From 34c06254ff82a815fdccdfae7517a06c9b768cee Mon Sep 17 00:00:00 2001
From: Tejun Heo
Date: Thu, 5 Nov 2015 00:12:24 -0500
Subject: cgroup: fix cftype->file_offset handling

6f60eade2433 ("cgroup: generalize obtaining the handles of and
notifying cgroup files") introduced cftype->file_offset so that the
handles for per-css file instances can be recorded.  These handles
then can be used, for example, to generate file modified
notifications.

Unfortunately, it made the wrong assumption that files are created
once for a given css and removed on its destruction.  Due to the
dependencies among subsystems, a css may be hidden from userland and
then later shown again.  This is implemented by removing and
re-creating the affected files, so the associated kernfs_node for a
given cgroup file may change over time.  This incorrect assumption led
to the corruption of css->files lists.

Reimplement cftype->file_offset handling so that cgroup_file->kn is
protected by a lock and updated as files are created and destroyed.
This also makes keeping them on per-cgroup list unnecessary.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: James Sedgwick <jsedgwick@fb.com>
Fixes: 6f60eade2433 ("cgroup: generalize obtaining the handles of and notifying cgroup files")
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Zefan Li <lizefan@huawei.com>
---
 include/linux/cgroup-defs.h |  4 ----
 include/linux/cgroup.h      | 14 +-------------
 2 files changed, 1 insertion(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 60d44b26276d..869fd4a3d28e 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -90,7 +90,6 @@ enum {
  */
 struct cgroup_file {
 	/* do not access any fields from outside cgroup core */
-	struct list_head node;			/* anchored at css->files */
 	struct kernfs_node *kn;
 };
 
@@ -134,9 +133,6 @@ struct cgroup_subsys_state {
 	 */
 	u64 serial_nr;
 
-	/* all cgroup_files associated with this css */
-	struct list_head files;
-
 	/* percpu_ref killing and RCU release */
 	struct rcu_head rcu_head;
 	struct work_struct destroy_work;
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 22e3754f89c5..f64083030ad5 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -88,6 +88,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from);
 int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
 int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
 int cgroup_rm_cftypes(struct cftype *cfts);
+void cgroup_file_notify(struct cgroup_file *cfile);
 
 char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen);
 int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry);
@@ -516,19 +517,6 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp)
 	pr_cont_kernfs_path(cgrp->kn);
 }
 
-/**
- * cgroup_file_notify - generate a file modified event for a cgroup_file
- * @cfile: target cgroup_file
- *
- * @cfile must have been obtained by setting cftype->file_offset.
- */
-static inline void cgroup_file_notify(struct cgroup_file *cfile)
-{
-	/* might not have been created due to one of the CFTYPE selector flags */
-	if (cfile->kn)
-		kernfs_notify(cfile->kn);
-}
-
 #else /* !CONFIG_CGROUPS */
 
 struct cgroup_subsys_state;
-- 
cgit v1.2.3


From aedf17f4515b12ba1cd73298e66baa69cf93010e Mon Sep 17 00:00:00 2001
From: Matias Bjørling
Date: Mon, 16 Nov 2015 15:34:36 +0100
Subject: lightnvm: change max_phys_sect to uint

The max_phys_sect variable is defined as a char. We do a boundary check
to maximally allow 256 physical page descriptors per command. As we are
not indexing from zero. This expression is always false. Bump the
max_phys_sect to an unsigned int to support the range check.

Signed-off-by: Matias Bjørling <m@bjorling.me>
Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 include/linux/lightnvm.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index 69c9057e1ab8..32b5369e814e 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -220,7 +220,7 @@ struct nvm_dev_ops {
 	nvm_dev_dma_alloc_fn	*dev_dma_alloc;
 	nvm_dev_dma_free_fn	*dev_dma_free;
 
-	uint8_t			max_phys_sect;
+	unsigned int		max_phys_sect;
 };
 
 struct nvm_lun {
-- 
cgit v1.2.3


From 11450469830f2481a9e7cb181609288d40f41323 Mon Sep 17 00:00:00 2001
From: Matias Bjørling
Date: Mon, 16 Nov 2015 15:34:37 +0100
Subject: lightnvm: update bad block table format

The specification was changed to reflect a multi-value bad block table.
Instead of bit-based bad block table, the bad block table now allows
eight bad block categories. Currently four are defined:

 * Factory bad blocks
 * Grown bad blocks
 * Device-side reserved blocks
 * Host-side reserved blocks

The factory and grown bad blocks are the regular bad blocks. The
reserved blocks are either for internal use or external use. In
particular, the device-side reserved blocks allows the host to
bootstrap from a limited number of flash blocks. Reducing the flash
blocks to scan upon super block initialization.

Support for both get bad block table and set bad block table is added.

Signed-off-by: Matias Bjørling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 drivers/lightnvm/gennvm.c    |  32 ++++++++----
 drivers/lightnvm/gennvm.h    |   2 +
 drivers/nvme/host/lightnvm.c | 113 ++++++++++++++++++++++++++++++++++---------
 include/linux/lightnvm.h     |   6 +--
 4 files changed, 117 insertions(+), 36 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/lightnvm/gennvm.c b/drivers/lightnvm/gennvm.c
index ae1fb2bdc5f4..8cfc0114ff13 100644
--- a/drivers/lightnvm/gennvm.c
+++ b/drivers/lightnvm/gennvm.c
@@ -64,19 +64,22 @@ static int gennvm_luns_init(struct nvm_dev *dev, struct gen_nvm *gn)
 	return 0;
 }
 
-static int gennvm_block_bb(u32 lun_id, void *bb_bitmap, unsigned int nr_blocks,
+static int gennvm_block_bb(struct ppa_addr ppa, int nr_blocks, u8 *blks,
 								void *private)
 {
 	struct gen_nvm *gn = private;
-	struct gen_lun *lun = &gn->luns[lun_id];
+	struct nvm_dev *dev = gn->dev;
+	struct gen_lun *lun;
 	struct nvm_block *blk;
 	int i;
 
-	if (unlikely(bitmap_empty(bb_bitmap, nr_blocks)))
-		return 0;
+	ppa = addr_to_generic_mode(gn->dev, ppa);
+	lun = &gn->luns[(dev->nr_luns * ppa.g.ch) + ppa.g.lun];
+
+	for (i = 0; i < nr_blocks; i++) {
+		if (blks[i] == 0)
+			continue;
 
