mon, 10 Jul 2017 15:48:18 -0700
Subject: oom, trace: remove ENUM evaluation of COMPACTION_FEEDBACK

After enabling CONFIG_TRACE_ENUM_MAP_FILE (which will soon be renamed to
CONFIG_TRACE_EVAL_MAP_FILE), I am able to examine the enums that have
been evaluated:

 # cat /sys/kernel/debug/tracing/enum_map

(which will soon be renamed to eval_map)

And it showed some interesting results:

  [..]
  ZONE_MOVABLE 3 (oom)
  ZONE_NORMAL 2 (oom)
  ZONE_DMA32 1 (oom)
  ZONE_DMA 0 (oom)
  3 3 (oom)
  2 2 (oom)
  1 1 (oom)
  COMPACT_PRIO_ASYNC 2 (oom)
  COMPACT_PRIO_SYNC_LIGHT 1 (oom)
  COMPACT_PRIO_SYNC_FULL 0 (oom)
  [..]
  ZONE_DMA 0 (vmscan)
  3 3 (vmscan)
  2 2 (vmscan)
  1 1 (vmscan)
  COMPACT_PRIO_ASYNC 2 (vmscan)
  [..]
  ZONE_DMA 0 (kmem)
  3 3 (kmem)
  2 2 (kmem)
  1 1 (kmem)
  COMPACT_PRIO_ASYNC 2 (kmem)
  [..]
  ZONE_DMA 0 (compaction)
  3 3 (compaction)
  2 2 (compaction)
  1 1 (compaction)
  COMPACT_PRIO_ASYNC 2 (compaction)
  [..]

The name within the parenthesis are the trace systems that the enum/eval
maps are associated with. When there's a number evaluated to another
number, that tells me that the TRACE_DEFINE_ENUM() was used on a #define
and not an enum. As #defines get converted normally, they are not needed
to be evaluated.

Each of the above trace systems with the number to number evaluation
included the file include/trace/events/mmflags.h which has:

 /* High-level compaction status feedback */
 #define COMPACTION_FAILED       1
 #define COMPACTION_WITHDRAWN    2
 #define COMPACTION_PROGRESS     3

[..]

 #define COMPACTION_FEEDBACK             \
        EM(COMPACTION_FAILED,           "failed")       \
        EM(COMPACTION_WITHDRAWN,        "withdrawn")    \
        EMe(COMPACTION_PROGRESS,        "progress")

Which is still needed for the __print_symbolic() usage in the
trace_event.  But it is not needed to be evaluated.

Removing the evaluation part removes the unnecessary evaluations of
numbers to numbers.

Link: http://lkml.kernel.org/r/20170615074944.7be9a647@gandalf.local.home
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: David Rientjes <rientjes@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/trace/events/mmflags.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index 304ff94363b2..10e3663a75a6 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -257,7 +257,7 @@ IF_HAVE_VM_SOFTDIRTY(VM_SOFTDIRTY,	"softdirty"	)		\
 
 COMPACTION_STATUS
 COMPACTION_PRIORITY
-COMPACTION_FEEDBACK
+/* COMPACTION_FEEDBACK are defines not enums. Not needed here. */
 ZONE_TYPE
 LRU_NAMES
 
-- 
cgit v1.2.3


From 16981d763501c0e06e434cf6b59f964c520e0ccc Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Mon, 10 Jul 2017 15:48:22 -0700
Subject: mm: improve readability of transparent_hugepage_enabled()

Turn the macro into a static inline and rewrite the condition checks for
better readability in preparation for adding another condition.

[ross.zwisler@linux.intel.com: fix logic to make conversion equivalent]
[akpm@linux-foundation.org: resolve vs mm-make-pr_set_thp_disable-immediately-active.patch]
[akpm@linux-foundation.org: include coredump.h for MMF_DISABLE_THP]
Link: http://lkml.kernel.org/r/149739530612.20686.14760671150202647861.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Acked-by: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Jan Kara <jack@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/huge_mm.h | 41 +++++++++++++++++++++++++++++------------
 1 file changed, 29 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 40d7b7dd2653..f4239d3c9c73 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -1,6 +1,8 @@
 #ifndef _LINUX_HUGE_MM_H
 #define _LINUX_HUGE_MM_H
 
+#include <linux/sched/coredump.h>
+
 extern int do_huge_pmd_anonymous_page(struct vm_fault *vmf);
 extern int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 			 pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
@@ -85,15 +87,29 @@ extern struct kobj_attribute shmem_enabled_attr;
 
 extern bool is_vma_temporary_stack(struct vm_area_struct *vma);
 
-#define transparent_hugepage_enabled(__vma)				\
-	((transparent_hugepage_flags &					\
-	  (1<<TRANSPARENT_HUGEPAGE_FLAG) ||				\
-	  (transparent_hugepage_flags &					\
-	   (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG) &&			\
-	   ((__vma)->vm_flags & VM_HUGEPAGE))) &&			\
-	 !((__vma)->vm_flags & VM_NOHUGEPAGE) &&			\
-	 !test_bit(MMF_DISABLE_THP, &(__vma)->vm_mm->flags) &&		\
-	 !is_vma_temporary_stack(__vma))
+extern unsigned long transparent_hugepage_flags;
+
+static inline bool transparent_hugepage_enabled(struct vm_area_struct *vma)
+{
+	if (vma->vm_flags & VM_NOHUGEPAGE)
+		return false;
+
+	if (is_vma_temporary_stack(vma))
+		return false;
+
+	if (test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))
+		return false;
+
+	if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_FLAG))
+		return true;
+
+	if (transparent_hugepage_flags &
+				(1 << TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG))
+		return !!(vma->vm_flags & VM_HUGEPAGE);
+
+	return false;
+}
+
 #define transparent_hugepage_use_zero_page()				\
 	(transparent_hugepage_flags &					\
 	 (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG))
@@ -105,8 +121,6 @@ extern bool is_vma_temporary_stack(struct vm_area_struct *vma);
 #define transparent_hugepage_debug_cow() 0
 #endif /* CONFIG_DEBUG_VM */
 
-extern unsigned long transparent_hugepage_flags;
-
 extern unsigned long thp_get_unmapped_area(struct file *filp,
 		unsigned long addr, unsigned long len, unsigned long pgoff,
 		unsigned long flags);
@@ -225,7 +239,10 @@ void mm_put_huge_zero_page(struct mm_struct *mm);
 
 #define hpage_nr_pages(x) 1
 
-#define transparent_hugepage_enabled(__vma) 0
+static inline bool transparent_hugepage_enabled(struct vm_area_struct *vma)
+{
+	return false;
+}
 
 static inline void prep_transhuge_page(struct page *page) {}
 
-- 
cgit v1.2.3


From baabda261424517110ea98c6651f632ebf2561e3 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Mon, 10 Jul 2017 15:48:25 -0700
Subject: mm: always enable thp for dax mappings

The madvise policy for transparent huge pages is meant to avoid unwanted
allocations of transparent huge pages.  It allows a policy of disabling
the extra memory pressure and effort to arrange for a huge page when it
is not needed.

DAX by definition never incurs this overhead since it is statically
allocated.  The policy choice makes even less sense for device-dax which
tries to guarantee a given tlb-fault size.  Specifically, the following
setting:

	echo never > /sys/kernel/mm/transparent_hugepage/enabled

...violates that guarantee and silently disables all device-dax
instances with a 2M or 1G alignment.  So, let's avoid that non-obvious
side effect by force enabling thp for dax mappings in all cases.

It is worth noting that the reason this uses vma_is_dax(), and the
resulting header include changes, is that previous attempts to add a
VM_DAX flag were NAKd.

Link: http://lkml.kernel.org/r/149739531127.20686.15813586620597484283.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Christoph Hellwig <hch@lst.de>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Michal Hocko <mhocko@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/dax.h     | 5 -----
 include/linux/fs.h      | 6 ++++++
 include/linux/huge_mm.h | 5 +++++
 3 files changed, 11 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/dax.h b/include/linux/dax.h
index 8f39db7439c3..794811875732 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -154,11 +154,6 @@ static inline unsigned int dax_radix_order(void *entry)
 #endif
 int dax_pfn_mkwrite(struct vm_fault *vmf);
 
-static inline bool vma_is_dax(struct vm_area_struct *vma)
-{
-	return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host);
-}
-
 static inline bool dax_mapping(struct address_space *mapping)
 {
 	return mapping->host && IS_DAX(mapping->host);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 0cfa47125d52..78e1dbbe4cfd 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -18,6 +18,7 @@
 #include <linux/bug.h>
 #include <linux/mutex.h>
 #include <linux/rwsem.h>
+#include <linux/mm_types.h>
 #include <linux/capability.h>
 #include <linux/semaphore.h>
 #include <linux/fcntl.h>
@@ -3127,6 +3128,11 @@ static inline bool io_is_direct(struct file *filp)
 	return (filp->f_flags & O_DIRECT) || IS_DAX(filp->f_mapping->host);
 }
 
+static inline bool vma_is_dax(struct vm_area_struct *vma)
+{
+	return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host);
+}
+
 static inline int iocb_flags(struct file *file)
 {
 	int res = 0;
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index f4239d3c9c73..ee696347f928 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -3,6 +3,8 @@
 
 #include <linux/sched/coredump.h>
 
+#include <linux/fs.h> /* only for vma_is_dax() */
+
 extern int do_huge_pmd_anonymous_page(struct vm_fault *vmf);
 extern int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 			 pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
@@ -103,6 +105,9 @@ static inline bool transparent_hugepage_enabled(struct vm_area_struct *vma)
 	if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_FLAG))
 		return true;
 
+	if (vma_is_dax(vma))
+		return true;
+
 	if (transparent_hugepage_flags &
 				(1 << TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG))
 		return !!(vma->vm_flags & VM_HUGEPAGE);
-- 
cgit v1.2.3


From 108a7ac448caff8e35e8c3f92f65faad893e5aca Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Mon, 10 Jul 2017 15:48:28 -0700
Subject: include/linux/page_ref.h: ensure page_ref_unfreeze is ordered against
 prior accesses

page_ref_freeze and page_ref_unfreeze are designed to be used as a pair,
wrapping a critical section where struct pages can be modified without
having to worry about consistency for a concurrent fast-GUP.

Whilst page_ref_freeze has full barrier semantics due to its use of
atomic_cmpxchg, page_ref_unfreeze is implemented using atomic_set, which
doesn't provide any barrier semantics and allows the operation to be
reordered with respect to page modifications in the critical section.

This patch ensures that page_ref_unfreeze is ordered after any critical
section updates, by invoking smp_mb() prior to the atomic_set.

Link: http://lkml.kernel.org/r/1497349722-6731-3-git-send-email-will.deacon@arm.com
Signed-off-by: Will Deacon <will.deacon@arm.com>
Acked-by: Steve Capper <steve.capper@arm.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/page_ref.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h
index 610e13271918..1fd71733aa68 100644
--- a/include/linux/page_ref.h
+++ b/include/linux/page_ref.h
@@ -174,6 +174,7 @@ static inline void page_ref_unfreeze(struct page *page, int count)
 	VM_BUG_ON_PAGE(page_count(page) != 0, page);
 	VM_BUG_ON(count == 0);
 
+	smp_mb();
 	atomic_set(&page->_refcount, count);
 	if (page_ref_tracepoint_active(__tracepoint_page_ref_unfreeze))
 		__page_ref_unfreeze(page, count);
-- 
cgit v1.2.3


From 4db9b2efe94967be34e3b136a93251a3c1736dd5 Mon Sep 17 00:00:00 2001
From: Michal Hocko <mhocko@suse.com>
Date: Mon, 10 Jul 2017 15:48:44 -0700
Subject: hugetlb, memory_hotplug: prefer to use reserved pages for migration

new_node_page will try to use the origin's next NUMA node as the
migration destination for hugetlb pages.  If such a node doesn't have
any preallocated pool it falls back to __alloc_buddy_huge_page_no_mpol
to allocate a surplus page instead.  This is quite subotpimal for any
configuration when hugetlb pages are no distributed to all NUMA nodes
evenly.  Say we have a hotplugable node 4 and spare hugetlb pages are
node 0

  /sys/devices/system/node/node0/hugepages/hugepages-2048kB/nr_hugepages:10000
  /sys/devices/system/node/node1/hugepages/hugepages-2048kB/nr_hugepages:0
  /sys/devices/system/node/node2/hugepages/hugepages-2048kB/nr_hugepages:0
  /sys/devices/system/node/node3/hugepages/hugepages-2048kB/nr_hugepages:0
  /sys/devices/system/node/node4/hugepages/hugepages-2048kB/nr_hugepages:10000
  /sys/devices/system/node/node5/hugepages/hugepages-2048kB/nr_hugepages:0
  /sys/devices/system/node/node6/hugepages/hugepages-2048kB/nr_hugepages:0
  /sys/devices/system/node/node7/hugepages/hugepages-2048kB/nr_hugepages:0

Now we consume the whole pool on node 4 and try to offline this node.
All the allocated pages should be moved to node0 which has enough
preallocated pages to hold them.  With the current implementation
offlining very likely fails because hugetlb allocations during runtime
are much less reliable.

Fix this by reusing the nodemask which excludes migration source and try
to find a first node which has a page in the preallocated pool first and
fall back to __alloc_buddy_huge_page_no_mpol only when the whole pool is
consumed.

[akpm@linux-foundation.org: remove bogus arg from alloc_huge_page_nodemask() stub]
Link: http://lkml.kernel.org/r/20170608074553.22152-3-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Xishi Qiu <qiuxishi@huawei.com>
Cc: zhong jiang <zhongjiang@huawei.com>
Cc: Joonsoo Kim <js1304@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/hugetlb.h |  2 ++
 mm/hugetlb.c            | 27 +++++++++++++++++++++++++++
 mm/memory_hotplug.c     |  9 ++-------
 3 files changed, 31 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 57f700ac127e..8fd0725d3f30 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -349,6 +349,7 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,
 struct page *alloc_huge_page_node(struct hstate *h, int nid);
 struct page *alloc_huge_page_noerr(struct vm_area_struct *vma,
 				unsigned long addr, int avoid_reserve);
+struct page *alloc_huge_page_nodemask(struct hstate *h, const nodemask_t *nmask);
 int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
 			pgoff_t idx);
 
@@ -524,6 +525,7 @@ static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr
 struct hstate {};
 #define alloc_huge_page(v, a, r) NULL
 #define alloc_huge_page_node(h, nid) NULL
+#define alloc_huge_page_nodemask(h, nmask) NULL
 #define alloc_huge_page_noerr(v, a, r) NULL
 #define alloc_bootmem_huge_page(h) NULL
 #define hstate_file(f) NULL
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 761a669d0b62..01c11ceb47d6 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1723,6 +1723,33 @@ struct page *alloc_huge_page_node(struct hstate *h, int nid)
 	return page;
 }
 
+struct page *alloc_huge_page_nodemask(struct hstate *h, const nodemask_t *nmask)
+{
+	struct page *page = NULL;
+	int node;
+
+	spin_lock(&hugetlb_lock);
+	if (h->free_huge_pages - h->resv_huge_pages > 0) {
+		for_each_node_mask(node, *nmask) {
+			page = dequeue_huge_page_node_exact(h, node);
+			if (page)
+				break;
+		}
+	}
+	spin_unlock(&hugetlb_lock);
+	if (page)
+		return page;
+
+	/* No reservations, try to overcommit */
+	for_each_node_mask(node, *nmask) {
+		page = __alloc_buddy_huge_page_no_mpol(h, node);
+		if (page)
+			return page;
+	}
+
+	return NULL;
+}
+
 /*
  * Increase the hugetlb pool such that it can accommodate a reservation
  * of size 'delta'.
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index f42a8ef93ec4..1cf3404bd065 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1446,14 +1446,9 @@ static struct page *new_node_page(struct page *page, unsigned long private,
 	if (nodes_empty(nmask))
 		node_set(nid, nmask);
 
-	/*
-	 * TODO: allocate a destination hugepage from a nearest neighbor node,
-	 * accordance with memory policy of the user process if possible. For
-	 * now as a simple work-around, we use the next node for destination.
-	 */
 	if (PageHuge(page))
-		return alloc_huge_page_node(page_hstate(compound_head(page)),
-					next_node_in(nid, nmask));
+		return alloc_huge_page_nodemask(
+				page_hstate(compound_head(page)), &nmask);
 
 	if (PageHighMem(page)
 	    || (zone_idx(page_zone(page)) == ZONE_MOVABLE))
-- 
cgit v1.2.3


From 8b9132388964df2cfe151a88fd1dd8219dabf23c Mon Sep 17 00:00:00 2001
From: Michal Hocko <mhocko@suse.com>
Date: Mon, 10 Jul 2017 15:48:47 -0700
Subject: mm: unify new_node_page and alloc_migrate_target

Commit 394e31d2ceb4 ("mem-hotplug: alloc new page from a nearest
neighbor node when mem-offline") has duplicated a large part of
alloc_migrate_target with some hotplug specific special casing.

To be more precise it tried to enfore the allocation from a different
node than the original page.  As a result the two function diverged in
their shared logic, e.g.  the hugetlb allocation strategy.

Let's unify the two and express different NUMA requirements by the given
nodemask.  new_node_page will simply exclude the node it doesn't care
about and alloc_migrate_target will use all the available nodes.
alloc_migrate_target will then learn to migrate hugetlb pages more
sanely and use preallocated pool when possible.

Please note that alloc_migrate_target used to call alloc_page resp.
alloc_pages_current so the memory policy of the current context which is
quite strange when we consider that it is used in the context of
alloc_contig_range which just tries to migrate pages which stand in the
way.

Link: http://lkml.kernel.org/r/20170608074553.22152-4-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Xishi Qiu <qiuxishi@huawei.com>
Cc: zhong jiang <zhongjiang@huawei.com>
Cc: Joonsoo Kim <js1304@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/migrate.h | 16 ++++++++++++++++
 mm/memory_hotplug.c     | 11 +----------
 mm/page_isolation.c     | 18 ++----------------
 3 files changed, 19 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 48e24844b3c5..d9675b665cc4 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -4,6 +4,7 @@
 #include <linux/mm.h>
 #include <linux/mempolicy.h>
 #include <linux/migrate_mode.h>
+#include <linux/hugetlb.h>
 
 typedef struct page *new_page_t(struct page *page, unsigned long private,
 				int **reason);
@@ -30,6 +31,21 @@ enum migrate_reason {
 /* In mm/debug.c; also keep sync with include/trace/events/migrate.h */
 extern char *migrate_reason_names[MR_TYPES];
 
+static inline struct page *new_page_nodemask(struct page *page,
+				int preferred_nid, nodemask_t *nodemask)
+{
+	gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE;
+
+	if (PageHuge(page))
+		return alloc_huge_page_nodemask(page_hstate(compound_head(page)),
+				nodemask);
+
+	if (PageHighMem(page) || (zone_idx(page_zone(page)) == ZONE_MOVABLE))
+		gfp_mask |= __GFP_HIGHMEM;
+
+	return __alloc_pages_nodemask(gfp_mask, 0, preferred_nid, nodemask);
+}
+
 #ifdef CONFIG_MIGRATION
 
 extern void putback_movable_pages(struct list_head *l);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 1cf3404bd065..203c46306a74 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1433,7 +1433,6 @@ static unsigned long scan_movable_pages(unsigned long start, unsigned long end)
 static struct page *new_node_page(struct page *page, unsigned long private,
 		int **result)
 {
-	gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE;
 	int nid = page_to_nid(page);
 	nodemask_t nmask = node_states[N_MEMORY];
 
@@ -1446,15 +1445,7 @@ static struct page *new_node_page(struct page *page, unsigned long private,
 	if (nodes_empty(nmask))
 		node_set(nid, nmask);
 
-	if (PageHuge(page))
-		return alloc_huge_page_nodemask(
-				page_hstate(compound_head(page)), &nmask);
-
-	if (PageHighMem(page)
-	    || (zone_idx(page_zone(page)) == ZONE_MOVABLE))
-		gfp_mask |= __GFP_HIGHMEM;
-
-	return __alloc_pages_nodemask(gfp_mask, 0, nid, &nmask);
+	return new_page_nodemask(page, nid, &nmask);
 }
 
 #define NR_OFFLINE_AT_ONCE_PAGES	(256)
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 3606104893e0..757410d9f758 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -8,6 +8,7 @@
 #include <linux/memory.h>
 #include <linux/hugetlb.h>
 #include <linux/page_owner.h>
+#include <linux/migrate.h>
 #include "internal.h"
 
 #define CREATE_TRACE_POINTS
@@ -294,20 +295,5 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
 struct page *alloc_migrate_target(struct page *page, unsigned long private,
 				  int **resultp)
 {
-	gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE;
-
-	/*
-	 * TODO: allocate a destination hugepage from a nearest neighbor node,
-	 * accordance with memory policy of the user process if possible. For
-	 * now as a simple work-around, we use the next node for destination.
-	 */
-	if (PageHuge(page))
-		return alloc_huge_page_node(page_hstate(compound_head(page)),
-					    next_node_in(page_to_nid(page),
-							 node_online_map));
-
-	if (PageHighMem(page))
-		gfp_mask |= __GFP_HIGHMEM;
-
-	return alloc_page(gfp_mask);
+	return new_page_nodemask(page, numa_node_id(), &node_states[N_MEMORY]);
 }
-- 
cgit v1.2.3


From 422580c3cea7faaca67f6199375b79565d3d8ebd Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Mon, 10 Jul 2017 15:49:05 -0700
Subject: mm/oom_kill.c: add tracepoints for oom reaper-related events

During the debugging of the problem described in
https://lkml.org/lkml/2017/5/17/542 and fixed by Tetsuo Handa in
https://lkml.org/lkml/2017/5/19/383 , I've found that the existing debug
output is not really useful to understand issues related to the oom
reaper.

So, I assume, that adding some tracepoints might help with debugging of
similar issues.

Trace the following events:
 1) a process is marked as an oom victim,
 2) a process is added to the oom reaper list,
 3) the oom reaper starts reaping process's mm,
 4) the oom reaper finished reaping,
 5) the oom reaper skips reaping.

How it works in practice? Below is an example which show how the problem
mentioned above can be found: one process is added twice to the
oom_reaper list:

  $ cd /sys/kernel/debug/tracing
  $ echo "oom:mark_victim" > set_event
  $ echo "oom:wake_reaper" >> set_event
  $ echo "oom:skip_task_reaping" >> set_event
  $ echo "oom:start_task_reaping" >> set_event
  $ echo "oom:finish_task_reaping" >> set_event
  $ cat trace_pipe
          allocate-502   [001] ....    91.836405: mark_victim: pid=502
          allocate-502   [001] .N..    91.837356: wake_reaper: pid=502
          allocate-502   [000] .N..    91.871149: wake_reaper: pid=502
        oom_reaper-23    [000] ....    91.871177: start_task_reaping: pid=502
        oom_reaper-23    [000] .N..    91.879511: finish_task_reaping: pid=502
        oom_reaper-23    [000] ....    91.879580: skip_task_reaping: pid=502

Link: http://lkml.kernel.org/r/20170530185231.GA13412@castle
Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/trace/events/oom.h | 80 ++++++++++++++++++++++++++++++++++++++++++++++
 mm/oom_kill.c              |  7 ++++
 2 files changed, 87 insertions(+)

(limited to 'include')

diff --git a/include/trace/events/oom.h b/include/trace/events/oom.h
index 38baeb27221a..c3c19d47ae5e 100644
--- a/include/trace/events/oom.h
+++ b/include/trace/events/oom.h
@@ -70,6 +70,86 @@ TRACE_EVENT(reclaim_retry_zone,
 			__entry->wmark_check)
 );
 
+TRACE_EVENT(mark_victim,
+	TP_PROTO(int pid),
+
+	TP_ARGS(pid),
+
+	TP_STRUCT__entry(
+		__field(int, pid)
+	),
+
+	TP_fast_assign(
+		__entry->pid = pid;
+	),
+
+	TP_printk("pid=%d", __entry->pid)
+);
+
+TRACE_EVENT(wake_reaper,
+	TP_PROTO(int pid),
+
+	TP_ARGS(pid),
+
+	TP_STRUCT__entry(
+		__field(int, pid)
+	),
+
+	TP_fast_assign(
+		__entry->pid = pid;
+	),
+
+	TP_printk("pid=%d", __entry->pid)
+);
+
+TRACE_EVENT(start_task_reaping,
+	TP_PROTO(int pid),
+
+	TP_ARGS(pid),
+
+	TP_STRUCT__entry(
+		__field(int, pid)
+	),
+
+	TP_fast_assign(
+		__entry->pid = pid;
+	),
+
+	TP_printk("pid=%d", __entry->pid)
+);
+
+TRACE_EVENT(finish_task_reaping,
+	TP_PROTO(int pid),
+
+	TP_ARGS(pid),
+
+	TP_STRUCT__entry(
+		__field(int, pid)
+	),
+
+	TP_fast_assign(
+		__entry->pid = pid;
+	),
+
+	TP_printk("pid=%d", __entry->pid)
+);
+
+TRACE_EVENT(skip_task_reaping,
+	TP_PROTO(int pid),
+
+	TP_ARGS(pid),
+
+	TP_STRUCT__entry(
+		__field(int, pid)
+	),
+
+	TP_fast_assign(
+		__entry->pid = pid;
+	),
+
+	TP_printk("pid=%d", __entry->pid)
+);
+
 #ifdef CONFIG_COMPACTION
 TRACE_EVENT(compact_retry,
 
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 0e2c925e7826..9e8b4f030c1c 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -490,6 +490,7 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
 
 	if (!down_read_trylock(&mm->mmap_sem)) {
 		ret = false;
+		trace_skip_task_reaping(tsk->pid);
 		goto unlock_oom;
 	}
 
@@ -500,9 +501,12 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
 	 */
 	if (!mmget_not_zero(mm)) {
 		up_read(&mm->mmap_sem);
+		trace_skip_task_reaping(tsk->pid);
 		goto unlock_oom;
 	}
 
+	trace_start_task_reaping(tsk->pid);
+
 	/*
 	 * Tell all users of get_user/copy_from_user etc... that the content
 	 * is no longer stable. No barriers really needed because unmapping
@@ -544,6 +548,7 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
 	 * put the oom_reaper out of the way.
 	 */
 	mmput_async(mm);
+	trace_finish_task_reaping(tsk->pid);
 unlock_oom:
 	mutex_unlock(&oom_lock);
 	return ret;
@@ -615,6 +620,7 @@ static void wake_oom_reaper(struct task_struct *tsk)
 	tsk->oom_reaper_list = oom_reaper_list;
 	oom_reaper_list = tsk;
 	spin_unlock(&oom_reaper_lock);
+	trace_wake_reaper(tsk->pid);
 	wake_up(&oom_reaper_wait);
 }
 
@@ -666,6 +672,7 @@ static void mark_oom_victim(struct task_struct *tsk)
 	 */
 	__thaw_task(tsk);
 	atomic_inc(&oom_victims);
+	trace_mark_victim(tsk->pid);
 }
 
 /**
-- 
cgit v1.2.3


From aaf14e40a33a2c9350471387031ca40c00f5a006 Mon Sep 17 00:00:00 2001
From: Michal Hocko <mhocko@suse.com>
Date: Mon, 10 Jul 2017 15:49:08 -0700
Subject: mm, hugetlb: unclutter hugetlb allocation layers

Patch series "mm, hugetlb: allow proper node fallback dequeue".

While working on a hugetlb migration issue addressed in a separate
patchset[1] I have noticed that the hugetlb allocations from the
preallocated pool are quite subotimal.

 [1] //lkml.kernel.org/r/20170608074553.22152-1-mhocko@kernel.org

There is no fallback mechanism implemented and no notion of preferred
node.  I have tried to work around it but Vlastimil was right to push
back for a more robust solution.  It seems that such a solution is to
reuse zonelist approach we use for the page alloctor.

This series has 3 patches.  The first one tries to make hugetlb
allocation layers more clear.  The second one implements the zonelist
hugetlb pool allocation and introduces a preferred node semantic which
is used by the migration callbacks.  The last patch is a clean up.

This patch (of 3):

Hugetlb allocation path for fresh huge pages is unnecessarily complex
and it mixes different interfaces between layers.

__alloc_buddy_huge_page is the central place to perform a new
allocation.  It checks for the hugetlb overcommit and then relies on
__hugetlb_alloc_buddy_huge_page to invoke the page allocator.  This is
all good except that __alloc_buddy_huge_page pushes vma and address down
the callchain and so __hugetlb_alloc_buddy_huge_page has to deal with
two different allocation modes - one for memory policy and other node
specific (or to make it more obscure node non-specific) requests.

This just screams for a reorganization.

This patch pulls out all the vma specific handling up to
__alloc_buddy_huge_page_with_mpol where it belongs.
__alloc_buddy_huge_page will get nodemask argument and
__hugetlb_alloc_buddy_huge_page will become a trivial wrapper over the
page allocator.

In short:
__alloc_buddy_huge_page_with_mpol - memory policy handling
  __alloc_buddy_huge_page - overcommit handling and accounting
    __hugetlb_alloc_buddy_huge_page - page allocator layer

Also note that __hugetlb_alloc_buddy_huge_page and its cpuset retry loop
is not really needed because the page allocator already handles the
cpusets update.

Finally __hugetlb_alloc_buddy_huge_page had a special case for node
specific allocations (when no policy is applied and there is a node
given).  This has relied on __GFP_THISNODE to not fallback to a different
node.  alloc_huge_page_node is the only caller which relies on this
behavior so move the __GFP_THISNODE there.

Not only does this remove quite some code it also should make those
layers easier to follow and clear wrt responsibilities.

Link: http://lkml.kernel.org/r/20170622193034.28972-2-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Tested-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/hugetlb.h |   2 +-
 mm/hugetlb.c            | 133 +++++++++++-------------------------------------
 2 files changed, 30 insertions(+), 105 deletions(-)

(limited to 'include')

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 8fd0725d3f30..66b621469f52 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -349,7 +349,7 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,
 struct page *alloc_huge_page_node(struct hstate *h, int nid);
 struct page *alloc_huge_page_noerr(struct vm_area_struct *vma,
 				unsigned long addr, int avoid_reserve);
-struct page *alloc_huge_page_nodemask(struct hstate *h, const nodemask_t *nmask);
+struct page *alloc_huge_page_nodemask(struct hstate *h, nodemask_t *nmask);
 int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
 			pgoff_t idx);
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 907786581812..fd6e0c50f949 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1521,82 +1521,19 @@ int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn)
 	return rc;
 }
 
-/*
- * There are 3 ways this can get called:
- * 1. With vma+addr: we use the VMA's memory policy
- * 2. With !vma, but nid=NUMA_NO_NODE:  We try to allocate a huge
- *    page from any node, and let the buddy allocator itself figure
- *    it out.
- * 3. With !vma, but nid!=NUMA_NO_NODE.  We allocate a huge page
- *    strictly from 'nid'
- */
 static struct page *__hugetlb_alloc_buddy_huge_page(struct hstate *h,
-		struct vm_area_struct *vma, unsigned long addr, int nid)
+		gfp_t gfp_mask, int nid, nodemask_t *nmask)
 {
 	int order = huge_page_order(h);
-	gfp_t gfp = htlb_alloc_mask(h)|__GFP_COMP|__GFP_REPEAT|__GFP_NOWARN;
-	unsigned int cpuset_mems_cookie;
 
-	/*
-	 * We need a VMA to get a memory policy.  If we do not
-	 * have one, we use the 'nid' argument.
-	 *
-	 * The mempolicy stuff below has some non-inlined bits
-	 * and calls ->vm_ops.  That makes it hard to optimize at
-	 * compile-time, even when NUMA is off and it does
-	 * nothing.  This helps the compiler optimize it out.
-	 */
-	if (!IS_ENABLED(CONFIG_NUMA) || !vma) {
-		/*
-		 * If a specific node is requested, make sure to
-		 * get memory from there, but only when a node
-		 * is explicitly specified.
-		 */
-		if (nid != NUMA_NO_NODE)
-			gfp |= __GFP_THISNODE;
-		/*
-		 * Make sure to call something that can handle
-		 * nid=NUMA_NO_NODE
-		 */
-		return alloc_pages_node(nid, gfp, order);
-	}
-
-	/*
-	 * OK, so we have a VMA.  Fetch the mempolicy and try to
-	 * allocate a huge page with it.  We will only reach this
-	 * when CONFIG_NUMA=y.
-	 */
-	do {
-		struct page *page;
-		struct mempolicy *mpol;
-		int nid;
-		nodemask_t *nodemask;
-
-		cpuset_mems_cookie = read_mems_allowed_begin();
-		nid = huge_node(vma, addr, gfp, &mpol, &nodemask);
-		mpol_cond_put(mpol);
-		page = __alloc_pages_nodemask(gfp, order, nid, nodemask);
-		if (page)
-			return page;
-	} while (read_mems_allowed_retry(cpuset_mems_cookie));
-
-	return NULL;
+	gfp_mask |= __GFP_COMP|__GFP_REPEAT|__GFP_NOWARN;
+	if (nid == NUMA_NO_NODE)
+		nid = numa_mem_id();
+	return __alloc_pages_nodemask(gfp_mask, order, nid, nmask);
 }
 
-/*
- * There are two ways to allocate a huge page:
- * 1. When you have a VMA and an address (like a fault)
- * 2. When you have no VMA (like when setting /proc/.../nr_hugepages)
- *
- * 'vma' and 'addr' are only for (1).  'nid' is always NUMA_NO_NODE in
- * this case which signifies that the allocation should be done with
- * respect for the VMA's memory policy.
- *
- * For (2), we ignore 'vma' and 'addr' and use 'nid' exclusively. This
- * implies that memory policies will not be taken in to account.
- */
-static struct page *__alloc_buddy_huge_page(struct hstate *h,
-		struct vm_area_struct *vma, unsigned long addr, int nid)
+static struct page *__alloc_buddy_huge_page(struct hstate *h, gfp_t gfp_mask,
+		int nid, nodemask_t *nmask)
 {
 	struct page *page;
 	unsigned int r_nid;
@@ -1604,15 +1541,6 @@ static struct page *__alloc_buddy_huge_page(struct hstate *h,
 	if (hstate_is_gigantic(h))
 		return NULL;
 
-	/*
-	 * Make sure that anyone specifying 'nid' is not also specifying a VMA.
-	 * This makes sure the caller is picking _one_ of the modes with which
-	 * we can call this function, not both.
-	 */
-	if (vma || (addr != -1)) {
-		VM_WARN_ON_ONCE(addr == -1);
-		VM_WARN_ON_ONCE(nid != NUMA_NO_NODE);
-	}
 	/*
 	 * Assume we will successfully allocate the surplus page to
 	 * prevent racing processes from causing the surplus to exceed
@@ -1646,7 +1574,7 @@ static struct page *__alloc_buddy_huge_page(struct hstate *h,
 	}
 	spin_unlock(&hugetlb_lock);
 
-	page = __hugetlb_alloc_buddy_huge_page(h, vma, addr, nid);
+	page = __hugetlb_alloc_buddy_huge_page(h, gfp_mask, nid, nmask);
 
 	spin_lock(&hugetlb_lock);
 	if (page) {
@@ -1670,19 +1598,6 @@ static struct page *__alloc_buddy_huge_page(struct hstate *h,
 	return page;
 }
 
-/*
- * Allocate a huge page from 'nid'.  Note, 'nid' may be
- * NUMA_NO_NODE, which means that it may be allocated
- * anywhere.
- */
-static
-struct page *__alloc_buddy_huge_page_no_mpol(struct hstate *h, int nid)
-{
-	unsigned long addr = -1;
-
-	return __alloc_buddy_huge_page(h, NULL, addr, nid);
-}
-
 /*
  * Use the VMA's mpolicy to allocate a huge page from the buddy.
  */
@@ -1690,7 +1605,17 @@ static
 struct page *__alloc_buddy_huge_page_with_mpol(struct hstate *h,
 		struct vm_area_struct *vma, unsigned long addr)
 {
-	return __alloc_buddy_huge_page(h, vma, addr, NUMA_NO_NODE);
+	struct page *page;
+	struct mempolicy *mpol;
+	gfp_t gfp_mask = htlb_alloc_mask(h);
+	int nid;
+	nodemask_t *nodemask;
+
+	nid = huge_node(vma, addr, gfp_mask, &mpol, &nodemask);
+	page = __alloc_buddy_huge_page(h, gfp_mask, nid, nodemask);
+	mpol_cond_put(mpol);
+
+	return page;
 }
 
 /*
@@ -1700,21 +1625,26 @@ struct page *__alloc_buddy_huge_page_with_mpol(struct hstate *h,
  */
 struct page *alloc_huge_page_node(struct hstate *h, int nid)
 {
+	gfp_t gfp_mask = htlb_alloc_mask(h);
 	struct page *page = NULL;
 
+	if (nid != NUMA_NO_NODE)
+		gfp_mask |= __GFP_THISNODE;
+
 	spin_lock(&hugetlb_lock);
 	if (h->free_huge_pages - h->resv_huge_pages > 0)
 		page = dequeue_huge_page_node(h, nid);
 	spin_unlock(&hugetlb_lock);
 
 	if (!page)
-		page = __alloc_buddy_huge_page_no_mpol(h, nid);
+		page = __alloc_buddy_huge_page(h, gfp_mask, nid, NULL);
 
 	return page;
 }
 
-struct page *alloc_huge_page_nodemask(struct hstate *h, const nodemask_t *nmask)
+struct page *alloc_huge_page_nodemask(struct hstate *h, nodemask_t *nmask)
 {
+	gfp_t gfp_mask = htlb_alloc_mask(h);
 	struct page *page = NULL;
 	int node;
 
@@ -1731,13 +1661,7 @@ struct page *alloc_huge_page_nodemask(struct hstate *h, const nodemask_t *nmask)
 		return page;
 
 	/* No reservations, try to overcommit */
-	for_each_node_mask(node, *nmask) {
-		page = __alloc_buddy_huge_page_no_mpol(h, node);
-		if (page)
-			return page;
-	}
-
-	return NULL;
+	return __alloc_buddy_huge_page(h, gfp_mask, NUMA_NO_NODE, nmask);
 }
 
 /*
@@ -1765,7 +1689,8 @@ static int gather_surplus_pages(struct hstate *h, int delta)
 retry:
 	spin_unlock(&hugetlb_lock);
 	for (i = 0; i < needed; i++) {
-		page = __alloc_buddy_huge_page_no_mpol(h, NUMA_NO_NODE);
+		page = __alloc_buddy_huge_page(h, htlb_alloc_mask(h),
+				NUMA_NO_NODE, NULL);
 		if (!page) {
 			alloc_ok = false;
 			break;
-- 
cgit v1.2.3


From 3e59fcb0e8c1c40aecb60fa4c2d1543d6a097184 Mon Sep 17 00:00:00 2001
From: Michal Hocko <mhocko@suse.com>
Date: Mon, 10 Jul 2017 15:49:11 -0700
Subject: hugetlb: add support for preferred node to alloc_huge_page_nodemask

alloc_huge_page_nodemask tries to allocate from any numa node in the
allowed node mask starting from lower numa nodes.  This might lead to
filling up those low NUMA nodes while others are not used.  We can
reduce this risk by introducing a concept of the preferred node similar
to what we have in the regular page allocator.  We will start allocating
from the preferred nid and then iterate over all allowed nodes in the
zonelist order until we try them all.

This is mimicing the page allocator logic except it operates on per-node
mempools.  dequeue_huge_page_vma already does this so distill the
zonelist logic into a more generic dequeue_huge_page_nodemask and use it
in alloc_huge_page_nodemask.

This will allow us to use proper per numa distance fallback also for
alloc_huge_page_node which can use alloc_huge_page_nodemask now and we
can get rid of alloc_huge_page_node helper which doesn't have any user
anymore.

Link: http://lkml.kernel.org/r/20170622193034.28972-3-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Tested-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/hugetlb.h |  5 +--
 include/linux/migrate.h |  2 +-
 mm/hugetlb.c            | 88 ++++++++++++++++++++++++-------------------------
 3 files changed, 48 insertions(+), 47 deletions(-)

(limited to 'include')

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 66b621469f52..8d9fe131a240 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -349,7 +349,8 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,
 struct page *alloc_huge_page_node(struct hstate *h, int nid);
 struct page *alloc_huge_page_noerr(struct vm_area_struct *vma,
 				unsigned long addr, int avoid_reserve);
-struct page *alloc_huge_page_nodemask(struct hstate *h, nodemask_t *nmask);
+struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
+				nodemask_t *nmask);
 int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
 			pgoff_t idx);
 
@@ -525,7 +526,7 @@ static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr
 struct hstate {};
 #define alloc_huge_page(v, a, r) NULL
 #define alloc_huge_page_node(h, nid) NULL
-#define alloc_huge_page_nodemask(h, nmask) NULL
+#define alloc_huge_page_nodemask(h, preferred_nid, nmask) NULL
 #define alloc_huge_page_noerr(v, a, r) NULL
 #define alloc_bootmem_huge_page(h) NULL
 #define hstate_file(f) NULL
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index d9675b665cc4..4634da521238 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -38,7 +38,7 @@ static inline struct page *new_page_nodemask(struct page *page,
 
 	if (PageHuge(page))
 		return alloc_huge_page_nodemask(page_hstate(compound_head(page)),
-				nodemask);
+				preferred_nid, nodemask);
 
 	if (PageHighMem(page) || (zone_idx(page_zone(page)) == ZONE_MOVABLE))
 		gfp_mask |= __GFP_HIGHMEM;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index fd6e0c50f949..1e516520433d 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -887,19 +887,39 @@ static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)
 	return page;
 }
 
-static struct page *dequeue_huge_page_node(struct hstate *h, int nid)
+static struct page *dequeue_huge_page_nodemask(struct hstate *h, gfp_t gfp_mask, int nid,
+		nodemask_t *nmask)
 {
-	struct page *page;
-	int node;
+	unsigned int cpuset_mems_cookie;
+	struct zonelist *zonelist;
+	struct zone *zone;
+	struct zoneref *z;
+	int node = -1;
 
-	if (nid != NUMA_NO_NODE)
-		return dequeue_huge_page_node_exact(h, nid);
+	zonelist = node_zonelist(nid, gfp_mask);
+
+retry_cpuset:
+	cpuset_mems_cookie = read_mems_allowed_begin();
+	for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp_mask), nmask) {
+		struct page *page;
+
+		if (!cpuset_zone_allowed(zone, gfp_mask))
+			continue;
+		/*
+		 * no need to ask again on the same node. Pool is node rather than
+		 * zone aware
+		 */
+		if (zone_to_nid(zone) == node)
+			continue;
+		node = zone_to_nid(zone);
 
-	for_each_online_node(node) {
 		page = dequeue_huge_page_node_exact(h, node);
 		if (page)
 			return page;
 	}
+	if (unlikely(read_mems_allowed_retry(cpuset_mems_cookie)))
+		goto retry_cpuset;
+
 	return NULL;
 }
 
@@ -917,15 +937,11 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 				unsigned long address, int avoid_reserve,
 				long chg)
 {
-	struct page *page = NULL;
+	struct page *page;
 	struct mempolicy *mpol;
-	nodemask_t *nodemask;
 	gfp_t gfp_mask;
+	nodemask_t *nodemask;
 	int nid;
-	struct zonelist *zonelist;
-	struct zone *zone;
-	struct zoneref *z;
-	unsigned int cpuset_mems_cookie;
 
 	/*
 	 * A child process with MAP_PRIVATE mappings created by their parent
@@ -940,32 +956,15 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 	if (avoid_reserve && h->free_huge_pages - h->resv_huge_pages == 0)
 		goto err;
 
-retry_cpuset:
-	cpuset_mems_cookie = read_mems_allowed_begin();
 	gfp_mask = htlb_alloc_mask(h);
 	nid = huge_node(vma, address, gfp_mask, &mpol, &nodemask);
-	zonelist = node_zonelist(nid, gfp_mask);
-
-	for_each_zone_zonelist_nodemask(zone, z, zonelist,
-						MAX_NR_ZONES - 1, nodemask) {
-		if (cpuset_zone_allowed(zone, gfp_mask)) {
-			page = dequeue_huge_page_node(h, zone_to_nid(zone));
-			if (page) {
-				if (avoid_reserve)
-					break;
-				if (!vma_has_reserves(vma, chg))
-					break;
-
-				SetPagePrivate(page);
-				h->resv_huge_pages--;
-				break;
-			}
-		}
+	page = dequeue_huge_page_nodemask(h, gfp_mask, nid, nodemask);
+	if (page && !avoid_reserve && vma_has_reserves(vma, chg)) {
+		SetPagePrivate(page);
+		h->resv_huge_pages--;
 	}
 
 	mpol_cond_put(mpol);
-	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
-		goto retry_cpuset;
 	return page;
 
 err:
@@ -1633,7 +1632,7 @@ struct page *alloc_huge_page_node(struct hstate *h, int nid)
 
 	spin_lock(&hugetlb_lock);
 	if (h->free_huge_pages - h->resv_huge_pages > 0)
-		page = dequeue_huge_page_node(h, nid);
+		page = dequeue_huge_page_nodemask(h, gfp_mask, nid, NULL);
 	spin_unlock(&hugetlb_lock);
 
 	if (!page)
@@ -1642,26 +1641,27 @@ struct page *alloc_huge_page_node(struct hstate *h, int nid)
 	return page;
 }
 
-struct page *alloc_huge_page_nodemask(struct hstate *h, nodemask_t *nmask)
+
+struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
+		nodemask_t *nmask)
 {
 	gfp_t gfp_mask = htlb_alloc_mask(h);
-	struct page *page = NULL;
-	int node;
 
 	spin_lock(&hugetlb_lock);
 	if (h->free_huge_pages - h->resv_huge_pages > 0) {
-		for_each_node_mask(node, *nmask) {
-			page = dequeue_huge_page_node_exact(h, node);
-			if (page)
-				break;
+		struct page *page;
+
+		page = dequeue_huge_page_nodemask(h, gfp_mask, preferred_nid, nmask);
+		if (page) {
+			spin_unlock(&hugetlb_lock);
+			return page;
 		}
 	}
 	spin_unlock(&hugetlb_lock);
-	if (page)
-		return page;
 
 	/* No reservations, try to overcommit */
-	return __alloc_buddy_huge_page(h, gfp_mask, NUMA_NO_NODE, nmask);
+
+	return __alloc_buddy_huge_page(h, gfp_mask, preferred_nid, nmask);
 }
 
 /*
-- 
cgit v1.2.3


From 618b8c20d03c9ea06711bd36d906322ba35c0add Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 10 Jul 2017 15:49:32 -0700
Subject: include/linux/mmzone.h: remove ancient/ambiguous comment

Currently pg_data_t is just a struct which describes a NUMA node memory
layout.  Let's keep the comment simple and remove ambiguity.

Link: http://lkml.kernel.org/r/1498220534-22717-1-git-send-email-nborisov@suse.com
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmzone.h | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 7e8f100cb56d..16532fa0bb64 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -603,12 +603,9 @@ extern struct page *mem_map;
 #endif
 
 /*
- * The pg_data_t structure is used in machines with CONFIG_DISCONTIGMEM
- * (mostly NUMA machines?) to denote a higher-level memory zone than the
- * zone denotes.
- *
  * On NUMA machines, each NUMA node would have a pg_data_t to describe
- * it's memory layout.
+ * it's memory layout. On UMA machines there is a single pglist_data which
+ * describes the whole memory.
  *
  * Memory statistics and page replacement data structures are maintained on a
  * per-zone basis.
-- 
cgit v1.2.3


From e3d3910a57ab9c70cddb2522ae711ff9bff89e7c Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 10 Jul 2017 15:49:35 -0700
Subject: include/linux/backing-dev.h: simplify wb_stat_sum

wb_stat_sum() disables interrupts and calls __wb_stat_sum() which
eventually calls __percpu_counter_sum().  However, the percpu routine is
already irq-safe.  Simplify the code a bit by making wb_stat_sum()
directly call percpu_counter_sum_positive() and not disable interrupts.

Also remove the now-uneeded __wb_stat_sum() which was just a wrapper
over percpu_counter_sum_positive().

Link: http://lkml.kernel.org/r/1498230681-29103-1-git-send-email-nborisov@suse.com
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Jens Axboe <axboe@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/backing-dev.h | 15 +--------------
 1 file changed, 1 insertion(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index ace73f96eb1e..334165c911f0 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -104,22 +104,9 @@ static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
 	return percpu_counter_read_positive(&wb->stat[item]);
 }
 
-static inline s64 __wb_stat_sum(struct bdi_writeback *wb,
-				enum wb_stat_item item)
-{
-	return percpu_counter_sum_positive(&wb->stat[item]);
-}
-
 static inline s64 wb_stat_sum(struct bdi_writeback *wb, enum wb_stat_item item)
 {
-	s64 sum;
-	unsigned long flags;
-
-	local_irq_save(flags);
-	sum = __wb_stat_sum(wb, item);
-	local_irq_restore(flags);
-
-	return sum;
+	return percpu_counter_sum_positive(&wb->stat[item]);
 }
 
 extern void wb_writeout_inc(struct bdi_writeback *wb);
-- 
cgit v1.2.3


From 2c80cd57c74339889a8752b20862a16c28929c3a Mon Sep 17 00:00:00 2001
From: Sahitya Tummala <stummala@codeaurora.org>
Date: Mon, 10 Jul 2017 15:49:57 -0700
Subject: mm/list_lru.c: fix list_lru_count_node() to be race free

list_lru_count_node() iterates over all memcgs to get the total number of
entries on the node but it can race with memcg_drain_all_list_lrus(),
which migrates the entries from a dead cgroup to another.  This can return
incorrect number of entries from list_lru_count_node().

Fix this by keeping track of entries per node and simply return it in
list_lru_count_node().

Link: http://lkml.kernel.org/r/1498707555-30525-1-git-send-email-stummala@codeaurora.org
Signed-off-by: Sahitya Tummala <stummala@codeaurora.org>
Acked-by: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Alexander Polakov <apolyakov@beget.ru>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/list_lru.h |  1 +
 mm/list_lru.c            | 14 ++++++--------
 2 files changed, 7 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index cb0ba9f2a9a2..fa7fd03cb5f9 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -44,6 +44,7 @@ struct list_lru_node {
 	/* for cgroup aware lrus points to per cgroup lists, otherwise NULL */
 	struct list_lru_memcg	*memcg_lrus;
 #endif
+	long nr_items;
 } ____cacheline_aligned_in_smp;
 
 struct list_lru {
diff --git a/mm/list_lru.c b/mm/list_lru.c
index 234676e31edd..7a40fa2be858 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -117,6 +117,7 @@ bool list_lru_add(struct list_lru *lru, struct list_head *item)
 		l = list_lru_from_kmem(nlru, item);
 		list_add_tail(item, &l->list);
 		l->nr_items++;
+		nlru->nr_items++;
 		spin_unlock(&nlru->lock);
 		return true;
 	}
@@ -136,6 +137,7 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item)
 		l = list_lru_from_kmem(nlru, item);
 		list_del_init(item);
 		l->nr_items--;
+		nlru->nr_items--;
 		spin_unlock(&nlru->lock);
 		return true;
 	}
@@ -183,15 +185,10 @@ EXPORT_SYMBOL_GPL(list_lru_count_one);
 
 unsigned long list_lru_count_node(struct list_lru *lru, int nid)
 {
-	long count = 0;
-	int memcg_idx;
+	struct list_lru_node *nlru;
 
-	count += __list_lru_count_one(lru, nid, -1);
-	if (list_lru_memcg_aware(lru)) {
-		for_each_memcg_cache_index(memcg_idx)
-			count += __list_lru_count_one(lru, nid, memcg_idx);
-	}
-	return count;
+	nlru = &lru->node[nid];
+	return nlru->nr_items;
 }
 EXPORT_SYMBOL_GPL(list_lru_count_node);
 
@@ -226,6 +223,7 @@ restart:
 			assert_spin_locked(&nlru->lock);
 		case LRU_REMOVED:
 			isolated++;
+			nlru->nr_items--;
 			/*
 			 * If the lru lock has been dropped, our list
 			 * traversal is now invalid and so we have to
-- 
cgit v1.2.3


From a47fed5b5b014f5a13878b90ef2c3a7dc294189f Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 10 Jul 2017 15:50:06 -0700
Subject: mm: swap: provide lru_add_drain_all_cpuslocked()

The rework of the cpu hotplug locking unearthed potential deadlocks with
the memory hotplug locking code.

The solution for these is to rework the memory hotplug locking code as
well and take the cpu hotplug lock before the memory hotplug lock in
mem_hotplug_begin(), but this will cause a recursive locking of the cpu
hotplug lock when the memory hotplug code calls lru_add_drain_all().

Split out the inner workings of lru_add_drain_all() into
lru_add_drain_all_cpuslocked() so this function can be invoked from the
memory hotplug code with the cpu hotplug lock held.

Link: http://lkml.kernel.org/r/20170704093421.419329357@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reported-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/swap.h |  1 +
 mm/swap.c            | 11 ++++++++---
 2 files changed, 9 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 61e7180cee21..d83d28e53e62 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -277,6 +277,7 @@ extern void mark_page_accessed(struct page *);
 extern void lru_add_drain(void);
 extern void lru_add_drain_cpu(int cpu);
 extern void lru_add_drain_all(void);
+extern void lru_add_drain_all_cpuslocked(void);
 extern void rotate_reclaimable_page(struct page *page);
 extern void deactivate_file_page(struct page *page);
 extern void mark_page_lazyfree(struct page *page);
diff --git a/mm/swap.c b/mm/swap.c
index 4f44dbd7f780..60b1d2a75852 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -688,7 +688,7 @@ static void lru_add_drain_per_cpu(struct work_struct *dummy)
 
 static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work);
 
-void lru_add_drain_all(void)
+void lru_add_drain_all_cpuslocked(void)
 {
 	static DEFINE_MUTEX(lock);
 	static struct cpumask has_work;
@@ -702,7 +702,6 @@ void lru_add_drain_all(void)
 		return;
 
 	mutex_lock(&lock);
-	get_online_cpus();
 	cpumask_clear(&has_work);
 
 	for_each_online_cpu(cpu) {
@@ -722,10 +721,16 @@ void lru_add_drain_all(void)
 	for_each_cpu(cpu, &has_work)
 		flush_work(&per_cpu(lru_add_drain_work, cpu));
 
-	put_online_cpus();
 	mutex_unlock(&lock);
 }
 
+void lru_add_drain_all(void)
+{
+	get_online_cpus();
+	lru_add_drain_all_cpuslocked();
+	put_online_cpus();
+}
+
 /**
  * release_pages - batched put_page()
  * @pages: array of pages to release
-- 
cgit v1.2.3


From 9d1f4b3f5b29bea431525e528a3ff2dc806ad904 Mon Sep 17 00:00:00 2001
From: Michal Hocko <mhocko@suse.com>
Date: Mon, 10 Jul 2017 15:50:12 -0700
Subject: mm: disallow early_pfn_to_nid on configurations which do not
 implement it

early_pfn_to_nid will return node 0 if both HAVE_ARCH_EARLY_PFN_TO_NID
and HAVE_MEMBLOCK_NODE_MAP are disabled.  It seems we are safe now
because all architectures which support NUMA define one of them (with an
exception of alpha which however has CONFIG_NUMA marked as broken) so
this works as expected.  It can get silently and subtly broken too
easily, though.  Make sure we fail the compilation if NUMA is enabled
and there is no proper implementation for this function.  If that ever
happens we know that either the specific configuration is invalid and
the fix should either disable NUMA or enable one of the above configs.

Link: http://lkml.kernel.org/r/20170704075803.15979-1-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Joonsoo Kim <js1304@gmail.com>
Cc: Yang Shi <yang.shi@linaro.org>
Cc: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmzone.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 16532fa0bb64..fc14b8b3f6ce 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1055,6 +1055,7 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist,
 	!defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP)
 static inline unsigned long early_pfn_to_nid(unsigned long pfn)
 {
+	BUILD_BUG_ON(IS_ENABLED(CONFIG_NUMA));
 	return 0;
 }
 #endif
-- 
cgit v1.2.3


From 0b396923ee9bdcb4a208df2148712b79b6dee73e Mon Sep 17 00:00:00 2001
From: Ian Abbott <abbotti@mev.co.uk>
Date: Mon, 10 Jul 2017 15:50:55 -0700
Subject: asm-generic/bug.h: declare struct pt_regs; before function prototype

This series of patches splits BUILD_BUG related macros out of
"include/linux/bug.h" into new file "include/linux/build_bug.h" (patch
5), and changes the pointer type checking in the `container_of()` macro
to deal with pointers of array type better (patch 6).  Patches 1 to 4
are prerequisites.

Patches 2, 3, 4, and 5 have been inserted since the previous version of
this patch series.  Patch 6 here corresponds to v3 and v4's patch 2.

Patch 1 was a prerequisite in v3 of this series to avoid a lot of
warnings when <linux/bug.h> was included by <linux/kernel.h>.  That is
no longer relevant for v5 of the series, but I left it in because it was
acked by a Arnd Bergmann and Michal Nazarewicz.

Patches 2, 3, and 4 are some checkpatch clean-ups on
"include/linux/bug.h" before splitting out the BUILD_BUG stuff in patch
5.

Patch 5 splits the BUILD_BUG related macros out of "include/linux/bug.h"
into new file "include/linux/build_bug.h" because including
<linux/bug.h> in "include/linux/kernel.h" would result in build failures
due to circular dependencies.

Patch 6 changes the pointer type checking by `container_of()` to avoid
some incompatible pointer warnings when the dereferenced pointer has
array type.

1) asm-generic/bug.h: declare struct pt_regs; before function prototype
2) linux/bug.h: correct formatting of block comment
3) linux/bug.h: correct "(foo*)" should be "(foo *)"
4) linux/bug.h: correct "space required before that '-'"
5) bug: split BUILD_BUG stuff out into <linux/build_bug.h>
6) kernel.h: handle pointers to arrays better in container_of()

This patch (of 6):

The declaration of `__warn()` has `struct pt_regs *regs` as one of its
parameters.  This can result in compiler warnings if `struct regs` is not
already declared.  Add an empty declaration of `struct pt_regs` to avoid
the warnings.

Link: http://lkml.kernel.org/r/20170525120316.24473-2-abbotti@mev.co.uk
Signed-off-by: Ian Abbott <abbotti@mev.co.uk>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Michal Nazarewicz <mina86@mina86.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Kees Cook <keescook@chromium.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/asm-generic/bug.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h
index d6f4aed479a1..87191357d303 100644
--- a/include/asm-generic/bug.h
+++ b/include/asm-generic/bug.h
@@ -97,6 +97,7 @@ extern void warn_slowpath_null(const char *file, const int line);
 
 /* used internally by panic.c */
 struct warn_args;
+struct pt_regs;
 
 void __warn(const char *file, int line, void *caller, unsigned taint,
 	    struct pt_regs *regs, struct warn_args *args);
-- 
cgit v1.2.3


From e9d5a48499391fe5b0615610858665ba8149e255 Mon Sep 17 00:00:00 2001
From: Ian Abbott <abbotti@mev.co.uk>
Date: Mon, 10 Jul 2017 15:50:58 -0700
Subject: linux/bug.h: correct formatting of block comment

Correct these checkpatch.pl warnings:

|WARNING: Block comments use * on subsequent lines
|#34: FILE: include/linux/bug.h:34:
|+/* Force a compilation error if condition is true, but also produce a
|+   result (of value 0 and type size_t), so the expression can be used

|WARNING: Block comments use a trailing */ on a separate line
|#36: FILE: include/linux/bug.h:36:
|+   aren't permitted). */

Link: http://lkml.kernel.org/r/20170525120316.24473-3-abbotti@mev.co.uk
Signed-off-by: Ian Abbott <abbotti@mev.co.uk>
Acked-by: Michal Nazarewicz <mina86@mina86.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Jakub Kicinski <jakub.kicinski@netronome.com>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/bug.h | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/bug.h b/include/linux/bug.h
index 687b557fc5eb..ca24007e2dc3 100644
--- a/include/linux/bug.h
+++ b/include/linux/bug.h
@@ -30,10 +30,12 @@ struct pt_regs;
 #define BUILD_BUG_ON_NOT_POWER_OF_2(n)			\
 	BUILD_BUG_ON((n) == 0 || (((n) & ((n) - 1)) != 0))
 
-/* Force a compilation error if condition is true, but also produce a
-   result (of value 0 and type size_t), so the expression can be used
-   e.g. in a structure initializer (or where-ever else comma expressions
-   aren't permitted). */
+/*
+ * Force a compilation error if condition is true, but also produce a
+ * result (of value 0 and type size_t), so the expression can be used
+ * e.g. in a structure initializer (or where-ever else comma expressions
+ * aren't permitted).
+ */
 #define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); }))
 #define BUILD_BUG_ON_NULL(e) ((void *)sizeof(struct { int:-!!(e); }))
 
-- 
cgit v1.2.3


From 8cdd7cca9287abf4c849c01e2a4e8207ad3e3a82 Mon Sep 17 00:00:00 2001
From: Ian Abbott <abbotti@mev.co.uk>
Date: Mon, 10 Jul 2017 15:51:01 -0700
Subject: linux/bug.h: correct "(foo*)" should be "(foo *)"

Correct this checkpatch.pl error:

|ERROR: "(foo*)" should be "(foo *)"
|#19: FILE: include/linux/bug.h:19:
|+#define BUILD_BUG_ON_NULL(e) ((void*)0)

Link: http://lkml.kernel.org/r/20170525120316.24473-4-abbotti@mev.co.uk
Signed-off-by: Ian Abbott <abbotti@mev.co.uk>
Acked-by: Michal Nazarewicz <mina86@mina86.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Jakub Kicinski <jakub.kicinski@netronome.com>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/bug.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/bug.h b/include/linux/bug.h
index ca24007e2dc3..216a1b79653d 100644
--- a/include/linux/bug.h
+++ b/include/linux/bug.h
@@ -16,7 +16,7 @@ struct pt_regs;
 #define __BUILD_BUG_ON_NOT_POWER_OF_2(n) (0)
 #define BUILD_BUG_ON_NOT_POWER_OF_2(n) (0)
 #define BUILD_BUG_ON_ZERO(e) (0)
-#define BUILD_BUG_ON_NULL(e) ((void*)0)
+#define BUILD_BUG_ON_NULL(e) ((void *)0)
 #define BUILD_BUG_ON_INVALID(e) (0)
 #define BUILD_BUG_ON_MSG(cond, msg) (0)
 #define BUILD_BUG_ON(condition) (0)
-- 
cgit v1.2.3


From 47e81e59d98b90727a02ceb486407eeed5eb8727 Mon Sep 17 00:00:00 2001
From: Ian Abbott <abbotti@mev.co.uk>
Date: Mon, 10 Jul 2017 15:51:04 -0700
Subject: linux/bug.h: correct "space required before that '-'"

Correct these checkpatch.pl errors:

|ERROR: space required before that '-' (ctx:OxO)
|#37: FILE: include/linux/bug.h:37:
|+#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); }))

|ERROR: space required before that '-' (ctx:OxO)
|#38: FILE: include/linux/bug.h:38:
|+#define BUILD_BUG_ON_NULL(e) ((void *)sizeof(struct { int:-!!(e); }))

I decided to wrap the bitfield expressions that begin with minus signs
in parentheses rather than insert spaces before the minus signs.

Link: http://lkml.kernel.org/r/20170525120316.24473-5-abbotti@mev.co.uk
Signed-off-by: Ian Abbott <abbotti@mev.co.uk>
Acked-by: Michal Nazarewicz <mina86@mina86.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Jakub Kicinski <jakub.kicinski@netronome.com>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/bug.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/bug.h b/include/linux/bug.h
index 216a1b79653d..483207cb99fb 100644
--- a/include/linux/bug.h
+++ b/include/linux/bug.h
@@ -36,8 +36,8 @@ struct pt_regs;
  * e.g. in a structure initializer (or where-ever else comma expressions
  * aren't permitted).
  */
-#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); }))
-#define BUILD_BUG_ON_NULL(e) ((void *)sizeof(struct { int:-!!(e); }))
+#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:(-!!(e)); }))
+#define BUILD_BUG_ON_NULL(e) ((void *)sizeof(struct { int:(-!!(e)); }))
 
 /*
  * BUILD_BUG_ON_INVALID() permits the compiler to check the validity of the
-- 
cgit v1.2.3


From bc6245e5efd70c41eaf9334b1b5e646745cb0fb3 Mon Sep 17 00:00:00 2001
From: Ian Abbott <abbotti@mev.co.uk>
Date: Mon, 10 Jul 2017 15:51:07 -0700
Subject: bug: split BUILD_BUG stuff out into <linux/build_bug.h>

Including <linux/bug.h> pulls in a lot of bloat from <asm/bug.h> and
<asm-generic/bug.h> that is not needed to call the BUILD_BUG() family of
macros.  Split them out into their own header, <linux/build_bug.h>.

Also correct some checkpatch.pl errors for the BUILD_BUG_ON_ZERO() and
BUILD_BUG_ON_NULL() macros by adding parentheses around the bitfield
widths that begin with a minus sign.

Link: http://lkml.kernel.org/r/20170525120316.24473-6-abbotti@mev.co.uk
Signed-off-by: Ian Abbott <abbotti@mev.co.uk>
Acked-by: Michal Nazarewicz <mina86@mina86.com>
Acked-by: Kees Cook <keescook@chromium.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Jakub Kicinski <jakub.kicinski@netronome.com>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/bug.h       | 74 +----------------------------------------
 include/linux/build_bug.h | 84 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 85 insertions(+), 73 deletions(-)
 create mode 100644 include/linux/build_bug.h

(limited to 'include')

diff --git a/include/linux/bug.h b/include/linux/bug.h
index 483207cb99fb..5d5554c874fd 100644
--- a/include/linux/bug.h
+++ b/include/linux/bug.h
@@ -3,6 +3,7 @@
 
 #include <asm/bug.h>
 #include <linux/compiler.h>
+#include <linux/build_bug.h>
 
 enum bug_trap_type {
 	BUG_TRAP_TYPE_NONE = 0,
@@ -13,82 +14,9 @@ enum bug_trap_type {
 struct pt_regs;
 
 #ifdef __CHECKER__
-#define __BUILD_BUG_ON_NOT_POWER_OF_2(n) (0)
-#define BUILD_BUG_ON_NOT_POWER_OF_2(n) (0)
-#define BUILD_BUG_ON_ZERO(e) (0)
-#define BUILD_BUG_ON_NULL(e) ((void *)0)
-#define BUILD_BUG_ON_INVALID(e) (0)
-#define BUILD_BUG_ON_MSG(cond, msg) (0)
-#define BUILD_BUG_ON(condition) (0)
-#define BUILD_BUG() (0)
 #define MAYBE_BUILD_BUG_ON(cond) (0)
 #else /* __CHECKER__ */
 
-/* Force a compilation error if a constant expression is not a power of 2 */
-#define __BUILD_BUG_ON_NOT_POWER_OF_2(n)	\
-	BUILD_BUG_ON(((n) & ((n) - 1)) != 0)
-#define BUILD_BUG_ON_NOT_POWER_OF_2(n)			\
-	BUILD_BUG_ON((n) == 0 || (((n) & ((n) - 1)) != 0))
-
-/*
- * Force a compilation error if condition is true, but also produce a
- * result (of value 0 and type size_t), so the expression can be used
- * e.g. in a structure initializer (or where-ever else comma expressions
- * aren't permitted).
- */
-#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:(-!!(e)); }))
-#define BUILD_BUG_ON_NULL(e) ((void *)sizeof(struct { int:(-!!(e)); }))
-
-/*
- * BUILD_BUG_ON_INVALID() permits the compiler to check the validity of the
- * expression but avoids the generation of any code, even if that expression
- * has side-effects.
- */
-#define BUILD_BUG_ON_INVALID(e) ((void)(sizeof((__force long)(e))))
-
-/**
- * BUILD_BUG_ON_MSG - break compile if a condition is true & emit supplied
- *		      error message.
- * @condition: the condition which the compiler should know is false.
- *
- * See BUILD_BUG_ON for description.
- */
-#define BUILD_BUG_ON_MSG(cond, msg) compiletime_assert(!(cond), msg)
-
-/**
- * BUILD_BUG_ON - break compile if a condition is true.
- * @condition: the condition which the compiler should know is false.
- *
- * If you have some code which relies on certain constants being equal, or
- * some other compile-time-evaluated condition, you should use BUILD_BUG_ON to
- * detect if someone changes it.
- *
- * The implementation uses gcc's reluctance to create a negative array, but gcc
- * (as of 4.4) only emits that error for obvious cases (e.g. not arguments to
- * inline functions).  Luckily, in 4.3 they added the "error" function
- * attribute just for this type of case.  Thus, we use a negative sized array
- * (should always create an error on gcc versions older than 4.4) and then call
- * an undefined function with the error attribute (should always create an
- * error on gcc 4.3 and later).  If for some reason, neither creates a
- * compile-time error, we'll still have a link-time error, which is harder to
- * track down.
- */
-#ifndef __OPTIMIZE__
-#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)]))
-#else
-#define BUILD_BUG_ON(condition) \
-	BUILD_BUG_ON_MSG(condition, "BUILD_BUG_ON failed: " #condition)
-#endif
-
-/**
- * BUILD_BUG - break compile if used.
- *
- * If you have some code that you expect the compiler to eliminate at
- * build time, you should use BUILD_BUG to detect if it is
- * unexpectedly used.
- */
-#define BUILD_BUG() BUILD_BUG_ON_MSG(1, "BUILD_BUG failed")
-
 #define MAYBE_BUILD_BUG_ON(cond)			\
 	do {						\
 		if (__builtin_constant_p((cond)))       \
diff --git a/include/linux/build_bug.h b/include/linux/build_bug.h
new file mode 100644
index 000000000000..b7d22d60008a
--- /dev/null
+++ b/include/linux/build_bug.h
@@ -0,0 +1,84 @@
+#ifndef _LINUX_BUILD_BUG_H
+#define _LINUX_BUILD_BUG_H
+
+#include <linux/compiler.h>
+
+#ifdef __CHECKER__
+#define __BUILD_BUG_ON_NOT_POWER_OF_2(n) (0)
+#define BUILD_BUG_ON_NOT_POWER_OF_2(n) (0)
+#define BUILD_BUG_ON_ZERO(e) (0)
+#define BUILD_BUG_ON_NULL(e) ((void *)0)
+#define BUILD_BUG_ON_INVALID(e) (0)
+#define BUILD_BUG_ON_MSG(cond, msg) (0)
+#define BUILD_BUG_ON(condition) (0)
+#define BUILD_BUG() (0)
+#else /* __CHECKER__ */
+
+/* Force a compilation error if a constant expression is not a power of 2 */
+#define __BUILD_BUG_ON_NOT_POWER_OF_2(n)	\
+	BUILD_BUG_ON(((n) & ((n) - 1)) != 0)
+#define BUILD_BUG_ON_NOT_POWER_OF_2(n)			\
+	BUILD_BUG_ON((n) == 0 || (((n) & ((n) - 1)) != 0))
+
+/*
+ * Force a compilation error if condition is true, but also produce a
+ * result (of value 0 and type size_t), so the expression can be used
+ * e.g. in a structure initializer (or where-ever else comma expressions
+ * aren't permitted).
+ */
+#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:(-!!(e)); }))
+#define BUILD_BUG_ON_NULL(e) ((void *)sizeof(struct { int:(-!!(e)); }))
+
+/*
+ * BUILD_BUG_ON_INVALID() permits the compiler to check the validity of the
+ * expression but avoids the generation of any code, even if that expression
+ * has side-effects.
+ */
+#define BUILD_BUG_ON_INVALID(e) ((void)(sizeof((__force long)(e))))
+
+/**
+ * BUILD_BUG_ON_MSG - break compile if a condition is true & emit supplied
+ *		      error message.
+ * @condition: the condition which the compiler should know is false.
+ *
+ * See BUILD_BUG_ON for description.
+ */
+#define BUILD_BUG_ON_MSG(cond, msg) compiletime_assert(!(cond), msg)
+
+/**
+ * BUILD_BUG_ON - break compile if a condition is true.
+ * @condition: the condition which the compiler should know is false.
+ *
+ * If you have some code which relies on certain constants being equal, or
+ * some other compile-time-evaluated condition, you should use BUILD_BUG_ON to
+ * detect if someone changes it.
+ *
+ * The implementation uses gcc's reluctance to create a negative array, but gcc
+ * (as of 4.4) only emits that error for obvious cases (e.g. not arguments to
+ * inline functions).  Luckily, in 4.3 they added the "error" function
+ * attribute just for this type of case.  Thus, we use a negative sized array
+ * (should always create an error on gcc versions older than 4.4) and then call
+ * an undefined function with the error attribute (should always create an
+ * error on gcc 4.3 and later).  If for some reason, neither creates a
+ * compile-time error, we'll still have a link-time error, which is harder to
+ * track down.
+ */
+#ifndef __OPTIMIZE__
+#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)]))
+#else
+#define BUILD_BUG_ON(condition) \
+	BUILD_BUG_ON_MSG(condition, "BUILD_BUG_ON failed: " #condition)
+#endif
+
+/**
+ * BUILD_BUG - break compile if used.
+ *
+ * If you have some code that you expect the compiler to eliminate at
+ * build time, you should use BUILD_BUG to detect if it is
+ * unexpectedly used.
+ */
+#define BUILD_BUG() BUILD_BUG_ON_MSG(1, "BUILD_BUG failed")
+
+#endif	/* __CHECKER__ */
+
+#endif	/* _LINUX_BUILD_BUG_H */
-- 
cgit v1.2.3


From 287f3ca563d8ba0ede4ac0cec84218a1ea5e848f Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Mon, 10 Jul 2017 15:51:10 -0700
Subject: ARM: fix rd_size declaration

The global variable 'rd_size' is declared as 'int' in source file
arch/arm/kernel/atags_parse.c and as 'unsigned long' in
drivers/block/brd.c.  Fix this inconsistency.

Additionally, remove the declarations of rd_image_start, rd_prompt and
rd_doload from parse_tag_ramdisk() since these duplicate existing
declarations in <linux/initrd.h>.

Link: http://lkml.kernel.org/r/20170627065024.12347-1-bart.vanassche@wdc.com
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Acked-by: Russell King <rmk+kernel@armlinux.org.uk>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Jan Kara <jack@suse.cz>
Cc: Jason Yan <yanaijie@huawei.com>
Cc: Zhaohongjiang <zhaohongjiang@huawei.com>
Cc: Miao Xie <miaoxie@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arm/kernel/atags_parse.c | 3 +--
 drivers/block/brd.c           | 1 +
 include/linux/initrd.h        | 3 +++
 3 files changed, 5 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/arm/kernel/atags_parse.c b/arch/arm/kernel/atags_parse.c
index 68c6ae0b9e4c..98fbfd235ac8 100644
--- a/arch/arm/kernel/atags_parse.c
+++ b/arch/arm/kernel/atags_parse.c
@@ -18,6 +18,7 @@
  */
 
 #include <linux/init.h>
+#include <linux/initrd.h>
 #include <linux/kernel.h>
 #include <linux/fs.h>
 #include <linux/root_dev.h>
@@ -91,8 +92,6 @@ __tagtable(ATAG_VIDEOTEXT, parse_tag_videotext);
 #ifdef CONFIG_BLK_DEV_RAM
 static int __init parse_tag_ramdisk(const struct tag *tag)
 {
-	extern int rd_size, rd_image_start, rd_prompt, rd_doload;
-
 	rd_image_start = tag->u.ramdisk.start;
 	rd_doload = (tag->u.ramdisk.flags & 1) == 0;
 	rd_prompt = (tag->u.ramdisk.flags & 2) == 0;
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 17723fd50a53..104b71c0490d 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/init.h>
+#include <linux/initrd.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/major.h>
diff --git a/include/linux/initrd.h b/include/linux/initrd.h
index 55289d261b4f..bc67b767f9ce 100644
--- a/include/linux/initrd.h
+++ b/include/linux/initrd.h
@@ -10,6 +10,9 @@ extern int rd_prompt;
 /* starting block # of image */
 extern int rd_image_start;
 
+/* size of a single RAM disk */
+extern unsigned long rd_size;
+
 /* 1 if it is not an error if initrd_start < memory_start */
 extern int initrd_below_start_ok;
 
-- 
cgit v1.2.3


From e5af323c9badd5dc09af7ccf9d45616ebffc623c Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <mawilcox@microsoft.com>
Date: Mon, 10 Jul 2017 15:51:29 -0700
Subject: bitmap: optimise bitmap_set and bitmap_clear of a single bit

We have eight users calling bitmap_clear for a single bit and seventeen
calling bitmap_set for a single bit.  Rather than fix all of them to
call __clear_bit or __set_bit, turn bitmap_clear and bitmap_set into
inline functions and make this special case efficient.

Link: http://lkml.kernel.org/r/20170628153221.11322-3-willy@infradead.org
Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com>
Acked-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/bitmap.h | 23 ++++++++++++++++++++---
 lib/bitmap.c           |  8 ++++----
 lib/test_bitmap.c      |  3 ---
 3 files changed, 24 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 3b77588a9360..4e0f0c8167af 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -112,9 +112,8 @@ extern int __bitmap_intersects(const unsigned long *bitmap1,
 extern int __bitmap_subset(const unsigned long *bitmap1,
 			const unsigned long *bitmap2, unsigned int nbits);
 extern int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits);
-
-extern void bitmap_set(unsigned long *map, unsigned int start, int len);
-extern void bitmap_clear(unsigned long *map, unsigned int start, int len);
+extern void __bitmap_set(unsigned long *map, unsigned int start, int len);
+extern void __bitmap_clear(unsigned long *map, unsigned int start, int len);
 
 extern unsigned long bitmap_find_next_zero_area_off(unsigned long *map,
 						    unsigned long size,
@@ -315,6 +314,24 @@ static __always_inline int bitmap_weight(const unsigned long *src, unsigned int
 	return __bitmap_weight(src, nbits);
 }
 
+static __always_inline void bitmap_set(unsigned long *map, unsigned int start,
+		unsigned int nbits)
+{
+	if (__builtin_constant_p(nbits) && nbits == 1)
+		__set_bit(start, map);
+	else
+		__bitmap_set(map, start, nbits);
+}
+
+static __always_inline void bitmap_clear(unsigned long *map, unsigned int start,
+		unsigned int nbits)
+{
+	if (__builtin_constant_p(nbits) && nbits == 1)
+		__clear_bit(start, map);
+	else
+		__bitmap_clear(map, start, nbits);
+}
+
 static inline void bitmap_shift_right(unsigned long *dst, const unsigned long *src,
 				unsigned int shift, int nbits)
 {
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 08c6ef3a2b6f..9a532805364b 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -251,7 +251,7 @@ int __bitmap_weight(const unsigned long *bitmap, unsigned int bits)
 }
 EXPORT_SYMBOL(__bitmap_weight);
 
-void bitmap_set(unsigned long *map, unsigned int start, int len)
+void __bitmap_set(unsigned long *map, unsigned int start, int len)
 {
 	unsigned long *p = map + BIT_WORD(start);
 	const unsigned int size = start + len;
@@ -270,9 +270,9 @@ void bitmap_set(unsigned long *map, unsigned int start, int len)
 		*p |= mask_to_set;
 	}
 }
-EXPORT_SYMBOL(bitmap_set);
+EXPORT_SYMBOL(__bitmap_set);
 
-void bitmap_clear(unsigned long *map, unsigned int start, int len)
+void __bitmap_clear(unsigned long *map, unsigned int start, int len)
 {
 	unsigned long *p = map + BIT_WORD(start);
 	const unsigned int size = start + len;
@@ -291,7 +291,7 @@ void bitmap_clear(unsigned long *map, unsigned int start, int len)
 		*p &= ~mask_to_clear;
 	}
 }
-EXPORT_SYMBOL(bitmap_clear);
+EXPORT_SYMBOL(__bitmap_clear);
 
 /**
  * bitmap_find_next_zero_area_off - find a contiguous aligned zero area
diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c
index 252d3bddbe7d..2526a2975c51 100644
--- a/lib/test_bitmap.c
+++ b/lib/test_bitmap.c
@@ -333,9 +333,6 @@ static void __init test_bitmap_u32_array_conversions(void)
 	}
 }
 
-#define __bitmap_set(a, b, c)	bitmap_set(a, b, c)
-#define __bitmap_clear(a, b, c)	bitmap_clear(a, b, c)
-
 static void noinline __init test_mem_optimisations(void)
 {
 	DECLARE_BITMAP(bmap1, 1024);
-- 
cgit v1.2.3


From 2a98dc028f911a7c59c87d11d4eed6626be1605b Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <mawilcox@microsoft.com>
Date: Mon, 10 Jul 2017 15:51:32 -0700
Subject: include/linux/bitmap.h: turn bitmap_set and bitmap_clear into memset
 when possible

Several callers have constant 'start' and an 'nbits' that is a multiple
of 8, so we can turn them into calls to memset.  We don't need the
entirety of 'start' and 'nbits' to be constant, we just need to know
whether they're divisible by 8.

Link: http://lkml.kernel.org/r/20170628153221.11322-4-willy@infradead.org
Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com>
Acked-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/bitmap.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include')

diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 4e0f0c8167af..c04c9d155e59 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -319,6 +319,9 @@ static __always_inline void bitmap_set(unsigned long *map, unsigned int start,
 {
 	if (__builtin_constant_p(nbits) && nbits == 1)
 		__set_bit(start, map);
+	else if (__builtin_constant_p(start & 7) && IS_ALIGNED(start, 8) &&
+		 __builtin_constant_p(nbits & 7) && IS_ALIGNED(nbits, 8))
+		memset((char *)map + start / 8, 0xff, nbits / 8);
 	else
 		__bitmap_set(map, start, nbits);
 }
@@ -328,6 +331,9 @@ static __always_inline void bitmap_clear(unsigned long *map, unsigned int start,
 {
 	if (__builtin_constant_p(nbits) && nbits == 1)
 		__clear_bit(start, map);
+	else if (__builtin_constant_p(start & 7) && IS_ALIGNED(start, 8) &&
+		 __builtin_constant_p(nbits & 7) && IS_ALIGNED(nbits, 8))
+		memset((char *)map + start / 8, 0, nbits / 8);
 	else
 		__bitmap_clear(map, start, nbits);
 }
-- 
cgit v1.2.3


From 2c6deb01525ac11cc03c44fe31e3f45ce2cadaf9 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <mawilcox@microsoft.com>
Date: Mon, 10 Jul 2017 15:51:35 -0700
Subject: bitmap: use memcmp optimisation in more situations

Commit 7dd968163f7c ("bitmap: bitmap_equal memcmp optimization") was
rather more restrictive than necessary; we can use memcmp() to implement
bitmap_equal() as long as the number of bits can be proved to be a
multiple of 8.  And architectures other than s390 may be able to make
good use of this optimisation.

[arnd@arndb.de: fix build: add a memcmp() declaration]
  Link: http://lkml.kernel.org/r/20170630153908.3439707-1-arnd@arndb.de
Link: http://lkml.kernel.org/r/20170628153221.11322-5-willy@infradead.org
Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arm/boot/compressed/decompress.c | 1 +
 include/linux/bitmap.h                | 4 +---
 2 files changed, 2 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/arch/arm/boot/compressed/decompress.c b/arch/arm/boot/compressed/decompress.c
index ea7832702a8f..f3a4bedd1afc 100644
--- a/arch/arm/boot/compressed/decompress.c
+++ b/arch/arm/boot/compressed/decompress.c
@@ -33,6 +33,7 @@ extern void error(char *);
 /* Not needed, but used in some headers pulled in by decompressors */
 extern char * strstr(const char * s1, const char *s2);
 extern size_t strlen(const char *s);
+extern int memcmp(const void *cs, const void *ct, size_t count);
 
 #ifdef CONFIG_KERNEL_GZIP
 #include "../../../../lib/decompress_inflate.c"
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index c04c9d155e59..5797ca6fdfe2 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -266,10 +266,8 @@ static inline int bitmap_equal(const unsigned long *src1,
 {
 	if (small_const_nbits(nbits))
 		return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits));
-#ifdef CONFIG_S390
-	if (__builtin_constant_p(nbits) && (nbits % BITS_PER_LONG) == 0)
+	if (__builtin_constant_p(nbits & 7) && IS_ALIGNED(nbits, 8))
 		return !memcmp(src1, src2, nbits / 8);
-#endif
 	return __bitmap_equal(src1, src2, nbits);
 }
 
-- 
cgit v1.2.3


From a94c33dd1f677d16c4f1a162b4b3e9eba1b07c24 Mon Sep 17 00:00:00 2001
From: Thomas Meyer <thomas@m3y3r.de>
Date: Mon, 10 Jul 2017 15:51:58 -0700
Subject: lib/extable.c: use bsearch() library function in search_extable()

[thomas@m3y3r.de: v3: fix arch specific implementations]
  Link: http://lkml.kernel.org/r/1497890858.12931.7.camel@m3y3r.de
Signed-off-by: Thomas Meyer <thomas@m3y3r.de>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/mips/kernel/module.c |  3 ++-
 arch/mips/kernel/traps.c  |  3 ++-
 arch/sh/mm/extable_64.c   | 34 ++++++++++++++++++----------------
 arch/sparc/mm/extable.c   | 28 ++++++++++++++--------------
 include/linux/extable.h   |  5 +++--
 kernel/extable.c          |  3 ++-
 kernel/module.c           |  2 +-
 lib/extable.c             | 41 +++++++++++++++++++++--------------------
 8 files changed, 63 insertions(+), 56 deletions(-)

(limited to 'include')

diff --git a/arch/mips/kernel/module.c b/arch/mips/kernel/module.c
index 94627a3a6a0d..50c020c47e54 100644
--- a/arch/mips/kernel/module.c
+++ b/arch/mips/kernel/module.c
@@ -317,7 +317,8 @@ const struct exception_table_entry *search_module_dbetables(unsigned long addr)
 
 	spin_lock_irqsave(&dbe_lock, flags);
 	list_for_each_entry(dbe, &dbe_list, dbe_list) {
-		e = search_extable(dbe->dbe_start, dbe->dbe_end - 1, addr);
+		e = search_extable(dbe->dbe_start,
+				   dbe->dbe_end - dbe->dbe_start, addr);
 		if (e)
 			break;
 	}
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 38dfa27730ff..b68b4d0726d3 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -429,7 +429,8 @@ static const struct exception_table_entry *search_dbe_tables(unsigned long addr)
 {
 	const struct exception_table_entry *e;
 
-	e = search_extable(__start___dbe_table, __stop___dbe_table - 1, addr);
+	e = search_extable(__start___dbe_table,
+			   __stop___dbe_table - __start___dbe_table, addr);
 	if (!e)
 		e = search_module_dbetables(addr);
 	return e;
diff --git a/arch/sh/mm/extable_64.c b/arch/sh/mm/extable_64.c
index b90cdfad2c78..7a3b4d33d2e7 100644
--- a/arch/sh/mm/extable_64.c
+++ b/arch/sh/mm/extable_64.c
@@ -10,6 +10,7 @@
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  */
+#include <linux/bsearch.h>
 #include <linux/rwsem.h>
 #include <linux/extable.h>
 #include <linux/uaccess.h>
@@ -40,10 +41,23 @@ static const struct exception_table_entry *check_exception_ranges(unsigned long
 	return NULL;
 }
 
+static int cmp_ex_search(const void *key, const void *elt)
+{
+	const struct exception_table_entry *_elt = elt;
+	unsigned long _key = *(unsigned long *)key;
+
+	/* avoid overflow */
+	if (_key > _elt->insn)
+		return 1;
+	if (_key < _elt->insn)
+		return -1;
+	return 0;
+}
+
 /* Simple binary search */
 const struct exception_table_entry *
-search_extable(const struct exception_table_entry *first,
-		 const struct exception_table_entry *last,
+search_extable(const struct exception_table_entry *base,
+		 const size_t num,
 		 unsigned long value)
 {
 	const struct exception_table_entry *mid;
@@ -52,20 +66,8 @@ search_extable(const struct exception_table_entry *first,
 	if (mid)
 		return mid;
 
-        while (first <= last) {
-		long diff;
-
-		mid = (last - first) / 2 + first;
-		diff = mid->insn - value;
-                if (diff == 0)
-                        return mid;
-                else if (diff < 0)
-                        first = mid+1;
-                else
-                        last = mid-1;
-        }
-
-        return NULL;
+	return bsearch(&value, base, num,
+		       sizeof(struct exception_table_entry), cmp_ex_search);
 }
 
 int fixup_exception(struct pt_regs *regs)
diff --git a/arch/sparc/mm/extable.c b/arch/sparc/mm/extable.c
index db214e9931d9..2422511dc8c5 100644
--- a/arch/sparc/mm/extable.c
+++ b/arch/sparc/mm/extable.c
@@ -13,11 +13,11 @@ void sort_extable(struct exception_table_entry *start,
 
 /* Caller knows they are in a range if ret->fixup == 0 */
 const struct exception_table_entry *
-search_extable(const struct exception_table_entry *start,
-	       const struct exception_table_entry *last,
+search_extable(const struct exception_table_entry *base,
+	       const size_t num,
 	       unsigned long value)
 {
-	const struct exception_table_entry *walk;
+	int i;
 
 	/* Single insn entries are encoded as:
 	 *	word 1:	insn address
@@ -37,30 +37,30 @@ search_extable(const struct exception_table_entry *start,
 	 */
 
 	/* 1. Try to find an exact match. */
-	for (walk = start; walk <= last; walk++) {
-		if (walk->fixup == 0) {
+	for (i = 0; i < num; i++) {
+		if (base[i].fixup == 0) {
 			/* A range entry, skip both parts. */
-			walk++;
+			i++;
 			continue;
 		}
 
 		/* A deleted entry; see trim_init_extable */
-		if (walk->fixup == -1)
+		if (base[i].fixup == -1)
 			continue;
 
-		if (walk->insn == value)
-			return walk;
+		if (base[i].insn == value)
+			return &base[i];
 	}
 
 	/* 2. Try to find a range match. */
-	for (walk = start; walk <= (last - 1); walk++) {
-		if (walk->fixup)
+	for (i = 0; i < (num - 1); i++) {
+		if (base[i].fixup)
 			continue;
 
-		if (walk[0].insn <= value && walk[1].insn > value)
-			return walk;
+		if (base[i].insn <= value && base[i + 1].insn > value)
+			return &base[i];
 
-		walk++;
+		i++;
 	}
 
         return NULL;
diff --git a/include/linux/extable.h b/include/linux/extable.h
index 7effea4b257d..28addad0dda7 100644
--- a/include/linux/extable.h
+++ b/include/linux/extable.h
@@ -2,13 +2,14 @@
 #define _LINUX_EXTABLE_H
 
 #include <linux/stddef.h>	/* for NULL */
+#include <linux/types.h>
 
 struct module;
 struct exception_table_entry;
 
 const struct exception_table_entry *
-search_extable(const struct exception_table_entry *first,
-	       const struct exception_table_entry *last,
+search_extable(const struct exception_table_entry *base,
+	       const size_t num,
 	       unsigned long value);
 void sort_extable(struct exception_table_entry *start,
 		  struct exception_table_entry *finish);
diff --git a/kernel/extable.c b/kernel/extable.c
index 223df4a328a4..38c2412401a1 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -55,7 +55,8 @@ const struct exception_table_entry *search_exception_tables(unsigned long addr)
 {
 	const struct exception_table_entry *e;
 
-	e = search_extable(__start___ex_table, __stop___ex_table-1, addr);
+	e = search_extable(__start___ex_table,
+			   __stop___ex_table - __start___ex_table, addr);
 	if (!e)
 		e = search_module_extables(addr);
 	return e;
diff --git a/kernel/module.c b/kernel/module.c
index b3dbdde82e80..b0f92a365140 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -4196,7 +4196,7 @@ const struct exception_table_entry *search_module_extables(unsigned long addr)
 		goto out;
 
 	e = search_extable(mod->extable,
-			   mod->extable + mod->num_exentries - 1,
+			   mod->num_exentries,
 			   addr);
 out:
 	preempt_enable();
diff --git a/lib/extable.c b/lib/extable.c
index 62968daa66a9..f54996fdd0b8 100644
--- a/lib/extable.c
+++ b/lib/extable.c
@@ -9,6 +9,7 @@
  * 2 of the License, or (at your option) any later version.
  */
 
+#include <linux/bsearch.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/sort.h>
@@ -51,7 +52,7 @@ static void swap_ex(void *a, void *b, int size)
  * This is used both for the kernel exception table and for
  * the exception tables of modules that get loaded.
  */
-static int cmp_ex(const void *a, const void *b)
+static int cmp_ex_sort(const void *a, const void *b)
 {
 	const struct exception_table_entry *x = a, *y = b;
 
@@ -67,7 +68,7 @@ void sort_extable(struct exception_table_entry *start,
 		  struct exception_table_entry *finish)
 {
 	sort(start, finish - start, sizeof(struct exception_table_entry),
-	     cmp_ex, swap_ex);
+	     cmp_ex_sort, swap_ex);
 }
 
 #ifdef CONFIG_MODULES
@@ -93,6 +94,20 @@ void trim_init_extable(struct module *m)
 #endif /* !ARCH_HAS_SORT_EXTABLE */
 
 #ifndef ARCH_HAS_SEARCH_EXTABLE
+
+static int cmp_ex_search(const void *key, const void *elt)
+{
+	const struct exception_table_entry *_elt = elt;
+	unsigned long _key = *(unsigned long *)key;
+
+	/* avoid overflow */
+	if (_key > ex_to_insn(_elt))
+		return 1;
+	if (_key < ex_to_insn(_elt))
+		return -1;
+	return 0;
+}
+
 /*
  * Search one exception table for an entry corresponding to the
  * given instruction address, and return the address of the entry,
@@ -101,25 +116,11 @@ void trim_init_extable(struct module *m)
  * already sorted.
  */
 const struct exception_table_entry *
-search_extable(const struct exception_table_entry *first,
-	       const struct exception_table_entry *last,
+search_extable(const struct exception_table_entry *base,
+	       const size_t num,
 	       unsigned long value)
 {
-	while (first <= last) {
-		const struct exception_table_entry *mid;
-
-		mid = ((last - first) >> 1) + first;
-		/*
-		 * careful, the distance between value and insn
-		 * can be larger than MAX_LONG:
-		 */
-		if (ex_to_insn(mid) < value)
-			first = mid + 1;
-		else if (ex_to_insn(mid) > value)
-			last = mid - 1;
-		else
-			return mid;
-	}
-	return NULL;
+	return bsearch(&value, base, num,
+		       sizeof(struct exception_table_entry), cmp_ex_search);
 }
 #endif
-- 
cgit v1.2.3


From c4fac9100456995c10b65c13be84554258ed7fc8 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 5 Jul 2017 16:25:37 +0100
Subject: 9p: Implement show_options

Implement the show_options superblock op for 9p as part of a bid to get
rid of s_options and generic_show_options() to make it easier to implement
a context-based mount where the mount options can be passed individually
over a file descriptor.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Eric Van Hensbergen <ericvh@gmail.com>
cc: Ron Minnich <rminnich@sandia.gov>
cc: Latchesar Ionkov <lucho@ionkov.net>
cc: v9fs-developer@lists.sourceforge.net
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/9p/v9fs.c               | 61 ++++++++++++++++++++++++++++++++++++++++++++++
 fs/9p/v9fs.h               |  3 +++
 fs/9p/vfs_super.c          |  6 ++---
 include/net/9p/client.h    | 13 ++++++++++
 include/net/9p/transport.h |  1 +
 net/9p/client.c            | 25 +++++++++++++++++++
 net/9p/trans_fd.c          | 31 ++++++++++++++++++++---
 net/9p/trans_rdma.c        | 31 ++++++++++++++++++++---
 8 files changed, 161 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index c202930086ed..8fb89ddc6cc7 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -33,6 +33,7 @@
 #include <linux/parser.h>
 #include <linux/idr.h>
 #include <linux/slab.h>
+#include <linux/seq_file.h>
 #include <net/9p/9p.h>
 #include <net/9p/client.h>
 #include <net/9p/transport.h>
@@ -82,6 +83,13 @@ static const match_table_t tokens = {
 	{Opt_err, NULL}
 };
 
+static const char *const v9fs_cache_modes[nr__p9_cache_modes] = {
+	[CACHE_NONE]	= "none",
+	[CACHE_MMAP]	= "mmap",
+	[CACHE_LOOSE]	= "loose",
+	[CACHE_FSCACHE]	= "fscache",
+};
+
 /* Interpret mount options for cache mode */
 static int get_cache_mode(char *s)
 {
@@ -104,6 +112,58 @@ static int get_cache_mode(char *s)
 	return version;
 }
 
+/*
+ * Display the mount options in /proc/mounts.
+ */
+int v9fs_show_options(struct seq_file *m, struct dentry *root)
+{
+	struct v9fs_session_info *v9ses = root->d_sb->s_fs_info;
+
+	if (v9ses->debug)
+		seq_printf(m, ",debug=%x", v9ses->debug);
+	if (!uid_eq(v9ses->dfltuid, V9FS_DEFUID))
+		seq_printf(m, ",dfltuid=%u",
+			   from_kuid_munged(&init_user_ns, v9ses->dfltuid));
+	if (!gid_eq(v9ses->dfltgid, V9FS_DEFGID))
+		seq_printf(m, ",dfltgid=%u",
+			   from_kgid_munged(&init_user_ns, v9ses->dfltgid));
+	if (v9ses->afid != ~0)
+		seq_printf(m, ",afid=%u", v9ses->afid);
+	if (strcmp(v9ses->uname, V9FS_DEFUSER) != 0)
+		seq_printf(m, ",uname=%s", v9ses->uname);
+	if (strcmp(v9ses->aname, V9FS_DEFANAME) != 0)
+		seq_printf(m, ",aname=%s", v9ses->aname);
+	if (v9ses->nodev)
+		seq_puts(m, ",nodevmap");
+	if (v9ses->cache)
+		seq_printf(m, ",%s", v9fs_cache_modes[v9ses->cache]);
+#ifdef CONFIG_9P_FSCACHE
+	if (v9ses->cachetag && v9ses->cache == CACHE_FSCACHE)
+		seq_printf(m, ",cachetag=%s", v9ses->cachetag);
+#endif
+
+	switch (v9ses->flags & V9FS_ACCESS_MASK) {
+	case V9FS_ACCESS_USER:
+		seq_puts(m, ",access=user");
+		break;
+	case V9FS_ACCESS_ANY:
+		seq_puts(m, ",access=any");
+		break;
+	case V9FS_ACCESS_CLIENT:
+		seq_puts(m, ",access=client");
+		break;
+	case V9FS_ACCESS_SINGLE:
+		seq_printf(m, ",access=%u",
+			   from_kuid_munged(&init_user_ns, v9ses->uid));
+		break;
+	}
+
+	if (v9ses->flags & V9FS_POSIX_ACL)
+		seq_puts(m, ",posixacl");
+
+	return p9_show_client_options(m, v9ses->clnt);
+}
+
 /**
  * v9fs_parse_options - parse mount options into session structure
  * @v9ses: existing v9fs session information
@@ -230,6 +290,7 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts)
 			break;
 		case Opt_cachetag:
 #ifdef CONFIG_9P_FSCACHE
+			kfree(v9ses->cachetag);
 			v9ses->cachetag = match_strdup(&args[0]);
 #endif
 			break;
diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h
index 76eaf49abd3a..982e017acadb 100644
--- a/fs/9p/v9fs.h
+++ b/fs/9p/v9fs.h
@@ -67,6 +67,7 @@ enum p9_cache_modes {
 	CACHE_MMAP,
 	CACHE_LOOSE,
 	CACHE_FSCACHE,
+	nr__p9_cache_modes
 };
 
 /**
@@ -137,6 +138,8 @@ static inline struct v9fs_inode *V9FS_I(const struct inode *inode)
 	return container_of(inode, struct v9fs_inode, vfs_inode);
 }
 
+extern int v9fs_show_options(struct seq_file *m, struct dentry *root);
+
 struct p9_fid *v9fs_session_init(struct v9fs_session_info *, const char *,
 									char *);
 extern void v9fs_session_close(struct v9fs_session_info *v9ses);
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index a0965fb587a5..8b75463cb211 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -33,7 +33,6 @@
 #include <linux/string.h>
 #include <linux/inet.h>
 #include <linux/pagemap.h>
-#include <linux/seq_file.h>
 #include <linux/mount.h>
 #include <linux/idr.h>
 #include <linux/sched.h>
@@ -104,7 +103,6 @@ v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses,
 		sb->s_flags |= MS_POSIXACL;
 #endif
 
-	save_mount_options(sb, data);
 	return 0;
 }
 
@@ -349,7 +347,7 @@ static const struct super_operations v9fs_super_ops = {
 	.destroy_inode = v9fs_destroy_inode,
 	.statfs = simple_statfs,
 	.evict_inode = v9fs_evict_inode,
-	.show_options = generic_show_options,
+	.show_options = v9fs_show_options,
 	.umount_begin = v9fs_umount_begin,
 	.write_inode = v9fs_write_inode,
 };
@@ -360,7 +358,7 @@ static const struct super_operations v9fs_super_ops_dotl = {
 	.statfs = v9fs_statfs,
 	.drop_inode = v9fs_drop_inode,
 	.evict_inode = v9fs_evict_inode,
-	.show_options = generic_show_options,
+	.show_options = v9fs_show_options,
 	.umount_begin = v9fs_umount_begin,
 	.write_inode = v9fs_write_inode_dotl,
 };
diff --git a/include/net/9p/client.h b/include/net/9p/client.h
index b582339ccef5..7af9d769b97d 100644
--- a/include/net/9p/client.h
+++ b/include/net/9p/client.h
@@ -157,6 +157,18 @@ struct p9_client {
 	enum p9_trans_status status;
 	void *trans;
 
+	union {
+		struct {
+			int rfd;
+			int wfd;
+		} fd;
+		struct {
+			u16 port;
+			bool privport;
+
+		} tcp;
+	} trans_opts;
+
 	struct p9_idpool *fidpool;
 	struct list_head fidlist;
 
@@ -213,6 +225,7 @@ struct p9_dirent {
 
 struct iov_iter;
 
+int p9_show_client_options(struct seq_file *m, struct p9_client *clnt);
 int p9_client_statfs(struct p9_fid *fid, struct p9_rstatfs *sb);
 int p9_client_rename(struct p9_fid *fid, struct p9_fid *newdirfid,
 		     const char *name);
diff --git a/include/net/9p/transport.h b/include/net/9p/transport.h
index 5122b5e40f78..1625fb842ac4 100644
--- a/include/net/9p/transport.h
+++ b/include/net/9p/transport.h
@@ -62,6 +62,7 @@ struct p9_trans_module {
 	int (*cancelled)(struct p9_client *, struct p9_req_t *req);
 	int (*zc_request)(struct p9_client *, struct p9_req_t *,
 			  struct iov_iter *, struct iov_iter *, int , int, int);
+	int (*show_options)(struct seq_file *, struct p9_client *);
 };
 
 void v9fs_register_trans(struct p9_trans_module *m);
diff --git a/net/9p/client.c b/net/9p/client.c
index 1218fb3b52da..4674235b0d9b 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -37,6 +37,7 @@
 #include <linux/uio.h>
 #include <net/9p/9p.h>
 #include <linux/parser.h>
+#include <linux/seq_file.h>
 #include <net/9p/client.h>
 #include <net/9p/transport.h>
 #include "protocol.h"
@@ -77,6 +78,30 @@ inline int p9_is_proto_dotu(struct p9_client *clnt)
 }
 EXPORT_SYMBOL(p9_is_proto_dotu);
 
+int p9_show_client_options(struct seq_file *m, struct p9_client *clnt)
+{
+	if (clnt->msize != 8192)
+		seq_printf(m, ",msize=%u", clnt->msize);
+	seq_printf(m, "trans=%s", clnt->trans_mod->name);
+
+	switch (clnt->proto_version) {
+	case p9_proto_legacy:
+		seq_puts(m, ",noextend");
+		break;
+	case p9_proto_2000u:
+		seq_puts(m, ",version=9p2000.u");
+		break;
+	case p9_proto_2000L:
+		/* Default */
+		break;
+	}
+
+	if (clnt->trans_mod->show_options)
+		return clnt->trans_mod->show_options(m, clnt);
+	return 0;
+}
+EXPORT_SYMBOL(p9_show_client_options);
+
 /*
  * Some error codes are taken directly from the server replies,
  * make sure they are valid.
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index 7bc2208b6cc4..f2e0eaf58018 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -41,6 +41,7 @@
 #include <linux/file.h>
 #include <linux/parser.h>
 #include <linux/slab.h>
+#include <linux/seq_file.h>
 #include <net/9p/9p.h>
 #include <net/9p/client.h>
 #include <net/9p/transport.h>
@@ -51,6 +52,9 @@
 #define MAX_SOCK_BUF (64*1024)
 #define MAXPOLLWADDR	2
 
+static struct p9_trans_module p9_tcp_trans;
+static struct p9_trans_module p9_fd_trans;
+
 /**
  * struct p9_fd_opts - per-transport options
  * @rfd: file descriptor for reading (trans=fd)
@@ -63,7 +67,7 @@ struct p9_fd_opts {
 	int rfd;
 	int wfd;
 	u16 port;
-	int privport;
+	bool privport;
 };
 
 /*
@@ -720,6 +724,20 @@ static int p9_fd_cancelled(struct p9_client *client, struct p9_req_t *req)
 	return 0;
 }
 
+static int p9_fd_show_options(struct seq_file *m, struct p9_client *clnt)
+{
+	if (clnt->trans_mod == &p9_tcp_trans) {
+		if (clnt->trans_opts.tcp.port != P9_PORT)
+			seq_printf(m, "port=%u", clnt->trans_opts.tcp.port);
+	} else if (clnt->trans_mod == &p9_fd_trans) {
+		if (clnt->trans_opts.fd.rfd != ~0)
+			seq_printf(m, "rfd=%u", clnt->trans_opts.fd.rfd);
+		if (clnt->trans_opts.fd.wfd != ~0)
+			seq_printf(m, "wfd=%u", clnt->trans_opts.fd.wfd);
+	}
+	return 0;
+}
+
 /**
  * parse_opts - parse mount options into p9_fd_opts structure
  * @params: options string passed from mount
@@ -738,7 +756,7 @@ static int parse_opts(char *params, struct p9_fd_opts *opts)
 	opts->port = P9_PORT;
 	opts->rfd = ~0;
 	opts->wfd = ~0;
-	opts->privport = 0;
+	opts->privport = false;
 
 	if (!params)
 		return 0;
@@ -776,7 +794,7 @@ static int parse_opts(char *params, struct p9_fd_opts *opts)
 			opts->wfd = option;
 			break;
 		case Opt_privport:
-			opts->privport = 1;
+			opts->privport = true;
 			break;
 		default:
 			continue;
@@ -942,6 +960,8 @@ p9_fd_create_tcp(struct p9_client *client, const char *addr, char *args)
 
 	csocket = NULL;
 
+	client->trans_opts.tcp.port = opts.port;
+	client->trans_opts.tcp.privport = opts.privport;
 	sin_server.sin_family = AF_INET;
 	sin_server.sin_addr.s_addr = in_aton(addr);
 	sin_server.sin_port = htons(opts.port);
@@ -1020,6 +1040,8 @@ p9_fd_create(struct p9_client *client, const char *addr, char *args)
 	struct p9_fd_opts opts;
 
 	parse_opts(args, &opts);
+	client->trans_opts.fd.rfd = opts.rfd;
+	client->trans_opts.fd.wfd = opts.wfd;
 
 	if (opts.rfd == ~0 || opts.wfd == ~0) {
 		pr_err("Insufficient options for proto=fd\n");
@@ -1044,6 +1066,7 @@ static struct p9_trans_module p9_tcp_trans = {
 	.request = p9_fd_request,
 	.cancel = p9_fd_cancel,
 	.cancelled = p9_fd_cancelled,
+	.show_options = p9_fd_show_options,
 	.owner = THIS_MODULE,
 };
 
@@ -1056,6 +1079,7 @@ static struct p9_trans_module p9_unix_trans = {
 	.request = p9_fd_request,
 	.cancel = p9_fd_cancel,
 	.cancelled = p9_fd_cancelled,
+	.show_options = p9_fd_show_options,
 	.owner = THIS_MODULE,
 };
 
@@ -1068,6 +1092,7 @@ static struct p9_trans_module p9_fd_trans = {
 	.request = p9_fd_request,
 	.cancel = p9_fd_cancel,
 	.cancelled = p9_fd_cancelled,
+	.show_options = p9_fd_show_options,
 	.owner = THIS_MODULE,
 };
 
diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c
index 553ed4ecb6a0..6d8e3031978f 100644
--- a/net/9p/trans_rdma.c
+++ b/net/9p/trans_rdma.c
@@ -43,6 +43,7 @@
 #include <linux/parser.h>
 #include <linux/semaphore.h>
 #include <linux/slab.h>
+#include <linux/seq_file.h>
 #include <net/9p/9p.h>
 #include <net/9p/client.h>
 #include <net/9p/transport.h>
@@ -70,6 +71,8 @@
  * @dm_mr: DMA Memory Region pointer
  * @lkey: The local access only memory region key
  * @timeout: Number of uSecs to wait for connection management events
+ * @privport: Whether a privileged port may be used
+ * @port: The port to use
  * @sq_depth: The depth of the Send Queue
  * @sq_sem: Semaphore for the SQ
  * @rq_depth: The depth of the Receive Queue.
@@ -95,6 +98,8 @@ struct p9_trans_rdma {
 	struct ib_qp *qp;
 	struct ib_cq *cq;
 	long timeout;
+	bool privport;
+	u16 port;
 	int sq_depth;
 	struct semaphore sq_sem;
 	int rq_depth;
@@ -133,10 +138,10 @@ struct p9_rdma_context {
  */
 struct p9_rdma_opts {
 	short port;
+	bool privport;
 	int sq_depth;
 	int rq_depth;
 	long timeout;
-	int privport;
 };
 
 /*
@@ -159,6 +164,23 @@ static match_table_t tokens = {
 	{Opt_err, NULL},
 };
 
+static int p9_rdma_show_options(struct seq_file *m, struct p9_client *clnt)
+{
+	struct p9_trans_rdma *rdma = clnt->trans;
+
+	if (rdma->port != P9_PORT)
+		seq_printf(m, ",port=%u", rdma->port);
+	if (rdma->sq_depth != P9_RDMA_SQ_DEPTH)
+		seq_printf(m, ",sq=%u", rdma->sq_depth);
+	if (rdma->rq_depth != P9_RDMA_RQ_DEPTH)
+		seq_printf(m, ",rq=%u", rdma->rq_depth);
+	if (rdma->timeout != P9_RDMA_TIMEOUT)
+		seq_printf(m, ",timeout=%lu", rdma->timeout);
+	if (rdma->privport)
+		seq_puts(m, ",privport");
+	return 0;
+}
+
 /**
  * parse_opts - parse mount options into rdma options structure
  * @params: options string passed from mount
@@ -177,7 +199,7 @@ static int parse_opts(char *params, struct p9_rdma_opts *opts)
 	opts->sq_depth = P9_RDMA_SQ_DEPTH;
 	opts->rq_depth = P9_RDMA_RQ_DEPTH;
 	opts->timeout = P9_RDMA_TIMEOUT;
-	opts->privport = 0;
+	opts->privport = false;
 
 	if (!params)
 		return 0;
@@ -218,7 +240,7 @@ static int parse_opts(char *params, struct p9_rdma_opts *opts)
 			opts->timeout = option;
 			break;
 		case Opt_privport:
-			opts->privport = 1;
+			opts->privport = true;
 			break;
 		default:
 			continue;
@@ -560,6 +582,8 @@ static struct p9_trans_rdma *alloc_rdma(struct p9_rdma_opts *opts)
 	if (!rdma)
 		return NULL;
 
+	rdma->port = opts->port;
+	rdma->privport = opts->privport;
 	rdma->sq_depth = opts->sq_depth;
 	rdma->rq_depth = opts->rq_depth;
 	rdma->timeout = opts->timeout;
@@ -733,6 +757,7 @@ static struct p9_trans_module p9_rdma_trans = {
 	.request = rdma_request,
 	.cancel = rdma_cancel,
 	.cancelled = rdma_cancelled,
+	.show_options = p9_rdma_show_options,
 };
 
 /**
-- 
cgit v1.2.3


From 1d278a879081ddc40286500e58868aaee47de257 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 5 Jul 2017 16:25:53 +0100
Subject: VFS: Kill off s_options and helpers

Kill off s_options, save/replace_mount_options() and generic_show_options()
as all filesystems now implement ->show_options() for themselves.  This
should make it easier to implement a context-based mount where the mount
options can be passed individually over a file descriptor.

Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 Documentation/filesystems/vfs.txt |  6 ----
 fs/efivarfs/super.c               |  1 -
 fs/namespace.c                    | 59 ---------------------------------------
 fs/super.c                        |  1 -
 include/linux/fs.h                |  9 ------
 5 files changed, 76 deletions(-)

(limited to 'include')

diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index f42b90687d40..ee56a7d10da9 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -1187,12 +1187,6 @@ The underlying reason for the above rules is to make sure, that a
 mount can be accurately replicated (e.g. umounting and mounting again)
 based on the information found in /proc/mounts.
 
-A simple method of saving options at mount/remount time and showing
-them is provided with the save_mount_options() and
-generic_show_options() helper functions.  Please note, that using
-these may have drawbacks.  For more info see header comments for these
-functions in fs/namespace.c.
-
 Resources
 =========
 
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index d7a7c53803c1..5b68e4294faa 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -29,7 +29,6 @@ static const struct super_operations efivarfs_ops = {
 	.statfs = simple_statfs,
 	.drop_inode = generic_delete_inode,
 	.evict_inode = efivarfs_evict_inode,
-	.show_options = generic_show_options,
 };
 
 static struct super_block *efivarfs_sb;
diff --git a/fs/namespace.c b/fs/namespace.c
index 544ab84642eb..0e1fdb306133 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1237,65 +1237,6 @@ struct vfsmount *mnt_clone_internal(const struct path *path)
 	return &p->mnt;
 }
 
-static inline void mangle(struct seq_file *m, const char *s)
-{
-	seq_escape(m, s, " \t\n\\");
-}
-
-/*
- * Simple .show_options callback for filesystems which don't want to
- * implement more complex mount option showing.
- *
- * See also save_mount_options().
- */
-int generic_show_options(struct seq_file *m, struct dentry *root)
-{
-	const char *options;
-
-	rcu_read_lock();
-	options = rcu_dereference(root->d_sb->s_options);
-
-	if (options != NULL && options[0]) {
-		seq_putc(m, ',');
-		mangle(m, options);
-	}
-	rcu_read_unlock();
-
-	return 0;
-}
-EXPORT_SYMBOL(generic_show_options);
-
-/*
- * If filesystem uses generic_show_options(), this function should be
- * called from the fill_super() callback.
- *
- * The .remount_fs callback usually needs to be handled in a special
- * way, to make sure, that previous options are not overwritten if the
- * remount fails.
- *
- * Also note, that if the filesystem's .remount_fs function doesn't
- * reset all options to their default value, but changes only newly
- * given options, then the displayed options will not reflect reality
- * any more.
- */
-void save_mount_options(struct super_block *sb, char *options)
-{
-	BUG_ON(sb->s_options);
-	rcu_assign_pointer(sb->s_options, kstrdup(options, GFP_KERNEL));
-}
-EXPORT_SYMBOL(save_mount_options);
-
-void replace_mount_options(struct super_block *sb, char *options)
-{
-	char *old = sb->s_options;
-	rcu_assign_pointer(sb->s_options, options);
-	if (old) {
-		synchronize_rcu();
-		kfree(old);
-	}
-}
-EXPORT_SYMBOL(replace_mount_options);
-
 #ifdef CONFIG_PROC_FS
 /* iterator; we want it to have access to namespace_sem, thus here... */
 static void *m_start(struct seq_file *m, loff_t *pos)
diff --git a/fs/super.c b/fs/super.c
index dfb56a9665d8..6bc3352adcf3 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -168,7 +168,6 @@ static void destroy_super(struct super_block *s)
 	WARN_ON(!list_empty(&s->s_mounts));
 	put_user_ns(s->s_user_ns);
 	kfree(s->s_subtype);
-	kfree(s->s_options);
 	call_rcu(&s->rcu, destroy_super_rcu);
 }
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index bc0c054894b9..e265b2ea72c6 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1351,11 +1351,6 @@ struct super_block {
 	 */
 	char *s_subtype;
 
-	/*
-	 * Saved mount options for lazy filesystems using
-	 * generic_show_options()
-	 */
-	char __rcu *s_options;
 	const struct dentry_operations *s_d_op; /* default d_op for dentries */
 
 	/*
@@ -3033,10 +3028,6 @@ extern void setattr_copy(struct inode *inode, const struct iattr *attr);
 
 extern int file_update_time(struct file *file);
 
-extern int generic_show_options(struct seq_file *m, struct dentry *root);
-extern void save_mount_options(struct super_block *sb, char *options);
-extern void replace_mount_options(struct super_block *sb, char *options);
-
 static inline bool io_is_direct(struct file *filp)
 {
 	return (filp->f_flags & O_DIRECT) || IS_DAX(filp->f_mapping->host);
-- 
cgit v1.2.3


From 7461279bba4a62d192eda6dd10de68ac0543bfcd Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@imgtec.com>
Date: Sat, 17 Jun 2017 13:52:46 -0700
Subject: dt-bindings: Document img,boston-clock binding

Add device tree binding documentation for the clocks provided by the
MIPS Boston development board from Imagination Technologies, and a
header file describing the available clocks for use by device trees &
driver.

Signed-off-by: Paul Burton <paul.burton@imgtec.com>
Acked-by: Stephen Boyd <sboyd@codeaurora.org>
Cc: Frank Rowand <frowand.list@gmail.com>
Cc: Michael Turquette <mturquette@baylibre.com>
Cc: Rob Herring <robh+dt@kernel.org>
Cc: devicetree@vger.kernel.org
Cc: linux-clk@vger.kernel.org
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/16482/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 .../devicetree/bindings/clock/img,boston-clock.txt | 31 ++++++++++++++++++++++
 MAINTAINERS                                        |  7 +++++
 include/dt-bindings/clock/boston-clock.h           | 14 ++++++++++
 3 files changed, 52 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/clock/img,boston-clock.txt
 create mode 100644 include/dt-bindings/clock/boston-clock.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/clock/img,boston-clock.txt b/Documentation/devicetree/bindings/clock/img,boston-clock.txt
new file mode 100644
index 000000000000..7bc5e9ffb624
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/img,boston-clock.txt
@@ -0,0 +1,31 @@
+Binding for Imagination Technologies MIPS Boston clock sources.
+
+This binding uses the common clock binding[1].
+
+[1] Documentation/devicetree/bindings/clock/clock-bindings.txt
+
+The device node must be a child node of the syscon node corresponding to the
+Boston system's platform registers.
+
+Required properties:
+- compatible : Should be "img,boston-clock".
+- #clock-cells : Should be set to 1.
+  Values available for clock consumers can be found in the header file:
+    <dt-bindings/clock/boston-clock.h>
+
+Example:
+
+	system-controller@17ffd000 {
+		compatible = "img,boston-platform-regs", "syscon";
+		reg = <0x17ffd000 0x1000>;
+
+		clk_boston: clock {
+			compatible = "img,boston-clock";
+			#clock-cells = <1>;
+		};
+	};
+
+	uart0: uart@17ffe000 {
+		/* ... */
+		clocks = <&clk_boston BOSTON_CLK_SYS>;
+	};
diff --git a/MAINTAINERS b/MAINTAINERS
index bcf2d258c0dd..0b977a6bf849 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8504,6 +8504,13 @@ F:	arch/mips/include/asm/mach-loongson32/
 F:	drivers/*/*loongson1*
 F:	drivers/*/*/*loongson1*
 
+MIPS BOSTON DEVELOPMENT BOARD
+M:	Paul Burton <paul.burton@imgtec.com>
+L:	linux-mips@linux-mips.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/clock/img,boston-clock.txt
+F:	include/dt-bindings/clock/boston-clock.h
+
 MIROSOUND PCM20 FM RADIO RECEIVER DRIVER
 M:	Hans Verkuil <hverkuil@xs4all.nl>
 L:	linux-media@vger.kernel.org
diff --git a/include/dt-bindings/clock/boston-clock.h b/include/dt-bindings/clock/boston-clock.h
new file mode 100644
index 000000000000..a6f009821137
--- /dev/null
+++ b/include/dt-bindings/clock/boston-clock.h
@@ -0,0 +1,14 @@
+/*
+ * Copyright (C) 2016 Imagination Technologies
+ *
+ * SPDX-License-Identifier:	GPL-2.0
+ */
+
+#ifndef __DT_BINDINGS_CLOCK_BOSTON_CLOCK_H__
+#define __DT_BINDINGS_CLOCK_BOSTON_CLOCK_H__
+
+#define BOSTON_CLK_INPUT 0
+#define BOSTON_CLK_SYS 1
+#define BOSTON_CLK_CPU 2
+
+#endif /* __DT_BINDINGS_CLOCK_BOSTON_CLOCK_H__ */
-- 
cgit v1.2.3


From 2fd1d2c4ceb2248a727696962cf3370dc9f5a0a4 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Thu, 6 Jul 2017 08:41:06 -0500
Subject: proc: Fix proc_sys_prune_dcache to hold a sb reference

Andrei Vagin writes:
FYI: This bug has been reproduced on 4.11.7
> BUG: Dentry ffff895a3dd01240{i=4e7c09a,n=lo}  still in use (1) [unmount of proc proc]
> ------------[ cut here ]------------
> WARNING: CPU: 1 PID: 13588 at fs/dcache.c:1445 umount_check+0x6e/0x80
> CPU: 1 PID: 13588 Comm: kworker/1:1 Not tainted 4.11.7-200.fc25.x86_64 #1
> Hardware name: CompuLab sbc-flt1/fitlet, BIOS SBCFLT_0.08.04 06/27/2015
> Workqueue: events proc_cleanup_work
> Call Trace:
>  dump_stack+0x63/0x86
>  __warn+0xcb/0xf0
>  warn_slowpath_null+0x1d/0x20
>  umount_check+0x6e/0x80
>  d_walk+0xc6/0x270
>  ? dentry_free+0x80/0x80
>  do_one_tree+0x26/0x40
>  shrink_dcache_for_umount+0x2d/0x90
>  generic_shutdown_super+0x1f/0xf0
>  kill_anon_super+0x12/0x20
>  proc_kill_sb+0x40/0x50
>  deactivate_locked_super+0x43/0x70
>  deactivate_super+0x5a/0x60
>  cleanup_mnt+0x3f/0x90
>  mntput_no_expire+0x13b/0x190
>  kern_unmount+0x3e/0x50
>  pid_ns_release_proc+0x15/0x20
>  proc_cleanup_work+0x15/0x20
>  process_one_work+0x197/0x450
>  worker_thread+0x4e/0x4a0
>  kthread+0x109/0x140
>  ? process_one_work+0x450/0x450
>  ? kthread_park+0x90/0x90
>  ret_from_fork+0x2c/0x40
> ---[ end trace e1c109611e5d0b41 ]---
> VFS: Busy inodes after unmount of proc. Self-destruct in 5 seconds.  Have a nice day...
> BUG: unable to handle kernel NULL pointer dereference at           (null)
> IP: _raw_spin_lock+0xc/0x30
> PGD 0

Fix this by taking a reference to the super block in proc_sys_prune_dcache.

The superblock reference is the core of the fix however the sysctl_inodes
list is converted to a hlist so that hlist_del_init_rcu may be used.  This
allows proc_sys_prune_dache to remove inodes the sysctl_inodes list, while
not causing problems for proc_sys_evict_inode when if it later choses to
remove the inode from the sysctl_inodes list.  Removing inodes from the
sysctl_inodes list allows proc_sys_prune_dcache to have a progress
guarantee, while still being able to drop all locks.  The fact that
head->unregistering is set in start_unregistering ensures that no more
inodes will be added to the the sysctl_inodes list.

Previously the code did a dance where it delayed calling iput until the
next entry in the list was being considered to ensure the inode remained on
the sysctl_inodes list until the next entry was walked to.  The structure
of the loop in this patch does not need that so is much easier to
understand and maintain.

Cc: stable@vger.kernel.org
Reported-by: Andrei Vagin <avagin@gmail.com>
Tested-by: Andrei Vagin <avagin@openvz.org>
Fixes: ace0c791e6c3 ("proc/sysctl: Don't grab i_lock under sysctl_lock.")
Fixes: d6cffbbe9a7e ("proc/sysctl: prune stale dentries during unregistering")
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 fs/proc/internal.h     |  2 +-
 fs/proc/proc_sysctl.c  | 43 ++++++++++++++++++++++++++++++-------------
 include/linux/sysctl.h |  2 +-
 3 files changed, 32 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index c5ae09b6c726..18694598bebf 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -67,7 +67,7 @@ struct proc_inode {
 	struct proc_dir_entry *pde;
 	struct ctl_table_header *sysctl;
 	struct ctl_table *sysctl_entry;
-	struct list_head sysctl_inodes;
+	struct hlist_node sysctl_inodes;
 	const struct proc_ns_operations *ns_ops;
 	struct inode vfs_inode;
 };
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 67985a7233c2..9bf06e2b1284 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -191,7 +191,7 @@ static void init_header(struct ctl_table_header *head,
 	head->set = set;
 	head->parent = NULL;
 	head->node = node;
-	INIT_LIST_HEAD(&head->inodes);
+	INIT_HLIST_HEAD(&head->inodes);
 	if (node) {
 		struct ctl_table *entry;
 		for (entry = table; entry->procname; entry++, node++)
@@ -261,25 +261,42 @@ static void unuse_table(struct ctl_table_header *p)
 			complete(p->unregistering);
 }
 
-/* called under sysctl_lock */
 static void proc_sys_prune_dcache(struct ctl_table_header *head)
 {
-	struct inode *inode, *prev = NULL;
+	struct inode *inode;
 	struct proc_inode *ei;
+	struct hlist_node *node;
+	struct super_block *sb;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(ei, &head->inodes, sysctl_inodes) {
-		inode = igrab(&ei->vfs_inode);
-		if (inode) {
-			rcu_read_unlock();
-			iput(prev);
-			prev = inode;
-			d_prune_aliases(inode);
+	for (;;) {
+		node = hlist_first_rcu(&head->inodes);
+		if (!node)
+			break;
+		ei = hlist_entry(node, struct proc_inode, sysctl_inodes);
+		spin_lock(&sysctl_lock);
+		hlist_del_init_rcu(&ei->sysctl_inodes);
+		spin_unlock(&sysctl_lock);
+
+		inode = &ei->vfs_inode;
+		sb = inode->i_sb;
+		if (!atomic_inc_not_zero(&sb->s_active))
+			continue;
+		inode = igrab(inode);
+		rcu_read_unlock();
+		if (unlikely(!inode)) {
+			deactivate_super(sb);
 			rcu_read_lock();
+			continue;
 		}
+
+		d_prune_aliases(inode);
+		iput(inode);
+		deactivate_super(sb);
+
+		rcu_read_lock();
 	}
 	rcu_read_unlock();
-	iput(prev);
 }
 
 /* called under sysctl_lock, will reacquire if has to wait */
@@ -461,7 +478,7 @@ static struct inode *proc_sys_make_inode(struct super_block *sb,
 	}
 	ei->sysctl = head;
 	ei->sysctl_entry = table;
-	list_add_rcu(&ei->sysctl_inodes, &head->inodes);
+	hlist_add_head_rcu(&ei->sysctl_inodes, &head->inodes);
 	head->count++;
 	spin_unlock(&sysctl_lock);
 
@@ -489,7 +506,7 @@ out:
 void proc_sys_evict_inode(struct inode *inode, struct ctl_table_header *head)
 {
 	spin_lock(&sysctl_lock);
-	list_del_rcu(&PROC_I(inode)->sysctl_inodes);
+	hlist_del_init_rcu(&PROC_I(inode)->sysctl_inodes);
 	if (!--head->count)
 		kfree_rcu(head, rcu);
 	spin_unlock(&sysctl_lock);
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 80d07816def0..1c04a26bfd2f 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -143,7 +143,7 @@ struct ctl_table_header
 	struct ctl_table_set *set;
 	struct ctl_dir *parent;
 	struct ctl_node *node;
-	struct list_head inodes; /* head for proc_inode->sysctl_inodes */
+	struct hlist_head inodes; /* head for proc_inode->sysctl_inodes */
 };
 
 struct ctl_dir {
-- 
cgit v1.2.3


From 138d351eefb727ab9e41a3dc5f112ceb4f6e59f2 Mon Sep 17 00:00:00 2001
From: Nicholas Bellinger <nab@linux-iscsi.org>
Date: Fri, 7 Jul 2017 14:45:49 -0700
Subject: iscsi-target: Add login_keys_workaround attribute for non RFC
 initiators

This patch re-introduces part of a long standing login workaround that
was recently dropped by:

  commit 1c99de981f30b3e7868b8d20ce5479fa1c0fea46
  Author: Nicholas Bellinger <nab@linux-iscsi.org>
  Date:   Sun Apr 2 13:36:44 2017 -0700

      iscsi-target: Drop work-around for legacy GlobalSAN initiator

Namely, the workaround for FirstBurstLength ended up being required by
Mellanox Flexboot PXE boot ROMs as reported by Robert.

So this patch re-adds the work-around for FirstBurstLength within
iscsi_check_proposer_for_optional_reply(), and makes the key optional
to respond when the initiator does not propose, nor respond to it.

Also as requested by Arun, this patch introduces a new TPG attribute
named 'login_keys_workaround' that controls the use of both the
FirstBurstLength workaround, as well as the two other existing
workarounds for gPXE iSCSI boot client.

By default, the workaround is enabled with login_keys_workaround=1,
since Mellanox FlexBoot requires it, and Arun has verified the Qlogic
MSFT initiator already proposes FirstBurstLength, so it's uneffected
by this re-adding this part of the original work-around.

Reported-by: Robert LeBlanc <robert@leblancnet.us>
Cc: Robert LeBlanc <robert@leblancnet.us>
Reviewed-by: Arun Easi <arun.easi@cavium.com>
Cc: <stable@vger.kernel.org> # 3.1+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/iscsi/iscsi_target_configfs.c   |  2 ++
 drivers/target/iscsi/iscsi_target_nego.c       |  6 ++--
 drivers/target/iscsi/iscsi_target_parameters.c | 41 ++++++++++++++++++--------
 drivers/target/iscsi/iscsi_target_parameters.h |  2 +-
 drivers/target/iscsi/iscsi_target_tpg.c        | 19 ++++++++++++
 drivers/target/iscsi/iscsi_target_tpg.h        |  1 +
 include/target/iscsi/iscsi_target_core.h       |  9 ++++++
 7 files changed, 64 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c
index 535a8e06a401..0dd4c45f7575 100644
--- a/drivers/target/iscsi/iscsi_target_configfs.c
+++ b/drivers/target/iscsi/iscsi_target_configfs.c
@@ -781,6 +781,7 @@ DEF_TPG_ATTRIB(default_erl);
 DEF_TPG_ATTRIB(t10_pi);
 DEF_TPG_ATTRIB(fabric_prot_type);
 DEF_TPG_ATTRIB(tpg_enabled_sendtargets);
+DEF_TPG_ATTRIB(login_keys_workaround);
 
 static struct configfs_attribute *lio_target_tpg_attrib_attrs[] = {
 	&iscsi_tpg_attrib_attr_authentication,
@@ -796,6 +797,7 @@ static struct configfs_attribute *lio_target_tpg_attrib_attrs[] = {
 	&iscsi_tpg_attrib_attr_t10_pi,
 	&iscsi_tpg_attrib_attr_fabric_prot_type,
 	&iscsi_tpg_attrib_attr_tpg_enabled_sendtargets,
+	&iscsi_tpg_attrib_attr_login_keys_workaround,
 	NULL,
 };
 
diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c
index 96df63f1f795..7a6751fecd32 100644
--- a/drivers/target/iscsi/iscsi_target_nego.c
+++ b/drivers/target/iscsi/iscsi_target_nego.c
@@ -864,7 +864,8 @@ static int iscsi_target_handle_csg_zero(
 			SENDER_TARGET,
 			login->rsp_buf,
 			&login->rsp_length,
-			conn->param_list);
+			conn->param_list,
+			conn->tpg->tpg_attrib.login_keys_workaround);
 	if (ret < 0)
 		return -1;
 
@@ -934,7 +935,8 @@ static int iscsi_target_handle_csg_one(struct iscsi_conn *conn, struct iscsi_log
 			SENDER_TARGET,
 			login->rsp_buf,
 			&login->rsp_length,
-			conn->param_list);
+			conn->param_list,
+			conn->tpg->tpg_attrib.login_keys_workaround);
 	if (ret < 0) {
 		iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_INITIATOR_ERR,
 				ISCSI_LOGIN_STATUS_INIT_ERR);
diff --git a/drivers/target/iscsi/iscsi_target_parameters.c b/drivers/target/iscsi/iscsi_target_parameters.c
index fce627628200..caab1045742d 100644
--- a/drivers/target/iscsi/iscsi_target_parameters.c
+++ b/drivers/target/iscsi/iscsi_target_parameters.c
@@ -765,7 +765,8 @@ static int iscsi_check_for_auth_key(char *key)
 	return 0;
 }
 
-static void iscsi_check_proposer_for_optional_reply(struct iscsi_param *param)
+static void iscsi_check_proposer_for_optional_reply(struct iscsi_param *param,
+						    bool keys_workaround)
 {
 	if (IS_TYPE_BOOL_AND(param)) {
 		if (!strcmp(param->value, NO))
@@ -773,19 +774,31 @@ static void iscsi_check_proposer_for_optional_reply(struct iscsi_param *param)
 	} else if (IS_TYPE_BOOL_OR(param)) {
 		if (!strcmp(param->value, YES))
 			SET_PSTATE_REPLY_OPTIONAL(param);
-		 /*
-		  * Required for gPXE iSCSI boot client
-		  */
-		if (!strcmp(param->name, IMMEDIATEDATA))
-			SET_PSTATE_REPLY_OPTIONAL(param);
+
+		if (keys_workaround) {
+			/*
+			 * Required for gPXE iSCSI boot client
+			 */
+			if (!strcmp(param->name, IMMEDIATEDATA))
+				SET_PSTATE_REPLY_OPTIONAL(param);
+		}
 	} else if (IS_TYPE_NUMBER(param)) {
 		if (!strcmp(param->name, MAXRECVDATASEGMENTLENGTH))
 			SET_PSTATE_REPLY_OPTIONAL(param);
-		/*
-		 * Required for gPXE iSCSI boot client
-		 */
-		if (!strcmp(param->name, MAXCONNECTIONS))
-			SET_PSTATE_REPLY_OPTIONAL(param);
+
+		if (keys_workaround) {
+			/*
+			 * Required for Mellanox Flexboot PXE boot ROM
+			 */
+			if (!strcmp(param->name, FIRSTBURSTLENGTH))
+				SET_PSTATE_REPLY_OPTIONAL(param);
+
+			/*
+			 * Required for gPXE iSCSI boot client
+			 */
+			if (!strcmp(param->name, MAXCONNECTIONS))
+				SET_PSTATE_REPLY_OPTIONAL(param);
+		}
 	} else if (IS_PHASE_DECLARATIVE(param))
 		SET_PSTATE_REPLY_OPTIONAL(param);
 }
@@ -1422,7 +1435,8 @@ int iscsi_encode_text_output(
 	u8 sender,
 	char *textbuf,
 	u32 *length,
-	struct iscsi_param_list *param_list)
+	struct iscsi_param_list *param_list,
+	bool keys_workaround)
 {
 	char *output_buf = NULL;
 	struct iscsi_extra_response *er;
@@ -1458,7 +1472,8 @@ int iscsi_encode_text_output(
 			*length += 1;
 			output_buf = textbuf + *length;
 			SET_PSTATE_PROPOSER(param);
-			iscsi_check_proposer_for_optional_reply(param);
+			iscsi_check_proposer_for_optional_reply(param,
+							        keys_workaround);
 			pr_debug("Sending key: %s=%s\n",
 				param->name, param->value);
 		}
diff --git a/drivers/target/iscsi/iscsi_target_parameters.h b/drivers/target/iscsi/iscsi_target_parameters.h
index 9962ccf0ccd7..c47b73f57528 100644
--- a/drivers/target/iscsi/iscsi_target_parameters.h
+++ b/drivers/target/iscsi/iscsi_target_parameters.h
@@ -46,7 +46,7 @@ extern int iscsi_extract_key_value(char *, char **, char **);
 extern int iscsi_update_param_value(struct iscsi_param *, char *);
 extern int iscsi_decode_text_input(u8, u8, char *, u32, struct iscsi_conn *);
 extern int iscsi_encode_text_output(u8, u8, char *, u32 *,
-			struct iscsi_param_list *);
+			struct iscsi_param_list *, bool);
 extern int iscsi_check_negotiated_keys(struct iscsi_param_list *);
 extern void iscsi_set_connection_parameters(struct iscsi_conn_ops *,
 			struct iscsi_param_list *);
diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c
index abaabbaebd88..594d07a1e995 100644
--- a/drivers/target/iscsi/iscsi_target_tpg.c
+++ b/drivers/target/iscsi/iscsi_target_tpg.c
@@ -227,6 +227,7 @@ static void iscsit_set_default_tpg_attribs(struct iscsi_portal_group *tpg)
 	a->t10_pi = TA_DEFAULT_T10_PI;
 	a->fabric_prot_type = TA_DEFAULT_FABRIC_PROT_TYPE;
 	a->tpg_enabled_sendtargets = TA_DEFAULT_TPG_ENABLED_SENDTARGETS;
+	a->login_keys_workaround = TA_DEFAULT_LOGIN_KEYS_WORKAROUND;
 }
 
 int iscsit_tpg_add_portal_group(struct iscsi_tiqn *tiqn, struct iscsi_portal_group *tpg)
@@ -895,3 +896,21 @@ int iscsit_ta_tpg_enabled_sendtargets(
 
 	return 0;
 }
+
+int iscsit_ta_login_keys_workaround(
+	struct iscsi_portal_group *tpg,
+	u32 flag)
+{
+	struct iscsi_tpg_attrib *a = &tpg->tpg_attrib;
+
+	if ((flag != 0) && (flag != 1)) {
+		pr_err("Illegal value %d\n", flag);
+		return -EINVAL;
+	}
+
+	a->login_keys_workaround = flag;
+	pr_debug("iSCSI_TPG[%hu] - TPG enabled bit for login keys workaround: %s ",
+		tpg->tpgt, (a->login_keys_workaround) ? "ON" : "OFF");
+
+	return 0;
+}
diff --git a/drivers/target/iscsi/iscsi_target_tpg.h b/drivers/target/iscsi/iscsi_target_tpg.h
index ceba29851167..59fd3cabe89d 100644
--- a/drivers/target/iscsi/iscsi_target_tpg.h
+++ b/drivers/target/iscsi/iscsi_target_tpg.h
@@ -48,5 +48,6 @@ extern int iscsit_ta_default_erl(struct iscsi_portal_group *, u32);
 extern int iscsit_ta_t10_pi(struct iscsi_portal_group *, u32);
 extern int iscsit_ta_fabric_prot_type(struct iscsi_portal_group *, u32);
 extern int iscsit_ta_tpg_enabled_sendtargets(struct iscsi_portal_group *, u32);
+extern int iscsit_ta_login_keys_workaround(struct iscsi_portal_group *, u32);
 
 #endif /* ISCSI_TARGET_TPG_H */
diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h
index 7948fc68286b..0ca1fb08805b 100644
--- a/include/target/iscsi/iscsi_target_core.h
+++ b/include/target/iscsi/iscsi_target_core.h
@@ -66,6 +66,14 @@ struct sock;
 #define TA_DEFAULT_FABRIC_PROT_TYPE	0
 /* TPG status needs to be enabled to return sendtargets discovery endpoint info */
 #define TA_DEFAULT_TPG_ENABLED_SENDTARGETS 1
+/*
+ * Used to control the sending of keys with optional to respond state bit,
+ * as a workaround for non RFC compliant initiators,that do not propose,
+ * nor respond to specific keys required for login to complete.
+ *
+ * See iscsi_check_proposer_for_optional_reply() for more details.
+ */
+#define TA_DEFAULT_LOGIN_KEYS_WORKAROUND 1
 
 #define ISCSI_IOV_DATA_BUFFER		5
 
@@ -768,6 +776,7 @@ struct iscsi_tpg_attrib {
 	u8			t10_pi;
 	u32			fabric_prot_type;
 	u32			tpg_enabled_sendtargets;
+	u32			login_keys_workaround;
 	struct iscsi_portal_group *tpg;
 };
 
-- 
cgit v1.2.3


From e8158b486d5f3f55cf372c5a32b42f263bf7f123 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Tue, 11 Jul 2017 18:20:20 +0300
Subject: device property: Introduce fwnode_call_bool_op() for ops that return
 bool

fwnode_call_int_op() isn't suitable for calling ops that return bool
since it effectively causes the result returned to the user to be
true when an op hasn't been defined or the fwnode is NULL.

Address this by introducing fwnode_call_bool_op() for calling ops
that return bool.

Fixes: 3708184afc77 "device property: Move FW type specific functionality to FW specific files"
Fixes: 2294b3af05e9 "device property: Introduce fwnode_device_is_available()"
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/property.c | 6 +++---
 include/linux/fwnode.h  | 4 ++++
 2 files changed, 7 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/base/property.c b/drivers/base/property.c
index 692007e5a94b..edf02c1b5845 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -253,10 +253,10 @@ bool fwnode_property_present(struct fwnode_handle *fwnode, const char *propname)
 {
 	bool ret;
 
-	ret = fwnode_call_int_op(fwnode, property_present, propname);
+	ret = fwnode_call_bool_op(fwnode, property_present, propname);
 	if (ret == false && !IS_ERR_OR_NULL(fwnode) &&
 	    !IS_ERR_OR_NULL(fwnode->secondary))
-		ret = fwnode_call_int_op(fwnode->secondary, property_present,
+		ret = fwnode_call_bool_op(fwnode->secondary, property_present,
 					 propname);
 	return ret;
 }
@@ -1027,7 +1027,7 @@ EXPORT_SYMBOL_GPL(fwnode_handle_put);
  */
 bool fwnode_device_is_available(struct fwnode_handle *fwnode)
 {
-	return fwnode_call_int_op(fwnode, device_is_available);
+	return fwnode_call_bool_op(fwnode, device_is_available);
 }
 EXPORT_SYMBOL_GPL(fwnode_device_is_available);
 
diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h
index 9ab375419189..50893a1646cf 100644
--- a/include/linux/fwnode.h
+++ b/include/linux/fwnode.h
@@ -99,6 +99,10 @@ struct fwnode_operations {
 	(fwnode ? (fwnode_has_op(fwnode, op) ?				\
 		   (fwnode)->ops->op(fwnode, ## __VA_ARGS__) : -ENXIO) : \
 	 -EINVAL)
+#define fwnode_call_bool_op(fwnode, op, ...)				\
+	(fwnode ? (fwnode_has_op(fwnode, op) ?				\
+		   (fwnode)->ops->op(fwnode, ## __VA_ARGS__) : false) : \
+	 false)
 #define fwnode_call_ptr_op(fwnode, op, ...)		\
 	(fwnode_has_op(fwnode, op) ?			\
 	 (fwnode)->ops->op(fwnode, ## __VA_ARGS__) : NULL)
-- 
cgit v1.2.3


From 8c6ae4980e70395cbdfdf605c29673c5a6a89d9a Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 30 Jun 2017 12:03:54 -0400
Subject: sunrpc: Allocate up to RPCSVC_MAXPAGES per svc_rqst

svcrdma needs 259 pages allocated to receive 1MB NFSv4.0 WRITE requests:

 - 1 page for the transport header and head iovec
 - 256 pages for the data payload
 - 1 page for the trailing GETATTR request (since NFSD XDR decoding
   does not look for a tail iovec, the GETATTR is stuck at the end
   of the rqstp->rq_arg.pages list)
 - 1 page for building the reply xdr_buf

But RPCSVC_MAXPAGES is already 259 (on x86_64). The problem is that
svc_alloc_arg never allocates that many pages. To address this:

1. The final element of rq_pages always points to NULL. To
   accommodate up to 259 pages in rq_pages, add an extra element
   to rq_pages for the array termination sentinel.

2. Adjust the calculation of "pages" to match how RPCSVC_MAXPAGES
   is calculated, so it can go up to 259. Bruce noted that the
   calculation assumes sv_max_mesg is a multiple of PAGE_SIZE,
   which might not always be true. I didn't change this assumption.

3. Change the loop boundaries to allow 259 pages to be allocated.

Additional clean-up: WARN_ON_ONCE adds an extra conditional branch,
which is basically never taken. And there's no need to dump the
stack here because svc_alloc_arg has only one caller.

Keeping that NULL "array termination sentinel"; there doesn't appear to
be any code that depends on it, only code in nfsd_splice_actor() which
needs the 259th element to be initialized to *something*.  So it's
possible we could just keep the array at 259 elements and drop that
final NULL, but we're being conservative for now.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 include/linux/sunrpc/svc.h |  2 +-
 net/sunrpc/svc_xprt.c      | 10 ++++++----
 2 files changed, 7 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index eec04982a7ea..a3f8af9bd543 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -246,7 +246,7 @@ struct svc_rqst {
 	size_t			rq_xprt_hlen;	/* xprt header len */
 	struct xdr_buf		rq_arg;
 	struct xdr_buf		rq_res;
-	struct page *		rq_pages[RPCSVC_MAXPAGES];
+	struct page		*rq_pages[RPCSVC_MAXPAGES + 1];
 	struct page *		*rq_respages;	/* points into rq_pages */
 	struct page *		*rq_next_page; /* next reply page to use */
 	struct page *		*rq_page_end;  /* one past the last page */
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 7bfe1fb42add..d16a8b423c20 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -659,11 +659,13 @@ static int svc_alloc_arg(struct svc_rqst *rqstp)
 	int i;
 
 	/* now allocate needed pages.  If we get a failure, sleep briefly */
-	pages = (serv->sv_max_mesg + PAGE_SIZE) / PAGE_SIZE;
-	WARN_ON_ONCE(pages >= RPCSVC_MAXPAGES);
-	if (pages >= RPCSVC_MAXPAGES)
+	pages = (serv->sv_max_mesg + 2 * PAGE_SIZE) >> PAGE_SHIFT;
+	if (pages > RPCSVC_MAXPAGES) {
+		pr_warn_once("svc: warning: pages=%u > RPCSVC_MAXPAGES=%lu\n",
+			     pages, RPCSVC_MAXPAGES);
 		/* use as many pages as possible */
-		pages = RPCSVC_MAXPAGES - 1;
+		pages = RPCSVC_MAXPAGES;
+	}
 	for (i = 0; i < pages ; i++)
 		while (rqstp->rq_pages[i] == NULL) {
 			struct page *p = alloc_page(GFP_KERNEL);
-- 
cgit v1.2.3


From 026d958b38c628a1b4ced534808945365e2747a5 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 23 Jun 2017 17:18:24 -0400
Subject: svcrdma: Add recvfrom helpers to svc_rdma_rw.c

svc_rdma_rw.c already contains helpers for the sendto path.
Introduce helpers for the recvfrom path.

The plan is to replace the local NFSD bespoke code that constructs
and posts RDMA Read Work Requests with calls to the rdma_rw API.
This shares code with other RDMA-enabled ULPs that manages the gory
details of buffer registration and posting Work Requests.

This new code also puts all RDMA_NOMSG-specific logic in one place.

Lastly, the use of rqstp->rq_arg.pages is deprecated in favor of
using rqstp->rq_pages directly, for clarity.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 include/linux/sunrpc/svc_rdma.h   |   3 +
 net/sunrpc/xprtrdma/svc_rdma_rw.c | 425 +++++++++++++++++++++++++++++++++++++-
 2 files changed, 427 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 3ca991657889..cf5d5412298b 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -196,6 +196,9 @@ extern int rdma_read_chunk_frmr(struct svcxprt_rdma *, struct svc_rqst *,
 
 /* svc_rdma_rw.c */
 extern void svc_rdma_destroy_rw_ctxts(struct svcxprt_rdma *rdma);
+extern int svc_rdma_recv_read_chunk(struct svcxprt_rdma *rdma,
+				    struct svc_rqst *rqstp,
+				    struct svc_rdma_op_ctxt *head, __be32 *p);
 extern int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma,
 				     __be32 *wr_ch, struct xdr_buf *xdr);
 extern int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma,
diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c
index 3b35364d9a6b..77d38a4b8d99 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_rw.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c
@@ -12,6 +12,9 @@
 
 #define RPCDBG_FACILITY	RPCDBG_SVCXPRT
 
+static void svc_rdma_write_done(struct ib_cq *cq, struct ib_wc *wc);
+static void svc_rdma_wc_read_done(struct ib_cq *cq, struct ib_wc *wc);
+
 /* Each R/W context contains state for one chain of RDMA Read or
  * Write Work Requests.
  *
@@ -177,6 +180,7 @@ svc_rdma_write_info_alloc(struct svcxprt_rdma *rdma, __be32 *chunk)
 	info->wi_nsegs = be32_to_cpup(++chunk);
 	info->wi_segs = ++chunk;
 	svc_rdma_cc_init(rdma, &info->wi_cc, DMA_TO_DEVICE);
+	info->wi_cc.cc_cqe.done = svc_rdma_write_done;
 	return info;
 }
 
@@ -216,6 +220,76 @@ static void svc_rdma_write_done(struct ib_cq *cq, struct ib_wc *wc)
 	svc_rdma_write_info_free(info);
 }
 
+/* State for pulling a Read chunk.
+ */
+struct svc_rdma_read_info {
+	struct svc_rdma_op_ctxt		*ri_readctxt;
+	unsigned int			ri_position;
+	unsigned int			ri_pageno;
+	unsigned int			ri_pageoff;
+	unsigned int			ri_chunklen;
+
+	struct svc_rdma_chunk_ctxt	ri_cc;
+};
+
+static struct svc_rdma_read_info *
+svc_rdma_read_info_alloc(struct svcxprt_rdma *rdma)
+{
+	struct svc_rdma_read_info *info;
+
+	info = kmalloc(sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return info;
+
+	svc_rdma_cc_init(rdma, &info->ri_cc, DMA_FROM_DEVICE);
+	info->ri_cc.cc_cqe.done = svc_rdma_wc_read_done;
+	return info;
+}
+
+static void svc_rdma_read_info_free(struct svc_rdma_read_info *info)
+{
+	svc_rdma_cc_release(&info->ri_cc);
+	kfree(info);
+}
+
+/**
+ * svc_rdma_wc_read_done - Handle completion of an RDMA Read ctx
+ * @cq: controlling Completion Queue
+ * @wc: Work Completion
+ *
+ */
+static void svc_rdma_wc_read_done(struct ib_cq *cq, struct ib_wc *wc)
+{
+	struct ib_cqe *cqe = wc->wr_cqe;
+	struct svc_rdma_chunk_ctxt *cc =
+			container_of(cqe, struct svc_rdma_chunk_ctxt, cc_cqe);
+	struct svcxprt_rdma *rdma = cc->cc_rdma;
+	struct svc_rdma_read_info *info =
+			container_of(cc, struct svc_rdma_read_info, ri_cc);
+
+	atomic_add(cc->cc_sqecount, &rdma->sc_sq_avail);
+	wake_up(&rdma->sc_send_wait);
+
+	if (unlikely(wc->status != IB_WC_SUCCESS)) {
+		set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags);
+		if (wc->status != IB_WC_WR_FLUSH_ERR)
+			pr_err("svcrdma: read ctx: %s (%u/0x%x)\n",
+			       ib_wc_status_msg(wc->status),
+			       wc->status, wc->vendor_err);
+		svc_rdma_put_context(info->ri_readctxt, 1);
+	} else {
+		spin_lock(&rdma->sc_rq_dto_lock);
+		list_add_tail(&info->ri_readctxt->list,
+			      &rdma->sc_read_complete_q);
+		spin_unlock(&rdma->sc_rq_dto_lock);
+
+		set_bit(XPT_DATA, &rdma->sc_xprt.xpt_flags);
+		svc_xprt_enqueue(&rdma->sc_xprt);
+	}
+
+	svc_rdma_read_info_free(info);
+}
+
 /* This function sleeps when the transport's Send Queue is congested.
  *
  * Assumptions:
@@ -335,7 +409,6 @@ svc_rdma_build_writes(struct svc_rdma_write_info *info,
 	__be32 *seg;
 	int ret;
 
-	cc->cc_cqe.done = svc_rdma_write_done;
 	seg = info->wi_segs + info->wi_seg_no * rpcrdma_segment_maxsz;
 	do {
 		unsigned int write_len;
@@ -515,3 +588,353 @@ out_err:
 	svc_rdma_write_info_free(info);
 	return ret;
 }
+
+static int svc_rdma_build_read_segment(struct svc_rdma_read_info *info,
+				       struct svc_rqst *rqstp,
+				       u32 rkey, u32 len, u64 offset)
+{
+	struct svc_rdma_op_ctxt *head = info->ri_readctxt;
+	struct svc_rdma_chunk_ctxt *cc = &info->ri_cc;
+	struct svc_rdma_rw_ctxt *ctxt;
+	unsigned int sge_no, seg_len;
+	struct scatterlist *sg;
+	int ret;
+
+	sge_no = PAGE_ALIGN(info->ri_pageoff + len) >> PAGE_SHIFT;
+	ctxt = svc_rdma_get_rw_ctxt(cc->cc_rdma, sge_no);
+	if (!ctxt)
+		goto out_noctx;
+	ctxt->rw_nents = sge_no;
+
+	dprintk("svcrdma: reading segment %u@0x%016llx:0x%08x (%u sges)\n",
+		len, offset, rkey, sge_no);
+
+	sg = ctxt->rw_sg_table.sgl;
+	for (sge_no = 0; sge_no < ctxt->rw_nents; sge_no++) {
+		seg_len = min_t(unsigned int, len,
+				PAGE_SIZE - info->ri_pageoff);
+
+		head->arg.pages[info->ri_pageno] =
+			rqstp->rq_pages[info->ri_pageno];
+		if (!info->ri_pageoff)
+			head->count++;
+
+		sg_set_page(sg, rqstp->rq_pages[info->ri_pageno],
+			    seg_len, info->ri_pageoff);
+		sg = sg_next(sg);
+
+		info->ri_pageoff += seg_len;
+		if (info->ri_pageoff == PAGE_SIZE) {
+			info->ri_pageno++;
+			info->ri_pageoff = 0;
+		}
+		len -= seg_len;
+
+		/* Safety check */
+		if (len &&
+		    &rqstp->rq_pages[info->ri_pageno + 1] > rqstp->rq_page_end)
+			goto out_overrun;
+	}
+
+	ret = rdma_rw_ctx_init(&ctxt->rw_ctx, cc->cc_rdma->sc_qp,
+			       cc->cc_rdma->sc_port_num,
+			       ctxt->rw_sg_table.sgl, ctxt->rw_nents,
+			       0, offset, rkey, DMA_FROM_DEVICE);
+	if (ret < 0)
+		goto out_initerr;
+
+	list_add(&ctxt->rw_list, &cc->cc_rwctxts);
+	cc->cc_sqecount += ret;
+	return 0;
+
+out_noctx:
+	dprintk("svcrdma: no R/W ctxs available\n");
+	return -ENOMEM;
+
+out_overrun:
+	dprintk("svcrdma: request overruns rq_pages\n");
+	return -EINVAL;
+
+out_initerr:
+	svc_rdma_put_rw_ctxt(cc->cc_rdma, ctxt);
+	pr_err("svcrdma: failed to map pagelist (%d)\n", ret);
+	return -EIO;
+}
+
+static int svc_rdma_build_read_chunk(struct svc_rqst *rqstp,
+				     struct svc_rdma_read_info *info,
+				     __be32 *p)
+{
+	int ret;
+
+	info->ri_chunklen = 0;
+	while (*p++ != xdr_zero) {
+		u32 rs_handle, rs_length;
+		u64 rs_offset;
+
+		if (be32_to_cpup(p++) != info->ri_position)
+			break;
+		rs_handle = be32_to_cpup(p++);
+		rs_length = be32_to_cpup(p++);
+		p = xdr_decode_hyper(p, &rs_offset);
+
+		ret = svc_rdma_build_read_segment(info, rqstp,
+						  rs_handle, rs_length,
+						  rs_offset);
+		if (ret < 0)
+			break;
+
+		info->ri_chunklen += rs_length;
+	}
+
+	return ret;
+}
+
+/* If there is inline content following the Read chunk, append it to
+ * the page list immediately following the data payload. This has to
+ * be done after the reader function has determined how many pages
+ * were consumed for RDMA Read.
+ *
+ * On entry, ri_pageno and ri_pageoff point directly to the end of the
+ * page list. On exit, both have been updated to the new "next byte".
+ *
+ * Assumptions:
+ *	- Inline content fits entirely in rq_pages[0]
+ *	- Trailing content is only a handful of bytes
+ */
+static int svc_rdma_copy_tail(struct svc_rqst *rqstp,
+			      struct svc_rdma_read_info *info)
+{
+	struct svc_rdma_op_ctxt *head = info->ri_readctxt;
+	unsigned int tail_length, remaining;
+	u8 *srcp, *destp;
+
+	/* Assert that all inline content fits in page 0. This is an
+	 * implementation limit, not a protocol limit.
+	 */
+	if (head->arg.head[0].iov_len > PAGE_SIZE) {
+		pr_warn_once("svcrdma: too much trailing inline content\n");
+		return -EINVAL;
+	}
+
+	srcp = head->arg.head[0].iov_base;
+	srcp += info->ri_position;
+	tail_length = head->arg.head[0].iov_len - info->ri_position;
+	remaining = tail_length;
+
+	/* If there is room on the last page in the page list, try to
+	 * fit the trailing content there.
+	 */
+	if (info->ri_pageoff > 0) {
+		unsigned int len;
+
+		len = min_t(unsigned int, remaining,
+			    PAGE_SIZE - info->ri_pageoff);
+		destp = page_address(rqstp->rq_pages[info->ri_pageno]);
+		destp += info->ri_pageoff;
+
+		memcpy(destp, srcp, len);
+		srcp += len;
+		destp += len;
+		info->ri_pageoff += len;
+		remaining -= len;
+
+		if (info->ri_pageoff == PAGE_SIZE) {
+			info->ri_pageno++;
+			info->ri_pageoff = 0;
+		}
+	}
+
+	/* Otherwise, a fresh page is needed. */
+	if (remaining) {
+		head->arg.pages[info->ri_pageno] =
+				rqstp->rq_pages[info->ri_pageno];
+		head->count++;
+
+		destp = page_address(rqstp->rq_pages[info->ri_pageno]);
+		memcpy(destp, srcp, remaining);
+		info->ri_pageoff += remaining;
+	}
+
+	head->arg.page_len += tail_length;
+	head->arg.len += tail_length;
+	head->arg.buflen += tail_length;
+	return 0;
+}
+
+/* Construct RDMA Reads to pull over a normal Read chunk. The chunk
+ * data lands in the page list of head->arg.pages.
+ *
+ * Currently NFSD does not look at the head->arg.tail[0] iovec.
+ * Therefore, XDR round-up of the Read chunk and trailing
+ * inline content must both be added at the end of the pagelist.
+ */
+static int svc_rdma_build_normal_read_chunk(struct svc_rqst *rqstp,
+					    struct svc_rdma_read_info *info,
+					    __be32 *p)
+{
+	struct svc_rdma_op_ctxt *head = info->ri_readctxt;
+	int ret;
+
+	dprintk("svcrdma: Reading Read chunk at position %u\n",
+		info->ri_position);
+
+	info->ri_pageno = head->hdr_count;
+	info->ri_pageoff = 0;
+
+	ret = svc_rdma_build_read_chunk(rqstp, info, p);
+	if (ret < 0)
+		goto out;
+
+	/* Read chunk may need XDR round-up (see RFC 5666, s. 3.7).
+	 */
+	if (info->ri_chunklen & 3) {
+		u32 padlen = 4 - (info->ri_chunklen & 3);
+
+		info->ri_chunklen += padlen;
+
+		/* NB: data payload always starts on XDR alignment,
+		 * thus the pad can never contain a page boundary.
+		 */
+		info->ri_pageoff += padlen;
+		if (info->ri_pageoff == PAGE_SIZE) {
+			info->ri_pageno++;
+			info->ri_pageoff = 0;
+		}
+	}
+
+	head->arg.page_len = info->ri_chunklen;
+	head->arg.len += info->ri_chunklen;
+	head->arg.buflen += info->ri_chunklen;
+
+	if (info->ri_position < head->arg.head[0].iov_len) {
+		ret = svc_rdma_copy_tail(rqstp, info);
+		if (ret < 0)
+			goto out;
+	}
+	head->arg.head[0].iov_len = info->ri_position;
+
+out:
+	return ret;
+}
+
+/* Construct RDMA Reads to pull over a Position Zero Read chunk.
+ * The start of the data lands in the first page just after
+ * the Transport header, and the rest lands in the page list of
+ * head->arg.pages.
+ *
+ * Assumptions:
+ *	- A PZRC has an XDR-aligned length (no implicit round-up).
+ *	- There can be no trailing inline content (IOW, we assume
+ *	  a PZRC is never sent in an RDMA_MSG message, though it's
+ *	  allowed by spec).
+ */
+static int svc_rdma_build_pz_read_chunk(struct svc_rqst *rqstp,
+					struct svc_rdma_read_info *info,
+					__be32 *p)
+{
+	struct svc_rdma_op_ctxt *head = info->ri_readctxt;
+	int ret;
+
+	dprintk("svcrdma: Reading Position Zero Read chunk\n");
+
+	info->ri_pageno = head->hdr_count - 1;
+	info->ri_pageoff = offset_in_page(head->byte_len);
+
+	ret = svc_rdma_build_read_chunk(rqstp, info, p);
+	if (ret < 0)
+		goto out;
+
+	head->arg.len += info->ri_chunklen;
+	head->arg.buflen += info->ri_chunklen;
+
+	if (head->arg.len <= head->sge[0].length) {
+		/* Transport header and RPC message fit entirely
+		 * in page where head iovec resides.
+		 */
+		head->arg.head[0].iov_len = info->ri_chunklen;
+	} else {
+		/* Transport header and part of RPC message reside
+		 * in the head iovec's page.
+		 */
+		head->arg.head[0].iov_len =
+				head->sge[0].length - head->byte_len;
+		head->arg.page_len =
+				info->ri_chunklen - head->arg.head[0].iov_len;
+	}
+
+out:
+	return ret;
+}
+
+/**
+ * svc_rdma_recv_read_chunk - Pull a Read chunk from the client
+ * @rdma: controlling RDMA transport
+ * @rqstp: set of pages to use as Read sink buffers
+ * @head: pages under I/O collect here
+ * @p: pointer to start of Read chunk
+ *
+ * Returns:
+ *	%0 if all needed RDMA Reads were posted successfully,
+ *	%-EINVAL if client provided too many segments,
+ *	%-ENOMEM if rdma_rw context pool was exhausted,
+ *	%-ENOTCONN if posting failed (connection is lost),
+ *	%-EIO if rdma_rw initialization failed (DMA mapping, etc).
+ *
+ * Assumptions:
+ * - All Read segments in @p have the same Position value.
+ */
+int svc_rdma_recv_read_chunk(struct svcxprt_rdma *rdma, struct svc_rqst *rqstp,
+			     struct svc_rdma_op_ctxt *head, __be32 *p)
+{
+	struct svc_rdma_read_info *info;
+	struct page **page;
+	int ret;
+
+	/* The request (with page list) is constructed in
+	 * head->arg. Pages involved with RDMA Read I/O are
+	 * transferred there.
+	 */
+	head->hdr_count = head->count;
+	head->arg.head[0] = rqstp->rq_arg.head[0];
+	head->arg.tail[0] = rqstp->rq_arg.tail[0];
+	head->arg.pages = head->pages;
+	head->arg.page_base = 0;
+	head->arg.page_len = 0;
+	head->arg.len = rqstp->rq_arg.len;
+	head->arg.buflen = rqstp->rq_arg.buflen;
+
+	info = svc_rdma_read_info_alloc(rdma);
+	if (!info)
+		return -ENOMEM;
+	info->ri_readctxt = head;
+
+	info->ri_position = be32_to_cpup(p + 1);
+	if (info->ri_position)
+		ret = svc_rdma_build_normal_read_chunk(rqstp, info, p);
+	else
+		ret = svc_rdma_build_pz_read_chunk(rqstp, info, p);
+
+	/* Mark the start of the pages that can be used for the reply */
+	if (info->ri_pageoff > 0)
+		info->ri_pageno++;
+	rqstp->rq_respages = &rqstp->rq_pages[info->ri_pageno];
+	rqstp->rq_next_page = rqstp->rq_respages + 1;
+
+	if (ret < 0)
+		goto out;
+
+	ret = svc_rdma_post_chunk_ctxt(&info->ri_cc);
+
+out:
+	/* Read sink pages have been moved from rqstp->rq_pages to
+	 * head->arg.pages. Force svc_recv to refill those slots
+	 * in rq_pages.
+	 */
+	for (page = rqstp->rq_pages; page < rqstp->rq_respages; page++)
+		*page = NULL;
+
+	if (ret < 0)
+		svc_rdma_read_info_free(info);
+	return ret;
+}
-- 
cgit v1.2.3


From cafc739892f34b9090413179ca259409fc43bfae Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 23 Jun 2017 17:18:33 -0400
Subject: svcrdma: Use generic RDMA R/W API in RPC Call path

The current svcrdma recvfrom code path has a lot of detail about
registration mode and the type of port (iWARP, IB, etc).

Instead, use the RDMA core's generic R/W API. This shares code with
other RDMA-enabled ULPs that manages the gory details of buffer
registration and the posting of RDMA Read Work Requests.

Since the Read list marshaling code is being replaced, I took the
opportunity to replace C structure-based XDR encoding code with more
portable code that uses pointer arithmetic.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 include/linux/sunrpc/svc_rdma.h          |  14 -
 net/sunrpc/xprtrdma/svc_rdma_recvfrom.c  | 547 ++++++-------------------------
 net/sunrpc/xprtrdma/svc_rdma_transport.c |  13 -
 3 files changed, 106 insertions(+), 468 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index cf5d5412298b..b1ba19ba1071 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -82,10 +82,7 @@ struct svc_rdma_op_ctxt {
 	int hdr_count;
 	struct xdr_buf arg;
 	struct ib_cqe cqe;
-	struct ib_cqe reg_cqe;
-	struct ib_cqe inv_cqe;
 	u32 byte_len;
-	u32 position;
 	struct svcxprt_rdma *xprt;
 	unsigned long flags;
 	enum dma_data_direction direction;
@@ -116,7 +113,6 @@ struct svcxprt_rdma {
 	struct list_head     sc_accept_q;	/* Conn. waiting accept */
 	int		     sc_ord;		/* RDMA read limit */
 	int                  sc_max_sge;
-	int                  sc_max_sge_rd;	/* max sge for read target */
 	bool		     sc_snd_w_inv;	/* OK to use Send With Invalidate */
 
 	atomic_t             sc_sq_avail;	/* SQEs ready to be consumed */
@@ -141,10 +137,6 @@ struct svcxprt_rdma {
 	struct ib_qp         *sc_qp;
 	struct ib_cq         *sc_rq_cq;
 	struct ib_cq         *sc_sq_cq;
-	int		     (*sc_reader)(struct svcxprt_rdma *,
-					  struct svc_rqst *,
-					  struct svc_rdma_op_ctxt *,
-					  int *, u32 *, u32, u32, u64, bool);
 	u32		     sc_dev_caps;	/* distilled device caps */
 	unsigned int	     sc_frmr_pg_list_len;
 	struct list_head     sc_frmr_q;
@@ -187,12 +179,6 @@ extern int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt,
 
 /* svc_rdma_recvfrom.c */
 extern int svc_rdma_recvfrom(struct svc_rqst *);
-extern int rdma_read_chunk_lcl(struct svcxprt_rdma *, struct svc_rqst *,
-			       struct svc_rdma_op_ctxt *, int *, u32 *,
-			       u32, u32, u64, bool);
-extern int rdma_read_chunk_frmr(struct svcxprt_rdma *, struct svc_rqst *,
-				struct svc_rdma_op_ctxt *, int *, u32 *,
-				u32, u32, u64, bool);
 
 /* svc_rdma_rw.c */
 extern void svc_rdma_destroy_rw_ctxts(struct svcxprt_rdma *rdma);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 1452bd02d857..5fbcb73dd68d 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -41,13 +41,66 @@
  * Author: Tom Tucker <tom@opengridcomputing.com>
  */
 
-#include <linux/sunrpc/xdr.h>
-#include <linux/sunrpc/debug.h>
-#include <linux/sunrpc/rpc_rdma.h>
-#include <linux/spinlock.h>
+/* Operation
+ *
+ * The main entry point is svc_rdma_recvfrom. This is called from
+ * svc_recv when the transport indicates there is incoming data to
+ * be read. "Data Ready" is signaled when an RDMA Receive completes,
+ * or when a set of RDMA Reads complete.
+ *
+ * An svc_rqst is passed in. This structure contains an array of
+ * free pages (rq_pages) that will contain the incoming RPC message.
+ *
+ * Short messages are moved directly into svc_rqst::rq_arg, and
+ * the RPC Call is ready to be processed by the Upper Layer.
+ * svc_rdma_recvfrom returns the length of the RPC Call message,
+ * completing the reception of the RPC Call.
+ *
+ * However, when an incoming message has Read chunks,
+ * svc_rdma_recvfrom must post RDMA Reads to pull the RPC Call's
+ * data payload from the client. svc_rdma_recvfrom sets up the
+ * RDMA Reads using pages in svc_rqst::rq_pages, which are
+ * transferred to an svc_rdma_op_ctxt for the duration of the
+ * I/O. svc_rdma_recvfrom then returns zero, since the RPC message
+ * is still not yet ready.
+ *
+ * When the Read chunk payloads have become available on the
+ * server, "Data Ready" is raised again, and svc_recv calls
+ * svc_rdma_recvfrom again. This second call may use a different
+ * svc_rqst than the first one, thus any information that needs
+ * to be preserved across these two calls is kept in an
+ * svc_rdma_op_ctxt.
+ *
+ * The second call to svc_rdma_recvfrom performs final assembly
+ * of the RPC Call message, using the RDMA Read sink pages kept in
+ * the svc_rdma_op_ctxt. The xdr_buf is copied from the
+ * svc_rdma_op_ctxt to the second svc_rqst. The second call returns
+ * the length of the completed RPC Call message.
+ *
+ * Page Management
+ *
+ * Pages under I/O must be transferred from the first svc_rqst to an
+ * svc_rdma_op_ctxt before the first svc_rdma_recvfrom call returns.
+ *
+ * The first svc_rqst supplies pages for RDMA Reads. These are moved
+ * from rqstp::rq_pages into ctxt::pages. The consumed elements of
+ * the rq_pages array are set to NULL and refilled with the first
+ * svc_rdma_recvfrom call returns.
+ *
+ * During the second svc_rdma_recvfrom call, RDMA Read sink pages
+ * are transferred from the svc_rdma_op_ctxt to the second svc_rqst
+ * (see rdma_read_complete() below).
+ */
+
 #include <asm/unaligned.h>
 #include <rdma/ib_verbs.h>
 #include <rdma/rdma_cm.h>
+
+#include <linux/spinlock.h>
+
+#include <linux/sunrpc/xdr.h>
+#include <linux/sunrpc/debug.h>
+#include <linux/sunrpc/rpc_rdma.h>
 #include <linux/sunrpc/svc_rdma.h>
 
 #define RPCDBG_FACILITY	RPCDBG_SVCXPRT
@@ -61,7 +114,6 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp,
 			       struct svc_rdma_op_ctxt *ctxt,
 			       u32 byte_count)
 {
-	struct rpcrdma_msg *rmsgp;
 	struct page *page;
 	u32 bc;
 	int sge_no;
@@ -85,13 +137,6 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp,
 	rqstp->rq_arg.page_len = bc;
 	rqstp->rq_arg.page_base = 0;
 
-	/* RDMA_NOMSG: RDMA READ data should land just after RDMA RECV data */
-	rmsgp = (struct rpcrdma_msg *)rqstp->rq_arg.head[0].iov_base;
-	if (rmsgp->rm_type == rdma_nomsg)
-		rqstp->rq_arg.pages = &rqstp->rq_pages[0];
-	else
-		rqstp->rq_arg.pages = &rqstp->rq_pages[1];
-
 	sge_no = 1;
 	while (bc && sge_no < ctxt->count) {
 		page = ctxt->pages[sge_no];
@@ -320,395 +365,6 @@ out_inval:
 	return -EINVAL;
 }
 
-/* Issue an RDMA_READ using the local lkey to map the data sink */
-int rdma_read_chunk_lcl(struct svcxprt_rdma *xprt,
-			struct svc_rqst *rqstp,
-			struct svc_rdma_op_ctxt *head,
-			int *page_no,
-			u32 *page_offset,
-			u32 rs_handle,
-			u32 rs_length,
-			u64 rs_offset,
-			bool last)
-{
-	struct ib_rdma_wr read_wr;
-	int pages_needed = PAGE_ALIGN(*page_offset + rs_length) >> PAGE_SHIFT;
-	struct svc_rdma_op_ctxt *ctxt = svc_rdma_get_context(xprt);
-	int ret, read, pno;
-	u32 pg_off = *page_offset;
-	u32 pg_no = *page_no;
-
-	ctxt->direction = DMA_FROM_DEVICE;
-	ctxt->read_hdr = head;
-	pages_needed = min_t(int, pages_needed, xprt->sc_max_sge_rd);
-	read = min_t(int, (pages_needed << PAGE_SHIFT) - *page_offset,
-		     rs_length);
-
-	for (pno = 0; pno < pages_needed; pno++) {
-		int len = min_t(int, rs_length, PAGE_SIZE - pg_off);
-
-		head->arg.pages[pg_no] = rqstp->rq_arg.pages[pg_no];
-		head->arg.page_len += len;
-
-		head->arg.len += len;
-		if (!pg_off)
-			head->count++;
-		rqstp->rq_respages = &rqstp->rq_arg.pages[pg_no+1];
-		rqstp->rq_next_page = rqstp->rq_respages + 1;
-		ctxt->sge[pno].addr =
-			ib_dma_map_page(xprt->sc_cm_id->device,
-					head->arg.pages[pg_no], pg_off,
-					PAGE_SIZE - pg_off,
-					DMA_FROM_DEVICE);
-		ret = ib_dma_mapping_error(xprt->sc_cm_id->device,
-					   ctxt->sge[pno].addr);
-		if (ret)
-			goto err;
-		svc_rdma_count_mappings(xprt, ctxt);
-
-		ctxt->sge[pno].lkey = xprt->sc_pd->local_dma_lkey;
-		ctxt->sge[pno].length = len;
-		ctxt->count++;
-
-		/* adjust offset and wrap to next page if needed */
-		pg_off += len;
-		if (pg_off == PAGE_SIZE) {
-			pg_off = 0;
-			pg_no++;
-		}
-		rs_length -= len;
-	}
-
-	if (last && rs_length == 0)
-		set_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags);
-	else
-		clear_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags);
-
-	memset(&read_wr, 0, sizeof(read_wr));
-	ctxt->cqe.done = svc_rdma_wc_read;
-	read_wr.wr.wr_cqe = &ctxt->cqe;
-	read_wr.wr.opcode = IB_WR_RDMA_READ;
-	read_wr.wr.send_flags = IB_SEND_SIGNALED;
-	read_wr.rkey = rs_handle;
-	read_wr.remote_addr = rs_offset;
-	read_wr.wr.sg_list = ctxt->sge;
-	read_wr.wr.num_sge = pages_needed;
-
-	ret = svc_rdma_send(xprt, &read_wr.wr);
-	if (ret) {
-		pr_err("svcrdma: Error %d posting RDMA_READ\n", ret);
-		set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
-		goto err;
-	}
-
-	/* return current location in page array */
-	*page_no = pg_no;
-	*page_offset = pg_off;
-	ret = read;
-	atomic_inc(&rdma_stat_read);
-	return ret;
- err:
-	svc_rdma_unmap_dma(ctxt);
-	svc_rdma_put_context(ctxt, 0);
-	return ret;
-}
-
-/* Issue an RDMA_READ using an FRMR to map the data sink */
-int rdma_read_chunk_frmr(struct svcxprt_rdma *xprt,
-			 struct svc_rqst *rqstp,
-			 struct svc_rdma_op_ctxt *head,
-			 int *page_no,
-			 u32 *page_offset,
-			 u32 rs_handle,
-			 u32 rs_length,
-			 u64 rs_offset,
-			 bool last)
-{
-	struct ib_rdma_wr read_wr;
-	struct ib_send_wr inv_wr;
-	struct ib_reg_wr reg_wr;
-	u8 key;
-	int nents = PAGE_ALIGN(*page_offset + rs_length) >> PAGE_SHIFT;
-	struct svc_rdma_op_ctxt *ctxt = svc_rdma_get_context(xprt);
-	struct svc_rdma_fastreg_mr *frmr = svc_rdma_get_frmr(xprt);
-	int ret, read, pno, dma_nents, n;
-	u32 pg_off = *page_offset;
-	u32 pg_no = *page_no;
-
-	if (IS_ERR(frmr))
-		return -ENOMEM;
-
-	ctxt->direction = DMA_FROM_DEVICE;
-	ctxt->frmr = frmr;
-	nents = min_t(unsigned int, nents, xprt->sc_frmr_pg_list_len);
-	read = min_t(int, (nents << PAGE_SHIFT) - *page_offset, rs_length);
-
-	frmr->direction = DMA_FROM_DEVICE;
-	frmr->access_flags = (IB_ACCESS_LOCAL_WRITE|IB_ACCESS_REMOTE_WRITE);
-	frmr->sg_nents = nents;
-
-	for (pno = 0; pno < nents; pno++) {
-		int len = min_t(int, rs_length, PAGE_SIZE - pg_off);
-
-		head->arg.pages[pg_no] = rqstp->rq_arg.pages[pg_no];
-		head->arg.page_len += len;
-		head->arg.len += len;
-		if (!pg_off)
-			head->count++;
-
-		sg_set_page(&frmr->sg[pno], rqstp->rq_arg.pages[pg_no],
-			    len, pg_off);
-
-		rqstp->rq_respages = &rqstp->rq_arg.pages[pg_no+1];
-		rqstp->rq_next_page = rqstp->rq_respages + 1;
-
-		/* adjust offset and wrap to next page if needed */
-		pg_off += len;
-		if (pg_off == PAGE_SIZE) {
-			pg_off = 0;
-			pg_no++;
-		}
-		rs_length -= len;
-	}
-
-	if (last && rs_length == 0)
-		set_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags);
-	else
-		clear_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags);
-
-	dma_nents = ib_dma_map_sg(xprt->sc_cm_id->device,
-				  frmr->sg, frmr->sg_nents,
-				  frmr->direction);
-	if (!dma_nents) {
-		pr_err("svcrdma: failed to dma map sg %p\n",
-		       frmr->sg);
-		return -ENOMEM;
-	}
-
-	n = ib_map_mr_sg(frmr->mr, frmr->sg, frmr->sg_nents, NULL, PAGE_SIZE);
-	if (unlikely(n != frmr->sg_nents)) {
-		pr_err("svcrdma: failed to map mr %p (%d/%d elements)\n",
-		       frmr->mr, n, frmr->sg_nents);
-		return n < 0 ? n : -EINVAL;
-	}
-
-	/* Bump the key */
-	key = (u8)(frmr->mr->lkey & 0x000000FF);
-	ib_update_fast_reg_key(frmr->mr, ++key);
-
-	ctxt->sge[0].addr = frmr->mr->iova;
-	ctxt->sge[0].lkey = frmr->mr->lkey;
-	ctxt->sge[0].length = frmr->mr->length;
-	ctxt->count = 1;
-	ctxt->read_hdr = head;
-
-	/* Prepare REG WR */
-	ctxt->reg_cqe.done = svc_rdma_wc_reg;
-	reg_wr.wr.wr_cqe = &ctxt->reg_cqe;
-	reg_wr.wr.opcode = IB_WR_REG_MR;
-	reg_wr.wr.send_flags = IB_SEND_SIGNALED;
-	reg_wr.wr.num_sge = 0;
-	reg_wr.mr = frmr->mr;
-	reg_wr.key = frmr->mr->lkey;
-	reg_wr.access = frmr->access_flags;
-	reg_wr.wr.next = &read_wr.wr;
-
-	/* Prepare RDMA_READ */
-	memset(&read_wr, 0, sizeof(read_wr));
-	ctxt->cqe.done = svc_rdma_wc_read;
-	read_wr.wr.wr_cqe = &ctxt->cqe;
-	read_wr.wr.send_flags = IB_SEND_SIGNALED;
-	read_wr.rkey = rs_handle;
-	read_wr.remote_addr = rs_offset;
-	read_wr.wr.sg_list = ctxt->sge;
-	read_wr.wr.num_sge = 1;
-	if (xprt->sc_dev_caps & SVCRDMA_DEVCAP_READ_W_INV) {
-		read_wr.wr.opcode = IB_WR_RDMA_READ_WITH_INV;
-		read_wr.wr.ex.invalidate_rkey = ctxt->frmr->mr->lkey;
-	} else {
-		read_wr.wr.opcode = IB_WR_RDMA_READ;
-		read_wr.wr.next = &inv_wr;
-		/* Prepare invalidate */
-		memset(&inv_wr, 0, sizeof(inv_wr));
-		ctxt->inv_cqe.done = svc_rdma_wc_inv;
-		inv_wr.wr_cqe = &ctxt->inv_cqe;
-		inv_wr.opcode = IB_WR_LOCAL_INV;
-		inv_wr.send_flags = IB_SEND_SIGNALED | IB_SEND_FENCE;
-		inv_wr.ex.invalidate_rkey = frmr->mr->lkey;
-	}
-
-	/* Post the chain */
-	ret = svc_rdma_send(xprt, &reg_wr.wr);
-	if (ret) {
-		pr_err("svcrdma: Error %d posting RDMA_READ\n", ret);
-		set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
-		goto err;
-	}
-
-	/* return current location in page array */
-	*page_no = pg_no;
-	*page_offset = pg_off;
-	ret = read;
-	atomic_inc(&rdma_stat_read);
-	return ret;
- err:
-	svc_rdma_put_context(ctxt, 0);
-	svc_rdma_put_frmr(xprt, frmr);
-	return ret;
-}
-
-/* If there was additional inline content, append it to the end of arg.pages.
- * Tail copy has to be done after the reader function has determined how many
- * pages are needed for RDMA READ.
- */
-static int
-rdma_copy_tail(struct svc_rqst *rqstp, struct svc_rdma_op_ctxt *head,
-	       u32 position, u32 byte_count, u32 page_offset, int page_no)
-{
-	char *srcp, *destp;
-
-	srcp = head->arg.head[0].iov_base + position;
-	byte_count = head->arg.head[0].iov_len - position;
-	if (byte_count > PAGE_SIZE) {
-		dprintk("svcrdma: large tail unsupported\n");
-		return 0;
-	}
-
-	/* Fit as much of the tail on the current page as possible */
-	if (page_offset != PAGE_SIZE) {
-		destp = page_address(rqstp->rq_arg.pages[page_no]);
-		destp += page_offset;
-		while (byte_count--) {
-			*destp++ = *srcp++;
-			page_offset++;
-			if (page_offset == PAGE_SIZE && byte_count)
-				goto more;
-		}
-		goto done;
-	}
-
-more:
-	/* Fit the rest on the next page */
-	page_no++;
-	destp = page_address(rqstp->rq_arg.pages[page_no]);
-	while (byte_count--)
-		*destp++ = *srcp++;
-
-	rqstp->rq_respages = &rqstp->rq_arg.pages[page_no+1];
-	rqstp->rq_next_page = rqstp->rq_respages + 1;
-
-done:
-	byte_count = head->arg.head[0].iov_len - position;
-	head->arg.page_len += byte_count;
-	head->arg.len += byte_count;
-	head->arg.buflen += byte_count;
-	return 1;
-}
-
-/* Returns the address of the first read chunk or <nul> if no read chunk
- * is present
- */
-static struct rpcrdma_read_chunk *
-svc_rdma_get_read_chunk(struct rpcrdma_msg *rmsgp)
-{
-	struct rpcrdma_read_chunk *ch =
-		(struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
-
-	if (ch->rc_discrim == xdr_zero)
-		return NULL;
-	return ch;
-}
-
-static int rdma_read_chunks(struct svcxprt_rdma *xprt,
-			    struct rpcrdma_msg *rmsgp,
-			    struct svc_rqst *rqstp,
-			    struct svc_rdma_op_ctxt *head)
-{
-	int page_no, ret;
-	struct rpcrdma_read_chunk *ch;
-	u32 handle, page_offset, byte_count;
-	u32 position;
-	u64 rs_offset;
-	bool last;
-
-	/* If no read list is present, return 0 */
-	ch = svc_rdma_get_read_chunk(rmsgp);
-	if (!ch)
-		return 0;
-
-	/* The request is completed when the RDMA_READs complete. The
-	 * head context keeps all the pages that comprise the
-	 * request.
-	 */
-	head->arg.head[0] = rqstp->rq_arg.head[0];
-	head->arg.tail[0] = rqstp->rq_arg.tail[0];
-	head->hdr_count = head->count;
-	head->arg.page_base = 0;
-	head->arg.page_len = 0;
-	head->arg.len = rqstp->rq_arg.len;
-	head->arg.buflen = rqstp->rq_arg.buflen;
-
-	/* RDMA_NOMSG: RDMA READ data should land just after RDMA RECV data */
-	position = be32_to_cpu(ch->rc_position);
-	if (position == 0) {
-		head->arg.pages = &head->pages[0];
-		page_offset = head->byte_len;
-	} else {
-		head->arg.pages = &head->pages[head->count];
-		page_offset = 0;
-	}
-
-	ret = 0;
-	page_no = 0;
-	for (; ch->rc_discrim != xdr_zero; ch++) {
-		if (be32_to_cpu(ch->rc_position) != position)
-			goto err;
-
-		handle = be32_to_cpu(ch->rc_target.rs_handle),
-		byte_count = be32_to_cpu(ch->rc_target.rs_length);
-		xdr_decode_hyper((__be32 *)&ch->rc_target.rs_offset,
-				 &rs_offset);
-
-		while (byte_count > 0) {
-			last = (ch + 1)->rc_discrim == xdr_zero;
-			ret = xprt->sc_reader(xprt, rqstp, head,
-					      &page_no, &page_offset,
-					      handle, byte_count,
-					      rs_offset, last);
-			if (ret < 0)
-				goto err;
-			byte_count -= ret;
-			rs_offset += ret;
-			head->arg.buflen += ret;
-		}
-	}
-
-	/* Read list may need XDR round-up (see RFC 5666, s. 3.7) */
-	if (page_offset & 3) {
-		u32 pad = 4 - (page_offset & 3);
-
-		head->arg.tail[0].iov_len += pad;
-		head->arg.len += pad;
-		head->arg.buflen += pad;
-		page_offset += pad;
-	}
-
-	ret = 1;
-	if (position && position < head->arg.head[0].iov_len)
-		ret = rdma_copy_tail(rqstp, head, position,
-				     byte_count, page_offset, page_no);
-	head->arg.head[0].iov_len = position;
-	head->position = position;
-
- err:
-	/* Detach arg pages. svc_recv will replenish them */
-	for (page_no = 0;
-	     &rqstp->rq_pages[page_no] < rqstp->rq_respages; page_no++)
-		rqstp->rq_pages[page_no] = NULL;
-
-	return ret;
-}
-
 static void rdma_read_complete(struct svc_rqst *rqstp,
 			       struct svc_rdma_op_ctxt *head)
 {
@@ -720,24 +376,9 @@ static void rdma_read_complete(struct svc_rqst *rqstp,
 		rqstp->rq_pages[page_no] = head->pages[page_no];
 	}
 
-	/* Adjustments made for RDMA_NOMSG type requests */
-	if (head->position == 0) {
-		if (head->arg.len <= head->sge[0].length) {
-			head->arg.head[0].iov_len = head->arg.len -
-							head->byte_len;
-			head->arg.page_len = 0;
-		} else {
-			head->arg.head[0].iov_len = head->sge[0].length -
-								head->byte_len;
-			head->arg.page_len = head->arg.len -
-						head->sge[0].length;
-		}
-	}
-
 	/* Point rq_arg.pages past header */
 	rqstp->rq_arg.pages = &rqstp->rq_pages[head->hdr_count];
 	rqstp->rq_arg.page_len = head->arg.page_len;
-	rqstp->rq_arg.page_base = head->arg.page_base;
 
 	/* rq_respages starts after the last arg page */
 	rqstp->rq_respages = &rqstp->rq_pages[page_no];
@@ -834,10 +475,35 @@ static bool svc_rdma_is_backchannel_reply(struct svc_xprt *xprt,
 	return true;
 }
 
-/*
- * Set up the rqstp thread context to point to the RQ buffer. If
- * necessary, pull additional data from the client with an RDMA_READ
- * request.
+/**
+ * svc_rdma_recvfrom - Receive an RPC call
+ * @rqstp: request structure into which to receive an RPC Call
+ *
+ * Returns:
+ *	The positive number of bytes in the RPC Call message,
+ *	%0 if there were no Calls ready to return,
+ *	%-EINVAL if the Read chunk data is too large,
+ *	%-ENOMEM if rdma_rw context pool was exhausted,
+ *	%-ENOTCONN if posting failed (connection is lost),
+ *	%-EIO if rdma_rw initialization failed (DMA mapping, etc).
+ *
+ * Called in a loop when XPT_DATA is set. XPT_DATA is cleared only
+ * when there are no remaining ctxt's to process.
+ *
+ * The next ctxt is removed from the "receive" lists.
+ *
+ * - If the ctxt completes a Read, then finish assembling the Call
+ *   message and return the number of bytes in the message.
+ *
+ * - If the ctxt completes a Receive, then construct the Call
+ *   message from the contents of the Receive buffer.
+ *
+ *   - If there are no Read chunks in this message, then finish
+ *     assembling the Call message and return the number of bytes
+ *     in the message.
+ *
+ *   - If there are Read chunks in this message, post Read WRs to
+ *     pull that payload and return 0.
  */
 int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 {
@@ -845,11 +511,9 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 	struct svcxprt_rdma *rdma_xprt =
 		container_of(xprt, struct svcxprt_rdma, sc_xprt);
 	struct svc_rdma_op_ctxt *ctxt;
-	struct rpcrdma_msg *rmsgp;
+	__be32 *p;
 	int ret;
 
-	dprintk("svcrdma: rqstp=%p\n", rqstp);
-
 	spin_lock(&rdma_xprt->sc_rq_dto_lock);
 	if (!list_empty(&rdma_xprt->sc_read_complete_q)) {
 		ctxt = list_first_entry(&rdma_xprt->sc_read_complete_q,
@@ -870,7 +534,7 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 	}
 	spin_unlock(&rdma_xprt->sc_rq_dto_lock);
 
-	dprintk("svcrdma: processing ctxt=%p on xprt=%p, rqstp=%p\n",
+	dprintk("svcrdma: recvfrom: ctxt=%p on xprt=%p, rqstp=%p\n",
 		ctxt, rdma_xprt, rqstp);
 	atomic_inc(&rdma_stat_recv);
 
@@ -878,7 +542,7 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 	rdma_build_arg_xdr(rqstp, ctxt, ctxt->byte_len);
 
 	/* Decode the RDMA header. */
-	rmsgp = (struct rpcrdma_msg *)rqstp->rq_arg.head[0].iov_base;
+	p = (__be32 *)rqstp->rq_arg.head[0].iov_base;
 	ret = svc_rdma_xdr_decode_req(&rqstp->rq_arg);
 	if (ret < 0)
 		goto out_err;
@@ -886,9 +550,8 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 		goto out_drop;
 	rqstp->rq_xprt_hlen = ret;
 
-	if (svc_rdma_is_backchannel_reply(xprt, &rmsgp->rm_xid)) {
-		ret = svc_rdma_handle_bc_reply(xprt->xpt_bc_xprt,
-					       &rmsgp->rm_xid,
+	if (svc_rdma_is_backchannel_reply(xprt, p)) {
+		ret = svc_rdma_handle_bc_reply(xprt->xpt_bc_xprt, p,
 					       &rqstp->rq_arg);
 		svc_rdma_put_context(ctxt, 0);
 		if (ret)
@@ -896,16 +559,9 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 		return ret;
 	}
 
-	/* Read read-list data. */
-	ret = rdma_read_chunks(rdma_xprt, rmsgp, rqstp, ctxt);
-	if (ret > 0) {
-		/* read-list posted, defer until data received from client. */
-		goto defer;
-	} else if (ret < 0) {
-		/* Post of read-list failed, free context. */
-		svc_rdma_put_context(ctxt, 1);
-		return 0;
-	}
+	p += rpcrdma_fixed_maxsz;
+	if (*p != xdr_zero)
+		goto out_readchunk;
 
 complete:
 	ret = rqstp->rq_arg.head[0].iov_len
@@ -921,13 +577,22 @@ complete:
 	svc_xprt_copy_addrs(rqstp, xprt);
 	return ret;
 
+out_readchunk:
+	ret = svc_rdma_recv_read_chunk(rdma_xprt, rqstp, ctxt, p);
+	if (ret < 0)
+		goto out_postfail;
+	return 0;
+
 out_err:
-	svc_rdma_send_error(rdma_xprt, &rmsgp->rm_xid, ret);
+	svc_rdma_send_error(rdma_xprt, p, ret);
 	svc_rdma_put_context(ctxt, 0);
 	return 0;
 
-defer:
-	return 0;
+out_postfail:
+	if (ret == -EINVAL)
+		svc_rdma_send_error(rdma_xprt, p, ret);
+	svc_rdma_put_context(ctxt, 1);
+	return ret;
 
 out_drop:
 	svc_rdma_put_context(ctxt, 1);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index a9d9cb1ba4c6..72d2dcdca2e1 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -908,8 +908,6 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 	 * capabilities of this particular device */
 	newxprt->sc_max_sge = min((size_t)dev->attrs.max_sge,
 				  (size_t)RPCSVC_MAXPAGES);
-	newxprt->sc_max_sge_rd = min_t(size_t, dev->attrs.max_sge_rd,
-				       RPCSVC_MAXPAGES);
 	newxprt->sc_max_req_size = svcrdma_max_req_size;
 	newxprt->sc_max_requests = min_t(u32, dev->attrs.max_qp_wr,
 					 svcrdma_max_requests);
@@ -998,12 +996,10 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 	 * NB:	iWARP requires remote write access for the data sink
 	 *	of an RDMA_READ. IB does not.
 	 */
-	newxprt->sc_reader = rdma_read_chunk_lcl;
 	if (dev->attrs.device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS) {
 		newxprt->sc_frmr_pg_list_len =
 			dev->attrs.max_fast_reg_page_list_len;
 		newxprt->sc_dev_caps |= SVCRDMA_DEVCAP_FAST_REG;
-		newxprt->sc_reader = rdma_read_chunk_frmr;
 	} else
 		newxprt->sc_snd_w_inv = false;
 
@@ -1056,7 +1052,6 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 	sap = (struct sockaddr *)&newxprt->sc_cm_id->route.addr.dst_addr;
 	dprintk("    remote address  : %pIS:%u\n", sap, rpc_get_port(sap));
 	dprintk("    max_sge         : %d\n", newxprt->sc_max_sge);
-	dprintk("    max_sge_rd      : %d\n", newxprt->sc_max_sge_rd);
 	dprintk("    sq_depth        : %d\n", newxprt->sc_sq_depth);
 	dprintk("    max_requests    : %d\n", newxprt->sc_max_requests);
 	dprintk("    ord             : %d\n", newxprt->sc_ord);
@@ -1117,12 +1112,6 @@ static void __svc_rdma_free(struct work_struct *work)
 		pr_err("svcrdma: sc_xprt still in use? (%d)\n",
 		       kref_read(&xprt->xpt_ref));
 
-	/*
-	 * Destroy queued, but not processed read completions. Note
-	 * that this cleanup has to be done before destroying the
-	 * cm_id because the device ptr is needed to unmap the dma in
-	 * svc_rdma_put_context.
-	 */
 	while (!list_empty(&rdma->sc_read_complete_q)) {
 		struct svc_rdma_op_ctxt *ctxt;
 		ctxt = list_first_entry(&rdma->sc_read_complete_q,
@@ -1130,8 +1119,6 @@ static void __svc_rdma_free(struct work_struct *work)
 		list_del(&ctxt->list);
 		svc_rdma_put_context(ctxt, 1);
 	}
-
-	/* Destroy queued, but not processed recv completions */
 	while (!list_empty(&rdma->sc_rq_dto_q)) {
 		struct svc_rdma_op_ctxt *ctxt;
 		ctxt = list_first_entry(&rdma->sc_rq_dto_q,
-- 
cgit v1.2.3


From c84dc900d737a8d8f08768622226980ee863403b Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 23 Jun 2017 17:18:49 -0400
Subject: svcrdma: Remove unused Read completion handlers

Clean up:

The generic RDMA R/W API conversion of svc_rdma_recvfrom replaced
the Register, Read, and Invalidate completion handlers. Remove the
old ones, which are no longer used.

These handlers shared some helper code with svc_rdma_wc_send. Fold
the wc_common helper back into the one remaining completion handler.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 include/linux/sunrpc/svc_rdma.h          |  4 +-
 net/sunrpc/xprtrdma/svc_rdma_transport.c | 93 ++++----------------------------
 2 files changed, 10 insertions(+), 87 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index b1ba19ba1071..06d58a3f74bc 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -77,17 +77,15 @@ extern atomic_t rdma_stat_sq_prod;
  */
 struct svc_rdma_op_ctxt {
 	struct list_head list;
-	struct svc_rdma_op_ctxt *read_hdr;
 	struct svc_rdma_fastreg_mr *frmr;
-	int hdr_count;
 	struct xdr_buf arg;
 	struct ib_cqe cqe;
 	u32 byte_len;
 	struct svcxprt_rdma *xprt;
-	unsigned long flags;
 	enum dma_data_direction direction;
 	int count;
 	unsigned int mapped_sges;
+	int hdr_count;
 	struct ib_send_wr send_wr;
 	struct ib_sge sge[1 + RPCRDMA_MAX_INLINE_THRESH / PAGE_SIZE];
 	struct page *pages[RPCSVC_MAXPAGES];
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 72d2dcdca2e1..c915cba0f8e6 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -346,36 +346,6 @@ out:
 	svc_xprt_put(&xprt->sc_xprt);
 }
 
-static void svc_rdma_send_wc_common(struct svcxprt_rdma *xprt,
-				    struct ib_wc *wc,
-				    const char *opname)
-{
-	if (wc->status != IB_WC_SUCCESS)
-		goto err;
-
-out:
-	atomic_inc(&xprt->sc_sq_avail);
-	wake_up(&xprt->sc_send_wait);
-	return;
-
-err:
-	set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
-	if (wc->status != IB_WC_WR_FLUSH_ERR)
-		pr_err("svcrdma: %s: %s (%u/0x%x)\n",
-		       opname, ib_wc_status_msg(wc->status),
-		       wc->status, wc->vendor_err);
-	goto out;
-}
-
-static void svc_rdma_send_wc_common_put(struct ib_cq *cq, struct ib_wc *wc,
-					const char *opname)
-{
-	struct svcxprt_rdma *xprt = cq->cq_context;
-
-	svc_rdma_send_wc_common(xprt, wc, opname);
-	svc_xprt_put(&xprt->sc_xprt);
-}
-
 /**
  * svc_rdma_wc_send - Invoked by RDMA provider for each polled Send WC
  * @cq:        completion queue
@@ -383,74 +353,29 @@ static void svc_rdma_send_wc_common_put(struct ib_cq *cq, struct ib_wc *wc,
  *
  */
 void svc_rdma_wc_send(struct ib_cq *cq, struct ib_wc *wc)
-{
-	struct ib_cqe *cqe = wc->wr_cqe;
-	struct svc_rdma_op_ctxt *ctxt;
-
-	svc_rdma_send_wc_common_put(cq, wc, "send");
-
-	ctxt = container_of(cqe, struct svc_rdma_op_ctxt, cqe);
-	svc_rdma_unmap_dma(ctxt);
-	svc_rdma_put_context(ctxt, 1);
-}
-
-/**
- * svc_rdma_wc_reg - Invoked by RDMA provider for each polled FASTREG WC
- * @cq:        completion queue
- * @wc:        completed WR
- *
- */
-void svc_rdma_wc_reg(struct ib_cq *cq, struct ib_wc *wc)
-{
-	svc_rdma_send_wc_common_put(cq, wc, "fastreg");
-}
-
-/**
- * svc_rdma_wc_read - Invoked by RDMA provider for each polled Read WC
- * @cq:        completion queue
- * @wc:        completed WR
- *
- */
-void svc_rdma_wc_read(struct ib_cq *cq, struct ib_wc *wc)
 {
 	struct svcxprt_rdma *xprt = cq->cq_context;
 	struct ib_cqe *cqe = wc->wr_cqe;
 	struct svc_rdma_op_ctxt *ctxt;
 
-	svc_rdma_send_wc_common(xprt, wc, "read");
+	atomic_inc(&xprt->sc_sq_avail);
+	wake_up(&xprt->sc_send_wait);
 
 	ctxt = container_of(cqe, struct svc_rdma_op_ctxt, cqe);
 	svc_rdma_unmap_dma(ctxt);
-	svc_rdma_put_frmr(xprt, ctxt->frmr);
-
-	if (test_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags)) {
-		struct svc_rdma_op_ctxt *read_hdr;
-
-		read_hdr = ctxt->read_hdr;
-		spin_lock(&xprt->sc_rq_dto_lock);
-		list_add_tail(&read_hdr->list,
-			      &xprt->sc_read_complete_q);
-		spin_unlock(&xprt->sc_rq_dto_lock);
+	svc_rdma_put_context(ctxt, 1);
 
-		set_bit(XPT_DATA, &xprt->sc_xprt.xpt_flags);
-		svc_xprt_enqueue(&xprt->sc_xprt);
+	if (unlikely(wc->status != IB_WC_SUCCESS)) {
+		set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
+		if (wc->status != IB_WC_WR_FLUSH_ERR)
+			pr_err("svcrdma: Send: %s (%u/0x%x)\n",
+			       ib_wc_status_msg(wc->status),
+			       wc->status, wc->vendor_err);
 	}
 
-	svc_rdma_put_context(ctxt, 0);
 	svc_xprt_put(&xprt->sc_xprt);
 }
 
-/**
- * svc_rdma_wc_inv - Invoked by RDMA provider for each polled LOCAL_INV WC
- * @cq:        completion queue
- * @wc:        completed WR
- *
- */
-void svc_rdma_wc_inv(struct ib_cq *cq, struct ib_wc *wc)
-{
-	svc_rdma_send_wc_common_put(cq, wc, "localInv");
-}
-
 static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv,
 					     int listener)
 {
-- 
cgit v1.2.3


From 463e63d7014442002399903af027b63ae38f6e77 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 23 Jun 2017 17:18:57 -0400
Subject: svcrdma: Remove frmr cache

Clean up: Now that the svc_rdma_recvfrom path uses the rdma_rw API,
the details of Read sink buffer registration are dealt with by the
kernel's RDMA core. This cache is no longer used, and can be
removed.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 include/linux/sunrpc/svc_rdma.h          | 18 -------
 net/sunrpc/xprtrdma/svc_rdma_transport.c | 86 --------------------------------
 2 files changed, 104 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 06d58a3f74bc..fd7775f70bb5 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -77,7 +77,6 @@ extern atomic_t rdma_stat_sq_prod;
  */
 struct svc_rdma_op_ctxt {
 	struct list_head list;
-	struct svc_rdma_fastreg_mr *frmr;
 	struct xdr_buf arg;
 	struct ib_cqe cqe;
 	u32 byte_len;
@@ -91,17 +90,6 @@ struct svc_rdma_op_ctxt {
 	struct page *pages[RPCSVC_MAXPAGES];
 };
 
-struct svc_rdma_fastreg_mr {
-	struct ib_mr *mr;
-	struct scatterlist *sg;
-	int sg_nents;
-	unsigned long access_flags;
-	enum dma_data_direction direction;
-	struct list_head frmr_list;
-};
-
-#define RDMACTXT_F_LAST_CTXT	2
-
 #define	SVCRDMA_DEVCAP_FAST_REG		1	/* fast mr registration */
 #define	SVCRDMA_DEVCAP_READ_W_INV	2	/* read w/ invalidate */
 
@@ -136,9 +124,6 @@ struct svcxprt_rdma {
 	struct ib_cq         *sc_rq_cq;
 	struct ib_cq         *sc_sq_cq;
 	u32		     sc_dev_caps;	/* distilled device caps */
-	unsigned int	     sc_frmr_pg_list_len;
-	struct list_head     sc_frmr_q;
-	spinlock_t	     sc_frmr_q_lock;
 
 	spinlock_t	     sc_lock;		/* transport lock */
 
@@ -210,9 +195,6 @@ extern int svc_rdma_create_listen(struct svc_serv *, int, struct sockaddr *);
 extern struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *);
 extern void svc_rdma_put_context(struct svc_rdma_op_ctxt *, int);
 extern void svc_rdma_unmap_dma(struct svc_rdma_op_ctxt *ctxt);
-extern struct svc_rdma_fastreg_mr *svc_rdma_get_frmr(struct svcxprt_rdma *);
-extern void svc_rdma_put_frmr(struct svcxprt_rdma *,
-			      struct svc_rdma_fastreg_mr *);
 extern void svc_sq_reap(struct svcxprt_rdma *);
 extern void svc_rq_reap(struct svcxprt_rdma *);
 extern void svc_rdma_prep_reply_hdr(struct svc_rqst *);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index c915cba0f8e6..8864105d86ec 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -202,7 +202,6 @@ struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt)
 out:
 	ctxt->count = 0;
 	ctxt->mapped_sges = 0;
-	ctxt->frmr = NULL;
 	return ctxt;
 
 out_empty:
@@ -387,14 +386,12 @@ static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv,
 	INIT_LIST_HEAD(&cma_xprt->sc_accept_q);
 	INIT_LIST_HEAD(&cma_xprt->sc_rq_dto_q);
 	INIT_LIST_HEAD(&cma_xprt->sc_read_complete_q);
-	INIT_LIST_HEAD(&cma_xprt->sc_frmr_q);
 	INIT_LIST_HEAD(&cma_xprt->sc_ctxts);
 	INIT_LIST_HEAD(&cma_xprt->sc_rw_ctxts);
 	init_waitqueue_head(&cma_xprt->sc_send_wait);
 
 	spin_lock_init(&cma_xprt->sc_lock);
 	spin_lock_init(&cma_xprt->sc_rq_dto_lock);
-	spin_lock_init(&cma_xprt->sc_frmr_q_lock);
 	spin_lock_init(&cma_xprt->sc_ctxt_lock);
 	spin_lock_init(&cma_xprt->sc_rw_ctxt_lock);
 
@@ -705,86 +702,6 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv,
 	return ERR_PTR(ret);
 }
 
-static struct svc_rdma_fastreg_mr *rdma_alloc_frmr(struct svcxprt_rdma *xprt)
-{
-	struct ib_mr *mr;
-	struct scatterlist *sg;
-	struct svc_rdma_fastreg_mr *frmr;
-	u32 num_sg;
-
-	frmr = kmalloc(sizeof(*frmr), GFP_KERNEL);
-	if (!frmr)
-		goto err;
-
-	num_sg = min_t(u32, RPCSVC_MAXPAGES, xprt->sc_frmr_pg_list_len);
-	mr = ib_alloc_mr(xprt->sc_pd, IB_MR_TYPE_MEM_REG, num_sg);
-	if (IS_ERR(mr))
-		goto err_free_frmr;
-
-	sg = kcalloc(RPCSVC_MAXPAGES, sizeof(*sg), GFP_KERNEL);
-	if (!sg)
-		goto err_free_mr;
-
-	sg_init_table(sg, RPCSVC_MAXPAGES);
-
-	frmr->mr = mr;
-	frmr->sg = sg;
-	INIT_LIST_HEAD(&frmr->frmr_list);
-	return frmr;
-
- err_free_mr:
-	ib_dereg_mr(mr);
- err_free_frmr:
-	kfree(frmr);
- err:
-	return ERR_PTR(-ENOMEM);
-}
-
-static void rdma_dealloc_frmr_q(struct svcxprt_rdma *xprt)
-{
-	struct svc_rdma_fastreg_mr *frmr;
-
-	while (!list_empty(&xprt->sc_frmr_q)) {
-		frmr = list_entry(xprt->sc_frmr_q.next,
-				  struct svc_rdma_fastreg_mr, frmr_list);
-		list_del_init(&frmr->frmr_list);
-		kfree(frmr->sg);
-		ib_dereg_mr(frmr->mr);
-		kfree(frmr);
-	}
-}
-
-struct svc_rdma_fastreg_mr *svc_rdma_get_frmr(struct svcxprt_rdma *rdma)
-{
-	struct svc_rdma_fastreg_mr *frmr = NULL;
-
-	spin_lock(&rdma->sc_frmr_q_lock);
-	if (!list_empty(&rdma->sc_frmr_q)) {
-		frmr = list_entry(rdma->sc_frmr_q.next,
-				  struct svc_rdma_fastreg_mr, frmr_list);
-		list_del_init(&frmr->frmr_list);
-		frmr->sg_nents = 0;
-	}
-	spin_unlock(&rdma->sc_frmr_q_lock);
-	if (frmr)
-		return frmr;
-
-	return rdma_alloc_frmr(rdma);
-}
-
-void svc_rdma_put_frmr(struct svcxprt_rdma *rdma,
-		       struct svc_rdma_fastreg_mr *frmr)
-{
-	if (frmr) {
-		ib_dma_unmap_sg(rdma->sc_cm_id->device,
-				frmr->sg, frmr->sg_nents, frmr->direction);
-		spin_lock(&rdma->sc_frmr_q_lock);
-		WARN_ON_ONCE(!list_empty(&frmr->frmr_list));
-		list_add(&frmr->frmr_list, &rdma->sc_frmr_q);
-		spin_unlock(&rdma->sc_frmr_q_lock);
-	}
-}
-
 /*
  * This is the xpo_recvfrom function for listening endpoints. Its
  * purpose is to accept incoming connections. The CMA callback handler
@@ -922,8 +839,6 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 	 *	of an RDMA_READ. IB does not.
 	 */
 	if (dev->attrs.device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS) {
-		newxprt->sc_frmr_pg_list_len =
-			dev->attrs.max_fast_reg_page_list_len;
 		newxprt->sc_dev_caps |= SVCRDMA_DEVCAP_FAST_REG;
 	} else
 		newxprt->sc_snd_w_inv = false;
@@ -1063,7 +978,6 @@ static void __svc_rdma_free(struct work_struct *work)
 		xprt->xpt_bc_xprt = NULL;
 	}
 
-	rdma_dealloc_frmr_q(rdma);
 	svc_rdma_destroy_rw_ctxts(rdma);
 	svc_rdma_destroy_ctxts(rdma);
 
-- 
cgit v1.2.3


From 9450ca8e2febb0000a5efd4f5870915d59ae62bc Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 23 Jun 2017 17:19:13 -0400
Subject: svcrdma: Clean up after converting svc_rdma_recvfrom to rdma_rw API

Clean up: Registration mode details are now handled by the rdma_rw
API, and thus can be removed from svcrdma.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 include/linux/sunrpc/svc_rdma.h          |  4 ----
 net/sunrpc/xprtrdma/svc_rdma_transport.c | 39 ++++----------------------------
 2 files changed, 4 insertions(+), 39 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index fd7775f70bb5..995c6fe9ee90 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -90,9 +90,6 @@ struct svc_rdma_op_ctxt {
 	struct page *pages[RPCSVC_MAXPAGES];
 };
 
-#define	SVCRDMA_DEVCAP_FAST_REG		1	/* fast mr registration */
-#define	SVCRDMA_DEVCAP_READ_W_INV	2	/* read w/ invalidate */
-
 struct svcxprt_rdma {
 	struct svc_xprt      sc_xprt;		/* SVC transport structure */
 	struct rdma_cm_id    *sc_cm_id;		/* RDMA connection id */
@@ -123,7 +120,6 @@ struct svcxprt_rdma {
 	struct ib_qp         *sc_qp;
 	struct ib_cq         *sc_rq_cq;
 	struct ib_cq         *sc_sq_cq;
-	u32		     sc_dev_caps;	/* distilled device caps */
 
 	spinlock_t	     sc_lock;		/* transport lock */
 
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 75bd11f2b69e..e660d4965b18 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -783,7 +783,7 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 	memset(&qp_attr, 0, sizeof qp_attr);
 	qp_attr.event_handler = qp_event_handler;
 	qp_attr.qp_context = &newxprt->sc_xprt;
-	qp_attr.port_num = newxprt->sc_cm_id->port_num;
+	qp_attr.port_num = newxprt->sc_port_num;
 	qp_attr.cap.max_rdma_ctxs = newxprt->sc_max_requests;
 	qp_attr.cap.max_send_wr = newxprt->sc_sq_depth;
 	qp_attr.cap.max_recv_wr = newxprt->sc_rq_depth;
@@ -807,43 +807,12 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 	}
 	newxprt->sc_qp = newxprt->sc_cm_id->qp;
 
-	/*
-	 * Use the most secure set of MR resources based on the
-	 * transport type and available memory management features in
-	 * the device. Here's the table implemented below:
-	 *
-	 *		Fast	Global	DMA	Remote WR
-	 *		Reg	LKEY	MR	Access
-	 *		Sup'd	Sup'd	Needed	Needed
-	 *
-	 * IWARP	N	N	Y	Y
-	 *		N	Y	Y	Y
-	 *		Y	N	Y	N
-	 *		Y	Y	N	-
-	 *
-	 * IB		N	N	Y	N
-	 *		N	Y	N	-
-	 *		Y	N	Y	N
-	 *		Y	Y	N	-
-	 *
-	 * NB:	iWARP requires remote write access for the data sink
-	 *	of an RDMA_READ. IB does not.
-	 */
-	if (dev->attrs.device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS) {
-		newxprt->sc_dev_caps |= SVCRDMA_DEVCAP_FAST_REG;
-	} else
+	if (!(dev->attrs.device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS))
 		newxprt->sc_snd_w_inv = false;
-
-	/*
-	 * Determine if a DMA MR is required and if so, what privs are required
-	 */
-	if (!rdma_protocol_iwarp(dev, newxprt->sc_cm_id->port_num) &&
-	    !rdma_ib_or_roce(dev, newxprt->sc_cm_id->port_num))
+	if (!rdma_protocol_iwarp(dev, newxprt->sc_port_num) &&
+	    !rdma_ib_or_roce(dev, newxprt->sc_port_num))
 		goto errout;
 
-	if (rdma_protocol_iwarp(dev, newxprt->sc_cm_id->port_num))
-		newxprt->sc_dev_caps |= SVCRDMA_DEVCAP_READ_W_INV;
-
 	/* Post receive buffers */
 	for (i = 0; i < newxprt->sc_max_requests; i++) {
 		ret = svc_rdma_post_recv(newxprt, GFP_KERNEL);
-- 
cgit v1.2.3


From 949c033694864082db9b3f5304723a6d7407f8e2 Mon Sep 17 00:00:00 2001
From: Gleb Fotengauer-Malinovskiy <glebfm@altlinux.org>
Date: Tue, 11 Jul 2017 00:22:33 +0300
Subject: KVM: s390: Fix KVM_S390_GET_CMMA_BITS ioctl definition
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In case of KVM_S390_GET_CMMA_BITS, the kernel does not only read struct
kvm_s390_cmma_log passed from userspace (which constitutes _IOC_WRITE),
it also writes back a return value (which constitutes _IOC_READ) making
this an _IOWR ioctl instead of _IOW.