-	i = -1;
-	while ((i = find_next_bit(bb_bitmap, nr_blocks, i + 1)) < nr_blocks) {
 		blk = &lun->vlun.blocks[i];
 		if (!blk) {
 			pr_err("gennvm: BB data is out of bounds.\n");
@@ -171,8 +174,16 @@ static int gennvm_blocks_init(struct nvm_dev *dev, struct gen_nvm *gn)
 		}
 
 		if (dev->ops->get_bb_tbl) {
-			ret = dev->ops->get_bb_tbl(dev->q, lun->vlun.id,
-					dev->blks_per_lun, gennvm_block_bb, gn);
+			struct ppa_addr ppa;
+
+			ppa.ppa = 0;
+			ppa.g.ch = lun->vlun.chnl_id;
+			ppa.g.lun = lun->vlun.id;
+			ppa = generic_to_addr_mode(dev, ppa);
+
+			ret = dev->ops->get_bb_tbl(dev->q, ppa,
+						dev->blks_per_lun,
+						gennvm_block_bb, gn);
 			if (ret)
 				pr_err("gennvm: could not read BB table\n");
 		}
@@ -199,6 +210,7 @@ static int gennvm_register(struct nvm_dev *dev)
 	if (!gn)
 		return -ENOMEM;
 
+	gn->dev = dev;
 	gn->nr_luns = dev->nr_luns;
 	dev->mp = gn;
 
@@ -354,10 +366,10 @@ static void gennvm_mark_blk_bad(struct nvm_dev *dev, struct nvm_rq *rqd)
 {
 	int i;
 
-	if (!dev->ops->set_bb)
+	if (!dev->ops->set_bb_tbl)
 		return;
 
-	if (dev->ops->set_bb(dev->q, rqd, 1))
+	if (dev->ops->set_bb_tbl(dev->q, rqd, 1))
 		return;
 
 	gennvm_addr_to_generic_mode(dev, rqd);
diff --git a/drivers/lightnvm/gennvm.h b/drivers/lightnvm/gennvm.h
index d23bd3501ddc..9c24b5b32dac 100644
--- a/drivers/lightnvm/gennvm.h
+++ b/drivers/lightnvm/gennvm.h
@@ -35,6 +35,8 @@ struct gen_lun {
 };
 
 struct gen_nvm {
+	struct nvm_dev *dev;
+
 	int nr_luns;
 	struct gen_lun *luns;
 };
diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index e0b7b95813bc..2c3546516300 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -93,7 +93,7 @@ struct nvme_nvm_l2ptbl {
 	__le16			cdw14[6];
 };
 
-struct nvme_nvm_bbtbl {
+struct nvme_nvm_getbbtbl {
 	__u8			opcode;
 	__u8			flags;
 	__u16			command_id;
@@ -101,10 +101,23 @@ struct nvme_nvm_bbtbl {
 	__u64			rsvd[2];
 	__le64			prp1;
 	__le64			prp2;
-	__le32			prp1_len;
-	__le32			prp2_len;
-	__le32			lbb;
-	__u32			rsvd11[3];
+	__le64			spba;
+	__u32			rsvd4[4];
+};
+
+struct nvme_nvm_setbbtbl {
+	__u8			opcode;
+	__u8			flags;
+	__u16			command_id;
+	__le32			nsid;
+	__le64			rsvd[2];
+	__le64			prp1;
+	__le64			prp2;
+	__le64			spba;
+	__le16			nlb;
+	__u8			value;
+	__u8			rsvd3;
+	__u32			rsvd4[3];
 };
 
 struct nvme_nvm_erase_blk {
@@ -129,8 +142,8 @@ struct nvme_nvm_command {
 		struct nvme_nvm_hb_rw hb_rw;
 		struct nvme_nvm_ph_rw ph_rw;
 		struct nvme_nvm_l2ptbl l2p;
-		struct nvme_nvm_bbtbl get_bb;
-		struct nvme_nvm_bbtbl set_bb;
+		struct nvme_nvm_getbbtbl get_bb;
+		struct nvme_nvm_setbbtbl set_bb;
 		struct nvme_nvm_erase_blk erase;
 	};
 };
@@ -187,6 +200,20 @@ struct nvme_nvm_id {
 	struct nvme_nvm_id_group groups[4];
 } __packed;
 
+struct nvme_nvm_bb_tbl {
+	__u8	tblid[4];
+	__le16	verid;
+	__le16	revid;
+	__le32	rvsd1;
+	__le32	tblks;
+	__le32	tfact;
+	__le32	tgrown;
+	__le32	tdresv;
+	__le32	thresv;
+	__le32	rsvd2[8];
+	__u8	blk[0];
+};
+
 /*
  * Check we didn't inadvertently grow the command struct
  */
@@ -195,12 +222,14 @@ static inline void _nvme_nvm_check_size(void)
 	BUILD_BUG_ON(sizeof(struct nvme_nvm_identity) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_nvm_hb_rw) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_nvm_ph_rw) != 64);
-	BUILD_BUG_ON(sizeof(struct nvme_nvm_bbtbl) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_nvm_getbbtbl) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_nvm_setbbtbl) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_nvm_l2ptbl) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_nvm_erase_blk) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_nvm_id_group) != 960);
 	BUILD_BUG_ON(sizeof(struct nvme_nvm_addr_format) != 128);
 	BUILD_BUG_ON(sizeof(struct nvme_nvm_id) != 4096);
+	BUILD_BUG_ON(sizeof(struct nvme_nvm_bb_tbl) != 512);
 }
 
 static int init_grps(struct nvm_id *nvm_id, struct nvme_nvm_id *nvme_nvm_id)
@@ -322,43 +351,80 @@ out:
 	return ret;
 }
 
-static int nvme_nvm_get_bb_tbl(struct request_queue *q, int lunid,
-				unsigned int nr_blocks,
-				nvm_bb_update_fn *update_bbtbl, void *priv)
+static int nvme_nvm_get_bb_tbl(struct request_queue *q, struct ppa_addr ppa,
+				int nr_blocks, nvm_bb_update_fn *update_bbtbl,
+				void *priv)
 {
 	struct nvme_ns *ns = q->queuedata;
 	struct nvme_dev *dev = ns->dev;
 	struct nvme_nvm_command c = {};
-	void *bb_bitmap;
-	u16 bb_bitmap_size;
+	struct nvme_nvm_bb_tbl *bb_tbl;
+	int tblsz = sizeof(struct nvme_nvm_bb_tbl) + nr_blocks;
 	int ret = 0;
 
 	c.get_bb.opcode = nvme_nvm_admin_get_bb_tbl;
 	c.get_bb.nsid = cpu_to_le32(ns->ns_id);
-	c.get_bb.lbb = cpu_to_le32(lunid);
-	bb_bitmap_size = ((nr_blocks >> 15) + 1) * PAGE_SIZE;
-	bb_bitmap = kmalloc(bb_bitmap_size, GFP_KERNEL);
-	if (!bb_bitmap)
-		return -ENOMEM;
+	c.get_bb.spba = cpu_to_le64(ppa.ppa);
 