Fixes: 4036e387 ("KVM: s390: ioctls to get and set guest storage attributes")
Signed-off-by: Gleb Fotengauer-Malinovskiy <glebfm@altlinux.org>
Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
---
 include/uapi/linux/kvm.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index c0b6dfec5f87..ebd604c222d8 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1351,7 +1351,7 @@ struct kvm_s390_ucas_mapping {
 /* Available with KVM_CAP_X86_SMM */
 #define KVM_SMI                   _IO(KVMIO,   0xb7)
 /* Available with KVM_CAP_S390_CMMA_MIGRATION */
-#define KVM_S390_GET_CMMA_BITS      _IOW(KVMIO, 0xb8, struct kvm_s390_cmma_log)
+#define KVM_S390_GET_CMMA_BITS      _IOWR(KVMIO, 0xb8, struct kvm_s390_cmma_log)
 #define KVM_S390_SET_CMMA_BITS      _IOW(KVMIO, 0xb9, struct kvm_s390_cmma_log)
 
 #define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)
-- 
cgit v1.2.3


From 40bf6a35483ee25271ce2a90d8976cf1409a033a Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@free-electrons.com>
Date: Wed, 12 Jul 2017 10:23:13 +0200
Subject: rtc: Remove wrong deprecation comment

rtc_time_to_tm and rtc_tm_to_time are not deprecated and make perfect sense
for RTCs that are simple 32bit counters.

Signed-off-by: Alexandre Belloni <alexandre.belloni@free-electrons.com>
---
 include/linux/rtc.h | 6 ------
 1 file changed, 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/rtc.h b/include/linux/rtc.h
index d53ecdc060cf..0a0f0d14a5fb 100644
--- a/include/linux/rtc.h
+++ b/include/linux/rtc.h
@@ -33,17 +33,11 @@ static inline time64_t rtc_tm_sub(struct rtc_time *lhs, struct rtc_time *rhs)
 	return rtc_tm_to_time64(lhs) - rtc_tm_to_time64(rhs);
 }
 
-/**
- * Deprecated. Use rtc_time64_to_tm().
- */
 static inline void rtc_time_to_tm(unsigned long time, struct rtc_time *tm)
 {
 	rtc_time64_to_tm(time, tm);
 }
 
-/**
- * Deprecated. Use rtc_tm_to_time64().
- */
 static inline int rtc_tm_to_time(struct rtc_time *tm, unsigned long *time)
 {
 	*time = rtc_tm_to_time64(tm);
-- 
cgit v1.2.3


From 771edcafa753aad304babd3bab8e413574d5db3b Mon Sep 17 00:00:00 2001
From: stephen hemminger <stephen@networkplumber.org>
Date: Wed, 12 Jul 2017 09:29:06 -0700
Subject: socket: add documentation for missing elements

Fill in missing kernel-doc for missing elements in struct sock.

Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index 8c85791fc196..f69c8c2782df 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -246,6 +246,7 @@ struct sock_common {
   *	@sk_policy: flow policy
   *	@sk_receive_queue: incoming packets
   *	@sk_wmem_alloc: transmit queue bytes committed
+  *	@sk_tsq_flags: TCP Small Queues flags
   *	@sk_write_queue: Packet sending queue
   *	@sk_omem_alloc: "o" is "option" or "other"
   *	@sk_wmem_queued: persistent queue size
@@ -257,6 +258,7 @@ struct sock_common {
   *	@sk_pacing_status: Pacing status (requested, handled by sch_fq)
   *	@sk_max_pacing_rate: Maximum pacing rate (%SO_MAX_PACING_RATE)
   *	@sk_sndbuf: size of send buffer in bytes
+  *	@__sk_flags_offset: empty field used to determine location of bitfield
   *	@sk_padding: unused element for alignment
   *	@sk_no_check_tx: %SO_NO_CHECK setting, set checksum in TX packets
   *	@sk_no_check_rx: allow zero checksum in RX packets
@@ -277,6 +279,7 @@ struct sock_common {
   *	@sk_drops: raw/udp drops counter
   *	@sk_ack_backlog: current listen backlog
   *	@sk_max_ack_backlog: listen backlog set in listen()
+  *	@sk_uid: user id of owner
   *	@sk_priority: %SO_PRIORITY setting
   *	@sk_type: socket type (%SOCK_STREAM, etc)
   *	@sk_protocol: which protocol this socket belongs in this network family
-- 
cgit v1.2.3


From 0a2c13d9cd76c84f2520f573ff83f777eb7464aa Mon Sep 17 00:00:00 2001
From: Stephen Rothwell <sfr@canb.auug.org.au>
Date: Wed, 12 Jul 2017 14:33:01 -0700
Subject: include/linux/dcache.h: use unsigned chars in struct name_snapshot

"kernel.h: handle pointers to arrays better in container_of()" triggers:

In file included from include/uapi/linux/stddef.h:1:0,
                 from include/linux/stddef.h:4,
                 from include/uapi/linux/posix_types.h:4,
                 from include/uapi/linux/types.h:13,
                 from include/linux/types.h:5,
                 from include/linux/syscalls.h:71,
                 from fs/dcache.c:17:
fs/dcache.c: In function 'release_dentry_name_snapshot':
include/linux/compiler.h:542:38: error: call to '__compiletime_assert_305' declared with attribute error: pointer type mismatch in container_of()
  _compiletime_assert(condition, msg, __compiletime_assert_, __LINE__)
                                      ^
include/linux/compiler.h:525:4: note: in definition of macro '__compiletime_assert'
    prefix ## suffix();    \
    ^
include/linux/compiler.h:542:2: note: in expansion of macro '_compiletime_assert'
  _compiletime_assert(condition, msg, __compiletime_assert_, __LINE__)
  ^
include/linux/build_bug.h:46:37: note: in expansion of macro 'compiletime_assert'
 #define BUILD_BUG_ON_MSG(cond, msg) compiletime_assert(!(cond), msg)
                                     ^
include/linux/kernel.h:860:2: note: in expansion of macro 'BUILD_BUG_ON_MSG'
  BUILD_BUG_ON_MSG(!__same_type(*(ptr), ((type *)0)->member) && \
  ^
fs/dcache.c:305:7: note: in expansion of macro 'container_of'
   p = container_of(name->name, struct external_name, name[0]);

Switch name_snapshot to use unsigned chars, matching struct qstr and
struct external_name.

Link: http://lkml.kernel.org/r/20170710152134.0f78c1e6@canb.auug.org.au
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/dcache.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 025727bf6797..c706eaac692e 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -592,8 +592,8 @@ static inline struct inode *d_real_inode(const struct dentry *dentry)
 }
 
 struct name_snapshot {
-	const char *name;
-	char inline_name[DNAME_INLINE_LEN];
+	const unsigned char *name;
+	unsigned char inline_name[DNAME_INLINE_LEN];
 };
 void take_dentry_name_snapshot(struct name_snapshot *, struct dentry *);
 void release_dentry_name_snapshot(struct name_snapshot *);
-- 
cgit v1.2.3


From c7acec713d14c6ce8a20154f9dfda258d6bcad3b Mon Sep 17 00:00:00 2001
From: Ian Abbott <abbotti@mev.co.uk>
Date: Wed, 12 Jul 2017 14:33:04 -0700
Subject: kernel.h: handle pointers to arrays better in container_of()

If the first parameter of container_of() is a pointer to a
non-const-qualified array type (and the third parameter names a
non-const-qualified array member), the local variable __mptr will be
defined with a const-qualified array type.  In ISO C, these types are
incompatible.  They work as expected in GNU C, but some versions will
issue warnings.  For example, GCC 4.9 produces the warning
"initialization from incompatible pointer type".

Here is an example of where the problem occurs:

-------------------------------------------------------
   #include <linux/kernel.h>
   #include <linux/module.h>

  MODULE_LICENSE("GPL");

  struct st {
  	int a;
  	char b[16];
  };

  static int __init example_init(void) {
  	struct st t = { .a = 101, .b = "hello" };
  	char (*p)[16] = &t.b;
  	struct st *x = container_of(p, struct st, b);
  	printk(KERN_DEBUG "%p %p\n", (void *)&t, (void *)x);
  	return 0;
  }

  static void __exit example_exit(void) {
  }

  module_init(example_init);
  module_exit(example_exit);
-------------------------------------------------------

Building the module with gcc-4.9 results in these warnings (where '{m}'
is the module source and '{k}' is the kernel source):

-------------------------------------------------------
  In file included from {m}/example.c:1:0:
  {m}/example.c: In function `example_init':
  {k}/include/linux/kernel.h:854:48: warning: initialization from incompatible pointer type
    const typeof( ((type *)0)->member ) *__mptr = (ptr); \
                                                  ^
  {m}/example.c:14:17: note: in expansion of macro `container_of'
    struct st *x = container_of(p, struct st, b);
                   ^
  {k}/include/linux/kernel.h:854:48: warning: (near initialization for `x')
    const typeof( ((type *)0)->member ) *__mptr = (ptr); \
                                                  ^
  {m}/example.c:14:17: note: in expansion of macro `container_of'
    struct st *x = container_of(p, struct st, b);
                   ^
-------------------------------------------------------

Replace the type checking performed by the macro to avoid these
warnings.  Make sure `*(ptr)` either has type compatible with the
member, or has type compatible with `void`, ignoring qualifiers.  Raise
compiler errors if this is not true.  This is stronger than the previous
behaviour, which only resulted in compiler warnings for a type mismatch.

[arnd@arndb.de: fix new warnings for container_of()]
  Link: http://lkml.kernel.org/r/20170620200940.90557-1-arnd@arndb.de
Link: http://lkml.kernel.org/r/20170525120316.24473-7-abbotti@mev.co.uk
Signed-off-by: Ian Abbott <abbotti@mev.co.uk>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Michal Nazarewicz <mina86@mina86.com>
Acked-by: Kees Cook <keescook@chromium.org>
Cc: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Johannes Berg <johannes.berg@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Alexander Potapenko <glider@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kernel.h | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 1c91f26e2996..bd6d96cf80b1 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -11,6 +11,7 @@
 #include <linux/log2.h>
 #include <linux/typecheck.h>
 #include <linux/printk.h>
+#include <linux/build_bug.h>
 #include <asm/byteorder.h>
 #include <uapi/linux/kernel.h>
 
@@ -854,9 +855,12 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { }
  * @member:	the name of the member within the struct.
  *
  */
-#define container_of(ptr, type, member) ({			\
-	const typeof( ((type *)0)->member ) *__mptr = (ptr);	\
-	(type *)( (char *)__mptr - offsetof(type,member) );})
+#define container_of(ptr, type, member) ({				\
+	void *__mptr = (void *)(ptr);					\
+	BUILD_BUG_ON_MSG(!__same_type(*(ptr), ((type *)0)->member) &&	\
+			 !__same_type(*(ptr), void),			\
+			 "pointer type mismatch in container_of()");	\
+	((type *)(__mptr - offsetof(type, member))); })
 
 /* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
-- 
cgit v1.2.3


From 203e9e41219b4e7357104e525e91ac609fba2c6c Mon Sep 17 00:00:00 2001
From: Xunlei Pang <xlpang@redhat.com>
Date: Wed, 12 Jul 2017 14:33:14 -0700
Subject: kexec: move vmcoreinfo out of the kernel's .bss section

As Eric said,
 "what we need to do is move the variable vmcoreinfo_note out of the
  kernel's .bss section. And modify the code to regenerate and keep this
  information in something like the control page.

  Definitely something like this needs a page all to itself, and ideally
  far away from any other kernel data structures. I clearly was not
  watching closely the data someone decided to keep this silly thing in
  the kernel's .bss section."

This patch allocates extra pages for these vmcoreinfo_XXX variables, one
advantage is that it enhances some safety of vmcoreinfo, because
vmcoreinfo now is kept far away from other kernel data structures.

Link: http://lkml.kernel.org/r/1493281021-20737-1-git-send-email-xlpang@redhat.com
Signed-off-by: Xunlei Pang <xlpang@redhat.com>
Tested-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Suggested-by: Eric Biederman <ebiederm@xmission.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Dave Young <dyoung@redhat.com>
Cc: Hari Bathini <hbathini@linux.vnet.ibm.com>
Cc: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/ia64/kernel/machine_kexec.c |  5 -----
 arch/s390/kernel/machine_kexec.c |  1 +
 arch/s390/kernel/setup.c         |  6 ------
 arch/x86/kernel/crash.c          |  2 +-
 arch/x86/xen/mmu_pv.c            |  4 ++--
 include/linux/crash_core.h       |  4 ++--
 kernel/crash_core.c              | 26 ++++++++++++++++++++++----
 kernel/ksysfs.c                  |  2 +-
 8 files changed, 29 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/arch/ia64/kernel/machine_kexec.c b/arch/ia64/kernel/machine_kexec.c
index 599507bcec91..c14815dca747 100644
--- a/arch/ia64/kernel/machine_kexec.c
+++ b/arch/ia64/kernel/machine_kexec.c
@@ -163,8 +163,3 @@ void arch_crash_save_vmcoreinfo(void)
 #endif
 }
 
-phys_addr_t paddr_vmcoreinfo_note(void)
-{
-	return ia64_tpa((unsigned long)(char *)&vmcoreinfo_note);
-}
-
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index 49a6bd45957b..3d0b14afa232 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -246,6 +246,7 @@ void arch_crash_save_vmcoreinfo(void)
 	VMCOREINFO_SYMBOL(lowcore_ptr);
 	VMCOREINFO_SYMBOL(high_memory);
 	VMCOREINFO_LENGTH(lowcore_ptr, NR_CPUS);
+	mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note());
 }
 
 void machine_shutdown(void)
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 3ae756c0db3d..3d1d808ea8a9 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -496,11 +496,6 @@ static void __init setup_memory_end(void)
 	pr_notice("The maximum memory size is %luMB\n", memory_end >> 20);
 }
 
-static void __init setup_vmcoreinfo(void)
-{
-	mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note());
-}
-
 #ifdef CONFIG_CRASH_DUMP
 
 /*
@@ -939,7 +934,6 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
 	setup_resources();
-	setup_vmcoreinfo();
 	setup_lowcore();
 	smp_fill_possible_mask();
 	cpu_detect_mhz_feature();
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 22217ece26c8..44404e2307bb 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -457,7 +457,7 @@ static int prepare_elf64_headers(struct crash_elf_data *ced,
 	bufp += sizeof(Elf64_Phdr);
 	phdr->p_type = PT_NOTE;
 	phdr->p_offset = phdr->p_paddr = paddr_vmcoreinfo_note();
-	phdr->p_filesz = phdr->p_memsz = sizeof(vmcoreinfo_note);
+	phdr->p_filesz = phdr->p_memsz = VMCOREINFO_NOTE_SIZE;
 	(ehdr->e_phnum)++;
 
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 1d7a7213a310..cab28cf2cffb 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -2693,8 +2693,8 @@ EXPORT_SYMBOL_GPL(xen_destroy_contiguous_region);
 phys_addr_t paddr_vmcoreinfo_note(void)
 {
 	if (xen_pv_domain())
-		return virt_to_machine(&vmcoreinfo_note).maddr;
+		return virt_to_machine(vmcoreinfo_note).maddr;
 	else
-		return __pa_symbol(&vmcoreinfo_note);
+		return __pa(vmcoreinfo_note);
 }
 #endif /* CONFIG_KEXEC_CORE */
diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h
index 4090a42578a8..87506a02e914 100644
--- a/include/linux/crash_core.h
+++ b/include/linux/crash_core.h
@@ -19,7 +19,7 @@
 				     CRASH_CORE_NOTE_NAME_BYTES +	\
 				     CRASH_CORE_NOTE_DESC_BYTES)
 
-#define VMCOREINFO_BYTES	   (4096)
+#define VMCOREINFO_BYTES	   PAGE_SIZE
 #define VMCOREINFO_NOTE_NAME	   "VMCOREINFO"
 #define VMCOREINFO_NOTE_NAME_BYTES ALIGN(sizeof(VMCOREINFO_NOTE_NAME), 4)
 #define VMCOREINFO_NOTE_SIZE	   ((CRASH_CORE_NOTE_HEAD_BYTES * 2) +	\
@@ -56,7 +56,7 @@ phys_addr_t paddr_vmcoreinfo_note(void);
 #define VMCOREINFO_CONFIG(name) \
 	vmcoreinfo_append_str("CONFIG_%s=y\n", #name)
 
-extern u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
+extern u32 *vmcoreinfo_note;
 extern size_t vmcoreinfo_size;
 extern size_t vmcoreinfo_max_size;
 
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index fcbd568f1e95..2837d6164db8 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -14,10 +14,10 @@
 #include <asm/sections.h>
 
 /* vmcoreinfo stuff */
-static unsigned char vmcoreinfo_data[VMCOREINFO_BYTES];
-u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
+static unsigned char *vmcoreinfo_data;
 size_t vmcoreinfo_size;
-size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data);
+size_t vmcoreinfo_max_size = VMCOREINFO_BYTES;
+u32 *vmcoreinfo_note;
 
 /*
  * parsing the "crashkernel" commandline
@@ -326,6 +326,9 @@ static void update_vmcoreinfo_note(void)
 
 void crash_save_vmcoreinfo(void)
 {
+	if (!vmcoreinfo_note)
+		return;
+
 	vmcoreinfo_append_str("CRASHTIME=%ld\n", get_seconds());
 	update_vmcoreinfo_note();
 }
@@ -356,11 +359,26 @@ void __weak arch_crash_save_vmcoreinfo(void)
 
 phys_addr_t __weak paddr_vmcoreinfo_note(void)
 {
-	return __pa_symbol((unsigned long)(char *)&vmcoreinfo_note);
+	return __pa(vmcoreinfo_note);
 }
 
 static int __init crash_save_vmcoreinfo_init(void)
 {
+	vmcoreinfo_data = (unsigned char *)get_zeroed_page(GFP_KERNEL);
+	if (!vmcoreinfo_data) {
+		pr_warn("Memory allocation for vmcoreinfo_data failed\n");
+		return -ENOMEM;
+	}
+
+	vmcoreinfo_note = alloc_pages_exact(VMCOREINFO_NOTE_SIZE,
+						GFP_KERNEL | __GFP_ZERO);
+	if (!vmcoreinfo_note) {
+		free_page((unsigned long)vmcoreinfo_data);
+		vmcoreinfo_data = NULL;
+		pr_warn("Memory allocation for vmcoreinfo_note failed\n");
+		return -ENOMEM;
+	}
+
 	VMCOREINFO_OSRELEASE(init_uts_ns.name.release);
 	VMCOREINFO_PAGESIZE(PAGE_SIZE);
 
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index df1a9aa602a0..46ba853656f6 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -134,7 +134,7 @@ static ssize_t vmcoreinfo_show(struct kobject *kobj,
 {
 	phys_addr_t vmcore_base = paddr_vmcoreinfo_note();
 	return sprintf(buf, "%pa %x\n", &vmcore_base,
-		       (unsigned int)sizeof(vmcoreinfo_note));
+			(unsigned int)VMCOREINFO_NOTE_SIZE);
 }
 KERNEL_ATTR_RO(vmcoreinfo);
 
-- 
cgit v1.2.3


From 5203f4995d9a87952a83c2ce7866adbbe8f97bb5 Mon Sep 17 00:00:00 2001
From: Xunlei Pang <xlpang@redhat.com>
Date: Wed, 12 Jul 2017 14:33:17 -0700
Subject: powerpc/fadump: use the correct VMCOREINFO_NOTE_SIZE for phdr

vmcoreinfo_max_size stands for the vmcoreinfo_data, the correct one we
should use is vmcoreinfo_note whose total size is VMCOREINFO_NOTE_SIZE.

Like explained in commit 77019967f06b ("kdump: fix exported size of
vmcoreinfo note"), it should not affect the actual function, but we
better fix it, also this change should be safe and backward compatible.

After this, we can get rid of variable vmcoreinfo_max_size, let's use
the corresponding macros directly, fewer variables means more safety for
vmcoreinfo operation.

[xlpang@redhat.com: fix build warning]
  Link: http://lkml.kernel.org/r/1494830606-27736-1-git-send-email-xlpang@redhat.com
Link: http://lkml.kernel.org/r/1493281021-20737-2-git-send-email-xlpang@redhat.com
Signed-off-by: Xunlei Pang <xlpang@redhat.com>
Reviewed-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Reviewed-by: Dave Young <dyoung@redhat.com>
Cc: Hari Bathini <hbathini@linux.vnet.ibm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/powerpc/kernel/fadump.c | 3 +--
 include/linux/crash_core.h   | 1 -
 kernel/crash_core.c          | 3 +--
 3 files changed, 2 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index 3079518f2245..dc0c49cfd90a 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -999,8 +999,7 @@ static int fadump_create_elfcore_headers(char *bufp)
 
 	phdr->p_paddr	= fadump_relocate(paddr_vmcoreinfo_note());
 	phdr->p_offset	= phdr->p_paddr;
-	phdr->p_memsz	= vmcoreinfo_max_size;
-	phdr->p_filesz	= vmcoreinfo_max_size;
+	phdr->p_memsz	= phdr->p_filesz = VMCOREINFO_NOTE_SIZE;
 
 	/* Increment number of program headers. */
 	(elf->e_phnum)++;
diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h
index 87506a02e914..e5df1b3cf072 100644
--- a/include/linux/crash_core.h
+++ b/include/linux/crash_core.h
@@ -58,7 +58,6 @@ phys_addr_t paddr_vmcoreinfo_note(void);
 
 extern u32 *vmcoreinfo_note;
 extern size_t vmcoreinfo_size;
-extern size_t vmcoreinfo_max_size;
 
 Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type,
 			  void *data, size_t data_len);
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index 2837d6164db8..315adbf9cb68 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -16,7 +16,6 @@
 /* vmcoreinfo stuff */
 static unsigned char *vmcoreinfo_data;
 size_t vmcoreinfo_size;
-size_t vmcoreinfo_max_size = VMCOREINFO_BYTES;
 u32 *vmcoreinfo_note;
 
 /*
@@ -343,7 +342,7 @@ void vmcoreinfo_append_str(const char *fmt, ...)
 	r = vscnprintf(buf, sizeof(buf), fmt, args);
 	va_end(args);
 
-	r = min(r, vmcoreinfo_max_size - vmcoreinfo_size);
+	r = min(r, (size_t)VMCOREINFO_BYTES - vmcoreinfo_size);
 
 	memcpy(&vmcoreinfo_data[vmcoreinfo_size], buf, r);
 
-- 
cgit v1.2.3


From 1229384f5b856d83698c38f9dedfd836e26711cb Mon Sep 17 00:00:00 2001
From: Xunlei Pang <xlpang@redhat.com>
Date: Wed, 12 Jul 2017 14:33:21 -0700
Subject: kdump: protect vmcoreinfo data under the crash memory

Currently vmcoreinfo data is updated at boot time subsys_initcall(), it
has the risk of being modified by some wrong code during system is
running.

As a result, vmcore dumped may contain the wrong vmcoreinfo.  Later on,
when using "crash", "makedumpfile", etc utility to parse this vmcore, we
probably will get "Segmentation fault" or other unexpected errors.

E.g.  1) wrong code overwrites vmcoreinfo_data; 2) further crashes the
system; 3) trigger kdump, then we obviously will fail to recognize the
crash context correctly due to the corrupted vmcoreinfo.

Now except for vmcoreinfo, all the crash data is well
protected(including the cpu note which is fully updated in the crash
path, thus its correctness is guaranteed).  Given that vmcoreinfo data
is a large chunk prepared for kdump, we better protect it as well.

To solve this, we relocate and copy vmcoreinfo_data to the crash memory
when kdump is loading via kexec syscalls.  Because the whole crash
memory will be protected by existing arch_kexec_protect_crashkres()
mechanism, we naturally protect vmcoreinfo_data from write(even read)
access under kernel direct mapping after kdump is loaded.

Since kdump is usually loaded at the very early stage after boot, we can
trust the correctness of the vmcoreinfo data copied.

On the other hand, we still need to operate the vmcoreinfo safe copy
when crash happens to generate vmcoreinfo_note again, we rely on vmap()
to map out a new kernel virtual address and update to use this new one
instead in the following crash_save_vmcoreinfo().

BTW, we do not touch vmcoreinfo_note, because it will be fully updated
using the protected vmcoreinfo_data after crash which is surely correct
just like the cpu crash note.

Link: http://lkml.kernel.org/r/1493281021-20737-3-git-send-email-xlpang@redhat.com
Signed-off-by: Xunlei Pang <xlpang@redhat.com>
Tested-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Dave Young <dyoung@redhat.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Hari Bathini <hbathini@linux.vnet.ibm.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/crash_core.h |  2 +-
 include/linux/kexec.h      |  2 ++
 kernel/crash_core.c        | 17 ++++++++++++++++-
 kernel/kexec.c             |  8 ++++++++
 kernel/kexec_core.c        | 39 +++++++++++++++++++++++++++++++++++++++
 kernel/kexec_file.c        |  8 ++++++++
 6 files changed, 74 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h
index e5df1b3cf072..2df2118fbe13 100644
--- a/include/linux/crash_core.h
+++ b/include/linux/crash_core.h
@@ -28,6 +28,7 @@
 
 typedef u32 note_buf_t[CRASH_CORE_NOTE_BYTES/4];
 
+void crash_update_vmcoreinfo_safecopy(void *ptr);
 void crash_save_vmcoreinfo(void);
 void arch_crash_save_vmcoreinfo(void);
 __printf(1, 2)
@@ -57,7 +58,6 @@ phys_addr_t paddr_vmcoreinfo_note(void);
 	vmcoreinfo_append_str("CONFIG_%s=y\n", #name)
 
 extern u32 *vmcoreinfo_note;
-extern size_t vmcoreinfo_size;
 
 Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type,
 			  void *data, size_t data_len);
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index 65888418fb69..dd056fab9e35 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -172,6 +172,7 @@ struct kimage {
 	unsigned long start;
 	struct page *control_code_page;
 	struct page *swap_page;
+	void *vmcoreinfo_data_copy; /* locates in the crash memory */
 
 	unsigned long nr_segments;
 	struct kexec_segment segment[KEXEC_SEGMENT_MAX];
@@ -241,6 +242,7 @@ extern void crash_kexec(struct pt_regs *);
 int kexec_should_crash(struct task_struct *);
 int kexec_crash_loaded(void);
 void crash_save_cpu(struct pt_regs *regs, int cpu);
+extern int kimage_crash_copy_vmcoreinfo(struct kimage *image);
 
 extern struct kimage *kexec_image;
 extern struct kimage *kexec_crash_image;
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index 315adbf9cb68..6db80fc0810b 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -15,9 +15,12 @@
 
 /* vmcoreinfo stuff */
 static unsigned char *vmcoreinfo_data;
-size_t vmcoreinfo_size;
+static size_t vmcoreinfo_size;
 u32 *vmcoreinfo_note;
 
+/* trusted vmcoreinfo, e.g. we can make a copy in the crash memory */
+static unsigned char *vmcoreinfo_data_safecopy;
+
 /*
  * parsing the "crashkernel" commandline
  *
@@ -323,11 +326,23 @@ static void update_vmcoreinfo_note(void)
 	final_note(buf);
 }
 
+void crash_update_vmcoreinfo_safecopy(void *ptr)
+{
+	if (ptr)
+		memcpy(ptr, vmcoreinfo_data, vmcoreinfo_size);
+
+	vmcoreinfo_data_safecopy = ptr;
+}
+
 void crash_save_vmcoreinfo(void)
 {
 	if (!vmcoreinfo_note)
 		return;
 
+	/* Use the safe copy to generate vmcoreinfo note if have */
+	if (vmcoreinfo_data_safecopy)
+		vmcoreinfo_data = vmcoreinfo_data_safecopy;
+
 	vmcoreinfo_append_str("CRASHTIME=%ld\n", get_seconds());
 	update_vmcoreinfo_note();
 }
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 980936a90ee6..e62ec4dc6620 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -144,6 +144,14 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments,
 	if (ret)
 		goto out;
 
+	/*
+	 * Some architecture(like S390) may touch the crash memory before
+	 * machine_kexec_prepare(), we must copy vmcoreinfo data after it.
+	 */
+	ret = kimage_crash_copy_vmcoreinfo(image);
+	if (ret)
+		goto out;
+
 	for (i = 0; i < nr_segments; i++) {
 		ret = kimage_load_segment(image, &image->segment[i]);
 		if (ret)
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index 154ffb489b93..1ae7c41c33c1 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -482,6 +482,40 @@ struct page *kimage_alloc_control_pages(struct kimage *image,
 	return pages;
 }
 
+int kimage_crash_copy_vmcoreinfo(struct kimage *image)
+{
+	struct page *vmcoreinfo_page;
+	void *safecopy;
+
+	if (image->type != KEXEC_TYPE_CRASH)
+		return 0;
+
+	/*
+	 * For kdump, allocate one vmcoreinfo safe copy from the
+	 * crash memory. as we have arch_kexec_protect_crashkres()
+	 * after kexec syscall, we naturally protect it from write
+	 * (even read) access under kernel direct mapping. But on
+	 * the other hand, we still need to operate it when crash
+	 * happens to generate vmcoreinfo note, hereby we rely on
+	 * vmap for this purpose.
+	 */
+	vmcoreinfo_page = kimage_alloc_control_pages(image, 0);
+	if (!vmcoreinfo_page) {
+		pr_warn("Could not allocate vmcoreinfo buffer\n");
+		return -ENOMEM;
+	}
+	safecopy = vmap(&vmcoreinfo_page, 1, VM_MAP, PAGE_KERNEL);
+	if (!safecopy) {
+		pr_warn("Could not vmap vmcoreinfo buffer\n");
+		return -ENOMEM;
+	}
+
+	image->vmcoreinfo_data_copy = safecopy;
+	crash_update_vmcoreinfo_safecopy(safecopy);
+
+	return 0;
+}
+
 static int kimage_add_entry(struct kimage *image, kimage_entry_t entry)
 {
 	if (*image->entry != 0)
@@ -569,6 +603,11 @@ void kimage_free(struct kimage *image)
 	if (!image)
 		return;
 
+	if (image->vmcoreinfo_data_copy) {
+		crash_update_vmcoreinfo_safecopy(NULL);
+		vunmap(image->vmcoreinfo_data_copy);
+	}
+
 	kimage_free_extra_pages(image);
 	for_each_kimage_entry(image, ptr, entry) {
 		if (entry & IND_INDIRECTION) {
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index 766e7e4d3ad9..c8f7f77e9fa9 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -298,6 +298,14 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd,
 	if (ret)
 		goto out;
 
+	/*
+	 * Some architecture(like S390) may touch the crash memory before
+	 * machine_kexec_prepare(), we must copy vmcoreinfo data after it.
+	 */
+	ret = kimage_crash_copy_vmcoreinfo(image);
+	if (ret)
+		goto out;
+
 	ret = kexec_calculate_store_digests(image);
 	if (ret)
 		goto out;
-- 
cgit v1.2.3


From 61d9b56a89208d8cccd0b4cfec7e6959717e16e3 Mon Sep 17 00:00:00 2001
From: "Luis R. Rodriguez" <mcgrof@kernel.org>
Date: Wed, 12 Jul 2017 14:33:40 -0700
Subject: sysctl: add unsigned int range support

To keep parity with regular int interfaces provide the an unsigned int
proc_douintvec_minmax() which allows you to specify a range of allowed
valid numbers.

Adding proc_douintvec_minmax_sysadmin() is easy but we can wait for an
actual user for that.

Link: http://lkml.kernel.org/r/20170519033554.18592-6-mcgrof@kernel.org
Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org>
Acked-by: Kees Cook <keescook@chromium.org>
Cc: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Cc: Heinrich Schuchardt <xypron.glpk@gmx.de>
Cc: Kees Cook <keescook@chromium.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/proc/proc_sysctl.c  |  4 ++-
 include/linux/sysctl.h |  3 +++
 kernel/sysctl.c        | 66 ++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 72 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index ee6feba8b6c0..8f9d564d0969 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -1065,7 +1065,8 @@ static int sysctl_check_table_array(const char *path, struct ctl_table *table)
 {
 	int err = 0;
 
-	if (table->proc_handler == proc_douintvec) {
+	if ((table->proc_handler == proc_douintvec) ||
+	    (table->proc_handler == proc_douintvec_minmax)) {
 		if (table->maxlen != sizeof(unsigned int))
 			err |= sysctl_err(path, table, "array now allowed");
 	}
@@ -1083,6 +1084,7 @@ static int sysctl_check_table(const char *path, struct ctl_table *table)
 		if ((table->proc_handler == proc_dostring) ||
 		    (table->proc_handler == proc_dointvec) ||
 		    (table->proc_handler == proc_douintvec) ||
+		    (table->proc_handler == proc_douintvec_minmax) ||
 		    (table->proc_handler == proc_dointvec_minmax) ||
 		    (table->proc_handler == proc_dointvec_jiffies) ||
 		    (table->proc_handler == proc_dointvec_userhz_jiffies) ||
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 80d07816def0..225001d437ae 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -47,6 +47,9 @@ extern int proc_douintvec(struct ctl_table *, int,
 			 void __user *, size_t *, loff_t *);
 extern int proc_dointvec_minmax(struct ctl_table *, int,
 				void __user *, size_t *, loff_t *);
+extern int proc_douintvec_minmax(struct ctl_table *table, int write,
+				 void __user *buffer, size_t *lenp,
+				 loff_t *ppos);
 extern int proc_dointvec_jiffies(struct ctl_table *, int,
 				 void __user *, size_t *, loff_t *);
 extern int proc_dointvec_userhz_jiffies(struct ctl_table *, int,
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index d12078fc215f..df9f2a367882 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2567,6 +2567,65 @@ int proc_dointvec_minmax(struct ctl_table *table, int write,
 				do_proc_dointvec_minmax_conv, &param);
 }
 
+struct do_proc_douintvec_minmax_conv_param {
+	unsigned int *min;
+	unsigned int *max;
+};
+
+static int do_proc_douintvec_minmax_conv(unsigned long *lvalp,
+					 unsigned int *valp,
+					 int write, void *data)
+{
+	struct do_proc_douintvec_minmax_conv_param *param = data;
+
+	if (write) {
+		unsigned int val = *lvalp;
+
+		if ((param->min && *param->min > val) ||
+		    (param->max && *param->max < val))
+			return -ERANGE;
+
+		if (*lvalp > UINT_MAX)
+			return -EINVAL;
+		*valp = val;
+	} else {
+		unsigned int val = *valp;
+		*lvalp = (unsigned long) val;
+	}
+
+	return 0;
+}
+
+/**
+ * proc_douintvec_minmax - read a vector of unsigned ints with min/max values
+ * @table: the sysctl table
+ * @write: %TRUE if this is a write to the sysctl file
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: file position
+ *
+ * Reads/writes up to table->maxlen/sizeof(unsigned int) unsigned integer
+ * values from/to the user buffer, treated as an ASCII string. Negative
+ * strings are not allowed.
+ *
+ * This routine will ensure the values are within the range specified by
+ * table->extra1 (min) and table->extra2 (max). There is a final sanity
+ * check for UINT_MAX to avoid having to support wrap around uses from
+ * userspace.
+ *
+ * Returns 0 on success.
+ */
+int proc_douintvec_minmax(struct ctl_table *table, int write,
+			  void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct do_proc_douintvec_minmax_conv_param param = {
+		.min = (unsigned int *) table->extra1,
+		.max = (unsigned int *) table->extra2,
+	};
+	return do_proc_douintvec(table, write, buffer, lenp, ppos,
+				 do_proc_douintvec_minmax_conv, &param);
+}
+
 static void validate_coredump_safety(void)
 {
 #ifdef CONFIG_COREDUMP
@@ -3066,6 +3125,12 @@ int proc_dointvec_minmax(struct ctl_table *table, int write,
 	return -ENOSYS;
 }
 
+int proc_douintvec_minmax(struct ctl_table *table, int write,
+			  void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	return -ENOSYS;
+}
+
 int proc_dointvec_jiffies(struct ctl_table *table, int write,
 		    void __user *buffer, size_t *lenp, loff_t *ppos)
 {
@@ -3108,6 +3173,7 @@ EXPORT_SYMBOL(proc_dointvec);
 EXPORT_SYMBOL(proc_douintvec);
 EXPORT_SYMBOL(proc_dointvec_jiffies);
 EXPORT_SYMBOL(proc_dointvec_minmax);
+EXPORT_SYMBOL_GPL(proc_douintvec_minmax);
 EXPORT_SYMBOL(proc_dointvec_userhz_jiffies);
 EXPORT_SYMBOL(proc_dointvec_ms_jiffies);
 EXPORT_SYMBOL(proc_dostring);
-- 
cgit v1.2.3


From 0791e3644e5ef21646fe565b9061788d05ec71d4 Mon Sep 17 00:00:00 2001
From: Cyrill Gorcunov <gorcunov@gmail.com>
Date: Wed, 12 Jul 2017 14:34:28 -0700
Subject: kcmp: add KCMP_EPOLL_TFD mode to compare epoll target files

With current epoll architecture target files are addressed with
file_struct and file descriptor number, where the last is not unique.
Moreover files can be transferred from another process via unix socket,
added into queue and closed then so we won't find this descriptor in the
task fdinfo list.

Thus to checkpoint and restore such processes CRIU needs to find out
where exactly the target file is present to add it into epoll queue.
For this sake one can use kcmp call where some particular target file
from the queue is compared with arbitrary file passed as an argument.

Because epoll target files can have same file descriptor number but
different file_struct a caller should explicitly specify the offset
within.

To test if some particular file is matching entry inside epoll one have
to

 - fill kcmp_epoll_slot structure with epoll file descriptor,
   target file number and target file offset (in case if only
   one target is present then it should be 0)

 - call kcmp as kcmp(pid1, pid2, KCMP_EPOLL_TFD, fd, &kcmp_epoll_slot)
    - the kernel fetch file pointer matching file descriptor @fd of pid1
    - lookups for file struct in epoll queue of pid2 and returns traditional
      0,1,2 result for sorting purpose

Link: http://lkml.kernel.org/r/20170424154423.511592110@gmail.com
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Acked-by: Andrey Vagin <avagin@openvz.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Pavel Emelyanov <xemul@virtuozzo.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Jason Baron <jbaron@akamai.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/eventpoll.c            | 42 ++++++++++++++++++++++++++++++++++
 include/linux/eventpoll.h |  3 +++
 include/uapi/linux/kcmp.h | 10 +++++++++
 kernel/kcmp.c             | 57 +++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 112 insertions(+)

(limited to 'include')

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 322904c3ebdf..e7e9901c3790 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1077,6 +1077,48 @@ static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd)
 	return epir;
 }
 
+static struct epitem *ep_find_tfd(struct eventpoll *ep, int tfd, unsigned long toff)
+{
+	struct rb_node *rbp;
+	struct epitem *epi;
+
+	for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) {
+		epi = rb_entry(rbp, struct epitem, rbn);
+		if (epi->ffd.fd == tfd) {
+			if (toff == 0)
+				return epi;
+			else
+				toff--;
+		}
+		cond_resched();
+	}
+
+	return NULL;
+}
+
+struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd,
+				     unsigned long toff)
+{
+	struct file *file_raw;
+	struct eventpoll *ep;
+	struct epitem *epi;
+
+	if (!is_file_epoll(file))
+		return ERR_PTR(-EINVAL);
+
+	ep = file->private_data;
+
+	mutex_lock(&ep->mtx);
+	epi = ep_find_tfd(ep, tfd, toff);
+	if (epi)
+		file_raw = epi->ffd.file;
+	else
+		file_raw = ERR_PTR(-ENOENT);
+	mutex_unlock(&ep->mtx);
+
+	return file_raw;
+}
+
 /*
  * This is the callback that is passed to the wait queue wakeup
  * mechanism. It is called by the stored file descriptors when they
diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h
index 6daf6d4971f6..d8625d214ea7 100644
--- a/include/linux/eventpoll.h
+++ b/include/linux/eventpoll.h
@@ -14,6 +14,7 @@
 #define _LINUX_EVENTPOLL_H
 
 #include <uapi/linux/eventpoll.h>
+#include <uapi/linux/kcmp.h>
 
 
 /* Forward declarations to avoid compiler errors */
@@ -22,6 +23,8 @@ struct file;
 
 #ifdef CONFIG_EPOLL
 
+struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long toff);
+
 /* Used to initialize the epoll bits inside the "struct file" */
 static inline void eventpoll_init_file(struct file *file)
 {
diff --git a/include/uapi/linux/kcmp.h b/include/uapi/linux/kcmp.h
index 84df14b37360..481e103da78e 100644
--- a/include/uapi/linux/kcmp.h
+++ b/include/uapi/linux/kcmp.h
@@ -1,6 +1,8 @@
 #ifndef _UAPI_LINUX_KCMP_H
 #define _UAPI_LINUX_KCMP_H
 
+#include <linux/types.h>
+
 /* Comparison type */
 enum kcmp_type {
 	KCMP_FILE,
@@ -10,8 +12,16 @@ enum kcmp_type {
 	KCMP_SIGHAND,
 	KCMP_IO,
 	KCMP_SYSVSEM,
+	KCMP_EPOLL_TFD,
 
 	KCMP_TYPES,
 };
 
+/* Slot for KCMP_EPOLL_TFD */
+struct kcmp_epoll_slot {
+	__u32 efd;		/* epoll file descriptor */
+	__u32 tfd;		/* target file number */
+	__u32 toff;		/* target offset within same numbered sequence */
+};
+
 #endif /* _UAPI_LINUX_KCMP_H */
diff --git a/kernel/kcmp.c b/kernel/kcmp.c
index 3a47fa998fe0..ea34ed8bb952 100644
--- a/kernel/kcmp.c
+++ b/kernel/kcmp.c
@@ -11,6 +11,10 @@
 #include <linux/bug.h>
 #include <linux/err.h>
 #include <linux/kcmp.h>
+#include <linux/capability.h>
+#include <linux/list.h>
+#include <linux/eventpoll.h>
+#include <linux/file.h>
 
 #include <asm/unistd.h>
 
@@ -94,6 +98,56 @@ static int kcmp_lock(struct mutex *m1, struct mutex *m2)
 	return err;
 }
 
+#ifdef CONFIG_EPOLL
+static int kcmp_epoll_target(struct task_struct *task1,
+			     struct task_struct *task2,
+			     unsigned long idx1,
+			     struct kcmp_epoll_slot __user *uslot)
+{
+	struct file *filp, *filp_epoll, *filp_tgt;
+	struct kcmp_epoll_slot slot;
+	struct files_struct *files;
+
+	if (copy_from_user(&slot, uslot, sizeof(slot)))
+		return -EFAULT;
+
+	filp = get_file_raw_ptr(task1, idx1);
+	if (!filp)
+		return -EBADF;
+
+	files = get_files_struct(task2);
+	if (!files)
+		return -EBADF;
+
+	spin_lock(&files->file_lock);
+	filp_epoll = fcheck_files(files, slot.efd);
+	if (filp_epoll)
+		get_file(filp_epoll);
+	else
+		filp_tgt = ERR_PTR(-EBADF);
+	spin_unlock(&files->file_lock);
+	put_files_struct(files);
+
+	if (filp_epoll) {
+		filp_tgt = get_epoll_tfile_raw_ptr(filp_epoll, slot.tfd, slot.toff);
+		fput(filp_epoll);
+	} else
+
+	if (IS_ERR(filp_tgt))
+		return PTR_ERR(filp_tgt);
+
+	return kcmp_ptr(filp, filp_tgt, KCMP_FILE);
+}
+#else
+static int kcmp_epoll_target(struct task_struct *task1,
+			     struct task_struct *task2,
+			     unsigned long idx1,
+			     struct kcmp_epoll_slot __user *uslot)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
 SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type,
 		unsigned long, idx1, unsigned long, idx2)
 {
@@ -165,6 +219,9 @@ SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type,
 		ret = -EOPNOTSUPP;
 #endif
 		break;
+	case KCMP_EPOLL_TFD:
+		ret = kcmp_epoll_target(task1, task2, idx1, (void *)idx2);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
-- 
cgit v1.2.3


From 92ef6da3d06ff551a86de41ae37df9cc4b58d7a0 Mon Sep 17 00:00:00 2001
From: Cyrill Gorcunov <gorcunov@gmail.com>
Date: Wed, 12 Jul 2017 14:34:31 -0700
Subject: kcmp: fs/epoll: wrap kcmp code with CONFIG_CHECKPOINT_RESTORE

kcmp syscall is build iif CONFIG_CHECKPOINT_RESTORE is selected, so wrap
appropriate helpers in epoll code with the config to build it
conditionally.

Link: http://lkml.kernel.org/r/20170513083456.GG1881@uranus.lan
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Reported-by: Andrew Morton <akpm@linuxfoundation.org>
Cc: Andrey Vagin <avagin@openvz.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Pavel Emelyanov <xemul@virtuozzo.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Jason Baron <jbaron@akamai.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/eventpoll.c            | 2 ++
 include/linux/eventpoll.h | 2 ++
 2 files changed, 4 insertions(+)

(limited to 'include')

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index e7e9901c3790..e767e4389cb1 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1077,6 +1077,7 @@ static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd)
 	return epir;
 }
 
+#ifdef CONFIG_CHECKPOINT_RESTORE
 static struct epitem *ep_find_tfd(struct eventpoll *ep, int tfd, unsigned long toff)
 {
 	struct rb_node *rbp;
@@ -1118,6 +1119,7 @@ struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd,
 
 	return file_raw;
 }
+#endif /* CONFIG_CHECKPOINT_RESTORE */
 
 /*
  * This is the callback that is passed to the wait queue wakeup
diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h
index d8625d214ea7..2f14ac73d01d 100644
--- a/include/linux/eventpoll.h
+++ b/include/linux/eventpoll.h
@@ -23,7 +23,9 @@ struct file;
 
 #ifdef CONFIG_EPOLL
 
+#ifdef CONFIG_CHECKPOINT_RESTORE
 struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long toff);
+#endif
 
 /* Used to initialize the epoll bits inside the "struct file" */
 static inline void eventpoll_init_file(struct file *file)
-- 
cgit v1.2.3


From e41d58185f1444368873d4d7422f7664a68be61d Mon Sep 17 00:00:00 2001
From: Dmitry Vyukov <dvyukov@google.com>
Date: Wed, 12 Jul 2017 14:34:35 -0700
Subject: fault-inject: support systematic fault injection

Add /proc/self/task/<current-tid>/fail-nth file that allows failing
0-th, 1-st, 2-nd and so on calls systematically.
Excerpt from the added documentation:

 "Write to this file of integer N makes N-th call in the current task
  fail (N is 0-based). Read from this file returns a single char 'Y' or
  'N' that says if the fault setup with a previous write to this file
  was injected or not, and disables the fault if it wasn't yet injected.
  Note that this file enables all types of faults (slab, futex, etc).
  This setting takes precedence over all other generic settings like
  probability, interval, times, etc. But per-capability settings (e.g.
  fail_futex/ignore-private) take precedence over it. This feature is
  intended for systematic testing of faults in a single system call. See
  an example below"

Why add a new setting:
1. Existing settings are global rather than per-task.
   So parallel testing is not possible.
2. attr->interval is close but it depends on attr->count
   which is non reset to 0, so interval does not work as expected.
3. Trying to model this with existing settings requires manipulations
   of all of probability, interval, times, space, task-filter and
   unexposed count and per-task make-it-fail files.
4. Existing settings are per-failure-type, and the set of failure
   types is potentially expanding.
5. make-it-fail can't be changed by unprivileged user and aggressive
   stress testing better be done from an unprivileged user.
   Similarly, this would require opening the debugfs files to the
   unprivileged user, as he would need to reopen at least times file
   (not possible to pre-open before dropping privs).

The proposed interface solves all of the above (see the example).

We want to integrate this into syzkaller fuzzer.  A prototype has found
10 bugs in kernel in first day of usage:

  https://groups.google.com/forum/#!searchin/syzkaller/%22FAULT_INJECTION%22%7Csort:relevance

I've made the current interface work with all types of our sandboxes.
For setuid the secret sauce was prctl(PR_SET_DUMPABLE, 1, 0, 0, 0) to
make /proc entries non-root owned.  So I am fine with the current
version of the code.

[akpm@linux-foundation.org: fix build]
Link: http://lkml.kernel.org/r/20170328130128.101773-1-dvyukov@google.com
Signed-off-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Akinobu Mita <akinobu.mita@gmail.com>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/fault-injection/fault-injection.txt | 78 +++++++++++++++++++++++
 fs/proc/base.c                                    | 52 +++++++++++++++
 include/linux/sched.h                             |  1 +
 kernel/fork.c                                     |  4 ++
 lib/fault-inject.c                                |  7 ++
 5 files changed, 142 insertions(+)

(limited to 'include')

diff --git a/Documentation/fault-injection/fault-injection.txt b/Documentation/fault-injection/fault-injection.txt
index 415484f3d59a..192d8cbcc5f9 100644
--- a/Documentation/fault-injection/fault-injection.txt
+++ b/Documentation/fault-injection/fault-injection.txt
@@ -134,6 +134,22 @@ use the boot option:
 	fail_futex=
 	mmc_core.fail_request=<interval>,<probability>,<space>,<times>
 
+o proc entries
+
+- /proc/self/task/<current-tid>/fail-nth:
+
+	Write to this file of integer N makes N-th call in the current task fail
+	(N is 0-based). Read from this file returns a single char 'Y' or 'N'
+	that says if the fault setup with a previous write to this file was
+	injected or not, and disables the fault if it wasn't yet injected.
+	Note that this file enables all types of faults (slab, futex, etc).
+	This setting takes precedence over all other generic debugfs settings
+	like probability, interval, times, etc. But per-capability settings
+	(e.g. fail_futex/ignore-private) take precedence over it.
+
+	This feature is intended for systematic testing of faults in a single
+	system call. See an example below.
+
 How to add new fault injection capability
 -----------------------------------------
 
@@ -278,3 +294,65 @@ allocation failure.
 	# env FAILCMD_TYPE=fail_page_alloc \
 		./tools/testing/fault-injection/failcmd.sh --times=100 \
                 -- make -C tools/testing/selftests/ run_tests
+
+Systematic faults using fail-nth
+---------------------------------
+
+The following code systematically faults 0-th, 1-st, 2-nd and so on
+capabilities in the socketpair() system call.
+
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/socket.h>
+#include <sys/syscall.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <string.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <errno.h>
+
+int main()
+{
+	int i, err, res, fail_nth, fds[2];
+	char buf[128];
+
+	system("echo N > /sys/kernel/debug/failslab/ignore-gfp-wait");
+	sprintf(buf, "/proc/self/task/%ld/fail-nth", syscall(SYS_gettid));
+	fail_nth = open(buf, O_RDWR);
+	for (i = 0;; i++) {
+		sprintf(buf, "%d", i);
+		write(fail_nth, buf, strlen(buf));
+		res = socketpair(AF_LOCAL, SOCK_STREAM, 0, fds);
+		err = errno;
+		read(fail_nth, buf, 1);
+		if (res == 0) {
+			close(fds[0]);
+			close(fds[1]);
+		}
+		printf("%d-th fault %c: res=%d/%d\n", i, buf[0], res, err);
+		if (buf[0] != 'Y')
+			break;
+	}
+	return 0;
+}
+
+An example output:
+
+0-th fault Y: res=-1/23
+1-th fault Y: res=-1/23
+2-th fault Y: res=-1/23
+3-th fault Y: res=-1/12
+4-th fault Y: res=-1/12
+5-th fault Y: res=-1/23
+6-th fault Y: res=-1/23
+7-th fault Y: res=-1/23
+8-th fault Y: res=-1/12
+9-th fault Y: res=-1/12
+10-th fault Y: res=-1/12
+11-th fault Y: res=-1/12
+12-th fault Y: res=-1/12
+13-th fault Y: res=-1/12
+14-th fault Y: res=-1/12
+15-th fault Y: res=-1/12
+16-th fault N: res=0/12
diff --git a/fs/proc/base.c b/fs/proc/base.c
index f1e1927ccd48..88b773f318cd 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1355,6 +1355,53 @@ static const struct file_operations proc_fault_inject_operations = {
 	.write		= proc_fault_inject_write,
 	.llseek		= generic_file_llseek,
 };
+
+static ssize_t proc_fail_nth_write(struct file *file, const char __user *buf,
+				   size_t count, loff_t *ppos)
+{
+	struct task_struct *task;
+	int err, n;
+
+	task = get_proc_task(file_inode(file));
+	if (!task)
+		return -ESRCH;
+	put_task_struct(task);
+	if (task != current)
+		return -EPERM;
+	err = kstrtoint_from_user(buf, count, 10, &n);
+	if (err)
+		return err;
+	if (n < 0 || n == INT_MAX)
+		return -EINVAL;
+	current->fail_nth = n + 1;
+	return count;
+}
+
+static ssize_t proc_fail_nth_read(struct file *file, char __user *buf,
+				  size_t count, loff_t *ppos)
+{
+	struct task_struct *task;
+	int err;
+
+	task = get_proc_task(file_inode(file));
+	if (!task)
+		return -ESRCH;
+	put_task_struct(task);
+	if (task != current)
+		return -EPERM;
+	if (count < 1)
+		return -EINVAL;
+	err = put_user((char)(current->fail_nth ? 'N' : 'Y'), buf);
+	if (err)
+		return err;
+	current->fail_nth = 0;
+	return 1;
+}
+
+static const struct file_operations proc_fail_nth_operations = {
+	.read		= proc_fail_nth_read,
+	.write		= proc_fail_nth_write,
+};
 #endif
 
 
@@ -3311,6 +3358,11 @@ static const struct pid_entry tid_base_stuff[] = {
 #endif
 #ifdef CONFIG_FAULT_INJECTION
 	REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations),
+	/*
+	 * Operations on the file check that the task is current,
+	 * so we create it with 0666 to support testing under unprivileged user.
+	 */
+	REG("fail-nth", 0666, proc_fail_nth_operations),
 #endif
 #ifdef CONFIG_TASK_IO_ACCOUNTING
 	ONE("io",	S_IRUSR, proc_tid_io_accounting),
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 20814b7d7d70..3822d749fc9e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -974,6 +974,7 @@ struct task_struct {
 
 #ifdef CONFIG_FAULT_INJECTION
 	int				make_it_fail;
+	int fail_nth;
 #endif
 	/*
 	 * When (nr_dirtied >= nr_dirtied_pause), it's time to call
diff --git a/kernel/fork.c b/kernel/fork.c
index d2b9d7c31eaf..ade237a96308 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -573,6 +573,10 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 
 	kcov_task_init(tsk);
 
+#ifdef CONFIG_FAULT_INJECTION
+	tsk->fail_nth = 0;
+#endif
+
 	return tsk;
 
 free_stack:
diff --git a/lib/fault-inject.c b/lib/fault-inject.c
index 4ff157159a0d..09ac73c177fd 100644
--- a/lib/fault-inject.c
+++ b/lib/fault-inject.c
@@ -107,6 +107,12 @@ static inline bool fail_stacktrace(struct fault_attr *attr)
 
 bool should_fail(struct fault_attr *attr, ssize_t size)
 {
+	if (in_task() && current->fail_nth) {
+		if (--current->fail_nth == 0)
+			goto fail;
+		return false;
+	}
+
 	/* No need to check any other properties if the probability is 0 */
 	if (attr->probability == 0)
 		return false;
@@ -134,6 +140,7 @@ bool should_fail(struct fault_attr *attr, ssize_t size)
 	if (!fail_stacktrace(attr))
 		return false;
 
+fail:
 	fail_dump(attr);
 
 	if (atomic_read(&attr->times) != -1)
-- 
cgit v1.2.3


From 1a23395672658969a4035dcc518ea6cab835c579 Mon Sep 17 00:00:00 2001
From: Manfred Spraul <manfred@colorfullife.com>
Date: Wed, 12 Jul 2017 14:34:38 -0700
Subject: ipc/sem.c: remove sem_base, embed struct sem

sma->sem_base is initialized with

	sma->sem_base = (struct sem *) &sma[1];

The current code has four problems:
 - There is an unnecessary pointer dereference - sem_base is not needed.
 - Alignment for struct sem only works by chance.
 - The current code causes false positive for static code analysis.
 - This is a cast between different non-void types, which the future
   randstruct GCC plugin warns on.

And, as bonus, the code size gets smaller:

  Before:
    0 .text         00003770
  After:
    0 .text         0000374e

[manfred@colorfullife.com: s/[0]/[]/, per hch]
  Link: http://lkml.kernel.org/r/20170525185107.12869-2-manfred@colorfullife.com
Link: http://lkml.kernel.org/r/20170515171912.6298-2-manfred@colorfullife.com
Signed-off-by: Manfred Spraul <manfred@colorfullife.com>
Acked-by: Kees Cook <keescook@chromium.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: <1vier1@web.de>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Fabian Frederick <fabf@skynet.be>
Cc: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/sem.h | 22 +++++++++++++-
 ipc/sem.c           | 88 +++++++++++++++++++++--------------------------------
 2 files changed, 55 insertions(+), 55 deletions(-)

(limited to 'include')

diff --git a/include/linux/sem.h b/include/linux/sem.h
index 9edec926e9d9..9db14093b73c 100644
--- a/include/linux/sem.h
+++ b/include/linux/sem.h
@@ -8,11 +8,29 @@
 
 struct task_struct;
 
+/* One semaphore structure for each semaphore in the system. */
+struct sem {
+	int	semval;		/* current value */
+	/*
+	 * PID of the process that last modified the semaphore. For
+	 * Linux, specifically these are:
+	 *  - semop
+	 *  - semctl, via SETVAL and SETALL.
+	 *  - at task exit when performing undo adjustments (see exit_sem).
+	 */
+	int	sempid;
+	spinlock_t	lock;	/* spinlock for fine-grained semtimedop */
+	struct list_head pending_alter; /* pending single-sop operations */
+					/* that alter the semaphore */
+	struct list_head pending_const; /* pending single-sop operations */
+					/* that do not alter the semaphore*/
+	time_t	sem_otime;	/* candidate for sem_otime */
+} ____cacheline_aligned_in_smp;
+
 /* One sem_array data structure for each set of semaphores in the system. */
 struct sem_array {
 	struct kern_ipc_perm	sem_perm;	/* permissions .. see ipc.h */
 	time_t			sem_ctime;	/* last change time */
-	struct sem		*sem_base;	/* ptr to first semaphore in array */
 	struct list_head	pending_alter;	/* pending operations */
 						/* that alter the array */
 	struct list_head	pending_const;	/* pending complex operations */
@@ -21,6 +39,8 @@ struct sem_array {
 	int			sem_nsems;	/* no. of semaphores in array */
 	int			complex_count;	/* pending complex operations */
 	unsigned int		use_global_lock;/* >0: global lock required */
+
+	struct sem		sems[];
 };
 
 #ifdef CONFIG_SYSVIPC
diff --git a/ipc/sem.c b/ipc/sem.c
index 947dc2348271..fff8337ebab3 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -87,24 +87,6 @@
 #include <linux/uaccess.h>
 #include "util.h"
 
-/* One semaphore structure for each semaphore in the system. */
-struct sem {
-	int	semval;		/* current value */
-	/*
-	 * PID of the process that last modified the semaphore. For
-	 * Linux, specifically these are:
-	 *  - semop
-	 *  - semctl, via SETVAL and SETALL.
-	 *  - at task exit when performing undo adjustments (see exit_sem).
-	 */
-	int	sempid;
-	spinlock_t	lock;	/* spinlock for fine-grained semtimedop */
-	struct list_head pending_alter; /* pending single-sop operations */
-					/* that alter the semaphore */
-	struct list_head pending_const; /* pending single-sop operations */
-					/* that do not alter the semaphore*/
-	time_t	sem_otime;	/* candidate for sem_otime */
-} ____cacheline_aligned_in_smp;
 
 /* One queue for each sleeping process in the system. */
 struct sem_queue {
@@ -175,7 +157,7 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it);
  *	sem_array.sem_undo
  *
  * b) global or semaphore sem_lock() for read/write:
- *	sem_array.sem_base[i].pending_{const,alter}:
+ *	sem_array.sems[i].pending_{const,alter}:
  *
  * c) special:
  *	sem_undo_list.list_proc:
@@ -250,7 +232,7 @@ static void unmerge_queues(struct sem_array *sma)
 	 */
 	list_for_each_entry_safe(q, tq, &sma->pending_alter, list) {
 		struct sem *curr;
-		curr = &sma->sem_base[q->sops[0].sem_num];
+		curr = &sma->sems[q->sops[0].sem_num];
 
 		list_add_tail(&q->list, &curr->pending_alter);
 	}
@@ -270,7 +252,7 @@ static void merge_queues(struct sem_array *sma)
 {
 	int i;
 	for (i = 0; i < sma->sem_nsems; i++) {
-		struct sem *sem = sma->sem_base + i;
+		struct sem *sem = &sma->sems[i];
 
 		list_splice_init(&sem->pending_alter, &sma->pending_alter);
 	}
@@ -306,7 +288,7 @@ static void complexmode_enter(struct sem_array *sma)
 	sma->use_global_lock = USE_GLOBAL_LOCK_HYSTERESIS;
 
 	for (i = 0; i < sma->sem_nsems; i++) {
-		sem = sma->sem_base + i;
+		sem = &sma->sems[i];
 		spin_lock(&sem->lock);
 		spin_unlock(&sem->lock);
 	}
@@ -366,7 +348,7 @@ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops,
 	 *
 	 * Both facts are tracked by use_global_mode.
 	 */
-	sem = sma->sem_base + sops->sem_num;
+	sem = &sma->sems[sops->sem_num];
 
 	/*
 	 * Initial check for use_global_lock. Just an optimization,
@@ -421,7 +403,7 @@ static inline void sem_unlock(struct sem_array *sma, int locknum)
 		complexmode_tryleave(sma);
 		ipc_unlock_object(&sma->sem_perm);
 	} else {
-		struct sem *sem = sma->sem_base + locknum;
+		struct sem *sem = &sma->sems[locknum];
 		spin_unlock(&sem->lock);
 	}
 }
@@ -487,7 +469,7 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params)
 	if (ns->used_sems + nsems > ns->sc_semmns)
 		return -ENOSPC;
 
-	size = sizeof(*sma) + nsems * sizeof(struct sem);
+	size = sizeof(*sma) + nsems * sizeof(sma->sems[0]);
 	sma = ipc_rcu_alloc(size);
 	if (!sma)
 		return -ENOMEM;
@@ -504,12 +486,10 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params)
 		return retval;
 	}
 
-	sma->sem_base = (struct sem *) &sma[1];
-
 	for (i = 0; i < nsems; i++) {
-		INIT_LIST_HEAD(&sma->sem_base[i].pending_alter);
-		INIT_LIST_HEAD(&sma->sem_base[i].pending_const);
-		spin_lock_init(&sma->sem_base[i].lock);
+		INIT_LIST_HEAD(&sma->sems[i].pending_alter);
+		INIT_LIST_HEAD(&sma->sems[i].pending_const);
+		spin_lock_init(&sma->sems[i].lock);
 	}
 
 	sma->complex_count = 0;
@@ -612,7 +592,7 @@ static int perform_atomic_semop_slow(struct sem_array *sma, struct sem_queue *q)
 	un = q->undo;
 
 	for (sop = sops; sop < sops + nsops; sop++) {
-		curr = sma->sem_base + sop->sem_num;
+		curr = &sma->sems[sop->sem_num];
 		sem_op = sop->sem_op;
 		result = curr->semval;
 
@@ -639,7 +619,7 @@ static int perform_atomic_semop_slow(struct sem_array *sma, struct sem_queue *q)
 	sop--;
 	pid = q->pid;
 	while (sop >= sops) {
-		sma->sem_base[sop->sem_num].sempid = pid;
+		sma->sems[sop->sem_num].sempid = pid;
 		sop--;
 	}
 
@@ -661,7 +641,7 @@ undo:
 	sop--;
 	while (sop >= sops) {
 		sem_op = sop->sem_op;
-		sma->sem_base[sop->sem_num].semval -= sem_op;
+		sma->sems[sop->sem_num].semval -= sem_op;
 		if (sop->sem_flg & SEM_UNDO)
 			un->semadj[sop->sem_num] += sem_op;
 		sop--;
@@ -692,7 +672,7 @@ static int perform_atomic_semop(struct sem_array *sma, struct sem_queue *q)
 	 * until the operations can go through.
 	 */
 	for (sop = sops; sop < sops + nsops; sop++) {
-		curr = sma->sem_base + sop->sem_num;
+		curr = &sma->sems[sop->sem_num];
 		sem_op = sop->sem_op;
 		result = curr->semval;
 
@@ -716,7 +696,7 @@ static int perform_atomic_semop(struct sem_array *sma, struct sem_queue *q)
 	}
 
 	for (sop = sops; sop < sops + nsops; sop++) {
-		curr = sma->sem_base + sop->sem_num;
+		curr = &sma->sems[sop->sem_num];
 		sem_op = sop->sem_op;
 		result = curr->semval;
 
@@ -815,7 +795,7 @@ static int wake_const_ops(struct sem_array *sma, int semnum,
 	if (semnum == -1)
 		pending_list = &sma->pending_const;
 	else
-		pending_list = &sma->sem_base[semnum].pending_const;
+		pending_list = &sma->sems[semnum].pending_const;
 
 	list_for_each_entry_safe(q, tmp, pending_list, list) {
 		int error = perform_atomic_semop(sma, q);
@@ -856,7 +836,7 @@ static int do_smart_wakeup_zero(struct sem_array *sma, struct sembuf *sops,
 		for (i = 0; i < nsops; i++) {
 			int num = sops[i].sem_num;
 
-			if (sma->sem_base[num].semval == 0) {
+			if (sma->sems[num].semval == 0) {
 				got_zero = 1;
 				semop_completed |= wake_const_ops(sma, num, wake_q);
 			}
@@ -867,7 +847,7 @@ static int do_smart_wakeup_zero(struct sem_array *sma, struct sembuf *sops,
 		 * Assume all were changed.
 		 */
 		for (i = 0; i < sma->sem_nsems; i++) {
-			if (sma->sem_base[i].semval == 0) {
+			if (sma->sems[i].semval == 0) {
 				got_zero = 1;
 				semop_completed |= wake_const_ops(sma, i, wake_q);
 			}
@@ -909,7 +889,7 @@ static int update_queue(struct sem_array *sma, int semnum, struct wake_q_head *w
 	if (semnum == -1)
 		pending_list = &sma->pending_alter;
 	else
-		pending_list = &sma->sem_base[semnum].pending_alter;
+		pending_list = &sma->sems[semnum].pending_alter;
 
 again:
 	list_for_each_entry_safe(q, tmp, pending_list, list) {
@@ -922,7 +902,7 @@ again:
 		 * be in the  per semaphore pending queue, and decrements
 		 * cannot be successful if the value is already 0.
 		 */
-		if (semnum != -1 && sma->sem_base[semnum].semval == 0)
+		if (semnum != -1 && sma->sems[semnum].semval == 0)
 			break;
 
 		error = perform_atomic_semop(sma, q);
@@ -959,9 +939,9 @@ again:
 static void set_semotime(struct sem_array *sma, struct sembuf *sops)
 {
 	if (sops == NULL) {
-		sma->sem_base[0].sem_otime = get_seconds();
+		sma->sems[0].sem_otime = get_seconds();
 	} else {
-		sma->sem_base[sops[0].sem_num].sem_otime =
+		sma->sems[sops[0].sem_num].sem_otime =
 							get_seconds();
 	}
 }
@@ -1067,9 +1047,9 @@ static int count_semcnt(struct sem_array *sma, ushort semnum,
 	semcnt = 0;
 	/* First: check the simple operations. They are easy to evaluate */
 	if (count_zero)
-		l = &sma->sem_base[semnum].pending_const;
+		l = &sma->sems[semnum].pending_const;
 	else
-		l = &sma->sem_base[semnum].pending_alter;
+		l = &sma->sems[semnum].pending_alter;
 
 	list_for_each_entry(q, l, list) {
 		/* all task on a per-semaphore list sleep on exactly
@@ -1124,7 +1104,7 @@ static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
 		wake_up_sem_queue_prepare(q, -EIDRM, &wake_q);
 	}
 	for (i = 0; i < sma->sem_nsems; i++) {
-		struct sem *sem = sma->sem_base + i;
+		struct sem *sem = &sma->sems[i];
 		list_for_each_entry_safe(q, tq, &sem->pending_const, list) {
 			unlink_queue(sma, q);
 			wake_up_sem_queue_prepare(q, -EIDRM, &wake_q);
@@ -1174,9 +1154,9 @@ static time_t get_semotime(struct sem_array *sma)
 	int i;
 	time_t res;
 
-	res = sma->sem_base[0].sem_otime;
+	res = sma->sems[0].sem_otime;
 	for (i = 1; i < sma->sem_nsems; i++) {
-		time_t to = sma->sem_base[i].sem_otime;
+		time_t to = sma->sems[i].sem_otime;
 
 		if (to > res)
 			res = to;
@@ -1325,7 +1305,7 @@ static int semctl_setval(struct ipc_namespace *ns, int semid, int semnum,
 		return -EIDRM;
 	}
 
-	curr = &sma->sem_base[semnum];
+	curr = &sma->sems[semnum];
 
 	ipc_assert_locked_object(&sma->sem_perm);
 	list_for_each_entry(un, &sma->list_id, list_id)
@@ -1402,7 +1382,7 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 			}
 		}
 		for (i = 0; i < sma->sem_nsems; i++)
-			sem_io[i] = sma->sem_base[i].semval;
+			sem_io[i] = sma->sems[i].semval;
 		sem_unlock(sma, -1);
 		rcu_read_unlock();
 		err = 0;
@@ -1450,8 +1430,8 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 		}
 
 		for (i = 0; i < nsems; i++) {
-			sma->sem_base[i].semval = sem_io[i];
-			sma->sem_base[i].sempid = task_tgid_vnr(current);
+			sma->sems[i].semval = sem_io[i];
+			sma->sems[i].sempid = task_tgid_vnr(current);
 		}
 
 		ipc_assert_locked_object(&sma->sem_perm);
@@ -1476,7 +1456,7 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 		err = -EIDRM;
 		goto out_unlock;
 	}
-	curr = &sma->sem_base[semnum];
+	curr = &sma->sems[semnum];
 
 	switch (cmd) {
 	case GETVAL:
@@ -1932,7 +1912,7 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops,
 	 */
 	if (nsops == 1) {
 		struct sem *curr;
-		curr = &sma->sem_base[sops->sem_num];
+		curr = &sma->sems[sops->sem_num];
 
 		if (alter) {
 			if (sma->complex_count) {
@@ -2146,7 +2126,7 @@ void exit_sem(struct task_struct *tsk)
 
 		/* perform adjustments registered in un */
 		for (i = 0; i < sma->sem_nsems; i++) {
-			struct sem *semaphore = &sma->sem_base[i];
+			struct sem *semaphore = &sma->sems[i];
 			if (un->semadj[i]) {
 				semaphore->semval += un->semadj[i];
 				/*
-- 
cgit v1.2.3


From dba4cdd39e698d8dcdad0656825423052ac90ccd Mon Sep 17 00:00:00 2001
From: Manfred Spraul <manfred@colorfullife.com>
Date: Wed, 12 Jul 2017 14:34:41 -0700
Subject: ipc: merge ipc_rcu and kern_ipc_perm

ipc has two management structures that exist for every id:
 - struct kern_ipc_perm, it contains e.g. the permissions.
 - struct ipc_rcu, it contains the rcu head for rcu handling and the
   refcount.

The patch merges both structures.

As a bonus, we may save one cacheline, because both structures are
cacheline aligned.  In addition, it reduces the number of casts, instead
most codepaths can use container_of.

To simplify code, the ipc_rcu_alloc initializes the allocation to 0.

[manfred@colorfullife.com: really include the memset() into ipc_alloc_rcu()]
  Link: http://lkml.kernel.org/r/564f8612-0601-b267-514f-a9f650ec9b32@colorfullife.com
Link: http://lkml.kernel.org/r/20170525185107.12869-3-manfred@colorfullife.com
Signed-off-by: Manfred Spraul <manfred@colorfullife.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Kees Cook <keescook@chromium.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/ipc.h |  3 +++
 ipc/msg.c           | 19 +++++++++++--------
 ipc/sem.c           | 34 +++++++++++++++++-----------------
 ipc/shm.c           | 18 +++++++++++-------
 ipc/util.c          | 35 +++++++++++++++++------------------
 ipc/util.h          | 18 +++++++-----------
 6 files changed, 66 insertions(+), 61 deletions(-)

(limited to 'include')

diff --git a/include/linux/ipc.h b/include/linux/ipc.h
index 71fd92d81b26..5591f055e13f 100644
--- a/include/linux/ipc.h
+++ b/include/linux/ipc.h
@@ -20,6 +20,9 @@ struct kern_ipc_perm {
 	umode_t		mode;
 	unsigned long	seq;
 	void		*security;
+
+	struct rcu_head rcu;
+	atomic_t refcount;
 } ____cacheline_aligned_in_smp;
 
 #endif /* _LINUX_IPC_H */
diff --git a/ipc/msg.c b/ipc/msg.c
index 104926dc72be..0ed7dae7d4e8 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -97,8 +97,8 @@ static inline void msg_rmid(struct ipc_namespace *ns, struct msg_queue *s)
 
 static void msg_rcu_free(struct rcu_head *head)
 {
-	struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu);
-	struct msg_queue *msq = ipc_rcu_to_struct(p);
+	struct kern_ipc_perm *p = container_of(head, struct kern_ipc_perm, rcu);
+	struct msg_queue *msq = container_of(p, struct msg_queue, q_perm);
 
 	security_msg_queue_free(msq);
 	ipc_rcu_free(head);
@@ -118,7 +118,10 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params)
 	key_t key = params->key;
 	int msgflg = params->flg;
 
-	msq = ipc_rcu_alloc(sizeof(*msq));
+	BUILD_BUG_ON(offsetof(struct msg_queue, q_perm) != 0);
+
+	msq = container_of(ipc_rcu_alloc(sizeof(*msq)), struct msg_queue,
+				q_perm);
 	if (!msq)
 		return -ENOMEM;
 
@@ -128,7 +131,7 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params)
 	msq->q_perm.security = NULL;
 	retval = security_msg_queue_alloc(msq);
 	if (retval) {
-		ipc_rcu_putref(msq, ipc_rcu_free);
+		ipc_rcu_putref(&msq->q_perm, ipc_rcu_free);
 		return retval;
 	}
 
@@ -144,7 +147,7 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params)
 	/* ipc_addid() locks msq upon success. */
 	id = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni);
 	if (id < 0) {
-		ipc_rcu_putref(msq, msg_rcu_free);
+		ipc_rcu_putref(&msq->q_perm, msg_rcu_free);
 		return id;
 	}
 
@@ -249,7 +252,7 @@ static void freeque(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
 		free_msg(msg);
 	}
 	atomic_sub(msq->q_cbytes, &ns->msg_bytes);
-	ipc_rcu_putref(msq, msg_rcu_free);
+	ipc_rcu_putref(&msq->q_perm, msg_rcu_free);
 }
 
 /*
@@ -688,7 +691,7 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext,
 		/* enqueue the sender and prepare to block */
 		ss_add(msq, &s, msgsz);
 
-		if (!ipc_rcu_getref(msq)) {
+		if (!ipc_rcu_getref(&msq->q_perm)) {
 			err = -EIDRM;
 			goto out_unlock0;
 		}
@@ -700,7 +703,7 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext,
 		rcu_read_lock();
 		ipc_lock_object(&msq->q_perm);
 
-		ipc_rcu_putref(msq, msg_rcu_free);
+		ipc_rcu_putref(&msq->q_perm, msg_rcu_free);
 		/* raced with RMID? */
 		if (!ipc_valid_object(&msq->q_perm)) {
 			err = -EIDRM;
diff --git a/ipc/sem.c b/ipc/sem.c
index fff8337ebab3..bdff6d93d2c7 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -260,8 +260,8 @@ static void merge_queues(struct sem_array *sma)
 
 static void sem_rcu_free(struct rcu_head *head)
 {
-	struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu);
-	struct sem_array *sma = ipc_rcu_to_struct(p);
+	struct kern_ipc_perm *p = container_of(head, struct kern_ipc_perm, rcu);
+	struct sem_array *sma = container_of(p, struct sem_array, sem_perm);
 
 	security_sem_free(sma);
 	ipc_rcu_free(head);
@@ -438,7 +438,7 @@ static inline struct sem_array *sem_obtain_object_check(struct ipc_namespace *ns
 static inline void sem_lock_and_putref(struct sem_array *sma)
 {
 	sem_lock(sma, NULL, -1);
-	ipc_rcu_putref(sma, sem_rcu_free);
+	ipc_rcu_putref(&sma->sem_perm, sem_rcu_free);
 }
 
 static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s)
@@ -469,20 +469,20 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params)
 	if (ns->used_sems + nsems > ns->sc_semmns)
 		return -ENOSPC;
 
+	BUILD_BUG_ON(offsetof(struct sem_array, sem_perm) != 0);
+
 	size = sizeof(*sma) + nsems * sizeof(sma->sems[0]);
-	sma = ipc_rcu_alloc(size);
+	sma = container_of(ipc_rcu_alloc(size), struct sem_array, sem_perm);
 	if (!sma)
 		return -ENOMEM;
 
-	memset(sma, 0, size);
-
 	sma->sem_perm.mode = (semflg & S_IRWXUGO);
 	sma->sem_perm.key = key;
 
 	sma->sem_perm.security = NULL;
 	retval = security_sem_alloc(sma);
 	if (retval) {
-		ipc_rcu_putref(sma, ipc_rcu_free);
+		ipc_rcu_putref(&sma->sem_perm, ipc_rcu_free);
 		return retval;
 	}
 
@@ -502,7 +502,7 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params)
 
 	id = ipc_addid(&sem_ids(ns), &sma->sem_perm, ns->sc_semmni);
 	if (id < 0) {
-		ipc_rcu_putref(sma, sem_rcu_free);
+		ipc_rcu_putref(&sma->sem_perm, sem_rcu_free);
 		return id;
 	}
 	ns->used_sems += nsems;
@@ -1122,7 +1122,7 @@ static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
 
 	wake_up_q(&wake_q);
 	ns->used_sems -= sma->sem_nsems;
-	ipc_rcu_putref(sma, sem_rcu_free);
+	ipc_rcu_putref(&sma->sem_perm, sem_rcu_free);
 }
 
 static unsigned long copy_semid_to_user(void __user *buf, struct semid64_ds *in, int version)
@@ -1362,7 +1362,7 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 			goto out_unlock;
 		}
 		if (nsems > SEMMSL_FAST) {
-			if (!ipc_rcu_getref(sma)) {
+			if (!ipc_rcu_getref(&sma->sem_perm)) {
 				err = -EIDRM;
 				goto out_unlock;
 			}
@@ -1370,7 +1370,7 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 			rcu_read_unlock();
 			sem_io = ipc_alloc(sizeof(ushort)*nsems);
 			if (sem_io == NULL) {
-				ipc_rcu_putref(sma, sem_rcu_free);
+				ipc_rcu_putref(&sma->sem_perm, sem_rcu_free);
 				return -ENOMEM;
 			}
 
@@ -1395,7 +1395,7 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 		int i;
 		struct sem_undo *un;
 
-		if (!ipc_rcu_getref(sma)) {
+		if (!ipc_rcu_getref(&sma->sem_perm)) {
 			err = -EIDRM;
 			goto out_rcu_wakeup;
 		}
@@ -1404,20 +1404,20 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 		if (nsems > SEMMSL_FAST) {
 			sem_io = ipc_alloc(sizeof(ushort)*nsems);
 			if (sem_io == NULL) {
-				ipc_rcu_putref(sma, sem_rcu_free);
+				ipc_rcu_putref(&sma->sem_perm, sem_rcu_free);
 				return -ENOMEM;
 			}
 		}
 
 		if (copy_from_user(sem_io, p, nsems*sizeof(ushort))) {
-			ipc_rcu_putref(sma, sem_rcu_free);
+			ipc_rcu_putref(&sma->sem_perm, sem_rcu_free);
 			err = -EFAULT;
 			goto out_free;
 		}
 
 		for (i = 0; i < nsems; i++) {
 			if (sem_io[i] > SEMVMX) {
-				ipc_rcu_putref(sma, sem_rcu_free);
+				ipc_rcu_putref(&sma->sem_perm, sem_rcu_free);
 				err = -ERANGE;
 				goto out_free;
 			}
@@ -1699,7 +1699,7 @@ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid)
 	}
 
 	nsems = sma->sem_nsems;
-	if (!ipc_rcu_getref(sma)) {
+	if (!ipc_rcu_getref(&sma->sem_perm)) {
 		rcu_read_unlock();
 		un = ERR_PTR(-EIDRM);
 		goto out;
@@ -1709,7 +1709,7 @@ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid)
 	/* step 2: allocate new undo structure */
 	new = kzalloc(sizeof(struct sem_undo) + sizeof(short)*nsems, GFP_KERNEL);
 	if (!new) {
-		ipc_rcu_putref(sma, sem_rcu_free);
+		ipc_rcu_putref(&sma->sem_perm, sem_rcu_free);
 		return ERR_PTR(-ENOMEM);
 	}
 
diff --git a/ipc/shm.c b/ipc/shm.c
index f45c7959b264..5ef6d31a52c5 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -174,9 +174,10 @@ static inline void shm_lock_by_ptr(struct shmid_kernel *ipcp)
 
 static void shm_rcu_free(struct rcu_head *head)
 {
-	struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu);
-	struct shmid_kernel *shp = ipc_rcu_to_struct(p);
-
+	struct kern_ipc_perm *ptr = container_of(head, struct kern_ipc_perm,
+							rcu);
+	struct shmid_kernel *shp = container_of(ptr, struct shmid_kernel,
+							shm_perm);
 	security_shm_free(shp);
 	ipc_rcu_free(head);
 }
@@ -241,7 +242,7 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
 		user_shm_unlock(i_size_read(file_inode(shm_file)),
 				shp->mlock_user);
 	fput(shm_file);
-	ipc_rcu_putref(shp, shm_rcu_free);
+	ipc_rcu_putref(&shp->shm_perm, shm_rcu_free);
 }
 
 /*
@@ -542,7 +543,10 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 			ns->shm_tot + numpages > ns->shm_ctlall)
 		return -ENOSPC;
 
-	shp = ipc_rcu_alloc(sizeof(*shp));
+	BUILD_BUG_ON(offsetof(struct shmid_kernel, shm_perm) != 0);
+
+	shp = container_of(ipc_rcu_alloc(sizeof(*shp)), struct shmid_kernel,
+				shm_perm);
 	if (!shp)
 		return -ENOMEM;
 
@@ -553,7 +557,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 	shp->shm_perm.security = NULL;
 	error = security_shm_alloc(shp);
 	if (error) {
-		ipc_rcu_putref(shp, ipc_rcu_free);
+		ipc_rcu_putref(&shp->shm_perm, ipc_rcu_free);
 		return error;
 	}
 
@@ -624,7 +628,7 @@ no_id:
 		user_shm_unlock(size, shp->mlock_user);
 	fput(file);
 no_file:
-	ipc_rcu_putref(shp, shm_rcu_free);
+	ipc_rcu_putref(&shp->shm_perm, shm_rcu_free);
 	return error;
 }
 
diff --git a/ipc/util.c b/ipc/util.c
index caec7b1bfaa3..5d1ff1035efe 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -418,46 +418,45 @@ void ipc_free(void *ptr)
 }
 
 /**
- * ipc_rcu_alloc - allocate ipc and rcu space
+ * ipc_rcu_alloc - allocate ipc space
  * @size: size desired
  *
- * Allocate memory for the rcu header structure +  the object.
- * Returns the pointer to the object or NULL upon failure.
+ * Allocate memory for an ipc object.
+ * The first member must be struct kern_ipc_perm.
  */
-void *ipc_rcu_alloc(int size)
+struct kern_ipc_perm *ipc_rcu_alloc(int size)
 {
 	/*
 	 * We prepend the allocation with the rcu struct
 	 */
-	struct ipc_rcu *out = ipc_alloc(sizeof(struct ipc_rcu) + size);
+	struct kern_ipc_perm *out = ipc_alloc(size);
 	if (unlikely(!out))
 		return NULL;
+
+	memset(out, 0, size);
 	atomic_set(&out->refcount, 1);
-	return out + 1;
+	return out;
 }
 
-int ipc_rcu_getref(void *ptr)
+int ipc_rcu_getref(struct kern_ipc_perm *ptr)
 {
-	struct ipc_rcu *p = ((struct ipc_rcu *)ptr) - 1;
-
-	return atomic_inc_not_zero(&p->refcount);
+	return atomic_inc_not_zero(&ptr->refcount);
 }
 
-void ipc_rcu_putref(void *ptr, void (*func)(struct rcu_head *head))
+void ipc_rcu_putref(struct kern_ipc_perm *ptr,
+			void (*func)(struct rcu_head *head))
 {
-	struct ipc_rcu *p = ((struct ipc_rcu *)ptr) - 1;
-
-	if (!atomic_dec_and_test(&p->refcount))
+	if (!atomic_dec_and_test(&ptr->refcount))
 		return;
 
-	call_rcu(&p->rcu, func);
+	call_rcu(&ptr->rcu, func);
 }
 
-void ipc_rcu_free(struct rcu_head *head)
+void ipc_rcu_free(struct rcu_head *h)
 {
-	struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu);
+	struct kern_ipc_perm *ptr = container_of(h, struct kern_ipc_perm, rcu);
 
-	kvfree(p);
+	kvfree(ptr);
 }
 
 /**
diff --git a/ipc/util.h b/ipc/util.h
index 60ddccca464d..09d0f918c3e2 100644
--- a/ipc/util.h
+++ b/ipc/util.h
@@ -47,13 +47,6 @@ static inline void msg_exit_ns(struct ipc_namespace *ns) { }
 static inline void shm_exit_ns(struct ipc_namespace *ns) { }
 #endif
 
-struct ipc_rcu {
-	struct rcu_head rcu;
-	atomic_t refcount;
-} ____cacheline_aligned_in_smp;
-
-#define ipc_rcu_to_struct(p)  ((void *)(p+1))
-
 /*
  * Structure that holds the parameters needed by the ipc operations
  * (see after)
@@ -125,11 +118,14 @@ void ipc_free(void *ptr);
  * Objects are reference counted, they start with reference count 1.
  * getref increases the refcount, the putref call that reduces the recount
  * to 0 schedules the rcu destruction. Caller must guarantee locking.
+ *
+ * struct kern_ipc_perm must be the first member in the allocated structure.
  */
-void *ipc_rcu_alloc(int size);
-int ipc_rcu_getref(void *ptr);
-void ipc_rcu_putref(void *ptr, void (*func)(struct rcu_head *head));
-void ipc_rcu_free(struct rcu_head *head);
+struct kern_ipc_perm *ipc_rcu_alloc(int size);
+int ipc_rcu_getref(struct kern_ipc_perm *ptr);
+void ipc_rcu_putref(struct kern_ipc_perm *ptr,
+			void (*func)(struct rcu_head *head));
+void ipc_rcu_free(struct rcu_head *h);
 
 struct kern_ipc_perm *ipc_lock(struct ipc_ids *, int);
 struct kern_ipc_perm *ipc_obtain_object_idr(struct ipc_ids *ids, int id);
-- 
cgit v1.2.3


From 2cd648c110b5570c3280bd645797658cabbe5f5c Mon Sep 17 00:00:00 2001
From: Manfred Spraul <manfred@colorfullife.com>
Date: Wed, 12 Jul 2017 14:34:44 -0700
Subject: include/linux/sem.h: correctly document sem_ctime

sem_ctime is initialized to the semget() time and then updated at every
semctl() that changes the array.

Thus it does not represent the time of the last change.

Especially, semop() calls are only stored in sem_otime, not in
sem_ctime.

This is already described in ipc/sem.c, I just overlooked that there is
a comment in include/linux/sem.h and man semctl(2) as well.

So: Correct wrong comments.

Link: http://lkml.kernel.org/r/20170515171912.6298-4-manfred@colorfullife.com
Signed-off-by: Manfred Spraul <manfred@colorfullife.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: <1vier1@web.de>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Fabian Frederick <fabf@skynet.be>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/sem.h      | 2 +-
 include/uapi/linux/sem.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/sem.h b/include/linux/sem.h
index 9db14093b73c..be5cf2ea14ad 100644
--- a/include/linux/sem.h
+++ b/include/linux/sem.h
@@ -30,7 +30,7 @@ struct sem {
 /* One sem_array data structure for each set of semaphores in the system. */
 struct sem_array {
 	struct kern_ipc_perm	sem_perm;	/* permissions .. see ipc.h */
-	time_t			sem_ctime;	/* last change time */
+	time_t			sem_ctime;	/* create/last semctl() time */
 	struct list_head	pending_alter;	/* pending operations */
 						/* that alter the array */
 	struct list_head	pending_const;	/* pending complex operations */
diff --git a/include/uapi/linux/sem.h b/include/uapi/linux/sem.h
index dd73b908b2f3..67eb90361692 100644
--- a/include/uapi/linux/sem.h
+++ b/include/uapi/linux/sem.h
@@ -23,7 +23,7 @@
 struct semid_ds {
 	struct ipc_perm	sem_perm;		/* permissions .. see ipc.h */
 	__kernel_time_t	sem_otime;		/* last semop time */
-	__kernel_time_t	sem_ctime;		/* last change time */
+	__kernel_time_t	sem_ctime;		/* create/last semctl() time */
 	struct sem	*sem_base;		/* ptr to first semaphore in array */
 	struct sem_queue *sem_pending;		/* pending operations to be processed */
 	struct sem_queue **sem_pending_last;	/* last pending operation */
-- 
cgit v1.2.3


From 24bb44612c5f93a1dff1f7e71b7b7b109a988791 Mon Sep 17 00:00:00 2001
From: Nicholas Piggin <npiggin@gmail.com>
Date: Wed, 12 Jul 2017 14:35:40 -0700
Subject: kernel/watchdog: remove unused declaration

Patch series "Improve watchdog config for arch watchdogs", v4.

A series to make the hardlockup watchdog more easily replaceable by arch
code.  The last patch provides some justification for why we want to do
this (existing sparc watchdog is another that could benefit).

This patch (of 5):

Remove unused declaration.

Link: http://lkml.kernel.org/r/20170616065715.18390-2-npiggin@gmail.com
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Reviewed-by: Don Zickus <dzickus@redhat.com>
Reviewed-by: Babu Moger <babu.moger@oracle.com>
Tested-by: Babu Moger <babu.moger@oracle.com>	[sparc]
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/nmi.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index aa3cd0878270..5e2e57536d98 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -12,9 +12,6 @@ extern void touch_softlockup_watchdog_sched(void);
 extern void touch_softlockup_watchdog(void);
 extern void touch_softlockup_watchdog_sync(void);
 extern void touch_all_softlockup_watchdogs(void);
-extern int proc_dowatchdog_thresh(struct ctl_table *table, int write,
-				  void __user *buffer,
-				  size_t *lenp, loff_t *ppos);
 extern unsigned int  softlockup_panic;
 extern unsigned int  hardlockup_panic;
 void lockup_detector_init(void);
-- 
cgit v1.2.3


From f2e0cff85ed111a3cf24d894c3fa11697dfae628 Mon Sep 17 00:00:00 2001
From: Nicholas Piggin <npiggin@gmail.com>
Date: Wed, 12 Jul 2017 14:35:43 -0700
Subject: kernel/watchdog: introduce arch_touch_nmi_watchdog()

For architectures that define HAVE_NMI_WATCHDOG, instead of having them
provide the complete touch_nmi_watchdog() function, just have them
provide arch_touch_nmi_watchdog().

This gives the generic code more flexibility in implementing this
function, and arch implementations don't miss out on touching the
softlockup watchdog or other generic details.

Link: http://lkml.kernel.org/r/20170616065715.18390-3-npiggin@gmail.com
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Reviewed-by: Don Zickus <dzickus@redhat.com>
Reviewed-by: Babu Moger <babu.moger@oracle.com>
Tested-by: Babu Moger <babu.moger@oracle.com>	[sparc]
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/blackfin/include/asm/nmi.h            |  2 ++
 arch/blackfin/kernel/nmi.c                 |  2 +-
 arch/mn10300/include/asm/nmi.h             |  2 ++
 arch/mn10300/kernel/mn10300-watchdog-low.S |  8 ++++----
 arch/mn10300/kernel/mn10300-watchdog.c     |  2 +-
 arch/sparc/include/asm/nmi.h               |  1 +
 arch/sparc/kernel/nmi.c                    |  6 ++----
 include/linux/nmi.h                        | 27 ++++++++++++++++-----------
 kernel/watchdog_hld.c                      |  5 ++---
 9 files changed, 31 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/arch/blackfin/include/asm/nmi.h b/arch/blackfin/include/asm/nmi.h
index b9caac4fcfd8..107d23705f46 100644
--- a/arch/blackfin/include/asm/nmi.h
+++ b/arch/blackfin/include/asm/nmi.h
@@ -9,4 +9,6 @@
 
 #include <linux/nmi.h>
 
+extern void arch_touch_nmi_watchdog(void);
+
 #endif
diff --git a/arch/blackfin/kernel/nmi.c b/arch/blackfin/kernel/nmi.c
index 633c37083e87..1e714329fe8a 100644
--- a/arch/blackfin/kernel/nmi.c
+++ b/arch/blackfin/kernel/nmi.c
@@ -190,7 +190,7 @@ static int __init init_nmi_wdt(void)
 }
 device_initcall(init_nmi_wdt);
 
-void touch_nmi_watchdog(void)
+void arch_touch_nmi_watchdog(void)
 {
 	atomic_set(&nmi_touched[smp_processor_id()], 1);
 }
diff --git a/arch/mn10300/include/asm/nmi.h b/arch/mn10300/include/asm/nmi.h
index f3671cbbc117..b05627597b1b 100644
--- a/arch/mn10300/include/asm/nmi.h
+++ b/arch/mn10300/include/asm/nmi.h
@@ -11,4 +11,6 @@
 #ifndef _ASM_NMI_H
 #define _ASM_NMI_H
 
+extern void arch_touch_nmi_watchdog(void);
+
 #endif /* _ASM_NMI_H */
diff --git a/arch/mn10300/kernel/mn10300-watchdog-low.S b/arch/mn10300/kernel/mn10300-watchdog-low.S
index f2f5c9cfaabd..34f8773de7d0 100644
--- a/arch/mn10300/kernel/mn10300-watchdog-low.S
+++ b/arch/mn10300/kernel/mn10300-watchdog-low.S
@@ -50,9 +50,9 @@ watchdog_handler:
 #   we can't inline it)
 #
 ###############################################################################
-	.globl	touch_nmi_watchdog
-	.type	touch_nmi_watchdog,@function
-touch_nmi_watchdog:
+	.globl	arch_touch_nmi_watchdog
+	.type	arch_touch_nmi_watchdog,@function
+arch_touch_nmi_watchdog:
 	clr	d0
 	clr	d1
 	mov	watchdog_alert_counter, a0
@@ -63,4 +63,4 @@ touch_nmi_watchdog:
 	lne
 	ret	[],0
 
-	.size	touch_nmi_watchdog,.-touch_nmi_watchdog
+	.size	arch_touch_nmi_watchdog,.-arch_touch_nmi_watchdog
diff --git a/arch/mn10300/kernel/mn10300-watchdog.c b/arch/mn10300/kernel/mn10300-watchdog.c
index a2d8e6938d67..0d5641beadf5 100644
--- a/arch/mn10300/kernel/mn10300-watchdog.c
+++ b/arch/mn10300/kernel/mn10300-watchdog.c
@@ -31,7 +31,7 @@ static unsigned int watchdog;
 static unsigned int watchdog_hz = 1;
 unsigned int watchdog_alert_counter[NR_CPUS];
 
-EXPORT_SYMBOL(touch_nmi_watchdog);
+EXPORT_SYMBOL(arch_touch_nmi_watchdog);
 
 /*
  * the best way to detect whether a CPU has a 'hard lockup' problem
diff --git a/arch/sparc/include/asm/nmi.h b/arch/sparc/include/asm/nmi.h
index 26ad2b2607c6..284eac3ffaf2 100644
--- a/arch/sparc/include/asm/nmi.h
+++ b/arch/sparc/include/asm/nmi.h
@@ -7,6 +7,7 @@ void nmi_adjust_hz(unsigned int new_hz);
 
 extern atomic_t nmi_active;
 
+void arch_touch_nmi_watchdog(void);
 void start_nmi_watchdog(void *unused);
 void stop_nmi_watchdog(void *unused);
 
diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c
index 95e73c63c99d..048ad783ea3f 100644
--- a/arch/sparc/kernel/nmi.c
+++ b/arch/sparc/kernel/nmi.c
@@ -51,7 +51,7 @@ static DEFINE_PER_CPU(unsigned int, last_irq_sum);
 static DEFINE_PER_CPU(long, alert_counter);
 static DEFINE_PER_CPU(int, nmi_touch);
 
-void touch_nmi_watchdog(void)
+void arch_touch_nmi_watchdog(void)
 {
 	if (atomic_read(&nmi_active)) {
 		int cpu;
@@ -61,10 +61,8 @@ void touch_nmi_watchdog(void)
 				per_cpu(nmi_touch, cpu) = 1;
 		}
 	}
-
-	touch_softlockup_watchdog();
 }
-EXPORT_SYMBOL(touch_nmi_watchdog);
+EXPORT_SYMBOL(arch_touch_nmi_watchdog);
 
 static void die_nmi(const char *str, struct pt_regs *regs, int do_panic)
 {
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index 5e2e57536d98..bd387ef8bccd 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -6,6 +6,9 @@
 
 #include <linux/sched.h>
 #include <asm/irq.h>
+#if defined(CONFIG_HAVE_NMI_WATCHDOG)
+#include <asm/nmi.h>
+#endif
 
 #ifdef CONFIG_LOCKUP_DETECTOR
 extern void touch_softlockup_watchdog_sched(void);
@@ -58,6 +61,18 @@ static inline void reset_hung_task_detector(void)
 #define NMI_WATCHDOG_ENABLED      (1 << NMI_WATCHDOG_ENABLED_BIT)
 #define SOFT_WATCHDOG_ENABLED     (1 << SOFT_WATCHDOG_ENABLED_BIT)
 
+#if defined(CONFIG_HARDLOCKUP_DETECTOR)
+extern void hardlockup_detector_disable(void);
+#else
+static inline void hardlockup_detector_disable(void) {}
+#endif
+
+#if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HAVE_NMI_WATCHDOG)
+extern void arch_touch_nmi_watchdog(void);
+#else
+static inline void arch_touch_nmi_watchdog(void) {}
+#endif
+
 /**
  * touch_nmi_watchdog - restart NMI watchdog timeout.
  * 
@@ -65,21 +80,11 @@ static inline void reset_hung_task_detector(void)
  * may be used to reset the timeout - for code which intentionally
  * disables interrupts for a long time. This call is stateless.
  */
-#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR)
-#include <asm/nmi.h>
-extern void touch_nmi_watchdog(void);
-#else
 static inline void touch_nmi_watchdog(void)
 {
+	arch_touch_nmi_watchdog();
 	touch_softlockup_watchdog();
 }
-#endif
-
-#if defined(CONFIG_HARDLOCKUP_DETECTOR)
-extern void hardlockup_detector_disable(void);
-#else
-static inline void hardlockup_detector_disable(void) {}
-#endif
 
 /*
  * Create trigger_all_cpu_backtrace() out of the arch-provided
diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c
index 54a427d1f344..90d688df6ce1 100644
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -56,7 +56,7 @@ static int __init hardlockup_panic_setup(char *str)
 }
 __setup("nmi_watchdog=", hardlockup_panic_setup);
 
-void touch_nmi_watchdog(void)
+void arch_touch_nmi_watchdog(void)
 {
 	/*
 	 * Using __raw here because some code paths have
@@ -66,9 +66,8 @@ void touch_nmi_watchdog(void)
 	 * going off.
 	 */
 	raw_cpu_write(watchdog_nmi_touch, true);
-	touch_softlockup_watchdog();
 }
-EXPORT_SYMBOL(touch_nmi_watchdog);
+EXPORT_SYMBOL(arch_touch_nmi_watchdog);
 
 static struct perf_event_attr wd_hw_attr = {
 	.type		= PERF_TYPE_HARDWARE,
-- 
cgit v1.2.3


From 05a4a95279311c3a4633b4277a5d21cfd616c6c7 Mon Sep 17 00:00:00 2001
From: Nicholas Piggin <npiggin@gmail.com>
Date: Wed, 12 Jul 2017 14:35:46 -0700
Subject: kernel/watchdog: split up config options

Split SOFTLOCKUP_DETECTOR from LOCKUP_DETECTOR, and split
HARDLOCKUP_DETECTOR_PERF from HARDLOCKUP_DETECTOR.

LOCKUP_DETECTOR implies the general boot, sysctl, and programming
interfaces for the lockup detectors.

An architecture that wants to use a hard lockup detector must define
HAVE_HARDLOCKUP_DETECTOR_PERF or HAVE_HARDLOCKUP_DETECTOR_ARCH.

Alternatively an arch can define HAVE_NMI_WATCHDOG, which provides the
minimum arch_touch_nmi_watchdog, and it otherwise does its own thing and
does not implement the LOCKUP_DETECTOR interfaces.

sparc is unusual in that it has started to implement some of the
interfaces, but not fully yet.  It should probably be converted to a full
HAVE_HARDLOCKUP_DETECTOR_ARCH.

[npiggin@gmail.com: fix]
  Link: http://lkml.kernel.org/r/20170617223522.66c0ad88@roar.ozlabs.ibm.com
Link: http://lkml.kernel.org/r/20170616065715.18390-4-npiggin@gmail.com
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Reviewed-by: Don Zickus <dzickus@redhat.com>
Reviewed-by: Babu Moger <babu.moger@oracle.com>
Tested-by: Babu Moger <babu.moger@oracle.com>	[sparc]
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/Kconfig                   |  25 ++++-
 arch/powerpc/Kconfig           |   1 +
 arch/powerpc/kernel/setup_64.c |   2 +-
 arch/x86/Kconfig               |   1 +
 arch/x86/kernel/apic/hw_nmi.c  |   2 +-
 include/linux/nmi.h            |  29 +++--
 kernel/Makefile                |   2 +-
 kernel/sysctl.c                |  31 +++---
 kernel/watchdog.c              | 243 +++++++++++++++++++++++++++--------------
 kernel/watchdog_hld.c          |  32 ------
 lib/Kconfig.debug              |  45 +++++---
 11 files changed, 251 insertions(+), 162 deletions(-)

(limited to 'include')

diff --git a/arch/Kconfig b/arch/Kconfig
index cae0958a2298..fb9bd7d36b05 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -198,9 +198,6 @@ config HAVE_KPROBES_ON_FTRACE
 config HAVE_NMI
 	bool
 
-config HAVE_NMI_WATCHDOG
-	depends on HAVE_NMI
-	bool
 #
 # An arch should select this if it provides all these things:
 #
@@ -288,6 +285,28 @@ config HAVE_PERF_EVENTS_NMI
 	  subsystem.  Also has support for calculating CPU cycle events
 	  to determine how many clock cycles in a given period.
 
+config HAVE_HARDLOCKUP_DETECTOR_PERF
+	bool
+	depends on HAVE_PERF_EVENTS_NMI
+	help
+	  The arch chooses to use the generic perf-NMI-based hardlockup
+	  detector. Must define HAVE_PERF_EVENTS_NMI.
+
+config HAVE_NMI_WATCHDOG
+	depends on HAVE_NMI
+	bool
+	help
+	  The arch provides a low level NMI watchdog. It provides
+	  asm/nmi.h, and defines its own arch_touch_nmi_watchdog().
+
+config HAVE_HARDLOCKUP_DETECTOR_ARCH
+	bool
+	select HAVE_NMI_WATCHDOG
+	help
+	  The arch chooses to provide its own hardlockup detector, which is
+	  a superset of the HAVE_NMI_WATCHDOG. It also conforms to config
+	  interfaces and parameters provided by hardlockup detector subsystem.
+
 config HAVE_PERF_REGS
 	bool
 	help
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 7177a3f4f418..63ed758e1d20 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -197,6 +197,7 @@ config PPC
 	select HAVE_OPTPROBES			if PPC64
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_EVENTS_NMI		if PPC64
+	select HAVE_HARDLOCKUP_DETECTOR_PERF	if HAVE_PERF_EVENTS_NMI
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_RCU_TABLE_FREE		if SMP
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 4640f6d64f8b..074a075a9cdb 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -752,7 +752,7 @@ struct ppc_pci_io ppc_pci_io;
 EXPORT_SYMBOL(ppc_pci_io);
 #endif
 
-#ifdef CONFIG_HARDLOCKUP_DETECTOR
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF
 u64 hw_nmi_get_sample_period(int watchdog_thresh)
 {
 	return ppc_proc_freq * watchdog_thresh;
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 94a18681353d..3d2b8ce54e00 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -162,6 +162,7 @@ config X86
 	select HAVE_PCSPKR_PLATFORM
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_EVENTS_NMI
+	select HAVE_HARDLOCKUP_DETECTOR_PERF	if HAVE_PERF_EVENTS_NMI
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_REGS_AND_STACK_ACCESS_API
diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index c73c9fb281e1..d6f387780849 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -19,7 +19,7 @@
 #include <linux/init.h>
 #include <linux/delay.h>
 
-#ifdef CONFIG_HARDLOCKUP_DETECTOR
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF
 u64 hw_nmi_get_sample_period(int watchdog_thresh)
 {
 	return (u64)(cpu_khz) * 1000 * watchdog_thresh;
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index bd387ef8bccd..8aa01fd859fb 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -11,13 +11,21 @@
 #endif
 
 #ifdef CONFIG_LOCKUP_DETECTOR
+void lockup_detector_init(void);
+#else
+static inline void lockup_detector_init(void)
+{
+}
+#endif
+
+#ifdef CONFIG_SOFTLOCKUP_DETECTOR
 extern void touch_softlockup_watchdog_sched(void);
 extern void touch_softlockup_watchdog(void);
 extern void touch_softlockup_watchdog_sync(void);
 extern void touch_all_softlockup_watchdogs(void);
 extern unsigned int  softlockup_panic;
-extern unsigned int  hardlockup_panic;
-void lockup_detector_init(void);
+extern int soft_watchdog_enabled;
+extern atomic_t watchdog_park_in_progress;
 #else
 static inline void touch_softlockup_watchdog_sched(void)
 {
@@ -31,9 +39,6 @@ static inline void touch_softlockup_watchdog_sync(void)
 static inline void touch_all_softlockup_watchdogs(void)
 {
 }
-static inline void lockup_detector_init(void)
-{
-}
 #endif
 
 #ifdef CONFIG_DETECT_HUNG_TASK
@@ -63,15 +68,18 @@ static inline void reset_hung_task_detector(void)
 
 #if defined(CONFIG_HARDLOCKUP_DETECTOR)
 extern void hardlockup_detector_disable(void);
+extern unsigned int hardlockup_panic;
 #else
 static inline void hardlockup_detector_disable(void) {}
 #endif
 
-#if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HAVE_NMI_WATCHDOG)
+#if defined(CONFIG_HARDLOCKUP_DETECTOR_PERF)
 extern void arch_touch_nmi_watchdog(void);
 #else
+#if !defined(CONFIG_HAVE_NMI_WATCHDOG)
 static inline void arch_touch_nmi_watchdog(void) {}
 #endif
+#endif
 
 /**
  * touch_nmi_watchdog - restart NMI watchdog timeout.
@@ -141,15 +149,18 @@ static inline bool trigger_single_cpu_backtrace(int cpu)
 }
 #endif
 
-#ifdef CONFIG_LOCKUP_DETECTOR
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF
 u64 hw_nmi_get_sample_period(int watchdog_thresh);
+#endif
+
+#ifdef CONFIG_LOCKUP_DETECTOR
 extern int nmi_watchdog_enabled;
-extern int soft_watchdog_enabled;
 extern int watchdog_user_enabled;
 extern int watchdog_thresh;
 extern unsigned long watchdog_enabled;
+extern struct cpumask watchdog_cpumask;
 extern unsigned long *watchdog_cpumask_bits;
-extern atomic_t watchdog_park_in_progress;
+extern int __read_mostly watchdog_suspended;
 #ifdef CONFIG_SMP
 extern int sysctl_softlockup_all_cpu_backtrace;
 extern int sysctl_hardlockup_all_cpu_backtrace;
diff --git a/kernel/Makefile b/kernel/Makefile
index 72aa080f91f0..4cb8e8b23c6e 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -82,7 +82,7 @@ obj-$(CONFIG_KPROBES) += kprobes.o
 obj-$(CONFIG_KGDB) += debug/
 obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o
 obj-$(CONFIG_LOCKUP_DETECTOR) += watchdog.o
-obj-$(CONFIG_HARDLOCKUP_DETECTOR) += watchdog_hld.o
+obj-$(CONFIG_HARDLOCKUP_DETECTOR_PERF) += watchdog_hld.o
 obj-$(CONFIG_SECCOMP) += seccomp.o
 obj-$(CONFIG_RELAY) += relay.o
 obj-$(CONFIG_SYSCTL) += utsname_sysctl.o
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index df9f2a367882..6648fbbb8157 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -900,6 +900,14 @@ static struct ctl_table kern_table[] = {
 		.extra2		= &zero,
 #endif
 	},
+	{
+		.procname	= "watchdog_cpumask",
+		.data		= &watchdog_cpumask_bits,
+		.maxlen		= NR_CPUS,
+		.mode		= 0644,
+		.proc_handler	= proc_watchdog_cpumask,
+	},
+#ifdef CONFIG_SOFTLOCKUP_DETECTOR
 	{
 		.procname       = "soft_watchdog",
 		.data           = &soft_watchdog_enabled,
@@ -909,13 +917,6 @@ static struct ctl_table kern_table[] = {
 		.extra1		= &zero,
 		.extra2		= &one,
 	},
-	{
-		.procname	= "watchdog_cpumask",
-		.data		= &watchdog_cpumask_bits,
-		.maxlen		= NR_CPUS,
-		.mode		= 0644,
-		.proc_handler	= proc_watchdog_cpumask,
-	},
 	{
 		.procname	= "softlockup_panic",
 		.data		= &softlockup_panic,
@@ -925,27 +926,29 @@ static struct ctl_table kern_table[] = {
 		.extra1		= &zero,
 		.extra2		= &one,
 	},
-#ifdef CONFIG_HARDLOCKUP_DETECTOR
+#ifdef CONFIG_SMP
 	{
-		.procname	= "hardlockup_panic",
-		.data		= &hardlockup_panic,
+		.procname	= "softlockup_all_cpu_backtrace",
+		.data		= &sysctl_softlockup_all_cpu_backtrace,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &zero,
 		.extra2		= &one,
 	},
+#endif /* CONFIG_SMP */
 #endif
-#ifdef CONFIG_SMP
+#ifdef CONFIG_HARDLOCKUP_DETECTOR
 	{
-		.procname	= "softlockup_all_cpu_backtrace",
-		.data		= &sysctl_softlockup_all_cpu_backtrace,
+		.procname	= "hardlockup_panic",
+		.data		= &hardlockup_panic,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &zero,
 		.extra2		= &one,
 	},
+#ifdef CONFIG_SMP
 	{
 		.procname	= "hardlockup_all_cpu_backtrace",
 		.data		= &sysctl_hardlockup_all_cpu_backtrace,
@@ -957,6 +960,8 @@ static struct ctl_table kern_table[] = {
 	},
 #endif /* CONFIG_SMP */
 #endif
+#endif
+
 #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86)
 	{
 		.procname       = "unknown_nmi_panic",
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 03e0b69bb5bf..1fba9c3d66dc 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -29,15 +29,58 @@
 #include <linux/kvm_para.h>
 #include <linux/kthread.h>
 
+/* Watchdog configuration */
 static DEFINE_MUTEX(watchdog_proc_mutex);
 
-#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR)
-unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED|NMI_WATCHDOG_ENABLED;
+int __read_mostly nmi_watchdog_enabled;
+
+#if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HAVE_NMI_WATCHDOG)
+unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED |
+						NMI_WATCHDOG_ENABLED;
 #else
 unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED;
 #endif
-int __read_mostly nmi_watchdog_enabled;
+
+#ifdef CONFIG_HARDLOCKUP_DETECTOR
+/* boot commands */
+/*
+ * Should we panic when a soft-lockup or hard-lockup occurs:
+ */
+unsigned int __read_mostly hardlockup_panic =
+			CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE;
+/*
+ * We may not want to enable hard lockup detection by default in all cases,
+ * for example when running the kernel as a guest on a hypervisor. In these
+ * cases this function can be called to disable hard lockup detection. This
+ * function should only be executed once by the boot processor before the
+ * kernel command line parameters are parsed, because otherwise it is not
+ * possible to override this in hardlockup_panic_setup().
+ */
+void hardlockup_detector_disable(void)
+{
+	watchdog_enabled &= ~NMI_WATCHDOG_ENABLED;
+}
+
+static int __init hardlockup_panic_setup(char *str)
+{
+	if (!strncmp(str, "panic", 5))
+		hardlockup_panic = 1;
+	else if (!strncmp(str, "nopanic", 7))
+		hardlockup_panic = 0;
+	else if (!strncmp(str, "0", 1))
+		watchdog_enabled &= ~NMI_WATCHDOG_ENABLED;
+	else if (!strncmp(str, "1", 1))
+		watchdog_enabled |= NMI_WATCHDOG_ENABLED;
+	return 1;
+}
+__setup("nmi_watchdog=", hardlockup_panic_setup);
+
+#endif
+
+#ifdef CONFIG_SOFTLOCKUP_DETECTOR
 int __read_mostly soft_watchdog_enabled;
+#endif
+
 int __read_mostly watchdog_user_enabled;
 int __read_mostly watchdog_thresh = 10;
 
@@ -45,15 +88,9 @@ int __read_mostly watchdog_thresh = 10;
 int __read_mostly sysctl_softlockup_all_cpu_backtrace;
 int __read_mostly sysctl_hardlockup_all_cpu_backtrace;
 #endif
-static struct cpumask watchdog_cpumask __read_mostly;
+struct cpumask watchdog_cpumask __read_mostly;
 unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
 
-/* Helper for online, unparked cpus. */
-#define for_each_watchdog_cpu(cpu) \
-	for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask)
-
-atomic_t watchdog_park_in_progress = ATOMIC_INIT(0);
-
 /*
  * The 'watchdog_running' variable is set to 1 when the watchdog threads
  * are registered/started and is set to 0 when the watchdog threads are
@@ -72,7 +109,27 @@ static int __read_mostly watchdog_running;
  * of 'watchdog_running' cannot change while the watchdog is deactivated
  * temporarily (see related code in 'proc' handlers).
  */
-static int __read_mostly watchdog_suspended;
+int __read_mostly watchdog_suspended;
+
+/*
+ * These functions can be overridden if an architecture implements its
+ * own hardlockup detector.
+ */
+int __weak watchdog_nmi_enable(unsigned int cpu)
+{
+	return 0;
+}
+void __weak watchdog_nmi_disable(unsigned int cpu)
+{
+}
+
+#ifdef CONFIG_SOFTLOCKUP_DETECTOR
+
+/* Helper for online, unparked cpus. */
+#define for_each_watchdog_cpu(cpu) \
+	for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask)
+
+atomic_t watchdog_park_in_progress = ATOMIC_INIT(0);
 
 static u64 __read_mostly sample_period;
 
@@ -120,6 +177,7 @@ static int __init softlockup_all_cpu_backtrace_setup(char *str)
 	return 1;
 }
 __setup("softlockup_all_cpu_backtrace=", softlockup_all_cpu_backtrace_setup);
+#ifdef CONFIG_HARDLOCKUP_DETECTOR
 static int __init hardlockup_all_cpu_backtrace_setup(char *str)
 {
 	sysctl_hardlockup_all_cpu_backtrace =
@@ -128,6 +186,7 @@ static int __init hardlockup_all_cpu_backtrace_setup(char *str)
 }
 __setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup);
 #endif
+#endif
 
 /*
  * Hard-lockup warnings should be triggered after just a few seconds. Soft-
@@ -213,18 +272,6 @@ void touch_softlockup_watchdog_sync(void)
 	__this_cpu_write(watchdog_touch_ts, 0);
 }
 
-/* watchdog detector functions */
-bool is_hardlockup(void)
-{
-	unsigned long hrint = __this_cpu_read(hrtimer_interrupts);
-
-	if (__this_cpu_read(hrtimer_interrupts_saved) == hrint)
-		return true;
-
-	__this_cpu_write(hrtimer_interrupts_saved, hrint);
-	return false;
-}
-
 static int is_softlockup(unsigned long touch_ts)
 {
 	unsigned long now = get_timestamp();
@@ -237,21 +284,21 @@ static int is_softlockup(unsigned long touch_ts)
 	return 0;
 }
 
-static void watchdog_interrupt_count(void)
+/* watchdog detector functions */
+bool is_hardlockup(void)
 {
-	__this_cpu_inc(hrtimer_interrupts);
-}
+	unsigned long hrint = __this_cpu_read(hrtimer_interrupts);
 
-/*
- * These two functions are mostly architecture specific
- * defining them as weak here.
- */
-int __weak watchdog_nmi_enable(unsigned int cpu)
-{
-	return 0;
+	if (__this_cpu_read(hrtimer_interrupts_saved) == hrint)
+		return true;
+
+	__this_cpu_write(hrtimer_interrupts_saved, hrint);
+	return false;
 }
-void __weak watchdog_nmi_disable(unsigned int cpu)
+
+static void watchdog_interrupt_count(void)
 {
+	__this_cpu_inc(hrtimer_interrupts);
 }
 
 static int watchdog_enable_all_cpus(void);
@@ -502,57 +549,6 @@ static void watchdog_unpark_threads(void)
 		kthread_unpark(per_cpu(softlockup_watchdog, cpu));
 }
 
-/*
- * Suspend the hard and soft lockup detector by parking the watchdog threads.
- */
-int lockup_detector_suspend(void)
-{
-	int ret = 0;
-
-	get_online_cpus();
-	mutex_lock(&watchdog_proc_mutex);
-	/*
-	 * Multiple suspend requests can be active in parallel (counted by
-	 * the 'watchdog_suspended' variable). If the watchdog threads are
-	 * running, the first caller takes care that they will be parked.
-	 * The state of 'watchdog_running' cannot change while a suspend
-	 * request is active (see related code in 'proc' handlers).
-	 */
-	if (watchdog_running && !watchdog_suspended)
-		ret = watchdog_park_threads();
-
-	if (ret == 0)
-		watchdog_suspended++;
-	else {
-		watchdog_disable_all_cpus();
-		pr_err("Failed to suspend lockup detectors, disabled\n");
-		watchdog_enabled = 0;
-	}
-
-	mutex_unlock(&watchdog_proc_mutex);
-
-	return ret;
-}
-
-/*
- * Resume the hard and soft lockup detector by unparking the watchdog threads.
- */
-void lockup_detector_resume(void)
-{
-	mutex_lock(&watchdog_proc_mutex);
-
-	watchdog_suspended--;
-	/*
-	 * The watchdog threads are unparked if they were previously running
-	 * and if there is no more active suspend request.
-	 */
-	if (watchdog_running && !watchdog_suspended)
-		watchdog_unpark_threads();
-
-	mutex_unlock(&watchdog_proc_mutex);
-	put_online_cpus();
-}
-
 static int update_watchdog_all_cpus(void)
 {
 	int ret;
@@ -604,6 +600,81 @@ static void watchdog_disable_all_cpus(void)
 	}
 }
 
+#else /* SOFTLOCKUP */
+static int watchdog_park_threads(void)
+{
+	return 0;
+}
+
+static void watchdog_unpark_threads(void)
+{
+}
+
+static int watchdog_enable_all_cpus(void)
+{
+	return 0;
+}
+
+static void watchdog_disable_all_cpus(void)
+{
+}
+
+static void set_sample_period(void)
+{
+}
+#endif /* SOFTLOCKUP */
+
+/*
+ * Suspend the hard and soft lockup detector by parking the watchdog threads.
+ */
+int lockup_detector_suspend(void)
+{
+	int ret = 0;
+
+	get_online_cpus();
+	mutex_lock(&watchdog_proc_mutex);
+	/*
+	 * Multiple suspend requests can be active in parallel (counted by
+	 * the 'watchdog_suspended' variable). If the watchdog threads are
+	 * running, the first caller takes care that they will be parked.
+	 * The state of 'watchdog_running' cannot change while a suspend
+	 * request is active (see related code in 'proc' handlers).
+	 */
+	if (watchdog_running && !watchdog_suspended)
+		ret = watchdog_park_threads();
+
+	if (ret == 0)
+		watchdog_suspended++;
+	else {
+		watchdog_disable_all_cpus();
+		pr_err("Failed to suspend lockup detectors, disabled\n");
+		watchdog_enabled = 0;
+	}
+
+	mutex_unlock(&watchdog_proc_mutex);
+
+	return ret;
+}
+
+/*
+ * Resume the hard and soft lockup detector by unparking the watchdog threads.
+ */
+void lockup_detector_resume(void)
+{
+	mutex_lock(&watchdog_proc_mutex);
+
+	watchdog_suspended--;
+	/*
+	 * The watchdog threads are unparked if they were previously running
+	 * and if there is no more active suspend request.
+	 */
+	if (watchdog_running && !watchdog_suspended)
+		watchdog_unpark_threads();
+
+	mutex_unlock(&watchdog_proc_mutex);
+	put_online_cpus();
+}
+
 #ifdef CONFIG_SYSCTL
 
 /*
@@ -810,9 +881,11 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write,
 			 * a temporary cpumask, so we are likely not in a
 			 * position to do much else to make things better.
 			 */
+#ifdef CONFIG_SOFTLOCKUP_DETECTOR
 			if (smpboot_update_cpumask_percpu_thread(
 				    &watchdog_threads, &watchdog_cpumask) != 0)
 				pr_err("cpumask update failed\n");
+#endif
 		}
 	}
 out:
diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c
index 90d688df6ce1..295a0d84934c 100644
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -22,39 +22,7 @@ static DEFINE_PER_CPU(bool, hard_watchdog_warn);
 static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
 static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
 
-/* boot commands */
-/*
- * Should we panic when a soft-lockup or hard-lockup occurs:
- */
-unsigned int __read_mostly hardlockup_panic =
-			CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE;
 static unsigned long hardlockup_allcpu_dumped;
-/*
- * We may not want to enable hard lockup detection by default in all cases,
- * for example when running the kernel as a guest on a hypervisor. In these
- * cases this function can be called to disable hard lockup detection. This
- * function should only be executed once by the boot processor before the
- * kernel command line parameters are parsed, because otherwise it is not
- * possible to override this in hardlockup_panic_setup().
- */
-void hardlockup_detector_disable(void)
-{
-	watchdog_enabled &= ~NMI_WATCHDOG_ENABLED;
-}
-
-static int __init hardlockup_panic_setup(char *str)
-{
-	if (!strncmp(str, "panic", 5))
-		hardlockup_panic = 1;
-	else if (!strncmp(str, "nopanic", 7))
-		hardlockup_panic = 0;
-	else if (!strncmp(str, "0", 1))
-		watchdog_enabled &= ~NMI_WATCHDOG_ENABLED;
-	else if (!strncmp(str, "1", 1))
-		watchdog_enabled |= NMI_WATCHDOG_ENABLED;
-	return 1;
-}
-__setup("nmi_watchdog=", hardlockup_panic_setup);
 
 void arch_touch_nmi_watchdog(void)
 {
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index f28f4252e54a..b0d01c6d4e03 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -778,34 +778,45 @@ config DEBUG_SHIRQ
 menu "Debug Lockups and Hangs"
 
 config LOCKUP_DETECTOR
-	bool "Detect Hard and Soft Lockups"
+	bool
+
+config SOFTLOCKUP_DETECTOR
+	bool "Detect Soft Lockups"
 	depends on DEBUG_KERNEL && !S390
+	select LOCKUP_DETECTOR
 	help
 	  Say Y here to enable the kernel to act as a watchdog to detect
-	  hard and soft lockups.
+	  soft lockups.
 
 	  Softlockups are bugs that cause the kernel to loop in kernel
 	  mode for more than 20 seconds, without giving other tasks a
 	  chance to run.  The current stack trace is displayed upon
 	  detection and the system will stay locked up.
 
+config HARDLOCKUP_DETECTOR_PERF
+	bool
+	select SOFTLOCKUP_DETECTOR
+
+#
+# arch/ can define HAVE_HARDLOCKUP_DETECTOR_ARCH to provide their own hard
+# lockup detector rather than the perf based detector.
+#
+config HARDLOCKUP_DETECTOR
+	bool "Detect Hard Lockups"
+	depends on DEBUG_KERNEL && !S390
+	depends on HAVE_HARDLOCKUP_DETECTOR_PERF || HAVE_HARDLOCKUP_DETECTOR_ARCH
+	select LOCKUP_DETECTOR
+	select HARDLOCKUP_DETECTOR_PERF if HAVE_HARDLOCKUP_DETECTOR_PERF
+	select HARDLOCKUP_DETECTOR_ARCH if HAVE_HARDLOCKUP_DETECTOR_ARCH
+	help
+	  Say Y here to enable the kernel to act as a watchdog to detect
+	  hard lockups.
+
 	  Hardlockups are bugs that cause the CPU to loop in kernel mode
 	  for more than 10 seconds, without letting other interrupts have a
 	  chance to run.  The current stack trace is displayed upon detection
 	  and the system will stay locked up.
 
-	  The overhead should be minimal.  A periodic hrtimer runs to
-	  generate interrupts and kick the watchdog task every 4 seconds.
-	  An NMI is generated every 10 seconds or so to check for hardlockups.
-
-	  The frequency of hrtimer and NMI events and the soft and hard lockup
-	  thresholds can be controlled through the sysctl watchdog_thresh.
-
-config HARDLOCKUP_DETECTOR
-	def_bool y
-	depends on LOCKUP_DETECTOR && !HAVE_NMI_WATCHDOG
-	depends on PERF_EVENTS && HAVE_PERF_EVENTS_NMI
-
 config BOOTPARAM_HARDLOCKUP_PANIC
 	bool "Panic (Reboot) On Hard Lockups"
 	depends on HARDLOCKUP_DETECTOR
@@ -826,7 +837,7 @@ config BOOTPARAM_HARDLOCKUP_PANIC_VALUE
 
 config BOOTPARAM_SOFTLOCKUP_PANIC
 	bool "Panic (Reboot) On Soft Lockups"
-	depends on LOCKUP_DETECTOR
+	depends on SOFTLOCKUP_DETECTOR
 	help
 	  Say Y here to enable the kernel to panic on "soft lockups",
 	  which are bugs that cause the kernel to loop in kernel
@@ -843,7 +854,7 @@ config BOOTPARAM_SOFTLOCKUP_PANIC
 
 config BOOTPARAM_SOFTLOCKUP_PANIC_VALUE
 	int
-	depends on LOCKUP_DETECTOR
+	depends on SOFTLOCKUP_DETECTOR
 	range 0 1
 	default 0 if !BOOTPARAM_SOFTLOCKUP_PANIC
 	default 1 if BOOTPARAM_SOFTLOCKUP_PANIC
@@ -851,7 +862,7 @@ config BOOTPARAM_SOFTLOCKUP_PANIC_VALUE
 config DETECT_HUNG_TASK
 	bool "Detect Hung Tasks"
 	depends on DEBUG_KERNEL
-	default LOCKUP_DETECTOR
+	default SOFTLOCKUP_DETECTOR
 	help
 	  Say Y here to enable the kernel to detect "hung tasks",
 	  which are bugs that cause the task to be stuck in
-- 
cgit v1.2.3


From 6974f0c4555e285ab217cee58b6e874f776ff409 Mon Sep 17 00:00:00 2001
From: Daniel Micay <danielmicay@gmail.com>
Date: Wed, 12 Jul 2017 14:36:10 -0700
Subject: include/linux/string.h: add the option of fortified string.h
 functions

This adds support for compiling with a rough equivalent to the glibc
_FORTIFY_SOURCE=1 feature, providing compile-time and runtime buffer
overflow checks for string.h functions when the compiler determines the
size of the source or destination buffer at compile-time.  Unlike glibc,
it covers buffer reads in addition to writes.

GNU C __builtin_*_chk intrinsics are avoided because they would force a
much more complex implementation.  They aren't designed to detect read
overflows and offer no real benefit when using an implementation based
on inline checks.  Inline checks don't add up to much code size and
allow full use of the regular string intrinsics while avoiding the need
for a bunch of _chk functions and per-arch assembly to avoid wrapper
overhead.

This detects various overflows at compile-time in various drivers and
some non-x86 core kernel code.  There will likely be issues caught in
regular use at runtime too.

Future improvements left out of initial implementation for simplicity,
as it's all quite optional and can be done incrementally:

* Some of the fortified string functions (strncpy, strcat), don't yet
  place a limit on reads from the source based on __builtin_object_size of
  the source buffer.

* Extending coverage to more string functions like strlcat.

* It should be possible to optionally use __builtin_object_size(x, 1) for
  some functions (C strings) to detect intra-object overflows (like
  glibc's _FORTIFY_SOURCE=2), but for now this takes the conservative
  approach to avoid likely compatibility issues.

* The compile-time checks should be made available via a separate config
  option which can be enabled by default (or always enabled) once enough
  time has passed to get the issues it catches fixed.

Kees said:
 "This is great to have. While it was out-of-tree code, it would have
  blocked at least CVE-2016-3858 from being exploitable (improper size
  argument to strlcpy()). I've sent a number of fixes for
  out-of-bounds-reads that this detected upstream already"

[arnd@arndb.de: x86: fix fortified memcpy]
  Link: http://lkml.kernel.org/r/20170627150047.660360-1-arnd@arndb.de
[keescook@chromium.org: avoid panic() in favor of BUG()]
  Link: http://lkml.kernel.org/r/20170626235122.GA25261@beast
[keescook@chromium.org: move from -mm, add ARCH_HAS_FORTIFY_SOURCE, tweak Kconfig help]
Link: http://lkml.kernel.org/r/20170526095404.20439-1-danielmicay@gmail.com
Link: http://lkml.kernel.org/r/1497903987-21002-8-git-send-email-keescook@chromium.org
Signed-off-by: Daniel Micay <danielmicay@gmail.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Kees Cook <keescook@chromium.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Daniel Axtens <dja@axtens.net>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Chris Metcalf <cmetcalf@ezchip.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/Kconfig                     |   6 ++
 arch/arm64/Kconfig               |   1 +
 arch/arm64/include/asm/string.h  |   5 +
 arch/powerpc/Kconfig             |   1 +
 arch/x86/Kconfig                 |   1 +
 arch/x86/boot/compressed/misc.c  |   5 +
 arch/x86/include/asm/string_32.h |   9 ++
 arch/x86/include/asm/string_64.h |   7 ++
 arch/x86/lib/memcpy_32.c         |   2 +-
 include/linux/string.h           | 200 +++++++++++++++++++++++++++++++++++++++
 lib/string.c                     |   7 ++
 security/Kconfig                 |   7 ++
 12 files changed, 250 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/arch/Kconfig b/arch/Kconfig
index fb9bd7d36b05..21d0089117fe 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -223,6 +223,12 @@ config GENERIC_SMP_IDLE_THREAD
 config GENERIC_IDLE_POLL_SETUP
        bool
 
+config ARCH_HAS_FORTIFY_SOURCE
+	bool
+	help
+	  An architecture should select this when it can successfully
+	  build and run with CONFIG_FORTIFY_SOURCE.
+
 # Select if arch has all set_memory_ro/rw/x/nx() functions in asm/cacheflush.h
 config ARCH_HAS_SET_MEMORY
 	bool
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 8addb851ab5e..dfd908630631 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -12,6 +12,7 @@ config ARM64
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
 	select ARCH_HAS_ELF_RANDOMIZE
+	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
 	select ARCH_HAS_KCOV
diff --git a/arch/arm64/include/asm/string.h b/arch/arm64/include/asm/string.h
index 2eb714c4639f..d0aa42907569 100644
--- a/arch/arm64/include/asm/string.h
+++ b/arch/arm64/include/asm/string.h
@@ -63,6 +63,11 @@ extern int memcmp(const void *, const void *, size_t);
 #define memcpy(dst, src, len) __memcpy(dst, src, len)
 #define memmove(dst, src, len) __memmove(dst, src, len)
 #define memset(s, c, n) __memset(s, c, n)
+
+#ifndef __NO_FORTIFY
+#define __NO_FORTIFY /* FORTIFY_SOURCE uses __builtin_memcpy, etc. */
+#endif
+
 #endif
 
 #endif
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index fce2f4f20891..36f858c37ca7 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -125,6 +125,7 @@ config PPC
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_DMA_SET_COHERENT_MASK
 	select ARCH_HAS_ELF_RANDOMIZE
+	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_SCALED_CPUTIME		if VIRT_CPU_ACCOUNTING_NATIVE
 	select ARCH_HAS_SG_CHAIN
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 3d2b8ce54e00..781521b7cf9e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -50,6 +50,7 @@ config X86
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_FAST_MULTIPLIER
+	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_KCOV			if X86_64
 	select ARCH_HAS_MMIO_FLUSH
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 00241c815524..a0838ab929f2 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -411,3 +411,8 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
 	debug_putstr("done.\nBooting the kernel.\n");
 	return output;
 }
+
+void fortify_panic(const char *name)
+{
+	error("detected buffer overflow");
+}
diff --git a/arch/x86/include/asm/string_32.h b/arch/x86/include/asm/string_32.h
index 3d3e8353ee5c..e9ee84873de5 100644
--- a/arch/x86/include/asm/string_32.h
+++ b/arch/x86/include/asm/string_32.h
@@ -142,7 +142,9 @@ static __always_inline void *__constant_memcpy(void *to, const void *from,
 }
 
 #define __HAVE_ARCH_MEMCPY
+extern void *memcpy(void *, const void *, size_t);
 
+#ifndef CONFIG_FORTIFY_SOURCE
 #ifdef CONFIG_X86_USE_3DNOW
 
 #include <asm/mmx.h>
@@ -195,11 +197,15 @@ static inline void *__memcpy3d(void *to, const void *from, size_t len)
 #endif
 
 #endif
+#endif /* !CONFIG_FORTIFY_SOURCE */
 
 #define __HAVE_ARCH_MEMMOVE
 void *memmove(void *dest, const void *src, size_t n);
 
+extern int memcmp(const void *, const void *, size_t);
+#ifndef CONFIG_FORTIFY_SOURCE
 #define memcmp __builtin_memcmp
+#endif
 
 #define __HAVE_ARCH_MEMCHR
 extern void *memchr(const void *cs, int c, size_t count);
@@ -321,6 +327,8 @@ void *__constant_c_and_count_memset(void *s, unsigned long pattern,
 	 : __memset_generic((s), (c), (count)))
 
 #define __HAVE_ARCH_MEMSET
+extern void *memset(void *, int, size_t);
+#ifndef CONFIG_FORTIFY_SOURCE
 #if (__GNUC__ >= 4)
 #define memset(s, c, count) __builtin_memset(s, c, count)
 #else
@@ -330,6 +338,7 @@ void *__constant_c_and_count_memset(void *s, unsigned long pattern,
 				 (count))				\
 	 : __memset((s), (c), (count)))
 #endif
+#endif /* !CONFIG_FORTIFY_SOURCE */
 
 /*
  * find the first occurrence of byte 'c', or 1 past the area if none
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index 1f22bc277c45..2a8c822de1fc 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -31,6 +31,7 @@ static __always_inline void *__inline_memcpy(void *to, const void *from, size_t
 extern void *memcpy(void *to, const void *from, size_t len);
 extern void *__memcpy(void *to, const void *from, size_t len);
 
+#ifndef CONFIG_FORTIFY_SOURCE
 #ifndef CONFIG_KMEMCHECK
 #if (__GNUC__ == 4 && __GNUC_MINOR__ < 3) || __GNUC__ < 4
 #define memcpy(dst, src, len)					\
@@ -51,6 +52,7 @@ extern void *__memcpy(void *to, const void *from, size_t len);
  */
 #define memcpy(dst, src, len) __inline_memcpy((dst), (src), (len))
 #endif
+#endif /* !CONFIG_FORTIFY_SOURCE */
 
 #define __HAVE_ARCH_MEMSET
 void *memset(void *s, int c, size_t n);
@@ -77,6 +79,11 @@ int strcmp(const char *cs, const char *ct);
 #define memcpy(dst, src, len) __memcpy(dst, src, len)
 #define memmove(dst, src, len) __memmove(dst, src, len)
 #define memset(s, c, n) __memset(s, c, n)
+
+#ifndef __NO_FORTIFY
+#define __NO_FORTIFY /* FORTIFY_SOURCE uses __builtin_memcpy, etc. */
+#endif
+
 #endif
 
 #define __HAVE_ARCH_MEMCPY_MCSAFE 1
diff --git a/arch/x86/lib/memcpy_32.c b/arch/x86/lib/memcpy_32.c
index cad12634d6bd..2eab7d0bfedd 100644
--- a/arch/x86/lib/memcpy_32.c
+++ b/arch/x86/lib/memcpy_32.c
@@ -6,7 +6,7 @@
 
 __visible void *memcpy(void *to, const void *from, size_t n)
 {
-#ifdef CONFIG_X86_USE_3DNOW
+#if defined(CONFIG_X86_USE_3DNOW) && !defined(CONFIG_FORTIFY_SOURCE)
 	return __memcpy3d(to, from, n);
 #else
 	return __memcpy(to, from, n);
diff --git a/include/linux/string.h b/include/linux/string.h
index 7439d83eaa33..96f5a5fd0377 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -193,4 +193,204 @@ static inline const char *kbasename(const char *path)
 	return tail ? tail + 1 : path;
 }
 
+#define __FORTIFY_INLINE extern __always_inline __attribute__((gnu_inline))
+#define __RENAME(x) __asm__(#x)
+
+void fortify_panic(const char *name) __noreturn __cold;
+void __read_overflow(void) __compiletime_error("detected read beyond size of object passed as 1st parameter");
+void __read_overflow2(void) __compiletime_error("detected read beyond size of object passed as 2nd parameter");
+void __write_overflow(void) __compiletime_error("detected write beyond size of object passed as 1st parameter");
+
+#if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE)
+__FORTIFY_INLINE char *strcpy(char *p, const char *q)
+{
+	size_t p_size = __builtin_object_size(p, 0);
+	size_t q_size = __builtin_object_size(q, 0);
+	if (p_size == (size_t)-1 && q_size == (size_t)-1)
+		return __builtin_strcpy(p, q);
+	if (strscpy(p, q, p_size < q_size ? p_size : q_size) < 0)
+		fortify_panic(__func__);
+	return p;
+}
+
+__FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size)
+{
+	size_t p_size = __builtin_object_size(p, 0);
+	if (__builtin_constant_p(size) && p_size < size)
+		__write_overflow();
+	if (p_size < size)
+		fortify_panic(__func__);
+	return __builtin_strncpy(p, q, size);
+}
+
+__FORTIFY_INLINE char *strcat(char *p, const char *q)
+{
+	size_t p_size = __builtin_object_size(p, 0);
+	if (p_size == (size_t)-1)
+		return __builtin_strcat(p, q);
+	if (strlcat(p, q, p_size) >= p_size)
+		fortify_panic(__func__);
+	return p;
+}
+
+__FORTIFY_INLINE __kernel_size_t strlen(const char *p)
+{
+	__kernel_size_t ret;
+	size_t p_size = __builtin_object_size(p, 0);
+	if (p_size == (size_t)-1)
+		return __builtin_strlen(p);
+	ret = strnlen(p, p_size);
+	if (p_size <= ret)
+		fortify_panic(__func__);
+	return ret;
+}
+
+extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(strnlen);
+__FORTIFY_INLINE __kernel_size_t strnlen(const char *p, __kernel_size_t maxlen)
+{
+	size_t p_size = __builtin_object_size(p, 0);
+	__kernel_size_t ret = __real_strnlen(p, maxlen < p_size ? maxlen : p_size);
+	if (p_size <= ret && maxlen != ret)
+		fortify_panic(__func__);
+	return ret;
+}
+
+/* defined after fortified strlen to reuse it */
+extern size_t __real_strlcpy(char *, const char *, size_t) __RENAME(strlcpy);
+__FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size)
+{
+	size_t ret;
+	size_t p_size = __builtin_object_size(p, 0);
+	size_t q_size = __builtin_object_size(q, 0);
+	if (p_size == (size_t)-1 && q_size == (size_t)-1)
+		return __real_strlcpy(p, q, size);
+	ret = strlen(q);
+	if (size) {
+		size_t len = (ret >= size) ? size - 1 : ret;
+		if (__builtin_constant_p(len) && len >= p_size)
+			__write_overflow();
+		if (len >= p_size)
+			fortify_panic(__func__);
+		__builtin_memcpy(p, q, len);
+		p[len] = '\0';
+	}
+	return ret;
+}
+
+/* defined after fortified strlen and strnlen to reuse them */
+__FORTIFY_INLINE char *strncat(char *p, const char *q, __kernel_size_t count)
+{
+	size_t p_len, copy_len;
+	size_t p_size = __builtin_object_size(p, 0);
+	size_t q_size = __builtin_object_size(q, 0);
+	if (p_size == (size_t)-1 && q_size == (size_t)-1)
+		return __builtin_strncat(p, q, count);
+	p_len = strlen(p);
+	copy_len = strnlen(q, count);
+	if (p_size < p_len + copy_len + 1)
+		fortify_panic(__func__);
+	__builtin_memcpy(p + p_len, q, copy_len);
+	p[p_len + copy_len] = '\0';
+	return p;
+}
+
+__FORTIFY_INLINE void *memset(void *p, int c, __kernel_size_t size)
+{
+	size_t p_size = __builtin_object_size(p, 0);
+	if (__builtin_constant_p(size) && p_size < size)
+		__write_overflow();
+	if (p_size < size)
+		fortify_panic(__func__);
+	return __builtin_memset(p, c, size);
+}
+
+__FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size)
+{
+	size_t p_size = __builtin_object_size(p, 0);
+	size_t q_size = __builtin_object_size(q, 0);
+	if (__builtin_constant_p(size)) {
+		if (p_size < size)
+			__write_overflow();
+		if (q_size < size)
+			__read_overflow2();
+	}
+	if (p_size < size || q_size < size)
+		fortify_panic(__func__);
+	return __builtin_memcpy(p, q, size);
+}
+
+__FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size)
+{
+	size_t p_size = __builtin_object_size(p, 0);
+	size_t q_size = __builtin_object_size(q, 0);
+	if (__builtin_constant_p(size)) {
+		if (p_size < size)
+			__write_overflow();
+		if (q_size < size)
+			__read_overflow2();
+	}
+	if (p_size < size || q_size < size)
+		fortify_panic(__func__);
+	return __builtin_memmove(p, q, size);
+}
+
+extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan);
+__FORTIFY_INLINE void *memscan(void *p, int c, __kernel_size_t size)
+{
+	size_t p_size = __builtin_object_size(p, 0);
+	if (__builtin_constant_p(size) && p_size < size)
+		__read_overflow();
+	if (p_size < size)
+		fortify_panic(__func__);
+	return __real_memscan(p, c, size);
+}
+
+__FORTIFY_INLINE int memcmp(const void *p, const void *q, __kernel_size_t size)
+{
+	size_t p_size = __builtin_object_size(p, 0);
+	size_t q_size = __builtin_object_size(q, 0);
+	if (__builtin_constant_p(size)) {
+		if (p_size < size)
+			__read_overflow();
+		if (q_size < size)
+			__read_overflow2();
+	}
+	if (p_size < size || q_size < size)
+		fortify_panic(__func__);
+	return __builtin_memcmp(p, q, size);
+}
+
+__FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size)
+{
+	size_t p_size = __builtin_object_size(p, 0);
+	if (__builtin_constant_p(size) && p_size < size)
+		__read_overflow();
+	if (p_size < size)
+		fortify_panic(__func__);
+	return __builtin_memchr(p, c, size);
+}
+
+void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv);
+__FORTIFY_INLINE void *memchr_inv(const void *p, int c, size_t size)
+{
+	size_t p_size = __builtin_object_size(p, 0);
+	if (__builtin_constant_p(size) && p_size < size)
+		__read_overflow();
+	if (p_size < size)
+		fortify_panic(__func__);
+	return __real_memchr_inv(p, c, size);
+}
+
+extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup);
+__FORTIFY_INLINE void *kmemdup(const void *p, size_t size, gfp_t gfp)
+{
+	size_t p_size = __builtin_object_size(p, 0);
+	if (__builtin_constant_p(size) && p_size < size)
+		__read_overflow();
+	if (p_size < size)
+		fortify_panic(__func__);
+	return __real_kmemdup(p, size, gfp);
+}
+#endif
+
 #endif /* _LINUX_STRING_H_ */
diff --git a/lib/string.c b/lib/string.c
index 1c1fc9187b05..ebbb99c775bd 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -978,3 +978,10 @@ char *strreplace(char *s, char old, char new)
 	return s;
 }
 EXPORT_SYMBOL(strreplace);
+
+void fortify_panic(const char *name)
+{
+	pr_emerg("detected buffer overflow in %s\n", name);
+	BUG();
+}
+EXPORT_SYMBOL(fortify_panic);
diff --git a/security/Kconfig b/security/Kconfig
index d540bfe73190..e8e449444e65 100644
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -163,6 +163,13 @@ config HARDENED_USERCOPY_PAGESPAN
 	  been removed. This config is intended to be used only while
 	  trying to find such users.
 
+config FORTIFY_SOURCE
+	bool "Harden common str/mem functions against buffer overflows"
+	depends on ARCH_HAS_FORTIFY_SOURCE
+	help
+	  Detect overflows of buffers in common string and memory functions
+	  where the compiler can determine and validate the buffer sizes.
+
 config STATIC_USERMODEHELPER
 	bool "Force all usermode helper calls through a single binary"
 	help
-- 
cgit v1.2.3


From 022c204040f3fd22d6445bc35517786195b7ae80 Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@redhat.com>
Date: Wed, 12 Jul 2017 14:36:17 -0700
Subject: random,stackprotect: introduce get_random_canary function

Patch series "stackprotector: ascii armor the stack canary", v2.

Zero out the first byte of the stack canary value on 64 bit systems, in
order to mitigate unterminated C string overflows.

The null byte both prevents C string functions from reading the canary,
and from writing it if the canary value were guessed or obtained through
some other means.

Reducing the entropy by 8 bits is acceptable on 64-bit systems, which
will still have 56 bits of entropy left, but not on 32 bit systems, so
the "ascii armor" canary is only implemented on 64-bit systems.

Inspired by the "ascii armor" code in execshield and Daniel Micay's
linux-hardened tree.

Also see https://github.com/thestinger/linux-hardened/

This patch (of 5):

Introduce get_random_canary(), which provides a random unsigned long
canary value with the first byte zeroed out on 64 bit architectures, in
order to mitigate non-terminated C string overflows.

The null byte both prevents C string functions from reading the canary,
and from writing it if the canary value were guessed or obtained through
some other means.

Reducing the entropy by 8 bits is acceptable on 64-bit systems, which
will still have 56 bits of entropy left, but not on 32 bit systems, so
the "ascii armor" canary is only implemented on 64-bit systems.

Inspired by the "ascii armor" code in the old execshield patches, and
Daniel Micay's linux-hardened tree.

Link: http://lkml.kernel.org/r/20170524155751.424-2-riel@redhat.com
Signed-off-by: Rik van Riel <riel@redhat.com>
Acked-by: Kees Cook <keescook@chromium.org>
Cc: Daniel Micay <danielmicay@gmail.com>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/random.h | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

(limited to 'include')

diff --git a/include/linux/random.h b/include/linux/random.h
index ed5c3838780d..1fa0dc880bd7 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -57,6 +57,27 @@ static inline unsigned long get_random_long(void)
 #endif
 }
 
+/*
+ * On 64-bit architectures, protect against non-terminated C string overflows
+ * by zeroing out the first byte of the canary; this leaves 56 bits of entropy.
+ */
+#ifdef CONFIG_64BIT
+# ifdef __LITTLE_ENDIAN
+#  define CANARY_MASK 0xffffffffffffff00UL
+# else /* big endian, 64 bits: */
+#  define CANARY_MASK 0x00ffffffffffffffUL
+# endif
+#else /* 32 bits: */
+# define CANARY_MASK 0xffffffffUL
+#endif
+
+static inline unsigned long get_random_canary(void)
+{
+	unsigned long val = get_random_long();
+
+	return val & CANARY_MASK;
+}
+
 unsigned long randomize_page(unsigned long start, unsigned long range);
 
 u32 prandom_u32(void);
-- 
cgit v1.2.3


From dcda9b04713c3f6ff0875652924844fae28286ea Mon Sep 17 00:00:00 2001
From: Michal Hocko <mhocko@suse.com>
Date: Wed, 12 Jul 2017 14:36:45 -0700
Subject: mm, tree wide: replace __GFP_REPEAT by __GFP_RETRY_MAYFAIL with more
 useful semantic

__GFP_REPEAT was designed to allow retry-but-eventually-fail semantic to
the page allocator.  This has been true but only for allocations
requests larger than PAGE_ALLOC_COSTLY_ORDER.  It has been always
ignored for smaller sizes.  This is a bit unfortunate because there is
no way to express the same semantic for those requests and they are
considered too important to fail so they might end up looping in the
page allocator for ever, similarly to GFP_NOFAIL requests.

Now that the whole tree has been cleaned up and accidental or misled
usage of __GFP_REPEAT flag has been removed for !costly requests we can
give the original flag a better name and more importantly a more useful
semantic.  Let's rename it to __GFP_RETRY_MAYFAIL which tells the user
that the allocator would try really hard but there is no promise of a
success.  This will work independent of the order and overrides the
default allocator behavior.  Page allocator users have several levels of
guarantee vs.  cost options (take GFP_KERNEL as an example)

 - GFP_KERNEL & ~__GFP_RECLAIM - optimistic allocation without _any_
   attempt to free memory at all. The most light weight mode which even
   doesn't kick the background reclaim. Should be used carefully because
   it might deplete the memory and the next user might hit the more
   aggressive reclaim

 - GFP_KERNEL & ~__GFP_DIRECT_RECLAIM (or GFP_NOWAIT)- optimistic
   allocation without any attempt to free memory from the current
   context but can wake kswapd to reclaim memory if the zone is below
   the low watermark. Can be used from either atomic contexts or when
   the request is a performance optimization and there is another
   fallback for a slow path.

 - (GFP_KERNEL|__GFP_HIGH) & ~__GFP_DIRECT_RECLAIM (aka GFP_ATOMIC) -
   non sleeping allocation with an expensive fallback so it can access
   some portion of memory reserves. Usually used from interrupt/bh
   context with an expensive slow path fallback.

 - GFP_KERNEL - both background and direct reclaim are allowed and the
   _default_ page allocator behavior is used. That means that !costly
   allocation requests are basically nofail but there is no guarantee of
   that behavior so failures have to be checked properly by callers
   (e.g. OOM killer victim is allowed to fail currently).

 - GFP_KERNEL | __GFP_NORETRY - overrides the default allocator behavior
   and all allocation requests fail early rather than cause disruptive
   reclaim (one round of reclaim in this implementation). The OOM killer
   is not invoked.

 - GFP_KERNEL | __GFP_RETRY_MAYFAIL - overrides the default allocator
   behavior and all allocation requests try really hard. The request
   will fail if the reclaim cannot make any progress. The OOM killer
   won't be triggered.

 - GFP_KERNEL | __GFP_NOFAIL - overrides the default allocator behavior
   and all allocation requests will loop endlessly until they succeed.
   This might be really dangerous especially for larger orders.

Existing users of __GFP_REPEAT are changed to __GFP_RETRY_MAYFAIL
because they already had their semantic.  No new users are added.
__alloc_pages_slowpath is changed to bail out for __GFP_RETRY_MAYFAIL if
there is no progress and we have already passed the OOM point.

This means that all the reclaim opportunities have been exhausted except
the most disruptive one (the OOM killer) and a user defined fallback
behavior is more sensible than keep retrying in the page allocator.

[akpm@linux-foundation.org: fix arch/sparc/kernel/mdesc.c]
[mhocko@suse.com: semantic fix]
  Link: http://lkml.kernel.org/r/20170626123847.GM11534@dhcp22.suse.cz
[mhocko@kernel.org: address other thing spotted by Vlastimil]
  Link: http://lkml.kernel.org/r/20170626124233.GN11534@dhcp22.suse.cz
Link: http://lkml.kernel.org/r/20170623085345.11304-3-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Alex Belits <alex.belits@cavium.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Darrick J. Wong <darrick.wong@oracle.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: NeilBrown <neilb@suse.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/DMA-ISA-LPC.txt                |  2 +-
 arch/powerpc/include/asm/book3s/64/pgalloc.h |  2 +-
 arch/powerpc/kvm/book3s_64_mmu_hv.c          |  2 +-
 arch/sparc/kernel/mdesc.c                    |  2 +-
 drivers/mmc/host/wbsd.c                      |  2 +-
 drivers/s390/char/vmcp.c                     |  2 +-
 drivers/target/target_core_transport.c       |  2 +-
 drivers/vhost/net.c                          |  2 +-
 drivers/vhost/scsi.c                         |  2 +-
 drivers/vhost/vsock.c                        |  2 +-
 include/linux/gfp.h                          | 56 +++++++++++++++++++++-------
 include/linux/slab.h                         |  3 +-
 include/trace/events/mmflags.h               |  2 +-
 mm/hugetlb.c                                 |  4 +-
 mm/internal.h                                |  2 +-
 mm/page_alloc.c                              | 14 +++++--
 mm/sparse-vmemmap.c                          |  4 +-
 mm/util.c                                    |  6 +--
 mm/vmalloc.c                                 |  2 +-
 mm/vmscan.c                                  |  8 ++--
 net/core/dev.c                               |  6 +--
 net/core/skbuff.c                            |  2 +-
 net/sched/sch_fq.c                           |  2 +-
 tools/perf/builtin-kmem.c                    |  2 +-
 24 files changed, 86 insertions(+), 47 deletions(-)

(limited to 'include')

diff --git a/Documentation/DMA-ISA-LPC.txt b/Documentation/DMA-ISA-LPC.txt
index c41331398752..7a065ac4a9d1 100644
--- a/Documentation/DMA-ISA-LPC.txt
+++ b/Documentation/DMA-ISA-LPC.txt
@@ -42,7 +42,7 @@ requirements you pass the flag GFP_DMA to kmalloc.
 
 Unfortunately the memory available for ISA DMA is scarce so unless you
 allocate the memory during boot-up it's a good idea to also pass
-__GFP_REPEAT and __GFP_NOWARN to make the allocator try a bit harder.
+__GFP_RETRY_MAYFAIL and __GFP_NOWARN to make the allocator try a bit harder.
 
 (This scarcity also means that you should allocate the buffer as
 early as possible and not release it until the driver is unloaded.)
diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h
index 20b1485ff1e8..e2329db9d6f4 100644
--- a/arch/powerpc/include/asm/book3s/64/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h
@@ -56,7 +56,7 @@ static inline pgd_t *radix__pgd_alloc(struct mm_struct *mm)
 	return (pgd_t *)__get_free_page(pgtable_gfp_flags(mm, PGALLOC_GFP));
 #else
 	struct page *page;
-	page = alloc_pages(pgtable_gfp_flags(mm, PGALLOC_GFP | __GFP_REPEAT),
+	page = alloc_pages(pgtable_gfp_flags(mm, PGALLOC_GFP | __GFP_RETRY_MAYFAIL),
 				4);
 	if (!page)
 		return NULL;
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 710e491206ed..8cb0190e2a73 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -93,7 +93,7 @@ int kvmppc_allocate_hpt(struct kvm_hpt_info *info, u32 order)
 	}
 
 	if (!hpt)
-		hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT
+		hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_RETRY_MAYFAIL
 				       |__GFP_NOWARN, order - PAGE_SHIFT);
 
 	if (!hpt)
diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c
index e4b4e790bf89..fa466ce45bc9 100644
--- a/arch/sparc/kernel/mdesc.c
+++ b/arch/sparc/kernel/mdesc.c
@@ -205,7 +205,7 @@ static struct mdesc_handle *mdesc_kmalloc(unsigned int mdesc_size)
 	handle_size = (sizeof(struct mdesc_handle) -
 		       sizeof(struct mdesc_hdr) +
 		       mdesc_size);
-	base = kmalloc(handle_size + 15, GFP_KERNEL | __GFP_REPEAT);
+	base = kmalloc(handle_size + 15, GFP_KERNEL | __GFP_RETRY_MAYFAIL);
 	if (!base)
 		return NULL;
 
diff --git a/drivers/mmc/host/wbsd.c b/drivers/mmc/host/wbsd.c
index e15a9733fcfd..9668616faf16 100644
--- a/drivers/mmc/host/wbsd.c
+++ b/drivers/mmc/host/wbsd.c
@@ -1386,7 +1386,7 @@ static void wbsd_request_dma(struct wbsd_host *host, int dma)
 	 * order for ISA to be able to DMA to it.
 	 */
 	host->dma_buffer = kmalloc(WBSD_DMA_SIZE,
-		GFP_NOIO | GFP_DMA | __GFP_REPEAT | __GFP_NOWARN);
+		GFP_NOIO | GFP_DMA | __GFP_RETRY_MAYFAIL | __GFP_NOWARN);
 	if (!host->dma_buffer)
 		goto free;
 
diff --git a/drivers/s390/char/vmcp.c b/drivers/s390/char/vmcp.c
index 65f5a794f26d..98749fa817da 100644
--- a/drivers/s390/char/vmcp.c
+++ b/drivers/s390/char/vmcp.c
@@ -98,7 +98,7 @@ vmcp_write(struct file *file, const char __user *buff, size_t count,
 	}
 	if (!session->response)
 		session->response = (char *)__get_free_pages(GFP_KERNEL
-						| __GFP_REPEAT | GFP_DMA,
+						| __GFP_RETRY_MAYFAIL | GFP_DMA,
 						get_order(session->bufsize));
 	if (!session->response) {
 		mutex_unlock(&session->mutex);
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index f1b3a46bdcaf..1bdc10651bcd 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -252,7 +252,7 @@ int transport_alloc_session_tags(struct se_session *se_sess,
 	int rc;
 
 	se_sess->sess_cmd_map = kzalloc(tag_num * tag_size,
-					GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
+					GFP_KERNEL | __GFP_NOWARN | __GFP_RETRY_MAYFAIL);
 	if (!se_sess->sess_cmd_map) {
 		se_sess->sess_cmd_map = vzalloc(tag_num * tag_size);
 		if (!se_sess->sess_cmd_map) {
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index e3d7ea1288c6..06d044862e58 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -897,7 +897,7 @@ static int vhost_net_open(struct inode *inode, struct file *f)
 	struct sk_buff **queue;
 	int i;
 
-	n = kvmalloc(sizeof *n, GFP_KERNEL | __GFP_REPEAT);
+	n = kvmalloc(sizeof *n, GFP_KERNEL | __GFP_RETRY_MAYFAIL);
 	if (!n)
 		return -ENOMEM;
 	vqs = kmalloc(VHOST_NET_VQ_MAX * sizeof(*vqs), GFP_KERNEL);
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index fd6c8b66f06f..ff02a942c4d5 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -1404,7 +1404,7 @@ static int vhost_scsi_open(struct inode *inode, struct file *f)
 	struct vhost_virtqueue **vqs;
 	int r = -ENOMEM, i;
 
-	vs = kzalloc(sizeof(*vs), GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
+	vs = kzalloc(sizeof(*vs), GFP_KERNEL | __GFP_NOWARN | __GFP_RETRY_MAYFAIL);
 	if (!vs) {
 		vs = vzalloc(sizeof(*vs));
 		if (!vs)
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 3f63e03de8e8..c9de9c41aa97 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -508,7 +508,7 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file)
 	/* This struct is large and allocation could fail, fall back to vmalloc
 	 * if there is no other way.
 	 */
-	vsock = kvmalloc(sizeof(*vsock), GFP_KERNEL | __GFP_REPEAT);
+	vsock = kvmalloc(sizeof(*vsock), GFP_KERNEL | __GFP_RETRY_MAYFAIL);
 	if (!vsock)
 		return -ENOMEM;
 
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 4c6656f1fee7..bcfb9f7c46f5 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -25,7 +25,7 @@ struct vm_area_struct;
 #define ___GFP_FS		0x80u
 #define ___GFP_COLD		0x100u
 #define ___GFP_NOWARN		0x200u
-#define ___GFP_REPEAT		0x400u
+#define ___GFP_RETRY_MAYFAIL	0x400u
 #define ___GFP_NOFAIL		0x800u
 #define ___GFP_NORETRY		0x1000u
 #define ___GFP_MEMALLOC		0x2000u
@@ -136,26 +136,56 @@ struct vm_area_struct;
  *
  * __GFP_RECLAIM is shorthand to allow/forbid both direct and kswapd reclaim.
  *
- * __GFP_REPEAT: Try hard to allocate the memory, but the allocation attempt
- *   _might_ fail.  This depends upon the particular VM implementation.
+ * The default allocator behavior depends on the request size. We have a concept
+ * of so called costly allocations (with order > PAGE_ALLOC_COSTLY_ORDER).
+ * !costly allocations are too essential to fail so they are implicitly
+ * non-failing by default (with some exceptions like OOM victims might fail so
+ * the caller still has to check for failures) while costly requests try to be
+ * not disruptive and back off even without invoking the OOM killer.
+ * The following three modifiers might be used to override some of these
+ * implicit rules
+ *
+ * __GFP_NORETRY: The VM implementation will try only very lightweight
+ *   memory direct reclaim to get some memory under memory pressure (thus
+ *   it can sleep). It will avoid disruptive actions like OOM killer. The
+ *   caller must handle the failure which is quite likely to happen under
+ *   heavy memory pressure. The flag is suitable when failure can easily be
+ *   handled at small cost, such as reduced throughput
+ *
+ * __GFP_RETRY_MAYFAIL: The VM implementation will retry memory reclaim
+ *   procedures that have previously failed if there is some indication
+ *   that progress has been made else where.  It can wait for other
+ *   tasks to attempt high level approaches to freeing memory such as
+ *   compaction (which removes fragmentation) and page-out.
+ *   There is still a definite limit to the number of retries, but it is
+ *   a larger limit than with __GFP_NORETRY.
+ *   Allocations with this flag may fail, but only when there is
+ *   genuinely little unused memory. While these allocations do not
+ *   directly trigger the OOM killer, their failure indicates that
+ *   the system is likely to need to use the OOM killer soon.  The
+ *   caller must handle failure, but can reasonably do so by failing
+ *   a higher-level request, or completing it only in a much less
+ *   efficient manner.
+ *   If the allocation does fail, and the caller is in a position to
+ *   free some non-essential memory, doing so could benefit the system
+ *   as a whole.
  *
  * __GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller
- *   cannot handle allocation failures. New users should be evaluated carefully
- *   (and the flag should be used only when there is no reasonable failure
- *   policy) but it is definitely preferable to use the flag rather than
- *   opencode endless loop around allocator.
- *
- * __GFP_NORETRY: The VM implementation must not retry indefinitely and will
- *   return NULL when direct reclaim and memory compaction have failed to allow
- *   the allocation to succeed.  The OOM killer is not called with the current
- *   implementation.
+ *   cannot handle allocation failures. The allocation could block
+ *   indefinitely but will never return with failure. Testing for
+ *   failure is pointless.
+ *   New users should be evaluated carefully (and the flag should be
+ *   used only when there is no reasonable failure policy) but it is
+ *   definitely preferable to use the flag rather than opencode endless
+ *   loop around allocator.
+ *   Using this flag for costly allocations is _highly_ discouraged.
  */
 #define __GFP_IO	((__force gfp_t)___GFP_IO)
 #define __GFP_FS	((__force gfp_t)___GFP_FS)
 #define __GFP_DIRECT_RECLAIM	((__force gfp_t)___GFP_DIRECT_RECLAIM) /* Caller can reclaim */
 #define __GFP_KSWAPD_RECLAIM	((__force gfp_t)___GFP_KSWAPD_RECLAIM) /* kswapd can wake */
 #define __GFP_RECLAIM ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM))
-#define __GFP_REPEAT	((__force gfp_t)___GFP_REPEAT)
+#define __GFP_RETRY_MAYFAIL	((__force gfp_t)___GFP_RETRY_MAYFAIL)
 #define __GFP_NOFAIL	((__force gfp_t)___GFP_NOFAIL)
 #define __GFP_NORETRY	((__force gfp_t)___GFP_NORETRY)
 
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 04a7f7993e67..41473df6dfb0 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -471,7 +471,8 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags)
  *
  * %__GFP_NOWARN - If allocation fails, don't issue any warnings.
  *
- * %__GFP_REPEAT - If allocation fails initially, try once more before failing.
+ * %__GFP_RETRY_MAYFAIL - Try really hard to succeed the allocation but fail
+ *   eventually.
  *
  * There are other flags available as well, but these are not intended
  * for general use, and so are not documented here. For a full list of
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index 10e3663a75a6..8e50d01c645f 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -34,7 +34,7 @@
 	{(unsigned long)__GFP_FS,		"__GFP_FS"},		\
 	{(unsigned long)__GFP_COLD,		"__GFP_COLD"},		\
 	{(unsigned long)__GFP_NOWARN,		"__GFP_NOWARN"},	\
-	{(unsigned long)__GFP_REPEAT,		"__GFP_REPEAT"},	\
+	{(unsigned long)__GFP_RETRY_MAYFAIL,	"__GFP_RETRY_MAYFAIL"},	\
 	{(unsigned long)__GFP_NOFAIL,		"__GFP_NOFAIL"},	\
 	{(unsigned long)__GFP_NORETRY,		"__GFP_NORETRY"},	\
 	{(unsigned long)__GFP_COMP,		"__GFP_COMP"},		\
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 1e516520433d..bc48ee783dd9 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1384,7 +1384,7 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
 
 	page = __alloc_pages_node(nid,
 		htlb_alloc_mask(h)|__GFP_COMP|__GFP_THISNODE|
-						__GFP_REPEAT|__GFP_NOWARN,
+						__GFP_RETRY_MAYFAIL|__GFP_NOWARN,
 		huge_page_order(h));
 	if (page) {
 		prep_new_huge_page(h, page, nid);
@@ -1525,7 +1525,7 @@ static struct page *__hugetlb_alloc_buddy_huge_page(struct hstate *h,
 {
 	int order = huge_page_order(h);
 
-	gfp_mask |= __GFP_COMP|__GFP_REPEAT|__GFP_NOWARN;
+	gfp_mask |= __GFP_COMP|__GFP_RETRY_MAYFAIL|__GFP_NOWARN;
 	if (nid == NUMA_NO_NODE)
 		nid = numa_mem_id();
 	return __alloc_pages_nodemask(gfp_mask, order, nid, nmask);
diff --git a/mm/internal.h b/mm/internal.h
index 0e4f558412fb..24d88f084705 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -23,7 +23,7 @@
  * hints such as HIGHMEM usage.
  */
 #define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\
-			__GFP_NOWARN|__GFP_REPEAT|__GFP_NOFAIL|\
+			__GFP_NOWARN|__GFP_RETRY_MAYFAIL|__GFP_NOFAIL|\
 			__GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\
 			__GFP_ATOMIC)
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 64b7d82a9b1a..6d30e914afb6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3284,6 +3284,14 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	/* The OOM killer will not help higher order allocs */
 	if (order > PAGE_ALLOC_COSTLY_ORDER)
 		goto out;
+	/*
+	 * We have already exhausted all our reclaim opportunities without any
+	 * success so it is time to admit defeat. We will skip the OOM killer
+	 * because it is very likely that the caller has a more reasonable
+	 * fallback than shooting a random task.
+	 */
+	if (gfp_mask & __GFP_RETRY_MAYFAIL)
+		goto out;
 	/* The OOM killer does not needlessly kill tasks for lowmem */
 	if (ac->high_zoneidx < ZONE_NORMAL)
 		goto out;
@@ -3413,7 +3421,7 @@ should_compact_retry(struct alloc_context *ac, int order, int alloc_flags,
 	}
 
 	/*
-	 * !costly requests are much more important than __GFP_REPEAT
+	 * !costly requests are much more important than __GFP_RETRY_MAYFAIL
 	 * costly ones because they are de facto nofail and invoke OOM
 	 * killer to move on while costly can fail and users are ready
 	 * to cope with that. 1/4 retries is rather arbitrary but we
@@ -3920,9 +3928,9 @@ retry:
 
 	/*
 	 * Do not retry costly high order allocations unless they are
-	 * __GFP_REPEAT
+	 * __GFP_RETRY_MAYFAIL
 	 */
-	if (costly_order && !(gfp_mask & __GFP_REPEAT))
+	if (costly_order && !(gfp_mask & __GFP_RETRY_MAYFAIL))
 		goto nopage;
 
 	if (should_reclaim_retry(gfp_mask, order, ac, alloc_flags,
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index a56c3989f773..c50b1a14d55e 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -56,11 +56,11 @@ void * __meminit vmemmap_alloc_block(unsigned long size, int node)
 
 		if (node_state(node, N_HIGH_MEMORY))
 			page = alloc_pages_node(
-				node, GFP_KERNEL | __GFP_ZERO | __GFP_REPEAT,
+				node, GFP_KERNEL | __GFP_ZERO | __GFP_RETRY_MAYFAIL,
 				get_order(size));
 		else
 			page = alloc_pages(
-				GFP_KERNEL | __GFP_ZERO | __GFP_REPEAT,
+				GFP_KERNEL | __GFP_ZERO | __GFP_RETRY_MAYFAIL,
 				get_order(size));
 		if (page)
 			return page_address(page);
diff --git a/mm/util.c b/mm/util.c
index 26be6407abd7..6520f2d4a226 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -339,7 +339,7 @@ EXPORT_SYMBOL(vm_mmap);
  * Uses kmalloc to get the memory but if the allocation fails then falls back
  * to the vmalloc allocator. Use kvfree for freeing the memory.
  *
- * Reclaim modifiers - __GFP_NORETRY and __GFP_NOFAIL are not supported. __GFP_REPEAT
+ * Reclaim modifiers - __GFP_NORETRY and __GFP_NOFAIL are not supported. __GFP_RETRY_MAYFAIL
  * is supported only for large (>32kB) allocations, and it should be used only if
  * kmalloc is preferable to the vmalloc fallback, due to visible performance drawbacks.
  *
@@ -367,11 +367,11 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node)
 		kmalloc_flags |= __GFP_NOWARN;
 
 		/*
-		 * We have to override __GFP_REPEAT by __GFP_NORETRY for !costly
+		 * We have to override __GFP_RETRY_MAYFAIL by __GFP_NORETRY for !costly
 		 * requests because there is no other way to tell the allocator
 		 * that we want to fail rather than retry endlessly.
 		 */
-		if (!(kmalloc_flags & __GFP_REPEAT) ||
+		if (!(kmalloc_flags & __GFP_RETRY_MAYFAIL) ||
 				(size <= PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER))
 			kmalloc_flags |= __GFP_NORETRY;
 	}
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 6016ab079e2b..8698c1c86c4d 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1795,7 +1795,7 @@ fail:
  *	allocator with @gfp_mask flags.  Map them into contiguous
  *	kernel virtual space, using a pagetable protection of @prot.
  *
- *	Reclaim modifiers in @gfp_mask - __GFP_NORETRY, __GFP_REPEAT
+ *	Reclaim modifiers in @gfp_mask - __GFP_NORETRY, __GFP_RETRY_MAYFAIL
  *	and __GFP_NOFAIL are not supported
  *
  *	Any use of gfp flags outside of GFP_KERNEL should be consulted
diff --git a/mm/vmscan.c b/mm/vmscan.c
index e9210f825219..a1af041930a6 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2506,18 +2506,18 @@ static inline bool should_continue_reclaim(struct pglist_data *pgdat,
 		return false;
 
 	/* Consider stopping depending on scan and reclaim activity */
-	if (sc->gfp_mask & __GFP_REPEAT) {
+	if (sc->gfp_mask & __GFP_RETRY_MAYFAIL) {
 		/*
-		 * For __GFP_REPEAT allocations, stop reclaiming if the
+		 * For __GFP_RETRY_MAYFAIL allocations, stop reclaiming if the
 		 * full LRU list has been scanned and we are still failing
 		 * to reclaim pages. This full LRU scan is potentially
-		 * expensive but a __GFP_REPEAT caller really wants to succeed
+		 * expensive but a __GFP_RETRY_MAYFAIL caller really wants to succeed
 		 */
 		if (!nr_reclaimed && !nr_scanned)
 			return false;
 	} else {
 		/*
-		 * For non-__GFP_REPEAT allocations which can presumably
+		 * For non-__GFP_RETRY_MAYFAIL allocations which can presumably
 		 * fail without consequence, stop if we failed to reclaim
 		 * any pages from the last SWAP_CLUSTER_MAX number of
 		 * pages that were scanned. This will return to the
diff --git a/net/core/dev.c b/net/core/dev.c
index 02440518dd69..8515f8fe0460 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7384,7 +7384,7 @@ static int netif_alloc_rx_queues(struct net_device *dev)
 
 	BUG_ON(count < 1);
 
-	rx = kvzalloc(sz, GFP_KERNEL | __GFP_REPEAT);
+	rx = kvzalloc(sz, GFP_KERNEL | __GFP_RETRY_MAYFAIL);
 	if (!rx)
 		return -ENOMEM;
 
@@ -7424,7 +7424,7 @@ static int netif_alloc_netdev_queues(struct net_device *dev)
 	if (count < 1 || count > 0xffff)
 		return -EINVAL;
 
-	tx = kvzalloc(sz, GFP_KERNEL | __GFP_REPEAT);
+	tx = kvzalloc(sz, GFP_KERNEL | __GFP_RETRY_MAYFAIL);
 	if (!tx)
 		return -ENOMEM;
 
@@ -7965,7 +7965,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	/* ensure 32-byte alignment of whole construct */
 	alloc_size += NETDEV_ALIGN - 1;
 
-	p = kvzalloc(alloc_size, GFP_KERNEL | __GFP_REPEAT);
+	p = kvzalloc(alloc_size, GFP_KERNEL | __GFP_RETRY_MAYFAIL);
 	if (!p)
 		return NULL;
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 8b11341ed69a..f990eb8b30a9 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4747,7 +4747,7 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len,
 
 	gfp_head = gfp_mask;
 	if (gfp_head & __GFP_DIRECT_RECLAIM)
-		gfp_head |= __GFP_REPEAT;
+		gfp_head |= __GFP_RETRY_MAYFAIL;
 
 	*errcode = -ENOBUFS;
 	skb = alloc_skb(header_len, gfp_head);
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 147fde73a0f5..263d16e3219e 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -648,7 +648,7 @@ static int fq_resize(struct Qdisc *sch, u32 log)
 		return 0;
 
 	/* If XPS was setup, we can allocate memory on right NUMA node */
-	array = kvmalloc_node(sizeof(struct rb_root) << log, GFP_KERNEL | __GFP_REPEAT,
+	array = kvmalloc_node(sizeof(struct rb_root) << log, GFP_KERNEL | __GFP_RETRY_MAYFAIL,
 			      netdev_queue_numa_node_read(sch->dev_queue));
 	if (!array)
 		return -ENOMEM;
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 0a8a1c45af87..a1497c516d85 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -643,7 +643,7 @@ static const struct {
 	{ "__GFP_FS",			"F" },
 	{ "__GFP_COLD",			"CO" },
 	{ "__GFP_NOWARN",		"NWR" },
-	{ "__GFP_REPEAT",		"R" },
+	{ "__GFP_RETRY_MAYFAIL",	"R" },
 	{ "__GFP_NOFAIL",		"NF" },
 	{ "__GFP_NORETRY",		"NR" },
 	{ "__GFP_COMP",			"C" },
-- 
cgit v1.2.3


From 0f55685627d6dd2beda55a82abc02297f0f8e5c2 Mon Sep 17 00:00:00 2001
From: Michal Hocko <mhocko@suse.com>
Date: Wed, 12 Jul 2017 14:36:58 -0700
Subject: mm, migration: do not trigger OOM killer when migrating memory

Page migration (for memory hotplug, soft_offline_page or mbind) needs to
allocate a new memory.  This can trigger an oom killer if the target
memory is depleated.  Although quite unlikely, still possible,
especially for the memory hotplug (offlining of memoery).

Up to now we didn't really have reasonable means to back off.
__GFP_NORETRY can fail just too easily and __GFP_THISNODE sticks to a
single node and that is not suitable for all callers.

But now that we have __GFP_RETRY_MAYFAIL we should use it.  It is
preferable to fail the migration than disrupt the system by killing some
processes.

Link: http://lkml.kernel.org/r/20170623085345.11304-7-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Alex Belits <alex.belits@cavium.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Darrick J. Wong <darrick.wong@oracle.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: NeilBrown <neilb@suse.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/migrate.h | 2 +-
 mm/mempolicy.c          | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 4634da521238..3e0d405dc842 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -34,7 +34,7 @@ extern char *migrate_reason_names[MR_TYPES];
 static inline struct page *new_page_nodemask(struct page *page,
 				int preferred_nid, nodemask_t *nodemask)
 {
-	gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE;
+	gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL;
 
 	if (PageHuge(page))
 		return alloc_huge_page_nodemask(page_hstate(compound_head(page)),
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 7d8e56214ac0..d911fa5cb2a7 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1078,7 +1078,8 @@ static struct page *new_page(struct page *page, unsigned long start, int **x)
 	/*
 	 * if !vma, alloc_page_vma() will use task or system default policy
 	 */
-	return alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
+	return alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL,
+			vma, address);
 }
 #else
 
-- 
cgit v1.2.3


From c945dccc80856107f109c36a7d0e29a371b5d1b5 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Wed, 12 Jul 2017 14:37:48 -0700
Subject: ARM: samsung: usb-ohci: move inline before return type

Make the code like the rest of the kernel.

Link: http://lkml.kernel.org/r/667a515b8d0f10f2465d519f8595edd91552fc5e.1499284835.git.joe@perches.com
Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/platform_data/usb-ohci-s3c2410.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/platform_data/usb-ohci-s3c2410.h b/include/linux/platform_data/usb-ohci-s3c2410.h
index 7fa1fbefc3f2..cc7554ae6e8b 100644
--- a/include/linux/platform_data/usb-ohci-s3c2410.h
+++ b/include/linux/platform_data/usb-ohci-s3c2410.h
@@ -31,7 +31,7 @@ struct s3c2410_hcd_info {
 	void		(*report_oc)(struct s3c2410_hcd_info *, int ports);
 };
 
-static void inline s3c2410_usb_report_oc(struct s3c2410_hcd_info *info, int ports)
+static inline void s3c2410_usb_report_oc(struct s3c2410_hcd_info *info, int ports)
 {
 	if (info->report_oc != NULL) {
 		(info->report_oc)(info, ports);
-- 
cgit v1.2.3


From 3e8f399da490e6ac20a3cfd6aa404c9aa961a9a2 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 12 Jul 2017 14:37:51 -0700
Subject: writeback: rework wb_[dec|inc]_stat family of functions

Currently the writeback statistics code uses a percpu counters to hold
various statistics.  Furthermore we have 2 families of functions - those
which disable local irq and those which doesn't and whose names begin
with double underscore.  However, they both end up calling
__add_wb_stats which in turn calls percpu_counter_add_batch which is
already irq-safe.

Exploiting this fact allows to eliminated the __wb_* functions since
they don't add any further protection than we already have.
Furthermore, refactor the wb_* function to call __add_wb_stat directly
without the irq-disabling dance.  This will likely result in better
runtime of code which deals with modifying the stat counters.

While at it also document why percpu_counter_add_batch is in fact
preempt and irq-safe since at least 3 people got confused.

Link: http://lkml.kernel.org/r/1498029937-27293-1-git-send-email-nborisov@suse.com
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Acked-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Josef Bacik <jbacik@fb.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/fs-writeback.c           |  8 ++++----
 include/linux/backing-dev.h | 24 ++----------------------
 lib/percpu_counter.c        |  7 +++++++
 mm/page-writeback.c         | 10 +++++-----
 4 files changed, 18 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 8b426f83909f..245c430a2e41 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -380,8 +380,8 @@ static void inode_switch_wbs_work_fn(struct work_struct *work)
 		struct page *page = radix_tree_deref_slot_protected(slot,
 							&mapping->tree_lock);
 		if (likely(page) && PageDirty(page)) {
-			__dec_wb_stat(old_wb, WB_RECLAIMABLE);
-			__inc_wb_stat(new_wb, WB_RECLAIMABLE);
+			dec_wb_stat(old_wb, WB_RECLAIMABLE);
+			inc_wb_stat(new_wb, WB_RECLAIMABLE);
 		}
 	}
 
@@ -391,8 +391,8 @@ static void inode_switch_wbs_work_fn(struct work_struct *work)
 							&mapping->tree_lock);
 		if (likely(page)) {
 			WARN_ON_ONCE(!PageWriteback(page));
-			__dec_wb_stat(old_wb, WB_WRITEBACK);
-			__inc_wb_stat(new_wb, WB_WRITEBACK);
+			dec_wb_stat(old_wb, WB_WRITEBACK);
+			inc_wb_stat(new_wb, WB_WRITEBACK);
 		}
 	}
 
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 334165c911f0..854e1bdd0b2a 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -69,34 +69,14 @@ static inline void __add_wb_stat(struct bdi_writeback *wb,
 	percpu_counter_add_batch(&wb->stat[item], amount, WB_STAT_BATCH);
 }
 
-static inline void __inc_wb_stat(struct bdi_writeback *wb,
-				 enum wb_stat_item item)
-{
-	__add_wb_stat(wb, item, 1);
-}
-
 static inline void inc_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
 {
-	unsigned long flags;
-
-	local_irq_save(flags);
-	__inc_wb_stat(wb, item);
-	local_irq_restore(flags);
-}
-
-static inline void __dec_wb_stat(struct bdi_writeback *wb,
-				 enum wb_stat_item item)
-{
-	__add_wb_stat(wb, item, -1);
+	__add_wb_stat(wb, item, 1);
 }
 
 static inline void dec_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
 {
-	unsigned long flags;
-
-	local_irq_save(flags);
-	__dec_wb_stat(wb, item);
-	local_irq_restore(flags);
+	__add_wb_stat(wb, item, -1);
 }
 
 static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index 8ee7e5ec21be..3bf4a9984f4c 100644
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -72,6 +72,13 @@ void percpu_counter_set(struct percpu_counter *fbc, s64 amount)
 }
 EXPORT_SYMBOL(percpu_counter_set);
 
+/**
+ * This function is both preempt and irq safe. The former is due to explicit
+ * preemption disable. The latter is guaranteed by the fact that the slow path
+ * is explicitly protected by an irq-safe spinlock whereas the fast patch uses
+ * this_cpu_add which is irq-safe by definition. Hence there is no need muck
+ * with irq state before calling this one
+ */
 void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch)
 {
 	s64 count;
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 0b60cc7ddac2..96e93b214d31 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -601,7 +601,7 @@ static inline void __wb_writeout_inc(struct bdi_writeback *wb)
 {
 	struct wb_domain *cgdom;
 
-	__inc_wb_stat(wb, WB_WRITTEN);
+	inc_wb_stat(wb, WB_WRITTEN);
 	wb_domain_writeout_inc(&global_wb_domain, &wb->completions,
 			       wb->bdi->max_prop_frac);
 
@@ -2435,8 +2435,8 @@ void account_page_dirtied(struct page *page, struct address_space *mapping)
 		__inc_lruvec_page_state(page, NR_FILE_DIRTY);
 		__inc_zone_page_state(page, NR_ZONE_WRITE_PENDING);
 		__inc_node_page_state(page, NR_DIRTIED);
-		__inc_wb_stat(wb, WB_RECLAIMABLE);
-		__inc_wb_stat(wb, WB_DIRTIED);
+		inc_wb_stat(wb, WB_RECLAIMABLE);
+		inc_wb_stat(wb, WB_DIRTIED);
 		task_io_account_write(PAGE_SIZE);
 		current->nr_dirtied++;
 		this_cpu_inc(bdp_ratelimits);
@@ -2741,7 +2741,7 @@ int test_clear_page_writeback(struct page *page)
 			if (bdi_cap_account_writeback(bdi)) {
 				struct bdi_writeback *wb = inode_to_wb(inode);
 
-				__dec_wb_stat(wb, WB_WRITEBACK);
+				dec_wb_stat(wb, WB_WRITEBACK);
 				__wb_writeout_inc(wb);
 			}
 		}
@@ -2786,7 +2786,7 @@ int __test_set_page_writeback(struct page *page, bool keep_write)
 						page_index(page),
 						PAGECACHE_TAG_WRITEBACK);
 			if (bdi_cap_account_writeback(bdi))
-				__inc_wb_stat(inode_to_wb(inode), WB_WRITEBACK);
+				inc_wb_stat(inode_to_wb(inode), WB_WRITEBACK);
 
 			/*
 			 * We can come through here when swapping anonymous
-- 
cgit v1.2.3


From 3c48d86cc959309ee168fb87737a8cb3f97c5224 Mon Sep 17 00:00:00 2001
From: Bjorn Andersson <bjorn.andersson@linaro.org>
Date: Wed, 12 Jul 2017 15:04:16 -0700
Subject: clk: Provide bulk prepare_enable disable_unprepare variants

This extends the existing set of bulk helpers with prepare_enable and
disable_unprepare variants.

Cc: Russell King <linux@armlinux.org.uk>,
Cc: Dong Aisheng <aisheng.dong@nxp.com>
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
---
 include/linux/clk.h | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

(limited to 'include')

diff --git a/include/linux/clk.h b/include/linux/clk.h
index c673f0b91751..690e6a6921e1 100644
--- a/include/linux/clk.h
+++ b/include/linux/clk.h
@@ -657,6 +657,28 @@ static inline void clk_disable_unprepare(struct clk *clk)
 	clk_unprepare(clk);
 }
 
+static inline int clk_bulk_prepare_enable(int num_clks,
+					  struct clk_bulk_data *clks)
+{
+	int ret;
+
+	ret = clk_bulk_prepare(num_clks, clks);
+	if (ret)
+		return ret;
+	ret = clk_bulk_enable(num_clks, clks);
+	if (ret)
+		clk_bulk_unprepare(num_clks, clks);
+
+	return ret;
+}
+
+static inline void clk_bulk_disable_unprepare(int num_clks,
+					      struct clk_bulk_data *clks)
+{
+	clk_bulk_disable(num_clks, clks);
+	clk_bulk_unprepare(num_clks, clks);
+}
+
 #if defined(CONFIG_OF) && defined(CONFIG_COMMON_CLK)
 struct clk *of_clk_get(struct device_node *np, int index);
 struct clk *of_clk_get_by_name(struct device_node *np, const char *name);
-- 
cgit v1.2.3


From efc479e6900c22bad9a2b649d13405ed9cde2d53 Mon Sep 17 00:00:00 2001
From: Roman Kagan <rkagan@virtuozzo.com>
Date: Thu, 22 Jun 2017 16:51:01 +0300
Subject: kvm: x86: hyperv: add KVM_CAP_HYPERV_SYNIC2
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is a flaw in the Hyper-V SynIC implementation in KVM: when message
page or event flags page is enabled by setting the corresponding msr,
KVM zeroes it out.  This is problematic because on migration the
corresponding MSRs are loaded on the destination, so the content of
those pages is lost.

This went unnoticed so far because the only user of those pages was
in-KVM hyperv synic timers, which could continue working despite that
zeroing.

Newer QEMU uses those pages for Hyper-V VMBus implementation, and
zeroing them breaks the migration.

Besides, in newer QEMU the content of those pages is fully managed by
QEMU, so zeroing them is undesirable even when writing the MSRs from the
guest side.

To support this new scheme, introduce a new capability,
KVM_CAP_HYPERV_SYNIC2, which, when enabled, makes sure that the synic
pages aren't zeroed out in KVM.

Signed-off-by: Roman Kagan <rkagan@virtuozzo.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
---
 Documentation/virtual/kvm/api.txt |  9 +++++++++
 arch/x86/include/asm/kvm_host.h   |  1 +
 arch/x86/kvm/hyperv.c             | 13 +++++++++----
 arch/x86/kvm/hyperv.h             |  2 +-
 arch/x86/kvm/x86.c                |  7 ++++++-
 include/uapi/linux/kvm.h          |  1 +
 6 files changed, 27 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 3a9831b72945..78ac577c9378 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -4329,3 +4329,12 @@ Querying this capability returns a bitmap indicating the possible
 virtual SMT modes that can be set using KVM_CAP_PPC_SMT.  If bit N
 (counting from the right) is set, then a virtual SMT mode of 2^N is
 available.
+
+8.11 KVM_CAP_HYPERV_SYNIC2
+
+Architectures: x86
+
+This capability enables a newer version of Hyper-V Synthetic interrupt
+controller (SynIC).  The only difference with KVM_CAP_HYPERV_SYNIC is that KVM
+doesn't clear SynIC message and event flags pages when they are enabled by
+writing to the respective MSRs.
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index ef37d0dc61bd..9d8de5dd7546 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -462,6 +462,7 @@ struct kvm_vcpu_hv_synic {
 	DECLARE_BITMAP(auto_eoi_bitmap, 256);
 	DECLARE_BITMAP(vec_bitmap, 256);
 	bool active;
+	bool dont_zero_synic_pages;
 };
 
 /* Hyper-V per vcpu emulation context */
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index ebae57ac5902..a8084406707e 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -221,7 +221,8 @@ static int synic_set_msr(struct kvm_vcpu_hv_synic *synic,
 		synic->version = data;
 		break;
 	case HV_X64_MSR_SIEFP:
-		if (data & HV_SYNIC_SIEFP_ENABLE)
+		if ((data & HV_SYNIC_SIEFP_ENABLE) && !host &&
+		    !synic->dont_zero_synic_pages)
 			if (kvm_clear_guest(vcpu->kvm,
 					    data & PAGE_MASK, PAGE_SIZE)) {
 				ret = 1;
@@ -232,7 +233,8 @@ static int synic_set_msr(struct kvm_vcpu_hv_synic *synic,
 			synic_exit(synic, msr);
 		break;
 	case HV_X64_MSR_SIMP:
-		if (data & HV_SYNIC_SIMP_ENABLE)
+		if ((data & HV_SYNIC_SIMP_ENABLE) && !host &&
+		    !synic->dont_zero_synic_pages)
 			if (kvm_clear_guest(vcpu->kvm,
 					    data & PAGE_MASK, PAGE_SIZE)) {
 				ret = 1;
@@ -687,14 +689,17 @@ void kvm_hv_vcpu_init(struct kvm_vcpu *vcpu)
 		stimer_init(&hv_vcpu->stimer[i], i);
 }
 
-int kvm_hv_activate_synic(struct kvm_vcpu *vcpu)
+int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages)
 {
+	struct kvm_vcpu_hv_synic *synic = vcpu_to_synic(vcpu);
+
 	/*
 	 * Hyper-V SynIC auto EOI SINT's are
 	 * not compatible with APICV, so deactivate APICV
 	 */
 	kvm_vcpu_deactivate_apicv(vcpu);
-	vcpu_to_synic(vcpu)->active = true;
+	synic->active = true;
+	synic->dont_zero_synic_pages = dont_zero_synic_pages;
 	return 0;
 }
 
diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
index cd1119538add..12f65fe1011d 100644
--- a/arch/x86/kvm/hyperv.h
+++ b/arch/x86/kvm/hyperv.h
@@ -56,7 +56,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu);
 void kvm_hv_irq_routing_update(struct kvm *kvm);
 int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vcpu_id, u32 sint);
 void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector);
-int kvm_hv_activate_synic(struct kvm_vcpu *vcpu);
+int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages);
 
 void kvm_hv_vcpu_init(struct kvm_vcpu *vcpu);
 void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 08aa5e442aa7..4f41c5222ecd 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2659,6 +2659,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_HYPERV_VAPIC:
 	case KVM_CAP_HYPERV_SPIN:
 	case KVM_CAP_HYPERV_SYNIC:
+	case KVM_CAP_HYPERV_SYNIC2:
 	case KVM_CAP_PCI_SEGMENT:
 	case KVM_CAP_DEBUGREGS:
 	case KVM_CAP_X86_ROBUST_SINGLESTEP:
@@ -3382,10 +3383,14 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 
 	switch (cap->cap) {
+	case KVM_CAP_HYPERV_SYNIC2:
+		if (cap->args[0])
+			return -EINVAL;
 	case KVM_CAP_HYPERV_SYNIC:
 		if (!irqchip_in_kernel(vcpu->kvm))
 			return -EINVAL;
-		return kvm_hv_activate_synic(vcpu);
+		return kvm_hv_activate_synic(vcpu, cap->cap ==
+					     KVM_CAP_HYPERV_SYNIC2);
 	default:
 		return -EINVAL;
 	}
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index ebd604c222d8..38b2cfbc8112 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -927,6 +927,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_S390_CMMA_MIGRATION 145
 #define KVM_CAP_PPC_FWNMI 146
 #define KVM_CAP_PPC_SMT_POSSIBLE 147
+#define KVM_CAP_HYPERV_SYNIC2 148
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
-- 
cgit v1.2.3


From 2683701201ddb9a2a4d0fda5d950ab50ca8e77e4 Mon Sep 17 00:00:00 2001
From: Rolf Eike Beer <eb@emlix.com>
Date: Thu, 13 Jul 2017 16:46:43 +0200
Subject: netlink: correctly document nla_put_u64_64bit()

Signed-off-by: Rolf Eike Beer <eb@emlix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netlink.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/netlink.h b/include/net/netlink.h
index 01709172b3d3..ef8e6c3a80a6 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -98,8 +98,8 @@
  *   nla_put_u8(skb, type, value)	add u8 attribute to skb
  *   nla_put_u16(skb, type, value)	add u16 attribute to skb
  *   nla_put_u32(skb, type, value)	add u32 attribute to skb
- *   nla_put_u64_64bits(skb, type,
- *			value, padattr)	add u64 attribute to skb
+ *   nla_put_u64_64bit(skb, type,
+ *                     value, padattr)	add u64 attribute to skb
  *   nla_put_s8(skb, type, value)	add s8 attribute to skb
  *   nla_put_s16(skb, type, value)	add s16 attribute to skb
  *   nla_put_s32(skb, type, value)	add s32 attribute to skb
-- 
cgit v1.2.3


From 0aebdc52ca824c38837a652548028e45da72628f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 8 May 2017 09:31:19 +0200
Subject: sunrpc: properly type argument to kxdreproc_t

Pass struct rpc_request as the first argument instead of an untyped blob,
and mark the data object as const.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jeff Layton <jlayton@redhat.com>
---
 include/linux/sunrpc/xdr.h | 5 ++++-
 net/sunrpc/clnt.c          | 3 ++-
 2 files changed, 6 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 054c8cde18f3..290f189de200 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -17,6 +17,8 @@
 #include <asm/unaligned.h>
 #include <linux/scatterlist.h>
 
+struct rpc_rqst;
+
 /*
  * Buffer adjustment
  */
@@ -222,7 +224,8 @@ struct xdr_stream {
 /*
  * These are the xdr_stream style generic XDR encode and decode functions.
  */
-typedef void	(*kxdreproc_t)(void *rqstp, struct xdr_stream *xdr, void *obj);
+typedef void	(*kxdreproc_t)(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
+		const void *obj);
 typedef int	(*kxdrdproc_t)(void *rqstp, struct xdr_stream *xdr, void *obj);
 
 extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p);
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index b5cb921775a0..9fee20dc0c80 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -2476,7 +2476,8 @@ out_overflow:
 	goto out_garbage;
 }
 
-static void rpcproc_encode_null(void *rqstp, struct xdr_stream *xdr, void *obj)
+static void rpcproc_encode_null(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
+		const void *obj)
 {
 }
 
-- 
cgit v1.2.3


From 993328e2b31fedc35276a4828039ad7af6d519cb Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 8 May 2017 14:58:11 +0200
Subject: sunrpc: properly type argument to kxdrdproc_t

Pass struct rpc_request as the first argument instead of an untyped blob.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jeff Layton <jlayton@redhat.com>
Acked-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 include/linux/sunrpc/xdr.h | 3 ++-
 net/sunrpc/clnt.c          | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 290f189de200..ed0fbf0d8d0f 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -226,7 +226,8 @@ struct xdr_stream {
  */
 typedef void	(*kxdreproc_t)(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 		const void *obj);
-typedef int	(*kxdrdproc_t)(void *rqstp, struct xdr_stream *xdr, void *obj);
+typedef int	(*kxdrdproc_t)(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
+		void *obj);
 
 extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p);
 extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes);
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 9fee20dc0c80..964d5c4a1b60 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -2481,7 +2481,8 @@ static void rpcproc_encode_null(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 {
 }
 
-static int rpcproc_decode_null(void *rqstp, struct xdr_stream *xdr, void *obj)
+static int rpcproc_decode_null(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
+		void *obj)
 {
 	return 0;
 }
-- 
cgit v1.2.3


From c551858a884b6d81def3d1528a9002ba97f5d4ad Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 8 May 2017 23:27:10 +0200
Subject: sunrpc: move p_count out of struct rpc_procinfo

p_count is the only writeable memeber of struct rpc_procinfo, which is
a good candidate to be const-ified as it contains function pointers.