-	bitmap_zero(bb_bitmap, nr_blocks);
+	bb_tbl = kzalloc(tblsz, GFP_KERNEL);
+	if (!bb_tbl)
+		return -ENOMEM;
 
-	ret = nvme_submit_sync_cmd(q, (struct nvme_command *)&c, bb_bitmap,
-								bb_bitmap_size);
+	ret = nvme_submit_sync_cmd(q, (struct nvme_command *)&c, bb_tbl, tblsz);
 	if (ret) {
 		dev_err(dev->dev, "get bad block table failed (%d)\n", ret);
 		ret = -EIO;
 		goto out;
 	}
 
-	ret = update_bbtbl(lunid, bb_bitmap, nr_blocks, priv);
+	if (bb_tbl->tblid[0] != 'B' || bb_tbl->tblid[1] != 'B' ||
+		bb_tbl->tblid[2] != 'L' || bb_tbl->tblid[3] != 'T') {
+		dev_err(dev->dev, "bbt format mismatch\n");
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (le16_to_cpu(bb_tbl->verid) != 1) {
+		ret = -EINVAL;
+		dev_err(dev->dev, "bbt version not supported\n");
+		goto out;
+	}
+
+	if (le32_to_cpu(bb_tbl->tblks) != nr_blocks) {
+		ret = -EINVAL;
+		dev_err(dev->dev, "bbt unsuspected blocks returned (%u!=%u)",
+					le32_to_cpu(bb_tbl->tblks), nr_blocks);
+		goto out;
+	}
+
+	ret = update_bbtbl(ppa, nr_blocks, bb_tbl->blk, priv);
 	if (ret) {
 		ret = -EINTR;
 		goto out;
 	}
 
 out:
-	kfree(bb_bitmap);
+	kfree(bb_tbl);
+	return ret;
+}
+
+static int nvme_nvm_set_bb_tbl(struct request_queue *q, struct nvm_rq *rqd,
+								int type)
+{
+	struct nvme_ns *ns = q->queuedata;
+	struct nvme_dev *dev = ns->dev;
+	struct nvme_nvm_command c = {};
+	int ret = 0;
+
+	c.set_bb.opcode = nvme_nvm_admin_set_bb_tbl;
+	c.set_bb.nsid = cpu_to_le32(ns->ns_id);
+	c.set_bb.spba = cpu_to_le64(rqd->ppa_addr.ppa);
+	c.set_bb.nlb = cpu_to_le16(rqd->nr_pages - 1);
+	c.set_bb.value = type;
+
+	ret = nvme_submit_sync_cmd(q, (struct nvme_command *)&c, NULL, 0);
+	if (ret)
+		dev_err(dev->dev, "set bad block table failed (%d)\n", ret);
 	return ret;
 }
 
@@ -474,6 +540,7 @@ static struct nvm_dev_ops nvme_nvm_dev_ops = {
 	.get_l2p_tbl		= nvme_nvm_get_l2p_tbl,
 
 	.get_bb_tbl		= nvme_nvm_get_bb_tbl,
+	.set_bb_tbl		= nvme_nvm_set_bb_tbl,
 
 	.submit_io		= nvme_nvm_submit_io,
 	.erase_block		= nvme_nvm_erase_block,
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index 32b5369e814e..9b3dc1bc9296 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -191,11 +191,11 @@ static inline void *nvm_rq_to_pdu(struct nvm_rq *rqdata)
 struct nvm_block;
 
 typedef int (nvm_l2p_update_fn)(u64, u32, __le64 *, void *);
-typedef int (nvm_bb_update_fn)(u32, void *, unsigned int, void *);
+typedef int (nvm_bb_update_fn)(struct ppa_addr, int, u8 *, void *);
 typedef int (nvm_id_fn)(struct request_queue *, struct nvm_id *);
 typedef int (nvm_get_l2p_tbl_fn)(struct request_queue *, u64, u32,
 				nvm_l2p_update_fn *, void *);
-typedef int (nvm_op_bb_tbl_fn)(struct request_queue *, int, unsigned int,
+typedef int (nvm_op_bb_tbl_fn)(struct request_queue *, struct ppa_addr, int,
 				nvm_bb_update_fn *, void *);
 typedef int (nvm_op_set_bb_fn)(struct request_queue *, struct nvm_rq *, int);
 typedef int (nvm_submit_io_fn)(struct request_queue *, struct nvm_rq *);
@@ -210,7 +210,7 @@ struct nvm_dev_ops {
 	nvm_id_fn		*identity;
 	nvm_get_l2p_tbl_fn	*get_l2p_tbl;
 	nvm_op_bb_tbl_fn	*get_bb_tbl;
-	nvm_op_set_bb_fn	*set_bb;
+	nvm_op_set_bb_fn	*set_bb_tbl;
 
 	nvm_submit_io_fn	*submit_io;
 	nvm_erase_blk_fn	*erase_block;
-- 
cgit v1.2.3


From 12be5edf68e785dd5dc8665db5a88152b49c1fe8 Mon Sep 17 00:00:00 2001
From: Matias Bjørling
Date: Mon, 16 Nov 2015 15:34:39 +0100
Subject: lightnvm: expose mccap in identify command

The mccap field is required for I/O command option support. It defines the
following flash access modes:

 * SLC mode
 * Erase/Program Suspension
 * Scramble On/Off
 * Encryption

It is slotted in between mpos and cpar, changing the offset for
cpar as well.

Signed-off-by: Matias Bjørling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 drivers/nvme/host/lightnvm.c | 4 +++-
 include/linux/lightnvm.h     | 1 +
 2 files changed, 4 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index 60687ed68b5d..52b311cf694c 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -169,8 +169,9 @@ struct nvme_nvm_id_group {
 	__le32			tbet;
 	__le32			tbem;
 	__le32			mpos;
+	__le32			mccap;
 	__le16			cpar;
-	__u8			reserved[910];
+	__u8			reserved[906];
 } __packed;
 
 struct nvme_nvm_addr_format {
@@ -265,6 +266,7 @@ static int init_grps(struct nvm_id *nvm_id, struct nvme_nvm_id *nvme_nvm_id)
 		dst->tbet = le32_to_cpu(src->tbet);
 		dst->tbem = le32_to_cpu(src->tbem);
 		dst->mpos = le32_to_cpu(src->mpos);
+		dst->mccap = le32_to_cpu(src->mccap);
 
 		dst->cpar = le16_to_cpu(src->cpar);
 	}
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index 9b3dc1bc9296..2572856e2a89 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -74,6 +74,7 @@ struct nvm_id_group {
 	u32	tbet;
 	u32	tbem;
 	u32	mpos;
+	u32	mccap;
 	u16	cpar;
 	u8	res[913];
 } __packed;
-- 
cgit v1.2.3


From 73387e7bed260c89628fc6a4e3632b45be9776b0 Mon Sep 17 00:00:00 2001
From: Matias Bjørling
Date: Mon, 16 Nov 2015 15:34:40 +0100
Subject: lightnvm: remove unused attrs in nvm_id structs

The nvm_id, nvm_id_group and nvm_addr_format data structures contain
reserved attributes. They are unused by media managers and targets.
Remove them.