This patch moves it into out out struct rpc_procinfo, and into a
separate writable array that is pointed to by struct rpc_version and
indexed by p_statidx.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/lockd/clnt4xdr.c                  |  2 ++
 fs/lockd/clntxdr.c                   |  4 ++++
 fs/lockd/mon.c                       |  4 +++-
 fs/nfs/mount_clnt.c                  |  5 ++++-
 fs/nfs/nfs2xdr.c                     |  4 +++-
 fs/nfs/nfs3xdr.c                     |  6 +++++-
 fs/nfs/nfs4xdr.c                     |  4 +++-
 fs/nfsd/nfs4callback.c               |  4 +++-
 include/linux/sunrpc/clnt.h          |  2 +-
 net/sunrpc/auth_gss/gss_rpc_upcall.c |  3 ++-
 net/sunrpc/clnt.c                    |  6 ++++--
 net/sunrpc/rpcb_clnt.c               | 12 +++++++++---
 net/sunrpc/stats.c                   |  3 +--
 13 files changed, 44 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/fs/lockd/clnt4xdr.c b/fs/lockd/clnt4xdr.c
index f0ab7a99dd23..7c255d1d7c64 100644
--- a/fs/lockd/clnt4xdr.c
+++ b/fs/lockd/clnt4xdr.c
@@ -602,8 +602,10 @@ static struct rpc_procinfo	nlm4_procedures[] = {
 	PROC(GRANTED_RES,	res,		norep),
 };
 
+static unsigned int nlm_version4_counts[ARRAY_SIZE(nlm4_procedures)];
 const struct rpc_version nlm_version4 = {
 	.number		= 4,
 	.nrprocs	= ARRAY_SIZE(nlm4_procedures),
 	.procs		= nlm4_procedures,
+	.counts		= nlm_version4_counts,
 };
diff --git a/fs/lockd/clntxdr.c b/fs/lockd/clntxdr.c
index bd8a976785ae..39500c5743a5 100644
--- a/fs/lockd/clntxdr.c
+++ b/fs/lockd/clntxdr.c
@@ -600,16 +600,20 @@ static struct rpc_procinfo	nlm_procedures[] = {
 	PROC(GRANTED_RES,	res,		norep),
 };
 
+static unsigned int nlm_version1_counts[ARRAY_SIZE(nlm_procedures)];
 static const struct rpc_version	nlm_version1 = {
 	.number		= 1,
 	.nrprocs	= ARRAY_SIZE(nlm_procedures),
 	.procs		= nlm_procedures,
+	.counts		= nlm_version1_counts,
 };
 
+static unsigned int nlm_version3_counts[ARRAY_SIZE(nlm_procedures)];
 static const struct rpc_version	nlm_version3 = {
 	.number		= 3,
 	.nrprocs	= ARRAY_SIZE(nlm_procedures),
 	.procs		= nlm_procedures,
+	.counts		= nlm_version3_counts,
 };
 
 static const struct rpc_version	*nlm_versions[] = {
diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c
index 62424e929a7f..fe4ec82764fe 100644
--- a/fs/lockd/mon.c
+++ b/fs/lockd/mon.c
@@ -552,10 +552,12 @@ static struct rpc_procinfo	nsm_procedures[] = {
 	},
 };
 
+static unsigned int nsm_version1_counts[ARRAY_SIZE(nsm_procedures)];
 static const struct rpc_version nsm_version1 = {
 	.number		= 1,
 	.nrprocs	= ARRAY_SIZE(nsm_procedures),
-	.procs		= nsm_procedures
+	.procs		= nsm_procedures,
+	.counts		= nsm_version1_counts,
 };
 
 static const struct rpc_version *nsm_version[] = {
diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c
index 806657d65074..d25914aa8bf9 100644
--- a/fs/nfs/mount_clnt.c
+++ b/fs/nfs/mount_clnt.c
@@ -504,17 +504,20 @@ static struct rpc_procinfo mnt3_procedures[] = {
 	},
 };
 
-
+static unsigned int mnt_counts[ARRAY_SIZE(mnt_procedures)];
 static const struct rpc_version mnt_version1 = {
 	.number		= 1,
 	.nrprocs	= ARRAY_SIZE(mnt_procedures),
 	.procs		= mnt_procedures,
+	.counts		= mnt_counts,
 };
 
+static unsigned int mnt3_counts[ARRAY_SIZE(mnt_procedures)];
 static const struct rpc_version mnt_version3 = {
 	.number		= 3,
 	.nrprocs	= ARRAY_SIZE(mnt3_procedures),
 	.procs		= mnt3_procedures,
+	.counts		= mnt3_counts,
 };
 
 static const struct rpc_version *mnt_version[] = {
diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c
index a299648ea321..16b4526299c1 100644
--- a/fs/nfs/nfs2xdr.c
+++ b/fs/nfs/nfs2xdr.c
@@ -1170,8 +1170,10 @@ struct rpc_procinfo	nfs_procedures[] = {
 	PROC(STATFS,	fhandle,	statfsres,	0),
 };
 
+static unsigned int nfs_version2_counts[ARRAY_SIZE(nfs_procedures)];
 const struct rpc_version nfs_version2 = {
 	.number			= 2,
 	.nrprocs		= ARRAY_SIZE(nfs_procedures),
-	.procs			= nfs_procedures
+	.procs			= nfs_procedures,
+	.counts			= nfs_version2_counts,
 };
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index cc272eb8be3e..a017ec5c7a9d 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -2578,10 +2578,12 @@ struct rpc_procinfo	nfs3_procedures[] = {
 	PROC(COMMIT,		commit,		commit,		5),
 };
 
+static unsigned int nfs_version3_counts[ARRAY_SIZE(nfs3_procedures)];
 const struct rpc_version nfs_version3 = {
 	.number			= 3,
 	.nrprocs		= ARRAY_SIZE(nfs3_procedures),
-	.procs			= nfs3_procedures
+	.procs			= nfs3_procedures,
+	.counts			= nfs_version3_counts,
 };
 
 #ifdef CONFIG_NFS_V3_ACL
@@ -2606,10 +2608,12 @@ static struct rpc_procinfo	nfs3_acl_procedures[] = {
 	},
 };
 
+static unsigned int nfs3_acl_counts[ARRAY_SIZE(nfs3_acl_procedures)];
 const struct rpc_version nfsacl_version3 = {
 	.number			= 3,
 	.nrprocs		= sizeof(nfs3_acl_procedures)/
 				  sizeof(nfs3_acl_procedures[0]),
 	.procs			= nfs3_acl_procedures,
+	.counts			= nfs3_acl_counts,
 };
 #endif  /* CONFIG_NFS_V3_ACL */
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 797f3ce75286..40cf5529e65f 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -7661,10 +7661,12 @@ struct rpc_procinfo	nfs4_procedures[] = {
 #endif /* CONFIG_NFS_V4_2 */
 };
 
+static unsigned int nfs_version4_counts[ARRAY_SIZE(nfs4_procedures)];
 const struct rpc_version nfs_version4 = {
 	.number			= 4,
 	.nrprocs		= ARRAY_SIZE(nfs4_procedures),
-	.procs			= nfs4_procedures
+	.procs			= nfs4_procedures,
+	.counts			= nfs_version4_counts,
 };
 
 /*
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index a2bedbd05b2b..afa961fe073c 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -705,6 +705,7 @@ static struct rpc_procinfo nfs4_cb_procedures[] = {
 	PROC(CB_NOTIFY_LOCK,	COMPOUND,	cb_notify_lock,	cb_notify_lock),
 };
 
+static unsigned int nfs4_cb_counts[ARRAY_SIZE(nfs4_cb_procedures)];
 static struct rpc_version nfs_cb_version4 = {
 /*
  * Note on the callback rpc program version number: despite language in rfc
@@ -715,7 +716,8 @@ static struct rpc_version nfs_cb_version4 = {
  */
 	.number			= 1,
 	.nrprocs		= ARRAY_SIZE(nfs4_cb_procedures),
-	.procs			= nfs4_cb_procedures
+	.procs			= nfs4_cb_procedures,
+	.counts			= nfs4_cb_counts,
 };
 
 static const struct rpc_version *nfs_cb_version[] = {
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 6095ecba0dde..c75ba37151fe 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -88,6 +88,7 @@ struct rpc_version {
 	u32			number;		/* version number */
 	unsigned int		nrprocs;	/* number of procs */
 	struct rpc_procinfo *	procs;		/* procedure array */
+	unsigned int		*counts;	/* call counts */
 };
 
 /*
@@ -99,7 +100,6 @@ struct rpc_procinfo {
 	kxdrdproc_t		p_decode;	/* XDR decode function */
 	unsigned int		p_arglen;	/* argument hdr length (u32) */
 	unsigned int		p_replen;	/* reply hdr length (u32) */
-	unsigned int		p_count;	/* call count */
 	unsigned int		p_timer;	/* Which RTT timer to use */
 	u32			p_statidx;	/* Which procedure to account */
 	const char *		p_name;		/* name of procedure */
diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c
index a80b8e607478..f8729b647605 100644
--- a/net/sunrpc/auth_gss/gss_rpc_upcall.c
+++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c
@@ -364,11 +364,12 @@ void gssp_free_upcall_data(struct gssp_upcall_data *data)
 /*
  * Initialization stuff
  */
-
+static unsigned int gssp_version1_counts[ARRAY_SIZE(gssp_procedures)];
 static const struct rpc_version gssp_version1 = {
 	.number		= GSSPROXY_VERS_1,
 	.nrprocs	= ARRAY_SIZE(gssp_procedures),
 	.procs		= gssp_procedures,
+	.counts		= gssp_version1_counts,
 };
 
 static const struct rpc_version *gssp_version[] = {
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 964d5c4a1b60..f2d1f971247b 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1517,14 +1517,16 @@ static void
 call_start(struct rpc_task *task)
 {
 	struct rpc_clnt	*clnt = task->tk_client;
+	int idx = task->tk_msg.rpc_proc->p_statidx;
 
 	dprintk("RPC: %5u call_start %s%d proc %s (%s)\n", task->tk_pid,
 			clnt->cl_program->name, clnt->cl_vers,
 			rpc_proc_name(task),
 			(RPC_IS_ASYNC(task) ? "async" : "sync"));
 
-	/* Increment call count */
-	task->tk_msg.rpc_proc->p_count++;
+	/* Increment call count (version might not be valid for ping) */
+	if (clnt->cl_program->version[clnt->cl_vers])
+		clnt->cl_program->version[clnt->cl_vers]->counts[idx]++;
 	clnt->cl_stats->rpccnt++;
 	task->tk_action = call_reserve;
 }
diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c
index f67b9e2897b4..9d47b9d3bbee 100644
--- a/net/sunrpc/rpcb_clnt.c
+++ b/net/sunrpc/rpcb_clnt.c
@@ -1117,22 +1117,28 @@ static const struct rpcb_info rpcb_next_version6[] = {
 	},
 };
 
+static unsigned int rpcb_version2_counts[ARRAY_SIZE(rpcb_procedures2)];
 static const struct rpc_version rpcb_version2 = {
 	.number		= RPCBVERS_2,
 	.nrprocs	= ARRAY_SIZE(rpcb_procedures2),
-	.procs		= rpcb_procedures2
+	.procs		= rpcb_procedures2,
+	.counts		= rpcb_version2_counts,
 };
 
+static unsigned int rpcb_version3_counts[ARRAY_SIZE(rpcb_procedures3)];
 static const struct rpc_version rpcb_version3 = {
 	.number		= RPCBVERS_3,
 	.nrprocs	= ARRAY_SIZE(rpcb_procedures3),
-	.procs		= rpcb_procedures3
+	.procs		= rpcb_procedures3,
+	.counts		= rpcb_version3_counts,
 };
 
+static unsigned int rpcb_version4_counts[ARRAY_SIZE(rpcb_procedures4)];
 static const struct rpc_version rpcb_version4 = {
 	.number		= RPCBVERS_4,
 	.nrprocs	= ARRAY_SIZE(rpcb_procedures4),
-	.procs		= rpcb_procedures4
+	.procs		= rpcb_procedures4,
+	.counts		= rpcb_version4_counts,
 };
 
 static const struct rpc_version *rpcb_version[] = {
diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c
index caeb01ad2b5a..91c84d18bf9a 100644
--- a/net/sunrpc/stats.c
+++ b/net/sunrpc/stats.c
@@ -55,8 +55,7 @@ static int rpc_proc_show(struct seq_file *seq, void *v) {
 		seq_printf(seq, "proc%u %u",
 					vers->number, vers->nrprocs);
 		for (j = 0; j < vers->nrprocs; j++)
-			seq_printf(seq, " %u",
-					vers->procs[j].p_count);
+			seq_printf(seq, " %u", vers->counts[j]);
 		seq_putc(seq, '\n');
 	}
 	return 0;
-- 
cgit v1.2.3


From 511e936bf2b3e8be2a3160ace3d86be07962a7a8 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 12 May 2017 15:36:49 +0200
Subject: sunrpc: mark all struct rpc_procinfo instances as const

struct rpc_procinfo contains function pointers, and marking it as
constant avoids it being able to be used as an attach vector for
code injections.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 fs/lockd/clnt4xdr.c                  |  2 +-
 fs/lockd/clntxdr.c                   |  2 +-
 fs/lockd/mon.c                       |  2 +-
 fs/nfs/internal.h                    |  6 +++---
 fs/nfs/mount_clnt.c                  |  4 ++--
 fs/nfs/nfs2xdr.c                     |  2 +-
 fs/nfs/nfs3xdr.c                     |  4 ++--
 fs/nfs/nfs4_fs.h                     |  2 +-
 fs/nfs/nfs4xdr.c                     |  2 +-
 fs/nfsd/nfs4callback.c               |  2 +-
 include/linux/sunrpc/clnt.h          |  4 ++--
 include/linux/sunrpc/sched.h         |  2 +-
 net/sunrpc/auth_gss/gss_rpc_upcall.c |  2 +-
 net/sunrpc/clnt.c                    |  4 ++--
 net/sunrpc/rpcb_clnt.c               | 19 ++++++++++---------
 net/sunrpc/stats.c                   |  2 +-
 16 files changed, 31 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/fs/lockd/clnt4xdr.c b/fs/lockd/clnt4xdr.c
index 7c255d1d7c64..c349fc0f9b80 100644
--- a/fs/lockd/clnt4xdr.c
+++ b/fs/lockd/clnt4xdr.c
@@ -584,7 +584,7 @@ out:
 	.p_name      = #proc,						\
 	}
 
-static struct rpc_procinfo	nlm4_procedures[] = {
+static const struct rpc_procinfo nlm4_procedures[] = {
 	PROC(TEST,		testargs,	testres),
 	PROC(LOCK,		lockargs,	res),
 	PROC(CANCEL,		cancargs,	res),
diff --git a/fs/lockd/clntxdr.c b/fs/lockd/clntxdr.c
index 39500c5743a5..3b4724a6c4ee 100644
--- a/fs/lockd/clntxdr.c
+++ b/fs/lockd/clntxdr.c
@@ -582,7 +582,7 @@ out:
 	.p_name      = #proc,						\
 	}
 
-static struct rpc_procinfo	nlm_procedures[] = {
+static const struct rpc_procinfo nlm_procedures[] = {
 	PROC(TEST,		testargs,	testres),
 	PROC(LOCK,		lockargs,	res),
 	PROC(CANCEL,		cancargs,	res),
diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c
index fe4ec82764fe..9d8166c39c54 100644
--- a/fs/lockd/mon.c
+++ b/fs/lockd/mon.c
@@ -531,7 +531,7 @@ static int nsm_xdr_dec_stat(struct rpc_rqst *rqstp,
 #define SM_monres_sz	2
 #define SM_unmonres_sz	1
 
-static struct rpc_procinfo	nsm_procedures[] = {
+static const struct rpc_procinfo nsm_procedures[] = {
 [NSMPROC_MON] = {
 		.p_proc		= NSMPROC_MON,
 		.p_encode	= nsm_xdr_enc_mon,
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 3e24392f2caa..dc2a29a7d48b 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -270,12 +270,12 @@ static inline bool nfs_match_open_context(const struct nfs_open_context *ctx1,
 }
 
 /* nfs2xdr.c */
-extern struct rpc_procinfo nfs_procedures[];
+extern const struct rpc_procinfo nfs_procedures[];
 extern int nfs2_decode_dirent(struct xdr_stream *,
 				struct nfs_entry *, int);
 
 /* nfs3xdr.c */
-extern struct rpc_procinfo nfs3_procedures[];
+extern const struct rpc_procinfo nfs3_procedures[];
 extern int nfs3_decode_dirent(struct xdr_stream *,
 				struct nfs_entry *, int);
 
@@ -292,7 +292,7 @@ extern const u32 nfs41_maxgetdevinfo_overhead;
 
 /* nfs4proc.c */
 #if IS_ENABLED(CONFIG_NFS_V4)
-extern struct rpc_procinfo nfs4_procedures[];
+extern const struct rpc_procinfo nfs4_procedures[];
 #endif
 
 #ifdef CONFIG_NFS_V4_SECURITY_LABEL
diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c
index d25914aa8bf9..3efe946672be 100644
--- a/fs/nfs/mount_clnt.c
+++ b/fs/nfs/mount_clnt.c
@@ -466,7 +466,7 @@ static int mnt_xdr_dec_mountres3(struct rpc_rqst *req,
 	return decode_auth_flavors(xdr, res);
 }
 
-static struct rpc_procinfo mnt_procedures[] = {
+static const struct rpc_procinfo mnt_procedures[] = {
 	[MOUNTPROC_MNT] = {
 		.p_proc		= MOUNTPROC_MNT,
 		.p_encode	= mnt_xdr_enc_dirpath,
@@ -485,7 +485,7 @@ static struct rpc_procinfo mnt_procedures[] = {
 	},
 };
 
-static struct rpc_procinfo mnt3_procedures[] = {
+static const struct rpc_procinfo mnt3_procedures[] = {
 	[MOUNTPROC3_MNT] = {
 		.p_proc		= MOUNTPROC3_MNT,
 		.p_encode	= mnt_xdr_enc_dirpath,
diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c
index 16b4526299c1..c8a7e98c1371 100644
--- a/fs/nfs/nfs2xdr.c
+++ b/fs/nfs/nfs2xdr.c
@@ -1152,7 +1152,7 @@ static int nfs_stat_to_errno(enum nfs_stat status)
 	.p_statidx  =  NFSPROC_##proc,					\
 	.p_name     =  #proc,						\
 	}
-struct rpc_procinfo	nfs_procedures[] = {
+const struct rpc_procinfo nfs_procedures[] = {
 	PROC(GETATTR,	fhandle,	attrstat,	1),
 	PROC(SETATTR,	sattrargs,	attrstat,	0),
 	PROC(LOOKUP,	diropargs,	diropres,	2),
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index 85ff1187e637..670eddb3ae36 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -2554,7 +2554,7 @@ static int nfs3_stat_to_errno(enum nfs_stat status)
 	.p_name      = #proc,						\
 	}
 
-struct rpc_procinfo	nfs3_procedures[] = {
+const struct rpc_procinfo nfs3_procedures[] = {
 	PROC(GETATTR,		getattr,	getattr,	1),
 	PROC(SETATTR,		setattr,	setattr,	0),
 	PROC(LOOKUP,		lookup,		lookup,		2),
@@ -2587,7 +2587,7 @@ const struct rpc_version nfs_version3 = {
 };
 
 #ifdef CONFIG_NFS_V3_ACL
-static struct rpc_procinfo	nfs3_acl_procedures[] = {
+static const struct rpc_procinfo nfs3_acl_procedures[] = {
 	[ACLPROC3_GETACL] = {
 		.p_proc = ACLPROC3_GETACL,
 		.p_encode = nfs3_xdr_enc_getacl3args,
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index af285cc27ccf..9b0cf3872722 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -493,7 +493,7 @@ static inline void nfs4_unregister_sysctl(void)
 #endif
 
 /* nfs4xdr.c */
-extern struct rpc_procinfo nfs4_procedures[];
+extern const struct rpc_procinfo nfs4_procedures[];
 
 struct nfs4_mount_data;
 
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 40cf5529e65f..0f1f290c97cd 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -7594,7 +7594,7 @@ nfs4_stat_to_errno(int stat)
 	.p_name = #proc,	\
 }
 
-struct rpc_procinfo	nfs4_procedures[] = {
+const struct rpc_procinfo nfs4_procedures[] = {
 	PROC(READ,		enc_read,		dec_read),
 	PROC(WRITE,		enc_write,		dec_write),
 	PROC(COMMIT,		enc_commit,		dec_commit),
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index afa961fe073c..ac10f78c0fb3 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -696,7 +696,7 @@ static int nfs4_xdr_dec_cb_notify_lock(struct rpc_rqst *rqstp,
 	.p_name    = #proc,						\
 }
 
-static struct rpc_procinfo nfs4_cb_procedures[] = {
+static const struct rpc_procinfo nfs4_cb_procedures[] = {
 	PROC(CB_NULL,	NULL,		cb_null,	cb_null),
 	PROC(CB_RECALL,	COMPOUND,	cb_recall,	cb_recall),
 #ifdef CONFIG_NFSD_PNFS
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index c75ba37151fe..55ef67bea06b 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -39,7 +39,7 @@ struct rpc_clnt {
 	struct list_head	cl_tasks;	/* List of tasks */
 	spinlock_t		cl_lock;	/* spinlock */
 	struct rpc_xprt __rcu *	cl_xprt;	/* transport */
-	struct rpc_procinfo *	cl_procinfo;	/* procedure info */
+	const struct rpc_procinfo *cl_procinfo;	/* procedure info */
 	u32			cl_prog,	/* RPC program number */
 				cl_vers,	/* RPC version number */
 				cl_maxproc;	/* max procedure number */
@@ -87,7 +87,7 @@ struct rpc_program {
 struct rpc_version {
 	u32			number;		/* version number */
 	unsigned int		nrprocs;	/* number of procs */
-	struct rpc_procinfo *	procs;		/* procedure array */
+	const struct rpc_procinfo *procs;	/* procedure array */
 	unsigned int		*counts;	/* call counts */
 };
 
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index 7ba040c797ec..ed60253abd0a 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -22,7 +22,7 @@
  */
 struct rpc_procinfo;
 struct rpc_message {
-	struct rpc_procinfo *	rpc_proc;	/* Procedure information */
+	const struct rpc_procinfo *rpc_proc;	/* Procedure information */
 	void *			rpc_argp;	/* Arguments */
 	void *			rpc_resp;	/* Result */
 	struct rpc_cred *	rpc_cred;	/* Credentials */
diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c
index f8729b647605..46b295e4f2b8 100644
--- a/net/sunrpc/auth_gss/gss_rpc_upcall.c
+++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c
@@ -63,7 +63,7 @@ enum {
 	.p_name   = #proc,				\
 }
 
-static struct rpc_procinfo gssp_procedures[] = {
+static const struct rpc_procinfo gssp_procedures[] = {
 	PROC(INDICATE_MECHS, indicate_mechs),
         PROC(GET_CALL_CONTEXT, get_call_context),
         PROC(IMPORT_AND_CANON_NAME, import_and_canon_name),
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index f2d1f971247b..2e49d1f892b7 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1674,7 +1674,7 @@ call_allocate(struct rpc_task *task)
 	unsigned int slack = task->tk_rqstp->rq_cred->cr_auth->au_cslack;
 	struct rpc_rqst *req = task->tk_rqstp;
 	struct rpc_xprt *xprt = req->rq_xprt;
-	struct rpc_procinfo *proc = task->tk_msg.rpc_proc;
+	const struct rpc_procinfo *proc = task->tk_msg.rpc_proc;
 	int status;
 
 	dprint_status(task);
@@ -2489,7 +2489,7 @@ static int rpcproc_decode_null(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	return 0;
 }
 
-static struct rpc_procinfo rpcproc_null = {
+static const struct rpc_procinfo rpcproc_null = {
 	.p_encode = rpcproc_encode_null,
 	.p_decode = rpcproc_decode_null,
 };
diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c
index 9d47b9d3bbee..ea0676f199c8 100644
--- a/net/sunrpc/rpcb_clnt.c
+++ b/net/sunrpc/rpcb_clnt.c
@@ -128,13 +128,13 @@ struct rpcbind_args {
 	int			r_status;
 };
 
-static struct rpc_procinfo rpcb_procedures2[];
-static struct rpc_procinfo rpcb_procedures3[];
-static struct rpc_procinfo rpcb_procedures4[];
+static const struct rpc_procinfo rpcb_procedures2[];
+static const struct rpc_procinfo rpcb_procedures3[];
+static const struct rpc_procinfo rpcb_procedures4[];
 
 struct rpcb_info {
 	u32			rpc_vers;
-	struct rpc_procinfo *	rpc_proc;
+	const struct rpc_procinfo *rpc_proc;
 };
 
 static const struct rpcb_info rpcb_next_version[];
@@ -620,7 +620,8 @@ int rpcb_v4_register(struct net *net, const u32 program, const u32 version,
 	return -EAFNOSUPPORT;
 }
 
-static struct rpc_task *rpcb_call_async(struct rpc_clnt *rpcb_clnt, struct rpcbind_args *map, struct rpc_procinfo *proc)
+static struct rpc_task *rpcb_call_async(struct rpc_clnt *rpcb_clnt,
+		struct rpcbind_args *map, const struct rpc_procinfo *proc)
 {
 	struct rpc_message msg = {
 		.rpc_proc = proc,
@@ -671,7 +672,7 @@ static struct rpc_clnt *rpcb_find_transport_owner(struct rpc_clnt *clnt)
 void rpcb_getport_async(struct rpc_task *task)
 {
 	struct rpc_clnt *clnt;
-	struct rpc_procinfo *proc;
+	const struct rpc_procinfo *proc;
 	u32 bind_version;
 	struct rpc_xprt *xprt;
 	struct rpc_clnt	*rpcb_clnt;
@@ -994,7 +995,7 @@ out_fail:
  * since the Linux kernel RPC code requires only these.
  */
 
-static struct rpc_procinfo rpcb_procedures2[] = {
+static const struct rpc_procinfo rpcb_procedures2[] = {
 	[RPCBPROC_SET] = {
 		.p_proc		= RPCBPROC_SET,
 		.p_encode	= rpcb_enc_mapping,
@@ -1027,7 +1028,7 @@ static struct rpc_procinfo rpcb_procedures2[] = {
 	},
 };
 
-static struct rpc_procinfo rpcb_procedures3[] = {
+static const struct rpc_procinfo rpcb_procedures3[] = {
 	[RPCBPROC_SET] = {
 		.p_proc		= RPCBPROC_SET,
 		.p_encode	= rpcb_enc_getaddr,
@@ -1060,7 +1061,7 @@ static struct rpc_procinfo rpcb_procedures3[] = {
 	},
 };
 
-static struct rpc_procinfo rpcb_procedures4[] = {
+static const struct rpc_procinfo rpcb_procedures4[] = {
 	[RPCBPROC_SET] = {
 		.p_proc		= RPCBPROC_SET,
 		.p_encode	= rpcb_enc_getaddr,
diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c
index 91c84d18bf9a..8b6c35ae1d57 100644
--- a/net/sunrpc/stats.c
+++ b/net/sunrpc/stats.c
@@ -191,7 +191,7 @@ void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats)
 EXPORT_SYMBOL_GPL(rpc_count_iostats);
 
 static void _print_name(struct seq_file *seq, unsigned int op,
-			struct rpc_procinfo *procs)
+			const struct rpc_procinfo *procs)
 {
 	if (procs[op].p_name)
 		seq_printf(seq, "\t%12s: ", procs[op].p_name);
-- 
cgit v1.2.3


From 1c8a5409f3c4748ff42c1721d9578dd03091f378 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 8 May 2017 17:35:49 +0200
Subject: sunrpc: properly type pc_func callbacks

Drop the argp and resp arguments as they can trivially be derived from
the rqstp argument.  With that all functions now have the same prototype,
and we can remove the unsafe casting to svc_procfunc as well as the
svc_procfunc typedef itself.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/lockd/svc4proc.c        | 118 ++++++++++++++++++++++-------------
 fs/lockd/svcproc.c         | 118 ++++++++++++++++++++++-------------
 fs/nfs/callback_xdr.c      |   7 ++-
 fs/nfsd/nfs2acl.c          |  25 ++++----
 fs/nfsd/nfs3acl.c          |  15 ++---
 fs/nfsd/nfs3proc.c         | 151 ++++++++++++++++++++++++++-------------------
 fs/nfsd/nfs4proc.c         |   9 +--
 fs/nfsd/nfsproc.c          | 104 +++++++++++++++++--------------
 fs/nfsd/nfssvc.c           |   2 +-
 include/linux/sunrpc/svc.h |   4 +-
 net/sunrpc/svc.c           |   2 +-
 11 files changed, 328 insertions(+), 227 deletions(-)

(limited to 'include')

diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index 09c576f26c7b..3e4cba029d3d 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -62,7 +62,7 @@ no_locks:
  * NULL: Test for presence of service
  */
 static __be32
-nlm4svc_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
+nlm4svc_proc_null(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: NULL          called\n");
 	return rpc_success;
@@ -72,9 +72,9 @@ nlm4svc_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
  * TEST: Check for conflicting lock
  */
 static __be32
-nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp,
-				         struct nlm_res  *resp)
+__nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 	__be32 rc = rpc_success;
@@ -99,9 +99,15 @@ nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp,
 }
 
 static __be32
-nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp,
-				         struct nlm_res  *resp)
+nlm4svc_proc_test(struct svc_rqst *rqstp)
 {
+	return __nlm4svc_proc_test(rqstp, rqstp->rq_resp);
+}
+
+static __be32
+__nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_res *resp)
+{
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 	__be32 rc = rpc_success;
@@ -141,9 +147,15 @@ nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp,
 }
 
 static __be32
-nlm4svc_proc_cancel(struct svc_rqst *rqstp, struct nlm_args *argp,
-				           struct nlm_res  *resp)
+nlm4svc_proc_lock(struct svc_rqst *rqstp)
+{
+	return __nlm4svc_proc_lock(rqstp, rqstp->rq_resp);
+}
+
+static __be32
+__nlm4svc_proc_cancel(struct svc_rqst *rqstp, struct nlm_res *resp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 
@@ -170,13 +182,19 @@ nlm4svc_proc_cancel(struct svc_rqst *rqstp, struct nlm_args *argp,
 	return rpc_success;
 }
 
+static __be32
+nlm4svc_proc_cancel(struct svc_rqst *rqstp)
+{
+	return __nlm4svc_proc_cancel(rqstp, rqstp->rq_resp);
+}
+
 /*
  * UNLOCK: release a lock
  */
 static __be32
-nlm4svc_proc_unlock(struct svc_rqst *rqstp, struct nlm_args *argp,
-				           struct nlm_res  *resp)
+__nlm4svc_proc_unlock(struct svc_rqst *rqstp, struct nlm_res *resp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 
@@ -203,14 +221,21 @@ nlm4svc_proc_unlock(struct svc_rqst *rqstp, struct nlm_args *argp,
 	return rpc_success;
 }
 
+static __be32
+nlm4svc_proc_unlock(struct svc_rqst *rqstp)
+{
+	return __nlm4svc_proc_unlock(rqstp, rqstp->rq_resp);
+}
+
 /*
  * GRANTED: A server calls us to tell that a process' lock request
  * was granted
  */
 static __be32
-nlm4svc_proc_granted(struct svc_rqst *rqstp, struct nlm_args *argp,
-				            struct nlm_res  *resp)
+__nlm4svc_proc_granted(struct svc_rqst *rqstp, struct nlm_res *resp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
+
 	resp->cookie = argp->cookie;
 
 	dprintk("lockd: GRANTED       called\n");
@@ -219,6 +244,12 @@ nlm4svc_proc_granted(struct svc_rqst *rqstp, struct nlm_args *argp,
 	return rpc_success;
 }
 
+static __be32
+nlm4svc_proc_granted(struct svc_rqst *rqstp)
+{
+	return __nlm4svc_proc_granted(rqstp, rqstp->rq_resp);
+}
+
 /*
  * This is the generic lockd callback for async RPC calls
  */
@@ -243,9 +274,10 @@ static const struct rpc_call_ops nlm4svc_callback_ops = {
  * because we send the callback before the reply proper. I hope this
  * doesn't break any clients.
  */
-static __be32 nlm4svc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args *argp,
-		__be32 (*func)(struct svc_rqst *, struct nlm_args *, struct nlm_res  *))
+static __be32 nlm4svc_callback(struct svc_rqst *rqstp, u32 proc,
+		__be32 (*func)(struct svc_rqst *,  struct nlm_res *))
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 	struct nlm_rqst	*call;
 	__be32 stat;
@@ -261,7 +293,7 @@ static __be32 nlm4svc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args
 	if (call == NULL)
 		return rpc_system_err;
 
-	stat = func(rqstp, argp, &call->a_res);
+	stat = func(rqstp, &call->a_res);
 	if (stat != 0) {
 		nlmsvc_release_call(call);
 		return stat;
@@ -273,48 +305,44 @@ static __be32 nlm4svc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args
 	return rpc_success;
 }
 
-static __be32 nlm4svc_proc_test_msg(struct svc_rqst *rqstp, struct nlm_args *argp,
-					     void	     *resp)
+static __be32 nlm4svc_proc_test_msg(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: TEST_MSG      called\n");
-	return nlm4svc_callback(rqstp, NLMPROC_TEST_RES, argp, nlm4svc_proc_test);
+	return nlm4svc_callback(rqstp, NLMPROC_TEST_RES, __nlm4svc_proc_test);
 }
 
-static __be32 nlm4svc_proc_lock_msg(struct svc_rqst *rqstp, struct nlm_args *argp,
-					     void	     *resp)
+static __be32 nlm4svc_proc_lock_msg(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: LOCK_MSG      called\n");
-	return nlm4svc_callback(rqstp, NLMPROC_LOCK_RES, argp, nlm4svc_proc_lock);
+	return nlm4svc_callback(rqstp, NLMPROC_LOCK_RES, __nlm4svc_proc_lock);
 }
 
-static __be32 nlm4svc_proc_cancel_msg(struct svc_rqst *rqstp, struct nlm_args *argp,
-					       void	       *resp)
+static __be32 nlm4svc_proc_cancel_msg(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: CANCEL_MSG    called\n");
-	return nlm4svc_callback(rqstp, NLMPROC_CANCEL_RES, argp, nlm4svc_proc_cancel);
+	return nlm4svc_callback(rqstp, NLMPROC_CANCEL_RES, __nlm4svc_proc_cancel);
 }
 
-static __be32 nlm4svc_proc_unlock_msg(struct svc_rqst *rqstp, struct nlm_args *argp,
-                                               void            *resp)
+static __be32 nlm4svc_proc_unlock_msg(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: UNLOCK_MSG    called\n");
-	return nlm4svc_callback(rqstp, NLMPROC_UNLOCK_RES, argp, nlm4svc_proc_unlock);
+	return nlm4svc_callback(rqstp, NLMPROC_UNLOCK_RES, __nlm4svc_proc_unlock);
 }
 
-static __be32 nlm4svc_proc_granted_msg(struct svc_rqst *rqstp, struct nlm_args *argp,
-                                                void            *resp)
+static __be32 nlm4svc_proc_granted_msg(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: GRANTED_MSG   called\n");
-	return nlm4svc_callback(rqstp, NLMPROC_GRANTED_RES, argp, nlm4svc_proc_granted);
+	return nlm4svc_callback(rqstp, NLMPROC_GRANTED_RES, __nlm4svc_proc_granted);
 }
 
 /*
  * SHARE: create a DOS share or alter existing share.
  */
 static __be32
-nlm4svc_proc_share(struct svc_rqst *rqstp, struct nlm_args *argp,
-				          struct nlm_res  *resp)
+nlm4svc_proc_share(struct svc_rqst *rqstp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
+	struct nlm_res *resp = rqstp->rq_resp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 
@@ -345,9 +373,10 @@ nlm4svc_proc_share(struct svc_rqst *rqstp, struct nlm_args *argp,
  * UNSHARE: Release a DOS share.
  */
 static __be32
-nlm4svc_proc_unshare(struct svc_rqst *rqstp, struct nlm_args *argp,
-				            struct nlm_res  *resp)
+nlm4svc_proc_unshare(struct svc_rqst *rqstp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
+	struct nlm_res *resp = rqstp->rq_resp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 
@@ -378,22 +407,23 @@ nlm4svc_proc_unshare(struct svc_rqst *rqstp, struct nlm_args *argp,
  * NM_LOCK: Create an unmonitored lock
  */
 static __be32
-nlm4svc_proc_nm_lock(struct svc_rqst *rqstp, struct nlm_args *argp,
-				            struct nlm_res  *resp)
+nlm4svc_proc_nm_lock(struct svc_rqst *rqstp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
+
 	dprintk("lockd: NM_LOCK       called\n");
 
 	argp->monitor = 0;		/* just clean the monitor flag */
-	return nlm4svc_proc_lock(rqstp, argp, resp);
+	return nlm4svc_proc_lock(rqstp);
 }
 
 /*
  * FREE_ALL: Release all locks and shares held by client
  */
 static __be32
-nlm4svc_proc_free_all(struct svc_rqst *rqstp, struct nlm_args *argp,
-					     void            *resp)
+nlm4svc_proc_free_all(struct svc_rqst *rqstp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 
 	/* Obtain client */
@@ -409,9 +439,10 @@ nlm4svc_proc_free_all(struct svc_rqst *rqstp, struct nlm_args *argp,
  * SM_NOTIFY: private callback from statd (not part of official NLM proto)
  */
 static __be32
-nlm4svc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp,
-					      void	        *resp)
+nlm4svc_proc_sm_notify(struct svc_rqst *rqstp)
 {
+	struct nlm_reboot *argp = rqstp->rq_argp;
+
 	dprintk("lockd: SM_NOTIFY     called\n");
 
 	if (!nlm_privileged_requester(rqstp)) {
@@ -429,9 +460,10 @@ nlm4svc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp,
  * client sent a GRANTED_RES, let's remove the associated block
  */
 static __be32
-nlm4svc_proc_granted_res(struct svc_rqst *rqstp, struct nlm_res  *argp,
-                                                void            *resp)
+nlm4svc_proc_granted_res(struct svc_rqst *rqstp)
 {
+	struct nlm_res *argp = rqstp->rq_argp;
+
         if (!nlmsvc_ops)
                 return rpc_success;
 
@@ -463,7 +495,7 @@ nlm4svc_proc_granted_res(struct svc_rqst *rqstp, struct nlm_res  *argp,
 struct nlm_void			{ int dummy; };
 
 #define PROC(name, xargt, xrest, argt, rest, respsize)	\
- { .pc_func	= (svc_procfunc) nlm4svc_proc_##name,	\
+ { .pc_func	= nlm4svc_proc_##name,	\
    .pc_decode	= (kxdrproc_t) nlm4svc_decode_##xargt,	\
    .pc_encode	= (kxdrproc_t) nlm4svc_encode_##xrest,	\
    .pc_release	= NULL,					\
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index fb26b9f522e7..3add50661fab 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -92,7 +92,7 @@ no_locks:
  * NULL: Test for presence of service
  */
 static __be32
-nlmsvc_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
+nlmsvc_proc_null(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: NULL          called\n");
 	return rpc_success;
@@ -102,9 +102,9 @@ nlmsvc_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
  * TEST: Check for conflicting lock
  */
 static __be32
-nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp,
-				         struct nlm_res  *resp)
+__nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 	__be32 rc = rpc_success;
@@ -130,9 +130,15 @@ nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp,
 }
 
 static __be32
-nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp,
-				         struct nlm_res  *resp)
+nlmsvc_proc_test(struct svc_rqst *rqstp)
 {
+	return __nlmsvc_proc_test(rqstp, rqstp->rq_resp);
+}
+
+static __be32
+__nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_res *resp)
+{
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 	__be32 rc = rpc_success;
@@ -172,9 +178,15 @@ nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp,
 }
 
 static __be32
-nlmsvc_proc_cancel(struct svc_rqst *rqstp, struct nlm_args *argp,
-				           struct nlm_res  *resp)
+nlmsvc_proc_lock(struct svc_rqst *rqstp)
+{
+	return __nlmsvc_proc_lock(rqstp, rqstp->rq_resp);
+}
+
+static __be32
+__nlmsvc_proc_cancel(struct svc_rqst *rqstp, struct nlm_res *resp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 	struct net *net = SVC_NET(rqstp);
@@ -202,13 +214,19 @@ nlmsvc_proc_cancel(struct svc_rqst *rqstp, struct nlm_args *argp,
 	return rpc_success;
 }
 
+static __be32
+nlmsvc_proc_cancel(struct svc_rqst *rqstp)
+{
+	return __nlmsvc_proc_cancel(rqstp, rqstp->rq_resp);
+}
+
 /*
  * UNLOCK: release a lock
  */
 static __be32
-nlmsvc_proc_unlock(struct svc_rqst *rqstp, struct nlm_args *argp,
-				           struct nlm_res  *resp)
+__nlmsvc_proc_unlock(struct svc_rqst *rqstp, struct nlm_res *resp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 	struct net *net = SVC_NET(rqstp);
@@ -236,14 +254,21 @@ nlmsvc_proc_unlock(struct svc_rqst *rqstp, struct nlm_args *argp,
 	return rpc_success;
 }
 
+static __be32
+nlmsvc_proc_unlock(struct svc_rqst *rqstp)
+{
+	return __nlmsvc_proc_unlock(rqstp, rqstp->rq_resp);
+}
+
 /*
  * GRANTED: A server calls us to tell that a process' lock request
  * was granted
  */
 static __be32
-nlmsvc_proc_granted(struct svc_rqst *rqstp, struct nlm_args *argp,
-				            struct nlm_res  *resp)
+__nlmsvc_proc_granted(struct svc_rqst *rqstp, struct nlm_res *resp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
+
 	resp->cookie = argp->cookie;
 
 	dprintk("lockd: GRANTED       called\n");
@@ -252,6 +277,12 @@ nlmsvc_proc_granted(struct svc_rqst *rqstp, struct nlm_args *argp,
 	return rpc_success;
 }
 
+static __be32
+nlmsvc_proc_granted(struct svc_rqst *rqstp)
+{
+	return __nlmsvc_proc_granted(rqstp, rqstp->rq_resp);
+}
+
 /*
  * This is the generic lockd callback for async RPC calls
  */
@@ -284,9 +315,10 @@ static const struct rpc_call_ops nlmsvc_callback_ops = {
  * because we send the callback before the reply proper. I hope this
  * doesn't break any clients.
  */
-static __be32 nlmsvc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args *argp,
-		__be32 (*func)(struct svc_rqst *, struct nlm_args *, struct nlm_res  *))
+static __be32 nlmsvc_callback(struct svc_rqst *rqstp, u32 proc,
+		__be32 (*func)(struct svc_rqst *, struct nlm_res *))
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 	struct nlm_rqst	*call;
 	__be32 stat;
@@ -302,7 +334,7 @@ static __be32 nlmsvc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args
 	if (call == NULL)
 		return rpc_system_err;
 
-	stat = func(rqstp, argp, &call->a_res);
+	stat = func(rqstp, &call->a_res);
 	if (stat != 0) {
 		nlmsvc_release_call(call);
 		return stat;
@@ -314,50 +346,46 @@ static __be32 nlmsvc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args
 	return rpc_success;
 }
 
-static __be32 nlmsvc_proc_test_msg(struct svc_rqst *rqstp, struct nlm_args *argp,
-					     void	     *resp)
+static __be32 nlmsvc_proc_test_msg(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: TEST_MSG      called\n");
-	return nlmsvc_callback(rqstp, NLMPROC_TEST_RES, argp, nlmsvc_proc_test);
+	return nlmsvc_callback(rqstp, NLMPROC_TEST_RES, __nlmsvc_proc_test);
 }
 
-static __be32 nlmsvc_proc_lock_msg(struct svc_rqst *rqstp, struct nlm_args *argp,
-					     void	     *resp)
+static __be32 nlmsvc_proc_lock_msg(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: LOCK_MSG      called\n");
-	return nlmsvc_callback(rqstp, NLMPROC_LOCK_RES, argp, nlmsvc_proc_lock);
+	return nlmsvc_callback(rqstp, NLMPROC_LOCK_RES, __nlmsvc_proc_lock);
 }
 
-static __be32 nlmsvc_proc_cancel_msg(struct svc_rqst *rqstp, struct nlm_args *argp,
-					       void	       *resp)
+static __be32 nlmsvc_proc_cancel_msg(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: CANCEL_MSG    called\n");
-	return nlmsvc_callback(rqstp, NLMPROC_CANCEL_RES, argp, nlmsvc_proc_cancel);
+	return nlmsvc_callback(rqstp, NLMPROC_CANCEL_RES, __nlmsvc_proc_cancel);
 }
 
 static __be32
-nlmsvc_proc_unlock_msg(struct svc_rqst *rqstp, struct nlm_args *argp,
-                                               void            *resp)
+nlmsvc_proc_unlock_msg(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: UNLOCK_MSG    called\n");
-	return nlmsvc_callback(rqstp, NLMPROC_UNLOCK_RES, argp, nlmsvc_proc_unlock);
+	return nlmsvc_callback(rqstp, NLMPROC_UNLOCK_RES, __nlmsvc_proc_unlock);
 }
 
 static __be32
-nlmsvc_proc_granted_msg(struct svc_rqst *rqstp, struct nlm_args *argp,
-                                                void            *resp)
+nlmsvc_proc_granted_msg(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: GRANTED_MSG   called\n");
-	return nlmsvc_callback(rqstp, NLMPROC_GRANTED_RES, argp, nlmsvc_proc_granted);
+	return nlmsvc_callback(rqstp, NLMPROC_GRANTED_RES, __nlmsvc_proc_granted);
 }
 
 /*
  * SHARE: create a DOS share or alter existing share.
  */
 static __be32
-nlmsvc_proc_share(struct svc_rqst *rqstp, struct nlm_args *argp,
-				          struct nlm_res  *resp)
+nlmsvc_proc_share(struct svc_rqst *rqstp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
+	struct nlm_res *resp = rqstp->rq_resp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 
@@ -388,9 +416,10 @@ nlmsvc_proc_share(struct svc_rqst *rqstp, struct nlm_args *argp,
  * UNSHARE: Release a DOS share.
  */
 static __be32
-nlmsvc_proc_unshare(struct svc_rqst *rqstp, struct nlm_args *argp,
-				            struct nlm_res  *resp)
+nlmsvc_proc_unshare(struct svc_rqst *rqstp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
+	struct nlm_res *resp = rqstp->rq_resp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 
@@ -421,22 +450,23 @@ nlmsvc_proc_unshare(struct svc_rqst *rqstp, struct nlm_args *argp,
  * NM_LOCK: Create an unmonitored lock
  */
 static __be32
-nlmsvc_proc_nm_lock(struct svc_rqst *rqstp, struct nlm_args *argp,
-				            struct nlm_res  *resp)
+nlmsvc_proc_nm_lock(struct svc_rqst *rqstp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
+
 	dprintk("lockd: NM_LOCK       called\n");
 
 	argp->monitor = 0;		/* just clean the monitor flag */
-	return nlmsvc_proc_lock(rqstp, argp, resp);
+	return nlmsvc_proc_lock(rqstp);
 }
 
 /*
  * FREE_ALL: Release all locks and shares held by client
  */
 static __be32
-nlmsvc_proc_free_all(struct svc_rqst *rqstp, struct nlm_args *argp,
-					     void            *resp)
+nlmsvc_proc_free_all(struct svc_rqst *rqstp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 
 	/* Obtain client */
@@ -452,9 +482,10 @@ nlmsvc_proc_free_all(struct svc_rqst *rqstp, struct nlm_args *argp,
  * SM_NOTIFY: private callback from statd (not part of official NLM proto)
  */
 static __be32
-nlmsvc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp,
-					      void	        *resp)
+nlmsvc_proc_sm_notify(struct svc_rqst *rqstp)
 {
+	struct nlm_reboot *argp = rqstp->rq_argp;
+
 	dprintk("lockd: SM_NOTIFY     called\n");
 
 	if (!nlm_privileged_requester(rqstp)) {
@@ -472,9 +503,10 @@ nlmsvc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp,
  * client sent a GRANTED_RES, let's remove the associated block
  */
 static __be32
-nlmsvc_proc_granted_res(struct svc_rqst *rqstp, struct nlm_res  *argp,
-                                                void            *resp)
+nlmsvc_proc_granted_res(struct svc_rqst *rqstp)
 {
+	struct nlm_res *argp = rqstp->rq_argp;
+
 	if (!nlmsvc_ops)
 		return rpc_success;
 
@@ -505,7 +537,7 @@ nlmsvc_proc_granted_res(struct svc_rqst *rqstp, struct nlm_res  *argp,
 struct nlm_void			{ int dummy; };
 
 #define PROC(name, xargt, xrest, argt, rest, respsize)	\
- { .pc_func	= (svc_procfunc) nlmsvc_proc_##name,	\
+ { .pc_func	= nlmsvc_proc_##name,			\
    .pc_decode	= (kxdrproc_t) nlmsvc_decode_##xargt,	\
    .pc_encode	= (kxdrproc_t) nlmsvc_encode_##xrest,	\
    .pc_release	= NULL,					\
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index 287c02202b25..5a14bdaa5986 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -53,7 +53,7 @@ struct callback_op {
 
 static struct callback_op callback_ops[];
 
-static __be32 nfs4_callback_null(struct svc_rqst *rqstp, void *argp, void *resp)
+static __be32 nfs4_callback_null(struct svc_rqst *rqstp)
 {
 	return htonl(NFS4_OK);
 }
@@ -880,7 +880,7 @@ encode_hdr:
 /*
  * Decode, process and encode a COMPOUND
  */
-static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *resp)
+static __be32 nfs4_callback_compound(struct svc_rqst *rqstp)
 {
 	struct cb_compound_hdr_arg hdr_arg = { 0 };
 	struct cb_compound_hdr_res hdr_res = { NULL };
@@ -916,7 +916,8 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
 
 	while (status == 0 && nops != hdr_arg.nops) {
 		status = process_op(nops, rqstp, &xdr_in,
-				    argp, &xdr_out, resp, &cps);
+				    rqstp->rq_argp, &xdr_out, rqstp->rq_resp,
+				    &cps);
 		nops++;
 	}
 
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index 12933d07204c..4b7f84fa1fa5 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -19,7 +19,7 @@
  * NULL call.
  */
 static __be32
-nfsacld_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
+nfsacld_proc_null(struct svc_rqst *rqstp)
 {
 	return nfs_ok;
 }
@@ -27,9 +27,10 @@ nfsacld_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
 /*
  * Get the Access and/or Default ACL of a file.
  */
-static __be32 nfsacld_proc_getacl(struct svc_rqst * rqstp,
-		struct nfsd3_getaclargs *argp, struct nfsd3_getaclres *resp)
+static __be32 nfsacld_proc_getacl(struct svc_rqst *rqstp)
 {
+	struct nfsd3_getaclargs *argp = rqstp->rq_argp;
+	struct nfsd3_getaclres *resp = rqstp->rq_resp;
 	struct posix_acl *acl;
 	struct inode *inode;
 	svc_fh *fh;
@@ -87,10 +88,10 @@ fail:
 /*
  * Set the Access and/or Default ACL of a file.
  */
-static __be32 nfsacld_proc_setacl(struct svc_rqst * rqstp,
-		struct nfsd3_setaclargs *argp,
-		struct nfsd_attrstat *resp)
+static __be32 nfsacld_proc_setacl(struct svc_rqst *rqstp)
 {
+	struct nfsd3_setaclargs *argp = rqstp->rq_argp;
+	struct nfsd_attrstat *resp = rqstp->rq_resp;
 	struct inode *inode;
 	svc_fh *fh;
 	__be32 nfserr = 0;
@@ -141,9 +142,10 @@ out_errno:
 /*
  * Check file attributes
  */
-static __be32 nfsacld_proc_getattr(struct svc_rqst * rqstp,
-		struct nfsd_fhandle *argp, struct nfsd_attrstat *resp)
+static __be32 nfsacld_proc_getattr(struct svc_rqst *rqstp)
 {
+	struct nfsd_fhandle *argp = rqstp->rq_argp;
+	struct nfsd_attrstat *resp = rqstp->rq_resp;
 	__be32 nfserr;
 	dprintk("nfsd: GETATTR  %s\n", SVCFH_fmt(&argp->fh));
 
@@ -158,9 +160,10 @@ static __be32 nfsacld_proc_getattr(struct svc_rqst * rqstp,
 /*
  * Check file access
  */
-static __be32 nfsacld_proc_access(struct svc_rqst *rqstp, struct nfsd3_accessargs *argp,
-		struct nfsd3_accessres *resp)
+static __be32 nfsacld_proc_access(struct svc_rqst *rqstp)
 {
+	struct nfsd3_accessargs *argp = rqstp->rq_argp;
+	struct nfsd3_accessres *resp = rqstp->rq_resp;
 	__be32 nfserr;
 
 	dprintk("nfsd: ACCESS(2acl)   %s 0x%x\n",
@@ -347,7 +350,7 @@ struct nfsd3_voidargs { int dummy; };
 
 #define PROC(name, argt, rest, relt, cache, respsize)			\
 {									\
-	.pc_func	= (svc_procfunc) nfsacld_proc_##name,		\
+	.pc_func	= nfsacld_proc_##name,				\
 	.pc_decode	= (kxdrproc_t) nfsaclsvc_decode_##argt##args,	\
 	.pc_encode	= (kxdrproc_t) nfsaclsvc_encode_##rest##res,	\
 	.pc_release	= (kxdrproc_t) nfsaclsvc_release_##relt,	\
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index db988a229b3a..5e42004035e0 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -18,7 +18,7 @@
  * NULL call.
  */
 static __be32
-nfsd3_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
+nfsd3_proc_null(struct svc_rqst *rqstp)
 {
 	return nfs_ok;
 }
@@ -26,9 +26,10 @@ nfsd3_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
 /*
  * Get the Access and/or Default ACL of a file.
  */
-static __be32 nfsd3_proc_getacl(struct svc_rqst * rqstp,
-		struct nfsd3_getaclargs *argp, struct nfsd3_getaclres *resp)
+static __be32 nfsd3_proc_getacl(struct svc_rqst *rqstp)
 {
+	struct nfsd3_getaclargs *argp = rqstp->rq_argp;
+	struct nfsd3_getaclres *resp = rqstp->rq_resp;
 	struct posix_acl *acl;
 	struct inode *inode;
 	svc_fh *fh;
@@ -80,10 +81,10 @@ fail:
 /*
  * Set the Access and/or Default ACL of a file.
  */
-static __be32 nfsd3_proc_setacl(struct svc_rqst * rqstp,
-		struct nfsd3_setaclargs *argp,
-		struct nfsd3_attrstat *resp)
+static __be32 nfsd3_proc_setacl(struct svc_rqst *rqstp)
 {
+	struct nfsd3_setaclargs *argp = rqstp->rq_argp;
+	struct nfsd3_attrstat *resp = rqstp->rq_resp;
 	struct inode *inode;
 	svc_fh *fh;
 	__be32 nfserr = 0;
@@ -239,7 +240,7 @@ struct nfsd3_voidargs { int dummy; };
 
 #define PROC(name, argt, rest, relt, cache, respsize)			\
 {									\
-	.pc_func	= (svc_procfunc) nfsd3_proc_##name,		\
+	.pc_func	= nfsd3_proc_##name,				\
 	.pc_decode	= (kxdrproc_t) nfs3svc_decode_##argt##args,	\
 	.pc_encode	= (kxdrproc_t) nfs3svc_encode_##rest##res,	\
 	.pc_release	= (kxdrproc_t) nfs3svc_release_##relt,		\
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 24e035190770..4a2bae07cfbf 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -31,7 +31,7 @@ static int	nfs3_ftypes[] = {
  * NULL call.
  */
 static __be32
-nfsd3_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
+nfsd3_proc_null(struct svc_rqst *rqstp)
 {
 	return nfs_ok;
 }
@@ -40,9 +40,10 @@ nfsd3_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
  * Get a file's attributes
  */
 static __be32
-nfsd3_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle  *argp,
-					   struct nfsd3_attrstat *resp)
+nfsd3_proc_getattr(struct svc_rqst *rqstp)
 {
+	struct nfsd_fhandle *argp = rqstp->rq_argp;
+	struct nfsd3_attrstat *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: GETATTR(3)  %s\n",
@@ -63,9 +64,10 @@ nfsd3_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle  *argp,
  * Set a file's attributes
  */
 static __be32
-nfsd3_proc_setattr(struct svc_rqst *rqstp, struct nfsd3_sattrargs *argp,
-					   struct nfsd3_attrstat  *resp)
+nfsd3_proc_setattr(struct svc_rqst *rqstp)
 {
+	struct nfsd3_sattrargs *argp = rqstp->rq_argp;
+	struct nfsd3_attrstat *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: SETATTR(3)  %s\n",
@@ -81,9 +83,10 @@ nfsd3_proc_setattr(struct svc_rqst *rqstp, struct nfsd3_sattrargs *argp,
  * Look up a path name component
  */
 static __be32
-nfsd3_proc_lookup(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp,
-					  struct nfsd3_diropres  *resp)
+nfsd3_proc_lookup(struct svc_rqst *rqstp)
 {
+	struct nfsd3_diropargs *argp = rqstp->rq_argp;
+	struct nfsd3_diropres  *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: LOOKUP(3)   %s %.*s\n",
@@ -105,9 +108,10 @@ nfsd3_proc_lookup(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp,
  * Check file access
  */
 static __be32
-nfsd3_proc_access(struct svc_rqst *rqstp, struct nfsd3_accessargs *argp,
-					  struct nfsd3_accessres *resp)
+nfsd3_proc_access(struct svc_rqst *rqstp)
 {
+	struct nfsd3_accessargs *argp = rqstp->rq_argp;
+	struct nfsd3_accessres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: ACCESS(3)   %s 0x%x\n",
@@ -124,9 +128,10 @@ nfsd3_proc_access(struct svc_rqst *rqstp, struct nfsd3_accessargs *argp,
  * Read a symlink.
  */
 static __be32
-nfsd3_proc_readlink(struct svc_rqst *rqstp, struct nfsd3_readlinkargs *argp,
-					   struct nfsd3_readlinkres *resp)
+nfsd3_proc_readlink(struct svc_rqst *rqstp)
 {
+	struct nfsd3_readlinkargs *argp = rqstp->rq_argp;
+	struct nfsd3_readlinkres *resp = rqstp->rq_resp;
 	__be32 nfserr;
 
 	dprintk("nfsd: READLINK(3) %s\n", SVCFH_fmt(&argp->fh));
@@ -142,9 +147,10 @@ nfsd3_proc_readlink(struct svc_rqst *rqstp, struct nfsd3_readlinkargs *argp,
  * Read a portion of a file.
  */
 static __be32
-nfsd3_proc_read(struct svc_rqst *rqstp, struct nfsd3_readargs *argp,
-				        struct nfsd3_readres  *resp)
+nfsd3_proc_read(struct svc_rqst *rqstp)
 {
+	struct nfsd3_readargs *argp = rqstp->rq_argp;
+	struct nfsd3_readres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 	u32	max_blocksize = svc_max_payload(rqstp);
 	unsigned long cnt = min(argp->count, max_blocksize);
@@ -179,9 +185,10 @@ nfsd3_proc_read(struct svc_rqst *rqstp, struct nfsd3_readargs *argp,
  * Write data to a file
  */
 static __be32
-nfsd3_proc_write(struct svc_rqst *rqstp, struct nfsd3_writeargs *argp,
-					 struct nfsd3_writeres  *resp)
+nfsd3_proc_write(struct svc_rqst *rqstp)
 {
+	struct nfsd3_writeargs *argp = rqstp->rq_argp;
+	struct nfsd3_writeres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 	unsigned long cnt = argp->len;
 
@@ -206,9 +213,10 @@ nfsd3_proc_write(struct svc_rqst *rqstp, struct nfsd3_writeargs *argp,
  * first reports about SunOS compatibility problems start to pour in...
  */
 static __be32
-nfsd3_proc_create(struct svc_rqst *rqstp, struct nfsd3_createargs *argp,
-					  struct nfsd3_diropres   *resp)
+nfsd3_proc_create(struct svc_rqst *rqstp)
 {
+	struct nfsd3_createargs *argp = rqstp->rq_argp;
+	struct nfsd3_diropres *resp = rqstp->rq_resp;
 	svc_fh		*dirfhp, *newfhp = NULL;
 	struct iattr	*attr;
 	__be32		nfserr;
@@ -243,9 +251,10 @@ nfsd3_proc_create(struct svc_rqst *rqstp, struct nfsd3_createargs *argp,
  * Make directory. This operation is not idempotent.
  */
 static __be32
-nfsd3_proc_mkdir(struct svc_rqst *rqstp, struct nfsd3_createargs *argp,
-					 struct nfsd3_diropres   *resp)
+nfsd3_proc_mkdir(struct svc_rqst *rqstp)
 {
+	struct nfsd3_createargs *argp = rqstp->rq_argp;
+	struct nfsd3_diropres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: MKDIR(3)    %s %.*s\n",
@@ -263,9 +272,10 @@ nfsd3_proc_mkdir(struct svc_rqst *rqstp, struct nfsd3_createargs *argp,
 }
 
 static __be32
-nfsd3_proc_symlink(struct svc_rqst *rqstp, struct nfsd3_symlinkargs *argp,
-					   struct nfsd3_diropres    *resp)
+nfsd3_proc_symlink(struct svc_rqst *rqstp)
 {
+	struct nfsd3_symlinkargs *argp = rqstp->rq_argp;
+	struct nfsd3_diropres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: SYMLINK(3)  %s %.*s -> %.*s\n",
@@ -284,9 +294,10 @@ nfsd3_proc_symlink(struct svc_rqst *rqstp, struct nfsd3_symlinkargs *argp,
  * Make socket/fifo/device.
  */
 static __be32
-nfsd3_proc_mknod(struct svc_rqst *rqstp, struct nfsd3_mknodargs *argp,
-					 struct nfsd3_diropres  *resp)
+nfsd3_proc_mknod(struct svc_rqst *rqstp)
 {
+	struct nfsd3_mknodargs *argp = rqstp->rq_argp;
+	struct nfsd3_diropres  *resp = rqstp->rq_resp;
 	__be32	nfserr;
 	int type;
 	dev_t	rdev = 0;
@@ -321,9 +332,10 @@ nfsd3_proc_mknod(struct svc_rqst *rqstp, struct nfsd3_mknodargs *argp,
  * Remove file/fifo/socket etc.
  */
 static __be32
-nfsd3_proc_remove(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp,
-					  struct nfsd3_attrstat  *resp)
+nfsd3_proc_remove(struct svc_rqst *rqstp)
 {
+	struct nfsd3_diropargs *argp = rqstp->rq_argp;
+	struct nfsd3_attrstat *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: REMOVE(3)   %s %.*s\n",
@@ -342,9 +354,10 @@ nfsd3_proc_remove(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp,
  * Remove a directory
  */
 static __be32
-nfsd3_proc_rmdir(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp,
-					 struct nfsd3_attrstat  *resp)
+nfsd3_proc_rmdir(struct svc_rqst *rqstp)
 {
+	struct nfsd3_diropargs *argp = rqstp->rq_argp;
+	struct nfsd3_attrstat *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: RMDIR(3)    %s %.*s\n",
@@ -359,9 +372,10 @@ nfsd3_proc_rmdir(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp,
 }
 
 static __be32
-nfsd3_proc_rename(struct svc_rqst *rqstp, struct nfsd3_renameargs *argp,
-					  struct nfsd3_renameres  *resp)
+nfsd3_proc_rename(struct svc_rqst *rqstp)
 {
+	struct nfsd3_renameargs *argp = rqstp->rq_argp;
+	struct nfsd3_renameres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: RENAME(3)   %s %.*s ->\n",
@@ -381,9 +395,10 @@ nfsd3_proc_rename(struct svc_rqst *rqstp, struct nfsd3_renameargs *argp,
 }
 
 static __be32
-nfsd3_proc_link(struct svc_rqst *rqstp, struct nfsd3_linkargs *argp,
-					struct nfsd3_linkres  *resp)
+nfsd3_proc_link(struct svc_rqst *rqstp)
 {
+	struct nfsd3_linkargs *argp = rqstp->rq_argp;
+	struct nfsd3_linkres  *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: LINK(3)     %s ->\n",
@@ -404,9 +419,10 @@ nfsd3_proc_link(struct svc_rqst *rqstp, struct nfsd3_linkargs *argp,
  * Read a portion of a directory.
  */
 static __be32
-nfsd3_proc_readdir(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp,
-					   struct nfsd3_readdirres  *resp)
+nfsd3_proc_readdir(struct svc_rqst *rqstp)
 {
+	struct nfsd3_readdirargs *argp = rqstp->rq_argp;
+	struct nfsd3_readdirres  *resp = rqstp->rq_resp;
 	__be32		nfserr;
 	int		count;
 
@@ -440,9 +456,10 @@ nfsd3_proc_readdir(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp,
  * For now, we choose to ignore the dircount parameter.
  */
 static __be32
-nfsd3_proc_readdirplus(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp,
-					       struct nfsd3_readdirres  *resp)
+nfsd3_proc_readdirplus(struct svc_rqst *rqstp)
 {
+	struct nfsd3_readdirargs *argp = rqstp->rq_argp;
+	struct nfsd3_readdirres  *resp = rqstp->rq_resp;
 	__be32	nfserr;
 	int	count = 0;
 	loff_t	offset;
@@ -507,9 +524,10 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp,
  * Get file system stats
  */
 static __be32
-nfsd3_proc_fsstat(struct svc_rqst * rqstp, struct nfsd_fhandle    *argp,
-					   struct nfsd3_fsstatres *resp)
+nfsd3_proc_fsstat(struct svc_rqst *rqstp)
 {
+	struct nfsd_fhandle *argp = rqstp->rq_argp;
+	struct nfsd3_fsstatres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: FSSTAT(3)   %s\n",
@@ -524,9 +542,10 @@ nfsd3_proc_fsstat(struct svc_rqst * rqstp, struct nfsd_fhandle    *argp,
  * Get file system info
  */
 static __be32
-nfsd3_proc_fsinfo(struct svc_rqst * rqstp, struct nfsd_fhandle    *argp,
-					   struct nfsd3_fsinfores *resp)
+nfsd3_proc_fsinfo(struct svc_rqst *rqstp)
 {
+	struct nfsd_fhandle *argp = rqstp->rq_argp;
+	struct nfsd3_fsinfores *resp = rqstp->rq_resp;
 	__be32	nfserr;
 	u32	max_blocksize = svc_max_payload(rqstp);
 
@@ -567,9 +586,10 @@ nfsd3_proc_fsinfo(struct svc_rqst * rqstp, struct nfsd_fhandle    *argp,
  * Get pathconf info for the specified file
  */
 static __be32
-nfsd3_proc_pathconf(struct svc_rqst * rqstp, struct nfsd_fhandle      *argp,
-					     struct nfsd3_pathconfres *resp)
+nfsd3_proc_pathconf(struct svc_rqst *rqstp)
 {
+	struct nfsd_fhandle *argp = rqstp->rq_argp;
+	struct nfsd3_pathconfres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: PATHCONF(3) %s\n",
@@ -610,9 +630,10 @@ nfsd3_proc_pathconf(struct svc_rqst * rqstp, struct nfsd_fhandle      *argp,
  * Commit a file (range) to stable storage.
  */
 static __be32
-nfsd3_proc_commit(struct svc_rqst * rqstp, struct nfsd3_commitargs *argp,
-					   struct nfsd3_commitres  *resp)
+nfsd3_proc_commit(struct svc_rqst *rqstp)
 {
+	struct nfsd3_commitargs *argp = rqstp->rq_argp;
+	struct nfsd3_commitres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: COMMIT(3)   %s %u@%Lu\n",
@@ -655,7 +676,7 @@ struct nfsd3_voidargs { int dummy; };
 
 static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_NULL] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_null,
+		.pc_func = nfsd3_proc_null,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_voidres,
 		.pc_argsize = sizeof(struct nfsd3_voidargs),
 		.pc_ressize = sizeof(struct nfsd3_voidres),
@@ -663,7 +684,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST,
 	},
 	[NFS3PROC_GETATTR] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_getattr,
+		.pc_func = nfsd3_proc_getattr,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_attrstatres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
@@ -673,7 +694,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+AT,
 	},
 	[NFS3PROC_SETATTR] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_setattr,
+		.pc_func = nfsd3_proc_setattr,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_sattrargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
@@ -683,7 +704,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+WC,
 	},
 	[NFS3PROC_LOOKUP] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_lookup,
+		.pc_func = nfsd3_proc_lookup,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_diropres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
@@ -693,7 +714,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+FH+pAT+pAT,
 	},
 	[NFS3PROC_ACCESS] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_access,
+		.pc_func = nfsd3_proc_access,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_accessargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_accessres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
@@ -703,7 +724,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+pAT+1,
 	},
 	[NFS3PROC_READLINK] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_readlink,
+		.pc_func = nfsd3_proc_readlink,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_readlinkargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_readlinkres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
@@ -713,7 +734,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+pAT+1+NFS3_MAXPATHLEN/4,
 	},
 	[NFS3PROC_READ] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_read,
+		.pc_func = nfsd3_proc_read,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_readargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_readres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
@@ -723,7 +744,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+pAT+4+NFSSVC_MAXBLKSIZE/4,
 	},
 	[NFS3PROC_WRITE] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_write,
+		.pc_func = nfsd3_proc_write,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_writeargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_writeres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
@@ -733,7 +754,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+WC+4,
 	},
 	[NFS3PROC_CREATE] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_create,
+		.pc_func = nfsd3_proc_create,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_createargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
@@ -743,7 +764,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+(1+FH+pAT)+WC,
 	},
 	[NFS3PROC_MKDIR] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_mkdir,
+		.pc_func = nfsd3_proc_mkdir,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_mkdirargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
@@ -753,7 +774,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+(1+FH+pAT)+WC,
 	},
 	[NFS3PROC_SYMLINK] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_symlink,
+		.pc_func = nfsd3_proc_symlink,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_symlinkargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
@@ -763,7 +784,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+(1+FH+pAT)+WC,
 	},
 	[NFS3PROC_MKNOD] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_mknod,
+		.pc_func = nfsd3_proc_mknod,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_mknodargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
@@ -773,7 +794,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+(1+FH+pAT)+WC,
 	},
 	[NFS3PROC_REMOVE] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_remove,
+		.pc_func = nfsd3_proc_remove,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
@@ -783,7 +804,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+WC,
 	},
 	[NFS3PROC_RMDIR] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_rmdir,
+		.pc_func = nfsd3_proc_rmdir,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
@@ -793,7 +814,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+WC,
 	},
 	[NFS3PROC_RENAME] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_rename,
+		.pc_func = nfsd3_proc_rename,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_renameargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_renameres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
@@ -803,7 +824,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+WC+WC,
 	},
 	[NFS3PROC_LINK] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_link,
+		.pc_func = nfsd3_proc_link,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_linkargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_linkres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
@@ -813,7 +834,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+pAT+WC,
 	},
 	[NFS3PROC_READDIR] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_readdir,
+		.pc_func = nfsd3_proc_readdir,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_readdirargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
@@ -822,7 +843,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_cachetype = RC_NOCACHE,
 	},
 	[NFS3PROC_READDIRPLUS] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_readdirplus,
+		.pc_func = nfsd3_proc_readdirplus,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_readdirplusargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
@@ -831,7 +852,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_cachetype = RC_NOCACHE,
 	},
 	[NFS3PROC_FSSTAT] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_fsstat,
+		.pc_func = nfsd3_proc_fsstat,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_fsstatres,
 		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
@@ -840,7 +861,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+pAT+2*6+1,
 	},
 	[NFS3PROC_FSINFO] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_fsinfo,
+		.pc_func = nfsd3_proc_fsinfo,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_fsinfores,
 		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
@@ -849,7 +870,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+pAT+12,
 	},
 	[NFS3PROC_PATHCONF] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_pathconf,
+		.pc_func = nfsd3_proc_pathconf,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_pathconfres,
 		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
@@ -858,7 +879,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_xdrressize = ST+pAT+6,
 	},
 	[NFS3PROC_COMMIT] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_commit,
+		.pc_func = nfsd3_proc_commit,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_commitargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_commitres,
 		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 0833686ccdd3..43b2e5ab4430 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1510,7 +1510,7 @@ out:
  * NULL call.
  */
 static __be32
-nfsd4_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
+nfsd4_proc_null(struct svc_rqst *rqstp)
 {
 	return nfs_ok;
 }
@@ -1524,6 +1524,7 @@ static inline void nfsd4_increment_op_stats(u32 opnum)
 typedef __be32(*nfsd4op_func)(struct svc_rqst *, struct nfsd4_compound_state *,
 			      void *);
 typedef u32(*nfsd4op_rsize)(struct svc_rqst *, struct nfsd4_op *op);
+
 typedef void(*stateid_setter)(struct nfsd4_compound_state *, void *);
 typedef void(*stateid_getter)(struct nfsd4_compound_state *, void *);
 
@@ -1673,10 +1674,10 @@ static void svcxdr_init_encode(struct svc_rqst *rqstp,
  * COMPOUND call.
  */
 static __be32
-nfsd4_proc_compound(struct svc_rqst *rqstp, void *arg, void *res)
+nfsd4_proc_compound(struct svc_rqst *rqstp)
 {
-	struct nfsd4_compoundargs *args = arg;
-	struct nfsd4_compoundres *resp = res;
+	struct nfsd4_compoundargs *args = rqstp->rq_argp;
+	struct nfsd4_compoundres *resp = rqstp->rq_resp;
 	struct nfsd4_op	*op;
 	struct nfsd4_operation *opdesc;
 	struct nfsd4_compound_state *cstate = &resp->cstate;
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index 03a7e9da4da0..448505b939db 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -17,7 +17,7 @@ typedef struct svc_buf	svc_buf;
 
 
 static __be32
-nfsd_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
+nfsd_proc_null(struct svc_rqst *rqstp)
 {
 	return nfs_ok;
 }
@@ -39,9 +39,10 @@ nfsd_return_dirop(__be32 err, struct nfsd_diropres *resp)
  * N.B. After this call resp->fh needs an fh_put
  */
 static __be32
-nfsd_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle  *argp,
-					  struct nfsd_attrstat *resp)
+nfsd_proc_getattr(struct svc_rqst *rqstp)
 {
+	struct nfsd_fhandle *argp = rqstp->rq_argp;
+	struct nfsd_attrstat *resp = rqstp->rq_resp;
 	__be32 nfserr;
 	dprintk("nfsd: GETATTR  %s\n", SVCFH_fmt(&argp->fh));
 
@@ -56,9 +57,10 @@ nfsd_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle  *argp,
  * N.B. After this call resp->fh needs an fh_put
  */
 static __be32
-nfsd_proc_setattr(struct svc_rqst *rqstp, struct nfsd_sattrargs *argp,
-					  struct nfsd_attrstat  *resp)
+nfsd_proc_setattr(struct svc_rqst *rqstp)
 {
+	struct nfsd_sattrargs *argp = rqstp->rq_argp;
+	struct nfsd_attrstat *resp = rqstp->rq_resp;
 	struct iattr *iap = &argp->attrs;
 	struct svc_fh *fhp;
 	__be32 nfserr;
@@ -122,9 +124,10 @@ done:
  * N.B. After this call resp->fh needs an fh_put
  */
 static __be32
-nfsd_proc_lookup(struct svc_rqst *rqstp, struct nfsd_diropargs *argp,
-					 struct nfsd_diropres  *resp)
+nfsd_proc_lookup(struct svc_rqst *rqstp)
 {
+	struct nfsd_diropargs *argp = rqstp->rq_argp;
+	struct nfsd_diropres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: LOOKUP   %s %.*s\n",
@@ -142,9 +145,10 @@ nfsd_proc_lookup(struct svc_rqst *rqstp, struct nfsd_diropargs *argp,
  * Read a symlink.
  */
 static __be32
-nfsd_proc_readlink(struct svc_rqst *rqstp, struct nfsd_readlinkargs *argp,
-					   struct nfsd_readlinkres *resp)
+nfsd_proc_readlink(struct svc_rqst *rqstp)
 {
+	struct nfsd_readlinkargs *argp = rqstp->rq_argp;
+	struct nfsd_readlinkres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: READLINK %s\n", SVCFH_fmt(&argp->fh));
@@ -162,9 +166,10 @@ nfsd_proc_readlink(struct svc_rqst *rqstp, struct nfsd_readlinkargs *argp,
  * N.B. After this call resp->fh needs an fh_put
  */
 static __be32
-nfsd_proc_read(struct svc_rqst *rqstp, struct nfsd_readargs *argp,
-				       struct nfsd_readres  *resp)
+nfsd_proc_read(struct svc_rqst *rqstp)
 {
+	struct nfsd_readargs *argp = rqstp->rq_argp;
+	struct nfsd_readres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: READ    %s %d bytes at %d\n",
@@ -200,9 +205,10 @@ nfsd_proc_read(struct svc_rqst *rqstp, struct nfsd_readargs *argp,
  * N.B. After this call resp->fh needs an fh_put
  */
 static __be32
-nfsd_proc_write(struct svc_rqst *rqstp, struct nfsd_writeargs *argp,
-					struct nfsd_attrstat  *resp)
+nfsd_proc_write(struct svc_rqst *rqstp)
 {
+	struct nfsd_writeargs *argp = rqstp->rq_argp;
+	struct nfsd_attrstat *resp = rqstp->rq_resp;
 	__be32	nfserr;
 	unsigned long cnt = argp->len;
 
@@ -222,9 +228,10 @@ nfsd_proc_write(struct svc_rqst *rqstp, struct nfsd_writeargs *argp,
  * N.B. After this call _both_ argp->fh and resp->fh need an fh_put
  */
 static __be32
-nfsd_proc_create(struct svc_rqst *rqstp, struct nfsd_createargs *argp,
-					 struct nfsd_diropres   *resp)
+nfsd_proc_create(struct svc_rqst *rqstp)
 {
+	struct nfsd_createargs *argp = rqstp->rq_argp;
+	struct nfsd_diropres *resp = rqstp->rq_resp;
 	svc_fh		*dirfhp = &argp->fh;
 	svc_fh		*newfhp = &resp->fh;
 	struct iattr	*attr = &argp->attrs;
@@ -377,9 +384,9 @@ done:
 }
 
 static __be32
-nfsd_proc_remove(struct svc_rqst *rqstp, struct nfsd_diropargs *argp,
-					 void		       *resp)
+nfsd_proc_remove(struct svc_rqst *rqstp)
 {
+	struct nfsd_diropargs *argp = rqstp->rq_argp;
 	__be32	nfserr;
 
 	dprintk("nfsd: REMOVE   %s %.*s\n", SVCFH_fmt(&argp->fh),
@@ -392,9 +399,9 @@ nfsd_proc_remove(struct svc_rqst *rqstp, struct nfsd_diropargs *argp,
 }
 
 static __be32
-nfsd_proc_rename(struct svc_rqst *rqstp, struct nfsd_renameargs *argp,
-				  	 void		        *resp)
+nfsd_proc_rename(struct svc_rqst *rqstp)
 {
+	struct nfsd_renameargs *argp = rqstp->rq_argp;
 	__be32	nfserr;
 
 	dprintk("nfsd: RENAME   %s %.*s -> \n",
@@ -410,9 +417,9 @@ nfsd_proc_rename(struct svc_rqst *rqstp, struct nfsd_renameargs *argp,
 }
 
 static __be32
-nfsd_proc_link(struct svc_rqst *rqstp, struct nfsd_linkargs *argp,
-				void			    *resp)
+nfsd_proc_link(struct svc_rqst *rqstp)
 {
+	struct nfsd_linkargs *argp = rqstp->rq_argp;
 	__be32	nfserr;
 
 	dprintk("nfsd: LINK     %s ->\n",
@@ -430,9 +437,9 @@ nfsd_proc_link(struct svc_rqst *rqstp, struct nfsd_linkargs *argp,
 }
 
 static __be32
-nfsd_proc_symlink(struct svc_rqst *rqstp, struct nfsd_symlinkargs *argp,
-				          void			  *resp)
+nfsd_proc_symlink(struct svc_rqst *rqstp)
 {
+	struct nfsd_symlinkargs *argp = rqstp->rq_argp;
 	struct svc_fh	newfh;
 	__be32		nfserr;
 
@@ -460,9 +467,10 @@ nfsd_proc_symlink(struct svc_rqst *rqstp, struct nfsd_symlinkargs *argp,
  * N.B. After this call resp->fh needs an fh_put
  */
 static __be32
-nfsd_proc_mkdir(struct svc_rqst *rqstp, struct nfsd_createargs *argp,
-					struct nfsd_diropres   *resp)
+nfsd_proc_mkdir(struct svc_rqst *rqstp)
 {
+	struct nfsd_createargs *argp = rqstp->rq_argp;
+	struct nfsd_diropres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: MKDIR    %s %.*s\n", SVCFH_fmt(&argp->fh), argp->len, argp->name);
@@ -484,9 +492,9 @@ nfsd_proc_mkdir(struct svc_rqst *rqstp, struct nfsd_createargs *argp,
  * Remove a directory
  */
 static __be32
-nfsd_proc_rmdir(struct svc_rqst *rqstp, struct nfsd_diropargs *argp,
-				 	void		      *resp)
+nfsd_proc_rmdir(struct svc_rqst *rqstp)
 {
+	struct nfsd_diropargs *argp = rqstp->rq_argp;
 	__be32	nfserr;
 
 	dprintk("nfsd: RMDIR    %s %.*s\n", SVCFH_fmt(&argp->fh), argp->len, argp->name);
@@ -500,9 +508,10 @@ nfsd_proc_rmdir(struct svc_rqst *rqstp, struct nfsd_diropargs *argp,
  * Read a portion of a directory.
  */
 static __be32
-nfsd_proc_readdir(struct svc_rqst *rqstp, struct nfsd_readdirargs *argp,
-					  struct nfsd_readdirres  *resp)
+nfsd_proc_readdir(struct svc_rqst *rqstp)
 {
+	struct nfsd_readdirargs *argp = rqstp->rq_argp;
+	struct nfsd_readdirres *resp = rqstp->rq_resp;
 	int		count;
 	__be32		nfserr;
 	loff_t		offset;
@@ -540,9 +549,10 @@ nfsd_proc_readdir(struct svc_rqst *rqstp, struct nfsd_readdirargs *argp,
  * Get file system info
  */
 static __be32
-nfsd_proc_statfs(struct svc_rqst * rqstp, struct nfsd_fhandle   *argp,
-					  struct nfsd_statfsres *resp)
+nfsd_proc_statfs(struct svc_rqst *rqstp)
 {
+	struct nfsd_fhandle *argp = rqstp->rq_argp;
+	struct nfsd_statfsres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: STATFS   %s\n", SVCFH_fmt(&argp->fh));
@@ -565,7 +575,7 @@ struct nfsd_void { int dummy; };
 
 static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_NULL] = {
-		.pc_func = (svc_procfunc) nfsd_proc_null,
+		.pc_func = nfsd_proc_null,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_void,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_void),
@@ -574,7 +584,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_xdrressize = ST,
 	},
 	[NFSPROC_GETATTR] = {
-		.pc_func = (svc_procfunc) nfsd_proc_getattr,
+		.pc_func = nfsd_proc_getattr,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_fhandle,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
 		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
@@ -584,7 +594,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_xdrressize = ST+AT,
 	},
 	[NFSPROC_SETATTR] = {
-		.pc_func = (svc_procfunc) nfsd_proc_setattr,
+		.pc_func = nfsd_proc_setattr,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_sattrargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
 		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
@@ -602,7 +612,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_xdrressize = ST,
 	},
 	[NFSPROC_LOOKUP] = {
-		.pc_func = (svc_procfunc) nfsd_proc_lookup,
+		.pc_func = nfsd_proc_lookup,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_diropargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
 		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
@@ -612,7 +622,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_xdrressize = ST+FH+AT,
 	},
 	[NFSPROC_READLINK] = {
-		.pc_func = (svc_procfunc) nfsd_proc_readlink,
+		.pc_func = nfsd_proc_readlink,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_readlinkargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_readlinkres,
 		.pc_argsize = sizeof(struct nfsd_readlinkargs),
@@ -621,7 +631,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_xdrressize = ST+1+NFS_MAXPATHLEN/4,
 	},
 	[NFSPROC_READ] = {
-		.pc_func = (svc_procfunc) nfsd_proc_read,
+		.pc_func = nfsd_proc_read,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_readargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_readres,
 		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
@@ -639,7 +649,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_xdrressize = ST,
 	},
 	[NFSPROC_WRITE] = {
-		.pc_func = (svc_procfunc) nfsd_proc_write,
+		.pc_func = nfsd_proc_write,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_writeargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
 		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
@@ -649,7 +659,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_xdrressize = ST+AT,
 	},
 	[NFSPROC_CREATE] = {
-		.pc_func = (svc_procfunc) nfsd_proc_create,
+		.pc_func = nfsd_proc_create,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_createargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
 		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
@@ -659,7 +669,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_xdrressize = ST+FH+AT,
 	},
 	[NFSPROC_REMOVE] = {
-		.pc_func = (svc_procfunc) nfsd_proc_remove,
+		.pc_func = nfsd_proc_remove,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_diropargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_diropargs),
@@ -668,7 +678,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_xdrressize = ST,
 	},
 	[NFSPROC_RENAME] = {
-		.pc_func = (svc_procfunc) nfsd_proc_rename,
+		.pc_func = nfsd_proc_rename,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_renameargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_renameargs),
@@ -677,7 +687,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_xdrressize = ST,
 	},
 	[NFSPROC_LINK] = {
-		.pc_func = (svc_procfunc) nfsd_proc_link,
+		.pc_func = nfsd_proc_link,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_linkargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_linkargs),
@@ -686,7 +696,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_xdrressize = ST,
 	},
 	[NFSPROC_SYMLINK] = {
-		.pc_func = (svc_procfunc) nfsd_proc_symlink,
+		.pc_func = nfsd_proc_symlink,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_symlinkargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_symlinkargs),
@@ -695,7 +705,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_xdrressize = ST,
 	},
 	[NFSPROC_MKDIR] = {
-		.pc_func = (svc_procfunc) nfsd_proc_mkdir,
+		.pc_func = nfsd_proc_mkdir,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_createargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
 		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
@@ -705,7 +715,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_xdrressize = ST+FH+AT,
 	},
 	[NFSPROC_RMDIR] = {
-		.pc_func = (svc_procfunc) nfsd_proc_rmdir,
+		.pc_func = nfsd_proc_rmdir,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_diropargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_diropargs),
@@ -714,7 +724,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_xdrressize = ST,
 	},
 	[NFSPROC_READDIR] = {
-		.pc_func = (svc_procfunc) nfsd_proc_readdir,
+		.pc_func = nfsd_proc_readdir,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_readdirargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_readdirres,
 		.pc_argsize = sizeof(struct nfsd_readdirargs),
@@ -722,7 +732,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_cachetype = RC_NOCACHE,
 	},
 	[NFSPROC_STATFS] = {
-		.pc_func = (svc_procfunc) nfsd_proc_statfs,
+		.pc_func = nfsd_proc_statfs,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_fhandle,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_statfsres,
 		.pc_argsize = sizeof(struct nfsd_fhandle),
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 59979f0bbd4b..d64895fd8d25 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -827,7 +827,7 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 	rqstp->rq_res.head[0].iov_len += sizeof(__be32);
 
 	/* Now call the procedure handler, and encode NFS status. */
-	nfserr = proc->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp);
+	nfserr = proc->pc_func(rqstp);
 	nfserr = map_new_errors(rqstp->rq_vers, nfserr);
 	if (nfserr == nfserr_dropit || test_bit(RQ_DROPME, &rqstp->rq_flags)) {
 		dprintk("nfsd: Dropping request; may be revisited later\n");
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 11cef5a7bc87..3b58c55614c7 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -419,9 +419,9 @@ struct svc_version {
 /*
  * RPC procedure info
  */
-typedef __be32	(*svc_procfunc)(struct svc_rqst *, void *argp, void *resp);
 struct svc_procedure {
-	svc_procfunc		pc_func;	/* process the request */
+	/* process the request: */
+	__be32			(*pc_func)(struct svc_rqst *);
 	kxdrproc_t		pc_decode;	/* XDR decode args */
 	kxdrproc_t		pc_encode;	/* XDR encode result */
 	kxdrproc_t		pc_release;	/* XDR free result */
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index bc0f5a0ecbdc..95335455ad38 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1281,7 +1281,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 		if (xdr && !xdr(rqstp, argv->iov_base, rqstp->rq_argp))
 			goto err_garbage;
 
-		*statp = procp->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp);
+		*statp = procp->pc_func(rqstp);
 
 		/* Encode reply */
 		if (*statp == rpc_drop_reply ||
-- 
cgit v1.2.3


From 1150ded804c2be6d02efef3e39e39e570c9cea21 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 8 May 2017 18:48:24 +0200
Subject: sunrpc: properly type pc_release callbacks

Drop the p and resp arguments as they are always NULL or can trivially
be derived from the rqstp argument.  With that all functions now have the
same prototype, and we can remove the unsafe casting to kxdrproc_t.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/nfsd/nfs2acl.c          | 22 +++++++++++-----------
 fs/nfsd/nfs3acl.c          |  8 ++++----
 fs/nfsd/nfs3proc.c         | 36 ++++++++++++++++++------------------
 fs/nfsd/nfs3xdr.c          | 16 ++++++++--------
 fs/nfsd/nfs4xdr.c          |  4 +---
 fs/nfsd/nfsproc.c          | 14 +++++++-------
 fs/nfsd/nfsxdr.c           |  8 ++++----
 fs/nfsd/xdr.h              |  2 +-
 fs/nfsd/xdr3.h             |  6 ++----
 fs/nfsd/xdr4.h             |  2 +-
 include/linux/sunrpc/svc.h |  3 ++-
 net/sunrpc/svc.c           |  8 ++++----
 12 files changed, 63 insertions(+), 66 deletions(-)

(limited to 'include')

diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index 4b7f84fa1fa5..302441027f50 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -318,27 +318,27 @@ static int nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, __be32 *p,
 /*
  * XDR release functions
  */
-static int nfsaclsvc_release_getacl(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_getaclres *resp)
+static void nfsaclsvc_release_getacl(struct svc_rqst *rqstp)
 {
+	struct nfsd3_getaclres *resp = rqstp->rq_resp;
+
 	fh_put(&resp->fh);
 	posix_acl_release(resp->acl_access);
 	posix_acl_release(resp->acl_default);
-	return 1;
 }
 
-static int nfsaclsvc_release_attrstat(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd_attrstat *resp)
+static void nfsaclsvc_release_attrstat(struct svc_rqst *rqstp)
 {
+	struct nfsd_attrstat *resp = rqstp->rq_resp;
+
 	fh_put(&resp->fh);
-	return 1;
 }
 
-static int nfsaclsvc_release_access(struct svc_rqst *rqstp, __be32 *p,
-               struct nfsd3_accessres *resp)
+static void nfsaclsvc_release_access(struct svc_rqst *rqstp)
 {
-       fh_put(&resp->fh);
-       return 1;
+	struct nfsd3_accessres *resp = rqstp->rq_resp;
+
+	fh_put(&resp->fh);
 }
 
 #define nfsaclsvc_decode_voidargs	NULL
@@ -353,7 +353,7 @@ struct nfsd3_voidargs { int dummy; };
 	.pc_func	= nfsacld_proc_##name,				\
 	.pc_decode	= (kxdrproc_t) nfsaclsvc_decode_##argt##args,	\
 	.pc_encode	= (kxdrproc_t) nfsaclsvc_encode_##rest##res,	\
-	.pc_release	= (kxdrproc_t) nfsaclsvc_release_##relt,	\
+	.pc_release	= nfsaclsvc_release_##relt,	\
 	.pc_argsize	= sizeof(struct nfsd3_##argt##args),		\
 	.pc_ressize	= sizeof(struct nfsd3_##rest##res),		\
 	.pc_cachetype	= cache,					\
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index 5e42004035e0..56cdff4e954c 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -223,13 +223,13 @@ static int nfs3svc_encode_setaclres(struct svc_rqst *rqstp, __be32 *p,
 /*
  * XDR release functions
  */
-static int nfs3svc_release_getacl(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_getaclres *resp)
+static void nfs3svc_release_getacl(struct svc_rqst *rqstp)
 {
+	struct nfsd3_getaclres *resp = rqstp->rq_resp;
+
 	fh_put(&resp->fh);
 	posix_acl_release(resp->acl_access);
 	posix_acl_release(resp->acl_default);
-	return 1;
 }
 
 #define nfs3svc_decode_voidargs		NULL
@@ -243,7 +243,7 @@ struct nfsd3_voidargs { int dummy; };
 	.pc_func	= nfsd3_proc_##name,				\
 	.pc_decode	= (kxdrproc_t) nfs3svc_decode_##argt##args,	\
 	.pc_encode	= (kxdrproc_t) nfs3svc_encode_##rest##res,	\
-	.pc_release	= (kxdrproc_t) nfs3svc_release_##relt,		\
+	.pc_release	= nfs3svc_release_##relt,			\
 	.pc_argsize	= sizeof(struct nfsd3_##argt##args),		\
 	.pc_ressize	= sizeof(struct nfsd3_##rest##res),		\
 	.pc_cachetype	= cache,					\
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 4a2bae07cfbf..f0cccc0768ce 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -687,7 +687,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_getattr,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_attrstatres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
 		.pc_ressize = sizeof(struct nfsd3_attrstatres),
 		.pc_cachetype = RC_NOCACHE,
@@ -697,7 +697,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_setattr,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_sattrargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_sattrargs),
 		.pc_ressize = sizeof(struct nfsd3_wccstatres),
 		.pc_cachetype = RC_REPLBUFF,
@@ -707,7 +707,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_lookup,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_diropres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_diropargs),
 		.pc_ressize = sizeof(struct nfsd3_diropres),
 		.pc_cachetype = RC_NOCACHE,
@@ -717,7 +717,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_access,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_accessargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_accessres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_accessargs),
 		.pc_ressize = sizeof(struct nfsd3_accessres),
 		.pc_cachetype = RC_NOCACHE,
@@ -727,7 +727,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_readlink,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_readlinkargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_readlinkres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_readlinkargs),
 		.pc_ressize = sizeof(struct nfsd3_readlinkres),
 		.pc_cachetype = RC_NOCACHE,
@@ -737,7 +737,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_read,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_readargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_readres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_readargs),
 		.pc_ressize = sizeof(struct nfsd3_readres),
 		.pc_cachetype = RC_NOCACHE,
@@ -747,7 +747,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_write,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_writeargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_writeres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_writeargs),
 		.pc_ressize = sizeof(struct nfsd3_writeres),
 		.pc_cachetype = RC_REPLBUFF,
@@ -757,7 +757,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_create,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_createargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_createargs),
 		.pc_ressize = sizeof(struct nfsd3_createres),
 		.pc_cachetype = RC_REPLBUFF,
@@ -767,7 +767,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_mkdir,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_mkdirargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_mkdirargs),
 		.pc_ressize = sizeof(struct nfsd3_createres),
 		.pc_cachetype = RC_REPLBUFF,
@@ -777,7 +777,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_symlink,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_symlinkargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_symlinkargs),
 		.pc_ressize = sizeof(struct nfsd3_createres),
 		.pc_cachetype = RC_REPLBUFF,
@@ -787,7 +787,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_mknod,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_mknodargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_mknodargs),
 		.pc_ressize = sizeof(struct nfsd3_createres),
 		.pc_cachetype = RC_REPLBUFF,
@@ -797,7 +797,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_remove,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_diropargs),
 		.pc_ressize = sizeof(struct nfsd3_wccstatres),
 		.pc_cachetype = RC_REPLBUFF,
@@ -807,7 +807,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_rmdir,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_diropargs),
 		.pc_ressize = sizeof(struct nfsd3_wccstatres),
 		.pc_cachetype = RC_REPLBUFF,
@@ -817,7 +817,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_rename,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_renameargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_renameres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_renameargs),
 		.pc_ressize = sizeof(struct nfsd3_renameres),
 		.pc_cachetype = RC_REPLBUFF,
@@ -827,7 +827,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_link,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_linkargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_linkres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_linkargs),
 		.pc_ressize = sizeof(struct nfsd3_linkres),
 		.pc_cachetype = RC_REPLBUFF,
@@ -837,7 +837,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_readdir,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_readdirargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_readdirargs),
 		.pc_ressize = sizeof(struct nfsd3_readdirres),
 		.pc_cachetype = RC_NOCACHE,
@@ -846,7 +846,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_readdirplus,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_readdirplusargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_readdirplusargs),
 		.pc_ressize = sizeof(struct nfsd3_readdirres),
 		.pc_cachetype = RC_NOCACHE,
@@ -882,7 +882,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 		.pc_func = nfsd3_proc_commit,
 		.pc_decode = (kxdrproc_t) nfs3svc_decode_commitargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_commitres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_commitargs),
 		.pc_ressize = sizeof(struct nfsd3_commitres),
 		.pc_cachetype = RC_NOCACHE,
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 452334694a5d..c3d3ef28347c 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -1103,19 +1103,19 @@ nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p,
 /*
  * XDR release functions
  */
-int
-nfs3svc_release_fhandle(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_attrstat *resp)
+void
+nfs3svc_release_fhandle(struct svc_rqst *rqstp)
 {
+	struct nfsd3_attrstat *resp = rqstp->rq_resp;
+
 	fh_put(&resp->fh);
-	return 1;
 }
 
-int
-nfs3svc_release_fhandle2(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_fhandle_pair *resp)
+void
+nfs3svc_release_fhandle2(struct svc_rqst *rqstp)
 {
+	struct nfsd3_fhandle_pair *resp = rqstp->rq_resp;
+
 	fh_put(&resp->fh1);
 	fh_put(&resp->fh2);
-	return 1;
 }
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 26780d53a6f9..5aa847bdfc63 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -4543,9 +4543,8 @@ nfs4svc_encode_voidres(struct svc_rqst *rqstp, __be32 *p, void *dummy)
         return xdr_ressize_check(rqstp, p);
 }
 
-int nfsd4_release_compoundargs(void *rq, __be32 *p, void *resp)
+void nfsd4_release_compoundargs(struct svc_rqst *rqstp)
 {
-	struct svc_rqst *rqstp = rq;
 	struct nfsd4_compoundargs *args = rqstp->rq_argp;
 
 	if (args->ops != args->iops) {
@@ -4559,7 +4558,6 @@ int nfsd4_release_compoundargs(void *rq, __be32 *p, void *resp)
 		args->to_free = tb->next;
 		kfree(tb);
 	}
-	return 1;
 }
 
 int
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index 448505b939db..dc32e0f8480d 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -587,7 +587,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_func = nfsd_proc_getattr,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_fhandle,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
-		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_fhandle),
 		.pc_ressize = sizeof(struct nfsd_attrstat),
 		.pc_cachetype = RC_NOCACHE,
@@ -597,7 +597,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_func = nfsd_proc_setattr,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_sattrargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
-		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_sattrargs),
 		.pc_ressize = sizeof(struct nfsd_attrstat),
 		.pc_cachetype = RC_REPLBUFF,
@@ -615,7 +615,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_func = nfsd_proc_lookup,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_diropargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
-		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_diropargs),
 		.pc_ressize = sizeof(struct nfsd_diropres),
 		.pc_cachetype = RC_NOCACHE,
@@ -634,7 +634,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_func = nfsd_proc_read,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_readargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_readres,
-		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_readargs),
 		.pc_ressize = sizeof(struct nfsd_readres),
 		.pc_cachetype = RC_NOCACHE,
@@ -652,7 +652,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_func = nfsd_proc_write,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_writeargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
-		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_writeargs),
 		.pc_ressize = sizeof(struct nfsd_attrstat),
 		.pc_cachetype = RC_REPLBUFF,
@@ -662,7 +662,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_func = nfsd_proc_create,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_createargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
-		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_createargs),
 		.pc_ressize = sizeof(struct nfsd_diropres),
 		.pc_cachetype = RC_REPLBUFF,
@@ -708,7 +708,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_func = nfsd_proc_mkdir,
 		.pc_decode = (kxdrproc_t) nfssvc_decode_createargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
-		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_createargs),
 		.pc_ressize = sizeof(struct nfsd_diropres),
 		.pc_cachetype = RC_REPLBUFF,
diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c
index de07ff625777..2facfc6ac8f3 100644
--- a/fs/nfsd/nfsxdr.c
+++ b/fs/nfsd/nfsxdr.c
@@ -543,10 +543,10 @@ nfssvc_encode_entry(void *ccdv, const char *name,
 /*
  * XDR release functions
  */
-int
-nfssvc_release_fhandle(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_fhandle *resp)
+void
+nfssvc_release_fhandle(struct svc_rqst *rqstp)
 {
+	struct nfsd_fhandle *resp = rqstp->rq_resp;
+
 	fh_put(&resp->fh);
-	return 1;
 }
diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h
index 4f0481d63804..2c21fa843fbf 100644
--- a/fs/nfsd/xdr.h
+++ b/fs/nfsd/xdr.h
@@ -164,7 +164,7 @@ int nfssvc_encode_readdirres(struct svc_rqst *, __be32 *, struct nfsd_readdirres
 int nfssvc_encode_entry(void *, const char *name,
 			int namlen, loff_t offset, u64 ino, unsigned int);
 
-int nfssvc_release_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *);
+void nfssvc_release_fhandle(struct svc_rqst *);
 
 /* Helper functions for NFSv2 ACL code */
 __be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, struct kstat *stat);
diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h
index 335e04aaf7db..23fe456a223b 100644
--- a/fs/nfsd/xdr3.h
+++ b/fs/nfsd/xdr3.h
@@ -330,10 +330,8 @@ int nfs3svc_encode_pathconfres(struct svc_rqst *, __be32 *,
 int nfs3svc_encode_commitres(struct svc_rqst *, __be32 *,
 				struct nfsd3_commitres *);
 
-int nfs3svc_release_fhandle(struct svc_rqst *, __be32 *,
-				struct nfsd3_attrstat *);
-int nfs3svc_release_fhandle2(struct svc_rqst *, __be32 *,
-				struct nfsd3_fhandle_pair *);
+void nfs3svc_release_fhandle(struct svc_rqst *);
+void nfs3svc_release_fhandle2(struct svc_rqst *);
 int nfs3svc_encode_entry(void *, const char *name,
 				int namlen, loff_t offset, u64 ino,
 				unsigned int);
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 8fda4abdf3b1..a158579d55a2 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -743,7 +743,7 @@ extern __be32
 nfsd4_release_lockowner(struct svc_rqst *rqstp,
 		struct nfsd4_compound_state *,
 		struct nfsd4_release_lockowner *rlockowner);
-extern int nfsd4_release_compoundargs(void *rq, __be32 *p, void *resp);
+extern void nfsd4_release_compoundargs(struct svc_rqst *rqstp);
 extern __be32 nfsd4_delegreturn(struct svc_rqst *rqstp,
 		struct nfsd4_compound_state *, struct nfsd4_delegreturn *dr);
 extern __be32 nfsd4_renew(struct svc_rqst *rqstp,
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 3b58c55614c7..c73194e9c2bd 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -424,7 +424,8 @@ struct svc_procedure {
 	__be32			(*pc_func)(struct svc_rqst *);
 	kxdrproc_t		pc_decode;	/* XDR decode args */
 	kxdrproc_t		pc_encode;	/* XDR encode result */
-	kxdrproc_t		pc_release;	/* XDR free result */
+	/* XDR free result: */
+	void			(*pc_release)(struct svc_rqst *);
 	unsigned int		pc_argsize;	/* argument struct size */
 	unsigned int		pc_ressize;	/* result struct size */
 	unsigned int		pc_count;	/* call count */
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 95335455ad38..4611cb7adc04 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1287,12 +1287,12 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 		if (*statp == rpc_drop_reply ||
 		    test_bit(RQ_DROPME, &rqstp->rq_flags)) {
 			if (procp->pc_release)
-				procp->pc_release(rqstp, NULL, rqstp->rq_resp);
+				procp->pc_release(rqstp);
 			goto dropit;
 		}
 		if (*statp == rpc_autherr_badcred) {
 			if (procp->pc_release)
-				procp->pc_release(rqstp, NULL, rqstp->rq_resp);
+				procp->pc_release(rqstp);
 			goto err_bad_auth;
 		}
 		if (*statp == rpc_success &&
@@ -1307,7 +1307,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 		if (!versp->vs_dispatch(rqstp, statp)) {
 			/* Release reply info */
 			if (procp->pc_release)
-				procp->pc_release(rqstp, NULL, rqstp->rq_resp);
+				procp->pc_release(rqstp);
 			goto dropit;
 		}
 	}
@@ -1318,7 +1318,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 
 	/* Release reply info */
 	if (procp->pc_release)
-		procp->pc_release(rqstp, NULL, rqstp->rq_resp);
+		procp->pc_release(rqstp);
 
 	if (procp->pc_encode == NULL)
 		goto dropit;
-- 
cgit v1.2.3


From cc6acc20a606f9ca65a6338af8204b7ae9e67b1a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 8 May 2017 19:01:48 +0200
Subject: sunrpc: properly type pc_decode callbacks

Drop the argp argument as it can trivially be derived from the rqstp
argument.  With that all functions now have the same prototype, and we
can remove the unsafe casting to kxdrproc_t.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/lockd/svc4proc.c        |  2 +-
 fs/lockd/svcproc.c         |  2 +-
 fs/lockd/xdr.c             | 29 ++++++++++++------
 fs/lockd/xdr4.c            | 29 ++++++++++++------
 fs/nfs/callback_xdr.c      |  4 +--
 fs/nfsd/nfs2acl.c          | 21 +++++++------
 fs/nfsd/nfs3acl.c          | 11 +++----
 fs/nfsd/nfs3proc.c         | 42 +++++++++++++-------------
 fs/nfsd/nfs3xdr.c          | 74 +++++++++++++++++++++++++++-------------------
 fs/nfsd/nfs4proc.c         |  2 +-
 fs/nfsd/nfs4xdr.c          |  4 ++-
 fs/nfsd/nfsproc.c          | 36 +++++++++++-----------
 fs/nfsd/nfssvc.c           |  5 ++--
 fs/nfsd/nfsxdr.c           | 53 ++++++++++++++++++++-------------
 fs/nfsd/xdr.h              | 34 ++++++++-------------
 fs/nfsd/xdr3.h             | 47 ++++++++++-------------------
 fs/nfsd/xdr4.h             |  3 +-
 include/linux/lockd/xdr.h  | 18 +++++------
 include/linux/lockd/xdr4.h | 18 +++++------
 include/linux/sunrpc/svc.h |  3 +-
 net/sunrpc/svc.c           |  9 ++++--
 21 files changed, 237 insertions(+), 209 deletions(-)

(limited to 'include')

diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index 3e4cba029d3d..804744f7528c 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -496,7 +496,7 @@ struct nlm_void			{ int dummy; };
 
 #define PROC(name, xargt, xrest, argt, rest, respsize)	\
  { .pc_func	= nlm4svc_proc_##name,	\
-   .pc_decode	= (kxdrproc_t) nlm4svc_decode_##xargt,	\
+   .pc_decode	= nlm4svc_decode_##xargt,	\
    .pc_encode	= (kxdrproc_t) nlm4svc_encode_##xrest,	\
    .pc_release	= NULL,					\
    .pc_argsize	= sizeof(struct nlm_##argt),		\
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index 3add50661fab..204a698f7d41 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -538,7 +538,7 @@ struct nlm_void			{ int dummy; };
 
 #define PROC(name, xargt, xrest, argt, rest, respsize)	\
  { .pc_func	= nlmsvc_proc_##name,			\
-   .pc_decode	= (kxdrproc_t) nlmsvc_decode_##xargt,	\
+   .pc_decode	= nlmsvc_decode_##xargt,		\
    .pc_encode	= (kxdrproc_t) nlmsvc_encode_##xrest,	\
    .pc_release	= NULL,					\
    .pc_argsize	= sizeof(struct nlm_##argt),		\
diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c
index 5b651daad518..b57af63fba56 100644
--- a/fs/lockd/xdr.c
+++ b/fs/lockd/xdr.c
@@ -182,8 +182,9 @@ nlm_encode_testres(__be32 *p, struct nlm_res *resp)
  * First, the server side XDR functions
  */
 int
-nlmsvc_decode_testargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
+nlmsvc_decode_testargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	u32	exclusive;
 
 	if (!(p = nlm_decode_cookie(p, &argp->cookie)))
@@ -207,8 +208,9 @@ nlmsvc_encode_testres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
 }
 
 int
-nlmsvc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
+nlmsvc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	u32	exclusive;
 
 	if (!(p = nlm_decode_cookie(p, &argp->cookie)))
@@ -227,8 +229,9 @@ nlmsvc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
 }
 
 int
-nlmsvc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
+nlmsvc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	u32	exclusive;
 
 	if (!(p = nlm_decode_cookie(p, &argp->cookie)))
@@ -243,8 +246,10 @@ nlmsvc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
 }
 
 int
-nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
+nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
+
 	if (!(p = nlm_decode_cookie(p, &argp->cookie))
 	 || !(p = nlm_decode_lock(p, &argp->lock)))
 		return 0;
@@ -253,8 +258,9 @@ nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
 }
 
 int
-nlmsvc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
+nlmsvc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_lock	*lock = &argp->lock;
 
 	memset(lock, 0, sizeof(*lock));
@@ -293,8 +299,9 @@ nlmsvc_encode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
 }
 
 int
-nlmsvc_decode_notify(struct svc_rqst *rqstp, __be32 *p, struct nlm_args *argp)
+nlmsvc_decode_notify(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_lock	*lock = &argp->lock;
 
 	if (!(p = xdr_decode_string_inplace(p, &lock->caller,
@@ -305,8 +312,10 @@ nlmsvc_decode_notify(struct svc_rqst *rqstp, __be32 *p, struct nlm_args *argp)
 }
 
 int
-nlmsvc_decode_reboot(struct svc_rqst *rqstp, __be32 *p, struct nlm_reboot *argp)
+nlmsvc_decode_reboot(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_reboot *argp = rqstp->rq_argp;
+
 	if (!(p = xdr_decode_string_inplace(p, &argp->mon, &argp->len, SM_MAXSTRLEN)))
 		return 0;
 	argp->state = ntohl(*p++);
@@ -316,8 +325,10 @@ nlmsvc_decode_reboot(struct svc_rqst *rqstp, __be32 *p, struct nlm_reboot *argp)
 }
 
 int
-nlmsvc_decode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
+nlmsvc_decode_res(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_res *resp = rqstp->rq_argp;
+
 	if (!(p = nlm_decode_cookie(p, &resp->cookie)))
 		return 0;
 	resp->status = *p++;
@@ -325,7 +336,7 @@ nlmsvc_decode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
 }
 
 int
-nlmsvc_decode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+nlmsvc_decode_void(struct svc_rqst *rqstp, __be32 *p)
 {
 	return xdr_argsize_check(rqstp, p);
 }
diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c
index dfa4789cd460..46e18598a15c 100644
--- a/fs/lockd/xdr4.c
+++ b/fs/lockd/xdr4.c
@@ -179,8 +179,9 @@ nlm4_encode_testres(__be32 *p, struct nlm_res *resp)
  * First, the server side XDR functions
  */
 int
-nlm4svc_decode_testargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
+nlm4svc_decode_testargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	u32	exclusive;
 
 	if (!(p = nlm4_decode_cookie(p, &argp->cookie)))
@@ -204,8 +205,9 @@ nlm4svc_encode_testres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
 }
 
 int
-nlm4svc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
+nlm4svc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	u32	exclusive;
 
 	if (!(p = nlm4_decode_cookie(p, &argp->cookie)))
@@ -224,8 +226,9 @@ nlm4svc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
 }
 
 int
-nlm4svc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
+nlm4svc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	u32	exclusive;
 
 	if (!(p = nlm4_decode_cookie(p, &argp->cookie)))
@@ -240,8 +243,10 @@ nlm4svc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
 }
 
 int
-nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
+nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
+
 	if (!(p = nlm4_decode_cookie(p, &argp->cookie))
 	 || !(p = nlm4_decode_lock(p, &argp->lock)))
 		return 0;
@@ -250,8 +255,9 @@ nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
 }
 
 int
-nlm4svc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
+nlm4svc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_lock	*lock = &argp->lock;
 
 	memset(lock, 0, sizeof(*lock));
@@ -290,8 +296,9 @@ nlm4svc_encode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
 }
 
 int
-nlm4svc_decode_notify(struct svc_rqst *rqstp, __be32 *p, struct nlm_args *argp)
+nlm4svc_decode_notify(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_lock	*lock = &argp->lock;
 
 	if (!(p = xdr_decode_string_inplace(p, &lock->caller,
@@ -302,8 +309,10 @@ nlm4svc_decode_notify(struct svc_rqst *rqstp, __be32 *p, struct nlm_args *argp)
 }
 
 int
-nlm4svc_decode_reboot(struct svc_rqst *rqstp, __be32 *p, struct nlm_reboot *argp)
+nlm4svc_decode_reboot(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_reboot *argp = rqstp->rq_argp;
+
 	if (!(p = xdr_decode_string_inplace(p, &argp->mon, &argp->len, SM_MAXSTRLEN)))
 		return 0;
 	argp->state = ntohl(*p++);
@@ -313,8 +322,10 @@ nlm4svc_decode_reboot(struct svc_rqst *rqstp, __be32 *p, struct nlm_reboot *argp
 }
 
 int
-nlm4svc_decode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
+nlm4svc_decode_res(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_res *resp = rqstp->rq_argp;
+
 	if (!(p = nlm4_decode_cookie(p, &resp->cookie)))
 		return 0;
 	resp->status = *p++;
@@ -322,7 +333,7 @@ nlm4svc_decode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
 }
 
 int
-nlm4svc_decode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+nlm4svc_decode_void(struct svc_rqst *rqstp, __be32 *p)
 {
 	return xdr_argsize_check(rqstp, p);
 }
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index 5a14bdaa5986..23ecbf7a40c1 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -58,7 +58,7 @@ static __be32 nfs4_callback_null(struct svc_rqst *rqstp)
 	return htonl(NFS4_OK);
 }
 
-static int nfs4_decode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+static int nfs4_decode_void(struct svc_rqst *rqstp, __be32 *p)
 {
 	return xdr_argsize_check(rqstp, p);
 }
@@ -998,7 +998,7 @@ static struct callback_op callback_ops[] = {
 static struct svc_procedure nfs4_callback_procedures1[] = {
 	[CB_NULL] = {
 		.pc_func = nfs4_callback_null,
-		.pc_decode = (kxdrproc_t)nfs4_decode_void,
+		.pc_decode = nfs4_decode_void,
 		.pc_encode = (kxdrproc_t)nfs4_encode_void,
 		.pc_xdrressize = 1,
 	},
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index 302441027f50..bcfdaa83ee6c 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -182,9 +182,10 @@ static __be32 nfsacld_proc_access(struct svc_rqst *rqstp)
 /*
  * XDR decode functions
  */
-static int nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_getaclargs *argp)
+static int nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_getaclargs *argp = rqstp->rq_argp;
+
 	p = nfs2svc_decode_fh(p, &argp->fh);
 	if (!p)
 		return 0;
@@ -194,9 +195,9 @@ static int nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 
-static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_setaclargs *argp)
+static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_setaclargs *argp = rqstp->rq_argp;
 	struct kvec *head = rqstp->rq_arg.head;
 	unsigned int base;
 	int n;
@@ -220,18 +221,20 @@ static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p,
 	return (n > 0);
 }
 
-static int nfsaclsvc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd_fhandle *argp)
+static int nfsaclsvc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_fhandle *argp = rqstp->rq_argp;
+
 	p = nfs2svc_decode_fh(p, &argp->fh);
 	if (!p)
 		return 0;
 	return xdr_argsize_check(rqstp, p);
 }
 
-static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_accessargs *argp)
+static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_accessargs *argp = rqstp->rq_argp;
+
 	p = nfs2svc_decode_fh(p, &argp->fh);
 	if (!p)
 		return 0;
@@ -351,7 +354,7 @@ struct nfsd3_voidargs { int dummy; };
 #define PROC(name, argt, rest, relt, cache, respsize)			\
 {									\
 	.pc_func	= nfsacld_proc_##name,				\
-	.pc_decode	= (kxdrproc_t) nfsaclsvc_decode_##argt##args,	\
+	.pc_decode	= nfsaclsvc_decode_##argt##args,		\
 	.pc_encode	= (kxdrproc_t) nfsaclsvc_encode_##rest##res,	\
 	.pc_release	= nfsaclsvc_release_##relt,	\
 	.pc_argsize	= sizeof(struct nfsd3_##argt##args),		\
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index 56cdff4e954c..4e68d6b5f409 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -124,9 +124,10 @@ out:
 /*
  * XDR decode functions
  */
-static int nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_getaclargs *args)
+static int nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_getaclargs *args = rqstp->rq_argp;
+
 	p = nfs3svc_decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
@@ -136,9 +137,9 @@ static int nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 
-static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_setaclargs *args)
+static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_setaclargs *args = rqstp->rq_argp;
 	struct kvec *head = rqstp->rq_arg.head;
 	unsigned int base;
 	int n;
@@ -241,7 +242,7 @@ struct nfsd3_voidargs { int dummy; };
 #define PROC(name, argt, rest, relt, cache, respsize)			\
 {									\
 	.pc_func	= nfsd3_proc_##name,				\
-	.pc_decode	= (kxdrproc_t) nfs3svc_decode_##argt##args,	\
+	.pc_decode	= nfs3svc_decode_##argt##args,			\
 	.pc_encode	= (kxdrproc_t) nfs3svc_encode_##rest##res,	\
 	.pc_release	= nfs3svc_release_##relt,			\
 	.pc_argsize	= sizeof(struct nfsd3_##argt##args),		\
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index f0cccc0768ce..ed83e8a9e7b4 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -685,7 +685,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_GETATTR] = {
 		.pc_func = nfsd3_proc_getattr,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
+		.pc_decode = nfs3svc_decode_fhandleargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_attrstatres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
@@ -695,7 +695,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_SETATTR] = {
 		.pc_func = nfsd3_proc_setattr,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_sattrargs,
+		.pc_decode = nfs3svc_decode_sattrargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_sattrargs),
@@ -705,7 +705,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_LOOKUP] = {
 		.pc_func = nfsd3_proc_lookup,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs,
+		.pc_decode = nfs3svc_decode_diropargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_diropres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_diropargs),
@@ -715,7 +715,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_ACCESS] = {
 		.pc_func = nfsd3_proc_access,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_accessargs,
+		.pc_decode = nfs3svc_decode_accessargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_accessres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_accessargs),
@@ -725,7 +725,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_READLINK] = {
 		.pc_func = nfsd3_proc_readlink,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_readlinkargs,
+		.pc_decode = nfs3svc_decode_readlinkargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_readlinkres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_readlinkargs),
@@ -735,7 +735,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_READ] = {
 		.pc_func = nfsd3_proc_read,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_readargs,
+		.pc_decode = nfs3svc_decode_readargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_readres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_readargs),
@@ -745,7 +745,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_WRITE] = {
 		.pc_func = nfsd3_proc_write,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_writeargs,
+		.pc_decode = nfs3svc_decode_writeargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_writeres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_writeargs),
@@ -755,7 +755,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_CREATE] = {
 		.pc_func = nfsd3_proc_create,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_createargs,
+		.pc_decode = nfs3svc_decode_createargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_createargs),
@@ -765,7 +765,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_MKDIR] = {
 		.pc_func = nfsd3_proc_mkdir,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_mkdirargs,
+		.pc_decode = nfs3svc_decode_mkdirargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_mkdirargs),
@@ -775,7 +775,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_SYMLINK] = {
 		.pc_func = nfsd3_proc_symlink,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_symlinkargs,
+		.pc_decode = nfs3svc_decode_symlinkargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_symlinkargs),
@@ -785,7 +785,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_MKNOD] = {
 		.pc_func = nfsd3_proc_mknod,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_mknodargs,
+		.pc_decode = nfs3svc_decode_mknodargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_mknodargs),
@@ -795,7 +795,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_REMOVE] = {
 		.pc_func = nfsd3_proc_remove,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs,
+		.pc_decode = nfs3svc_decode_diropargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_diropargs),
@@ -805,7 +805,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_RMDIR] = {
 		.pc_func = nfsd3_proc_rmdir,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs,
+		.pc_decode = nfs3svc_decode_diropargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_diropargs),
@@ -815,7 +815,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_RENAME] = {
 		.pc_func = nfsd3_proc_rename,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_renameargs,
+		.pc_decode = nfs3svc_decode_renameargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_renameres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_renameargs),
@@ -825,7 +825,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_LINK] = {
 		.pc_func = nfsd3_proc_link,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_linkargs,
+		.pc_decode = nfs3svc_decode_linkargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_linkres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_linkargs),
@@ -835,7 +835,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_READDIR] = {
 		.pc_func = nfsd3_proc_readdir,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_readdirargs,
+		.pc_decode = nfs3svc_decode_readdirargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_readdirargs),
@@ -844,7 +844,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_READDIRPLUS] = {
 		.pc_func = nfsd3_proc_readdirplus,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_readdirplusargs,
+		.pc_decode = nfs3svc_decode_readdirplusargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_readdirplusargs),
@@ -853,7 +853,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_FSSTAT] = {
 		.pc_func = nfsd3_proc_fsstat,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
+		.pc_decode = nfs3svc_decode_fhandleargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_fsstatres,
 		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
 		.pc_ressize = sizeof(struct nfsd3_fsstatres),
@@ -862,7 +862,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_FSINFO] = {
 		.pc_func = nfsd3_proc_fsinfo,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
+		.pc_decode = nfs3svc_decode_fhandleargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_fsinfores,
 		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
 		.pc_ressize = sizeof(struct nfsd3_fsinfores),
@@ -871,7 +871,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_PATHCONF] = {
 		.pc_func = nfsd3_proc_pathconf,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
+		.pc_decode = nfs3svc_decode_fhandleargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_pathconfres,
 		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
 		.pc_ressize = sizeof(struct nfsd3_pathconfres),
@@ -880,7 +880,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 	[NFS3PROC_COMMIT] = {
 		.pc_func = nfsd3_proc_commit,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_commitargs,
+		.pc_decode = nfs3svc_decode_commitargs,
 		.pc_encode = (kxdrproc_t) nfs3svc_encode_commitres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_commitargs),
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index c3d3ef28347c..c56089ac2819 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -273,8 +273,10 @@ void fill_post_wcc(struct svc_fh *fhp)
  * XDR decode functions
  */
 int
-nfs3svc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *args)
+nfs3svc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_fhandle *args = rqstp->rq_argp;
+
 	p = decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
@@ -282,9 +284,10 @@ nfs3svc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *a
 }
 
 int
-nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_sattrargs *args)
+nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_sattrargs *args = rqstp->rq_argp;
+
 	p = decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
@@ -300,9 +303,10 @@ nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_diropargs *args)
+nfs3svc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_diropargs *args = rqstp->rq_argp;
+
 	if (!(p = decode_fh(p, &args->fh))
 	 || !(p = decode_filename(p, &args->name, &args->len)))
 		return 0;
@@ -311,9 +315,10 @@ nfs3svc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_accessargs *args)
+nfs3svc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_accessargs *args = rqstp->rq_argp;
+
 	p = decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
@@ -323,9 +328,9 @@ nfs3svc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_readargs *args)
+nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_readargs *args = rqstp->rq_argp;
 	unsigned int len;
 	int v;
 	u32 max_blocksize = svc_max_payload(rqstp);
@@ -353,9 +358,9 @@ nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_writeargs *args)
+nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_writeargs *args = rqstp->rq_argp;
 	unsigned int len, v, hdr, dlen;
 	u32 max_blocksize = svc_max_payload(rqstp);
 	struct kvec *head = rqstp->rq_arg.head;
@@ -413,9 +418,10 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_createargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_createargs *args)
+nfs3svc_decode_createargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_createargs *args = rqstp->rq_argp;
+
 	if (!(p = decode_fh(p, &args->fh))
 	 || !(p = decode_filename(p, &args->name, &args->len)))
 		return 0;
@@ -435,10 +441,12 @@ nfs3svc_decode_createargs(struct svc_rqst *rqstp, __be32 *p,
 
 	return xdr_argsize_check(rqstp, p);
 }
+
 int
-nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_createargs *args)
+nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_createargs *args = rqstp->rq_argp;
+
 	if (!(p = decode_fh(p, &args->fh)) ||
 	    !(p = decode_filename(p, &args->name, &args->len)))
 		return 0;
@@ -448,9 +456,9 @@ nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_symlinkargs *args)
+nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_symlinkargs *args = rqstp->rq_argp;
 	unsigned int len, avail;
 	char *old, *new;
 	struct kvec *vec;
@@ -500,9 +508,10 @@ nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_mknodargs *args)
+nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_mknodargs *args = rqstp->rq_argp;
+
 	if (!(p = decode_fh(p, &args->fh))
 	 || !(p = decode_filename(p, &args->name, &args->len)))
 		return 0;
@@ -522,9 +531,10 @@ nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_renameargs *args)
+nfs3svc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_renameargs *args = rqstp->rq_argp;
+
 	if (!(p = decode_fh(p, &args->ffh))
 	 || !(p = decode_filename(p, &args->fname, &args->flen))
 	 || !(p = decode_fh(p, &args->tfh))
@@ -535,9 +545,10 @@ nfs3svc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_readlinkargs *args)
+nfs3svc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_readlinkargs *args = rqstp->rq_argp;
+
 	p = decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
@@ -547,9 +558,10 @@ nfs3svc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_linkargs *args)
+nfs3svc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_linkargs *args = rqstp->rq_argp;
+
 	if (!(p = decode_fh(p, &args->ffh))
 	 || !(p = decode_fh(p, &args->tfh))
 	 || !(p = decode_filename(p, &args->tname, &args->tlen)))
@@ -559,9 +571,9 @@ nfs3svc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_readdirargs *args)
+nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_readdirargs *args = rqstp->rq_argp;
 	p = decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
@@ -576,9 +588,9 @@ nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_readdirargs *args)
+nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_readdirargs *args = rqstp->rq_argp;
 	int len;
 	u32 max_blocksize = svc_max_payload(rqstp);
 
@@ -602,9 +614,9 @@ nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_commitargs *args)
+nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_commitargs *args = rqstp->rq_argp;
 	p = decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 43b2e5ab4430..19c7d4b989c4 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -2527,7 +2527,7 @@ static struct svc_procedure		nfsd_procedures4[2] = {
 	},
 	[NFSPROC4_COMPOUND] = {
 		.pc_func = nfsd4_proc_compound,
-		.pc_decode = (kxdrproc_t) nfs4svc_decode_compoundargs,
+		.pc_decode = nfs4svc_decode_compoundargs,
 		.pc_encode = (kxdrproc_t) nfs4svc_encode_compoundres,
 		.pc_argsize = sizeof(struct nfsd4_compoundargs),
 		.pc_ressize = sizeof(struct nfsd4_compoundres),
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 5aa847bdfc63..3a7e117bd11e 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -4561,8 +4561,10 @@ void nfsd4_release_compoundargs(struct svc_rqst *rqstp)
 }
 
 int
-nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compoundargs *args)
+nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd4_compoundargs *args = rqstp->rq_argp;
+
 	if (rqstp->rq_arg.head[0].iov_len % 4) {
 		/* client is nuts */
 		dprintk("%s: compound not properly padded! (peeraddr=%pISc xid=0x%x)",
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index dc32e0f8480d..d351d0ef6d34 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -576,7 +576,7 @@ struct nfsd_void { int dummy; };
 static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_NULL] = {
 		.pc_func = nfsd_proc_null,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_void,
+		.pc_decode = nfssvc_decode_void,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_void),
 		.pc_ressize = sizeof(struct nfsd_void),
@@ -585,7 +585,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_GETATTR] = {
 		.pc_func = nfsd_proc_getattr,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_fhandle,
+		.pc_decode = nfssvc_decode_fhandle,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
 		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_fhandle),
@@ -595,7 +595,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_SETATTR] = {
 		.pc_func = nfsd_proc_setattr,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_sattrargs,
+		.pc_decode = nfssvc_decode_sattrargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
 		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_sattrargs),
@@ -604,7 +604,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_xdrressize = ST+AT,
 	},
 	[NFSPROC_ROOT] = {
-		.pc_decode = (kxdrproc_t) nfssvc_decode_void,
+		.pc_decode = nfssvc_decode_void,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_void),
 		.pc_ressize = sizeof(struct nfsd_void),
@@ -613,7 +613,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_LOOKUP] = {
 		.pc_func = nfsd_proc_lookup,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_diropargs,
+		.pc_decode = nfssvc_decode_diropargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
 		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_diropargs),
@@ -623,7 +623,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_READLINK] = {
 		.pc_func = nfsd_proc_readlink,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_readlinkargs,
+		.pc_decode = nfssvc_decode_readlinkargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_readlinkres,
 		.pc_argsize = sizeof(struct nfsd_readlinkargs),
 		.pc_ressize = sizeof(struct nfsd_readlinkres),
@@ -632,7 +632,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_READ] = {
 		.pc_func = nfsd_proc_read,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_readargs,
+		.pc_decode = nfssvc_decode_readargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_readres,
 		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_readargs),
@@ -641,7 +641,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 		.pc_xdrressize = ST+AT+1+NFSSVC_MAXBLKSIZE_V2/4,
 	},
 	[NFSPROC_WRITECACHE] = {
-		.pc_decode = (kxdrproc_t) nfssvc_decode_void,
+		.pc_decode = nfssvc_decode_void,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_void),
 		.pc_ressize = sizeof(struct nfsd_void),
@@ -650,7 +650,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_WRITE] = {
 		.pc_func = nfsd_proc_write,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_writeargs,
+		.pc_decode = nfssvc_decode_writeargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
 		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_writeargs),
@@ -660,7 +660,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_CREATE] = {
 		.pc_func = nfsd_proc_create,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_createargs,
+		.pc_decode = nfssvc_decode_createargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
 		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_createargs),
@@ -670,7 +670,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_REMOVE] = {
 		.pc_func = nfsd_proc_remove,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_diropargs,
+		.pc_decode = nfssvc_decode_diropargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_diropargs),
 		.pc_ressize = sizeof(struct nfsd_void),
@@ -679,7 +679,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_RENAME] = {
 		.pc_func = nfsd_proc_rename,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_renameargs,
+		.pc_decode = nfssvc_decode_renameargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_renameargs),
 		.pc_ressize = sizeof(struct nfsd_void),
@@ -688,7 +688,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_LINK] = {
 		.pc_func = nfsd_proc_link,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_linkargs,
+		.pc_decode = nfssvc_decode_linkargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_linkargs),
 		.pc_ressize = sizeof(struct nfsd_void),
@@ -697,7 +697,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_SYMLINK] = {
 		.pc_func = nfsd_proc_symlink,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_symlinkargs,
+		.pc_decode = nfssvc_decode_symlinkargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_symlinkargs),
 		.pc_ressize = sizeof(struct nfsd_void),
@@ -706,7 +706,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_MKDIR] = {
 		.pc_func = nfsd_proc_mkdir,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_createargs,
+		.pc_decode = nfssvc_decode_createargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
 		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_createargs),
@@ -716,7 +716,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_RMDIR] = {
 		.pc_func = nfsd_proc_rmdir,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_diropargs,
+		.pc_decode = nfssvc_decode_diropargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_diropargs),
 		.pc_ressize = sizeof(struct nfsd_void),
@@ -725,7 +725,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_READDIR] = {
 		.pc_func = nfsd_proc_readdir,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_readdirargs,
+		.pc_decode = nfssvc_decode_readdirargs,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_readdirres,
 		.pc_argsize = sizeof(struct nfsd_readdirargs),
 		.pc_ressize = sizeof(struct nfsd_readdirres),
@@ -733,7 +733,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_STATFS] = {
 		.pc_func = nfsd_proc_statfs,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_fhandle,
+		.pc_decode = nfssvc_decode_fhandle,
 		.pc_encode = (kxdrproc_t) nfssvc_encode_statfsres,
 		.pc_argsize = sizeof(struct nfsd_fhandle),
 		.pc_ressize = sizeof(struct nfsd_statfsres),
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index d64895fd8d25..3e00499d7ad7 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -801,9 +801,8 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 	 */
 	rqstp->rq_cachetype = proc->pc_cachetype;
 	/* Decode arguments */
-	xdr = proc->pc_decode;
-	if (xdr && !xdr(rqstp, (__be32*)rqstp->rq_arg.head[0].iov_base,
-			rqstp->rq_argp)) {
+	if (proc->pc_decode &&
+	    !proc->pc_decode(rqstp, (__be32*)rqstp->rq_arg.head[0].iov_base)) {
 		dprintk("nfsd: failed to decode arguments!\n");
 		*statp = rpc_garbage_args;
 		return 1;
diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c
index 2facfc6ac8f3..19cf04ebf388 100644
--- a/fs/nfsd/nfsxdr.c
+++ b/fs/nfsd/nfsxdr.c
@@ -206,14 +206,16 @@ __be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *f
  * XDR decode functions
  */
 int
-nfssvc_decode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+nfssvc_decode_void(struct svc_rqst *rqstp, __be32 *p)
 {
 	return xdr_argsize_check(rqstp, p);
 }
 
 int
-nfssvc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *args)
+nfssvc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_fhandle *args = rqstp->rq_argp;
+
 	p = decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
@@ -221,9 +223,10 @@ nfssvc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *ar
 }
 
 int
-nfssvc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_sattrargs *args)
+nfssvc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_sattrargs *args = rqstp->rq_argp;
+
 	p = decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
@@ -233,9 +236,10 @@ nfssvc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_diropargs *args)
+nfssvc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_diropargs *args = rqstp->rq_argp;
+
 	if (!(p = decode_fh(p, &args->fh))
 	 || !(p = decode_filename(p, &args->name, &args->len)))
 		return 0;
@@ -244,9 +248,9 @@ nfssvc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_readargs *args)
+nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_readargs *args = rqstp->rq_argp;
 	unsigned int len;
 	int v;
 	p = decode_fh(p, &args->fh);
@@ -276,9 +280,9 @@ nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_writeargs *args)
+nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_writeargs *args = rqstp->rq_argp;
 	unsigned int len, hdr, dlen;
 	struct kvec *head = rqstp->rq_arg.head;
 	int v;
@@ -332,9 +336,10 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_decode_createargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_createargs *args)
+nfssvc_decode_createargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_createargs *args = rqstp->rq_argp;
+
 	if (   !(p = decode_fh(p, &args->fh))
 	    || !(p = decode_filename(p, &args->name, &args->len)))
 		return 0;
@@ -344,9 +349,10 @@ nfssvc_decode_createargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_renameargs *args)
+nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_renameargs *args = rqstp->rq_argp;
+
 	if (!(p = decode_fh(p, &args->ffh))
 	 || !(p = decode_filename(p, &args->fname, &args->flen))
 	 || !(p = decode_fh(p, &args->tfh))
@@ -357,8 +363,10 @@ nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd_readlinkargs *args)
+nfssvc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_readlinkargs *args = rqstp->rq_argp;
+
 	p = decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
@@ -368,9 +376,10 @@ nfssvc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd_readli
 }
 
 int
-nfssvc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_linkargs *args)
+nfssvc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_linkargs *args = rqstp->rq_argp;
+
 	if (!(p = decode_fh(p, &args->ffh))
 	 || !(p = decode_fh(p, &args->tfh))
 	 || !(p = decode_filename(p, &args->tname, &args->tlen)))
@@ -380,9 +389,10 @@ nfssvc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_symlinkargs *args)
+nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_symlinkargs *args = rqstp->rq_argp;
+
 	if (   !(p = decode_fh(p, &args->ffh))
 	    || !(p = decode_filename(p, &args->fname, &args->flen))
 	    || !(p = decode_pathname(p, &args->tname, &args->tlen)))
@@ -393,9 +403,10 @@ nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_readdirargs *args)
+nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_readdirargs *args = rqstp->rq_argp;
+
 	p = decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h
index 2c21fa843fbf..8eeb752cf6f8 100644
--- a/fs/nfsd/xdr.h
+++ b/fs/nfsd/xdr.h
@@ -131,28 +131,18 @@ union nfsd_xdrstore {
 #define NFS2_SVC_XDRSIZE	sizeof(union nfsd_xdrstore)
 
 
-int nfssvc_decode_void(struct svc_rqst *, __be32 *, void *);
-int nfssvc_decode_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *);
-int nfssvc_decode_sattrargs(struct svc_rqst *, __be32 *,
-				struct nfsd_sattrargs *);
-int nfssvc_decode_diropargs(struct svc_rqst *, __be32 *,
-				struct nfsd_diropargs *);
-int nfssvc_decode_readargs(struct svc_rqst *, __be32 *,
-				struct nfsd_readargs *);
-int nfssvc_decode_writeargs(struct svc_rqst *, __be32 *,
-				struct nfsd_writeargs *);
-int nfssvc_decode_createargs(struct svc_rqst *, __be32 *,
-				struct nfsd_createargs *);
-int nfssvc_decode_renameargs(struct svc_rqst *, __be32 *,
-				struct nfsd_renameargs *);
-int nfssvc_decode_readlinkargs(struct svc_rqst *, __be32 *,
-				struct nfsd_readlinkargs *);
-int nfssvc_decode_linkargs(struct svc_rqst *, __be32 *,
-				struct nfsd_linkargs *);
-int nfssvc_decode_symlinkargs(struct svc_rqst *, __be32 *,
-				struct nfsd_symlinkargs *);
-int nfssvc_decode_readdirargs(struct svc_rqst *, __be32 *,
-				struct nfsd_readdirargs *);
+int nfssvc_decode_void(struct svc_rqst *, __be32 *);
+int nfssvc_decode_fhandle(struct svc_rqst *, __be32 *);
+int nfssvc_decode_sattrargs(struct svc_rqst *, __be32 *);
+int nfssvc_decode_diropargs(struct svc_rqst *, __be32 *);
+int nfssvc_decode_readargs(struct svc_rqst *, __be32 *);
+int nfssvc_decode_writeargs(struct svc_rqst *, __be32 *);
+int nfssvc_decode_createargs(struct svc_rqst *, __be32 *);
+int nfssvc_decode_renameargs(struct svc_rqst *, __be32 *);
+int nfssvc_decode_readlinkargs(struct svc_rqst *, __be32 *);
+int nfssvc_decode_linkargs(struct svc_rqst *, __be32 *);
+int nfssvc_decode_symlinkargs(struct svc_rqst *, __be32 *);
+int nfssvc_decode_readdirargs(struct svc_rqst *, __be32 *);
 int nfssvc_encode_void(struct svc_rqst *, __be32 *, void *);
 int nfssvc_encode_attrstat(struct svc_rqst *, __be32 *, struct nfsd_attrstat *);
 int nfssvc_encode_diropres(struct svc_rqst *, __be32 *, struct nfsd_diropres *);
diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h
index 23fe456a223b..f79be4c42e4a 100644
--- a/fs/nfsd/xdr3.h
+++ b/fs/nfsd/xdr3.h
@@ -269,37 +269,22 @@ union nfsd3_xdrstore {
 
 #define NFS3_SVC_XDRSIZE		sizeof(union nfsd3_xdrstore)
 
-int nfs3svc_decode_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *);
-int nfs3svc_decode_sattrargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_sattrargs *);
-int nfs3svc_decode_diropargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_diropargs *);
-int nfs3svc_decode_accessargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_accessargs *);
-int nfs3svc_decode_readargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_readargs *);
-int nfs3svc_decode_writeargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_writeargs *);
-int nfs3svc_decode_createargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_createargs *);
-int nfs3svc_decode_mkdirargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_createargs *);
-int nfs3svc_decode_mknodargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_mknodargs *);
-int nfs3svc_decode_renameargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_renameargs *);
-int nfs3svc_decode_readlinkargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_readlinkargs *);
-int nfs3svc_decode_linkargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_linkargs *);
-int nfs3svc_decode_symlinkargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_symlinkargs *);
-int nfs3svc_decode_readdirargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_readdirargs *);
-int nfs3svc_decode_readdirplusargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_readdirargs *);
-int nfs3svc_decode_commitargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_commitargs *);
+int nfs3svc_decode_fhandle(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_sattrargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_diropargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_accessargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_readargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_writeargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_createargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_mkdirargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_mknodargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_renameargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_readlinkargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_linkargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_symlinkargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_readdirargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_readdirplusargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_commitargs(struct svc_rqst *, __be32 *);
 int nfs3svc_encode_voidres(struct svc_rqst *, __be32 *, void *);
 int nfs3svc_encode_attrstat(struct svc_rqst *, __be32 *,
 				struct nfsd3_attrstat *);
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index a158579d55a2..2a53c1233884 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -683,8 +683,7 @@ set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp)
 
 bool nfsd4_mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp);
 int nfs4svc_encode_voidres(struct svc_rqst *, __be32 *, void *);
-int nfs4svc_decode_compoundargs(struct svc_rqst *, __be32 *,
-		struct nfsd4_compoundargs *);
+int nfs4svc_decode_compoundargs(struct svc_rqst *, __be32 *);
 int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *,
 		struct nfsd4_compoundres *);
 __be32 nfsd4_check_resp_size(struct nfsd4_compoundres *, u32);
diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h
index d39ed1cc5fbf..0416600844ce 100644
--- a/include/linux/lockd/xdr.h
+++ b/include/linux/lockd/xdr.h
@@ -95,19 +95,19 @@ struct nlm_reboot {
  */
 #define NLMSVC_XDRSIZE		sizeof(struct nlm_args)
 
-int	nlmsvc_decode_testargs(struct svc_rqst *, __be32 *, struct nlm_args *);
+int	nlmsvc_decode_testargs(struct svc_rqst *, __be32 *);
 int	nlmsvc_encode_testres(struct svc_rqst *, __be32 *, struct nlm_res *);
-int	nlmsvc_decode_lockargs(struct svc_rqst *, __be32 *, struct nlm_args *);
-int	nlmsvc_decode_cancargs(struct svc_rqst *, __be32 *, struct nlm_args *);
-int	nlmsvc_decode_unlockargs(struct svc_rqst *, __be32 *, struct nlm_args *);
+int	nlmsvc_decode_lockargs(struct svc_rqst *, __be32 *);
+int	nlmsvc_decode_cancargs(struct svc_rqst *, __be32 *);
+int	nlmsvc_decode_unlockargs(struct svc_rqst *, __be32 *);
 int	nlmsvc_encode_res(struct svc_rqst *, __be32 *, struct nlm_res *);
-int	nlmsvc_decode_res(struct svc_rqst *, __be32 *, struct nlm_res *);
+int	nlmsvc_decode_res(struct svc_rqst *, __be32 *);
 int	nlmsvc_encode_void(struct svc_rqst *, __be32 *, void *);
-int	nlmsvc_decode_void(struct svc_rqst *, __be32 *, void *);
-int	nlmsvc_decode_shareargs(struct svc_rqst *, __be32 *, struct nlm_args *);
+int	nlmsvc_decode_void(struct svc_rqst *, __be32 *);
+int	nlmsvc_decode_shareargs(struct svc_rqst *, __be32 *);
 int	nlmsvc_encode_shareres(struct svc_rqst *, __be32 *, struct nlm_res *);
-int	nlmsvc_decode_notify(struct svc_rqst *, __be32 *, struct nlm_args *);
-int	nlmsvc_decode_reboot(struct svc_rqst *, __be32 *, struct nlm_reboot *);
+int	nlmsvc_decode_notify(struct svc_rqst *, __be32 *);
+int	nlmsvc_decode_reboot(struct svc_rqst *, __be32 *);
 /*
 int	nlmclt_encode_testargs(struct rpc_rqst *, u32 *, struct nlm_args *);
 int	nlmclt_encode_lockargs(struct rpc_rqst *, u32 *, struct nlm_args *);
diff --git a/include/linux/lockd/xdr4.h b/include/linux/lockd/xdr4.h
index e58c88b52ce1..951bbe31fdb8 100644
--- a/include/linux/lockd/xdr4.h
+++ b/include/linux/lockd/xdr4.h
@@ -23,19 +23,19 @@
 
 
 
-int	nlm4svc_decode_testargs(struct svc_rqst *, __be32 *, struct nlm_args *);
+int	nlm4svc_decode_testargs(struct svc_rqst *, __be32 *);
 int	nlm4svc_encode_testres(struct svc_rqst *, __be32 *, struct nlm_res *);
-int	nlm4svc_decode_lockargs(struct svc_rqst *, __be32 *, struct nlm_args *);
-int	nlm4svc_decode_cancargs(struct svc_rqst *, __be32 *, struct nlm_args *);
-int	nlm4svc_decode_unlockargs(struct svc_rqst *, __be32 *, struct nlm_args *);
+int	nlm4svc_decode_lockargs(struct svc_rqst *, __be32 *);
+int	nlm4svc_decode_cancargs(struct svc_rqst *, __be32 *);
+int	nlm4svc_decode_unlockargs(struct svc_rqst *, __be32 *);
 int	nlm4svc_encode_res(struct svc_rqst *, __be32 *, struct nlm_res *);
-int	nlm4svc_decode_res(struct svc_rqst *, __be32 *, struct nlm_res *);
+int	nlm4svc_decode_res(struct svc_rqst *, __be32 *);
 int	nlm4svc_encode_void(struct svc_rqst *, __be32 *, void *);
-int	nlm4svc_decode_void(struct svc_rqst *, __be32 *, void *);
-int	nlm4svc_decode_shareargs(struct svc_rqst *, __be32 *, struct nlm_args *);
+int	nlm4svc_decode_void(struct svc_rqst *, __be32 *);
+int	nlm4svc_decode_shareargs(struct svc_rqst *, __be32 *);
 int	nlm4svc_encode_shareres(struct svc_rqst *, __be32 *, struct nlm_res *);
-int	nlm4svc_decode_notify(struct svc_rqst *, __be32 *, struct nlm_args *);
-int	nlm4svc_decode_reboot(struct svc_rqst *, __be32 *, struct nlm_reboot *);
+int	nlm4svc_decode_notify(struct svc_rqst *, __be32 *);
+int	nlm4svc_decode_reboot(struct svc_rqst *, __be32 *);
 /*
 int	nlmclt_encode_testargs(struct rpc_rqst *, u32 *, struct nlm_args *);
 int	nlmclt_encode_lockargs(struct rpc_rqst *, u32 *, struct nlm_args *);
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index c73194e9c2bd..d8703a5ab81e 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -422,7 +422,8 @@ struct svc_version {
 struct svc_procedure {
 	/* process the request: */
 	__be32			(*pc_func)(struct svc_rqst *);
-	kxdrproc_t		pc_decode;	/* XDR decode args */
+	/* XDR decode args: */
+	int			(*pc_decode)(struct svc_rqst *, __be32 *data);
 	kxdrproc_t		pc_encode;	/* XDR encode result */
 	/* XDR free result: */
 	void			(*pc_release)(struct svc_rqst *);
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 4611cb7adc04..18024c1b9b7b 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1276,9 +1276,12 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 
 	/* Call the function that processes the request. */
 	if (!versp->vs_dispatch) {
-		/* Decode arguments */
-		xdr = procp->pc_decode;
-		if (xdr && !xdr(rqstp, argv->iov_base, rqstp->rq_argp))
+		/*
+		 * Decode arguments
+		 * XXX: why do we ignore the return value?
+		 */
+		if (procp->pc_decode &&
+		    !procp->pc_decode(rqstp, argv->iov_base))
 			goto err_garbage;
 
 		*statp = procp->pc_func(rqstp);
-- 
cgit v1.2.3


From d16d1867215663907f3212590d1a9d32398a0f47 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 8 May 2017 19:42:02 +0200
Subject: sunrpc: properly type pc_encode callbacks

Drop the resp argument as it can trivially be derived from the rqstp
argument.  With that all functions now have the same prototype, and we
can remove the unsafe casting to kxdrproc_t.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 fs/lockd/svc4proc.c        |  2 +-
 fs/lockd/svcproc.c         |  2 +-
 fs/lockd/xdr.c             | 14 ++++++---
 fs/lockd/xdr4.c            | 14 ++++++---
 fs/nfs/callback_xdr.c      |  6 ++--
 fs/nfsd/nfs2acl.c          | 18 ++++++-----
 fs/nfsd/nfs3acl.c          | 11 +++----
 fs/nfsd/nfs3proc.c         | 44 +++++++++++++--------------
 fs/nfsd/nfs3xdr.c          | 74 +++++++++++++++++++++++++++-------------------
 fs/nfsd/nfs4proc.c         |  4 +--
 fs/nfsd/nfs4xdr.c          |  5 ++--
 fs/nfsd/nfsproc.c          | 36 +++++++++++-----------
 fs/nfsd/nfssvc.c           |  5 +---
 fs/nfsd/nfsxdr.c           | 31 +++++++++++--------
 fs/nfsd/xdr.h              | 14 ++++-----
 fs/nfsd/xdr3.h             | 45 ++++++++++------------------
 fs/nfsd/xdr4.h             |  5 ++--
 include/linux/lockd/xdr.h  |  8 ++---
 include/linux/lockd/xdr4.h |  8 ++---
 include/linux/sunrpc/svc.h |  3 +-
 net/sunrpc/svc.c           |  6 ++--
 21 files changed, 185 insertions(+), 170 deletions(-)

(limited to 'include')

diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index 804744f7528c..fed016155791 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -497,7 +497,7 @@ struct nlm_void			{ int dummy; };
 #define PROC(name, xargt, xrest, argt, rest, respsize)	\
  { .pc_func	= nlm4svc_proc_##name,	\
    .pc_decode	= nlm4svc_decode_##xargt,	\
-   .pc_encode	= (kxdrproc_t) nlm4svc_encode_##xrest,	\
+   .pc_encode	= nlm4svc_encode_##xrest,	\
    .pc_release	= NULL,					\
    .pc_argsize	= sizeof(struct nlm_##argt),		\
    .pc_ressize	= sizeof(struct nlm_##rest),		\
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index 204a698f7d41..14648b051eba 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -539,7 +539,7 @@ struct nlm_void			{ int dummy; };
 #define PROC(name, xargt, xrest, argt, rest, respsize)	\
  { .pc_func	= nlmsvc_proc_##name,			\
    .pc_decode	= nlmsvc_decode_##xargt,		\
-   .pc_encode	= (kxdrproc_t) nlmsvc_encode_##xrest,	\
+   .pc_encode	= nlmsvc_encode_##xrest,		\
    .pc_release	= NULL,					\
    .pc_argsize	= sizeof(struct nlm_##argt),		\
    .pc_ressize	= sizeof(struct nlm_##rest),		\
diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c
index b57af63fba56..442bbd0b0b29 100644
--- a/fs/lockd/xdr.c
+++ b/fs/lockd/xdr.c
@@ -200,8 +200,10 @@ nlmsvc_decode_testargs(struct svc_rqst *rqstp, __be32 *p)
 }
 
 int
-nlmsvc_encode_testres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
+nlmsvc_encode_testres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_res *resp = rqstp->rq_resp;
+
 	if (!(p = nlm_encode_testres(p, resp)))
 		return 0;
 	return xdr_ressize_check(rqstp, p);
@@ -280,8 +282,10 @@ nlmsvc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p)
 }
 
 int
-nlmsvc_encode_shareres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
+nlmsvc_encode_shareres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_res *resp = rqstp->rq_resp;
+
 	if (!(p = nlm_encode_cookie(p, &resp->cookie)))
 		return 0;
 	*p++ = resp->status;
@@ -290,8 +294,10 @@ nlmsvc_encode_shareres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
 }
 
 int
-nlmsvc_encode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
+nlmsvc_encode_res(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_res *resp = rqstp->rq_resp;
+
 	if (!(p = nlm_encode_cookie(p, &resp->cookie)))
 		return 0;
 	*p++ = resp->status;
@@ -342,7 +348,7 @@ nlmsvc_decode_void(struct svc_rqst *rqstp, __be32 *p)
 }
 
 int
-nlmsvc_encode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+nlmsvc_encode_void(struct svc_rqst *rqstp, __be32 *p)
 {
 	return xdr_ressize_check(rqstp, p);
 }
diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c
index 46e18598a15c..2a0cd5679c49 100644
--- a/fs/lockd/xdr4.c
+++ b/fs/lockd/xdr4.c
@@ -197,8 +197,10 @@ nlm4svc_decode_testargs(struct svc_rqst *rqstp, __be32 *p)
 }
 
 int
-nlm4svc_encode_testres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
+nlm4svc_encode_testres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_res *resp = rqstp->rq_resp;
+
 	if (!(p = nlm4_encode_testres(p, resp)))
 		return 0;
 	return xdr_ressize_check(rqstp, p);
@@ -277,8 +279,10 @@ nlm4svc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p)
 }
 
 int
-nlm4svc_encode_shareres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
+nlm4svc_encode_shareres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_res *resp = rqstp->rq_resp;
+
 	if (!(p = nlm4_encode_cookie(p, &resp->cookie)))
 		return 0;
 	*p++ = resp->status;
@@ -287,8 +291,10 @@ nlm4svc_encode_shareres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
 }
 
 int
-nlm4svc_encode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
+nlm4svc_encode_res(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_res *resp = rqstp->rq_resp;
+
 	if (!(p = nlm4_encode_cookie(p, &resp->cookie)))
 		return 0;
 	*p++ = resp->status;
@@ -339,7 +345,7 @@ nlm4svc_decode_void(struct svc_rqst *rqstp, __be32 *p)
 }
 
 int
-nlm4svc_encode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+nlm4svc_encode_void(struct svc_rqst *rqstp, __be32 *p)
 {
 	return xdr_ressize_check(rqstp, p);
 }
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index 23ecbf7a40c1..acf75dc63e14 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -63,7 +63,7 @@ static int nfs4_decode_void(struct svc_rqst *rqstp, __be32 *p)
 	return xdr_argsize_check(rqstp, p);
 }
 
-static int nfs4_encode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+static int nfs4_encode_void(struct svc_rqst *rqstp, __be32 *p)
 {
 	return xdr_ressize_check(rqstp, p);
 }
@@ -999,12 +999,12 @@ static struct svc_procedure nfs4_callback_procedures1[] = {
 	[CB_NULL] = {
 		.pc_func = nfs4_callback_null,
 		.pc_decode = nfs4_decode_void,
-		.pc_encode = (kxdrproc_t)nfs4_encode_void,
+		.pc_encode = nfs4_encode_void,
 		.pc_xdrressize = 1,
 	},
 	[CB_COMPOUND] = {
 		.pc_func = nfs4_callback_compound,
-		.pc_encode = (kxdrproc_t)nfs4_encode_void,
+		.pc_encode = nfs4_encode_void,
 		.pc_argsize = 256,
 		.pc_ressize = 256,
 		.pc_xdrressize = NFS4_CALLBACK_BUFSIZE,
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index bcfdaa83ee6c..fc6b179c8fff 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -251,15 +251,15 @@ static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p)
  * There must be an encoding function for void results so svc_process
  * will work properly.
  */
-static int nfsaclsvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+static int nfsaclsvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p)
 {
 	return xdr_ressize_check(rqstp, p);
 }
 
 /* GETACL */
-static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_getaclres *resp)
+static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_getaclres *resp = rqstp->rq_resp;
 	struct dentry *dentry = resp->fh.fh_dentry;
 	struct inode *inode;
 	struct kvec *head = rqstp->rq_res.head;
@@ -302,17 +302,19 @@ static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p,
 	return (n > 0);
 }
 
-static int nfsaclsvc_encode_attrstatres(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd_attrstat *resp)
+static int nfsaclsvc_encode_attrstatres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_attrstat *resp = rqstp->rq_resp;
+
 	p = nfs2svc_encode_fattr(rqstp, p, &resp->fh, &resp->stat);
 	return xdr_ressize_check(rqstp, p);
 }
 
 /* ACCESS */
-static int nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_accessres *resp)
+static int nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_accessres *resp = rqstp->rq_resp;
+
 	p = nfs2svc_encode_fattr(rqstp, p, &resp->fh, &resp->stat);
 	*p++ = htonl(resp->access);
 	return xdr_ressize_check(rqstp, p);
@@ -355,7 +357,7 @@ struct nfsd3_voidargs { int dummy; };
 {									\
 	.pc_func	= nfsacld_proc_##name,				\
 	.pc_decode	= nfsaclsvc_decode_##argt##args,		\
-	.pc_encode	= (kxdrproc_t) nfsaclsvc_encode_##rest##res,	\
+	.pc_encode	= nfsaclsvc_encode_##rest##res,			\
 	.pc_release	= nfsaclsvc_release_##relt,	\
 	.pc_argsize	= sizeof(struct nfsd3_##argt##args),		\
 	.pc_ressize	= sizeof(struct nfsd3_##rest##res),		\
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index 4e68d6b5f409..9437b758cbfd 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -168,9 +168,9 @@ static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p)
  */
 
 /* GETACL */
-static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_getaclres *resp)
+static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_getaclres *resp = rqstp->rq_resp;
 	struct dentry *dentry = resp->fh.fh_dentry;
 
 	p = nfs3svc_encode_post_op_attr(rqstp, p, &resp->fh);
@@ -213,9 +213,10 @@ static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p,
 }
 
 /* SETACL */
-static int nfs3svc_encode_setaclres(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_attrstat *resp)
+static int nfs3svc_encode_setaclres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_attrstat *resp = rqstp->rq_resp;
+
 	p = nfs3svc_encode_post_op_attr(rqstp, p, &resp->fh);
 
 	return xdr_ressize_check(rqstp, p);
@@ -243,7 +244,7 @@ struct nfsd3_voidargs { int dummy; };
 {									\
 	.pc_func	= nfsd3_proc_##name,				\
 	.pc_decode	= nfs3svc_decode_##argt##args,			\
-	.pc_encode	= (kxdrproc_t) nfs3svc_encode_##rest##res,	\
+	.pc_encode	= nfs3svc_encode_##rest##res,			\
 	.pc_release	= nfs3svc_release_##relt,			\
 	.pc_argsize	= sizeof(struct nfsd3_##argt##args),		\
 	.pc_ressize	= sizeof(struct nfsd3_##rest##res),		\
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index ed83e8a9e7b4..17c90c41a3a6 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -677,7 +677,7 @@ struct nfsd3_voidargs { int dummy; };
 static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_NULL] = {
 		.pc_func = nfsd3_proc_null,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_voidres,
+		.pc_encode = nfs3svc_encode_voidres,
 		.pc_argsize = sizeof(struct nfsd3_voidargs),
 		.pc_ressize = sizeof(struct nfsd3_voidres),
 		.pc_cachetype = RC_NOCACHE,
@@ -686,7 +686,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_GETATTR] = {
 		.pc_func = nfsd3_proc_getattr,
 		.pc_decode = nfs3svc_decode_fhandleargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_attrstatres,
+		.pc_encode = nfs3svc_encode_attrstatres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
 		.pc_ressize = sizeof(struct nfsd3_attrstatres),
@@ -696,7 +696,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_SETATTR] = {
 		.pc_func = nfsd3_proc_setattr,
 		.pc_decode = nfs3svc_decode_sattrargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
+		.pc_encode = nfs3svc_encode_wccstatres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_sattrargs),
 		.pc_ressize = sizeof(struct nfsd3_wccstatres),
@@ -706,7 +706,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_LOOKUP] = {
 		.pc_func = nfsd3_proc_lookup,
 		.pc_decode = nfs3svc_decode_diropargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_diropres,
+		.pc_encode = nfs3svc_encode_diropres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_diropargs),
 		.pc_ressize = sizeof(struct nfsd3_diropres),
@@ -716,7 +716,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_ACCESS] = {
 		.pc_func = nfsd3_proc_access,
 		.pc_decode = nfs3svc_decode_accessargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_accessres,
+		.pc_encode = nfs3svc_encode_accessres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_accessargs),
 		.pc_ressize = sizeof(struct nfsd3_accessres),
@@ -726,7 +726,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_READLINK] = {
 		.pc_func = nfsd3_proc_readlink,
 		.pc_decode = nfs3svc_decode_readlinkargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_readlinkres,
+		.pc_encode = nfs3svc_encode_readlinkres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_readlinkargs),
 		.pc_ressize = sizeof(struct nfsd3_readlinkres),
@@ -736,7 +736,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_READ] = {
 		.pc_func = nfsd3_proc_read,
 		.pc_decode = nfs3svc_decode_readargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_readres,
+		.pc_encode = nfs3svc_encode_readres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_readargs),
 		.pc_ressize = sizeof(struct nfsd3_readres),
@@ -746,7 +746,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_WRITE] = {
 		.pc_func = nfsd3_proc_write,
 		.pc_decode = nfs3svc_decode_writeargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_writeres,
+		.pc_encode = nfs3svc_encode_writeres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_writeargs),
 		.pc_ressize = sizeof(struct nfsd3_writeres),
@@ -756,7 +756,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_CREATE] = {
 		.pc_func = nfsd3_proc_create,
 		.pc_decode = nfs3svc_decode_createargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
+		.pc_encode = nfs3svc_encode_createres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_createargs),
 		.pc_ressize = sizeof(struct nfsd3_createres),
@@ -766,7 +766,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_MKDIR] = {
 		.pc_func = nfsd3_proc_mkdir,
 		.pc_decode = nfs3svc_decode_mkdirargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
+		.pc_encode = nfs3svc_encode_createres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_mkdirargs),
 		.pc_ressize = sizeof(struct nfsd3_createres),
@@ -776,7 +776,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_SYMLINK] = {
 		.pc_func = nfsd3_proc_symlink,
 		.pc_decode = nfs3svc_decode_symlinkargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
+		.pc_encode = nfs3svc_encode_createres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_symlinkargs),
 		.pc_ressize = sizeof(struct nfsd3_createres),
@@ -786,7 +786,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_MKNOD] = {
 		.pc_func = nfsd3_proc_mknod,
 		.pc_decode = nfs3svc_decode_mknodargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
+		.pc_encode = nfs3svc_encode_createres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_mknodargs),
 		.pc_ressize = sizeof(struct nfsd3_createres),
@@ -796,7 +796,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_REMOVE] = {
 		.pc_func = nfsd3_proc_remove,
 		.pc_decode = nfs3svc_decode_diropargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
+		.pc_encode = nfs3svc_encode_wccstatres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_diropargs),
 		.pc_ressize = sizeof(struct nfsd3_wccstatres),
@@ -806,7 +806,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_RMDIR] = {
 		.pc_func = nfsd3_proc_rmdir,
 		.pc_decode = nfs3svc_decode_diropargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
+		.pc_encode = nfs3svc_encode_wccstatres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_diropargs),
 		.pc_ressize = sizeof(struct nfsd3_wccstatres),
@@ -816,7 +816,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_RENAME] = {
 		.pc_func = nfsd3_proc_rename,
 		.pc_decode = nfs3svc_decode_renameargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_renameres,
+		.pc_encode = nfs3svc_encode_renameres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_renameargs),
 		.pc_ressize = sizeof(struct nfsd3_renameres),
@@ -826,7 +826,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_LINK] = {
 		.pc_func = nfsd3_proc_link,
 		.pc_decode = nfs3svc_decode_linkargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_linkres,
+		.pc_encode = nfs3svc_encode_linkres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_linkargs),
 		.pc_ressize = sizeof(struct nfsd3_linkres),
@@ -836,7 +836,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_READDIR] = {
 		.pc_func = nfsd3_proc_readdir,
 		.pc_decode = nfs3svc_decode_readdirargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres,
+		.pc_encode = nfs3svc_encode_readdirres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_readdirargs),
 		.pc_ressize = sizeof(struct nfsd3_readdirres),
@@ -845,7 +845,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_READDIRPLUS] = {
 		.pc_func = nfsd3_proc_readdirplus,
 		.pc_decode = nfs3svc_decode_readdirplusargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres,
+		.pc_encode = nfs3svc_encode_readdirres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_readdirplusargs),
 		.pc_ressize = sizeof(struct nfsd3_readdirres),
@@ -854,7 +854,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_FSSTAT] = {
 		.pc_func = nfsd3_proc_fsstat,
 		.pc_decode = nfs3svc_decode_fhandleargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_fsstatres,
+		.pc_encode = nfs3svc_encode_fsstatres,
 		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
 		.pc_ressize = sizeof(struct nfsd3_fsstatres),
 		.pc_cachetype = RC_NOCACHE,
@@ -863,7 +863,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_FSINFO] = {
 		.pc_func = nfsd3_proc_fsinfo,
 		.pc_decode = nfs3svc_decode_fhandleargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_fsinfores,
+		.pc_encode = nfs3svc_encode_fsinfores,
 		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
 		.pc_ressize = sizeof(struct nfsd3_fsinfores),
 		.pc_cachetype = RC_NOCACHE,
@@ -872,7 +872,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_PATHCONF] = {
 		.pc_func = nfsd3_proc_pathconf,
 		.pc_decode = nfs3svc_decode_fhandleargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_pathconfres,
+		.pc_encode = nfs3svc_encode_pathconfres,
 		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
 		.pc_ressize = sizeof(struct nfsd3_pathconfres),
 		.pc_cachetype = RC_NOCACHE,
@@ -881,7 +881,7 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	[NFS3PROC_COMMIT] = {
 		.pc_func = nfsd3_proc_commit,
 		.pc_decode = nfs3svc_decode_commitargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_commitres,
+		.pc_encode = nfs3svc_encode_commitres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_commitargs),
 		.pc_ressize = sizeof(struct nfsd3_commitres),
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index c56089ac2819..b8838d3023ff 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -634,16 +634,17 @@ nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p)
  * will work properly.
  */
 int
-nfs3svc_encode_voidres(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+nfs3svc_encode_voidres(struct svc_rqst *rqstp, __be32 *p)
 {
 	return xdr_ressize_check(rqstp, p);
 }
 
 /* GETATTR */
 int
-nfs3svc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_attrstat *resp)
+nfs3svc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_attrstat *resp = rqstp->rq_resp;
+
 	if (resp->status == 0) {
 		lease_get_mtime(d_inode(resp->fh.fh_dentry),
 				&resp->stat.mtime);
@@ -654,18 +655,20 @@ nfs3svc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p,
 
 /* SETATTR, REMOVE, RMDIR */
 int
-nfs3svc_encode_wccstat(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_attrstat *resp)
+nfs3svc_encode_wccstat(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_attrstat *resp = rqstp->rq_resp;
+
 	p = encode_wcc_data(rqstp, p, &resp->fh);
 	return xdr_ressize_check(rqstp, p);
 }
 
 /* LOOKUP */
 int
-nfs3svc_encode_diropres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_diropres *resp)
+nfs3svc_encode_diropres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_diropres *resp = rqstp->rq_resp;
+
 	if (resp->status == 0) {
 		p = encode_fh(p, &resp->fh);
 		p = encode_post_op_attr(rqstp, p, &resp->fh);
@@ -676,9 +679,10 @@ nfs3svc_encode_diropres(struct svc_rqst *rqstp, __be32 *p,
 
 /* ACCESS */
 int
-nfs3svc_encode_accessres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_accessres *resp)
+nfs3svc_encode_accessres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_accessres *resp = rqstp->rq_resp;
+
 	p = encode_post_op_attr(rqstp, p, &resp->fh);
 	if (resp->status == 0)
 		*p++ = htonl(resp->access);
@@ -687,9 +691,10 @@ nfs3svc_encode_accessres(struct svc_rqst *rqstp, __be32 *p,
 
 /* READLINK */
 int
-nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_readlinkres *resp)
+nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_readlinkres *resp = rqstp->rq_resp;
+
 	p = encode_post_op_attr(rqstp, p, &resp->fh);
 	if (resp->status == 0) {
 		*p++ = htonl(resp->len);
@@ -708,9 +713,10 @@ nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p,
 
 /* READ */
 int
-nfs3svc_encode_readres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_readres *resp)
+nfs3svc_encode_readres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_readres *resp = rqstp->rq_resp;
+
 	p = encode_post_op_attr(rqstp, p, &resp->fh);
 	if (resp->status == 0) {
 		*p++ = htonl(resp->count);
@@ -732,9 +738,9 @@ nfs3svc_encode_readres(struct svc_rqst *rqstp, __be32 *p,
 
 /* WRITE */
 int
-nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_writeres *resp)
+nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_writeres *resp = rqstp->rq_resp;
 	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
 
 	p = encode_wcc_data(rqstp, p, &resp->fh);
@@ -749,9 +755,10 @@ nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p,
 
 /* CREATE, MKDIR, SYMLINK, MKNOD */
 int
-nfs3svc_encode_createres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_diropres *resp)
+nfs3svc_encode_createres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_diropres *resp = rqstp->rq_resp;
+
 	if (resp->status == 0) {
 		*p++ = xdr_one;
 		p = encode_fh(p, &resp->fh);
@@ -763,9 +770,10 @@ nfs3svc_encode_createres(struct svc_rqst *rqstp, __be32 *p,
 
 /* RENAME */
 int
-nfs3svc_encode_renameres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_renameres *resp)
+nfs3svc_encode_renameres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_renameres *resp = rqstp->rq_resp;
+
 	p = encode_wcc_data(rqstp, p, &resp->ffh);
 	p = encode_wcc_data(rqstp, p, &resp->tfh);
 	return xdr_ressize_check(rqstp, p);
@@ -773,9 +781,10 @@ nfs3svc_encode_renameres(struct svc_rqst *rqstp, __be32 *p,
 
 /* LINK */
 int
-nfs3svc_encode_linkres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_linkres *resp)
+nfs3svc_encode_linkres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_linkres *resp = rqstp->rq_resp;
+
 	p = encode_post_op_attr(rqstp, p, &resp->fh);
 	p = encode_wcc_data(rqstp, p, &resp->tfh);
 	return xdr_ressize_check(rqstp, p);
@@ -783,9 +792,10 @@ nfs3svc_encode_linkres(struct svc_rqst *rqstp, __be32 *p,
 
 /* READDIR */
 int
-nfs3svc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_readdirres *resp)
+nfs3svc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_readdirres *resp = rqstp->rq_resp;
+
 	p = encode_post_op_attr(rqstp, p, &resp->fh);
 
 	if (resp->status == 0) {
@@ -1033,9 +1043,9 @@ nfs3svc_encode_entry_plus(void *cd, const char *name,
 
 /* FSSTAT */
 int
-nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_fsstatres *resp)
+nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_fsstatres *resp = rqstp->rq_resp;
 	struct kstatfs	*s = &resp->stats;
 	u64		bs = s->f_bsize;
 
@@ -1055,9 +1065,10 @@ nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, __be32 *p,
 
 /* FSINFO */
 int
-nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_fsinfores *resp)
+nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_fsinfores *resp = rqstp->rq_resp;
+
 	*p++ = xdr_zero;	/* no post_op_attr */
 
 	if (resp->status == 0) {
@@ -1079,9 +1090,10 @@ nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, __be32 *p,
 
 /* PATHCONF */
 int
-nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_pathconfres *resp)
+nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_pathconfres *resp = rqstp->rq_resp;
+
 	*p++ = xdr_zero;	/* no post_op_attr */
 
 	if (resp->status == 0) {
@@ -1098,9 +1110,9 @@ nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, __be32 *p,
 
 /* COMMIT */
 int
-nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_commitres *resp)
+nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_commitres *resp = rqstp->rq_resp;
 	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
 
 	p = encode_wcc_data(rqstp, p, &resp->fh);
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 19c7d4b989c4..726d28376f7b 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -2519,7 +2519,7 @@ struct nfsd4_voidargs { int dummy; };
 static struct svc_procedure		nfsd_procedures4[2] = {
 	[NFSPROC4_NULL] = {
 		.pc_func = nfsd4_proc_null,
-		.pc_encode = (kxdrproc_t) nfs4svc_encode_voidres,
+		.pc_encode = nfs4svc_encode_voidres,
 		.pc_argsize = sizeof(struct nfsd4_voidargs),
 		.pc_ressize = sizeof(struct nfsd4_voidres),
 		.pc_cachetype = RC_NOCACHE,
@@ -2528,7 +2528,7 @@ static struct svc_procedure		nfsd_procedures4[2] = {
 	[NFSPROC4_COMPOUND] = {
 		.pc_func = nfsd4_proc_compound,
 		.pc_decode = nfs4svc_decode_compoundargs,
-		.pc_encode = (kxdrproc_t) nfs4svc_encode_compoundres,
+		.pc_encode = nfs4svc_encode_compoundres,
 		.pc_argsize = sizeof(struct nfsd4_compoundargs),
 		.pc_ressize = sizeof(struct nfsd4_compoundres),
 		.pc_release = nfsd4_release_compoundargs,
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 3a7e117bd11e..54e212e3541e 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -4538,7 +4538,7 @@ nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op)
 }
 
 int
-nfs4svc_encode_voidres(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+nfs4svc_encode_voidres(struct svc_rqst *rqstp, __be32 *p)
 {
         return xdr_ressize_check(rqstp, p);
 }
@@ -4584,11 +4584,12 @@ nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, __be32 *p)
 }
 
 int
-nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compoundres *resp)
+nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p)
 {
 	/*
 	 * All that remains is to write the tag and operation count...
 	 */
+	struct nfsd4_compoundres *resp = rqstp->rq_resp;
 	struct xdr_buf *buf = resp->xdr.buf;
 
 	WARN_ON_ONCE(buf->len != buf->head[0].iov_len + buf->page_len +
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index d351d0ef6d34..0ef88d0e67d9 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -577,7 +577,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_NULL] = {
 		.pc_func = nfsd_proc_null,
 		.pc_decode = nfssvc_decode_void,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
+		.pc_encode = nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_void),
 		.pc_ressize = sizeof(struct nfsd_void),
 		.pc_cachetype = RC_NOCACHE,
@@ -586,7 +586,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_GETATTR] = {
 		.pc_func = nfsd_proc_getattr,
 		.pc_decode = nfssvc_decode_fhandle,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
+		.pc_encode = nfssvc_encode_attrstat,
 		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_fhandle),
 		.pc_ressize = sizeof(struct nfsd_attrstat),
@@ -596,7 +596,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_SETATTR] = {
 		.pc_func = nfsd_proc_setattr,
 		.pc_decode = nfssvc_decode_sattrargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
+		.pc_encode = nfssvc_encode_attrstat,
 		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_sattrargs),
 		.pc_ressize = sizeof(struct nfsd_attrstat),
@@ -605,7 +605,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_ROOT] = {
 		.pc_decode = nfssvc_decode_void,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
+		.pc_encode = nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_void),
 		.pc_ressize = sizeof(struct nfsd_void),
 		.pc_cachetype = RC_NOCACHE,
@@ -614,7 +614,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_LOOKUP] = {
 		.pc_func = nfsd_proc_lookup,
 		.pc_decode = nfssvc_decode_diropargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
+		.pc_encode = nfssvc_encode_diropres,
 		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_diropargs),
 		.pc_ressize = sizeof(struct nfsd_diropres),
@@ -624,7 +624,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_READLINK] = {
 		.pc_func = nfsd_proc_readlink,
 		.pc_decode = nfssvc_decode_readlinkargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_readlinkres,
+		.pc_encode = nfssvc_encode_readlinkres,
 		.pc_argsize = sizeof(struct nfsd_readlinkargs),
 		.pc_ressize = sizeof(struct nfsd_readlinkres),
 		.pc_cachetype = RC_NOCACHE,
@@ -633,7 +633,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_READ] = {
 		.pc_func = nfsd_proc_read,
 		.pc_decode = nfssvc_decode_readargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_readres,
+		.pc_encode = nfssvc_encode_readres,
 		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_readargs),
 		.pc_ressize = sizeof(struct nfsd_readres),
@@ -642,7 +642,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	},
 	[NFSPROC_WRITECACHE] = {
 		.pc_decode = nfssvc_decode_void,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
+		.pc_encode = nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_void),
 		.pc_ressize = sizeof(struct nfsd_void),
 		.pc_cachetype = RC_NOCACHE,
@@ -651,7 +651,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_WRITE] = {
 		.pc_func = nfsd_proc_write,
 		.pc_decode = nfssvc_decode_writeargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
+		.pc_encode = nfssvc_encode_attrstat,
 		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_writeargs),
 		.pc_ressize = sizeof(struct nfsd_attrstat),
@@ -661,7 +661,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_CREATE] = {
 		.pc_func = nfsd_proc_create,
 		.pc_decode = nfssvc_decode_createargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
+		.pc_encode = nfssvc_encode_diropres,
 		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_createargs),
 		.pc_ressize = sizeof(struct nfsd_diropres),
@@ -671,7 +671,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_REMOVE] = {
 		.pc_func = nfsd_proc_remove,
 		.pc_decode = nfssvc_decode_diropargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
+		.pc_encode = nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_diropargs),
 		.pc_ressize = sizeof(struct nfsd_void),
 		.pc_cachetype = RC_REPLSTAT,
@@ -680,7 +680,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_RENAME] = {
 		.pc_func = nfsd_proc_rename,
 		.pc_decode = nfssvc_decode_renameargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
+		.pc_encode = nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_renameargs),
 		.pc_ressize = sizeof(struct nfsd_void),
 		.pc_cachetype = RC_REPLSTAT,
@@ -689,7 +689,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_LINK] = {
 		.pc_func = nfsd_proc_link,
 		.pc_decode = nfssvc_decode_linkargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
+		.pc_encode = nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_linkargs),
 		.pc_ressize = sizeof(struct nfsd_void),
 		.pc_cachetype = RC_REPLSTAT,
@@ -698,7 +698,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_SYMLINK] = {
 		.pc_func = nfsd_proc_symlink,
 		.pc_decode = nfssvc_decode_symlinkargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
+		.pc_encode = nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_symlinkargs),
 		.pc_ressize = sizeof(struct nfsd_void),
 		.pc_cachetype = RC_REPLSTAT,
@@ -707,7 +707,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_MKDIR] = {
 		.pc_func = nfsd_proc_mkdir,
 		.pc_decode = nfssvc_decode_createargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
+		.pc_encode = nfssvc_encode_diropres,
 		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_createargs),
 		.pc_ressize = sizeof(struct nfsd_diropres),
@@ -717,7 +717,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_RMDIR] = {
 		.pc_func = nfsd_proc_rmdir,
 		.pc_decode = nfssvc_decode_diropargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
+		.pc_encode = nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_diropargs),
 		.pc_ressize = sizeof(struct nfsd_void),
 		.pc_cachetype = RC_REPLSTAT,
@@ -726,7 +726,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_READDIR] = {
 		.pc_func = nfsd_proc_readdir,
 		.pc_decode = nfssvc_decode_readdirargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_readdirres,
+		.pc_encode = nfssvc_encode_readdirres,
 		.pc_argsize = sizeof(struct nfsd_readdirargs),
 		.pc_ressize = sizeof(struct nfsd_readdirres),
 		.pc_cachetype = RC_NOCACHE,
@@ -734,7 +734,7 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 	[NFSPROC_STATFS] = {
 		.pc_func = nfsd_proc_statfs,
 		.pc_decode = nfssvc_decode_fhandle,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_statfsres,
+		.pc_encode = nfssvc_encode_statfsres,
 		.pc_argsize = sizeof(struct nfsd_fhandle),
 		.pc_ressize = sizeof(struct nfsd_statfsres),
 		.pc_cachetype = RC_NOCACHE,
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 3e00499d7ad7..555233664124 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -782,7 +782,6 @@ int
 nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 {
 	struct svc_procedure	*proc;
-	kxdrproc_t		xdr;
 	__be32			nfserr;
 	__be32			*nfserrp;
 
@@ -841,9 +840,7 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 	 * For NFSv2, additional info is never returned in case of an error.
 	 */
 	if (!(nfserr && rqstp->rq_vers == 2)) {
-		xdr = proc->pc_encode;
-		if (xdr && !xdr(rqstp, nfserrp,
-				rqstp->rq_resp)) {
+		if (proc->pc_encode && !proc->pc_encode(rqstp, nfserrp)) {
 			/* Failed to encode result. Release cache entry */
 			dprintk("nfsd: failed to encode result!\n");
 			nfsd_cache_update(rqstp, RC_NOCACHE, NULL);
diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c
index 19cf04ebf388..e4da2717982d 100644
--- a/fs/nfsd/nfsxdr.c
+++ b/fs/nfsd/nfsxdr.c
@@ -422,32 +422,35 @@ nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p)
  * XDR encode functions
  */
 int
-nfssvc_encode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+nfssvc_encode_void(struct svc_rqst *rqstp, __be32 *p)
 {
 	return xdr_ressize_check(rqstp, p);
 }
 
 int
-nfssvc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_attrstat *resp)
+nfssvc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_attrstat *resp = rqstp->rq_resp;
+
 	p = encode_fattr(rqstp, p, &resp->fh, &resp->stat);
 	return xdr_ressize_check(rqstp, p);
 }
 
 int
-nfssvc_encode_diropres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_diropres *resp)
+nfssvc_encode_diropres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_diropres *resp = rqstp->rq_resp;
+
 	p = encode_fh(p, &resp->fh);
 	p = encode_fattr(rqstp, p, &resp->fh, &resp->stat);
 	return xdr_ressize_check(rqstp, p);
 }
 
 int
-nfssvc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_readlinkres *resp)
+nfssvc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_readlinkres *resp = rqstp->rq_resp;
+
 	*p++ = htonl(resp->len);
 	xdr_ressize_check(rqstp, p);
 	rqstp->rq_res.page_len = resp->len;
@@ -461,9 +464,10 @@ nfssvc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_encode_readres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_readres *resp)
+nfssvc_encode_readres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_readres *resp = rqstp->rq_resp;
+
 	p = encode_fattr(rqstp, p, &resp->fh, &resp->stat);
 	*p++ = htonl(resp->count);
 	xdr_ressize_check(rqstp, p);
@@ -480,9 +484,10 @@ nfssvc_encode_readres(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_readdirres *resp)
+nfssvc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_readdirres *resp = rqstp->rq_resp;
+
 	xdr_ressize_check(rqstp, p);
 	p = resp->buffer;
 	*p++ = 0;			/* no more entries */
@@ -493,9 +498,9 @@ nfssvc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_encode_statfsres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_statfsres *resp)
+nfssvc_encode_statfsres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_statfsres *resp = rqstp->rq_resp;
 	struct kstatfs	*stat = &resp->stats;
 
 	*p++ = htonl(NFSSVC_MAXBLKSIZE_V2);	/* max transfer size */
diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h
index 8eeb752cf6f8..457ce45e5084 100644
--- a/fs/nfsd/xdr.h
+++ b/fs/nfsd/xdr.h
@@ -143,13 +143,13 @@ int nfssvc_decode_readlinkargs(struct svc_rqst *, __be32 *);
 int nfssvc_decode_linkargs(struct svc_rqst *, __be32 *);
 int nfssvc_decode_symlinkargs(struct svc_rqst *, __be32 *);
 int nfssvc_decode_readdirargs(struct svc_rqst *, __be32 *);
-int nfssvc_encode_void(struct svc_rqst *, __be32 *, void *);
-int nfssvc_encode_attrstat(struct svc_rqst *, __be32 *, struct nfsd_attrstat *);
-int nfssvc_encode_diropres(struct svc_rqst *, __be32 *, struct nfsd_diropres *);
-int nfssvc_encode_readlinkres(struct svc_rqst *, __be32 *, struct nfsd_readlinkres *);
-int nfssvc_encode_readres(struct svc_rqst *, __be32 *, struct nfsd_readres *);
-int nfssvc_encode_statfsres(struct svc_rqst *, __be32 *, struct nfsd_statfsres *);
-int nfssvc_encode_readdirres(struct svc_rqst *, __be32 *, struct nfsd_readdirres *);
+int nfssvc_encode_void(struct svc_rqst *, __be32 *);
+int nfssvc_encode_attrstat(struct svc_rqst *, __be32 *);
+int nfssvc_encode_diropres(struct svc_rqst *, __be32 *);
+int nfssvc_encode_readlinkres(struct svc_rqst *, __be32 *);
+int nfssvc_encode_readres(struct svc_rqst *, __be32 *);
+int nfssvc_encode_statfsres(struct svc_rqst *, __be32 *);
+int nfssvc_encode_readdirres(struct svc_rqst *, __be32 *);
 
 int nfssvc_encode_entry(void *, const char *name,
 			int namlen, loff_t offset, u64 ino, unsigned int);
diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h
index f79be4c42e4a..80d7da620e91 100644
--- a/fs/nfsd/xdr3.h
+++ b/fs/nfsd/xdr3.h
@@ -285,35 +285,22 @@ int nfs3svc_decode_symlinkargs(struct svc_rqst *, __be32 *);
 int nfs3svc_decode_readdirargs(struct svc_rqst *, __be32 *);
 int nfs3svc_decode_readdirplusargs(struct svc_rqst *, __be32 *);
 int nfs3svc_decode_commitargs(struct svc_rqst *, __be32 *);
-int nfs3svc_encode_voidres(struct svc_rqst *, __be32 *, void *);
-int nfs3svc_encode_attrstat(struct svc_rqst *, __be32 *,
-				struct nfsd3_attrstat *);
-int nfs3svc_encode_wccstat(struct svc_rqst *, __be32 *,
-				struct nfsd3_attrstat *);
-int nfs3svc_encode_diropres(struct svc_rqst *, __be32 *,
-				struct nfsd3_diropres *);
-int nfs3svc_encode_accessres(struct svc_rqst *, __be32 *,
-				struct nfsd3_accessres *);
-int nfs3svc_encode_readlinkres(struct svc_rqst *, __be32 *,
-				struct nfsd3_readlinkres *);
-int nfs3svc_encode_readres(struct svc_rqst *, __be32 *, struct nfsd3_readres *);
-int nfs3svc_encode_writeres(struct svc_rqst *, __be32 *, struct nfsd3_writeres *);
-int nfs3svc_encode_createres(struct svc_rqst *, __be32 *,
-				struct nfsd3_diropres *);
-int nfs3svc_encode_renameres(struct svc_rqst *, __be32 *,
-				struct nfsd3_renameres *);
-int nfs3svc_encode_linkres(struct svc_rqst *, __be32 *,
-				struct nfsd3_linkres *);
-int nfs3svc_encode_readdirres(struct svc_rqst *, __be32 *,
-				struct nfsd3_readdirres *);
-int nfs3svc_encode_fsstatres(struct svc_rqst *, __be32 *,
-				struct nfsd3_fsstatres *);
-int nfs3svc_encode_fsinfores(struct svc_rqst *, __be32 *,
-				struct nfsd3_fsinfores *);
-int nfs3svc_encode_pathconfres(struct svc_rqst *, __be32 *,
-				struct nfsd3_pathconfres *);
-int nfs3svc_encode_commitres(struct svc_rqst *, __be32 *,
-				struct nfsd3_commitres *);
+int nfs3svc_encode_voidres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_attrstat(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_wccstat(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_diropres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_accessres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_readlinkres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_readres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_writeres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_createres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_renameres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_linkres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_readdirres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_fsstatres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_fsinfores(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_pathconfres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_commitres(struct svc_rqst *, __be32 *);
 
 void nfs3svc_release_fhandle(struct svc_rqst *);
 void nfs3svc_release_fhandle2(struct svc_rqst *);
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 2a53c1233884..eb7f9239304f 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -682,10 +682,9 @@ set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp)
 
 
 bool nfsd4_mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp);
-int nfs4svc_encode_voidres(struct svc_rqst *, __be32 *, void *);
+int nfs4svc_encode_voidres(struct svc_rqst *, __be32 *);
 int nfs4svc_decode_compoundargs(struct svc_rqst *, __be32 *);
-int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *,
-		struct nfsd4_compoundres *);
+int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *);
 __be32 nfsd4_check_resp_size(struct nfsd4_compoundres *, u32);
 void nfsd4_encode_operation(struct nfsd4_compoundres *, struct nfsd4_op *);
 void nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op);
diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h
index 0416600844ce..7acbecc21a40 100644
--- a/include/linux/lockd/xdr.h
+++ b/include/linux/lockd/xdr.h
@@ -96,16 +96,16 @@ struct nlm_reboot {
 #define NLMSVC_XDRSIZE		sizeof(struct nlm_args)
 
 int	nlmsvc_decode_testargs(struct svc_rqst *, __be32 *);
-int	nlmsvc_encode_testres(struct svc_rqst *, __be32 *, struct nlm_res *);
+int	nlmsvc_encode_testres(struct svc_rqst *, __be32 *);
 int	nlmsvc_decode_lockargs(struct svc_rqst *, __be32 *);
 int	nlmsvc_decode_cancargs(struct svc_rqst *, __be32 *);
 int	nlmsvc_decode_unlockargs(struct svc_rqst *, __be32 *);
-int	nlmsvc_encode_res(struct svc_rqst *, __be32 *, struct nlm_res *);
+int	nlmsvc_encode_res(struct svc_rqst *, __be32 *);
 int	nlmsvc_decode_res(struct svc_rqst *, __be32 *);
-int	nlmsvc_encode_void(struct svc_rqst *, __be32 *, void *);
+int	nlmsvc_encode_void(struct svc_rqst *, __be32 *);
 int	nlmsvc_decode_void(struct svc_rqst *, __be32 *);
 int	nlmsvc_decode_shareargs(struct svc_rqst *, __be32 *);
-int	nlmsvc_encode_shareres(struct svc_rqst *, __be32 *, struct nlm_res *);
+int	nlmsvc_encode_shareres(struct svc_rqst *, __be32 *);
 int	nlmsvc_decode_notify(struct svc_rqst *, __be32 *);
 int	nlmsvc_decode_reboot(struct svc_rqst *, __be32 *);
 /*
diff --git a/include/linux/lockd/xdr4.h b/include/linux/lockd/xdr4.h
index 951bbe31fdb8..bf1645609225 100644
--- a/include/linux/lockd/xdr4.h
+++ b/include/linux/lockd/xdr4.h
@@ -24,16 +24,16 @@
 
 
 int	nlm4svc_decode_testargs(struct svc_rqst *, __be32 *);
-int	nlm4svc_encode_testres(struct svc_rqst *, __be32 *, struct nlm_res *);
+int	nlm4svc_encode_testres(struct svc_rqst *, __be32 *);
 int	nlm4svc_decode_lockargs(struct svc_rqst *, __be32 *);
 int	nlm4svc_decode_cancargs(struct svc_rqst *, __be32 *);
 int	nlm4svc_decode_unlockargs(struct svc_rqst *, __be32 *);
-int	nlm4svc_encode_res(struct svc_rqst *, __be32 *, struct nlm_res *);
+int	nlm4svc_encode_res(struct svc_rqst *, __be32 *);
 int	nlm4svc_decode_res(struct svc_rqst *, __be32 *);
-int	nlm4svc_encode_void(struct svc_rqst *, __be32 *, void *);
+int	nlm4svc_encode_void(struct svc_rqst *, __be32 *);
 int	nlm4svc_decode_void(struct svc_rqst *, __be32 *);
 int	nlm4svc_decode_shareargs(struct svc_rqst *, __be32 *);
-int	nlm4svc_encode_shareres(struct svc_rqst *, __be32 *, struct nlm_res *);
+int	nlm4svc_encode_shareres(struct svc_rqst *, __be32 *);
 int	nlm4svc_decode_notify(struct svc_rqst *, __be32 *);
 int	nlm4svc_decode_reboot(struct svc_rqst *, __be32 *);
 /*
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index d8703a5ab81e..bd9e313c444a 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -424,7 +424,8 @@ struct svc_procedure {
 	__be32			(*pc_func)(struct svc_rqst *);
 	/* XDR decode args: */
 	int			(*pc_decode)(struct svc_rqst *, __be32 *data);
-	kxdrproc_t		pc_encode;	/* XDR encode result */
+	/* XDR encode result: */
+	int			(*pc_encode)(struct svc_rqst *, __be32 *data);
 	/* XDR free result: */
 	void			(*pc_release)(struct svc_rqst *);
 	unsigned int		pc_argsize;	/* argument struct size */
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 18024c1b9b7b..aa643a29fdc6 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1154,7 +1154,6 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 	struct svc_version	*versp = NULL;	/* compiler food */
 	struct svc_procedure	*procp = NULL;
 	struct svc_serv		*serv = rqstp->rq_server;
-	kxdrproc_t		xdr;
 	__be32			*statp;
 	u32			prog, vers, proc;
 	__be32			auth_stat, rpc_stat;
@@ -1298,9 +1297,8 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 				procp->pc_release(rqstp);
 			goto err_bad_auth;
 		}
-		if (*statp == rpc_success &&
-		    (xdr = procp->pc_encode) &&
-		    !xdr(rqstp, resv->iov_base+resv->iov_len, rqstp->rq_resp)) {
+		if (*statp == rpc_success && procp->pc_encode &&
+		    !procp->pc_encode(rqstp, resv->iov_base + resv->iov_len)) {
 			dprintk("svc: failed to encode reply\n");
 			/* serv->sv_stats->rpcsystemerr++; */
 			*statp = rpc_system_err;
-- 
cgit v1.2.3


From 408b3d46ae06e1d219f31cbe629789a5e5c862aa Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 8 May 2017 19:56:10 +0200
Subject: sunrpc: remove kxdrproc_t

Remove the now unused typedef.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/sunrpc/xdr.h | 7 -------
 1 file changed, 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index ed0fbf0d8d0f..261b48a2701d 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -34,13 +34,6 @@ struct xdr_netobj {
 	u8 *			data;
 };
 
-/*
- * This is the legacy generic XDR function. rqstp is either a rpc_rqst
- * (client side) or svc_rqst pointer (server side).
- * Encode functions always assume there's enough room in the buffer.
- */
-typedef int	(*kxdrproc_t)(void *rqstp, __be32 *data, void *obj);
-
 /*
  * Basic structure for transmission/reception of a client XDR message.
  * Features a header (for a linear buffer containing RPC headers
-- 
cgit v1.2.3


From 0becc1181cdba562730be4d4b8a5fcb4368ef527 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 8 May 2017 23:40:27 +0200
Subject: sunrpc: move pc_count out of struct svc_procinfo

pc_count is the only writeable memeber of struct svc_procinfo, which is
a good candidate to be const-ified as it contains function pointers.

This patch moves it into out out struct svc_procinfo, and into a
separate writable array that is pointed to by struct svc_version.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/lockd/svc.c             |  6 ++++++
 fs/nfs/callback_xdr.c      |  4 ++++
 fs/nfsd/nfs2acl.c          |  2 ++
 fs/nfsd/nfs3acl.c          |  2 ++
 fs/nfsd/nfs3proc.c         |  2 ++
 fs/nfsd/nfs4proc.c         |  2 ++
 fs/nfsd/nfsproc.c          |  2 ++
 include/linux/sunrpc/svc.h |  2 +-
 net/sunrpc/stats.c         | 11 ++++++-----
 net/sunrpc/svc.c           |  2 +-
 10 files changed, 28 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index 5d481e8a1b5d..cc6abe6280bc 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -739,23 +739,29 @@ module_exit(exit_nlm);
 /*
  * Define NLM program and procedures
  */
+static unsigned int nlmsvc_version1_count[17];
 static struct svc_version	nlmsvc_version1 = {
 		.vs_vers	= 1,
 		.vs_nproc	= 17,
 		.vs_proc	= nlmsvc_procedures,
+		.vs_count	= nlmsvc_version1_count,
 		.vs_xdrsize	= NLMSVC_XDRSIZE,
 };
+static unsigned int nlmsvc_version3_count[24];
 static struct svc_version	nlmsvc_version3 = {
 		.vs_vers	= 3,
 		.vs_nproc	= 24,
 		.vs_proc	= nlmsvc_procedures,
+		.vs_count	= nlmsvc_version3_count,
 		.vs_xdrsize	= NLMSVC_XDRSIZE,
 };
 #ifdef CONFIG_LOCKD_V4
+static unsigned int nlmsvc_version4_count[24];
 static struct svc_version	nlmsvc_version4 = {
 		.vs_vers	= 4,
 		.vs_nproc	= 24,
 		.vs_proc	= nlmsvc_procedures4,
+		.vs_count	= nlmsvc_version4_count,
 		.vs_xdrsize	= NLMSVC_XDRSIZE,
 };
 #endif
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index acf75dc63e14..ecd46b8c0985 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -1011,20 +1011,24 @@ static struct svc_procedure nfs4_callback_procedures1[] = {
 	}
 };
 
+static unsigned int nfs4_callback_count1[ARRAY_SIZE(nfs4_callback_procedures1)];
 struct svc_version nfs4_callback_version1 = {
 	.vs_vers = 1,
 	.vs_nproc = ARRAY_SIZE(nfs4_callback_procedures1),
 	.vs_proc = nfs4_callback_procedures1,
+	.vs_count = nfs4_callback_count1,
 	.vs_xdrsize = NFS4_CALLBACK_XDRSIZE,
 	.vs_dispatch = NULL,
 	.vs_hidden = true,
 	.vs_need_cong_ctrl = true,
 };
 
+static unsigned int nfs4_callback_count4[ARRAY_SIZE(nfs4_callback_procedures1)];
 struct svc_version nfs4_callback_version4 = {
 	.vs_vers = 4,
 	.vs_nproc = ARRAY_SIZE(nfs4_callback_procedures1),
 	.vs_proc = nfs4_callback_procedures1,
+	.vs_count = nfs4_callback_count4,
 	.vs_xdrsize = NFS4_CALLBACK_XDRSIZE,
 	.vs_dispatch = NULL,
 	.vs_hidden = true,
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index fc6b179c8fff..026edfe73fd5 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -378,10 +378,12 @@ static struct svc_procedure		nfsd_acl_procedures2[] = {
   PROC(access,	access,		access,		access,   RC_NOCACHE, ST+AT+1),
 };
 
+static unsigned int nfsd_acl_count2[ARRAY_SIZE(nfsd_acl_procedures2)];
 struct svc_version	nfsd_acl_version2 = {
 		.vs_vers	= 2,
 		.vs_nproc	= 5,
 		.vs_proc	= nfsd_acl_procedures2,
+		.vs_count	= nfsd_acl_count2,
 		.vs_dispatch	= nfsd_dispatch,
 		.vs_xdrsize	= NFS3_SVC_XDRSIZE,
 };
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index 9437b758cbfd..73c0970ccefb 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -263,10 +263,12 @@ static struct svc_procedure		nfsd_acl_procedures3[] = {
   PROC(setacl,	setacl,		setacl,		fhandle,  RC_NOCACHE, ST+pAT),
 };
 
+static unsigned int nfsd_acl_count3[ARRAY_SIZE(nfsd_acl_procedures3)];
 struct svc_version	nfsd_acl_version3 = {
 		.vs_vers	= 3,
 		.vs_nproc	= 3,
 		.vs_proc	= nfsd_acl_procedures3,
+		.vs_count	= nfsd_acl_count3,
 		.vs_dispatch	= nfsd_dispatch,
 		.vs_xdrsize	= NFS3_SVC_XDRSIZE,
 };
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 17c90c41a3a6..b5823802e278 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -890,10 +890,12 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 };
 
+static unsigned int nfsd_count3[ARRAY_SIZE(nfsd_procedures3)];
 struct svc_version	nfsd_version3 = {
 		.vs_vers	= 3,
 		.vs_nproc	= 22,
 		.vs_proc	= nfsd_procedures3,
+		.vs_count	= nfsd_count3,
 		.vs_dispatch	= nfsd_dispatch,
 		.vs_xdrsize	= NFS3_SVC_XDRSIZE,
 };
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 403c1d14d99a..4de6a9950722 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -2553,10 +2553,12 @@ static struct svc_procedure		nfsd_procedures4[2] = {
 	},
 };
 
+static unsigned int nfsd_count3[ARRAY_SIZE(nfsd_procedures4)];
 struct svc_version	nfsd_version4 = {
 	.vs_vers		= 4,
 	.vs_nproc		= 2,
 	.vs_proc		= nfsd_procedures4,
+	.vs_count		= nfsd_count3,
 	.vs_dispatch		= nfsd_dispatch,
 	.vs_xdrsize		= NFS4_SVC_XDRSIZE,
 	.vs_rpcb_optnl		= true,
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index 0ef88d0e67d9..44b157553733 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -743,10 +743,12 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 };
 
 
+static unsigned int nfsd_count2[ARRAY_SIZE(nfsd_procedures2)];
 struct svc_version	nfsd_version2 = {
 		.vs_vers	= 2,
 		.vs_nproc	= 18,
 		.vs_proc	= nfsd_procedures2,
+		.vs_count	= nfsd_count2,
 		.vs_dispatch	= nfsd_dispatch,
 		.vs_xdrsize	= NFS2_SVC_XDRSIZE,
 };
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index bd9e313c444a..bcd114f038ef 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -398,6 +398,7 @@ struct svc_version {
 	u32			vs_vers;	/* version number */
 	u32			vs_nproc;	/* number of procedures */
 	struct svc_procedure *	vs_proc;	/* per-procedure info */
+	unsigned int		*vs_count;	/* call counts */
 	u32			vs_xdrsize;	/* xdrsize needed for this version */
 
 	/* Don't register with rpcbind */
@@ -430,7 +431,6 @@ struct svc_procedure {
 	void			(*pc_release)(struct svc_rqst *);
 	unsigned int		pc_argsize;	/* argument struct size */
 	unsigned int		pc_ressize;	/* result struct size */
-	unsigned int		pc_count;	/* call count */
 	unsigned int		pc_cachetype;	/* cache info (NFS) */
 	unsigned int		pc_xdrressize;	/* maximum size of XDR reply */
 };
diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c
index 8b6c35ae1d57..1e671333c3d5 100644
--- a/net/sunrpc/stats.c
+++ b/net/sunrpc/stats.c
@@ -77,9 +77,9 @@ static const struct file_operations rpc_proc_fops = {
 /*
  * Get RPC server stats
  */
-void svc_seq_show(struct seq_file *seq, const struct svc_stat *statp) {
+void svc_seq_show(struct seq_file *seq, const struct svc_stat *statp)
+{
 	const struct svc_program *prog = statp->program;
-	const struct svc_procedure *proc;
 	const struct svc_version *vers;
 	unsigned int i, j;
 
@@ -98,11 +98,12 @@ void svc_seq_show(struct seq_file *seq, const struct svc_stat *statp) {
 			statp->rpcbadclnt);
 
 	for (i = 0; i < prog->pg_nvers; i++) {
-		if (!(vers = prog->pg_vers[i]) || !(proc = vers->vs_proc))
+		vers = prog->pg_vers[i];
+		if (!vers)
 			continue;
 		seq_printf(seq, "proc%d %u", i, vers->vs_nproc);
-		for (j = 0; j < vers->vs_nproc; j++, proc++)
-			seq_printf(seq, " %u", proc->pc_count);
+		for (j = 0; j < vers->vs_nproc; j++)
+			seq_printf(seq, " %u", vers->vs_count[j]);
 		seq_putc(seq, '\n');
 	}
 }
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index aa643a29fdc6..6452592194ac 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1261,7 +1261,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 	svc_putnl(resv, RPC_SUCCESS);
 
 	/* Bump per-procedure stats counter */
-	procp->pc_count++;
+	versp->vs_count[proc]++;
 
 	/* Initialize storage for argp and resp */
 	memset(rqstp->rq_argp, 0, procp->pc_argsize);
-- 
cgit v1.2.3


From b9c744c19c441f306239ac3e60a2a95b40d698f8 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 12 May 2017 16:11:49 +0200
Subject: sunrpc: mark all struct svc_procinfo instances as const

struct svc_procinfo contains function pointers, and marking it as
constant avoids it being able to be used as an attach vector for
code injections.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/lockd/svc4proc.c         | 2 +-
 fs/lockd/svcproc.c          | 2 +-
 fs/nfs/callback_xdr.c       | 2 +-
 fs/nfsd/nfs2acl.c           | 2 +-
 fs/nfsd/nfs3acl.c           | 2 +-
 fs/nfsd/nfs3proc.c          | 2 +-
 fs/nfsd/nfs4proc.c          | 2 +-
 fs/nfsd/nfsproc.c           | 2 +-
 fs/nfsd/nfssvc.c            | 4 ++--
 include/linux/lockd/lockd.h | 4 ++--
 include/linux/sunrpc/svc.h  | 4 ++--
 net/sunrpc/svc.c            | 2 +-
 12 files changed, 15 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index fed016155791..82925f17ec45 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -507,7 +507,7 @@ struct nlm_void			{ int dummy; };
 #define	No	(1+1024/4)				/* netobj */
 #define	St	1					/* status */
 #define	Rg	4					/* range (offset + length) */
-struct svc_procedure		nlmsvc_procedures4[] = {
+const struct svc_procedure nlmsvc_procedures4[] = {
   PROC(null,		void,		void,		void,	void, 1),
   PROC(test,		testargs,	testres,	args,	res, Ck+St+2+No+Rg),
   PROC(lock,		lockargs,	res,		args,	res, Ck+St),
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index 14648b051eba..07915162581d 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -551,7 +551,7 @@ struct nlm_void			{ int dummy; };
 #define	No	(1+1024/4)			/* Net Obj */
 #define	Rg	2				/* range - offset + size */
 
-struct svc_procedure		nlmsvc_procedures[] = {
+const struct svc_procedure nlmsvc_procedures[] = {
   PROC(null,		void,		void,		void,	void, 1),
   PROC(test,		testargs,	testres,	args,	res, Ck+St+2+No+Rg),
   PROC(lock,		lockargs,	res,		args,	res, Ck+St),
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index ecd46b8c0985..ae249f27297f 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -995,7 +995,7 @@ static struct callback_op callback_ops[] = {
 /*
  * Define NFS4 callback procedures
  */
-static struct svc_procedure nfs4_callback_procedures1[] = {
+static const struct svc_procedure nfs4_callback_procedures1[] = {
 	[CB_NULL] = {
 		.pc_func = nfs4_callback_null,
 		.pc_decode = nfs4_decode_void,
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index 026edfe73fd5..c3f6b8a6b659 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -370,7 +370,7 @@ struct nfsd3_voidargs { int dummy; };
 #define pAT (1+AT)	/* post attributes - conditional */
 #define ACL (1+NFS_ACL_MAX_ENTRIES*3)  /* Access Control List */
 
-static struct svc_procedure		nfsd_acl_procedures2[] = {
+static const struct svc_procedure nfsd_acl_procedures2[] = {
   PROC(null,	void,		void,		void,	  RC_NOCACHE, ST),
   PROC(getacl,	getacl,		getacl,		getacl,	  RC_NOCACHE, ST+1+2*(1+ACL)),
   PROC(setacl,	setacl,		attrstat,	attrstat, RC_NOCACHE, ST+AT),
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index 73c0970ccefb..1a482ac9d4e9 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -257,7 +257,7 @@ struct nfsd3_voidargs { int dummy; };
 #define pAT (1+AT)	/* post attributes - conditional */
 #define ACL (1+NFS_ACL_MAX_ENTRIES*3)  /* Access Control List */
 
-static struct svc_procedure		nfsd_acl_procedures3[] = {
+static const struct svc_procedure nfsd_acl_procedures3[] = {
   PROC(null,	void,		void,		void,	  RC_NOCACHE, ST),
   PROC(getacl,	getacl,		getacl,		getacl,	  RC_NOCACHE, ST+1+2*(1+ACL)),
   PROC(setacl,	setacl,		setacl,		fhandle,  RC_NOCACHE, ST+pAT),
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index b5823802e278..96e0e6a2af51 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -674,7 +674,7 @@ struct nfsd3_voidargs { int dummy; };
 #define pAT (1+AT)	/* post attributes - conditional */
 #define WC (7+pAT)	/* WCC attributes */
 
-static struct svc_procedure		nfsd_procedures3[22] = {
+static const struct svc_procedure nfsd_procedures3[22] = {
 	[NFS3PROC_NULL] = {
 		.pc_func = nfsd3_proc_null,
 		.pc_encode = nfs3svc_encode_voidres,
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 4de6a9950722..68aa175b1cb3 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -2532,7 +2532,7 @@ static const char *nfsd4_op_name(unsigned opnum)
 #define nfsd4_voidres			nfsd4_voidargs
 struct nfsd4_voidargs { int dummy; };
 
-static struct svc_procedure		nfsd_procedures4[2] = {
+static const struct svc_procedure nfsd_procedures4[2] = {
 	[NFSPROC4_NULL] = {
 		.pc_func = nfsd4_proc_null,
 		.pc_encode = nfs4svc_encode_voidres,
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index 44b157553733..a68b686fda12 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -573,7 +573,7 @@ struct nfsd_void { int dummy; };
 #define FH 8		/* filehandle */
 #define	AT 18		/* attributes */
 
-static struct svc_procedure		nfsd_procedures2[18] = {
+static const struct svc_procedure nfsd_procedures2[18] = {
 	[NFSPROC_NULL] = {
 		.pc_func = nfsd_proc_null,
 		.pc_decode = nfssvc_decode_void,
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 555233664124..379b310c445d 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -756,7 +756,7 @@ static __be32 map_new_errors(u32 vers, __be32 nfserr)
  * problem, we enforce these assumptions here:
  */
 static bool nfs_request_too_big(struct svc_rqst *rqstp,
-				struct svc_procedure *proc)
+				const struct svc_procedure *proc)
 {
 	/*
 	 * The ACL code has more careful bounds-checking and is not
@@ -781,7 +781,7 @@ static bool nfs_request_too_big(struct svc_rqst *rqstp,
 int
 nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 {
-	struct svc_procedure	*proc;
+	const struct svc_procedure *proc;
 	__be32			nfserr;
 	__be32			*nfserrp;
 
diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h
index 41f7b6a04d69..3eca67728366 100644
--- a/include/linux/lockd/lockd.h
+++ b/include/linux/lockd/lockd.h
@@ -192,9 +192,9 @@ struct nlm_block {
  * Global variables
  */
 extern const struct rpc_program	nlm_program;
-extern struct svc_procedure	nlmsvc_procedures[];
+extern const struct svc_procedure nlmsvc_procedures[];
 #ifdef CONFIG_LOCKD_V4
-extern struct svc_procedure	nlmsvc_procedures4[];
+extern const struct svc_procedure nlmsvc_procedures4[];
 #endif
 extern int			nlmsvc_grace_period;
 extern unsigned long		nlmsvc_timeout;
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index bcd114f038ef..992ea3419795 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -237,7 +237,7 @@ struct svc_rqst {
 
 	struct svc_serv *	rq_server;	/* RPC service definition */
 	struct svc_pool *	rq_pool;	/* thread pool */
-	struct svc_procedure *	rq_procinfo;	/* procedure info */
+	const struct svc_procedure *rq_procinfo;/* procedure info */
 	struct auth_ops *	rq_authop;	/* authentication flavour */
 	struct svc_cred		rq_cred;	/* auth info */
 	void *			rq_xprt_ctxt;	/* transport specific context ptr */
@@ -397,7 +397,7 @@ struct svc_program {
 struct svc_version {
 	u32			vs_vers;	/* version number */
 	u32			vs_nproc;	/* number of procedures */
-	struct svc_procedure *	vs_proc;	/* per-procedure info */
+	const struct svc_procedure *vs_proc;	/* per-procedure info */
 	unsigned int		*vs_count;	/* call counts */
 	u32			vs_xdrsize;	/* xdrsize needed for this version */
 
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 6452592194ac..049963d676a7 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1152,7 +1152,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 {
 	struct svc_program	*progp;
 	struct svc_version	*versp = NULL;	/* compiler food */
-	struct svc_procedure	*procp = NULL;
+	const struct svc_procedure *procp = NULL;
 	struct svc_serv		*serv = rqstp->rq_server;
 	__be32			*statp;
 	u32			prog, vers, proc;
-- 
cgit v1.2.3


From aa8217d5dcb1db594d816794ef6ab434ebf3e127 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 12 May 2017 16:21:37 +0200
Subject: sunrpc: mark all struct svc_version instances as const

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 fs/lockd/svc.c             | 38 +++++++++++++++++++-------------------
 fs/nfs/callback.c          |  2 +-
 fs/nfs/callback_xdr.c      |  4 ++--
 fs/nfs/internal.h          |  4 ++--
 fs/nfs/nfs4_fs.h           |  4 ++--
 fs/nfsd/nfs2acl.c          | 14 +++++++-------
 fs/nfsd/nfs3acl.c          | 14 +++++++-------
 fs/nfsd/nfs3proc.c         | 14 +++++++-------
 fs/nfsd/nfs4proc.c         |  2 +-
 fs/nfsd/nfsd.h             |  6 +++---
 fs/nfsd/nfsproc.c          | 14 +++++++-------
 fs/nfsd/nfssvc.c           |  8 ++++----
 include/linux/sunrpc/svc.h |  2 +-
 net/sunrpc/svc.c           |  4 ++--
 14 files changed, 65 insertions(+), 65 deletions(-)

(limited to 'include')

diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index cc6abe6280bc..726b6cecf430 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -740,32 +740,32 @@ module_exit(exit_nlm);
  * Define NLM program and procedures
  */
 static unsigned int nlmsvc_version1_count[17];
-static struct svc_version	nlmsvc_version1 = {
-		.vs_vers	= 1,
-		.vs_nproc	= 17,
-		.vs_proc	= nlmsvc_procedures,
-		.vs_count	= nlmsvc_version1_count,
-		.vs_xdrsize	= NLMSVC_XDRSIZE,
+static const struct svc_version	nlmsvc_version1 = {
+	.vs_vers	= 1,
+	.vs_nproc	= 17,
+	.vs_proc	= nlmsvc_procedures,
+	.vs_count	= nlmsvc_version1_count,
+	.vs_xdrsize	= NLMSVC_XDRSIZE,
 };
 static unsigned int nlmsvc_version3_count[24];
-static struct svc_version	nlmsvc_version3 = {
-		.vs_vers	= 3,
-		.vs_nproc	= 24,
-		.vs_proc	= nlmsvc_procedures,
-		.vs_count	= nlmsvc_version3_count,
-		.vs_xdrsize	= NLMSVC_XDRSIZE,
+static const struct svc_version	nlmsvc_version3 = {
+	.vs_vers	= 3,
+	.vs_nproc	= 24,
+	.vs_proc	= nlmsvc_procedures,
+	.vs_count	= nlmsvc_version3_count,
+	.vs_xdrsize	= NLMSVC_XDRSIZE,
 };
 #ifdef CONFIG_LOCKD_V4
 static unsigned int nlmsvc_version4_count[24];
-static struct svc_version	nlmsvc_version4 = {
-		.vs_vers	= 4,
-		.vs_nproc	= 24,
-		.vs_proc	= nlmsvc_procedures4,
-		.vs_count	= nlmsvc_version4_count,
-		.vs_xdrsize	= NLMSVC_XDRSIZE,
+static const struct svc_version	nlmsvc_version4 = {
+	.vs_vers	= 4,
+	.vs_nproc	= 24,
+	.vs_proc	= nlmsvc_procedures4,
+	.vs_count	= nlmsvc_version4_count,
+	.vs_xdrsize	= NLMSVC_XDRSIZE,
 };
 #endif
-static struct svc_version *	nlmsvc_version[] = {
+static const struct svc_version *nlmsvc_version[] = {
 	[1] = &nlmsvc_version1,
 	[3] = &nlmsvc_version3,
 #ifdef CONFIG_LOCKD_V4
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index 73a1f928226c..34323877ec13 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -439,7 +439,7 @@ static int nfs_callback_authenticate(struct svc_rqst *rqstp)
 /*
  * Define NFS4 callback program
  */
-static struct svc_version *nfs4_callback_version[] = {
+static const struct svc_version *nfs4_callback_version[] = {
 	[1] = &nfs4_callback_version1,
 	[4] = &nfs4_callback_version4,
 };
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index ae249f27297f..01a430e51daa 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -1012,7 +1012,7 @@ static const struct svc_procedure nfs4_callback_procedures1[] = {
 };
 
 static unsigned int nfs4_callback_count1[ARRAY_SIZE(nfs4_callback_procedures1)];
-struct svc_version nfs4_callback_version1 = {
+const struct svc_version nfs4_callback_version1 = {
 	.vs_vers = 1,
 	.vs_nproc = ARRAY_SIZE(nfs4_callback_procedures1),
 	.vs_proc = nfs4_callback_procedures1,
@@ -1024,7 +1024,7 @@ struct svc_version nfs4_callback_version1 = {
 };
 
 static unsigned int nfs4_callback_count4[ARRAY_SIZE(nfs4_callback_procedures1)];
-struct svc_version nfs4_callback_version4 = {
+const struct svc_version nfs4_callback_version4 = {
 	.vs_vers = 4,
 	.vs_nproc = ARRAY_SIZE(nfs4_callback_procedures1),
 	.vs_proc = nfs4_callback_procedures1,
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index dc2a29a7d48b..1c0ce9c15e94 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -225,8 +225,8 @@ static inline void nfs_fs_proc_exit(void)
 #endif
 
 /* callback_xdr.c */
-extern struct svc_version nfs4_callback_version1;
-extern struct svc_version nfs4_callback_version4;
+extern const struct svc_version nfs4_callback_version1;
+extern const struct svc_version nfs4_callback_version4;
 
 struct nfs_pageio_descriptor;
 /* pagelist.c */
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 9b0cf3872722..40bd05f05e74 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -498,8 +498,8 @@ extern const struct rpc_procinfo nfs4_procedures[];
 struct nfs4_mount_data;
 
 /* callback_xdr.c */
-extern struct svc_version nfs4_callback_version1;
-extern struct svc_version nfs4_callback_version4;
+extern const struct svc_version nfs4_callback_version1;
+extern const struct svc_version nfs4_callback_version4;
 
 static inline void nfs4_stateid_copy(nfs4_stateid *dst, const nfs4_stateid *src)
 {
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index c3f6b8a6b659..6276ec8608b0 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -379,11 +379,11 @@ static const struct svc_procedure nfsd_acl_procedures2[] = {
 };
 
 static unsigned int nfsd_acl_count2[ARRAY_SIZE(nfsd_acl_procedures2)];
-struct svc_version	nfsd_acl_version2 = {
-		.vs_vers	= 2,
-		.vs_nproc	= 5,
-		.vs_proc	= nfsd_acl_procedures2,
-		.vs_count	= nfsd_acl_count2,
-		.vs_dispatch	= nfsd_dispatch,
-		.vs_xdrsize	= NFS3_SVC_XDRSIZE,
+const struct svc_version nfsd_acl_version2 = {
+	.vs_vers	= 2,
+	.vs_nproc	= 5,
+	.vs_proc	= nfsd_acl_procedures2,
+	.vs_count	= nfsd_acl_count2,
+	.vs_dispatch	= nfsd_dispatch,
+	.vs_xdrsize	= NFS3_SVC_XDRSIZE,
 };
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index 1a482ac9d4e9..01976529f042 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -264,12 +264,12 @@ static const struct svc_procedure nfsd_acl_procedures3[] = {
 };
 
 static unsigned int nfsd_acl_count3[ARRAY_SIZE(nfsd_acl_procedures3)];
-struct svc_version	nfsd_acl_version3 = {
-		.vs_vers	= 3,
-		.vs_nproc	= 3,
-		.vs_proc	= nfsd_acl_procedures3,
-		.vs_count	= nfsd_acl_count3,
-		.vs_dispatch	= nfsd_dispatch,
-		.vs_xdrsize	= NFS3_SVC_XDRSIZE,
+const struct svc_version nfsd_acl_version3 = {
+	.vs_vers	= 3,
+	.vs_nproc	= 3,
+	.vs_proc	= nfsd_acl_procedures3,
+	.vs_count	= nfsd_acl_count3,
+	.vs_dispatch	= nfsd_dispatch,
+	.vs_xdrsize	= NFS3_SVC_XDRSIZE,
 };
 
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 96e0e6a2af51..2cb56a0d6625 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -891,11 +891,11 @@ static const struct svc_procedure nfsd_procedures3[22] = {
 };
 
 static unsigned int nfsd_count3[ARRAY_SIZE(nfsd_procedures3)];
-struct svc_version	nfsd_version3 = {
-		.vs_vers	= 3,
-		.vs_nproc	= 22,
-		.vs_proc	= nfsd_procedures3,
-		.vs_count	= nfsd_count3,
-		.vs_dispatch	= nfsd_dispatch,
-		.vs_xdrsize	= NFS3_SVC_XDRSIZE,
+const struct svc_version nfsd_version3 = {
+	.vs_vers	= 3,
+	.vs_nproc	= 22,
+	.vs_proc	= nfsd_procedures3,
+	.vs_dispatch	= nfsd_dispatch,
+	.vs_count	= nfsd_count3,
+	.vs_xdrsize	= NFS3_SVC_XDRSIZE,
 };
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 68aa175b1cb3..3cbd065c639f 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -2554,7 +2554,7 @@ static const struct svc_procedure nfsd_procedures4[2] = {
 };
 
 static unsigned int nfsd_count3[ARRAY_SIZE(nfsd_procedures4)];
-struct svc_version	nfsd_version4 = {
+const struct svc_version nfsd_version4 = {
 	.vs_vers		= 4,
 	.vs_nproc		= 2,
 	.vs_proc		= nfsd_procedures4,
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index d96606801d47..b9c538ab7a59 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -60,7 +60,7 @@ struct readdir_cd {
 
 
 extern struct svc_program	nfsd_program;
-extern struct svc_version	nfsd_version2, nfsd_version3,
+extern const struct svc_version	nfsd_version2, nfsd_version3,
 				nfsd_version4;
 extern struct mutex		nfsd_mutex;
 extern spinlock_t		nfsd_drc_lock;
@@ -86,12 +86,12 @@ void		nfsd_destroy(struct net *net);
 
 #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
 #ifdef CONFIG_NFSD_V2_ACL
-extern struct svc_version nfsd_acl_version2;
+extern const struct svc_version nfsd_acl_version2;
 #else
 #define nfsd_acl_version2 NULL
 #endif
 #ifdef CONFIG_NFSD_V3_ACL
-extern struct svc_version nfsd_acl_version3;
+extern const struct svc_version nfsd_acl_version3;
 #else
 #define nfsd_acl_version3 NULL
 #endif
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index a68b686fda12..5076ae2b8258 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -744,13 +744,13 @@ static const struct svc_procedure nfsd_procedures2[18] = {
 
 
 static unsigned int nfsd_count2[ARRAY_SIZE(nfsd_procedures2)];
-struct svc_version	nfsd_version2 = {
-		.vs_vers	= 2,
-		.vs_nproc	= 18,
-		.vs_proc	= nfsd_procedures2,
-		.vs_count	= nfsd_count2,
-		.vs_dispatch	= nfsd_dispatch,
-		.vs_xdrsize	= NFS2_SVC_XDRSIZE,
+const struct svc_version nfsd_version2 = {
+	.vs_vers	= 2,
+	.vs_nproc	= 18,
+	.vs_proc	= nfsd_procedures2,
+	.vs_count	= nfsd_count2,
+	.vs_dispatch	= nfsd_dispatch,
+	.vs_xdrsize	= NFS2_SVC_XDRSIZE,
 };
 
 /*
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 379b310c445d..063ae7de2c12 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -68,14 +68,14 @@ unsigned long	nfsd_drc_mem_used;
 
 #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
 static struct svc_stat	nfsd_acl_svcstats;
-static struct svc_version *	nfsd_acl_version[] = {
+static const struct svc_version *nfsd_acl_version[] = {
 	[2] = &nfsd_acl_version2,
 	[3] = &nfsd_acl_version3,
 };
 
 #define NFSD_ACL_MINVERS            2
 #define NFSD_ACL_NRVERS		ARRAY_SIZE(nfsd_acl_version)
-static struct svc_version *nfsd_acl_versions[NFSD_ACL_NRVERS];
+static const struct svc_version *nfsd_acl_versions[NFSD_ACL_NRVERS];
 
 static struct svc_program	nfsd_acl_program = {
 	.pg_prog		= NFS_ACL_PROGRAM,
@@ -92,7 +92,7 @@ static struct svc_stat	nfsd_acl_svcstats = {
 };
 #endif /* defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) */
 
-static struct svc_version *	nfsd_version[] = {
+static const struct svc_version *nfsd_version[] = {
 	[2] = &nfsd_version2,
 #if defined(CONFIG_NFSD_V3)
 	[3] = &nfsd_version3,
@@ -104,7 +104,7 @@ static struct svc_version *	nfsd_version[] = {
 
 #define NFSD_MINVERS    	2
 #define NFSD_NRVERS		ARRAY_SIZE(nfsd_version)
-static struct svc_version *nfsd_versions[NFSD_NRVERS];
+static const struct svc_version *nfsd_versions[NFSD_NRVERS];
 
 struct svc_program		nfsd_program = {
 #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 992ea3419795..eec04982a7ea 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -384,7 +384,7 @@ struct svc_program {
 	unsigned int		pg_lovers;	/* lowest version */
 	unsigned int		pg_hivers;	/* highest version */
 	unsigned int		pg_nvers;	/* number of versions */
-	struct svc_version **	pg_vers;	/* version array */
+	const struct svc_version **pg_vers;	/* version array */
 	char *			pg_name;	/* service name */
 	char *			pg_class;	/* class name: services sharing authentication */
 	struct svc_stat *	pg_stats;	/* rpc statistics */
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 049963d676a7..45b4f2d2e3bd 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1008,7 +1008,7 @@ int svc_register(const struct svc_serv *serv, struct net *net,
 		 const unsigned short port)
 {
 	struct svc_program	*progp;
-	struct svc_version	*vers;
+	const struct svc_version *vers;
 	unsigned int		i;
 	int			error = 0;
 
@@ -1151,7 +1151,7 @@ static int
 svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 {
 	struct svc_program	*progp;
-	struct svc_version	*versp = NULL;	/* compiler food */
+	const struct svc_version *versp = NULL;	/* compiler food */
 	const struct svc_procedure *procp = NULL;
 	struct svc_serv		*serv = rqstp->rq_server;
 	__be32			*statp;
-- 
cgit v1.2.3


From a7a3b1e971cd806b81ecea3a234d8dae9de0add0 Mon Sep 17 00:00:00 2001
From: Benjamin Coddington <bcodding@redhat.com>
Date: Tue, 20 Jun 2017 08:33:44 -0400
Subject: NFS: convert flags to bool

NFS uses some int, and unsigned int :1, and bool as flags in structs and
args.  Assert the preference for uniformly replacing these with the bool
type.