Signed-off-by: Matias Bjørling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 include/linux/lightnvm.h | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index 2572856e2a89..e6ef8aaf533f 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -58,7 +58,6 @@ enum {
 struct nvm_id_group {
 	u8	mtype;
 	u8	fmtype;
-	u16	res16;
 	u8	num_ch;
 	u8	num_lun;
 	u8	num_pln;
@@ -76,8 +75,7 @@ struct nvm_id_group {
 	u32	mpos;
 	u32	mccap;
 	u16	cpar;
-	u8	res[913];
-} __packed;
+};
 
 struct nvm_addr_format {
 	u8	ch_offset;
@@ -92,19 +90,16 @@ struct nvm_addr_format {
 	u8	pg_len;
 	u8	sect_offset;
 	u8	sect_len;
-	u8	res[4];
 };
 
 struct nvm_id {
 	u8	ver_id;
 	u8	vmnt;
 	u8	cgrps;
-	u8	res[5];
 	u32	cap;
 	u32	dom;
 	struct nvm_addr_format ppaf;
 	u8	ppat;
-	u8	resv[224];
 	struct nvm_id_group groups[4];
 } __packed;
 
-- 
cgit v1.2.3


From 7386af270c72be65c7cb2ba4ad0d4e70dc373106 Mon Sep 17 00:00:00 2001
From: Matias Bjørling
Date: Mon, 16 Nov 2015 15:34:44 +0100
Subject: lightnvm: remove linear and device addr modes

The linear and device specific address modes can be replaced with a
simple offset and bit length conversion that is generic across all
devices.

This both simplifies the specification and removes the special case for
qemu nvme, that previously relied on the linear address mapping.

Signed-off-by: Matias Bjørling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 drivers/lightnvm/core.c      |   3 +-
 drivers/lightnvm/gennvm.c    |  12 ++--
 drivers/lightnvm/rrpc.c      |  32 ++++++++-
 drivers/nvme/host/lightnvm.c |   3 +-
 include/linux/lightnvm.h     | 154 ++++++++++---------------------------------
 5 files changed, 73 insertions(+), 131 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c
index 899f6b9a9f68..790b1d7a8d43 100644
--- a/drivers/lightnvm/core.c
+++ b/drivers/lightnvm/core.c
@@ -174,8 +174,7 @@ static int nvm_core_init(struct nvm_dev *dev)
 	dev->sec_size = grp->csecs;
 	dev->oob_size = grp->sos;
 	dev->sec_per_pg = grp->fpg_sz / grp->csecs;
-	dev->addr_mode = id->ppat;
-	dev->addr_format = id->ppaf;
+	memcpy(&dev->ppaf, &id->ppaf, sizeof(struct nvm_addr_format));
 
 	dev->plane_mode = NVM_PLANE_SINGLE;
 	dev->max_rq_size = dev->ops->max_phys_sect * dev->sec_size;
diff --git a/drivers/lightnvm/gennvm.c b/drivers/lightnvm/gennvm.c
index 8cfc0114ff13..c0d0eb2357a8 100644
--- a/drivers/lightnvm/gennvm.c
+++ b/drivers/lightnvm/gennvm.c
@@ -73,7 +73,7 @@ static int gennvm_block_bb(struct ppa_addr ppa, int nr_blocks, u8 *blks,
 	struct nvm_block *blk;
 	int i;
 
-	ppa = addr_to_generic_mode(gn->dev, ppa);
+	ppa = dev_to_generic_addr(gn->dev, ppa);
 	lun = &gn->luns[(dev->nr_luns * ppa.g.ch) + ppa.g.lun];
 
 	for (i = 0; i < nr_blocks; i++) {
@@ -179,7 +179,7 @@ static int gennvm_blocks_init(struct nvm_dev *dev, struct gen_nvm *gn)
 			ppa.ppa = 0;
 			ppa.g.ch = lun->vlun.chnl_id;
 			ppa.g.lun = lun->vlun.id;
-			ppa = generic_to_addr_mode(dev, ppa);
+			ppa = generic_to_dev_addr(dev, ppa);
 
 			ret = dev->ops->get_bb_tbl(dev->q, ppa,
 						dev->blks_per_lun,
@@ -304,10 +304,10 @@ static void gennvm_addr_to_generic_mode(struct nvm_dev *dev, struct nvm_rq *rqd)
 
 	if (rqd->nr_pages > 1) {
 		for (i = 0; i < rqd->nr_pages; i++)
-			rqd->ppa_list[i] = addr_to_generic_mode(dev,
+			rqd->ppa_list[i] = dev_to_generic_addr(dev,
 							rqd->ppa_list[i]);
 	} else {
-		rqd->ppa_addr = addr_to_generic_mode(dev, rqd->ppa_addr);
+		rqd->ppa_addr = dev_to_generic_addr(dev, rqd->ppa_addr);
 	}
 }
 
@@ -317,10 +317,10 @@ static void gennvm_generic_to_addr_mode(struct nvm_dev *dev, struct nvm_rq *rqd)
 
 	if (rqd->nr_pages > 1) {
 		for (i = 0; i < rqd->nr_pages; i++)
-			rqd->ppa_list[i] = generic_to_addr_mode(dev,
+			rqd->ppa_list[i] = generic_to_dev_addr(dev,
 							rqd->ppa_list[i]);
 	} else {
-		rqd->ppa_addr = generic_to_addr_mode(dev, rqd->ppa_addr);
+		rqd->ppa_addr = generic_to_dev_addr(dev, rqd->ppa_addr);
 	}
 }
 
diff --git a/drivers/lightnvm/rrpc.c b/drivers/lightnvm/rrpc.c
index 7ba64c87ba1c..75e59c3a3f96 100644
--- a/drivers/lightnvm/rrpc.c
+++ b/drivers/lightnvm/rrpc.c
@@ -123,12 +123,42 @@ static u64 block_to_addr(struct rrpc *rrpc, struct rrpc_block *rblk)
 	return blk->id * rrpc->dev->pgs_per_blk;
 }
 