Signed-off-by: Benjamin Coddington <bcodding@redhat.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/dir.c            | 16 ++++++++--------
 fs/nfs/internal.h       |  6 +++---
 fs/nfs/nfs2xdr.c        |  2 +-
 fs/nfs/nfs3proc.c       |  2 +-
 fs/nfs/nfs3xdr.c        |  2 +-
 fs/nfs/nfs4proc.c       | 42 +++++++++++++++++++++---------------------
 fs/nfs/nfs4xdr.c        |  2 +-
 fs/nfs/proc.c           |  2 +-
 include/linux/nfs_xdr.h | 10 +++++-----
 9 files changed, 42 insertions(+), 42 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 32ccd7754f8a..9688e9bb13dc 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -151,7 +151,7 @@ struct nfs_cache_array {
 	struct nfs_cache_array_entry array[0];
 };
 
-typedef int (*decode_dirent_t)(struct xdr_stream *, struct nfs_entry *, int);
+typedef int (*decode_dirent_t)(struct xdr_stream *, struct nfs_entry *, bool);
 typedef struct {
 	struct file	*file;
 	struct page	*page;
@@ -165,8 +165,8 @@ typedef struct {
 	unsigned long	timestamp;
 	unsigned long	gencount;
 	unsigned int	cache_entry_index;
-	unsigned int	plus:1;
-	unsigned int	eof:1;
+	bool plus;
+	bool eof;
 } nfs_readdir_descriptor_t;
 
 /*
@@ -355,7 +355,7 @@ int nfs_readdir_xdr_filler(struct page **pages, nfs_readdir_descriptor_t *desc,
 		if (error == -ENOTSUPP && desc->plus) {
 			NFS_SERVER(inode)->caps &= ~NFS_CAP_READDIRPLUS;
 			clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags);
-			desc->plus = 0;
+			desc->plus = false;
 			goto again;
 		}
 		goto error;
@@ -557,7 +557,7 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en
 
 		count++;
 
-		if (desc->plus != 0)
+		if (desc->plus)
 			nfs_prime_dcache(file_dentry(desc->file), entry);
 
 		status = nfs_readdir_add_to_array(entry, page);
@@ -860,7 +860,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 	desc->ctx = ctx;
 	desc->dir_cookie = &dir_ctx->dir_cookie;
 	desc->decode = NFS_PROTO(inode)->decode_dirent;
-	desc->plus = nfs_use_readdirplus(inode, ctx) ? 1 : 0;
+	desc->plus = nfs_use_readdirplus(inode, ctx);
 
 	if (ctx->pos == 0 || nfs_attribute_cache_expired(inode))
 		res = nfs_revalidate_mapping(inode, file->f_mapping);
@@ -885,8 +885,8 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 			clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags);
 			nfs_zap_caches(inode);
 			desc->page_index = 0;
-			desc->plus = 0;
-			desc->eof = 0;
+			desc->plus = false;
+			desc->eof = false;
 			continue;
 		}
 		if (res < 0)
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 1c0ce9c15e94..c5054edb0157 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -272,17 +272,17 @@ static inline bool nfs_match_open_context(const struct nfs_open_context *ctx1,
 /* nfs2xdr.c */
 extern const struct rpc_procinfo nfs_procedures[];
 extern int nfs2_decode_dirent(struct xdr_stream *,
-				struct nfs_entry *, int);
+				struct nfs_entry *, bool);
 
 /* nfs3xdr.c */
 extern const struct rpc_procinfo nfs3_procedures[];
 extern int nfs3_decode_dirent(struct xdr_stream *,
-				struct nfs_entry *, int);
+				struct nfs_entry *, bool);
 
 /* nfs4xdr.c */
 #if IS_ENABLED(CONFIG_NFS_V4)
 extern int nfs4_decode_dirent(struct xdr_stream *,
-				struct nfs_entry *, int);
+				struct nfs_entry *, bool);
 #endif
 #ifdef CONFIG_NFS_V4_1
 extern const u32 nfs41_maxread_overhead;
diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c
index c8a7e98c1371..fe68dabfbde6 100644
--- a/fs/nfs/nfs2xdr.c
+++ b/fs/nfs/nfs2xdr.c
@@ -939,7 +939,7 @@ static int nfs2_xdr_dec_writeres(struct rpc_rqst *req, struct xdr_stream *xdr,
  *	};
  */
 int nfs2_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
-		       int plus)
+		       bool plus)
 {
 	__be32 *p;
 	int error;
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 0c07b567118d..df4a7d3ab915 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -621,7 +621,7 @@ out:
  */
 static int
 nfs3_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
-		  u64 cookie, struct page **pages, unsigned int count, int plus)
+		  u64 cookie, struct page **pages, unsigned int count, bool plus)
 {
 	struct inode		*dir = d_inode(dentry);
 	__be32			*verf = NFS_I(dir)->cookieverf;
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index 670eddb3ae36..e82c9e553224 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -1991,7 +1991,7 @@ out_status:
  *	};
  */
 int nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
-		       int plus)
+		       bool plus)
 {
 	struct nfs_entry old = *entry;
 	__be32 *p;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 735b3068a2d1..e678fa8f6979 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1037,11 +1037,11 @@ struct nfs4_opendata {
 	struct nfs4_state *state;
 	struct iattr attrs;
 	unsigned long timestamp;
-	unsigned int rpc_done : 1;
-	unsigned int file_created : 1;
-	unsigned int is_recover : 1;
+	bool rpc_done;
+	bool file_created;
+	bool is_recover;
+	bool cancelled;
 	int rpc_status;
-	int cancelled;
 };
 
 static bool nfs4_clear_cap_atomic_open_v1(struct nfs_server *server,
@@ -1965,7 +1965,7 @@ static void nfs4_open_confirm_done(struct rpc_task *task, void *calldata)
 		nfs4_stateid_copy(&data->o_res.stateid, &data->c_res.stateid);
 		nfs_confirm_seqid(&data->owner->so_seqid, 0);
 		renew_lease(data->o_res.server, data->timestamp);
-		data->rpc_done = 1;
+		data->rpc_done = true;
 	}
 }
 
@@ -1975,7 +1975,7 @@ static void nfs4_open_confirm_release(void *calldata)
 	struct nfs4_state *state = NULL;
 
 	/* If this request hasn't been cancelled, do nothing */
-	if (data->cancelled == 0)
+	if (!data->cancelled)
 		goto out_free;
 	/* In case of error, no cleanup! */
 	if (!data->rpc_done)
@@ -2018,7 +2018,7 @@ static int _nfs4_proc_open_confirm(struct nfs4_opendata *data)
 
 	nfs4_init_sequence(&data->c_arg.seq_args, &data->c_res.seq_res, 1);
 	kref_get(&data->kref);
-	data->rpc_done = 0;
+	data->rpc_done = false;
 	data->rpc_status = 0;
 	data->timestamp = jiffies;
 	if (data->is_recover)
@@ -2028,7 +2028,7 @@ static int _nfs4_proc_open_confirm(struct nfs4_opendata *data)
 		return PTR_ERR(task);
 	status = rpc_wait_for_completion_task(task);
 	if (status != 0) {
-		data->cancelled = 1;
+		data->cancelled = true;
 		smp_wmb();
 	} else
 		status = data->rpc_status;
@@ -2127,7 +2127,7 @@ static void nfs4_open_done(struct rpc_task *task, void *calldata)
 		if (!(data->o_res.rflags & NFS4_OPEN_RESULT_CONFIRM))
 			nfs_confirm_seqid(&data->owner->so_seqid, 0);
 	}
-	data->rpc_done = 1;
+	data->rpc_done = true;
 }
 
 static void nfs4_open_release(void *calldata)
@@ -2136,7 +2136,7 @@ static void nfs4_open_release(void *calldata)
 	struct nfs4_state *state = NULL;
 
 	/* If this request hasn't been cancelled, do nothing */
-	if (data->cancelled == 0)
+	if (!data->cancelled)
 		goto out_free;
 	/* In case of error, no cleanup! */
 	if (data->rpc_status != 0 || !data->rpc_done)
@@ -2182,20 +2182,20 @@ static int nfs4_run_open_task(struct nfs4_opendata *data, int isrecover)
 
 	nfs4_init_sequence(&o_arg->seq_args, &o_res->seq_res, 1);
 	kref_get(&data->kref);
-	data->rpc_done = 0;
+	data->rpc_done = false;
 	data->rpc_status = 0;
-	data->cancelled = 0;
-	data->is_recover = 0;
+	data->cancelled = false;
+	data->is_recover = false;
 	if (isrecover) {
 		nfs4_set_sequence_privileged(&o_arg->seq_args);
-		data->is_recover = 1;
+		data->is_recover = true;
 	}
 	task = rpc_run_task(&task_setup_data);
 	if (IS_ERR(task))
 		return PTR_ERR(task);
 	status = rpc_wait_for_completion_task(task);
 	if (status != 0) {
-		data->cancelled = 1;
+		data->cancelled = true;
 		smp_wmb();
 	} else
 		status = data->rpc_status;
@@ -2290,9 +2290,9 @@ static int _nfs4_proc_open(struct nfs4_opendata *data)
 
 	if (o_arg->open_flags & O_CREAT) {
 		if (o_arg->open_flags & O_EXCL)
-			data->file_created = 1;
+			data->file_created = true;
 		else if (o_res->cinfo.before != o_res->cinfo.after)
-			data->file_created = 1;
+			data->file_created = true;
 		if (data->file_created || dir->i_version != o_res->cinfo.after)
 			update_changeattr(dir, &o_res->cinfo,
 					o_res->f_attr->time_start);
@@ -4275,7 +4275,7 @@ static int nfs4_proc_mkdir(struct inode *dir, struct dentry *dentry,
 }
 
 static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
-		u64 cookie, struct page **pages, unsigned int count, int plus)
+		u64 cookie, struct page **pages, unsigned int count, bool plus)
 {
 	struct inode		*dir = d_inode(dentry);
 	struct nfs4_readdir_arg args = {
@@ -4313,7 +4313,7 @@ static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
 }
 
 static int nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
-		u64 cookie, struct page **pages, unsigned int count, int plus)
+		u64 cookie, struct page **pages, unsigned int count, bool plus)
 {
 	struct nfs4_exception exception = { };
 	int err;
@@ -6137,7 +6137,7 @@ static void nfs4_lock_release(void *calldata)
 
 	dprintk("%s: begin!\n", __func__);
 	nfs_free_seqid(data->arg.open_seqid);
-	if (data->cancelled != 0) {
+	if (data->cancelled) {
 		struct rpc_task *task;
 		task = nfs4_do_unlck(&data->fl, data->ctx, data->lsp,
 				data->arg.lock_seqid);
@@ -6220,7 +6220,7 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f
 			nfs4_handle_setlk_error(data->server, data->lsp,
 					data->arg.new_lock_owner, ret);
 	} else
-		data->cancelled = 1;
+		data->cancelled = true;
 	rpc_put_task(task);
 	dprintk("%s: done, ret = %d!\n", __func__, ret);
 	trace_nfs4_set_lock(fl, state, &data->res.stateid, cmd, ret);
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 0f1f290c97cd..495d493d3a35 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -7447,7 +7447,7 @@ out:
  * on a directory already in our cache.
  */
 int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
-		       int plus)
+		       bool plus)
 {
 	unsigned int savep;
 	uint32_t bitmap[3] = {0};
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index 9872cf676a50..7962e49097c3 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -485,7 +485,7 @@ nfs_proc_rmdir(struct inode *dir, const struct qstr *name)
  */
 static int
 nfs_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
-		 u64 cookie, struct page **pages, unsigned int count, int plus)
+		 u64 cookie, struct page **pages, unsigned int count, bool plus)
 {
 	struct inode		*dir = d_inode(dentry);
 	struct nfs_readdirargs	arg = {
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index b28c83475ee8..9b42bffbe07b 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -878,7 +878,7 @@ struct nfs3_readdirargs {
 	struct nfs_fh *		fh;
 	__u64			cookie;
 	__be32			verf[2];
-	int			plus;
+	bool			plus;
 	unsigned int            count;
 	struct page **		pages;
 };
@@ -909,7 +909,7 @@ struct nfs3_linkres {
 struct nfs3_readdirres {
 	struct nfs_fattr *	dir_attr;
 	__be32 *		verf;
-	int			plus;
+	bool			plus;
 };
 
 struct nfs3_getaclres {
@@ -1053,7 +1053,7 @@ struct nfs4_readdir_arg {
 	struct page **			pages;	/* zero-copy data */
 	unsigned int			pgbase;	/* zero-copy data */
 	const u32 *			bitmask;
-	int				plus;
+	bool				plus;
 };
 
 struct nfs4_readdir_res {
@@ -1585,7 +1585,7 @@ struct nfs_rpc_ops {
 	int	(*mkdir)   (struct inode *, struct dentry *, struct iattr *);
 	int	(*rmdir)   (struct inode *, const struct qstr *);
 	int	(*readdir) (struct dentry *, struct rpc_cred *,
-			    u64, struct page **, unsigned int, int);
+			    u64, struct page **, unsigned int, bool);
 	int	(*mknod)   (struct inode *, struct dentry *, struct iattr *,
 			    dev_t);
 	int	(*statfs)  (struct nfs_server *, struct nfs_fh *,
@@ -1595,7 +1595,7 @@ struct nfs_rpc_ops {
 	int	(*pathconf) (struct nfs_server *, struct nfs_fh *,
 			     struct nfs_pathconf *);
 	int	(*set_capabilities)(struct nfs_server *, struct nfs_fh *);
-	int	(*decode_dirent)(struct xdr_stream *, struct nfs_entry *, int);
+	int	(*decode_dirent)(struct xdr_stream *, struct nfs_entry *, bool);
 	int	(*pgio_rpc_prepare)(struct rpc_task *,
 				    struct nfs_pgio_header *);
 	void	(*read_setup)(struct nfs_pgio_header *, struct rpc_message *);
-- 
cgit v1.2.3


From 818a8dbe83fddff534b814a7d4e0c75b511dff2e Mon Sep 17 00:00:00 2001
From: Benjamin Coddington <bcodding@redhat.com>
Date: Fri, 16 Jun 2017 11:13:00 -0400
Subject: NFS: nfs_rename() - revalidate directories on -ERESTARTSYS

An interrupted rename will leave the old dentry behind if the rename
succeeds.  Fix this by forcing a lookup the next time through
->d_revalidate.

A previous attempt at solving this problem took the approach to complete
the work of the rename asynchronously, however that approach was wrong
since it would allow the d_move() to occur after the directory's i_mutex
had been dropped by the original process.

Signed-off-by: Benjamin Coddington <bcodding@redhat.com>
Reviewed-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/dir.c            |  6 +++++-
 fs/nfs/unlink.c         | 13 +++++++++++++
 include/linux/nfs_xdr.h |  1 +
 3 files changed, 19 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 9688e9bb13dc..ab69ebb48350 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -2056,7 +2056,11 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	}
 
 	error = rpc_wait_for_completion_task(task);
-	if (error == 0)
+	if (error != 0) {
+		((struct nfs_renamedata *)task->tk_calldata)->cancelled = 1;
+		/* Paired with the atomic_dec_and_test() barrier in rpc_do_put_task() */
+		smp_wmb();
+	} else
 		error = task->tk_status;
 	rpc_put_task(task);
 out:
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index 191aa577dd1f..e3949d93085c 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -288,6 +288,19 @@ static void nfs_async_rename_release(void *calldata)
 	if (d_really_is_positive(data->old_dentry))
 		nfs_mark_for_revalidate(d_inode(data->old_dentry));
 
+	/* The result of the rename is unknown. Play it safe by
+	 * forcing a new lookup */
+	if (data->cancelled) {
+		spin_lock(&data->old_dir->i_lock);
+		nfs_force_lookup_revalidate(data->old_dir);
+		spin_unlock(&data->old_dir->i_lock);
+		if (data->new_dir != data->old_dir) {
+			spin_lock(&data->new_dir->i_lock);
+			nfs_force_lookup_revalidate(data->new_dir);
+			spin_unlock(&data->new_dir->i_lock);
+		}
+	}
+
 	dput(data->old_dentry);
 	dput(data->new_dentry);
 	iput(data->old_dir);
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 9b42bffbe07b..9463eeff9e3c 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1533,6 +1533,7 @@ struct nfs_renamedata {
 	struct nfs_fattr	new_fattr;
 	void (*complete)(struct rpc_task *, struct nfs_renamedata *);
 	long timeout;
+	bool cancelled;
 };
 
 struct nfs_access_entry;
-- 
cgit v1.2.3


From b5973a8c1ccf375c9ab9e2428e1185e3f799af06 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@primarydata.com>
Date: Tue, 20 Jun 2017 19:35:36 -0400
Subject: NFS: Remove unused fields in the page I/O structures

Remove the 'layout_private' fields that were only used by the pNFS OSD
layout driver.

Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/pagelist.c        | 2 --
 include/linux/nfs_page.h | 1 -
 include/linux/nfs_xdr.h  | 1 -
 3 files changed, 4 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index ad92b401326c..de107d866297 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -51,7 +51,6 @@ void nfs_pgheader_init(struct nfs_pageio_descriptor *desc,
 	hdr->io_start = req_offset(hdr->req);
 	hdr->good_bytes = mirror->pg_count;
 	hdr->dreq = desc->pg_dreq;
-	hdr->layout_private = desc->pg_layout_private;
 	hdr->release = release;
 	hdr->completion_ops = desc->pg_completion_ops;
 	if (hdr->completion_ops->init_hdr)
@@ -711,7 +710,6 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
 	desc->pg_error = 0;
 	desc->pg_lseg = NULL;
 	desc->pg_dreq = NULL;
-	desc->pg_layout_private = NULL;
 	desc->pg_bsize = bsize;
 
 	desc->pg_mirror_count = 1;
diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h
index 247cc3d3498f..6138cf91346b 100644
--- a/include/linux/nfs_page.h
+++ b/include/linux/nfs_page.h
@@ -94,7 +94,6 @@ struct nfs_pageio_descriptor {
 	const struct nfs_pgio_completion_ops *pg_completion_ops;
 	struct pnfs_layout_segment *pg_lseg;
 	struct nfs_direct_req	*pg_dreq;
-	void			*pg_layout_private;
 	unsigned int		pg_bsize;	/* default bsize for mirrors */
 
 	u32			pg_mirror_count;
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 9463eeff9e3c..7f1e04941763 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1436,7 +1436,6 @@ struct nfs_pgio_header {
 	const struct nfs_pgio_completion_ops *completion_ops;
 	const struct nfs_rw_ops	*rw_ops;
 	struct nfs_direct_req	*dreq;
-	void			*layout_private;
 	spinlock_t		lock;
 	/* fields protected by lock */
 	int			pnfs_error;
-- 
cgit v1.2.3


From 919e3bd9a87593520a2c5dfda27bd3e6599852ed Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@primarydata.com>
Date: Tue, 20 Jun 2017 19:35:37 -0400
Subject: NFS: Ensure we commit after writeback is complete

If the page cache is being flushed, then we want to ensure that we
do start a commit once the pages are done being flushed.
If we just wait until all I/O is done to that file, we can end up
livelocking until the balance_dirty_pages() mechanism puts its
foot down and forces I/O to stop.
So instead we do more or less the same thing that O_DIRECT does,
and set up a counter to tell us when the flush is done,

Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/pagelist.c        |  3 +++
 fs/nfs/write.c           | 57 ++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/nfs_page.h |  1 +
 include/linux/nfs_xdr.h  |  2 ++
 4 files changed, 63 insertions(+)

(limited to 'include')

diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index de107d866297..83d2918f1b13 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -50,6 +50,7 @@ void nfs_pgheader_init(struct nfs_pageio_descriptor *desc,
 	hdr->cred = hdr->req->wb_context->cred;
 	hdr->io_start = req_offset(hdr->req);
 	hdr->good_bytes = mirror->pg_count;
+	hdr->io_completion = desc->pg_io_completion;
 	hdr->dreq = desc->pg_dreq;
 	hdr->release = release;
 	hdr->completion_ops = desc->pg_completion_ops;
@@ -709,6 +710,7 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
 	desc->pg_ioflags = io_flags;
 	desc->pg_error = 0;
 	desc->pg_lseg = NULL;
+	desc->pg_io_completion = NULL;
 	desc->pg_dreq = NULL;
 	desc->pg_bsize = bsize;
 
@@ -1231,6 +1233,7 @@ int nfs_pageio_resend(struct nfs_pageio_descriptor *desc,
 {
 	LIST_HEAD(failed);
 
+	desc->pg_io_completion = hdr->io_completion;
 	desc->pg_dreq = hdr->dreq;
 	while (!list_empty(&hdr->pages)) {
 		struct nfs_page *req = nfs_list_entry(hdr->pages.next);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index db7ba542559e..051197cb9195 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -40,6 +40,12 @@
 #define MIN_POOL_WRITE		(32)
 #define MIN_POOL_COMMIT		(4)
 
+struct nfs_io_completion {
+	void (*complete)(void *data);
+	void *data;
+	struct kref refcount;
+};
+
 /*
  * Local function declarations
  */
@@ -108,6 +114,39 @@ static void nfs_writehdr_free(struct nfs_pgio_header *hdr)
 	mempool_free(hdr, nfs_wdata_mempool);
 }
 
+static struct nfs_io_completion *nfs_io_completion_alloc(gfp_t gfp_flags)
+{
+	return kmalloc(sizeof(struct nfs_io_completion), gfp_flags);
+}
+
+static void nfs_io_completion_init(struct nfs_io_completion *ioc,
+		void (*complete)(void *), void *data)
+{
+	ioc->complete = complete;
+	ioc->data = data;
+	kref_init(&ioc->refcount);
+}
+
+static void nfs_io_completion_release(struct kref *kref)
+{
+	struct nfs_io_completion *ioc = container_of(kref,
+			struct nfs_io_completion, refcount);
+	ioc->complete(ioc->data);
+	kfree(ioc);
+}
+
+static void nfs_io_completion_get(struct nfs_io_completion *ioc)
+{
+	if (ioc != NULL)
+		kref_get(&ioc->refcount);
+}
+
+static void nfs_io_completion_put(struct nfs_io_completion *ioc)
+{
+	if (ioc != NULL)
+		kref_put(&ioc->refcount, nfs_io_completion_release);
+}
+
 static void nfs_context_set_write_error(struct nfs_open_context *ctx, int error)
 {
 	ctx->error = error;
@@ -681,18 +720,29 @@ static int nfs_writepages_callback(struct page *page, struct writeback_control *
 	return ret;
 }
 
+static void nfs_io_completion_commit(void *inode)
+{
+	nfs_commit_inode(inode, 0);
+}
+
 int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
 {
 	struct inode *inode = mapping->host;
 	struct nfs_pageio_descriptor pgio;
+	struct nfs_io_completion *ioc = nfs_io_completion_alloc(GFP_NOFS);
 	int err;
 
 	nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES);
 
+	if (ioc)
+		nfs_io_completion_init(ioc, nfs_io_completion_commit, inode);
+
 	nfs_pageio_init_write(&pgio, inode, wb_priority(wbc), false,
 				&nfs_async_write_completion_ops);
+	pgio.pg_io_completion = ioc;
 	err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio);
 	nfs_pageio_complete(&pgio);
+	nfs_io_completion_put(ioc);
 
 	if (err < 0)
 		goto out_err;
@@ -940,6 +990,11 @@ int nfs_write_need_commit(struct nfs_pgio_header *hdr)
 	return hdr->verf.committed != NFS_FILE_SYNC;
 }
 
+static void nfs_async_write_init(struct nfs_pgio_header *hdr)
+{
+	nfs_io_completion_get(hdr->io_completion);
+}
+
 static void nfs_write_completion(struct nfs_pgio_header *hdr)
 {
 	struct nfs_commit_info cinfo;
@@ -973,6 +1028,7 @@ next:
 		nfs_release_request(req);
 	}
 out:
+	nfs_io_completion_put(hdr->io_completion);
 	hdr->release(hdr);
 }
 
@@ -1378,6 +1434,7 @@ static void nfs_async_write_reschedule_io(struct nfs_pgio_header *hdr)
 }
 
 static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops = {
+	.init_hdr = nfs_async_write_init,
 	.error_cleanup = nfs_async_write_error,
 	.completion = nfs_write_completion,
 	.reschedule_io = nfs_async_write_reschedule_io,
diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h
index 6138cf91346b..abbee2d15dce 100644
--- a/include/linux/nfs_page.h
+++ b/include/linux/nfs_page.h
@@ -93,6 +93,7 @@ struct nfs_pageio_descriptor {
 	const struct rpc_call_ops *pg_rpc_callops;
 	const struct nfs_pgio_completion_ops *pg_completion_ops;
 	struct pnfs_layout_segment *pg_lseg;
+	struct nfs_io_completion *pg_io_completion;
 	struct nfs_direct_req	*pg_dreq;
 	unsigned int		pg_bsize;	/* default bsize for mirrors */
 
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 7f1e04941763..89093341f076 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1422,6 +1422,7 @@ enum {
 	NFS_IOHDR_STAT,
 };
 
+struct nfs_io_completion;
 struct nfs_pgio_header {
 	struct inode		*inode;
 	struct rpc_cred		*cred;
@@ -1435,6 +1436,7 @@ struct nfs_pgio_header {
 	void (*release) (struct nfs_pgio_header *hdr);
 	const struct nfs_pgio_completion_ops *completion_ops;
 	const struct nfs_rw_ops	*rw_ops;
+	struct nfs_io_completion *io_completion;
 	struct nfs_direct_req	*dreq;
 	spinlock_t		lock;
 	/* fields protected by lock */
-- 
cgit v1.2.3


From 8dcbec6d20eb881ba368d0aebc3a8a678aebb1da Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 8 Jun 2017 11:52:44 -0400
Subject: NFSv4.1: Handle EXCHGID4_FLAG_CONFIRMED_R during NFSv4.1 migration

Transparent State Migration copies a client's lease state from the
server where a filesystem used to reside to the server where it now
resides. When an NFSv4.1 client first contacts that destination
server, it uses EXCHANGE_ID to detect trunking relationships.

The lease that was copied there is returned to that client, but the
destination server sets EXCHGID4_FLAG_CONFIRMED_R when replying to
the client. This is because the lease was confirmed on the source
server (before it was copied).

Normally, when CONFIRMED_R is set, a client purges the lease and
creates a new one. However, that throws away the entire benefit of
Transparent State Migration.

Therefore, the client must not purge that lease when it is possible
that Transparent State Migration has occurred.

Reported-by: Xuan Qi <xuan.qi@oracle.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Tested-by: Xuan Qi <xuan.qi@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/nfs4client.c       |  5 +++++
 fs/nfs/nfs4state.c        | 16 +++++++++++-----
 include/linux/nfs_fs_sb.h |  2 ++
 3 files changed, 18 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 66776f022111..50566acb5469 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -414,6 +414,7 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp,
 	if (clp != old)
 		clp->cl_preserve_clid = true;
 	nfs_put_client(clp);
+	clear_bit(NFS_CS_TSM_POSSIBLE, &clp->cl_flags);
 	return old;
 
 error:
@@ -852,6 +853,8 @@ static int nfs4_set_client(struct nfs_server *server,
 		set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
 	if (server->options & NFS_OPTION_MIGRATION)
 		set_bit(NFS_CS_MIGRATION, &cl_init.init_flags);
+	if (test_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status))
+		set_bit(NFS_CS_TSM_POSSIBLE, &cl_init.init_flags);
 
 	/* Allocate or find a client reference we can use */
 	clp = nfs_get_client(&cl_init);
@@ -1212,9 +1215,11 @@ int nfs4_update_server(struct nfs_server *server, const char *hostname,
 		return -EAFNOSUPPORT;
 
 	nfs_server_remove_lists(server);
+	set_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status);
 	error = nfs4_set_client(server, hostname, sap, salen, buf,
 				clp->cl_proto, clnt->cl_timeout,
 				clp->cl_minorversion, net);
+	clear_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status);
 	nfs_put_client(clp);
 	if (error != 0) {
 		nfs_server_insert_lists(server);
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index b34de036501b..83f8e60bb1e3 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -352,11 +352,17 @@ int nfs41_discover_server_trunking(struct nfs_client *clp,
 	if (clp != *result)
 		return 0;
 
-	/* Purge state if the client id was established in a prior instance */
-	if (clp->cl_exchange_flags & EXCHGID4_FLAG_CONFIRMED_R)
-		set_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state);
-	else
-		set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
+	/*
+	 * Purge state if the client id was established in a prior
+	 * instance and the client id could not have arrived on the
+	 * server via Transparent State Migration.
+	 */
+	if (clp->cl_exchange_flags & EXCHGID4_FLAG_CONFIRMED_R) {
+		if (!test_bit(NFS_CS_TSM_POSSIBLE, &clp->cl_flags))
+			set_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state);
+		else
+			set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
+	}
 	nfs4_schedule_state_manager(clp);
 	status = nfs_wait_client_init_complete(clp);
 	if (status < 0)
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index e418a1096662..74c44665e6d3 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -42,6 +42,7 @@ struct nfs_client {
 #define NFS_CS_MIGRATION	2		/* - transparent state migr */
 #define NFS_CS_INFINITE_SLOTS	3		/* - don't limit TCP slots */
 #define NFS_CS_NO_RETRANS_TIMEOUT	4	/* - Disable retransmit timeouts */
+#define NFS_CS_TSM_POSSIBLE	5		/* - Maybe state migration */
 	struct sockaddr_storage	cl_addr;	/* server identifier */
 	size_t			cl_addrlen;
 	char *			cl_hostname;	/* hostname of server */
@@ -210,6 +211,7 @@ struct nfs_server {
 	unsigned long		mig_status;
 #define NFS_MIG_IN_TRANSITION		(1)
 #define NFS_MIG_FAILED			(2)
+#define NFS_MIG_TSM_POSSIBLE		(3)
 
 	void (*destroy)(struct nfs_server *);
 
-- 
cgit v1.2.3


From f174ff7a0ab6a097455a94abfc99517940041c07 Mon Sep 17 00:00:00 2001
From: Peng Tao <tao.peng@primarydata.com>
Date: Thu, 29 Jun 2017 06:34:51 -0700
Subject: nfs: add a nfs_ilookup helper

This helper will allow to find an existing NFS inode by the file handle
and fattr.

Signed-off-by: Peng Tao <tao.peng@primarydata.com>
[hch: split from a larger patch]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/inode.c         | 22 ++++++++++++++++++++++
 include/linux/nfs_fs.h |  1 +
 2 files changed, 23 insertions(+)

(limited to 'include')

diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 7e7a894601b9..109279d6d91b 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -386,6 +386,28 @@ void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr,
 #endif
 EXPORT_SYMBOL_GPL(nfs_setsecurity);
 
+/* Search for inode identified by fh, fileid and i_mode in inode cache. */
+struct inode *
+nfs_ilookup(struct super_block *sb, struct nfs_fattr *fattr, struct nfs_fh *fh)
+{
+	struct nfs_find_desc desc = {
+		.fh	= fh,
+		.fattr	= fattr,
+	};
+	struct inode *inode;
+	unsigned long hash;
+
+	if (!(fattr->valid & NFS_ATTR_FATTR_FILEID) ||
+	    !(fattr->valid & NFS_ATTR_FATTR_TYPE))
+		return NULL;
+
+	hash = nfs_fattr_to_ino_t(fattr);
+	inode = ilookup5(sb, hash, nfs_find_actor, &desc);
+
+	dprintk("%s: returning %p\n", __func__, inode);
+	return inode;
+}
+
 /*
  * This is our front-end to iget that looks up inodes by file handle
  * instead of inode number.
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index bb0eb2c9acca..e52cc55ac300 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -332,6 +332,7 @@ extern void nfs_zap_caches(struct inode *);
 extern void nfs_invalidate_atime(struct inode *);
 extern struct inode *nfs_fhget(struct super_block *, struct nfs_fh *,
 				struct nfs_fattr *, struct nfs4_label *);
+struct inode *nfs_ilookup(struct super_block *sb, struct nfs_fattr *, struct nfs_fh *);
 extern int nfs_refresh_inode(struct inode *, struct nfs_fattr *);
 extern int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr);
 extern int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr);
-- 
cgit v1.2.3


From 5b5faaf6df73412af0278997db36dbcb51011d9d Mon Sep 17 00:00:00 2001
From: Jeff Layton <jeff.layton@primarydata.com>
Date: Thu, 29 Jun 2017 06:34:52 -0700
Subject: nfs4: add NFSv4 LOOKUPP handlers

This will be needed in order to implement the get_parent export op
for nfsd.

Signed-off-by: Jeff Layton <jeff.layton@primarydata.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/nfs4proc.c       | 49 ++++++++++++++++++++++++++++++++
 fs/nfs/nfs4trace.h      | 29 +++++++++++++++++++
 fs/nfs/nfs4xdr.c        | 75 +++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/nfs4.h    |  1 +
 include/linux/nfs_xdr.h | 17 ++++++++++-
 5 files changed, 170 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 01dcd4c8dc4f..e1a26c653e78 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -3805,6 +3805,54 @@ nfs4_proc_lookup_mountpoint(struct inode *dir, const struct qstr *name,
 	return (client == NFS_CLIENT(dir)) ? rpc_clone_client(client) : client;
 }
 
+static int _nfs4_proc_lookupp(struct inode *inode,
+		struct nfs_fh *fhandle, struct nfs_fattr *fattr,
+		struct nfs4_label *label)
+{
+	struct rpc_clnt *clnt = NFS_CLIENT(inode);
+	struct nfs_server *server = NFS_SERVER(inode);
+	int		       status;
+	struct nfs4_lookupp_arg args = {
+		.bitmask = server->attr_bitmask,
+		.fh = NFS_FH(inode),
+	};
+	struct nfs4_lookupp_res res = {
+		.server = server,
+		.fattr = fattr,
+		.label = label,
+		.fh = fhandle,
+	};
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LOOKUPP],
+		.rpc_argp = &args,
+		.rpc_resp = &res,
+	};
+
+	args.bitmask = nfs4_bitmask(server, label);
+
+	nfs_fattr_init(fattr);
+
+	dprintk("NFS call  lookupp ino=0x%lx\n", inode->i_ino);
+	status = nfs4_call_sync(clnt, server, &msg, &args.seq_args,
+				&res.seq_res, 0);
+	dprintk("NFS reply lookupp: %d\n", status);
+	return status;
+}
+
+static int nfs4_proc_lookupp(struct inode *inode, struct nfs_fh *fhandle,
+			     struct nfs_fattr *fattr, struct nfs4_label *label)
+{
+	struct nfs4_exception exception = { };
+	int err;
+	do {
+		err = _nfs4_proc_lookupp(inode, fhandle, fattr, label);
+		trace_nfs4_lookupp(inode, err);
+		err = nfs4_handle_exception(NFS_SERVER(inode), err,
+				&exception);
+	} while (exception.retry);
+	return err;
+}
+
 static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry)
 {
 	struct nfs_server *server = NFS_SERVER(inode);
@@ -9314,6 +9362,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
 	.getattr	= nfs4_proc_getattr,
 	.setattr	= nfs4_proc_setattr,
 	.lookup		= nfs4_proc_lookup,
+	.lookupp	= nfs4_proc_lookupp,
 	.access		= nfs4_proc_access,
 	.readlink	= nfs4_proc_readlink,
 	.create		= nfs4_proc_create,
diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h
index 845d0eadefc9..be1da19c65d6 100644
--- a/fs/nfs/nfs4trace.h
+++ b/fs/nfs/nfs4trace.h
@@ -891,6 +891,35 @@ DEFINE_NFS4_LOOKUP_EVENT(nfs4_remove);
 DEFINE_NFS4_LOOKUP_EVENT(nfs4_get_fs_locations);
 DEFINE_NFS4_LOOKUP_EVENT(nfs4_secinfo);
 
+TRACE_EVENT(nfs4_lookupp,
+		TP_PROTO(
+			const struct inode *inode,
+			int error
+		),
+
+		TP_ARGS(inode, error),
+
+		TP_STRUCT__entry(
+			__field(dev_t, dev)
+			__field(u64, ino)
+			__field(int, error)
+		),
+
+		TP_fast_assign(
+			__entry->dev = inode->i_sb->s_dev;
+			__entry->ino = NFS_FILEID(inode);
+			__entry->error = error;
+		),
+
+		TP_printk(
+			"error=%d (%s) inode=%02x:%02x:%llu",
+			__entry->error,
+			show_nfsv4_errors(__entry->error),
+			MAJOR(__entry->dev), MINOR(__entry->dev),
+			(unsigned long long)__entry->ino
+		)
+);
+
 TRACE_EVENT(nfs4_rename,
 		TP_PROTO(
 			const struct inode *olddir,
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 495d493d3a35..fa3eb361d4f8 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -159,6 +159,8 @@ static int nfs4_stat_to_errno(int);
 				(op_decode_hdr_maxsz)
 #define encode_lookup_maxsz	(op_encode_hdr_maxsz + nfs4_name_maxsz)
 #define decode_lookup_maxsz	(op_decode_hdr_maxsz)
+#define encode_lookupp_maxsz	(op_encode_hdr_maxsz)
+#define decode_lookupp_maxsz	(op_decode_hdr_maxsz)
 #define encode_share_access_maxsz \
 				(2)
 #define encode_createmode_maxsz	(1 + encode_attrs_maxsz + encode_verifier_maxsz)
@@ -618,6 +620,18 @@ static int nfs4_stat_to_errno(int);
 				decode_lookup_maxsz + \
 				decode_getattr_maxsz + \
 				decode_getfh_maxsz)
+#define NFS4_enc_lookupp_sz	(compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
+				encode_putfh_maxsz + \
+				encode_lookupp_maxsz + \
+				encode_getattr_maxsz + \
+				encode_getfh_maxsz)
+#define NFS4_dec_lookupp_sz	(compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
+				decode_putfh_maxsz + \
+				decode_lookupp_maxsz + \
+				decode_getattr_maxsz + \
+				decode_getfh_maxsz)
 #define NFS4_enc_lookup_root_sz (compound_encode_hdr_maxsz + \
 				encode_sequence_maxsz + \
 				encode_putrootfh_maxsz + \
@@ -1368,6 +1382,11 @@ static void encode_lookup(struct xdr_stream *xdr, const struct qstr *name, struc
 	encode_string(xdr, name->len, name->name);
 }
 
+static void encode_lookupp(struct xdr_stream *xdr, struct compound_hdr *hdr)
+{
+	encode_op_hdr(xdr, OP_LOOKUPP, decode_lookupp_maxsz, hdr);
+}
+
 static void encode_share_access(struct xdr_stream *xdr, u32 share_access)
 {
 	__be32 *p;
@@ -2122,6 +2141,26 @@ static void nfs4_xdr_enc_lookup(struct rpc_rqst *req, struct xdr_stream *xdr,
 	encode_nops(&hdr);
 }
 
+/*
+ * Encode LOOKUPP request
+ */
+static void nfs4_xdr_enc_lookupp(struct rpc_rqst *req, struct xdr_stream *xdr,
+		const void *data)
+{
+	const struct nfs4_lookupp_arg *args = data;
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->seq_args, &hdr);
+	encode_putfh(xdr, args->fh, &hdr);
+	encode_lookupp(xdr, &hdr);
+	encode_getfh(xdr, &hdr);
+	encode_getfattr(xdr, args->bitmask, &hdr);
+	encode_nops(&hdr);
+}
+
 /*
  * Encode LOOKUP_ROOT request
  */
@@ -5058,6 +5097,11 @@ static int decode_lookup(struct xdr_stream *xdr)
 	return decode_op_hdr(xdr, OP_LOOKUP);
 }
 
+static int decode_lookupp(struct xdr_stream *xdr)
+{
+	return decode_op_hdr(xdr, OP_LOOKUPP);
+}
+
 /* This is too sick! */
 static int decode_space_limit(struct xdr_stream *xdr,
 		unsigned long *pagemod_limit)
@@ -6237,6 +6281,36 @@ out:
 	return status;
 }
 
+/*
+ * Decode LOOKUPP response
+ */
+static int nfs4_xdr_dec_lookupp(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
+		void *data)
+{
+	struct nfs4_lookupp_res *res = data;
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->seq_res, rqstp);
+	if (status)
+		goto out;
+	status = decode_putfh(xdr);
+	if (status)
+		goto out;
+	status = decode_lookupp(xdr);
+	if (status)
+		goto out;
+	status = decode_getfh(xdr, res->fh);
+	if (status)
+		goto out;
+	status = decode_getfattr_label(xdr, res->fattr, res->label, res->server);
+out:
+	return status;
+}
+
 /*
  * Decode LOOKUP_ROOT response
  */
@@ -7614,6 +7688,7 @@ const struct rpc_procinfo nfs4_procedures[] = {
 	PROC(ACCESS,		enc_access,		dec_access),
 	PROC(GETATTR,		enc_getattr,		dec_getattr),
 	PROC(LOOKUP,		enc_lookup,		dec_lookup),
+	PROC(LOOKUPP,		enc_lookupp,		dec_lookupp),
 	PROC(LOOKUP_ROOT,	enc_lookup_root,	dec_lookup_root),
 	PROC(REMOVE,		enc_remove,		dec_remove),
 	PROC(RENAME,		enc_rename,		dec_rename),
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 1b1ca04820a3..47239c336688 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -479,6 +479,7 @@ enum {
 	NFSPROC4_CLNT_ACCESS,
 	NFSPROC4_CLNT_GETATTR,
 	NFSPROC4_CLNT_LOOKUP,
+	NFSPROC4_CLNT_LOOKUPP,
 	NFSPROC4_CLNT_LOOKUP_ROOT,
 	NFSPROC4_CLNT_REMOVE,
 	NFSPROC4_CLNT_RENAME,
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 89093341f076..ca3bcc4ed4e5 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1012,7 +1012,6 @@ struct nfs4_link_res {
 	struct nfs_fattr *		dir_attr;
 };
 
-
 struct nfs4_lookup_arg {
 	struct nfs4_sequence_args	seq_args;
 	const struct nfs_fh *		dir_fh;
@@ -1028,6 +1027,20 @@ struct nfs4_lookup_res {
 	struct nfs4_label		*label;
 };
 
+struct nfs4_lookupp_arg {
+	struct nfs4_sequence_args	seq_args;
+	const struct nfs_fh		*fh;
+	const u32			*bitmask;
+};
+
+struct nfs4_lookupp_res {
+	struct nfs4_sequence_res	seq_res;
+	const struct nfs_server		*server;
+	struct nfs_fattr		*fattr;
+	struct nfs_fh			*fh;
+	struct nfs4_label		*label;
+};
+
 struct nfs4_lookup_root_arg {
 	struct nfs4_sequence_args	seq_args;
 	const u32 *			bitmask;
@@ -1569,6 +1582,8 @@ struct nfs_rpc_ops {
 	int	(*lookup)  (struct inode *, const struct qstr *,
 			    struct nfs_fh *, struct nfs_fattr *,
 			    struct nfs4_label *);
+	int	(*lookupp) (struct inode *, struct nfs_fh *,
+			    struct nfs_fattr *, struct nfs4_label *);
 	int	(*access)  (struct inode *, struct nfs_access_entry *);
 	int	(*readlink)(struct inode *, struct page *, unsigned int,
 			    unsigned int);
-- 
cgit v1.2.3


From 301bfa483016d48b7fb9cbad87c0a04a15c25b90 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@primarydata.com>
Date: Tue, 11 Jul 2017 17:53:48 -0400
Subject: NFS: Don't run wake_up_bit() when nobody is waiting...

"perf lock" shows fairly heavy contention for the bit waitqueue locks
when doing an I/O heavy workload.
Use a bit to tell whether or not there has been contention for a lock
so that we can optimise away the bit waitqueue options in those cases.

Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/pagelist.c        | 17 ++++++++++++++++-
 include/linux/nfs_page.h |  2 ++
 2 files changed, 18 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 8a23e2b40b04..de9066a92c0d 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -155,9 +155,12 @@ nfs_page_group_lock(struct nfs_page *req, bool nonblock)
 	if (!test_and_set_bit(PG_HEADLOCK, &head->wb_flags))
 		return 0;
 
-	if (!nonblock)
+	if (!nonblock) {
+		set_bit(PG_CONTENDED1, &head->wb_flags);
+		smp_mb__after_atomic();
 		return wait_on_bit_lock(&head->wb_flags, PG_HEADLOCK,
 				TASK_UNINTERRUPTIBLE);
+	}
 
 	return -EAGAIN;
 }
@@ -175,6 +178,10 @@ nfs_page_group_lock_wait(struct nfs_page *req)
 
 	WARN_ON_ONCE(head != head->wb_head);
 
+	if (!test_bit(PG_HEADLOCK, &head->wb_flags))
+		return;
+	set_bit(PG_CONTENDED1, &head->wb_flags);
+	smp_mb__after_atomic();
 	wait_on_bit(&head->wb_flags, PG_HEADLOCK,
 		TASK_UNINTERRUPTIBLE);
 }
@@ -193,6 +200,8 @@ nfs_page_group_unlock(struct nfs_page *req)
 	smp_mb__before_atomic();
 	clear_bit(PG_HEADLOCK, &head->wb_flags);
 	smp_mb__after_atomic();
+	if (!test_bit(PG_CONTENDED1, &head->wb_flags))
+		return;
 	wake_up_bit(&head->wb_flags, PG_HEADLOCK);
 }
 
@@ -383,6 +392,8 @@ void nfs_unlock_request(struct nfs_page *req)
 	smp_mb__before_atomic();
 	clear_bit(PG_BUSY, &req->wb_flags);
 	smp_mb__after_atomic();
+	if (!test_bit(PG_CONTENDED2, &req->wb_flags))
+		return;
 	wake_up_bit(&req->wb_flags, PG_BUSY);
 }
 
@@ -465,6 +476,10 @@ void nfs_release_request(struct nfs_page *req)
 int
 nfs_wait_on_request(struct nfs_page *req)
 {
+	if (!test_bit(PG_BUSY, &req->wb_flags))
+		return 0;
+	set_bit(PG_CONTENDED2, &req->wb_flags);
+	smp_mb__after_atomic();
 	return wait_on_bit_io(&req->wb_flags, PG_BUSY,
 			      TASK_UNINTERRUPTIBLE);
 }
diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h
index abbee2d15dce..d67b67ae6c8b 100644
--- a/include/linux/nfs_page.h
+++ b/include/linux/nfs_page.h
@@ -33,6 +33,8 @@ enum {
 	PG_UPTODATE,		/* page group sync bit in read path */
 	PG_WB_END,		/* page group sync bit in write path */
 	PG_REMOVE,		/* page group sync bit in write path */
+	PG_CONTENDED1,		/* Is someone waiting for a lock? */
+	PG_CONTENDED2,		/* Is someone waiting for a lock? */
 };
 
 struct nfs_inode;
-- 
cgit v1.2.3


From b4f937cffa66b3d56eb8f586e620d0b223a281a3 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@primarydata.com>
Date: Tue, 11 Jul 2017 17:53:48 -0400
Subject: NFS: Don't run wake_up_bit() when nobody is waiting...

"perf lock" shows fairly heavy contention for the bit waitqueue locks
when doing an I/O heavy workload.
Use a bit to tell whether or not there has been contention for a lock
so that we can optimise away the bit waitqueue options in those cases.

Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/pagelist.c        | 17 ++++++++++++++++-
 include/linux/nfs_page.h |  2 ++
 2 files changed, 18 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 8a23e2b40b04..de9066a92c0d 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -155,9 +155,12 @@ nfs_page_group_lock(struct nfs_page *req, bool nonblock)
 	if (!test_and_set_bit(PG_HEADLOCK, &head->wb_flags))
 		return 0;
 
-	if (!nonblock)
+	if (!nonblock) {
+		set_bit(PG_CONTENDED1, &head->wb_flags);
+		smp_mb__after_atomic();
 		return wait_on_bit_lock(&head->wb_flags, PG_HEADLOCK,
 				TASK_UNINTERRUPTIBLE);
+	}
 
 	return -EAGAIN;
 }
@@ -175,6 +178,10 @@ nfs_page_group_lock_wait(struct nfs_page *req)
 
 	WARN_ON_ONCE(head != head->wb_head);
 
+	if (!test_bit(PG_HEADLOCK, &head->wb_flags))
+		return;
+	set_bit(PG_CONTENDED1, &head->wb_flags);
+	smp_mb__after_atomic();
 	wait_on_bit(&head->wb_flags, PG_HEADLOCK,
 		TASK_UNINTERRUPTIBLE);
 }
@@ -193,6 +200,8 @@ nfs_page_group_unlock(struct nfs_page *req)
 	smp_mb__before_atomic();
 	clear_bit(PG_HEADLOCK, &head->wb_flags);
 	smp_mb__after_atomic();
+	if (!test_bit(PG_CONTENDED1, &head->wb_flags))
+		return;
 	wake_up_bit(&head->wb_flags, PG_HEADLOCK);
 }
 
@@ -383,6 +392,8 @@ void nfs_unlock_request(struct nfs_page *req)
 	smp_mb__before_atomic();
 	clear_bit(PG_BUSY, &req->wb_flags);
 	smp_mb__after_atomic();
+	if (!test_bit(PG_CONTENDED2, &req->wb_flags))
+		return;
 	wake_up_bit(&req->wb_flags, PG_BUSY);
 }
 
@@ -465,6 +476,10 @@ void nfs_release_request(struct nfs_page *req)
 int
 nfs_wait_on_request(struct nfs_page *req)
 {
+	if (!test_bit(PG_BUSY, &req->wb_flags))
+		return 0;
+	set_bit(PG_CONTENDED2, &req->wb_flags);
+	smp_mb__after_atomic();
 	return wait_on_bit_io(&req->wb_flags, PG_BUSY,
 			      TASK_UNINTERRUPTIBLE);
 }
diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h
index abbee2d15dce..d67b67ae6c8b 100644
--- a/include/linux/nfs_page.h
+++ b/include/linux/nfs_page.h
@@ -33,6 +33,8 @@ enum {
 	PG_UPTODATE,		/* page group sync bit in read path */
 	PG_WB_END,		/* page group sync bit in write path */
 	PG_REMOVE,		/* page group sync bit in write path */
+	PG_CONTENDED1,		/* Is someone waiting for a lock? */
+	PG_CONTENDED2,		/* Is someone waiting for a lock? */
 };
 
 struct nfs_inode;
-- 
cgit v1.2.3


From d3457c877b14aaee8c52923eedf05a3b78af0476 Mon Sep 17 00:00:00 2001
From: Roman Kagan <rkagan@virtuozzo.com>
Date: Fri, 14 Jul 2017 17:13:20 +0300
Subject: kvm: x86: hyperv: make VP_INDEX managed by userspace
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Hyper-V identifies vCPUs by Virtual Processor Index, which can be
queried via HV_X64_MSR_VP_INDEX msr.  It is defined by the spec as a
sequential number which can't exceed the maximum number of vCPUs per VM.
APIC ids can be sparse and thus aren't a valid replacement for VP
indices.

Current KVM uses its internal vcpu index as VP_INDEX.  However, to make
it predictable and persistent across VM migrations, the userspace has to
control the value of VP_INDEX.

This patch achieves that, by storing vp_index explicitly on vcpu, and
allowing HV_X64_MSR_VP_INDEX to be set from the host side.  For
compatibility it's initialized to KVM vcpu index.  Also a few variables
are renamed to make clear distinction betweed this Hyper-V vp_index and
KVM vcpu_id (== APIC id).  Besides, a new capability,
KVM_CAP_HYPERV_VP_INDEX, is added to allow the userspace to skip
attempting msr writes where unsupported, to avoid spamming error logs.

Signed-off-by: Roman Kagan <rkagan@virtuozzo.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
---
 Documentation/virtual/kvm/api.txt |  9 +++++++
 arch/x86/include/asm/kvm_host.h   |  1 +
 arch/x86/kvm/hyperv.c             | 54 +++++++++++++++++++++++++--------------
 arch/x86/kvm/hyperv.h             |  1 +
 arch/x86/kvm/x86.c                |  3 +++
 include/uapi/linux/kvm.h          |  1 +
 6 files changed, 50 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 78ac577c9378..e63a35fafef0 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -4338,3 +4338,12 @@ This capability enables a newer version of Hyper-V Synthetic interrupt
 controller (SynIC).  The only difference with KVM_CAP_HYPERV_SYNIC is that KVM
 doesn't clear SynIC message and event flags pages when they are enabled by
 writing to the respective MSRs.
+
+8.12 KVM_CAP_HYPERV_VP_INDEX
+
+Architectures: x86
+
+This capability indicates that userspace can load HV_X64_MSR_VP_INDEX msr.  Its
+value is used to denote the target vcpu for a SynIC interrupt.  For
+compatibilty, KVM initializes this msr to KVM's internal vcpu index.  When this
+capability is absent, userspace can still query this msr's value.
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index da3261e384d3..87ac4fba6d8e 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -467,6 +467,7 @@ struct kvm_vcpu_hv_synic {
 
 /* Hyper-V per vcpu emulation context */
 struct kvm_vcpu_hv {
+	u32 vp_index;
 	u64 hv_vapic;
 	s64 runtime_offset;
 	struct kvm_vcpu_hv_synic synic;
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index a8084406707e..2695a34fa1c5 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -106,14 +106,27 @@ static int synic_set_sint(struct kvm_vcpu_hv_synic *synic, int sint,
 	return 0;
 }
 
-static struct kvm_vcpu_hv_synic *synic_get(struct kvm *kvm, u32 vcpu_id)
+static struct kvm_vcpu *get_vcpu_by_vpidx(struct kvm *kvm, u32 vpidx)
+{
+	struct kvm_vcpu *vcpu = NULL;
+	int i;
+
+	if (vpidx < KVM_MAX_VCPUS)
+		vcpu = kvm_get_vcpu(kvm, vpidx);
+	if (vcpu && vcpu_to_hv_vcpu(vcpu)->vp_index == vpidx)
+		return vcpu;
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		if (vcpu_to_hv_vcpu(vcpu)->vp_index == vpidx)
+			return vcpu;
+	return NULL;
+}
+
+static struct kvm_vcpu_hv_synic *synic_get(struct kvm *kvm, u32 vpidx)
 {
 	struct kvm_vcpu *vcpu;
 	struct kvm_vcpu_hv_synic *synic;
 
-	if (vcpu_id >= atomic_read(&kvm->online_vcpus))
-		return NULL;
-	vcpu = kvm_get_vcpu(kvm, vcpu_id);
+	vcpu = get_vcpu_by_vpidx(kvm, vpidx);
 	if (!vcpu)
 		return NULL;
 	synic = vcpu_to_synic(vcpu);
@@ -320,11 +333,11 @@ static int synic_set_irq(struct kvm_vcpu_hv_synic *synic, u32 sint)
 	return ret;
 }
 
-int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vcpu_id, u32 sint)
+int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vpidx, u32 sint)
 {
 	struct kvm_vcpu_hv_synic *synic;
 
-	synic = synic_get(kvm, vcpu_id);
+	synic = synic_get(kvm, vpidx);
 	if (!synic)
 		return -EINVAL;
 
@@ -343,11 +356,11 @@ void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector)
 			kvm_hv_notify_acked_sint(vcpu, i);
 }
 
-static int kvm_hv_set_sint_gsi(struct kvm *kvm, u32 vcpu_id, u32 sint, int gsi)
+static int kvm_hv_set_sint_gsi(struct kvm *kvm, u32 vpidx, u32 sint, int gsi)
 {
 	struct kvm_vcpu_hv_synic *synic;
 
-	synic = synic_get(kvm, vcpu_id);
+	synic = synic_get(kvm, vpidx);
 	if (!synic)
 		return -EINVAL;
 
@@ -689,6 +702,13 @@ void kvm_hv_vcpu_init(struct kvm_vcpu *vcpu)
 		stimer_init(&hv_vcpu->stimer[i], i);
 }
 
+void kvm_hv_vcpu_postcreate(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu);
+
+	hv_vcpu->vp_index = kvm_vcpu_get_idx(vcpu);
+}
+
 int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages)
 {
 	struct kvm_vcpu_hv_synic *synic = vcpu_to_synic(vcpu);
@@ -983,6 +1003,11 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
 	struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv;
 
 	switch (msr) {
+	case HV_X64_MSR_VP_INDEX:
+		if (!host)
+			return 1;
+		hv->vp_index = (u32)data;
+		break;
 	case HV_X64_MSR_APIC_ASSIST_PAGE: {
 		u64 gfn;
 		unsigned long addr;
@@ -1094,18 +1119,9 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv;
 
 	switch (msr) {
-	case HV_X64_MSR_VP_INDEX: {
-		int r;
-		struct kvm_vcpu *v;
-
-		kvm_for_each_vcpu(r, v, vcpu->kvm) {
-			if (v == vcpu) {
-				data = r;
-				break;
-			}
-		}
+	case HV_X64_MSR_VP_INDEX:
+		data = hv->vp_index;
 		break;
-	}
 	case HV_X64_MSR_EOI:
 		return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata);
 	case HV_X64_MSR_ICR:
diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
index 12f65fe1011d..e637631a9574 100644
--- a/arch/x86/kvm/hyperv.h
+++ b/arch/x86/kvm/hyperv.h
@@ -59,6 +59,7 @@ void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector);
 int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages);
 
 void kvm_hv_vcpu_init(struct kvm_vcpu *vcpu);
+void kvm_hv_vcpu_postcreate(struct kvm_vcpu *vcpu);
 void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu);
 
 static inline struct kvm_vcpu_hv_stimer *vcpu_to_stimer(struct kvm_vcpu *vcpu,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6753f0982791..5b8f07889f6a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2666,6 +2666,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_HYPERV_SPIN:
 	case KVM_CAP_HYPERV_SYNIC:
 	case KVM_CAP_HYPERV_SYNIC2:
+	case KVM_CAP_HYPERV_VP_INDEX:
 	case KVM_CAP_PCI_SEGMENT:
 	case KVM_CAP_DEBUGREGS:
 	case KVM_CAP_X86_ROBUST_SINGLESTEP:
@@ -7688,6 +7689,8 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 	struct msr_data msr;
 	struct kvm *kvm = vcpu->kvm;
 
+	kvm_hv_vcpu_postcreate(vcpu);
+
 	if (vcpu_load(vcpu))
 		return;
 	msr.data = 0x0;
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 38b2cfbc8112..6cd63c18708a 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -928,6 +928,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_PPC_FWNMI 146
 #define KVM_CAP_PPC_SMT_POSSIBLE 147
 #define KVM_CAP_HYPERV_SYNIC2 148
+#define KVM_CAP_HYPERV_VP_INDEX 149
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
-- 
cgit v1.2.3


From 2b02c20ce0c28974b44e69a2e2f5ddc6a470ad6f Mon Sep 17 00:00:00 2001
From: Enrico Mioso <mrkiko.rs@gmail.com>
Date: Tue, 11 Jul 2017 17:21:52 +0200
Subject: cdc_ncm: Set NTB format again after altsetting switch for Huawei
 devices
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some firmwares in Huawei E3372H devices have been observed to switch back
to NTB 32-bit format after altsetting switch.
This patch implements a driver flag to check for the device settings and
set NTB format to 16-bit again if needed.
The flag has been activated for devices controlled by the huawei_cdc_ncm.c
driver.

V1->V2:
- fixed broken error checks
- some corrections to the commit message
V2->V3:
- variable name changes, to clarify what's happening
- check (and possibly set) the NTB format later in the common bind code path

Signed-off-by: Enrico Mioso <mrkiko.rs@gmail.com>
Reported-and-tested-by: Christian Panton <christian@panton.org>
Reviewed-by: Bjørn Mork <bjorn@mork.no>
CC: Bjørn Mork <bjorn@mork.no>
CC: Christian Panton <christian@panton.org>
CC: linux-usb@vger.kernel.org
CC: netdev@vger.kernel.org
CC: Oliver Neukum <oliver@neukum.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ncm.c        | 28 ++++++++++++++++++++++++++++
 drivers/net/usb/huawei_cdc_ncm.c |  6 ++++++
 include/linux/usb/cdc_ncm.h      |  1 +
 3 files changed, 35 insertions(+)

(limited to 'include')

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index d103a1d4fb36..8f572b9f3625 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -768,8 +768,10 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_
 	u8 *buf;
 	int len;
 	int temp;
+	int err;
 	u8 iface_no;
 	struct usb_cdc_parsed_header hdr;
+	u16 curr_ntb_format;
 
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
@@ -874,6 +876,32 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_
 		goto error2;
 	}
 
+	/*
+	 * Some Huawei devices have been observed to come out of reset in NDP32 mode.
+	 * Let's check if this is the case, and set the device to NDP16 mode again if
+	 * needed.
+	*/
+	if (ctx->drvflags & CDC_NCM_FLAG_RESET_NTB16) {
+		err = usbnet_read_cmd(dev, USB_CDC_GET_NTB_FORMAT,
+				      USB_TYPE_CLASS | USB_DIR_IN | USB_RECIP_INTERFACE,
+				      0, iface_no, &curr_ntb_format, 2);
+		if (err < 0) {
+			goto error2;
+		}
+
+		if (curr_ntb_format == USB_CDC_NCM_NTB32_FORMAT) {
+			dev_info(&intf->dev, "resetting NTB format to 16-bit");
+			err = usbnet_write_cmd(dev, USB_CDC_SET_NTB_FORMAT,
+					       USB_TYPE_CLASS | USB_DIR_OUT
+					       | USB_RECIP_INTERFACE,
+					       USB_CDC_NCM_NTB16_FORMAT,
+					       iface_no, NULL, 0);
+
+			if (err < 0)
+				goto error2;
+		}
+	}
+
 	cdc_ncm_find_endpoints(dev, ctx->data);
 	cdc_ncm_find_endpoints(dev, ctx->control);
 	if (!dev->in || !dev->out || !dev->status) {
diff --git a/drivers/net/usb/huawei_cdc_ncm.c b/drivers/net/usb/huawei_cdc_ncm.c
index 2680a65cd5e4..63f28908afda 100644
--- a/drivers/net/usb/huawei_cdc_ncm.c
+++ b/drivers/net/usb/huawei_cdc_ncm.c
@@ -80,6 +80,12 @@ static int huawei_cdc_ncm_bind(struct usbnet *usbnet_dev,
 	 * be at the end of the frame.
 	 */
 	drvflags |= CDC_NCM_FLAG_NDP_TO_END;
+
+	/* Additionally, it has been reported that some Huawei E3372H devices, with
+	 * firmware version 21.318.01.00.541, come out of reset in NTB32 format mode, hence
+	 * needing to be set to the NTB16 one again.
+	 */
+	drvflags |= CDC_NCM_FLAG_RESET_NTB16;
 	ret = cdc_ncm_bind_common(usbnet_dev, intf, 1, drvflags);
 	if (ret)
 		goto err;
diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h
index 021f7a88f52c..1a59699cf82a 100644
--- a/include/linux/usb/cdc_ncm.h
+++ b/include/linux/usb/cdc_ncm.h
@@ -83,6 +83,7 @@
 /* Driver flags */
 #define CDC_NCM_FLAG_NDP_TO_END			0x02	/* NDP is placed at end of frame */
 #define CDC_MBIM_FLAG_AVOID_ALTSETTING_TOGGLE	0x04	/* Avoid altsetting toggle during init */
+#define CDC_NCM_FLAG_RESET_NTB16 0x08	/* set NDP16 one more time after altsetting switch */
 
 #define cdc_ncm_comm_intf_is_mbim(x)  ((x)->desc.bInterfaceSubClass == USB_CDC_SUBCLASS_MBIM && \
 				       (x)->desc.bInterfaceProtocol == USB_CDC_PROTO_NONE)
-- 
cgit v1.2.3


From 76250f2b743b72cb685cc51ac0cdabb32957180b Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 14 Feb 2017 12:40:01 +0000
Subject: dma-buf/fence: Avoid use of uninitialised timestamp

[  236.821534] WARNING: kmemcheck: Caught 64-bit read from uninitialized memory (ffff8802538683d0)
[  236.828642] 420000001e7f0000000000000000000000080000000000000000000000000000
[  236.839543]  i i i i u u u u i i i i i i i i u u u u u u u u u u u u u u u u
[  236.850420]                                  ^
[  236.854123] RIP: 0010:[<ffffffff81396f07>]  [<ffffffff81396f07>] fence_signal+0x17/0xd0
[  236.861313] RSP: 0018:ffff88024acd7ba0  EFLAGS: 00010282
[  236.865027] RAX: ffffffff812f6a90 RBX: ffff8802527ca800 RCX: ffff880252cb30e0
[  236.868801] RDX: ffff88024ac5d918 RSI: ffff880252f780e0 RDI: ffff880253868380
[  236.872579] RBP: ffff88024acd7bc0 R08: ffff88024acd7be0 R09: 0000000000000000
[  236.876407] R10: 0000000000000000 R11: 0000000000000000 R12: ffff880253868380
[  236.880185] R13: ffff8802538684d0 R14: ffff880253868380 R15: ffff88024cd48e00
[  236.883983] FS:  00007f1646d1a740(0000) GS:ffff88025d000000(0000) knlGS:0000000000000000
[  236.890959] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  236.894702] CR2: ffff880251360318 CR3: 000000024ad21000 CR4: 00000000001406f0
[  236.898481]  [<ffffffff8130d1ad>] i915_gem_request_retire+0x1cd/0x230
[  236.902439]  [<ffffffff8130e2b3>] i915_gem_request_alloc+0xa3/0x2f0
[  236.906435]  [<ffffffff812fb1bd>] i915_gem_do_execbuffer.isra.41+0xb6d/0x18b0
[  236.910434]  [<ffffffff812fc265>] i915_gem_execbuffer2+0x95/0x1e0
[  236.914390]  [<ffffffff812ad625>] drm_ioctl+0x1e5/0x460
[  236.918275]  [<ffffffff8110d4cf>] do_vfs_ioctl+0x8f/0x5c0
[  236.922168]  [<ffffffff8110da3c>] SyS_ioctl+0x3c/0x70
[  236.926090]  [<ffffffff814b7a5f>] entry_SYSCALL_64_fastpath+0x17/0x93
[  236.930045]  [<ffffffffffffffff>] 0xffffffffffffffff

We only set the timestamp before we mark the fence as signaled. It is
done before to avoid observers having a window in which they may see the
fence as complete but no timestamp. Having it does incur a potential for
the timestamp to be written twice, and even for it to be corrupted if
the u64 write is not atomic. Instead use a new bit to record the
presence of the timestamp, and teach the readers to wait until it is set
if the fence is complete. There still remains a race where the timestamp
for the signaled fence may be shown before the fence is reported as
signaled, but that's a pre-existing error.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Sumit Semwal <sumit.semwal@linaro.org>
Cc: Gustavo Padovan <gustavo@padovan.org>
Cc: Daniel Vetter <daniel.vetter@intel.com>
Reported-by: Rafael Antognolli <rafael.antognolli@intel.com>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170214124001.1930-1-chris@chris-wilson.co.uk
---
 drivers/dma-buf/dma-fence.c  | 17 ++++++-----------
 drivers/dma-buf/sync_debug.c |  2 +-
 drivers/dma-buf/sync_file.c  |  8 +++++++-
 include/linux/dma-fence.h    |  2 ++
 4 files changed, 16 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c
index 0918d3f003d6..13556fdda2a5 100644
--- a/drivers/dma-buf/dma-fence.c
+++ b/drivers/dma-buf/dma-fence.c
@@ -75,11 +75,6 @@ int dma_fence_signal_locked(struct dma_fence *fence)
 	if (WARN_ON(!fence))
 		return -EINVAL;
 
-	if (!ktime_to_ns(fence->timestamp)) {
-		fence->timestamp = ktime_get();
-		smp_mb__before_atomic();
-	}
-
 	if (test_and_set_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) {
 		ret = -EINVAL;
 
@@ -87,8 +82,11 @@ int dma_fence_signal_locked(struct dma_fence *fence)
 		 * we might have raced with the unlocked dma_fence_signal,
 		 * still run through all callbacks
 		 */
-	} else
+	} else {
+		fence->timestamp = ktime_get();
+		set_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags);
 		trace_dma_fence_signaled(fence);
+	}
 
 	list_for_each_entry_safe(cur, tmp, &fence->cb_list, node) {
 		list_del_init(&cur->node);
@@ -115,14 +113,11 @@ int dma_fence_signal(struct dma_fence *fence)
 	if (!fence)
 		return -EINVAL;
 
-	if (!ktime_to_ns(fence->timestamp)) {
-		fence->timestamp = ktime_get();
-		smp_mb__before_atomic();
-	}
-
 	if (test_and_set_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
 		return -EINVAL;
 
+	fence->timestamp = ktime_get();
+	set_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags);
 	trace_dma_fence_signaled(fence);
 
 	if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &fence->flags)) {
diff --git a/drivers/dma-buf/sync_debug.c b/drivers/dma-buf/sync_debug.c
index c769dc653b34..bfead12390f2 100644
--- a/drivers/dma-buf/sync_debug.c
+++ b/drivers/dma-buf/sync_debug.c
@@ -84,7 +84,7 @@ static void sync_print_fence(struct seq_file *s,
 		   show ? "_" : "",
 		   sync_status_str(status));
 
-	if (status) {
+	if (test_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags)) {
 		struct timespec64 ts64 =
 			ktime_to_timespec64(fence->timestamp);
 
diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c
index 2321035f6204..95f259b719fc 100644
--- a/drivers/dma-buf/sync_file.c
+++ b/drivers/dma-buf/sync_file.c
@@ -375,7 +375,13 @@ static void sync_fill_fence_info(struct dma_fence *fence,
 		sizeof(info->driver_name));
 
 	info->status = dma_fence_get_status(fence);
-	info->timestamp_ns = ktime_to_ns(fence->timestamp);
+	while (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags) &&
+	       !test_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags))
+		cpu_relax();
+	info->timestamp_ns =
+		test_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags) ?
+		ktime_to_ns(fence->timestamp) :
+		ktime_set(0, 0);
 }
 
 static long sync_file_ioctl_fence_info(struct sync_file *sync_file,
diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h
index a5195a7d6f77..0a186c4f3981 100644
--- a/include/linux/dma-fence.h
+++ b/include/linux/dma-fence.h
@@ -55,6 +55,7 @@ struct dma_fence_cb;
  * of the time.
  *
  * DMA_FENCE_FLAG_SIGNALED_BIT - fence is already signaled
+ * DMA_FENCE_FLAG_TIMESTAMP_BIT - timestamp recorded for fence signaling
  * DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT - enable_signaling might have been called
  * DMA_FENCE_FLAG_USER_BITS - start of the unused bits, can be used by the
  * implementer of the fence for its own purposes. Can be used in different
@@ -84,6 +85,7 @@ struct dma_fence {
 
 enum dma_fence_flag_bits {
 	DMA_FENCE_FLAG_SIGNALED_BIT,
+	DMA_FENCE_FLAG_TIMESTAMP_BIT,
 	DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT,
 	DMA_FENCE_FLAG_USER_BITS, /* must always be last member */
 };
-- 
cgit v1.2.3


From 9049f2f6e7bdfb5de0c63c2635bf3cdb70c4efb5 Mon Sep 17 00:00:00 2001
From: Akinobu Mita <akinobu.mita@gmail.com>
Date: Fri, 14 Jul 2017 14:49:52 -0700
Subject: fault-inject: parse as natural 1-based value for fail-nth write
 interface

The value written to fail-nth file is parsed as 0-based.  Parsing as
one-based is more natural to understand and it enables to cancel the
previous setup by simply writing '0'.

This change also converts task->fail_nth from signed to unsigned int.

Link: http://lkml.kernel.org/r/1491490561-10485-3-git-send-email-akinobu.mita@gmail.com
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/fault-injection/fault-injection.txt | 7 +++----
 fs/proc/base.c                                    | 9 ++++-----
 include/linux/sched.h                             | 2 +-
 3 files changed, 8 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/Documentation/fault-injection/fault-injection.txt b/Documentation/fault-injection/fault-injection.txt
index 192d8cbcc5f9..a32190508751 100644
--- a/Documentation/fault-injection/fault-injection.txt
+++ b/Documentation/fault-injection/fault-injection.txt
@@ -138,8 +138,8 @@ o proc entries
 
 - /proc/self/task/<current-tid>/fail-nth:
 
-	Write to this file of integer N makes N-th call in the current task fail
-	(N is 0-based). Read from this file returns a single char 'Y' or 'N'
+	Write to this file of integer N makes N-th call in the task fail.
+	Read from this file returns a single char 'Y' or 'N'
 	that says if the fault setup with a previous write to this file was
 	injected or not, and disables the fault if it wasn't yet injected.
 	Note that this file enables all types of faults (slab, futex, etc).
@@ -320,7 +320,7 @@ int main()
 	system("echo N > /sys/kernel/debug/failslab/ignore-gfp-wait");
 	sprintf(buf, "/proc/self/task/%ld/fail-nth", syscall(SYS_gettid));
 	fail_nth = open(buf, O_RDWR);
-	for (i = 0;; i++) {
+	for (i = 1;; i++) {
 		sprintf(buf, "%d", i);
 		write(fail_nth, buf, strlen(buf));
 		res = socketpair(AF_LOCAL, SOCK_STREAM, 0, fds);
@@ -339,7 +339,6 @@ int main()
 
 An example output:
 
-0-th fault Y: res=-1/23
 1-th fault Y: res=-1/23
 2-th fault Y: res=-1/23
 3-th fault Y: res=-1/12
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 5d93512beea1..c1fdaecb8d23 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1360,7 +1360,8 @@ static ssize_t proc_fail_nth_write(struct file *file, const char __user *buf,
 				   size_t count, loff_t *ppos)
 {
 	struct task_struct *task;
-	int err, n;
+	int err;
+	unsigned int n;
 
 	task = get_proc_task(file_inode(file));
 	if (!task)
@@ -1368,12 +1369,10 @@ static ssize_t proc_fail_nth_write(struct file *file, const char __user *buf,
 	put_task_struct(task);
 	if (task != current)
 		return -EPERM;
-	err = kstrtoint_from_user(buf, count, 0, &n);
+	err = kstrtouint_from_user(buf, count, 0, &n);
 	if (err)
 		return err;
-	if (n < 0 || n == INT_MAX)
-		return -EINVAL;
-	current->fail_nth = n + 1;
+	current->fail_nth = n;
 	return count;
 }
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 3822d749fc9e..2ba9ec93423f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -974,7 +974,7 @@ struct task_struct {
 
 #ifdef CONFIG_FAULT_INJECTION
 	int				make_it_fail;
-	int fail_nth;
+	unsigned int			fail_nth;
 #endif
 	/*
 	 * When (nr_dirtied >= nr_dirtied_pause), it's time to call
-- 
cgit v1.2.3


From 077d2ba519b2e8bf1abd80cbade699b1de42cafe Mon Sep 17 00:00:00 2001
From: Daniel Micay <danielmicay@gmail.com>
Date: Fri, 14 Jul 2017 17:28:12 -0400
Subject: replace incorrect strscpy use in FORTIFY_SOURCE

Using strscpy was wrong because FORTIFY_SOURCE is passing the maximum
possible size of the outermost object, but strscpy defines the count
parameter as the exact buffer size, so this could copy past the end of
the source.  This would still be wrong with the planned usage of
__builtin_object_size(p, 1) for intra-object overflow checks since it's
the maximum possible size of the specified object with no guarantee of
it being that large.

Reuse of the fortified functions like this currently makes the runtime
error reporting less precise but that can be improved later on.

Noticed by Dave Jones and KASAN.

Signed-off-by: Daniel Micay <danielmicay@gmail.com>
Acked-by: Kees Cook <keescook@chromium.org>
Reported-by: Dave Jones <davej@codemonkey.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/string.h | 23 ++++++++++++-----------
 1 file changed, 12 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/string.h b/include/linux/string.h
index 96f5a5fd0377..049866760e8b 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -202,17 +202,6 @@ void __read_overflow2(void) __compiletime_error("detected read beyond size of ob
 void __write_overflow(void) __compiletime_error("detected write beyond size of object passed as 1st parameter");
 
 #if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE)
-__FORTIFY_INLINE char *strcpy(char *p, const char *q)
-{
-	size_t p_size = __builtin_object_size(p, 0);
-	size_t q_size = __builtin_object_size(q, 0);
-	if (p_size == (size_t)-1 && q_size == (size_t)-1)
-		return __builtin_strcpy(p, q);
-	if (strscpy(p, q, p_size < q_size ? p_size : q_size) < 0)
-		fortify_panic(__func__);
-	return p;
-}
-
 __FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size)
 {
 	size_t p_size = __builtin_object_size(p, 0);
@@ -391,6 +380,18 @@ __FORTIFY_INLINE void *kmemdup(const void *p, size_t size, gfp_t gfp)
 		fortify_panic(__func__);
 	return __real_kmemdup(p, size, gfp);
 }
+
+/* defined after fortified strlen and memcpy to reuse them */
+__FORTIFY_INLINE char *strcpy(char *p, const char *q)
+{
+	size_t p_size = __builtin_object_size(p, 0);
+	size_t q_size = __builtin_object_size(q, 0);
+	if (p_size == (size_t)-1 && q_size == (size_t)-1)
+		return __builtin_strcpy(p, q);
+	memcpy(p, q, strlen(q) + 1);
+	return p;
+}
+
 #endif
 
 #endif /* _LINUX_STRING_H_ */
-- 
cgit v1.2.3


From b1f5bfc27a19f214006b9b4db7b9126df2dfdf5a Mon Sep 17 00:00:00 2001
From: Alexander Potapenko <glider@google.com>
Date: Fri, 14 Jul 2017 18:32:45 +0200
Subject: sctp: don't dereference ptr before leaving _sctp_walk_{params,
 errors}()

If the length field of the iterator (|pos.p| or |err|) is past the end
of the chunk, we shouldn't access it.

This bug has been detected by KMSAN. For the following pair of system
calls:

  socket(PF_INET6, SOCK_STREAM, 0x84 /* IPPROTO_??? */) = 3
  sendto(3, "A", 1, MSG_OOB, {sa_family=AF_INET6, sin6_port=htons(0),
         inet_pton(AF_INET6, "::1", &sin6_addr), sin6_flowinfo=0,
         sin6_scope_id=0}, 28) = 1

the tool has reported a use of uninitialized memory:

  ==================================================================
  BUG: KMSAN: use of uninitialized memory in sctp_rcv+0x17b8/0x43b0
  CPU: 1 PID: 2940 Comm: probe Not tainted 4.11.0-rc5+ #2926
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs
  01/01/2011
  Call Trace:
   <IRQ>
   __dump_stack lib/dump_stack.c:16
   dump_stack+0x172/0x1c0 lib/dump_stack.c:52
   kmsan_report+0x12a/0x180 mm/kmsan/kmsan.c:927
   __msan_warning_32+0x61/0xb0 mm/kmsan/kmsan_instr.c:469
   __sctp_rcv_init_lookup net/sctp/input.c:1074
   __sctp_rcv_lookup_harder net/sctp/input.c:1233
   __sctp_rcv_lookup net/sctp/input.c:1255
   sctp_rcv+0x17b8/0x43b0 net/sctp/input.c:170
   sctp6_rcv+0x32/0x70 net/sctp/ipv6.c:984
   ip6_input_finish+0x82f/0x1ee0 net/ipv6/ip6_input.c:279
   NF_HOOK ./include/linux/netfilter.h:257
   ip6_input+0x239/0x290 net/ipv6/ip6_input.c:322
   dst_input ./include/net/dst.h:492
   ip6_rcv_finish net/ipv6/ip6_input.c:69
   NF_HOOK ./include/linux/netfilter.h:257
   ipv6_rcv+0x1dbd/0x22e0 net/ipv6/ip6_input.c:203
   __netif_receive_skb_core+0x2f6f/0x3a20 net/core/dev.c:4208
   __netif_receive_skb net/core/dev.c:4246
   process_backlog+0x667/0xba0 net/core/dev.c:4866
   napi_poll net/core/dev.c:5268
   net_rx_action+0xc95/0x1590 net/core/dev.c:5333
   __do_softirq+0x485/0x942 kernel/softirq.c:284
   do_softirq_own_stack+0x1c/0x30 arch/x86/entry/entry_64.S:902
   </IRQ>
   do_softirq kernel/softirq.c:328
   __local_bh_enable_ip+0x25b/0x290 kernel/softirq.c:181
   local_bh_enable+0x37/0x40 ./include/linux/bottom_half.h:31
   rcu_read_unlock_bh ./include/linux/rcupdate.h:931
   ip6_finish_output2+0x19b2/0x1cf0 net/ipv6/ip6_output.c:124
   ip6_finish_output+0x764/0x970 net/ipv6/ip6_output.c:149
   NF_HOOK_COND ./include/linux/netfilter.h:246
   ip6_output+0x456/0x520 net/ipv6/ip6_output.c:163
   dst_output ./include/net/dst.h:486
   NF_HOOK ./include/linux/netfilter.h:257
   ip6_xmit+0x1841/0x1c00 net/ipv6/ip6_output.c:261
   sctp_v6_xmit+0x3b7/0x470 net/sctp/ipv6.c:225
   sctp_packet_transmit+0x38cb/0x3a20 net/sctp/output.c:632
   sctp_outq_flush+0xeb3/0x46e0 net/sctp/outqueue.c:885
   sctp_outq_uncork+0xb2/0xd0 net/sctp/outqueue.c:750
   sctp_side_effects net/sctp/sm_sideeffect.c:1773
   sctp_do_sm+0x6962/0x6ec0 net/sctp/sm_sideeffect.c:1147
   sctp_primitive_ASSOCIATE+0x12c/0x160 net/sctp/primitive.c:88
   sctp_sendmsg+0x43e5/0x4f90 net/sctp/socket.c:1954
   inet_sendmsg+0x498/0x670 net/ipv4/af_inet.c:762
   sock_sendmsg_nosec net/socket.c:633
   sock_sendmsg net/socket.c:643
   SYSC_sendto+0x608/0x710 net/socket.c:1696
   SyS_sendto+0x8a/0xb0 net/socket.c:1664
   do_syscall_64+0xe6/0x130 arch/x86/entry/common.c:285
   entry_SYSCALL64_slow_path+0x25/0x25 arch/x86/entry/entry_64.S:246
  RIP: 0033:0x401133
  RSP: 002b:00007fff6d99cd38 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
  RAX: ffffffffffffffda RBX: 00000000004002b0 RCX: 0000000000401133
  RDX: 0000000000000001 RSI: 0000000000494088 RDI: 0000000000000003
  RBP: 00007fff6d99cd90 R08: 00007fff6d99cd50 R09: 000000000000001c
  R10: 0000000000000001 R11: 0000000000000246 R12: 0000000000000000
  R13: 00000000004063d0 R14: 0000000000406460 R15: 0000000000000000
  origin:
   save_stack_trace+0x37/0x40 arch/x86/kernel/stacktrace.c:59
   kmsan_save_stack_with_flags mm/kmsan/kmsan.c:302
   kmsan_internal_poison_shadow+0xb1/0x1a0 mm/kmsan/kmsan.c:198
   kmsan_poison_shadow+0x6d/0xc0 mm/kmsan/kmsan.c:211
   slab_alloc_node mm/slub.c:2743
   __kmalloc_node_track_caller+0x200/0x360 mm/slub.c:4351
   __kmalloc_reserve net/core/skbuff.c:138
   __alloc_skb+0x26b/0x840 net/core/skbuff.c:231
   alloc_skb ./include/linux/skbuff.h:933
   sctp_packet_transmit+0x31e/0x3a20 net/sctp/output.c:570
   sctp_outq_flush+0xeb3/0x46e0 net/sctp/outqueue.c:885
   sctp_outq_uncork+0xb2/0xd0 net/sctp/outqueue.c:750
   sctp_side_effects net/sctp/sm_sideeffect.c:1773
   sctp_do_sm+0x6962/0x6ec0 net/sctp/sm_sideeffect.c:1147
   sctp_primitive_ASSOCIATE+0x12c/0x160 net/sctp/primitive.c:88
   sctp_sendmsg+0x43e5/0x4f90 net/sctp/socket.c:1954
   inet_sendmsg+0x498/0x670 net/ipv4/af_inet.c:762
   sock_sendmsg_nosec net/socket.c:633
   sock_sendmsg net/socket.c:643
   SYSC_sendto+0x608/0x710 net/socket.c:1696
   SyS_sendto+0x8a/0xb0 net/socket.c:1664
   do_syscall_64+0xe6/0x130 arch/x86/entry/common.c:285
   return_from_SYSCALL_64+0x0/0x6a arch/x86/entry/entry_64.S:246
  ==================================================================

Signed-off-by: Alexander Potapenko <glider@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/sctp.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index a9519a06a23b..980807d7506f 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -469,6 +469,8 @@ _sctp_walk_params((pos), (chunk), ntohs((chunk)->chunk_hdr.length), member)
 
 #define _sctp_walk_params(pos, chunk, end, member)\
 for (pos.v = chunk->member;\
+     (pos.v + offsetof(struct sctp_paramhdr, length) + sizeof(pos.p->length) <\
+      (void *)chunk + end) &&\
      pos.v <= (void *)chunk + end - ntohs(pos.p->length) &&\
      ntohs(pos.p->length) >= sizeof(struct sctp_paramhdr);\
      pos.v += SCTP_PAD4(ntohs(pos.p->length)))
@@ -479,6 +481,8 @@ _sctp_walk_errors((err), (chunk_hdr), ntohs((chunk_hdr)->length))
 #define _sctp_walk_errors(err, chunk_hdr, end)\
 for (err = (sctp_errhdr_t *)((void *)chunk_hdr + \
 	    sizeof(struct sctp_chunkhdr));\
+     ((void *)err + offsetof(sctp_errhdr_t, length) + sizeof(err->length) <\
+      (void *)chunk_hdr + end) &&\
      (void *)err <= (void *)chunk_hdr + end - ntohs(err->length) &&\
      ntohs(err->length) >= sizeof(sctp_errhdr_t); \
      err = (sctp_errhdr_t *)((void *)err + SCTP_PAD4(ntohs(err->length))))
-- 
cgit v1.2.3


From e67ae2b7b23b283e657865b498b151e6a17b919d Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 10 Jul 2017 13:17:26 +0200
Subject: libceph: fix old style declaration warnings

The new macros don't follow the usual style for declarations,
which we get a warning for with 'make W=1':

In file included from fs/ceph/mds_client.c:16:0:
include/linux/ceph/ceph_features.h:74:1: error: 'static' is not at beginning of declaration [-Werror=old-style-declaration]

This moves the 'static' keyword to the front of the
declaration.

Fixes: f179d3ba8cb9 ("libceph: new features macros")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/ceph_features.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h
index f0f6c537b64c..040dd105c3e7 100644
--- a/include/linux/ceph/ceph_features.h
+++ b/include/linux/ceph/ceph_features.h
@@ -10,14 +10,14 @@
 #define CEPH_FEATURE_INCARNATION_2 (1ull<<57) // CEPH_FEATURE_SERVER_JEWEL
 
 #define DEFINE_CEPH_FEATURE(bit, incarnation, name)			\
-	const static uint64_t CEPH_FEATURE_##name = (1ULL<<bit);		\
-	const static uint64_t CEPH_FEATUREMASK_##name =			\
+	static const uint64_t CEPH_FEATURE_##name = (1ULL<<bit);		\
+	static const uint64_t CEPH_FEATUREMASK_##name =			\
 		(1ULL<<bit | CEPH_FEATURE_INCARNATION_##incarnation);
 
 /* this bit is ignored but still advertised by release *when* */
 #define DEFINE_CEPH_FEATURE_DEPRECATED(bit, incarnation, name, when) \
-	const static uint64_t DEPRECATED_CEPH_FEATURE_##name = (1ULL<<bit); \
-	const static uint64_t DEPRECATED_CEPH_FEATUREMASK_##name =		\
+	static const uint64_t DEPRECATED_CEPH_FEATURE_##name = (1ULL<<bit); \
+	static const uint64_t DEPRECATED_CEPH_FEATUREMASK_##name =		\
 		(1ULL<<bit | CEPH_FEATURE_INCARNATION_##incarnation);
 
 /*
-- 
cgit v1.2.3


From cf56c2f892a8a1870a8358114ad896772da7543a Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 6 Jul 2017 23:17:44 +0200
Subject: netfilter: remove old pre-netns era hook api

no more users in the tree, remove this.

The old api is racy wrt. module removal, all users have been converted
to the netns-aware api.

The old api pretended we still have global hooks but that has not been
true for a long time.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter.h |   9 ---
 net/netfilter/core.c      | 143 ----------------------------------------------
 2 files changed, 152 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index a4b97be30b28..22f081065d49 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -61,8 +61,6 @@ typedef unsigned int nf_hookfn(void *priv,
 			       struct sk_buff *skb,
 			       const struct nf_hook_state *state);
 struct nf_hook_ops {
-	struct list_head	list;
-
 	/* User fills in from here down. */
 	nf_hookfn		*hook;
 	struct net_device	*dev;
@@ -160,13 +158,6 @@ int nf_register_net_hooks(struct net *net, const struct nf_hook_ops *reg,
 void nf_unregister_net_hooks(struct net *net, const struct nf_hook_ops *reg,
 			     unsigned int n);
 
-int nf_register_hook(struct nf_hook_ops *reg);
-void nf_unregister_hook(struct nf_hook_ops *reg);
-int nf_register_hooks(struct nf_hook_ops *reg, unsigned int n);
-void nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n);
-int _nf_register_hooks(struct nf_hook_ops *reg, unsigned int n);
-void _nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n);
-
 /* Functions to register get/setsockopt ranges (non-inclusive).  You
    need to check permissions yourself! */
 int nf_register_sockopt(struct nf_sockopt_ops *reg);
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 552d606e57ca..368610dbc3c0 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -227,114 +227,6 @@ void nf_unregister_net_hooks(struct net *net, const struct nf_hook_ops *reg,
 }
 EXPORT_SYMBOL(nf_unregister_net_hooks);
 
-static LIST_HEAD(nf_hook_list);
-
-static int _nf_register_hook(struct nf_hook_ops *reg)
-{
-	struct net *net, *last;
-	int ret;
-
-	for_each_net(net) {
-		ret = nf_register_net_hook(net, reg);
-		if (ret && ret != -ENOENT)
-			goto rollback;
-	}
-	list_add_tail(&reg->list, &nf_hook_list);
-
-	return 0;
-rollback:
-	last = net;
-	for_each_net(net) {
-		if (net == last)
-			break;
-		nf_unregister_net_hook(net, reg);
-	}
-	return ret;
-}
-
-int nf_register_hook(struct nf_hook_ops *reg)
-{
-	int ret;
-
-	rtnl_lock();
-	ret = _nf_register_hook(reg);
-	rtnl_unlock();
-
-	return ret;
-}
-EXPORT_SYMBOL(nf_register_hook);
-
-static void _nf_unregister_hook(struct nf_hook_ops *reg)
-{
-	struct net *net;
-
-	list_del(&reg->list);
-	for_each_net(net)
-		nf_unregister_net_hook(net, reg);
-}
-
-void nf_unregister_hook(struct nf_hook_ops *reg)
-{
-	rtnl_lock();
-	_nf_unregister_hook(reg);
-	rtnl_unlock();
-}
-EXPORT_SYMBOL(nf_unregister_hook);
-
-int nf_register_hooks(struct nf_hook_ops *reg, unsigned int n)
-{
-	unsigned int i;
-	int err = 0;
-
-	for (i = 0; i < n; i++) {
-		err = nf_register_hook(&reg[i]);
-		if (err)
-			goto err;
-	}
-	return err;
-
-err:
-	if (i > 0)
-		nf_unregister_hooks(reg, i);
-	return err;
-}
-EXPORT_SYMBOL(nf_register_hooks);
-
-/* Caller MUST take rtnl_lock() */
-int _nf_register_hooks(struct nf_hook_ops *reg, unsigned int n)
-{
-	unsigned int i;
-	int err = 0;
-
-	for (i = 0; i < n; i++) {
-		err = _nf_register_hook(&reg[i]);
-		if (err)
-			goto err;
-	}
-	return err;
-
-err:
-	if (i > 0)
-		_nf_unregister_hooks(reg, i);
-	return err;
-}
-EXPORT_SYMBOL(_nf_register_hooks);
-
-void nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n)
-{
-	while (n-- > 0)
-		nf_unregister_hook(&reg[n]);
-}
-EXPORT_SYMBOL(nf_unregister_hooks);
-
-/* Caller MUST take rtnl_lock */
-void _nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n)
-{
-	while (n-- > 0)
-		_nf_unregister_hook(&reg[n]);
-}
-EXPORT_SYMBOL(_nf_unregister_hooks);
-
 /* Returns 1 if okfn() needs to be executed by the caller,
  * -EPERM for NF_DROP, 0 otherwise.  Caller must hold rcu_read_lock. */
 int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state,
@@ -450,37 +342,6 @@ void (*nf_nat_decode_session_hook)(struct sk_buff *, struct flowi *);
 EXPORT_SYMBOL(nf_nat_decode_session_hook);
 #endif
 
-static int nf_register_hook_list(struct net *net)
-{
-	struct nf_hook_ops *elem;
-	int ret;
-
-	rtnl_lock();
-	list_for_each_entry(elem, &nf_hook_list, list) {
-		ret = nf_register_net_hook(net, elem);
-		if (ret && ret != -ENOENT)
-			goto out_undo;
-	}
-	rtnl_unlock();
-	return 0;
-
-out_undo:
-	list_for_each_entry_continue_reverse(elem, &nf_hook_list, list)
-		nf_unregister_net_hook(net, elem);
-	rtnl_unlock();
-	return ret;
-}
-
-static void nf_unregister_hook_list(struct net *net)
-{
-	struct nf_hook_ops *elem;
-
-	rtnl_lock();
-	list_for_each_entry(elem, &nf_hook_list, list)
-		nf_unregister_net_hook(net, elem);
-	rtnl_unlock();
-}
-
 static int __net_init netfilter_net_init(struct net *net)
 {
 	int i, h, ret;
@@ -500,16 +361,12 @@ static int __net_init netfilter_net_init(struct net *net)
 		return -ENOMEM;
 	}
 #endif
-	ret = nf_register_hook_list(net);
-	if (ret)
-		remove_proc_entry("netfilter", net->proc_net);
 
 	return ret;
 }
 
 static void __net_exit netfilter_net_exit(struct net *net)
 {
-	nf_unregister_hook_list(net);
 	remove_proc_entry("netfilter", net->proc_net);
 }
 
-- 
cgit v1.2.3


From c6325179238f1d4683edbec53d8322575d76d7e2 Mon Sep 17 00:00:00 2001
From: Gleb Fotengauer-Malinovskiy <glebfm@altlinux.org>
Date: Mon, 17 Jul 2017 16:29:46 +0300
Subject: tty: Fix TIOCGPTPEER ioctl definition

This ioctl does nothing to justify an _IOC_READ or _IOC_WRITE flag
because it doesn't copy anything from/to userspace to access the
argument.

Fixes: 54ebbfb16034 ("tty: add TIOCGPTPEER ioctl")
Signed-off-by: Gleb Fotengauer-Malinovskiy <glebfm@altlinux.org>
Acked-by: Aleksa Sarai <asarai@suse.de>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/alpha/include/uapi/asm/ioctls.h   | 2 +-
 arch/mips/include/uapi/asm/ioctls.h    | 2 +-
 arch/parisc/include/uapi/asm/ioctls.h  | 2 +-
 arch/powerpc/include/uapi/asm/ioctls.h | 2 +-
 arch/sh/include/uapi/asm/ioctls.h      | 2 +-
 arch/sparc/include/uapi/asm/ioctls.h   | 2 +-
 arch/xtensa/include/uapi/asm/ioctls.h  | 2 +-
 include/uapi/asm-generic/ioctls.h      | 2 +-
 8 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/include/uapi/asm/ioctls.h b/arch/alpha/include/uapi/asm/ioctls.h
index ff67b8373bf7..1cd7dc7d4870 100644
--- a/arch/alpha/include/uapi/asm/ioctls.h
+++ b/arch/alpha/include/uapi/asm/ioctls.h
@@ -100,7 +100,7 @@
 #define TIOCGPKT	_IOR('T', 0x38, int) /* Get packet mode state */
 #define TIOCGPTLCK	_IOR('T', 0x39, int) /* Get Pty lock state */
 #define TIOCGEXCL	_IOR('T', 0x40, int) /* Get exclusive mode state */
-#define TIOCGPTPEER	_IOR('T', 0x41, int) /* Safely open the slave */
+#define TIOCGPTPEER	_IO('T', 0x41) /* Safely open the slave */
 
 #define TIOCSERCONFIG	0x5453
 #define TIOCSERGWILD	0x5454
diff --git a/arch/mips/include/uapi/asm/ioctls.h b/arch/mips/include/uapi/asm/ioctls.h
index 68e19b689a00..1609cb0907ac 100644
--- a/arch/mips/include/uapi/asm/ioctls.h
+++ b/arch/mips/include/uapi/asm/ioctls.h
@@ -91,7 +91,7 @@
 #define TIOCGPKT	_IOR('T', 0x38, int) /* Get packet mode state */
 #define TIOCGPTLCK	_IOR('T', 0x39, int) /* Get Pty lock state */
 #define TIOCGEXCL	_IOR('T', 0x40, int) /* Get exclusive mode state */
-#define TIOCGPTPEER	_IOR('T', 0x41, int) /* Safely open the slave */
+#define TIOCGPTPEER	_IO('T', 0x41) /* Safely open the slave */
 
 /* I hope the range from 0x5480 on is free ... */
 #define TIOCSCTTY	0x5480		/* become controlling tty */
diff --git a/arch/parisc/include/uapi/asm/ioctls.h b/arch/parisc/include/uapi/asm/ioctls.h
index 674c68a5bbd0..d0e3321403be 100644
--- a/arch/parisc/include/uapi/asm/ioctls.h
+++ b/arch/parisc/include/uapi/asm/ioctls.h
@@ -60,7 +60,7 @@
 #define TIOCGPKT	_IOR('T', 0x38, int) /* Get packet mode state */
 #define TIOCGPTLCK	_IOR('T', 0x39, int) /* Get Pty lock state */
 #define TIOCGEXCL	_IOR('T', 0x40, int) /* Get exclusive mode state */
-#define TIOCGPTPEER	_IOR('T', 0x41, int) /* Safely open the slave */
+#define TIOCGPTPEER	_IO('T', 0x41) /* Safely open the slave */
 
 #define FIONCLEX	0x5450  /* these numbers need to be adjusted. */
 #define FIOCLEX		0x5451
diff --git a/arch/powerpc/include/uapi/asm/ioctls.h b/arch/powerpc/include/uapi/asm/ioctls.h
index bfd609a3e928..e3b10469f787 100644
--- a/arch/powerpc/include/uapi/asm/ioctls.h
+++ b/arch/powerpc/include/uapi/asm/ioctls.h
@@ -100,7 +100,7 @@
 #define TIOCGPKT	_IOR('T', 0x38, int) /* Get packet mode state */
 #define TIOCGPTLCK	_IOR('T', 0x39, int) /* Get Pty lock state */
 #define TIOCGEXCL	_IOR('T', 0x40, int) /* Get exclusive mode state */
-#define TIOCGPTPEER	_IOR('T', 0x41, int) /* Safely open the slave */
+#define TIOCGPTPEER	_IO('T', 0x41) /* Safely open the slave */
 
 #define TIOCSERCONFIG	0x5453
 #define TIOCSERGWILD	0x5454
diff --git a/arch/sh/include/uapi/asm/ioctls.h b/arch/sh/include/uapi/asm/ioctls.h
index eec7901e9e65..787bac9f67da 100644
--- a/arch/sh/include/uapi/asm/ioctls.h
+++ b/arch/sh/include/uapi/asm/ioctls.h
@@ -93,7 +93,7 @@
 #define TIOCGPKT	_IOR('T', 0x38, int) /* Get packet mode state */
 #define TIOCGPTLCK	_IOR('T', 0x39, int) /* Get Pty lock state */
 #define TIOCGEXCL	_IOR('T', 0x40, int) /* Get exclusive mode state */
-#define TIOCGPTPEER	_IOR('T', 0x41, int) /* Safely open the slave */
+#define TIOCGPTPEER	_IO('T', 0x41) /* Safely open the slave */
 
 #define TIOCSERCONFIG	_IO('T', 83) /* 0x5453 */
 #define TIOCSERGWILD	_IOR('T', 84,  int) /* 0x5454 */
diff --git a/arch/sparc/include/uapi/asm/ioctls.h b/arch/sparc/include/uapi/asm/ioctls.h
index 6d27398632ea..f5df72b93bb2 100644
--- a/arch/sparc/include/uapi/asm/ioctls.h
+++ b/arch/sparc/include/uapi/asm/ioctls.h
@@ -88,7 +88,7 @@
 #define TIOCGPTN	_IOR('t', 134, unsigned int) /* Get Pty Number */
 #define TIOCSPTLCK	_IOW('t', 135, int) /* Lock/unlock PTY */
 #define TIOCSIG		_IOW('t', 136, int) /* Generate signal on Pty slave */
-#define TIOCGPTPEER	_IOR('t', 137, int) /* Safely open the slave */
+#define TIOCGPTPEER	_IO('t', 137) /* Safely open the slave */
 
 /* Little f */
 #define FIOCLEX		_IO('f', 1)
diff --git a/arch/xtensa/include/uapi/asm/ioctls.h b/arch/xtensa/include/uapi/asm/ioctls.h
index 98b004e24e85..47d82c09be7b 100644
--- a/arch/xtensa/include/uapi/asm/ioctls.h
+++ b/arch/xtensa/include/uapi/asm/ioctls.h
@@ -105,7 +105,7 @@
 #define TIOCGPKT	_IOR('T', 0x38, int) /* Get packet mode state */
 #define TIOCGPTLCK	_IOR('T', 0x39, int) /* Get Pty lock state */
 #define TIOCGEXCL	_IOR('T', 0x40, int) /* Get exclusive mode state */
-#define TIOCGPTPEER	_IOR('T', 0x41, int) /* Safely open the slave */
+#define TIOCGPTPEER	_IO('T', 0x41) /* Safely open the slave */
 
 #define TIOCSERCONFIG	_IO('T', 83)
 #define TIOCSERGWILD	_IOR('T', 84,  int)
diff --git a/include/uapi/asm-generic/ioctls.h b/include/uapi/asm-generic/ioctls.h
index 06d5f7ddf84e..14baf9f23a14 100644
--- a/include/uapi/asm-generic/ioctls.h
+++ b/include/uapi/asm-generic/ioctls.h
@@ -77,7 +77,7 @@
 #define TIOCGPKT	_IOR('T', 0x38, int) /* Get packet mode state */
 #define TIOCGPTLCK	_IOR('T', 0x39, int) /* Get Pty lock state */
 #define TIOCGEXCL	_IOR('T', 0x40, int) /* Get exclusive mode state */
-#define TIOCGPTPEER	_IOR('T', 0x41, int) /* Safely open the slave */
+#define TIOCGPTPEER	_IO('T', 0x41) /* Safely open the slave */
 
 #define FIONCLEX	0x5450
 #define FIOCLEX		0x5451
-- 
cgit v1.2.3


From 13c401f33e19c20431d9888a91d9ea82e5133bd9 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 14 Jul 2017 23:03:49 -0700
Subject: jhash: fix -Wimplicit-fallthrough warnings

GCC 7 added a new -Wimplicit-fallthrough warning.  It's only enabled
with W=1, but since linux/jhash.h is included in over hundred places
(including other global headers) it seems worthwhile fixing this
warning.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/jhash.h | 29 ++++++++++++++---------------
 1 file changed, 14 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/jhash.h b/include/linux/jhash.h
index 348c6f47e4cc..8037850f3104 100644
--- a/include/linux/jhash.h
+++ b/include/linux/jhash.h
@@ -85,19 +85,18 @@ static inline u32 jhash(const void *key, u32 length, u32 initval)
 		k += 12;
 	}
 	/* Last block: affect all 32 bits of (c) */
-	/* All the case statements fall through */
 	switch (length) {
-	case 12: c += (u32)k[11]<<24;
-	case 11: c += (u32)k[10]<<16;
-	case 10: c += (u32)k[9]<<8;
-	case 9:  c += k[8];
-	case 8:  b += (u32)k[7]<<24;
-	case 7:  b += (u32)k[6]<<16;
-	case 6:  b += (u32)k[5]<<8;
-	case 5:  b += k[4];
-	case 4:  a += (u32)k[3]<<24;
-	case 3:  a += (u32)k[2]<<16;
-	case 2:  a += (u32)k[1]<<8;
+	case 12: c += (u32)k[11]<<24;	/* fall through */
+	case 11: c += (u32)k[10]<<16;	/* fall through */
+	case 10: c += (u32)k[9]<<8;	/* fall through */
+	case 9:  c += k[8];		/* fall through */
+	case 8:  b += (u32)k[7]<<24;	/* fall through */
+	case 7:  b += (u32)k[6]<<16;	/* fall through */
+	case 6:  b += (u32)k[5]<<8;	/* fall through */
+	case 5:  b += k[4];		/* fall through */
+	case 4:  a += (u32)k[3]<<24;	/* fall through */
+	case 3:  a += (u32)k[2]<<16;	/* fall through */
+	case 2:  a += (u32)k[1]<<8;	/* fall through */
 	case 1:  a += k[0];
 		 __jhash_final(a, b, c);
 	case 0: /* Nothing left to add */
@@ -131,10 +130,10 @@ static inline u32 jhash2(const u32 *k, u32 length, u32 initval)
 		k += 3;
 	}
 
-	/* Handle the last 3 u32's: all the case statements fall through */
+	/* Handle the last 3 u32's */
 	switch (length) {
-	case 3: c += k[2];
-	case 2: b += k[1];
+	case 3: c += k[2];	/* fall through */
+	case 2: b += k[1];	/* fall through */
 	case 1: a += k[0];
 		__jhash_final(a, b, c);
 	case 0:	/* Nothing left to add */
-- 
cgit v1.2.3


From df39a9f106d53532443a804352894480ca6ca5fd Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Mon, 17 Jul 2017 11:42:55 -0700
Subject: bpf: check NULL for sk_to_full_sk() return value

When req->rsk_listener is NULL, sk_to_full_sk() returns
NULL too, so we have to check its return value against
NULL here.

Fixes: 40304b2a1567 ("bpf: BPF support for sock_ops")
Reported-by: David Ahern <dsahern@gmail.com>
Tested-by: David Ahern <dsahern@gmail.com>
Cc: Lawrence Brakmo <brakmo@fb.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/bpf-cgroup.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 360c082e885c..d41d40ac3efd 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -85,7 +85,7 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
 	int __ret = 0;							       \
 	if (cgroup_bpf_enabled && (sock_ops)->sk) {	       \
 		typeof(sk) __sk = sk_to_full_sk((sock_ops)->sk);	       \
-		if (sk_fullsock(__sk))					       \
+		if (__sk && sk_fullsock(__sk))				       \
 			__ret = __cgroup_bpf_run_filter_sock_ops(__sk,	       \
 								 sock_ops,     \
 							 BPF_CGROUP_SOCK_OPS); \
-- 
cgit v1.2.3


From a512c2fbef9c700ee1ee0e045b75e140fef8f5ee Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@mellanox.com>
Date: Tue, 23 May 2017 11:26:08 +0300
Subject: IB/core: Introduce modify QP operation with udata

This patch adds new function ib_modify_qp_with_udata so that
uverbs layer can avoid handling L2 mac address at verbs layer
and depend on the core layer to resolve the mac address consistently
for all required QPs.

Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Eli Cohen <eli@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/verbs.c | 32 ++++++++++++++++++++++++--------
 include/rdma/ib_verbs.h         | 16 ++++++++++++++++
 2 files changed, 40 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 644fa0d13f02..7f8fe443df46 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1276,20 +1276,36 @@ out:
 }
 EXPORT_SYMBOL(ib_resolve_eth_dmac);
 
-int ib_modify_qp(struct ib_qp *qp,
-		 struct ib_qp_attr *qp_attr,
-		 int qp_attr_mask)
+/**
+ * ib_modify_qp_with_udata - Modifies the attributes for the specified QP.
+ * @qp: The QP to modify.
+ * @attr: On input, specifies the QP attributes to modify.  On output,
+ *   the current values of selected QP attributes are returned.
+ * @attr_mask: A bit-mask used to specify which attributes of the QP
+ *   are being modified.
+ * @udata: pointer to user's input output buffer information
+ *   are being modified.
+ * It returns 0 on success and returns appropriate error code on error.
+ */
+int ib_modify_qp_with_udata(struct ib_qp *qp, struct ib_qp_attr *attr,
+			    int attr_mask, struct ib_udata *udata)
 {
+	int ret;
 
-	if (qp_attr_mask & IB_QP_AV) {
-		int ret;
-
-		ret = ib_resolve_eth_dmac(qp->device, &qp_attr->ah_attr);
+	if (attr_mask & IB_QP_AV) {
+		ret = ib_resolve_eth_dmac(qp->device, &attr->ah_attr);
 		if (ret)
 			return ret;
 	}
+	return ib_security_modify_qp(qp, attr, attr_mask, udata);
+}
+EXPORT_SYMBOL(ib_modify_qp_with_udata);
 
-	return ib_security_modify_qp(qp->real_qp, qp_attr, qp_attr_mask, NULL);
+int ib_modify_qp(struct ib_qp *qp,
+		 struct ib_qp_attr *qp_attr,
+		 int qp_attr_mask)
+{
+	return ib_modify_qp_with_udata(qp, qp_attr, qp_attr_mask, NULL);
 }
 EXPORT_SYMBOL(ib_modify_qp);
 
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 356953d3dbd1..6e62c9e2c971 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2947,6 +2947,22 @@ static inline int ib_post_srq_recv(struct ib_srq *srq,
 struct ib_qp *ib_create_qp(struct ib_pd *pd,
 			   struct ib_qp_init_attr *qp_init_attr);
 
+/**
+ * ib_modify_qp_with_udata - Modifies the attributes for the specified QP.
+ * @qp: The QP to modify.
+ * @attr: On input, specifies the QP attributes to modify.  On output,
+ *   the current values of selected QP attributes are returned.
+ * @attr_mask: A bit-mask used to specify which attributes of the QP
+ *   are being modified.
+ * @udata: pointer to user's input output buffer information
+ *   are being modified.
+ * It returns 0 on success and returns appropriate error code on error.
+ */
+int ib_modify_qp_with_udata(struct ib_qp *qp,
+			    struct ib_qp_attr *attr,
+			    int attr_mask,
+			    struct ib_udata *udata);
+
 /**
  * ib_modify_qp - Modifies the attributes for the specified QP and then
  *   transitions the QP to the given state.
-- 
cgit v1.2.3


From 0f4d027c3b4240ecb314daa948238d459fdc3a00 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Tue, 23 May 2017 14:38:14 +0300
Subject: IB/{rdmavt, qib, hfi1}: Remove gfp flags argument

The caller to the driver marks GFP_NOIO allocations with help
of memalloc_noio-* calls now. This makes redundant to pass down
to the driver gfp flags, which can be GFP_KERNEL only.