+static struct ppa_addr linear_to_generic_addr(struct nvm_dev *dev,
+							struct ppa_addr r)
+{
+	struct ppa_addr l;
+	int secs, pgs, blks, luns;
+	sector_t ppa = r.ppa;
+
+	l.ppa = 0;
+
+	div_u64_rem(ppa, dev->sec_per_pg, &secs);
+	l.g.sec = secs;
+
+	sector_div(ppa, dev->sec_per_pg);
+	div_u64_rem(ppa, dev->sec_per_blk, &pgs);
+	l.g.pg = pgs;
+
+	sector_div(ppa, dev->pgs_per_blk);
+	div_u64_rem(ppa, dev->blks_per_lun, &blks);
+	l.g.blk = blks;
+
+	sector_div(ppa, dev->blks_per_lun);
+	div_u64_rem(ppa, dev->luns_per_chnl, &luns);
+	l.g.lun = luns;
+
+	sector_div(ppa, dev->luns_per_chnl);
+	l.g.ch = ppa;
+
+	return l;
+}
+
 static struct ppa_addr rrpc_ppa_to_gaddr(struct nvm_dev *dev, u64 addr)
 {
 	struct ppa_addr paddr;
 
 	paddr.ppa = addr;
-	return __linear_to_generic_addr(dev, paddr);
+	return linear_to_generic_addr(dev, paddr);
 }
 
 /* requires lun->lock taken */
diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index 52b311cf694c..9069be811f82 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -198,8 +198,7 @@ struct nvme_nvm_id {
 	__le32			cap;
 	__le32			dom;
 	struct nvme_nvm_addr_format ppaf;
-	__u8			ppat;
-	__u8			resv[223];
+	__u8			resv[224];
 	struct nvme_nvm_id_group groups[4];
 } __packed;
 
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index e6ef8aaf533f..cbe288acb1de 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -99,7 +99,6 @@ struct nvm_id {
 	u32	cap;
 	u32	dom;
 	struct nvm_addr_format ppaf;
-	u8	ppat;
 	struct nvm_id_group groups[4];
 } __packed;
 
@@ -119,39 +118,28 @@ struct nvm_tgt_instance {
 #define NVM_VERSION_MINOR 0
 #define NVM_VERSION_PATCH 0
 
-#define NVM_SEC_BITS (8)
-#define NVM_PL_BITS  (6)
-#define NVM_PG_BITS  (16)
 #define NVM_BLK_BITS (16)
-#define NVM_LUN_BITS (10)
+#define NVM_PG_BITS  (16)
+#define NVM_SEC_BITS (8)
+#define NVM_PL_BITS  (8)
+#define NVM_LUN_BITS (8)
 #define NVM_CH_BITS  (8)
 
 struct ppa_addr {
+	/* Generic structure for all addresses */
 	union {
-		/* Channel-based PPA format in nand 4x2x2x2x8x10 */
-		struct {
-			u64 ch		: 4;
-			u64 sec		: 2; /* 4 sectors per page */
-			u64 pl		: 2; /* 4 planes per LUN */
-			u64 lun		: 2; /* 4 LUNs per channel */
-			u64 pg		: 8; /* 256 pages per block */
-			u64 blk		: 10;/* 1024 blocks per plane */
-			u64 resved		: 36;
-		} chnl;
-
-		/* Generic structure for all addresses */
 		struct {
+			u64 blk		: NVM_BLK_BITS;
+			u64 pg		: NVM_PG_BITS;
 			u64 sec		: NVM_SEC_BITS;
 			u64 pl		: NVM_PL_BITS;
-			u64 pg		: NVM_PG_BITS;
-			u64 blk		: NVM_BLK_BITS;
 			u64 lun		: NVM_LUN_BITS;
 			u64 ch		: NVM_CH_BITS;
 		} g;
 
 		u64 ppa;
 	};
-} __packed;
+};
 
 struct nvm_rq {
 	struct nvm_tgt_instance *ins;
@@ -259,8 +247,7 @@ struct nvm_dev {
 	int blks_per_lun;
 	int sec_size;
 	int oob_size;
-	int addr_mode;
-	struct nvm_addr_format addr_format;
+	struct nvm_addr_format ppaf;
 
 	/* Calculated/Cached values. These do not reflect the actual usable
 	 * blocks at run-time.
@@ -286,118 +273,45 @@ struct nvm_dev {
 	char name[DISK_NAME_LEN];
 };
 
-/* fallback conversion */
-static struct ppa_addr __generic_to_linear_addr(struct nvm_dev *dev,
-							struct ppa_addr r)
-{
-	struct ppa_addr l;
-
-	l.ppa = r.g.sec +
-		r.g.pg  * dev->sec_per_pg +
-		r.g.blk * (dev->pgs_per_blk *
-				dev->sec_per_pg) +
-		r.g.lun * (dev->blks_per_lun *
-				dev->pgs_per_blk *
-				dev->sec_per_pg) +
-		r.g.ch * (dev->blks_per_lun *
-				dev->pgs_per_blk *
-				dev->luns_per_chnl *
-				dev->sec_per_pg);
-
-	return l;
-}
-
-/* fallback conversion */
-static struct ppa_addr __linear_to_generic_addr(struct nvm_dev *dev,
-							struct ppa_addr r)
-{
-	struct ppa_addr l;
-	int secs, pgs, blks, luns;
-	sector_t ppa = r.ppa;
-
-	l.ppa = 0;
-
-	div_u64_rem(ppa, dev->sec_per_pg, &secs);
-	l.g.sec = secs;
-
-	sector_div(ppa, dev->sec_per_pg);
-	div_u64_rem(ppa, dev->sec_per_blk, &pgs);
-	l.g.pg = pgs;
-
-	sector_div(ppa, dev->pgs_per_blk);
-	div_u64_rem(ppa, dev->blks_per_lun, &blks);
-	l.g.blk = blks;
-
-	sector_div(ppa, dev->blks_per_lun);
-	div_u64_rem(ppa, dev->luns_per_chnl, &luns);
-	l.g.lun = luns;
-
-	sector_div(ppa, dev->luns_per_chnl);
-	l.g.ch = ppa;
-
-	return l;
-}
-
-static struct ppa_addr __generic_to_chnl_addr(struct ppa_addr r)
+static inline struct ppa_addr generic_to_dev_addr(struct nvm_dev *dev,
+						struct ppa_addr r)
 {
 	struct ppa_addr l;
 