The patch removes the gfp flags argument and updates all driver paths.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Acked-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/hw/hfi1/qp.c       |  7 +++--
 drivers/infiniband/hw/hfi1/qp.h       |  3 +--
 drivers/infiniband/hw/qib/qib_qp.c    | 15 +++++------
 drivers/infiniband/hw/qib/qib_verbs.h |  4 +--
 drivers/infiniband/sw/rdmavt/qp.c     | 48 ++++++++++-------------------------
 include/rdma/rdma_vt.h                |  5 ++--
 6 files changed, 28 insertions(+), 54 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/hfi1/qp.c b/drivers/infiniband/hw/hfi1/qp.c
index 650305cc0373..1a7af9f60c13 100644
--- a/drivers/infiniband/hw/hfi1/qp.c
+++ b/drivers/infiniband/hw/hfi1/qp.c
@@ -647,18 +647,17 @@ void qp_iter_print(struct seq_file *s, struct qp_iter *iter)
 		   qp->pid);
 }
 
-void *qp_priv_alloc(struct rvt_dev_info *rdi, struct rvt_qp *qp,
-		    gfp_t gfp)
+void *qp_priv_alloc(struct rvt_dev_info *rdi, struct rvt_qp *qp)
 {
 	struct hfi1_qp_priv *priv;
 
-	priv = kzalloc_node(sizeof(*priv), gfp, rdi->dparms.node);
+	priv = kzalloc_node(sizeof(*priv), GFP_KERNEL, rdi->dparms.node);
 	if (!priv)
 		return ERR_PTR(-ENOMEM);
 
 	priv->owner = qp;
 
-	priv->s_ahg = kzalloc_node(sizeof(*priv->s_ahg), gfp,
+	priv->s_ahg = kzalloc_node(sizeof(*priv->s_ahg), GFP_KERNEL,
 				   rdi->dparms.node);
 	if (!priv->s_ahg) {
 		kfree(priv);
diff --git a/drivers/infiniband/hw/hfi1/qp.h b/drivers/infiniband/hw/hfi1/qp.h
index 1eb9cd7b8c19..6fe542b6a927 100644
--- a/drivers/infiniband/hw/hfi1/qp.h
+++ b/drivers/infiniband/hw/hfi1/qp.h
@@ -123,8 +123,7 @@ void hfi1_migrate_qp(struct rvt_qp *qp);
 /*
  * Functions provided by hfi1 driver for rdmavt to use
  */
-void *qp_priv_alloc(struct rvt_dev_info *rdi, struct rvt_qp *qp,
-		    gfp_t gfp);
+void *qp_priv_alloc(struct rvt_dev_info *rdi, struct rvt_qp *qp);
 void qp_priv_free(struct rvt_dev_info *rdi, struct rvt_qp *qp);
 unsigned free_all_qps(struct rvt_dev_info *rdi);
 void notify_qp_reset(struct rvt_qp *qp);
diff --git a/drivers/infiniband/hw/qib/qib_qp.c b/drivers/infiniband/hw/qib/qib_qp.c
index 5984981e7dd4..a343e3b5d4cb 100644
--- a/drivers/infiniband/hw/qib/qib_qp.c
+++ b/drivers/infiniband/hw/qib/qib_qp.c
@@ -104,10 +104,9 @@ const struct rvt_operation_params qib_post_parms[RVT_OPERATION_MAX] = {
 
 };
 
-static void get_map_page(struct rvt_qpn_table *qpt, struct rvt_qpn_map *map,
-			 gfp_t gfp)
+static void get_map_page(struct rvt_qpn_table *qpt, struct rvt_qpn_map *map)
 {
-	unsigned long page = get_zeroed_page(gfp);
+	unsigned long page = get_zeroed_page(GFP_KERNEL);
 
 	/*
 	 * Free the page if someone raced with us installing it.
@@ -126,7 +125,7 @@ static void get_map_page(struct rvt_qpn_table *qpt, struct rvt_qpn_map *map,
  * zero/one for QP type IB_QPT_SMI/IB_QPT_GSI.
  */
 int qib_alloc_qpn(struct rvt_dev_info *rdi, struct rvt_qpn_table *qpt,
-		  enum ib_qp_type type, u8 port, gfp_t gfp)
+		  enum ib_qp_type type, u8 port)
 {
 	u32 i, offset, max_scan, qpn;
 	struct rvt_qpn_map *map;
@@ -160,7 +159,7 @@ int qib_alloc_qpn(struct rvt_dev_info *rdi, struct rvt_qpn_table *qpt,
 	max_scan = qpt->nmaps - !offset;
 	for (i = 0;;) {
 		if (unlikely(!map->page)) {
-			get_map_page(qpt, map, gfp);
+			get_map_page(qpt, map);
 			if (unlikely(!map->page))
 				break;
 		}
@@ -317,16 +316,16 @@ u32 qib_mtu_from_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp, u32 pmtu)
 	return ib_mtu_enum_to_int(pmtu);
 }
 
-void *qib_qp_priv_alloc(struct rvt_dev_info *rdi, struct rvt_qp *qp, gfp_t gfp)
+void *qib_qp_priv_alloc(struct rvt_dev_info *rdi, struct rvt_qp *qp)
 {
 	struct qib_qp_priv *priv;
 
-	priv = kzalloc(sizeof(*priv), gfp);
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return ERR_PTR(-ENOMEM);
 	priv->owner = qp;
 
-	priv->s_hdr = kzalloc(sizeof(*priv->s_hdr), gfp);
+	priv->s_hdr = kzalloc(sizeof(*priv->s_hdr), GFP_KERNEL);
 	if (!priv->s_hdr) {
 		kfree(priv);
 		return ERR_PTR(-ENOMEM);
diff --git a/drivers/infiniband/hw/qib/qib_verbs.h b/drivers/infiniband/hw/qib/qib_verbs.h
index da0db5485ddc..a52fc67b40d7 100644
--- a/drivers/infiniband/hw/qib/qib_verbs.h
+++ b/drivers/infiniband/hw/qib/qib_verbs.h
@@ -274,11 +274,11 @@ int qib_get_counters(struct qib_pportdata *ppd,
  * Functions provided by qib driver for rdmavt to use
  */
 unsigned qib_free_all_qps(struct rvt_dev_info *rdi);
-void *qib_qp_priv_alloc(struct rvt_dev_info *rdi, struct rvt_qp *qp, gfp_t gfp);
+void *qib_qp_priv_alloc(struct rvt_dev_info *rdi, struct rvt_qp *qp);
 void qib_qp_priv_free(struct rvt_dev_info *rdi, struct rvt_qp *qp);
 void qib_notify_qp_reset(struct rvt_qp *qp);
 int qib_alloc_qpn(struct rvt_dev_info *rdi, struct rvt_qpn_table *qpt,
-		  enum ib_qp_type type, u8 port, gfp_t gfp);
+		  enum ib_qp_type type, u8 port);
 void qib_restart_rc(struct rvt_qp *qp, u32 psn, int wait);
 #ifdef CONFIG_DEBUG_FS
 
diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c
index 727e81cc2c8f..459865439a0b 100644
--- a/drivers/infiniband/sw/rdmavt/qp.c
+++ b/drivers/infiniband/sw/rdmavt/qp.c
@@ -118,10 +118,9 @@ const int ib_rvt_state_ops[IB_QPS_ERR + 1] = {
 EXPORT_SYMBOL(ib_rvt_state_ops);
 
 static void get_map_page(struct rvt_qpn_table *qpt,
-			 struct rvt_qpn_map *map,
-			 gfp_t gfp)
+			 struct rvt_qpn_map *map)
 {
-	unsigned long page = get_zeroed_page(gfp);
+	unsigned long page = get_zeroed_page(GFP_KERNEL);
 
 	/*
 	 * Free the page if someone raced with us installing it.
@@ -173,7 +172,7 @@ static int init_qpn_table(struct rvt_dev_info *rdi, struct rvt_qpn_table *qpt)
 		    rdi->dparms.qpn_res_start, rdi->dparms.qpn_res_end);
 	for (i = rdi->dparms.qpn_res_start; i <= rdi->dparms.qpn_res_end; i++) {
 		if (!map->page) {
-			get_map_page(qpt, map, GFP_KERNEL);
+			get_map_page(qpt, map);
 			if (!map->page) {
 				ret = -ENOMEM;
 				break;
@@ -342,14 +341,14 @@ static inline unsigned mk_qpn(struct rvt_qpn_table *qpt,
  * Return: The queue pair number
  */
 static int alloc_qpn(struct rvt_dev_info *rdi, struct rvt_qpn_table *qpt,
-		     enum ib_qp_type type, u8 port_num, gfp_t gfp)
+		     enum ib_qp_type type, u8 port_num)
 {
 	u32 i, offset, max_scan, qpn;
 	struct rvt_qpn_map *map;
 	u32 ret;
 
 	if (rdi->driver_f.alloc_qpn)
-		return rdi->driver_f.alloc_qpn(rdi, qpt, type, port_num, gfp);
+		return rdi->driver_f.alloc_qpn(rdi, qpt, type, port_num);
 
 	if (type == IB_QPT_SMI || type == IB_QPT_GSI) {
 		unsigned n;
@@ -374,7 +373,7 @@ static int alloc_qpn(struct rvt_dev_info *rdi, struct rvt_qpn_table *qpt,
 	max_scan = qpt->nmaps - !offset;
 	for (i = 0;;) {
 		if (unlikely(!map->page)) {
-			get_map_page(qpt, map, gfp);
+			get_map_page(qpt, map);
 			if (unlikely(!map->page))
 				break;
 		}
@@ -672,7 +671,6 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd,
 	struct ib_qp *ret = ERR_PTR(-ENOMEM);
 	struct rvt_dev_info *rdi = ib_to_rvt(ibpd->device);
 	void *priv = NULL;
-	gfp_t gfp;
 	size_t sqsize;
 
 	if (!rdi)
@@ -680,18 +678,9 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd,
 
 	if (init_attr->cap.max_send_sge > rdi->dparms.props.max_sge ||
 	    init_attr->cap.max_send_wr > rdi->dparms.props.max_qp_wr ||
-	    init_attr->create_flags & ~(IB_QP_CREATE_USE_GFP_NOIO))
+	    init_attr->create_flags)
 		return ERR_PTR(-EINVAL);
 
-	/* GFP_NOIO is applicable to RC QP's only */
-
-	if (init_attr->create_flags & IB_QP_CREATE_USE_GFP_NOIO &&
-	    init_attr->qp_type != IB_QPT_RC)
-		return ERR_PTR(-EINVAL);
-
-	gfp = init_attr->create_flags & IB_QP_CREATE_USE_GFP_NOIO ?
-						GFP_NOIO : GFP_KERNEL;
-
 	/* Check receive queue parameters if no SRQ is specified. */
 	if (!init_attr->srq) {
 		if (init_attr->cap.max_recv_sge > rdi->dparms.props.max_sge ||
@@ -719,14 +708,7 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd,
 		sz = sizeof(struct rvt_sge) *
 			init_attr->cap.max_send_sge +
 			sizeof(struct rvt_swqe);
-		if (gfp == GFP_NOIO)
-			swq = __vmalloc(
-				sqsize * sz,
-				gfp | __GFP_ZERO, PAGE_KERNEL);
-		else
-			swq = vzalloc_node(
-				sqsize * sz,
-				rdi->dparms.node);
+		swq = vzalloc_node(sqsize * sz, rdi->dparms.node);
 		if (!swq)
 			return ERR_PTR(-ENOMEM);
 
@@ -741,7 +723,8 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd,
 		} else if (init_attr->cap.max_recv_sge > 1)
 			sg_list_sz = sizeof(*qp->r_sg_list) *
 				(init_attr->cap.max_recv_sge - 1);
-		qp = kzalloc_node(sz + sg_list_sz, gfp, rdi->dparms.node);
+		qp = kzalloc_node(sz + sg_list_sz, GFP_KERNEL,
+				  rdi->dparms.node);
 		if (!qp)
 			goto bail_swq;
 
@@ -751,7 +734,7 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd,
 				kzalloc_node(
 					sizeof(*qp->s_ack_queue) *
 					 rvt_max_atomic(rdi),
-					gfp,
+					GFP_KERNEL,
 					rdi->dparms.node);
 			if (!qp->s_ack_queue)
 				goto bail_qp;
@@ -766,7 +749,7 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd,
 		 * Driver needs to set up it's private QP structure and do any
 		 * initialization that is needed.
 		 */
-		priv = rdi->driver_f.qp_priv_alloc(rdi, qp, gfp);
+		priv = rdi->driver_f.qp_priv_alloc(rdi, qp);
 		if (IS_ERR(priv)) {
 			ret = priv;
 			goto bail_qp;
@@ -786,11 +769,6 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd,
 				qp->r_rq.wq = vmalloc_user(
 						sizeof(struct rvt_rwq) +
 						qp->r_rq.size * sz);
-			else if (gfp == GFP_NOIO)
-				qp->r_rq.wq = __vmalloc(
-						sizeof(struct rvt_rwq) +
-						qp->r_rq.size * sz,
-						gfp | __GFP_ZERO, PAGE_KERNEL);
 			else
 				qp->r_rq.wq = vzalloc_node(
 						sizeof(struct rvt_rwq) +
@@ -824,7 +802,7 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd,
 
 		err = alloc_qpn(rdi, &rdi->qp_dev->qpn_table,
 				init_attr->qp_type,
-				init_attr->port_num, gfp);
+				init_attr->port_num);
 		if (err < 0) {
 			ret = ERR_PTR(err);
 			goto bail_rq_wq;
diff --git a/include/rdma/rdma_vt.h b/include/rdma/rdma_vt.h
index 4878aaf7bdff..55af69271053 100644
--- a/include/rdma/rdma_vt.h
+++ b/include/rdma/rdma_vt.h
@@ -229,8 +229,7 @@ struct rvt_driver_provided {
 	 * ERR_PTR(err).  The driver is free to return NULL or a valid
 	 * pointer.
 	 */
-	void * (*qp_priv_alloc)(struct rvt_dev_info *rdi, struct rvt_qp *qp,
-				gfp_t gfp);
+	void * (*qp_priv_alloc)(struct rvt_dev_info *rdi, struct rvt_qp *qp);
 
 	/*
 	 * Free the driver's private qp structure.
@@ -319,7 +318,7 @@ struct rvt_driver_provided {
 
 	/* Let the driver pick the next queue pair number*/
 	int (*alloc_qpn)(struct rvt_dev_info *rdi, struct rvt_qpn_table *qpt,
-			 enum ib_qp_type type, u8 port_num, gfp_t gfp);
+			 enum ib_qp_type type, u8 port_num);
 
 	/* Determine if its safe or allowed to modify the qp */
 	int (*check_modify_qp)(struct rvt_qp *qp, struct ib_qp_attr *attr,
-- 
cgit v1.2.3


From 8900b894e769dd88b53e519e3502e0e3c349fe95 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Tue, 23 May 2017 14:38:15 +0300
Subject: {net, IB}/mlx4: Remove gfp flags argument

The caller to the driver marks GFP_NOIO allocations with help
of memalloc_noio-* calls now. This makes redundant to pass down
to the driver gfp flags, which can be GFP_KERNEL only.

The patch removes the gfp flags argument and updates all driver paths.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/hw/mlx4/cq.c                    |  6 ++--
 drivers/infiniband/hw/mlx4/mlx4_ib.h               |  1 -
 drivers/infiniband/hw/mlx4/qp.c                    | 40 +++++++++-------------
 drivers/infiniband/hw/mlx4/srq.c                   |  8 ++---
 drivers/net/ethernet/mellanox/mlx4/alloc.c         | 29 ++++++++--------
 drivers/net/ethernet/mellanox/mlx4/cq.c            |  4 +--
 drivers/net/ethernet/mellanox/mlx4/en_rx.c         |  7 ++--
 drivers/net/ethernet/mellanox/mlx4/en_tx.c         |  2 +-
 drivers/net/ethernet/mellanox/mlx4/icm.c           |  7 ++--
 drivers/net/ethernet/mellanox/mlx4/icm.h           |  3 +-
 drivers/net/ethernet/mellanox/mlx4/mlx4.h          |  4 +--
 drivers/net/ethernet/mellanox/mlx4/mr.c            | 17 +++++----
 drivers/net/ethernet/mellanox/mlx4/qp.c            | 20 +++++------
 .../net/ethernet/mellanox/mlx4/resource_tracker.c  |  4 +--
 drivers/net/ethernet/mellanox/mlx4/srq.c           |  4 +--
 include/linux/mlx4/device.h                        | 10 +++---
 16 files changed, 76 insertions(+), 90 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index 4f5a143fc0a7..ff931c580557 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -102,7 +102,7 @@ static int mlx4_ib_alloc_cq_buf(struct mlx4_ib_dev *dev, struct mlx4_ib_cq_buf *
 	int err;
 
 	err = mlx4_buf_alloc(dev->dev, nent * dev->dev->caps.cqe_size,
-			     PAGE_SIZE * 2, &buf->buf, GFP_KERNEL);
+			     PAGE_SIZE * 2, &buf->buf);
 
 	if (err)
 		goto out;
@@ -113,7 +113,7 @@ static int mlx4_ib_alloc_cq_buf(struct mlx4_ib_dev *dev, struct mlx4_ib_cq_buf *
 	if (err)
 		goto err_buf;
 
-	err = mlx4_buf_write_mtt(dev->dev, &buf->mtt, &buf->buf, GFP_KERNEL);
+	err = mlx4_buf_write_mtt(dev->dev, &buf->mtt, &buf->buf);
 	if (err)
 		goto err_mtt;
 
@@ -219,7 +219,7 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev,
 
 		uar = &to_mucontext(context)->uar;
 	} else {
-		err = mlx4_db_alloc(dev->dev, &cq->db, 1, GFP_KERNEL);
+		err = mlx4_db_alloc(dev->dev, &cq->db, 1);
 		if (err)
 			goto err_cq;
 
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index c2b9cbf4da05..9db82e67e959 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -185,7 +185,6 @@ enum mlx4_ib_qp_flags {
 	MLX4_IB_QP_LSO = IB_QP_CREATE_IPOIB_UD_LSO,
 	MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK = IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK,
 	MLX4_IB_QP_NETIF = IB_QP_CREATE_NETIF_QP,
-	MLX4_IB_QP_CREATE_USE_GFP_NOIO = IB_QP_CREATE_USE_GFP_NOIO,
 
 	/* Mellanox specific flags start from IB_QP_CREATE_RESERVED_START */
 	MLX4_IB_ROCE_V2_GSI_QP = MLX4_IB_QP_CREATE_ROCE_V2_GSI,
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 996e9058e515..75c0e6c5dd56 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -634,8 +634,8 @@ static void mlx4_ib_free_qp_counter(struct mlx4_ib_dev *dev,
 
 static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 			    struct ib_qp_init_attr *init_attr,
-			    struct ib_udata *udata, int sqpn, struct mlx4_ib_qp **caller_qp,
-			    gfp_t gfp)
+			    struct ib_udata *udata, int sqpn,
+			    struct mlx4_ib_qp **caller_qp)
 {
 	int qpn;
 	int err;
@@ -691,14 +691,14 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 		if (qp_type == MLX4_IB_QPT_SMI || qp_type == MLX4_IB_QPT_GSI ||
 		    (qp_type & (MLX4_IB_QPT_PROXY_SMI | MLX4_IB_QPT_PROXY_SMI_OWNER |
 				MLX4_IB_QPT_PROXY_GSI | MLX4_IB_QPT_TUN_SMI_OWNER))) {
-			sqp = kzalloc(sizeof (struct mlx4_ib_sqp), gfp);
+			sqp = kzalloc(sizeof(struct mlx4_ib_sqp), GFP_KERNEL);
 			if (!sqp)
 				return -ENOMEM;
 			qp = &sqp->qp;
 			qp->pri.vid = 0xFFFF;
 			qp->alt.vid = 0xFFFF;
 		} else {
-			qp = kzalloc(sizeof (struct mlx4_ib_qp), gfp);
+			qp = kzalloc(sizeof(struct mlx4_ib_qp), GFP_KERNEL);
 			if (!qp)
 				return -ENOMEM;
 			qp->pri.vid = 0xFFFF;
@@ -780,7 +780,7 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 			goto err;
 
 		if (qp_has_rq(init_attr)) {
-			err = mlx4_db_alloc(dev->dev, &qp->db, 0, gfp);
+			err = mlx4_db_alloc(dev->dev, &qp->db, 0);
 			if (err)
 				goto err;
 
@@ -788,7 +788,7 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 		}
 
 		if (mlx4_buf_alloc(dev->dev, qp->buf_size, qp->buf_size,
-				   &qp->buf, gfp)) {
+				   &qp->buf)) {
 			memcpy(&init_attr->cap, &backup_cap,
 			       sizeof(backup_cap));
 			err = set_kernel_sq_size(dev, &init_attr->cap, qp_type,
@@ -797,7 +797,7 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 				goto err_db;
 
 			if (mlx4_buf_alloc(dev->dev, qp->buf_size,
-					   PAGE_SIZE * 2, &qp->buf, gfp)) {
+					   PAGE_SIZE * 2, &qp->buf)) {
 				err = -ENOMEM;
 				goto err_db;
 			}
@@ -808,20 +808,20 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 		if (err)
 			goto err_buf;
 
-		err = mlx4_buf_write_mtt(dev->dev, &qp->mtt, &qp->buf, gfp);
+		err = mlx4_buf_write_mtt(dev->dev, &qp->mtt, &qp->buf);
 		if (err)
 			goto err_mtt;
 
 		qp->sq.wrid = kmalloc_array(qp->sq.wqe_cnt, sizeof(u64),
-					gfp | __GFP_NOWARN);
+					GFP_KERNEL | __GFP_NOWARN);
 		if (!qp->sq.wrid)
 			qp->sq.wrid = __vmalloc(qp->sq.wqe_cnt * sizeof(u64),
-						gfp, PAGE_KERNEL);
+						GFP_KERNEL, PAGE_KERNEL);
 		qp->rq.wrid = kmalloc_array(qp->rq.wqe_cnt, sizeof(u64),
-					gfp | __GFP_NOWARN);
+					GFP_KERNEL | __GFP_NOWARN);
 		if (!qp->rq.wrid)
 			qp->rq.wrid = __vmalloc(qp->rq.wqe_cnt * sizeof(u64),
-						gfp, PAGE_KERNEL);
+						GFP_KERNEL, PAGE_KERNEL);
 		if (!qp->sq.wrid || !qp->rq.wrid) {
 			err = -ENOMEM;
 			goto err_wrid;
@@ -859,7 +859,7 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 	if (init_attr->create_flags & IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK)
 		qp->flags |= MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK;
 
-	err = mlx4_qp_alloc(dev->dev, qpn, &qp->mqp, gfp);
+	err = mlx4_qp_alloc(dev->dev, qpn, &qp->mqp);
 	if (err)
 		goto err_qpn;
 
@@ -1127,10 +1127,7 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd,
 	int err;
 	int sup_u_create_flags = MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK;
 	u16 xrcdn = 0;
-	gfp_t gfp;
 
-	gfp = (init_attr->create_flags & MLX4_IB_QP_CREATE_USE_GFP_NOIO) ?
-		GFP_NOIO : GFP_KERNEL;
 	/*
 	 * We only support LSO, vendor flag1, and multicast loopback blocking,
 	 * and only for kernel UD QPs.
@@ -1140,8 +1137,7 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd,
 					MLX4_IB_SRIOV_TUNNEL_QP |
 					MLX4_IB_SRIOV_SQP |
 					MLX4_IB_QP_NETIF |
-					MLX4_IB_QP_CREATE_ROCE_V2_GSI |
-					MLX4_IB_QP_CREATE_USE_GFP_NOIO))
+					MLX4_IB_QP_CREATE_ROCE_V2_GSI))
 		return ERR_PTR(-EINVAL);
 
 	if (init_attr->create_flags & IB_QP_CREATE_NETIF_QP) {
@@ -1154,7 +1150,6 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd,
 			return ERR_PTR(-EINVAL);
 
 		if ((init_attr->create_flags & ~(MLX4_IB_SRIOV_SQP |
-						 MLX4_IB_QP_CREATE_USE_GFP_NOIO |
 						 MLX4_IB_QP_CREATE_ROCE_V2_GSI  |
 						 MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK) &&
 		     init_attr->qp_type != IB_QPT_UD) ||
@@ -1179,7 +1174,7 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd,
 	case IB_QPT_RC:
 	case IB_QPT_UC:
 	case IB_QPT_RAW_PACKET:
-		qp = kzalloc(sizeof *qp, gfp);
+		qp = kzalloc(sizeof(*qp), GFP_KERNEL);
 		if (!qp)
 			return ERR_PTR(-ENOMEM);
 		qp->pri.vid = 0xFFFF;
@@ -1188,7 +1183,7 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd,
 	case IB_QPT_UD:
 	{
 		err = create_qp_common(to_mdev(pd->device), pd, init_attr,
-				       udata, 0, &qp, gfp);
+				       udata, 0, &qp);
 		if (err) {
 			kfree(qp);
 			return ERR_PTR(err);
@@ -1217,8 +1212,7 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd,
 		}
 
 		err = create_qp_common(to_mdev(pd->device), pd, init_attr, udata,
-				       sqpn,
-				       &qp, gfp);
+				       sqpn, &qp);
 		if (err)
 			return ERR_PTR(err);
 
diff --git a/drivers/infiniband/hw/mlx4/srq.c b/drivers/infiniband/hw/mlx4/srq.c
index e32dd58937a8..0facaf5f6d23 100644
--- a/drivers/infiniband/hw/mlx4/srq.c
+++ b/drivers/infiniband/hw/mlx4/srq.c
@@ -135,14 +135,14 @@ struct ib_srq *mlx4_ib_create_srq(struct ib_pd *pd,
 		if (err)
 			goto err_mtt;
 	} else {
-		err = mlx4_db_alloc(dev->dev, &srq->db, 0, GFP_KERNEL);
+		err = mlx4_db_alloc(dev->dev, &srq->db, 0);
 		if (err)
 			goto err_srq;
 
 		*srq->db.db = 0;
 
-		if (mlx4_buf_alloc(dev->dev, buf_size, PAGE_SIZE * 2, &srq->buf,
-				   GFP_KERNEL)) {
+		if (mlx4_buf_alloc(dev->dev, buf_size, PAGE_SIZE * 2,
+				   &srq->buf)) {
 			err = -ENOMEM;
 			goto err_db;
 		}
@@ -167,7 +167,7 @@ struct ib_srq *mlx4_ib_create_srq(struct ib_pd *pd,
 		if (err)
 			goto err_buf;
 
-		err = mlx4_buf_write_mtt(dev->dev, &srq->mtt, &srq->buf, GFP_KERNEL);
+		err = mlx4_buf_write_mtt(dev->dev, &srq->mtt, &srq->buf);
 		if (err)
 			goto err_mtt;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/alloc.c b/drivers/net/ethernet/mellanox/mlx4/alloc.c
index 249a4584401a..d94b3744a5b9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/alloc.c
+++ b/drivers/net/ethernet/mellanox/mlx4/alloc.c
@@ -578,7 +578,7 @@ out:
 }
 
 static int mlx4_buf_direct_alloc(struct mlx4_dev *dev, int size,
-				 struct mlx4_buf *buf, gfp_t gfp)
+				 struct mlx4_buf *buf)
 {
 	dma_addr_t t;
 
@@ -587,7 +587,7 @@ static int mlx4_buf_direct_alloc(struct mlx4_dev *dev, int size,
 	buf->page_shift   = get_order(size) + PAGE_SHIFT;
 	buf->direct.buf   =
 		dma_zalloc_coherent(&dev->persist->pdev->dev,
-				    size, &t, gfp);
+				    size, &t, GFP_KERNEL);
 	if (!buf->direct.buf)
 		return -ENOMEM;
 
@@ -607,10 +607,10 @@ static int mlx4_buf_direct_alloc(struct mlx4_dev *dev, int size,
  *  multiple pages, so we don't require too much contiguous memory.
  */
 int mlx4_buf_alloc(struct mlx4_dev *dev, int size, int max_direct,
-		   struct mlx4_buf *buf, gfp_t gfp)
+		   struct mlx4_buf *buf)
 {
 	if (size <= max_direct) {
-		return mlx4_buf_direct_alloc(dev, size, buf, gfp);
+		return mlx4_buf_direct_alloc(dev, size, buf);
 	} else {
 		dma_addr_t t;
 		int i;
@@ -620,14 +620,14 @@ int mlx4_buf_alloc(struct mlx4_dev *dev, int size, int max_direct,
 		buf->npages	= buf->nbufs;
 		buf->page_shift  = PAGE_SHIFT;
 		buf->page_list   = kcalloc(buf->nbufs, sizeof(*buf->page_list),
-					   gfp);
+					   GFP_KERNEL);
 		if (!buf->page_list)
 			return -ENOMEM;
 
 		for (i = 0; i < buf->nbufs; ++i) {
 			buf->page_list[i].buf =
 				dma_zalloc_coherent(&dev->persist->pdev->dev,
-						    PAGE_SIZE, &t, gfp);
+						    PAGE_SIZE, &t, GFP_KERNEL);
 			if (!buf->page_list[i].buf)
 				goto err_free;
 
@@ -663,12 +663,11 @@ void mlx4_buf_free(struct mlx4_dev *dev, int size, struct mlx4_buf *buf)
 }
 EXPORT_SYMBOL_GPL(mlx4_buf_free);
 
-static struct mlx4_db_pgdir *mlx4_alloc_db_pgdir(struct device *dma_device,
-						 gfp_t gfp)
+static struct mlx4_db_pgdir *mlx4_alloc_db_pgdir(struct device *dma_device)
 {
 	struct mlx4_db_pgdir *pgdir;
 
-	pgdir = kzalloc(sizeof *pgdir, gfp);
+	pgdir = kzalloc(sizeof(*pgdir), GFP_KERNEL);
 	if (!pgdir)
 		return NULL;
 
@@ -676,7 +675,7 @@ static struct mlx4_db_pgdir *mlx4_alloc_db_pgdir(struct device *dma_device,
 	pgdir->bits[0] = pgdir->order0;
 	pgdir->bits[1] = pgdir->order1;
 	pgdir->db_page = dma_alloc_coherent(dma_device, PAGE_SIZE,
-					    &pgdir->db_dma, gfp);
+					    &pgdir->db_dma, GFP_KERNEL);
 	if (!pgdir->db_page) {
 		kfree(pgdir);
 		return NULL;
@@ -716,7 +715,7 @@ found:
 	return 0;
 }
 
-int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order, gfp_t gfp)
+int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_db_pgdir *pgdir;
@@ -728,7 +727,7 @@ int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order, gfp_t gfp
 		if (!mlx4_alloc_db_from_pgdir(pgdir, db, order))
 			goto out;
 
-	pgdir = mlx4_alloc_db_pgdir(&dev->persist->pdev->dev, gfp);
+	pgdir = mlx4_alloc_db_pgdir(&dev->persist->pdev->dev);
 	if (!pgdir) {
 		ret = -ENOMEM;
 		goto out;
@@ -780,13 +779,13 @@ int mlx4_alloc_hwq_res(struct mlx4_dev *dev, struct mlx4_hwq_resources *wqres,
 {
 	int err;
 
-	err = mlx4_db_alloc(dev, &wqres->db, 1, GFP_KERNEL);
+	err = mlx4_db_alloc(dev, &wqres->db, 1);
 	if (err)
 		return err;
 
 	*wqres->db.db = 0;
 
-	err = mlx4_buf_direct_alloc(dev, size, &wqres->buf, GFP_KERNEL);
+	err = mlx4_buf_direct_alloc(dev, size, &wqres->buf);
 	if (err)
 		goto err_db;
 
@@ -795,7 +794,7 @@ int mlx4_alloc_hwq_res(struct mlx4_dev *dev, struct mlx4_hwq_resources *wqres,
 	if (err)
 		goto err_buf;
 
-	err = mlx4_buf_write_mtt(dev, &wqres->mtt, &wqres->buf, GFP_KERNEL);
+	err = mlx4_buf_write_mtt(dev, &wqres->mtt, &wqres->buf);
 	if (err)
 		goto err_mtt;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c
index fa6d2354a0e9..c56a511b918e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cq.c
@@ -224,11 +224,11 @@ int __mlx4_cq_alloc_icm(struct mlx4_dev *dev, int *cqn)
 	if (*cqn == -1)
 		return -ENOMEM;
 
-	err = mlx4_table_get(dev, &cq_table->table, *cqn, GFP_KERNEL);
+	err = mlx4_table_get(dev, &cq_table->table, *cqn);
 	if (err)
 		goto err_out;
 
-	err = mlx4_table_get(dev, &cq_table->cmpt_table, *cqn, GFP_KERNEL);
+	err = mlx4_table_get(dev, &cq_table->cmpt_table, *cqn);
 	if (err)
 		goto err_put;
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index e5fb89505a13..436f7689a032 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -1042,7 +1042,7 @@ static int mlx4_en_config_rss_qp(struct mlx4_en_priv *priv, int qpn,
 	if (!context)
 		return -ENOMEM;
 
-	err = mlx4_qp_alloc(mdev->dev, qpn, qp, GFP_KERNEL);
+	err = mlx4_qp_alloc(mdev->dev, qpn, qp);
 	if (err) {
 		en_err(priv, "Failed to allocate qp #%x\n", qpn);
 		goto out;
@@ -1086,7 +1086,7 @@ int mlx4_en_create_drop_qp(struct mlx4_en_priv *priv)
 		en_err(priv, "Failed reserving drop qpn\n");
 		return err;
 	}
-	err = mlx4_qp_alloc(priv->mdev->dev, qpn, &priv->drop_qp, GFP_KERNEL);
+	err = mlx4_qp_alloc(priv->mdev->dev, qpn, &priv->drop_qp);
 	if (err) {
 		en_err(priv, "Failed allocating drop qp\n");
 		mlx4_qp_release_range(priv->mdev->dev, qpn, 1);
@@ -1158,8 +1158,7 @@ int mlx4_en_config_rss_steer(struct mlx4_en_priv *priv)
 	}
 
 	/* Configure RSS indirection qp */
-	err = mlx4_qp_alloc(mdev->dev, priv->base_qpn, rss_map->indir_qp,
-			    GFP_KERNEL);
+	err = mlx4_qp_alloc(mdev->dev, priv->base_qpn, rss_map->indir_qp);
 	if (err) {
 		en_err(priv, "Failed to allocate RSS indirection QP\n");
 		goto rss_err;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 4f3a9b27ce4a..73faa3d77921 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -111,7 +111,7 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 		goto err_hwq_res;
 	}
 
-	err = mlx4_qp_alloc(mdev->dev, ring->qpn, &ring->sp_qp, GFP_KERNEL);
+	err = mlx4_qp_alloc(mdev->dev, ring->qpn, &ring->sp_qp);
 	if (err) {
 		en_err(priv, "Failed allocating qp %d\n", ring->qpn);
 		goto err_reserve;
diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.c b/drivers/net/ethernet/mellanox/mlx4/icm.c
index e1f9e7cebf8f..5a7816e7c7b4 100644
--- a/drivers/net/ethernet/mellanox/mlx4/icm.c
+++ b/drivers/net/ethernet/mellanox/mlx4/icm.c
@@ -251,8 +251,7 @@ int mlx4_UNMAP_ICM_AUX(struct mlx4_dev *dev)
 			MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
 }
 
-int mlx4_table_get(struct mlx4_dev *dev, struct mlx4_icm_table *table, u32 obj,
-		   gfp_t gfp)
+int mlx4_table_get(struct mlx4_dev *dev, struct mlx4_icm_table *table, u32 obj)
 {
 	u32 i = (obj & (table->num_obj - 1)) /
 			(MLX4_TABLE_CHUNK_SIZE / table->obj_size);
@@ -266,7 +265,7 @@ int mlx4_table_get(struct mlx4_dev *dev, struct mlx4_icm_table *table, u32 obj,
 	}
 
 	table->icm[i] = mlx4_alloc_icm(dev, MLX4_TABLE_CHUNK_SIZE >> PAGE_SHIFT,
-				       (table->lowmem ? gfp : GFP_HIGHUSER) |
+				       (table->lowmem ? GFP_KERNEL : GFP_HIGHUSER) |
 				       __GFP_NOWARN, table->coherent);
 	if (!table->icm[i]) {
 		ret = -ENOMEM;
@@ -363,7 +362,7 @@ int mlx4_table_get_range(struct mlx4_dev *dev, struct mlx4_icm_table *table,
 	u32 i;
 
 	for (i = start; i <= end; i += inc) {
-		err = mlx4_table_get(dev, table, i, GFP_KERNEL);
+		err = mlx4_table_get(dev, table, i);
 		if (err)
 			goto fail;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.h b/drivers/net/ethernet/mellanox/mlx4/icm.h
index 0c7364550150..dee67fa39107 100644
--- a/drivers/net/ethernet/mellanox/mlx4/icm.h
+++ b/drivers/net/ethernet/mellanox/mlx4/icm.h
@@ -71,8 +71,7 @@ struct mlx4_icm *mlx4_alloc_icm(struct mlx4_dev *dev, int npages,
 				gfp_t gfp_mask, int coherent);
 void mlx4_free_icm(struct mlx4_dev *dev, struct mlx4_icm *icm, int coherent);
 
-int mlx4_table_get(struct mlx4_dev *dev, struct mlx4_icm_table *table, u32 obj,
-		   gfp_t gfp);
+int mlx4_table_get(struct mlx4_dev *dev, struct mlx4_icm_table *table, u32 obj);
 void mlx4_table_put(struct mlx4_dev *dev, struct mlx4_icm_table *table, u32 obj);
 int mlx4_table_get_range(struct mlx4_dev *dev, struct mlx4_icm_table *table,
 			 u32 start, u32 end);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 30616cd0140d..706d7f21ac5c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -969,7 +969,7 @@ void mlx4_cleanup_cq_table(struct mlx4_dev *dev);
 void mlx4_cleanup_qp_table(struct mlx4_dev *dev);
 void mlx4_cleanup_srq_table(struct mlx4_dev *dev);
 void mlx4_cleanup_mcg_table(struct mlx4_dev *dev);
-int __mlx4_qp_alloc_icm(struct mlx4_dev *dev, int qpn, gfp_t gfp);
+int __mlx4_qp_alloc_icm(struct mlx4_dev *dev, int qpn);
 void __mlx4_qp_free_icm(struct mlx4_dev *dev, int qpn);
 int __mlx4_cq_alloc_icm(struct mlx4_dev *dev, int *cqn);
 void __mlx4_cq_free_icm(struct mlx4_dev *dev, int cqn);
@@ -977,7 +977,7 @@ int __mlx4_srq_alloc_icm(struct mlx4_dev *dev, int *srqn);
 void __mlx4_srq_free_icm(struct mlx4_dev *dev, int srqn);
 int __mlx4_mpt_reserve(struct mlx4_dev *dev);
 void __mlx4_mpt_release(struct mlx4_dev *dev, u32 index);
-int __mlx4_mpt_alloc_icm(struct mlx4_dev *dev, u32 index, gfp_t gfp);
+int __mlx4_mpt_alloc_icm(struct mlx4_dev *dev, u32 index);
 void __mlx4_mpt_free_icm(struct mlx4_dev *dev, u32 index);
 u32 __mlx4_alloc_mtt_range(struct mlx4_dev *dev, int order);
 void __mlx4_free_mtt_range(struct mlx4_dev *dev, u32 first_seg, int order);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c
index ce852ca22a96..24282cd017d3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mr.c
@@ -479,14 +479,14 @@ static void mlx4_mpt_release(struct mlx4_dev *dev, u32 index)
 	__mlx4_mpt_release(dev, index);
 }
 
-int __mlx4_mpt_alloc_icm(struct mlx4_dev *dev, u32 index, gfp_t gfp)
+int __mlx4_mpt_alloc_icm(struct mlx4_dev *dev, u32 index)
 {
 	struct mlx4_mr_table *mr_table = &mlx4_priv(dev)->mr_table;
 
-	return mlx4_table_get(dev, &mr_table->dmpt_table, index, gfp);
+	return mlx4_table_get(dev, &mr_table->dmpt_table, index);
 }
 
-static int mlx4_mpt_alloc_icm(struct mlx4_dev *dev, u32 index, gfp_t gfp)
+static int mlx4_mpt_alloc_icm(struct mlx4_dev *dev, u32 index)
 {
 	u64 param = 0;
 
@@ -497,7 +497,7 @@ static int mlx4_mpt_alloc_icm(struct mlx4_dev *dev, u32 index, gfp_t gfp)
 							MLX4_CMD_TIME_CLASS_A,
 							MLX4_CMD_WRAPPED);
 	}
-	return __mlx4_mpt_alloc_icm(dev, index, gfp);
+	return __mlx4_mpt_alloc_icm(dev, index);
 }
 
 void __mlx4_mpt_free_icm(struct mlx4_dev *dev, u32 index)
@@ -629,7 +629,7 @@ int mlx4_mr_enable(struct mlx4_dev *dev, struct mlx4_mr *mr)
 	struct mlx4_mpt_entry *mpt_entry;
 	int err;
 
-	err = mlx4_mpt_alloc_icm(dev, key_to_hw_index(mr->key), GFP_KERNEL);
+	err = mlx4_mpt_alloc_icm(dev, key_to_hw_index(mr->key));
 	if (err)
 		return err;
 
@@ -787,14 +787,13 @@ int mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 EXPORT_SYMBOL_GPL(mlx4_write_mtt);
 
 int mlx4_buf_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
-		       struct mlx4_buf *buf, gfp_t gfp)
+		       struct mlx4_buf *buf)
 {
 	u64 *page_list;
 	int err;
 	int i;
 
-	page_list = kmalloc(buf->npages * sizeof *page_list,
-			    gfp);
+	page_list = kcalloc(buf->npages, sizeof(*page_list), GFP_KERNEL);
 	if (!page_list)
 		return -ENOMEM;
 
@@ -841,7 +840,7 @@ int mlx4_mw_enable(struct mlx4_dev *dev, struct mlx4_mw *mw)
 	struct mlx4_mpt_entry *mpt_entry;
 	int err;
 
-	err = mlx4_mpt_alloc_icm(dev, key_to_hw_index(mw->key), GFP_KERNEL);
+	err = mlx4_mpt_alloc_icm(dev, key_to_hw_index(mw->key));
 	if (err)
 		return err;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c
index 5a310d313e94..26747212526b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx4/qp.c
@@ -301,29 +301,29 @@ void mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt)
 }
 EXPORT_SYMBOL_GPL(mlx4_qp_release_range);
 
-int __mlx4_qp_alloc_icm(struct mlx4_dev *dev, int qpn, gfp_t gfp)
+int __mlx4_qp_alloc_icm(struct mlx4_dev *dev, int qpn)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_qp_table *qp_table = &priv->qp_table;
 	int err;
 
-	err = mlx4_table_get(dev, &qp_table->qp_table, qpn, gfp);
+	err = mlx4_table_get(dev, &qp_table->qp_table, qpn);
 	if (err)
 		goto err_out;
 
-	err = mlx4_table_get(dev, &qp_table->auxc_table, qpn, gfp);
+	err = mlx4_table_get(dev, &qp_table->auxc_table, qpn);
 	if (err)
 		goto err_put_qp;
 
-	err = mlx4_table_get(dev, &qp_table->altc_table, qpn, gfp);
+	err = mlx4_table_get(dev, &qp_table->altc_table, qpn);
 	if (err)
 		goto err_put_auxc;
 
-	err = mlx4_table_get(dev, &qp_table->rdmarc_table, qpn, gfp);
+	err = mlx4_table_get(dev, &qp_table->rdmarc_table, qpn);
 	if (err)
 		goto err_put_altc;
 
-	err = mlx4_table_get(dev, &qp_table->cmpt_table, qpn, gfp);
+	err = mlx4_table_get(dev, &qp_table->cmpt_table, qpn);
 	if (err)
 		goto err_put_rdmarc;
 
@@ -345,7 +345,7 @@ err_out:
 	return err;
 }
 
-static int mlx4_qp_alloc_icm(struct mlx4_dev *dev, int qpn, gfp_t gfp)
+static int mlx4_qp_alloc_icm(struct mlx4_dev *dev, int qpn)
 {
 	u64 param = 0;
 
@@ -355,7 +355,7 @@ static int mlx4_qp_alloc_icm(struct mlx4_dev *dev, int qpn, gfp_t gfp)
 				    MLX4_CMD_ALLOC_RES, MLX4_CMD_TIME_CLASS_A,
 				    MLX4_CMD_WRAPPED);
 	}
-	return __mlx4_qp_alloc_icm(dev, qpn, gfp);
+	return __mlx4_qp_alloc_icm(dev, qpn);
 }
 
 void __mlx4_qp_free_icm(struct mlx4_dev *dev, int qpn)
@@ -397,7 +397,7 @@ struct mlx4_qp *mlx4_qp_lookup(struct mlx4_dev *dev, u32 qpn)
 	return qp;
 }
 
-int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp, gfp_t gfp)
+int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_qp_table *qp_table = &priv->qp_table;
@@ -408,7 +408,7 @@ int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp, gfp_t gfp)
 
 	qp->qpn = qpn;
 
-	err = mlx4_qp_alloc_icm(dev, qpn, gfp);
+	err = mlx4_qp_alloc_icm(dev, qpn);
 	if (err)
 		return err;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 812783865205..215e21c3dc8a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -1822,7 +1822,7 @@ static int qp_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
 			return err;
 
 		if (!fw_reserved(dev, qpn)) {
-			err = __mlx4_qp_alloc_icm(dev, qpn, GFP_KERNEL);
+			err = __mlx4_qp_alloc_icm(dev, qpn);
 			if (err) {
 				res_abort_move(dev, slave, RES_QP, qpn);
 				return err;
@@ -1909,7 +1909,7 @@ static int mpt_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
 		if (err)
 			return err;
 
-		err = __mlx4_mpt_alloc_icm(dev, mpt->key, GFP_KERNEL);
+		err = __mlx4_mpt_alloc_icm(dev, mpt->key);
 		if (err) {
 			res_abort_move(dev, slave, RES_MPT, id);
 			return err;
diff --git a/drivers/net/ethernet/mellanox/mlx4/srq.c b/drivers/net/ethernet/mellanox/mlx4/srq.c
index f44d089e2ca6..bedf52126824 100644
--- a/drivers/net/ethernet/mellanox/mlx4/srq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/srq.c
@@ -100,11 +100,11 @@ int __mlx4_srq_alloc_icm(struct mlx4_dev *dev, int *srqn)
 	if (*srqn == -1)
 		return -ENOMEM;
 
-	err = mlx4_table_get(dev, &srq_table->table, *srqn, GFP_KERNEL);
+	err = mlx4_table_get(dev, &srq_table->table, *srqn);
 	if (err)
 		goto err_out;
 
-	err = mlx4_table_get(dev, &srq_table->cmpt_table, *srqn, GFP_KERNEL);
+	err = mlx4_table_get(dev, &srq_table->cmpt_table, *srqn);
 	if (err)
 		goto err_put;
 	return 0;
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index d5bed0875d30..aad5d81dfb44 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -1068,7 +1068,7 @@ static inline int mlx4_is_eth(struct mlx4_dev *dev, int port)
 }
 
 int mlx4_buf_alloc(struct mlx4_dev *dev, int size, int max_direct,
-		   struct mlx4_buf *buf, gfp_t gfp);
+		   struct mlx4_buf *buf);
 void mlx4_buf_free(struct mlx4_dev *dev, int size, struct mlx4_buf *buf);
 static inline void *mlx4_buf_offset(struct mlx4_buf *buf, int offset)
 {
@@ -1105,10 +1105,9 @@ int mlx4_mw_enable(struct mlx4_dev *dev, struct mlx4_mw *mw);
 int mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 		   int start_index, int npages, u64 *page_list);
 int mlx4_buf_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
-		       struct mlx4_buf *buf, gfp_t gfp);
+		       struct mlx4_buf *buf);
 
-int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order,
-		  gfp_t gfp);
+int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order);
 void mlx4_db_free(struct mlx4_dev *dev, struct mlx4_db *db);
 
 int mlx4_alloc_hwq_res(struct mlx4_dev *dev, struct mlx4_hwq_resources *wqres,
@@ -1124,8 +1123,7 @@ int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align,
 			  int *base, u8 flags);
 void mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt);
 
-int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp,
-		  gfp_t gfp);
+int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp);
 void mlx4_qp_free(struct mlx4_dev *dev, struct mlx4_qp *qp);
 
 int mlx4_srq_alloc(struct mlx4_dev *dev, u32 pdn, u32 cqn, u16 xrcdn,
-- 
cgit v1.2.3


From 7855f5842741e5835b9be073079780c444dca898 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Tue, 23 May 2017 14:38:16 +0300
Subject: IB/core: Remove NOIO QP create flag

There are no users for IB_QP_CREATE_USE_GFP_NOIO flag,
so let's remove it.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 include/rdma/ib_verbs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 6e62c9e2c971..b5732432bb29 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1056,7 +1056,7 @@ enum ib_qp_create_flags {
 	IB_QP_CREATE_MANAGED_RECV               = 1 << 4,
 	IB_QP_CREATE_NETIF_QP			= 1 << 5,
 	IB_QP_CREATE_SIGNATURE_EN		= 1 << 6,
-	IB_QP_CREATE_USE_GFP_NOIO		= 1 << 7,
+	/* FREE					= 1 << 7, */
 	IB_QP_CREATE_SCATTER_FCS		= 1 << 8,
 	IB_QP_CREATE_CVLAN_STRIPPING		= 1 << 9,
 	/* reserve bits 26-31 for low level drivers' internal use */
-- 
cgit v1.2.3


From 8bd226f9a7dc18740a916dcba3112f2bfc3ad9e8 Mon Sep 17 00:00:00 2001
From: Ruslan Bilovol <ruslan.bilovol@gmail.com>
Date: Sun, 25 Jun 2017 16:23:45 +0300
Subject: include: usb: audio: specify exact endiannes of descriptors

USB spec says that multiple byte fields are stored in
little-endian order (see chapter 8.1 of USB2.0 spec and
chapter 7.1 of USB3.0 spec), thus mark such fields as LE
for UAC1 and UAC2 headers

Signed-off-by: Ruslan Bilovol <ruslan.bilovol@gmail.com>
Signed-off-by: Felipe Balbi <felipe.balbi@linux.intel.com>
---
 include/linux/usb/audio-v2.h   | 14 +++++++-------
 include/uapi/linux/usb/audio.h |  6 +++---
 2 files changed, 10 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/usb/audio-v2.h b/include/linux/usb/audio-v2.h
index c5f2158ab00e..fd73bc0e9027 100644
--- a/include/linux/usb/audio-v2.h
+++ b/include/linux/usb/audio-v2.h
@@ -115,13 +115,13 @@ struct uac2_input_terminal_descriptor {
 	__u8 bDescriptorType;
 	__u8 bDescriptorSubtype;
 	__u8 bTerminalID;
-	__u16 wTerminalType;
+	__le16 wTerminalType;
 	__u8 bAssocTerminal;
 	__u8 bCSourceID;
 	__u8 bNrChannels;
-	__u32 bmChannelConfig;
+	__le32 bmChannelConfig;
 	__u8 iChannelNames;
-	__u16 bmControls;
+	__le16 bmControls;
 	__u8 iTerminal;
 } __attribute__((packed));
 
@@ -132,11 +132,11 @@ struct uac2_output_terminal_descriptor {
 	__u8 bDescriptorType;
 	__u8 bDescriptorSubtype;
 	__u8 bTerminalID;
-	__u16 wTerminalType;
+	__le16 wTerminalType;
 	__u8 bAssocTerminal;
 	__u8 bSourceID;
 	__u8 bCSourceID;
-	__u16 bmControls;
+	__le16 bmControls;
 	__u8 iTerminal;
 } __attribute__((packed));
 
@@ -164,9 +164,9 @@ struct uac2_as_header_descriptor {
 	__u8 bTerminalLink;
 	__u8 bmControls;
 	__u8 bFormatType;
-	__u32 bmFormats;
+	__le32 bmFormats;
 	__u8 bNrChannels;
-	__u32 bmChannelConfig;
+	__le32 bmChannelConfig;
 	__u8 iChannelNames;
 } __attribute__((packed));
 
diff --git a/include/uapi/linux/usb/audio.h b/include/uapi/linux/usb/audio.h
index d2314be4f0c0..a4680a5bf5dd 100644
--- a/include/uapi/linux/usb/audio.h
+++ b/include/uapi/linux/usb/audio.h
@@ -333,7 +333,7 @@ struct uac_processing_unit_descriptor {
 	__u8 bDescriptorType;
 	__u8 bDescriptorSubtype;
 	__u8 bUnitID;
-	__u16 wProcessType;
+	__le16 wProcessType;
 	__u8 bNrInPins;
 	__u8 baSourceID[];
 } __attribute__ ((packed));
@@ -491,8 +491,8 @@ struct uac_format_type_ii_ext_descriptor {
 	__u8 bDescriptorType;
 	__u8 bDescriptorSubtype;
 	__u8 bFormatType;
-	__u16 wMaxBitRate;
-	__u16 wSamplesPerFrame;
+	__le16 wMaxBitRate;
+	__le16 wSamplesPerFrame;
 	__u8 bHeaderLength;
 	__u8 bSideBandProtocol;
 } __attribute__((packed));
-- 
cgit v1.2.3


From beaec533fc2701a28a4d667f67c9f59c6e4e0d13 Mon Sep 17 00:00:00 2001
From: Alexander Potapenko <glider@google.com>
Date: Wed, 19 Jul 2017 20:27:30 +0200
Subject: llist: clang: introduce member_address_is_nonnull()

Currently llist_for_each_entry() and llist_for_each_entry_safe() iterate
until &pos->member != NULL.  But when building the kernel with Clang,
the compiler assumes &pos->member cannot be NULL if the member's offset
is greater than 0 (which would be equivalent to the object being
non-contiguous in memory).  Therefore the loop condition is always true,
and the loops become infinite.

To work around this, introduce the member_address_is_nonnull() macro,
which casts object pointer to uintptr_t, thus letting the member pointer
to be NULL.

Signed-off-by: Alexander Potapenko <glider@google.com>
Tested-by: Sodagudi Prasad <psodagud@codeaurora.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/llist.h | 21 +++++++++++++++++++--
 1 file changed, 19 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/llist.h b/include/linux/llist.h
index d11738110a7a..1957635e6d5f 100644
--- a/include/linux/llist.h
+++ b/include/linux/llist.h
@@ -92,6 +92,23 @@ static inline void init_llist_head(struct llist_head *list)
 #define llist_entry(ptr, type, member)		\
 	container_of(ptr, type, member)
 
+/**
+ * member_address_is_nonnull - check whether the member address is not NULL
+ * @ptr:	the object pointer (struct type * that contains the llist_node)
+ * @member:	the name of the llist_node within the struct.
+ *
+ * This macro is conceptually the same as
+ *	&ptr->member != NULL
+ * but it works around the fact that compilers can decide that taking a member
+ * address is never a NULL pointer.
+ *
+ * Real objects that start at a high address and have a member at NULL are
+ * unlikely to exist, but such pointers may be returned e.g. by the
+ * container_of() macro.
+ */
+#define member_address_is_nonnull(ptr, member)	\
+	((uintptr_t)(ptr) + offsetof(typeof(*(ptr)), member) != 0)
+
 /**
  * llist_for_each - iterate over some deleted entries of a lock-less list
  * @pos:	the &struct llist_node to use as a loop cursor
@@ -145,7 +162,7 @@ static inline void init_llist_head(struct llist_head *list)
  */
 #define llist_for_each_entry(pos, node, member)				\
 	for ((pos) = llist_entry((node), typeof(*(pos)), member);	\
-	     &(pos)->member != NULL;					\
+	     member_address_is_nonnull(pos, member);			\
 	     (pos) = llist_entry((pos)->member.next, typeof(*(pos)), member))
 
 /**
@@ -167,7 +184,7 @@ static inline void init_llist_head(struct llist_head *list)
  */
 #define llist_for_each_entry_safe(pos, n, node, member)			       \
 	for (pos = llist_entry((node), typeof(*pos), member);		       \
-	     &pos->member != NULL &&					       \
+	     member_address_is_nonnull(pos, member) &&			       \
 	        (n = llist_entry(pos->member.next, typeof(*n), member), true); \
 	     pos = n)
 
-- 
cgit v1.2.3


From f86f418059b94aa01f9342611a272ca60c583e89 Mon Sep 17 00:00:00 2001
From: Chunyan Zhang <zhang.chunyan@linaro.org>
Date: Wed, 7 Jun 2017 16:12:51 +0800
Subject: trace: fix the errors caused by incompatible type of RCU variables

The variables which are processed by RCU functions should be annotated
as RCU, otherwise sparse will report the errors like below:

"error: incompatible types in comparison expression (different
address spaces)"

Link: http://lkml.kernel.org/r/1496823171-7758-1-git-send-email-zhang.chunyan@linaro.org

Signed-off-by: Chunyan Zhang <zhang.chunyan@linaro.org>
[ Updated to not be 100% 80 column strict ]
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/ftrace.h       |  6 +++---
 include/linux/trace_events.h |  2 +-
 kernel/trace/ftrace.c        | 41 +++++++++++++++++++++++++++--------------
 kernel/trace/trace.h         |  6 +++---
 4 files changed, 34 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 5857390ac35a..6383115e9d2c 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -145,8 +145,8 @@ enum {
 #ifdef CONFIG_DYNAMIC_FTRACE
 /* The hash used to know what functions callbacks trace */
 struct ftrace_ops_hash {
-	struct ftrace_hash		*notrace_hash;
-	struct ftrace_hash		*filter_hash;
+	struct ftrace_hash __rcu	*notrace_hash;
+	struct ftrace_hash __rcu	*filter_hash;
 	struct mutex			regex_lock;
 };
 
@@ -168,7 +168,7 @@ static inline void ftrace_free_init_mem(void) { }
  */
 struct ftrace_ops {
 	ftrace_func_t			func;
-	struct ftrace_ops		*next;
+	struct ftrace_ops __rcu		*next;
 	unsigned long			flags;
 	void				*private;
 	ftrace_func_t			saved_func;
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index f73cedfa2e0b..536c80ff7ad9 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -338,7 +338,7 @@ enum {
 struct trace_event_file {
 	struct list_head		list;
 	struct trace_event_call		*event_call;
-	struct event_filter		*filter;
+	struct event_filter __rcu	*filter;
 	struct dentry			*dir;
 	struct trace_array		*tr;
 	struct trace_subsystem_dir	*system;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 53f6b6401cf0..02004ae91860 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -113,7 +113,7 @@ static int ftrace_disabled __read_mostly;
 
 static DEFINE_MUTEX(ftrace_lock);
 
-static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end;
+static struct ftrace_ops __rcu *ftrace_ops_list __read_mostly = &ftrace_list_end;
 ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
 static struct ftrace_ops global_ops;
 
@@ -169,8 +169,11 @@ int ftrace_nr_registered_ops(void)
 
 	mutex_lock(&ftrace_lock);
 
-	for (ops = ftrace_ops_list;
-	     ops != &ftrace_list_end; ops = ops->next)
+	for (ops = rcu_dereference_protected(ftrace_ops_list,
+					     lockdep_is_held(&ftrace_lock));
+	     ops != &ftrace_list_end;
+	     ops = rcu_dereference_protected(ops->next,
+					     lockdep_is_held(&ftrace_lock)))
 		cnt++;
 
 	mutex_unlock(&ftrace_lock);
@@ -275,10 +278,11 @@ static void update_ftrace_function(void)
 	 * If there's only one ftrace_ops registered, the ftrace_ops_list
 	 * will point to the ops we want.
 	 */
-	set_function_trace_op = ftrace_ops_list;
+	set_function_trace_op = rcu_dereference_protected(ftrace_ops_list,
+						lockdep_is_held(&ftrace_lock));
 
 	/* If there's no ftrace_ops registered, just call the stub function */
-	if (ftrace_ops_list == &ftrace_list_end) {
+	if (set_function_trace_op == &ftrace_list_end) {
 		func = ftrace_stub;
 
 	/*
@@ -286,7 +290,8 @@ static void update_ftrace_function(void)
 	 * recursion safe and not dynamic and the arch supports passing ops,
 	 * then have the mcount trampoline call the function directly.
 	 */
-	} else if (ftrace_ops_list->next == &ftrace_list_end) {
+	} else if (rcu_dereference_protected(ftrace_ops_list->next,
+			lockdep_is_held(&ftrace_lock)) == &ftrace_list_end) {
 		func = ftrace_ops_get_list_func(ftrace_ops_list);
 
 	} else {
@@ -348,9 +353,11 @@ int using_ftrace_ops_list_func(void)
 	return ftrace_trace_function == ftrace_ops_list_func;
 }
 
-static void add_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops)
+static void add_ftrace_ops(struct ftrace_ops __rcu **list,
+			   struct ftrace_ops *ops)
 {
-	ops->next = *list;
+	rcu_assign_pointer(ops->next, *list);
+
 	/*
 	 * We are entering ops into the list but another
 	 * CPU might be walking that list. We need to make sure
@@ -360,7 +367,8 @@ static void add_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops)
 	rcu_assign_pointer(*list, ops);
 }
 
-static int remove_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops)
+static int remove_ftrace_ops(struct ftrace_ops __rcu **list,
+			     struct ftrace_ops *ops)
 {
 	struct ftrace_ops **p;
 
@@ -368,7 +376,10 @@ static int remove_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops)
 	 * If we are removing the last function, then simply point
 	 * to the ftrace_stub.
 	 */
-	if (*list == ops && ops->next == &ftrace_list_end) {
+	if (rcu_dereference_protected(*list,
+			lockdep_is_held(&ftrace_lock)) == ops &&
+	    rcu_dereference_protected(ops->next,
+			lockdep_is_held(&ftrace_lock)) == &ftrace_list_end) {
 		*list = &ftrace_list_end;
 		return 0;
 	}
@@ -1569,8 +1580,8 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs)
 		return 0;
 #endif
 
-	hash.filter_hash = rcu_dereference_raw_notrace(ops->func_hash->filter_hash);
-	hash.notrace_hash = rcu_dereference_raw_notrace(ops->func_hash->notrace_hash);
+	rcu_assign_pointer(hash.filter_hash, ops->func_hash->filter_hash);
+	rcu_assign_pointer(hash.notrace_hash, ops->func_hash->notrace_hash);
 
 	if (hash_contains_ip(ip, &hash))
 		ret = 1;
@@ -2840,7 +2851,8 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command)
 	 * If there's no more ops registered with ftrace, run a
 	 * sanity check to make sure all rec flags are cleared.
 	 */
-	if (ftrace_ops_list == &ftrace_list_end) {
+	if (rcu_dereference_protected(ftrace_ops_list,
+			lockdep_is_held(&ftrace_lock)) == &ftrace_list_end) {
 		struct ftrace_page *pg;
 		struct dyn_ftrace *rec;
 
@@ -6453,7 +6465,8 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 	if (ftrace_enabled) {
 
 		/* we are starting ftrace again */
-		if (ftrace_ops_list != &ftrace_list_end)
+		if (rcu_dereference_protected(ftrace_ops_list,
+			lockdep_is_held(&ftrace_lock)) != &ftrace_list_end)
 			update_ftrace_function();
 
 		ftrace_startup_sysctl();
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 6ade1c55cc3a..490ba229931d 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1210,9 +1210,9 @@ struct ftrace_event_field {
 struct event_filter {
 	int			n_preds;	/* Number assigned */
 	int			a_preds;	/* allocated */
-	struct filter_pred	*preds;
-	struct filter_pred	*root;
-	char			*filter_string;
+	struct filter_pred __rcu	*preds;
+	struct filter_pred __rcu	*root;
+	char				*filter_string;
 };
 
 struct event_subsystem {
-- 
cgit v1.2.3


From dc1a0afbacaeaced8f5679a99047c0467f1099e9 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 14 Jul 2017 11:12:09 +0200
Subject: nvme: fix byte swapping in the streams code

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/nvme/host/core.c |  2 +-
 include/linux/nvme.h     | 14 +++++++-------
 2 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index cb96f4a7ae3a..3b77cfe5aa1e 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -336,7 +336,7 @@ static int nvme_get_stream_params(struct nvme_ctrl *ctrl,
 
 	c.directive.opcode = nvme_admin_directive_recv;
 	c.directive.nsid = cpu_to_le32(nsid);
-	c.directive.numd = sizeof(*s);
+	c.directive.numd = cpu_to_le32(sizeof(*s));
 	c.directive.doper = NVME_DIR_RCV_ST_OP_PARAM;
 	c.directive.dtype = NVME_DIR_STREAMS;
 
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 6b8ee9e628e1..bc74da018bdc 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -963,14 +963,14 @@ struct nvme_dbbuf {
 };
 
 struct streams_directive_params {
-	__u16	msl;
-	__u16	nssa;
-	__u16	nsso;
+	__le16	msl;
+	__le16	nssa;
+	__le16	nsso;
 	__u8	rsvd[10];
-	__u32	sws;
-	__u16	sgs;
-	__u16	nsa;
-	__u16	nso;
+	__le32	sws;
+	__le16	sgs;
+	__le16	nsa;
+	__le16	nso;
 	__u8	rsvd2[6];
 };
 
-- 
cgit v1.2.3


From a25ce4270bfdd522207b02f81a594c7d1746b697 Mon Sep 17 00:00:00 2001
From: Kaike Wan <kaike.wan@intel.com>
Date: Sat, 17 Jun 2017 10:37:26 -0700
Subject: IB/rdmavt: Setting of QP timeout can overflow jiffies computation

Current computation of qp->timeout_jiffies in rvt_modify_qp() will cause
overflow due to the fact that the input to the function usecs_to_jiffies
is only 32-bit ( unsigned int). Overflow will occur when attr->timeout is
equal to or greater than 30. The consequence is unnecessarily excessive
retry and thus degradation of the system performance.

This patch fixes the problem by limiting the input to 5-bit and calling
usecs_to_jiffies() before multiplying the scaling factor.

Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Kaike Wan <kaike.wan@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/sw/rdmavt/qp.c |  4 +---
 include/rdma/rdmavt_qp.h          | 14 ++++++++++++++
 2 files changed, 15 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c
index 459865439a0b..8876ee7bc326 100644
--- a/drivers/infiniband/sw/rdmavt/qp.c
+++ b/drivers/infiniband/sw/rdmavt/qp.c
@@ -1258,9 +1258,7 @@ int rvt_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 
 	if (attr_mask & IB_QP_TIMEOUT) {
 		qp->timeout = attr->timeout;
-		qp->timeout_jiffies =
-			usecs_to_jiffies((4096UL * (1UL << qp->timeout)) /
-				1000UL);
+		qp->timeout_jiffies = rvt_timeout_to_jiffies(qp->timeout);
 	}
 
 	if (attr_mask & IB_QP_QKEY)
diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h
index be6472e5b06b..d664d2e76280 100644
--- a/include/rdma/rdmavt_qp.h
+++ b/include/rdma/rdmavt_qp.h
@@ -647,6 +647,20 @@ static inline u32 rvt_div_mtu(struct rvt_qp *qp, u32 len)
 	return len >> qp->log_pmtu;
 }
 
+/**
+ * rvt_timeout_to_jiffies - Convert a ULP timeout input into jiffies
+ * @timeout - timeout input(0 - 31).
+ *
+ * Return a timeout value in jiffies.
+ */
+static inline unsigned long rvt_timeout_to_jiffies(u8 timeout)
+{
+	if (timeout > 31)
+		timeout = 31;
+
+	return usecs_to_jiffies(1U << timeout) * 4096UL / 1000UL;
+}
+
 extern const int  ib_rvt_state_ops[];
 
 struct rvt_dev_info;
-- 
cgit v1.2.3


From 963916fdb3e5ad4af57ac959b5a03bf23f7568ca Mon Sep 17 00:00:00 2001
From: "Kalderon, Michal" <Michal.Kalderon@cavium.com>
Date: Thu, 6 Jul 2017 23:22:11 +0300
Subject: IB/cma: Fix reference count leak when no ipv4 addresses are set

Once in_dev_get is called to receive in_device pointer, the
in_device reference counter is increased, but if there are
no ipv4 addresses configured on the net-device the ifa_list
will be null, resulting in a flow that doesn't call in_dev_put
to decrease the ref_cnt.
This was exposed when running RoCE over ipv6 without any ipv4
addresses configured

Fixes: commit 8e3867310c90 ("IB/cma: Fix a race condition in iboe_addr_get_sgid()")

Signed-off-by: Michal Kalderon <Michal.Kalderon@cavium.com>
Signed-off-by: Ariel Elior <Ariel.Elior@cavium.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 include/rdma/ib_addr.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/rdma/ib_addr.h b/include/rdma/ib_addr.h
index 4b34c51f859e..b73a14edc85e 100644
--- a/include/rdma/ib_addr.h
+++ b/include/rdma/ib_addr.h
@@ -205,11 +205,13 @@ static inline void iboe_addr_get_sgid(struct rdma_dev_addr *dev_addr,
 	dev = dev_get_by_index(&init_net, dev_addr->bound_dev_if);
 	if (dev) {
 		ip4 = in_dev_get(dev);
-		if (ip4 && ip4->ifa_list && ip4->ifa_list->ifa_address) {
+		if (ip4 && ip4->ifa_list && ip4->ifa_list->ifa_address)
 			ipv6_addr_set_v4mapped(ip4->ifa_list->ifa_address,
 					       (struct in6_addr *)gid);
+
+		if (ip4)
 			in_dev_put(ip4);
-		}
+
 		dev_put(dev);
 	}
 }
-- 
cgit v1.2.3


From 4cabc5b186b5427b9ee5a7495172542af105f02b Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 21 Jul 2017 00:00:21 +0200
Subject: bpf: fix mixed signed/unsigned derived min/max value bounds

Edward reported that there's an issue in min/max value bounds
tracking when signed and unsigned compares both provide hints
on limits when having unknown variables. E.g. a program such
as the following should have been rejected:

   0: (7a) *(u64 *)(r10 -8) = 0
   1: (bf) r2 = r10
   2: (07) r2 += -8
   3: (18) r1 = 0xffff8a94cda93400
   5: (85) call bpf_map_lookup_elem#1
   6: (15) if r0 == 0x0 goto pc+7
  R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R10=fp
   7: (7a) *(u64 *)(r10 -16) = -8
   8: (79) r1 = *(u64 *)(r10 -16)
   9: (b7) r2 = -1
  10: (2d) if r1 > r2 goto pc+3
  R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R1=inv,min_value=0
  R2=imm-1,max_value=18446744073709551615,min_align=1 R10=fp
  11: (65) if r1 s> 0x1 goto pc+2
  R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R1=inv,min_value=0,max_value=1
  R2=imm-1,max_value=18446744073709551615,min_align=1 R10=fp
  12: (0f) r0 += r1
  13: (72) *(u8 *)(r0 +0) = 0
  R0=map_value_adj(ks=8,vs=8,id=0),min_value=0,max_value=1 R1=inv,min_value=0,max_value=1
  R2=imm-1,max_value=18446744073709551615,min_align=1 R10=fp
  14: (b7) r0 = 0
  15: (95) exit

What happens is that in the first part ...

   8: (79) r1 = *(u64 *)(r10 -16)
   9: (b7) r2 = -1
  10: (2d) if r1 > r2 goto pc+3

... r1 carries an unsigned value, and is compared as unsigned
against a register carrying an immediate. Verifier deduces in
reg_set_min_max() that since the compare is unsigned and operation
is greater than (>), that in the fall-through/false case, r1's
minimum bound must be 0 and maximum bound must be r2. Latter is
larger than the bound and thus max value is reset back to being
'invalid' aka BPF_REGISTER_MAX_RANGE. Thus, r1 state is now
'R1=inv,min_value=0'. The subsequent test ...

  11: (65) if r1 s> 0x1 goto pc+2

... is a signed compare of r1 with immediate value 1. Here,
verifier deduces in reg_set_min_max() that since the compare
is signed this time and operation is greater than (>), that
in the fall-through/false case, we can deduce that r1's maximum
bound must be 1, meaning with prior test, we result in r1 having
the following state: R1=inv,min_value=0,max_value=1. Given that
the actual value this holds is -8, the bounds are wrongly deduced.
When this is being added to r0 which holds the map_value(_adj)
type, then subsequent store access in above case will go through
check_mem_access() which invokes check_map_access_adj(), that
will then probe whether the map memory is in bounds based
on the min_value and max_value as well as access size since
the actual unknown value is min_value <= x <= max_value; commit
fce366a9dd0d ("bpf, verifier: fix alu ops against map_value{,
_adj} register types") provides some more explanation on the
semantics.

It's worth to note in this context that in the current code,
min_value and max_value tracking are used for two things, i)
dynamic map value access via check_map_access_adj() and since
commit 06c1c049721a ("bpf: allow helpers access to variable memory")
ii) also enforced at check_helper_mem_access() when passing a
memory address (pointer to packet, map value, stack) and length
pair to a helper and the length in this case is an unknown value
defining an access range through min_value/max_value in that
case. The min_value/max_value tracking is /not/ used in the
direct packet access case to track ranges. However, the issue
also affects case ii), for example, the following crafted program
based on the same principle must be rejected as well:

   0: (b7) r2 = 0
   1: (bf) r3 = r10
   2: (07) r3 += -512
   3: (7a) *(u64 *)(r10 -16) = -8
   4: (79) r4 = *(u64 *)(r10 -16)
   5: (b7) r6 = -1
   6: (2d) if r4 > r6 goto pc+5
  R1=ctx R2=imm0,min_value=0,max_value=0,min_align=2147483648 R3=fp-512
  R4=inv,min_value=0 R6=imm-1,max_value=18446744073709551615,min_align=1 R10=fp
   7: (65) if r4 s> 0x1 goto pc+4
  R1=ctx R2=imm0,min_value=0,max_value=0,min_align=2147483648 R3=fp-512
  R4=inv,min_value=0,max_value=1 R6=imm-1,max_value=18446744073709551615,min_align=1
  R10=fp
   8: (07) r4 += 1
   9: (b7) r5 = 0
  10: (6a) *(u16 *)(r10 -512) = 0
  11: (85) call bpf_skb_load_bytes#26
  12: (b7) r0 = 0
  13: (95) exit

Meaning, while we initialize the max_value stack slot that the
verifier thinks we access in the [1,2] range, in reality we
pass -7 as length which is interpreted as u32 in the helper.
Thus, this issue is relevant also for the case of helper ranges.
Resetting both bounds in check_reg_overflow() in case only one
of them exceeds limits is also not enough as similar test can be
created that uses values which are within range, thus also here
learned min value in r1 is incorrect when mixed with later signed
test to create a range:

   0: (7a) *(u64 *)(r10 -8) = 0
   1: (bf) r2 = r10
   2: (07) r2 += -8
   3: (18) r1 = 0xffff880ad081fa00
   5: (85) call bpf_map_lookup_elem#1
   6: (15) if r0 == 0x0 goto pc+7
  R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R10=fp
   7: (7a) *(u64 *)(r10 -16) = -8
   8: (79) r1 = *(u64 *)(r10 -16)
   9: (b7) r2 = 2
  10: (3d) if r2 >= r1 goto pc+3
  R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R1=inv,min_value=3
  R2=imm2,min_value=2,max_value=2,min_align=2 R10=fp
  11: (65) if r1 s> 0x4 goto pc+2
  R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0
  R1=inv,min_value=3,max_value=4 R2=imm2,min_value=2,max_value=2,min_align=2 R10=fp
  12: (0f) r0 += r1
  13: (72) *(u8 *)(r0 +0) = 0
  R0=map_value_adj(ks=8,vs=8,id=0),min_value=3,max_value=4
  R1=inv,min_value=3,max_value=4 R2=imm2,min_value=2,max_value=2,min_align=2 R10=fp
  14: (b7) r0 = 0
  15: (95) exit

This leaves us with two options for fixing this: i) to invalidate
all prior learned information once we switch signed context, ii)
to track min/max signed and unsigned boundaries separately as
done in [0]. (Given latter introduces major changes throughout
the whole verifier, it's rather net-next material, thus this
patch follows option i), meaning we can derive bounds either
from only signed tests or only unsigned tests.) There is still the
case of adjust_reg_min_max_vals(), where we adjust bounds on ALU
operations, meaning programs like the following where boundaries
on the reg get mixed in context later on when bounds are merged
on the dst reg must get rejected, too:

   0: (7a) *(u64 *)(r10 -8) = 0
   1: (bf) r2 = r10
   2: (07) r2 += -8
   3: (18) r1 = 0xffff89b2bf87ce00
   5: (85) call bpf_map_lookup_elem#1
   6: (15) if r0 == 0x0 goto pc+6
  R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R10=fp
   7: (7a) *(u64 *)(r10 -16) = -8
   8: (79) r1 = *(u64 *)(r10 -16)
   9: (b7) r2 = 2
  10: (3d) if r2 >= r1 goto pc+2
  R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R1=inv,min_value=3
  R2=imm2,min_value=2,max_value=2,min_align=2 R10=fp
  11: (b7) r7 = 1
  12: (65) if r7 s> 0x0 goto pc+2
  R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R1=inv,min_value=3
  R2=imm2,min_value=2,max_value=2,min_align=2 R7=imm1,max_value=0 R10=fp
  13: (b7) r0 = 0
  14: (95) exit

  from 12 to 15: R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0
  R1=inv,min_value=3 R2=imm2,min_value=2,max_value=2,min_align=2 R7=imm1,min_value=1 R10=fp
  15: (0f) r7 += r1
  16: (65) if r7 s> 0x4 goto pc+2
  R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R1=inv,min_value=3
  R2=imm2,min_value=2,max_value=2,min_align=2 R7=inv,min_value=4,max_value=4 R10=fp
  17: (0f) r0 += r7
  18: (72) *(u8 *)(r0 +0) = 0
  R0=map_value_adj(ks=8,vs=8,id=0),min_value=4,max_value=4 R1=inv,min_value=3
  R2=imm2,min_value=2,max_value=2,min_align=2 R7=inv,min_value=4,max_value=4 R10=fp
  19: (b7) r0 = 0
  20: (95) exit

Meaning, in adjust_reg_min_max_vals() we must also reset range
values on the dst when src/dst registers have mixed signed/
unsigned derived min/max value bounds with one unbounded value
as otherwise they can be added together deducing false boundaries.
Once both boundaries are established from either ALU ops or
compare operations w/o mixing signed/unsigned insns, then they
can safely be added to other regs also having both boundaries
established. Adding regs with one unbounded side to a map value
where the bounded side has been learned w/o mixing ops is
possible, but the resulting map value won't recover from that,
meaning such op is considered invalid on the time of actual
access. Invalid bounds are set on the dst reg in case i) src reg,
or ii) in case dst reg already had them. The only way to recover
would be to perform i) ALU ops but only 'add' is allowed on map
value types or ii) comparisons, but these are disallowed on
pointers in case they span a range. This is fine as only BPF_JEQ
and BPF_JNE may be performed on PTR_TO_MAP_VALUE_OR_NULL registers
which potentially turn them into PTR_TO_MAP_VALUE type depending
on the branch, so only here min/max value cannot be invalidated
for them.

In terms of state pruning, value_from_signed is considered
as well in states_equal() when dealing with adjusted map values.
With regards to breaking existing programs, there is a small
risk, but use-cases are rather quite narrow where this could
occur and mixing compares probably unlikely.

Joint work with Josef and Edward.

  [0] https://lists.iovisor.org/pipermail/iovisor-dev/2017-June/000822.html

Fixes: 484611357c19 ("bpf: allow access into map value arrays")
Reported-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/bpf_verifier.h |   1 +
 kernel/bpf/verifier.c        | 108 +++++++++++++++++++++++++++++++++++++------
 2 files changed, 95 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 621076f56251..8e5d31f6faef 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -43,6 +43,7 @@ struct bpf_reg_state {
 	u32 min_align;
 	u32 aux_off;
 	u32 aux_off_align;
+	bool value_from_signed;
 };
 
 enum bpf_stack_slot_type {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 6a86723c5b64..af9e84a4944e 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -504,6 +504,7 @@ static void reset_reg_range_values(struct bpf_reg_state *regs, u32 regno)
 {
 	regs[regno].min_value = BPF_REGISTER_MIN_RANGE;
 	regs[regno].max_value = BPF_REGISTER_MAX_RANGE;
+	regs[regno].value_from_signed = false;
 	regs[regno].min_align = 0;
 }
 
@@ -777,12 +778,13 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off,
 	return -EACCES;
 }
 
-static bool is_pointer_value(struct bpf_verifier_env *env, int regno)
+static bool __is_pointer_value(bool allow_ptr_leaks,
+			       const struct bpf_reg_state *reg)
 {
-	if (env->allow_ptr_leaks)
+	if (allow_ptr_leaks)
 		return false;
 
-	switch (env->cur_state.regs[regno].type) {
+	switch (reg->type) {
 	case UNKNOWN_VALUE:
 	case CONST_IMM:
 		return false;
@@ -791,6 +793,11 @@ static bool is_pointer_value(struct bpf_verifier_env *env, int regno)
 	}
 }
 
+static bool is_pointer_value(struct bpf_verifier_env *env, int regno)
+{
+	return __is_pointer_value(env->allow_ptr_leaks, &env->cur_state.regs[regno]);
+}
+
 static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg,
 				   int off, int size, bool strict)
 {
@@ -1832,10 +1839,24 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 	dst_align = dst_reg->min_align;
 
 	/* We don't know anything about what was done to this register, mark it
-	 * as unknown.
+	 * as unknown. Also, if both derived bounds came from signed/unsigned
+	 * mixed compares and one side is unbounded, we cannot really do anything
+	 * with them as boundaries cannot be trusted. Thus, arithmetic of two
+	 * regs of such kind will get invalidated bounds on the dst side.
 	 */
-	if (min_val == BPF_REGISTER_MIN_RANGE &&
-	    max_val == BPF_REGISTER_MAX_RANGE) {
+	if ((min_val == BPF_REGISTER_MIN_RANGE &&
+	     max_val == BPF_REGISTER_MAX_RANGE) ||
+	    (BPF_SRC(insn->code) == BPF_X &&
+	     ((min_val != BPF_REGISTER_MIN_RANGE &&
+	       max_val == BPF_REGISTER_MAX_RANGE) ||
+	      (min_val == BPF_REGISTER_MIN_RANGE &&
+	       max_val != BPF_REGISTER_MAX_RANGE) ||
+	      (dst_reg->min_value != BPF_REGISTER_MIN_RANGE &&
+	       dst_reg->max_value == BPF_REGISTER_MAX_RANGE) ||
+	      (dst_reg->min_value == BPF_REGISTER_MIN_RANGE &&
+	       dst_reg->max_value != BPF_REGISTER_MAX_RANGE)) &&
+	     regs[insn->dst_reg].value_from_signed !=
+	     regs[insn->src_reg].value_from_signed)) {
 		reset_reg_range_values(regs, insn->dst_reg);
 		return;
 	}
@@ -2023,6 +2044,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 			regs[insn->dst_reg].max_value = insn->imm;
 			regs[insn->dst_reg].min_value = insn->imm;
 			regs[insn->dst_reg].min_align = calc_align(insn->imm);
+			regs[insn->dst_reg].value_from_signed = false;
 		}
 
 	} else if (opcode > BPF_END) {
@@ -2198,40 +2220,63 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg,
 			    struct bpf_reg_state *false_reg, u64 val,
 			    u8 opcode)
 {
+	bool value_from_signed = true;
+	bool is_range = true;
+
 	switch (opcode) {
 	case BPF_JEQ:
 		/* If this is false then we know nothing Jon Snow, but if it is
 		 * true then we know for sure.
 		 */
 		true_reg->max_value = true_reg->min_value = val;
+		is_range = false;
 		break;
 	case BPF_JNE:
 		/* If this is true we know nothing Jon Snow, but if it is false
 		 * we know the value for sure;
 		 */
 		false_reg->max_value = false_reg->min_value = val;
+		is_range = false;
 		break;
 	case BPF_JGT:
-		/* Unsigned comparison, the minimum value is 0. */
-		false_reg->min_value = 0;
+		value_from_signed = false;
 		/* fallthrough */
 	case BPF_JSGT:
+		if (true_reg->value_from_signed != value_from_signed)
+			reset_reg_range_values(true_reg, 0);
+		if (false_reg->value_from_signed != value_from_signed)
+			reset_reg_range_values(false_reg, 0);
+		if (opcode == BPF_JGT) {
+			/* Unsigned comparison, the minimum value is 0. */
+			false_reg->min_value = 0;
+		}
 		/* If this is false then we know the maximum val is val,
 		 * otherwise we know the min val is val+1.
 		 */
 		false_reg->max_value = val;
+		false_reg->value_from_signed = value_from_signed;
 		true_reg->min_value = val + 1;
+		true_reg->value_from_signed = value_from_signed;
 		break;
 	case BPF_JGE:
-		/* Unsigned comparison, the minimum value is 0. */
-		false_reg->min_value = 0;
+		value_from_signed = false;
 		/* fallthrough */
 	case BPF_JSGE:
+		if (true_reg->value_from_signed != value_from_signed)
+			reset_reg_range_values(true_reg, 0);
+		if (false_reg->value_from_signed != value_from_signed)
+			reset_reg_range_values(false_reg, 0);
+		if (opcode == BPF_JGE) {
+			/* Unsigned comparison, the minimum value is 0. */
+			false_reg->min_value = 0;
+		}
 		/* If this is false then we know the maximum value is val - 1,
 		 * otherwise we know the mimimum value is val.
 		 */
 		false_reg->max_value = val - 1;
+		false_reg->value_from_signed = value_from_signed;
 		true_reg->min_value = val;
+		true_reg->value_from_signed = value_from_signed;
 		break;
 	default:
 		break;
@@ -2239,6 +2284,12 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg,
 
 	check_reg_overflow(false_reg);
 	check_reg_overflow(true_reg);
+	if (is_range) {
+		if (__is_pointer_value(false, false_reg))
+			reset_reg_range_values(false_reg, 0);
+		if (__is_pointer_value(false, true_reg))
+			reset_reg_range_values(true_reg, 0);
+	}
 }
 
 /* Same as above, but for the case that dst_reg is a CONST_IMM reg and src_reg
@@ -2248,41 +2299,64 @@ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
 				struct bpf_reg_state *false_reg, u64 val,
 				u8 opcode)
 {
+	bool value_from_signed = true;
+	bool is_range = true;
+
 	switch (opcode) {
 	case BPF_JEQ:
 		/* If this is false then we know nothing Jon Snow, but if it is
 		 * true then we know for sure.
 		 */
 		true_reg->max_value = true_reg->min_value = val;
+		is_range = false;
 		break;
 	case BPF_JNE:
 		/* If this is true we know nothing Jon Snow, but if it is false
 		 * we know the value for sure;
 		 */
 		false_reg->max_value = false_reg->min_value = val;
+		is_range = false;
 		break;
 	case BPF_JGT:
-		/* Unsigned comparison, the minimum value is 0. */
-		true_reg->min_value = 0;
+		value_from_signed = false;
 		/* fallthrough */
 	case BPF_JSGT:
+		if (true_reg->value_from_signed != value_from_signed)
+			reset_reg_range_values(true_reg, 0);
+		if (false_reg->value_from_signed != value_from_signed)
+			reset_reg_range_values(false_reg, 0);
+		if (opcode == BPF_JGT) {
+			/* Unsigned comparison, the minimum value is 0. */
+			true_reg->min_value = 0;
+		}
 		/*
 		 * If this is false, then the val is <= the register, if it is
 		 * true the register <= to the val.
 		 */
 		false_reg->min_value = val;
+		false_reg->value_from_signed = value_from_signed;
 		true_reg->max_value = val - 1;
+		true_reg->value_from_signed = value_from_signed;
 		break;
 	case BPF_JGE:
-		/* Unsigned comparison, the minimum value is 0. */
-		true_reg->min_value = 0;
+		value_from_signed = false;
 		/* fallthrough */
 	case BPF_JSGE:
+		if (true_reg->value_from_signed != value_from_signed)
+			reset_reg_range_values(true_reg, 0);
+		if (false_reg->value_from_signed != value_from_signed)
+			reset_reg_range_values(false_reg, 0);
+		if (opcode == BPF_JGE) {
+			/* Unsigned comparison, the minimum value is 0. */
+			true_reg->min_value = 0;
+		}
 		/* If this is false then constant < register, if it is true then
 		 * the register < constant.
 		 */
 		false_reg->min_value = val + 1;
+		false_reg->value_from_signed = value_from_signed;
 		true_reg->max_value = val;
+		true_reg->value_from_signed = value_from_signed;
 		break;
 	default:
 		break;
@@ -2290,6 +2364,12 @@ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
 
 	check_reg_overflow(false_reg);
 	check_reg_overflow(true_reg);
+	if (is_range) {
+		if (__is_pointer_value(false, false_reg))
+			reset_reg_range_values(false_reg, 0);
+		if (__is_pointer_value(false, true_reg))
+			reset_reg_range_values(true_reg, 0);
+	}
 }
 
 static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id,
-- 
cgit v1.2.3


From bd8b2441742b49c76bec707757bd9c028ea9838e Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@primarydata.com>
Date: Tue, 11 Jul 2017 17:54:34 -0400
Subject: NFS: Store the raw NFS access mask in the inode's access cache

Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/dir.c           | 9 ++++++---
 include/linux/nfs_fs.h | 2 +-
 2 files changed, 7 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 24b3a6748062..8fae8b00b8f5 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -2399,7 +2399,7 @@ nfs_access_calc_mask(u32 access_result)
 
 void nfs_access_set_mask(struct nfs_access_entry *entry, u32 access_result)
 {
-	entry->mask = nfs_access_calc_mask(access_result);
+	entry->mask = access_result;
 }
 EXPORT_SYMBOL_GPL(nfs_access_set_mask);
 
@@ -2407,6 +2407,7 @@ static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask)
 {
 	struct nfs_access_entry cache;
 	bool may_block = (mask & MAY_NOT_BLOCK) == 0;
+	int cache_mask;
 	int status;
 
 	trace_nfs_access_enter(inode);
@@ -2422,7 +2423,8 @@ static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask)
 		goto out;
 
 	/* Be clever: ask server to check for all possible rights */
-	cache.mask = MAY_EXEC | MAY_WRITE | MAY_READ;
+	cache.mask = NFS_MAY_LOOKUP | NFS_MAY_EXECUTE
+		     | NFS_MAY_WRITE | NFS_MAY_READ;
 	cache.cred = cred;
 	cache.jiffies = jiffies;
 	status = NFS_PROTO(inode)->access(inode, &cache);
@@ -2436,7 +2438,8 @@ static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask)
 	}
 	nfs_access_add_cache(inode, &cache);
 out_cached:
-	if ((mask & ~cache.mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) != 0)
+	cache_mask = nfs_access_calc_mask(cache.mask);
+	if ((mask & ~cache_mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) != 0)
 		status = -EACCES;
 out:
 	trace_nfs_access_exit(inode, status);
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index e52cc55ac300..5cc91d6381a3 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -51,7 +51,7 @@ struct nfs_access_entry {
 	struct list_head	lru;
 	unsigned long		jiffies;
 	struct rpc_cred *	cred;
-	int			mask;
+	__u32			mask;
 	struct rcu_head		rcu_head;
 };
 
-- 
cgit v1.2.3


From 96edd61dcf44362d3ef0bed1a5361e0ac7886a63 Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Mon, 10 Jul 2017 10:10:45 +0200
Subject: xen/balloon: don't online new memory initially

When setting up the Xenstore watch for the memory target size the new
watch will fire at once. Don't try to reach the configured target size
by onlining new memory in this case, as the current memory size will
be smaller in almost all cases due to e.g. BIOS reserved pages.

Onlining new memory will lead to more problems e.g. undesired conflicts
with NVMe devices meant to be operated as block devices.

Instead remember the difference between target size and current size
when the watch fires for the first time and apply it to any further
size changes, too.

In order to avoid races between balloon.c and xen-balloon.c init calls
do the xen-balloon.c initialization from balloon.c.

Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
---
 drivers/xen/balloon.c     |  3 +++
 drivers/xen/xen-balloon.c | 22 ++++++++++++----------
 include/xen/balloon.h     |  8 ++++++++
 3 files changed, 23 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 50dcb68d8070..ab609255a0f3 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -780,6 +780,9 @@ static int __init balloon_init(void)
 	}
 #endif
 
+	/* Init the xen-balloon driver. */
+	xen_balloon_init();
+
 	return 0;
 }
 subsys_initcall(balloon_init);
diff --git a/drivers/xen/xen-balloon.c b/drivers/xen/xen-balloon.c
index e7715cb62eef..e89136ab851e 100644
--- a/drivers/xen/xen-balloon.c
+++ b/drivers/xen/xen-balloon.c
@@ -59,6 +59,8 @@ static void watch_target(struct xenbus_watch *watch,
 {
 	unsigned long long new_target;
 	int err;
+	static bool watch_fired;
+	static long target_diff;
 
 	err = xenbus_scanf(XBT_NIL, "memory", "target", "%llu", &new_target);
 	if (err != 1) {
@@ -69,7 +71,14 @@ static void watch_target(struct xenbus_watch *watch,
 	/* The given memory/target value is in KiB, so it needs converting to
 	 * pages. PAGE_SHIFT converts bytes to pages, hence PAGE_SHIFT - 10.
 	 */
-	balloon_set_new_target(new_target >> (PAGE_SHIFT - 10));
+	new_target >>= PAGE_SHIFT - 10;
+	if (watch_fired) {
+		balloon_set_new_target(new_target - target_diff);
+		return;
+	}
+
+	watch_fired = true;
+	target_diff = new_target - balloon_stats.target_pages;
 }
 static struct xenbus_watch target_watch = {
 	.node = "memory/target",
@@ -94,22 +103,15 @@ static struct notifier_block xenstore_notifier = {
 	.notifier_call = balloon_init_watcher,
 };
 
-static int __init balloon_init(void)
+void xen_balloon_init(void)
 {
-	if (!xen_domain())
-		return -ENODEV;
-
-	pr_info("Initialising balloon driver\n");
-
 	register_balloon(&balloon_dev);
 
 	register_xen_selfballooning(&balloon_dev);
 
 	register_xenstore_notifier(&xenstore_notifier);
-
-	return 0;
 }
-subsys_initcall(balloon_init);
+EXPORT_SYMBOL_GPL(xen_balloon_init);
 
 #define BALLOON_SHOW(name, format, args...)				\
 	static ssize_t show_##name(struct device *dev,			\
diff --git a/include/xen/balloon.h b/include/xen/balloon.h
index d1767dfb0d95..8906361bb50c 100644
--- a/include/xen/balloon.h
+++ b/include/xen/balloon.h
@@ -35,3 +35,11 @@ static inline int register_xen_selfballooning(struct device *dev)
 	return -ENOSYS;
 }
 #endif
+
+#ifdef CONFIG_XEN_BALLOON
+void xen_balloon_init(void);
+#else
+static inline void xen_balloon_init(void)
+{
+}
+#endif
-- 
cgit v1.2.3


From 581c4484769e692eade761c17c22549aaefe6749 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 1 Aug 2017 15:38:01 -0700
Subject: HID: input: map digitizer battery usage

We already mapped battery strength reports from the generic device
control page, but we did not update capacity from input reports, nor we
mapped the battery strength report from the digitizer page, so let's
implement this now.

Batteries driven by the input reports will now start in "unknown" state,
and will get updated once we receive first report containing battery
strength from the device.

Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/hid-input.c | 184 ++++++++++++++++++++++++++++++++----------------
 include/linux/hid.h     |   2 +
 2 files changed, 127 insertions(+), 59 deletions(-)

(limited to 'include')

diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index ccdff1ee1f0c..2158ec766dd5 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -340,13 +340,45 @@ static unsigned find_battery_quirk(struct hid_device *hdev)
 	return quirks;
 }
 
+static int hidinput_scale_battery_capacity(struct hid_device *dev,
+					   int value)
+{
+	if (dev->battery_min < dev->battery_max &&
+	    value >= dev->battery_min && value <= dev->battery_max)
+		value = ((value - dev->battery_min) * 100) /
+			(dev->battery_max - dev->battery_min);
+
+	return value;
+}
+
+static int hidinput_query_battery_capacity(struct hid_device *dev)
+{
+	u8 *buf;
+	int ret;
+
+	buf = kmalloc(2, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	ret = hid_hw_raw_request(dev, dev->battery_report_id, buf, 2,
+				 dev->battery_report_type, HID_REQ_GET_REPORT);
+	if (ret != 2) {
+		kfree(buf);
+		return -ENODATA;
+	}
+
+	ret = hidinput_scale_battery_capacity(dev, buf[1]);
+	kfree(buf);
+	return ret;
+}
+
 static int hidinput_get_battery_property(struct power_supply *psy,
 					 enum power_supply_property prop,
 					 union power_supply_propval *val)
 {
 	struct hid_device *dev = power_supply_get_drvdata(psy);
+	int value;
 	int ret = 0;
-	__u8 *buf;
 
 	switch (prop) {
 	case POWER_SUPPLY_PROP_PRESENT:
@@ -355,29 +387,15 @@ static int hidinput_get_battery_property(struct power_supply *psy,
 		break;
 
 	case POWER_SUPPLY_PROP_CAPACITY:
-
-		buf = kmalloc(2 * sizeof(__u8), GFP_KERNEL);
-		if (!buf) {
-			ret = -ENOMEM;
-			break;
-		}
-		ret = hid_hw_raw_request(dev, dev->battery_report_id, buf, 2,
-					 dev->battery_report_type,
-					 HID_REQ_GET_REPORT);
-
-		if (ret != 2) {
-			ret = -ENODATA;
-			kfree(buf);
-			break;
+		if (dev->battery_report_type == HID_FEATURE_REPORT) {
+			value = hidinput_query_battery_capacity(dev);
+			if (value < 0)
+				return value;
+		} else  {
+			value = dev->battery_capacity;
 		}
-		ret = 0;
 
-		if (dev->battery_min < dev->battery_max &&
-		    buf[1] >= dev->battery_min &&
-		    buf[1] <= dev->battery_max)
-			val->intval = (100 * (buf[1] - dev->battery_min)) /
-				(dev->battery_max - dev->battery_min);
-		kfree(buf);
+		val->intval = value;
 		break;
 
 	case POWER_SUPPLY_PROP_MODEL_NAME:
@@ -385,7 +403,22 @@ static int hidinput_get_battery_property(struct power_supply *psy,
 		break;
 
 	case POWER_SUPPLY_PROP_STATUS:
-		val->intval = POWER_SUPPLY_STATUS_DISCHARGING;
+		if (!dev->battery_reported &&
+		    dev->battery_report_type == HID_FEATURE_REPORT) {
+			value = hidinput_query_battery_capacity(dev);
+			if (value < 0)
+				return value;
+
+			dev->battery_capacity = value;
+			dev->battery_reported = true;
+		}
+
+		if (!dev->battery_reported)
+			val->intval = POWER_SUPPLY_STATUS_UNKNOWN;
+		else if (dev->battery_capacity == 100)
+			val->intval = POWER_SUPPLY_STATUS_FULL;
+		else
+			val->intval = POWER_SUPPLY_STATUS_DISCHARGING;
 		break;
 
 	case POWER_SUPPLY_PROP_SCOPE:
@@ -400,18 +433,16 @@ static int hidinput_get_battery_property(struct power_supply *psy,
 	return ret;
 }
 
-static bool hidinput_setup_battery(struct hid_device *dev, unsigned report_type, struct hid_field *field)
+static int hidinput_setup_battery(struct hid_device *dev, unsigned report_type, struct hid_field *field)
 {
-	struct power_supply_desc *psy_desc = NULL;
+	struct power_supply_desc *psy_desc;
 	struct power_supply_config psy_cfg = { .drv_data = dev, };
 	unsigned quirks;
 	s32 min, max;
+	int error;
 
-	if (field->usage->hid != HID_DC_BATTERYSTRENGTH)
-		return false;	/* no match */
-
-	if (dev->battery != NULL)
-		goto out;	/* already initialized? */
+	if (dev->battery)
+		return 0;	/* already initialized? */
 
 	quirks = find_battery_quirk(dev);
 
@@ -419,16 +450,16 @@ static bool hidinput_setup_battery(struct hid_device *dev, unsigned report_type,
 		dev->bus, dev->vendor, dev->product, dev->version, quirks);
 
 	if (quirks & HID_BATTERY_QUIRK_IGNORE)
-		goto out;
+		return 0;
 
 	psy_desc = kzalloc(sizeof(*psy_desc), GFP_KERNEL);
-	if (psy_desc == NULL)
-		goto out;
+	if (!psy_desc)
+		return -ENOMEM;
 
 	psy_desc->name = kasprintf(GFP_KERNEL, "hid-%s-battery", dev->uniq);
-	if (psy_desc->name == NULL) {
-		kfree(psy_desc);
-		goto out;
+	if (!psy_desc->name) {
+		error = -ENOMEM;
+		goto err_free_mem;
 	}
 
 	psy_desc->type = POWER_SUPPLY_TYPE_BATTERY;
@@ -455,17 +486,20 @@ static bool hidinput_setup_battery(struct hid_device *dev, unsigned report_type,
 
 	dev->battery = power_supply_register(&dev->dev, psy_desc, &psy_cfg);
 	if (IS_ERR(dev->battery)) {
-		hid_warn(dev, "can't register power supply: %ld\n",
-				PTR_ERR(dev->battery));
-		kfree(psy_desc->name);
-		kfree(psy_desc);
-		dev->battery = NULL;
-	} else {
-		power_supply_powers(dev->battery, &dev->dev);
+		error = PTR_ERR(dev->battery);
+		hid_warn(dev, "can't register power supply: %d\n", error);
+		goto err_free_name;
 	}
 
-out:
-	return true;
+	power_supply_powers(dev->battery, &dev->dev);
+	return 0;
+
+err_free_name:
+	kfree(psy_desc->name);
+err_free_mem:
+	kfree(psy_desc);
+	dev->battery = NULL;
+	return error;
 }
 
 static void hidinput_cleanup_battery(struct hid_device *dev)
@@ -481,16 +515,33 @@ static void hidinput_cleanup_battery(struct hid_device *dev)
 	kfree(psy_desc);
 	dev->battery = NULL;
 }
+
+static void hidinput_update_battery(struct hid_device *dev, int value)
+{
+	if (!dev->battery)
+		return;
+
+	if (value == 0 || value < dev->battery_min || value > dev->battery_max)
+		return;
+
+	dev->battery_capacity = hidinput_scale_battery_capacity(dev, value);
+	dev->battery_reported = true;
+	power_supply_changed(dev->battery);
+}
 #else  /* !CONFIG_HID_BATTERY_STRENGTH */
-static bool hidinput_setup_battery(struct hid_device *dev, unsigned report_type,
-				   struct hid_field *field)
+static int hidinput_setup_battery(struct hid_device *dev, unsigned report_type,
+				  struct hid_field *field)
 {
-	return false;
+	return 0;
 }
 
 static void hidinput_cleanup_battery(struct hid_device *dev)
 {
 }
+
+static void hidinput_update_battery(struct hid_device *dev, int value)
+{
+}
 #endif	/* CONFIG_HID_BATTERY_STRENGTH */
 
 static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_field *field,
@@ -710,6 +761,11 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel
 			}
 			break;
 
+		case 0x3b: /* Battery Strength */
+			hidinput_setup_battery(device, HID_INPUT_REPORT, field);
+			usage->type = EV_PWR;
+			goto ignore;
+
 		case 0x3c: /* Invert */
 			map_key_clear(BTN_TOOL_RUBBER);
 			break;
@@ -944,11 +1000,13 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel
 		break;
 
 	case HID_UP_GENDEVCTRLS:
-		if (hidinput_setup_battery(device, HID_INPUT_REPORT, field))
+		switch (usage->hid) {
+		case HID_DC_BATTERYSTRENGTH:
+			hidinput_setup_battery(device, HID_INPUT_REPORT, field);
+			usage->type = EV_PWR;
 			goto ignore;
-		else
-			goto unknown;
-		break;
+		}
+		goto unknown;
 
 	case HID_UP_HPVENDOR:	/* Reported on a Dutch layout HP5308 */
 		set_bit(EV_REP, input->evbit);
@@ -1031,7 +1089,6 @@ mapped:
 	if (usage->code > max)
 		goto ignore;
 
-
 	if (usage->type == EV_ABS) {
 
 		int a = field->logical_minimum;
@@ -1090,14 +1147,19 @@ void hidinput_hid_event(struct hid_device *hid, struct hid_field *field, struct
 	struct input_dev *input;
 	unsigned *quirks = &hid->quirks;
 
-	if (!field->hidinput)
+	if (!usage->type)
 		return;
 
-	input = field->hidinput->input;
+	if (usage->type == EV_PWR) {
+		hidinput_update_battery(hid, value);
+		return;
+	}
 
-	if (!usage->type)
+	if (!field->hidinput)
 		return;
 
+	input = field->hidinput->input;
+
 	if (usage->hat_min < usage->hat_max || usage->hat_dir) {
 		int hat_dir = usage->hat_dir;
 		if (!hat_dir)
@@ -1373,6 +1435,7 @@ static void report_features(struct hid_device *hid)
 	struct hid_driver *drv = hid->driver;
 	struct hid_report_enum *rep_enum;
 	struct hid_report *rep;
+	struct hid_usage *usage;
 	int i, j;
 
 	rep_enum = &hid->report_enum[HID_FEATURE_REPORT];
@@ -1383,12 +1446,15 @@ static void report_features(struct hid_device *hid)
 				continue;
 
 			for (j = 0; j < rep->field[i]->maxusage; j++) {
+				usage = &rep->field[i]->usage[j];
+
 				/* Verify if Battery Strength feature is available */
-				hidinput_setup_battery(hid, HID_FEATURE_REPORT, rep->field[i]);
+				if (usage->hid == HID_DC_BATTERYSTRENGTH)
+					hidinput_setup_battery(hid, HID_FEATURE_REPORT,
+							       rep->field[i]);
 
 				if (drv->feature_mapping)
-					drv->feature_mapping(hid, rep->field[i],
-							     rep->field[i]->usage + j);
+					drv->feature_mapping(hid, rep->field[i], usage);
 			}
 		}
 }
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 5006f9b5d837..281d1ffcbe02 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -542,10 +542,12 @@ struct hid_device {							/* device report descriptor */
 	 * battery is non-NULL.
 	 */
 	struct power_supply *battery;
+	__s32 battery_capacity;
 	__s32 battery_min;
 	__s32 battery_max;
 	__s32 battery_report_type;
 	__s32 battery_report_id;
+	bool battery_reported;
 #endif
 
 	unsigned int status;						/* see STAT flags above */
-- 
cgit v1.2.3