-	l.ppa = 0;
-
-	l.chnl.sec = r.g.sec;
-	l.chnl.pl = r.g.pl;
-	l.chnl.pg = r.g.pg;
-	l.chnl.blk = r.g.blk;
-	l.chnl.lun = r.g.lun;
-	l.chnl.ch = r.g.ch;
+	l.ppa = ((u64)r.g.blk) << dev->ppaf.blk_offset;
+	l.ppa |= ((u64)r.g.pg) << dev->ppaf.pg_offset;
+	l.ppa |= ((u64)r.g.sec) << dev->ppaf.sect_offset;
+	l.ppa |= ((u64)r.g.pl) << dev->ppaf.pln_offset;
+	l.ppa |= ((u64)r.g.lun) << dev->ppaf.lun_offset;
+	l.ppa |= ((u64)r.g.ch) << dev->ppaf.ch_offset;
 
 	return l;
 }
 
-static struct ppa_addr __chnl_to_generic_addr(struct ppa_addr r)
+static inline struct ppa_addr dev_to_generic_addr(struct nvm_dev *dev,
+						struct ppa_addr r)
 {
 	struct ppa_addr l;
 
-	l.ppa = 0;
-
-	l.g.sec = r.chnl.sec;
-	l.g.pl = r.chnl.pl;
-	l.g.pg = r.chnl.pg;
-	l.g.blk = r.chnl.blk;
-	l.g.lun = r.chnl.lun;
-	l.g.ch = r.chnl.ch;
+	/*
+	 * (r.ppa << X offset) & X len bitmask. X eq. blk, pg, etc.
+	 */
+	l.g.blk = (r.ppa >> dev->ppaf.blk_offset) &
+					(((1 << dev->ppaf.blk_len) - 1));
+	l.g.pg |= (r.ppa >> dev->ppaf.pg_offset) &
+					(((1 << dev->ppaf.pg_len) - 1));
+	l.g.sec |= (r.ppa >> dev->ppaf.sect_offset) &
+					(((1 << dev->ppaf.sect_len) - 1));
+	l.g.pl |= (r.ppa >> dev->ppaf.pln_offset) &
+					(((1 << dev->ppaf.pln_len) - 1));
+	l.g.lun |= (r.ppa >> dev->ppaf.lun_offset) &
+					(((1 << dev->ppaf.lun_len) - 1));
+	l.g.ch |= (r.ppa >> dev->ppaf.ch_offset) &
+					(((1 << dev->ppaf.ch_len) - 1));
 
 	return l;
 }
 
-static inline struct ppa_addr addr_to_generic_mode(struct nvm_dev *dev,
-						struct ppa_addr gppa)
-{
-	switch (dev->addr_mode) {
-	case NVM_ADDRMODE_LINEAR:
-		return __linear_to_generic_addr(dev, gppa);
-	case NVM_ADDRMODE_CHANNEL:
-		return __chnl_to_generic_addr(gppa);
-	default:
-		BUG();
-	}
-	return gppa;
-}
-
-static inline struct ppa_addr generic_to_addr_mode(struct nvm_dev *dev,
-						struct ppa_addr gppa)
-{
-	switch (dev->addr_mode) {
-	case NVM_ADDRMODE_LINEAR:
-		return __generic_to_linear_addr(dev, gppa);
-	case NVM_ADDRMODE_CHANNEL:
-		return __generic_to_chnl_addr(gppa);
-	default:
-		BUG();
-	}
-	return gppa;
-}
-
 static inline int ppa_empty(struct ppa_addr ppa_addr)
 {
 	return (ppa_addr.ppa == ADDR_EMPTY);
-- 
cgit v1.2.3


From 451c2b5caf37b526ae34a1081b71115e1de2d063 Mon Sep 17 00:00:00 2001
From: Aya Mahfouz
Date: Wed, 18 Nov 2015 08:36:44 +0200
Subject: net: dns_resolver: convert time_t to time64_t

Changes the definition of the pointer _expiry from time_t to
time64_t. This is to handle the Y2038 problem where time_t
will overflow in the year 2038. The change is safe because
the kernel subsystems that call dns_query pass NULL.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Aya Mahfouz <mahfouz.saif.elyazal@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/dns_resolver.h | 2 +-
 net/dns_resolver/dns_query.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/dns_resolver.h b/include/linux/dns_resolver.h
index cc92268af89a..6ac3cad9aef1 100644
--- a/include/linux/dns_resolver.h
+++ b/include/linux/dns_resolver.h
@@ -27,7 +27,7 @@
 #ifdef __KERNEL__
 
 extern int dns_query(const char *type, const char *name, size_t namelen,
-		     const char *options, char **_result, time_t *_expiry);
+		     const char *options, char **_result, time64_t *_expiry);
 
 #endif /* KERNEL */
 
diff --git a/net/dns_resolver/dns_query.c b/net/dns_resolver/dns_query.c
index 4677b6fa6dda..ecc28cff08ab 100644
--- a/net/dns_resolver/dns_query.c
+++ b/net/dns_resolver/dns_query.c
@@ -67,7 +67,7 @@
  * Returns the size of the result on success, -ve error code otherwise.
  */
 int dns_query(const char *type, const char *name, size_t namelen,
-	      const char *options, char **_result, time_t *_expiry)
+	      const char *options, char **_result, time64_t *_expiry)
 {
 	struct key *rkey;
 	const struct user_key_payload *upayload;
-- 
cgit v1.2.3


From db27a7a37aa0b1f8b373f8b0fb72a2ccaafb85b7 Mon Sep 17 00:00:00 2001
From: David Hildenbrand
Date: Thu, 5 Nov 2015 09:03:50 +0100
Subject: KVM: Provide function for VCPU lookup by id

Let's provide a function to lookup a VCPU by id.

Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com>
Reviewed-by: Dominik Dingel <dingel@linux.vnet.ibm.com>
Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
[split patch from refactoring patch]
---
 include/linux/kvm_host.h | 11 +++++++++++
 1 file changed, 11 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 5706a2108f0a..c923350ca20a 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -460,6 +460,17 @@ static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i)
 	     (vcpup = kvm_get_vcpu(kvm, idx)) != NULL; \
 	     idx++)
 
+static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id)
+{
+	struct kvm_vcpu *vcpu;
+	int i;
+
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		if (vcpu->vcpu_id == id)
+			return vcpu;
+	return NULL;
+}
+
 #define kvm_for_each_memslot(memslot, slots)	\
 	for (memslot = &slots->memslots[0];	\
 	      memslot < slots->memslots + KVM_MEM_SLOTS_NUM && memslot->npages;\
-- 
cgit v1.2.3


From 851df3dc11136fde86ebd78ee7527cb43c7cd349 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann
Date: Mon, 16 Nov 2015 22:34:58 +0100
Subject: scpi: hide get_scpi_ops in module from built-in code

The scpi_clock driver can be built-in when CONFIG_COMPILE_TEST
is set even when ARM_SCPI_PROTOCOL is a loadable module, and
that results in a link error:

drivers/built-in.o: In function `scpi_clocks_probe':
(.text+0x14453c): undefined reference to `get_scpi_ops'

Using #if IS_REACHABLE() around the get_scpi_ops() declaration
makes it build successfully in this case for compile-testing,
but the effect is the same as when ARM_SCPI_PROTOCOL is
disabled, as the code will not be used.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Punit Agrawal <punit.agrawal@arm.com>
---
 include/linux/scpi_protocol.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/scpi_protocol.h b/include/linux/scpi_protocol.h
index 80af3cd35ae4..72ce932c69b2 100644
--- a/include/linux/scpi_protocol.h
+++ b/include/linux/scpi_protocol.h
@@ -71,7 +71,7 @@ struct scpi_ops {
 	int (*sensor_get_value)(u16, u32 *);
 };
 
-#if IS_ENABLED(CONFIG_ARM_SCPI_PROTOCOL)
+#if IS_REACHABLE(CONFIG_ARM_SCPI_PROTOCOL)
 struct scpi_ops *get_scpi_ops(void);
 #else
 static inline struct scpi_ops *get_scpi_ops(void) { return NULL; }
-- 
cgit v1.2.3


From 0b59733b95f9d7af6bee6e6a4d0d444eb694c514 Mon Sep 17 00:00:00 2001
From: Javier Gonzalez
Date: Fri, 20 Nov 2015 13:47:56 +0100
Subject: lightnvm: keep track of block counts

Maintain number of in use blocks, free blocks, and bad blocks in a per
lun basis. This allows the upper layers to get information about the
state of each lun.

Also, account for blocks reserved to the device on the free block count.
nr_free_blocks matches now the actual number of blocks on the free list
when the device is booted.

Signed-off-by: Javier Gonzalez <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 drivers/lightnvm/gennvm.c | 14 +++++++++++++-
 include/linux/lightnvm.h  |  2 ++
 2 files changed, 15 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/lightnvm/gennvm.c b/drivers/lightnvm/gennvm.c
index c0d0eb2357a8..43c01e0af887 100644
--- a/drivers/lightnvm/gennvm.c
+++ b/drivers/lightnvm/gennvm.c
@@ -60,6 +60,8 @@ static int gennvm_luns_init(struct nvm_dev *dev, struct gen_nvm *gn)
 		lun->vlun.lun_id = i % dev->luns_per_chnl;
 		lun->vlun.chnl_id = i / dev->luns_per_chnl;
 		lun->vlun.nr_free_blocks = dev->blks_per_lun;
+		lun->vlun.nr_inuse_blocks = 0;
+		lun->vlun.nr_bad_blocks = 0;
 	}
 	return 0;
 }
@@ -87,6 +89,7 @@ static int gennvm_block_bb(struct ppa_addr ppa, int nr_blocks, u8 *blks,
 		}
 
 		list_move_tail(&blk->list, &lun->bb_list);
+		lun->vlun.nr_bad_blocks++;
 	}
 
 	return 0;
@@ -139,6 +142,7 @@ static int gennvm_block_map(u64 slba, u32 nlb, __le64 *entries, void *private)
 			list_move_tail(&blk->list, &lun->used_list);
 			blk->type = 1;
 			lun->vlun.nr_free_blocks--;
+			lun->vlun.nr_inuse_blocks++;
 		}
 	}
 
@@ -167,8 +171,10 @@ static int gennvm_blocks_init(struct nvm_dev *dev, struct gen_nvm *gn)
 			block->id = cur_block_id++;
 
 			/* First block is reserved for device */
-			if (unlikely(lun_iter == 0 && blk_iter == 0))
+			if (unlikely(lun_iter == 0 && blk_iter == 0)) {
+				lun->vlun.nr_free_blocks--;
 				continue;
+			}
 
 			list_add_tail(&block->list, &lun->free_list);
 		}
@@ -266,6 +272,7 @@ static struct nvm_block *gennvm_get_blk(struct nvm_dev *dev,
 	blk->type = 1;
 
 	lun->vlun.nr_free_blocks--;
+	lun->vlun.nr_inuse_blocks++;
 
 	spin_unlock(&vlun->lock);
 out:
@@ -283,16 +290,21 @@ static void gennvm_put_blk(struct nvm_dev *dev, struct nvm_block *blk)
 	case 1:
 		list_move_tail(&blk->list, &lun->free_list);
 		lun->vlun.nr_free_blocks++;
+		lun->vlun.nr_inuse_blocks--;
 		blk->type = 0;
 		break;
 	case 2:
 		list_move_tail(&blk->list, &lun->bb_list);
+		lun->vlun.nr_bad_blocks++;
+		lun->vlun.nr_inuse_blocks--;
 		break;
 	default:
 		WARN_ON_ONCE(1);
 		pr_err("gennvm: erroneous block type (%lu -> %u)\n",
 							blk->id, blk->type);
 		list_move_tail(&blk->list, &lun->bb_list);
+		lun->vlun.nr_bad_blocks++;
+		lun->vlun.nr_inuse_blocks--;
 	}
 
 	spin_unlock(&vlun->lock);
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index cbe288acb1de..831a20cf070c 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -213,7 +213,9 @@ struct nvm_lun {
 	int lun_id;
 	int chnl_id;
 
+	unsigned int nr_inuse_blocks;	/* Number of used blocks */
 	unsigned int nr_free_blocks;	/* Number of unused blocks */
+	unsigned int nr_bad_blocks;	/* Number of bad blocks */
 	struct nvm_block *blocks;
 
 	spinlock_t lock;
-- 
cgit v1.2.3


From 2fde0e482db2b43bb4ed0e9aebfbe78ebcbbf5a6 Mon Sep 17 00:00:00 2001
From: Javier Gonzalez
Date: Fri, 20 Nov 2015 13:47:57 +0100
Subject: lightnvm: add free and bad lun info to show luns

Add free block, used block, and bad block information to the show debug
interface. This information is used to debug how targets track blocks.

Also, change debug function name to make it more generic.

Signed-off-by: Javier Gonzalez <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 drivers/lightnvm/core.c   |  2 +-
 drivers/lightnvm/gennvm.c | 19 ++++++++++++++-----
 include/linux/lightnvm.h  |  4 ++--
 3 files changed, 17 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c
index f61d325fd978..5178645ac42b 100644
--- a/drivers/lightnvm/core.c
+++ b/drivers/lightnvm/core.c
@@ -544,7 +544,7 @@ static int nvm_configure_show(const char *val)
 	if (!dev->mt)
 		return 0;
 
-	dev->mt->free_blocks_print(dev);
+	dev->mt->lun_info_print(dev);
 
 	return 0;
 }
diff --git a/drivers/lightnvm/gennvm.c b/drivers/lightnvm/gennvm.c
index 43c01e0af887..e20e74ec6b91 100644
--- a/drivers/lightnvm/gennvm.c
+++ b/drivers/lightnvm/gennvm.c
@@ -464,15 +464,24 @@ static struct nvm_lun *gennvm_get_lun(struct nvm_dev *dev, int lunid)
 	return &gn->luns[lunid].vlun;
 }
 
-static void gennvm_free_blocks_print(struct nvm_dev *dev)
+static void gennvm_lun_info_print(struct nvm_dev *dev)
 {
 	struct gen_nvm *gn = dev->mp;
 	struct gen_lun *lun;
 	unsigned int i;
 
-	gennvm_for_each_lun(gn, lun, i)
-		pr_info("%s: lun%8u\t%u\n",
-					dev->name, i, lun->vlun.nr_free_blocks);
+
+	gennvm_for_each_lun(gn, lun, i) {
+		spin_lock(&lun->vlun.lock);
+
+		pr_info("%s: lun%8u\t%u\t%u\t%u\n",
+				dev->name, i,
+				lun->vlun.nr_free_blocks,
+				lun->vlun.nr_inuse_blocks,
+				lun->vlun.nr_bad_blocks);
+
+		spin_unlock(&lun->vlun.lock);
+	}
 }
 
 static struct nvmm_type gennvm = {
@@ -490,7 +499,7 @@ static struct nvmm_type gennvm = {
 	.erase_blk	= gennvm_erase_blk,
 
 	.get_lun	= gennvm_get_lun,
-	.free_blocks_print = gennvm_free_blocks_print,
+	.lun_info_print = gennvm_lun_info_print,
 };
 
 static int __init gennvm_module_init(void)
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index 831a20cf070c..3db5552b17d5 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -380,7 +380,7 @@ typedef int (nvmm_end_io_fn)(struct nvm_rq *, int);
 typedef int (nvmm_erase_blk_fn)(struct nvm_dev *, struct nvm_block *,
 								unsigned long);
 typedef struct nvm_lun *(nvmm_get_lun_fn)(struct nvm_dev *, int);
-typedef void (nvmm_free_blocks_print_fn)(struct nvm_dev *);
+typedef void (nvmm_lun_info_print_fn)(struct nvm_dev *);
 
 struct nvmm_type {
 	const char *name;
@@ -404,7 +404,7 @@ struct nvmm_type {
 	nvmm_get_lun_fn *get_lun;
 
 	/* Statistics */
-	nvmm_free_blocks_print_fn *free_blocks_print;
+	nvmm_lun_info_print_fn *lun_info_print;
 	struct list_head list;
 };
 
-- 
cgit v1.2.3


From 614e4c4ebc75517295bccd29b20ddbc5b52af6fc Mon Sep 17 00:00:00 2001
From: Stephane Eranian
Date: Thu, 12 Nov 2015 11:00:04 +0100
Subject: perf/core: Robustify the perf_cgroup_from_task() RCU checks

This patch reinforces the lockdep checks performed by
perf_cgroup_from_tsk() by passing the perf_event_context
whenever possible. It is okay to not hold the RCU read lock
when we know we hold the ctx->lock. This patch makes sure this
property holds.

In some functions, such as perf_cgroup_sched_in(), we do not
pass the context because we are sure we are holding the RCU
read lock.

Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: edumazet@google.com
Link: http://lkml.kernel.org/r/1447322404-10920-3-git-send-email-eranian@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/cpu/perf_event_intel_cqm.c |  2 +-
 include/linux/perf_event.h                 |  6 ++++--
 kernel/events/core.c                       | 20 +++++++++++++-------
 3 files changed, 18 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
index 377e8f8ed391..a316ca96f1b6 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
@@ -298,7 +298,7 @@ static bool __match_event(struct perf_event *a, struct perf_event *b)
 static inline struct perf_cgroup *event_to_cgroup(struct perf_event *event)
 {
 	if (event->attach_state & PERF_ATTACH_TASK)
-		return perf_cgroup_from_task(event->hw.target);
+		return perf_cgroup_from_task(event->hw.target, event->ctx);
 
 	return event->cgrp;
 }
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index d841d33bcdc9..f9828a48f16a 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -697,9 +697,11 @@ struct perf_cgroup {
  * if there is no cgroup event for the current CPU context.
  */
 static inline struct perf_cgroup *
-perf_cgroup_from_task(struct task_struct *task)
+perf_cgroup_from_task(struct task_struct *task, struct perf_event_context *ctx)
 {
-	return container_of(task_css(task, perf_event_cgrp_id),
+	return container_of(task_css_check(task, perf_event_cgrp_id,
+					   ctx ? lockdep_is_held(&ctx->lock)
+					       : true),
 			    struct perf_cgroup, css);
 }
 #endif /* CONFIG_CGROUP_PERF */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 60e71ca42c22..1ac857aff7b0 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -435,7 +435,7 @@ static inline void update_cgrp_time_from_event(struct perf_event *event)
 	if (!is_cgroup_event(event))
 		return;
 
-	cgrp = perf_cgroup_from_task(current);
+	cgrp = perf_cgroup_from_task(current, event->ctx);
 	/*
 	 * Do not update time when cgroup is not active
 	 */
@@ -458,7 +458,7 @@ perf_cgroup_set_timestamp(struct task_struct *task,
 	if (!task || !ctx->nr_cgroups)
 		return;
 
-	cgrp = perf_cgroup_from_task(task);
+	cgrp = perf_cgroup_from_task(task, ctx);
 	info = this_cpu_ptr(cgrp->info);
 	info->timestamp = ctx->timestamp;
 }
@@ -521,8 +521,10 @@ static void perf_cgroup_switch(struct task_struct *task, int mode)
 				 * set cgrp before ctxsw in to allow
 				 * event_filter_match() to not have to pass
 				 * task around
+				 * we pass the cpuctx->ctx to perf_cgroup_from_task()
+				 * because cgorup events are only per-cpu
 				 */
-				cpuctx->cgrp = perf_cgroup_from_task(task);
+				cpuctx->cgrp = perf_cgroup_from_task(task, &cpuctx->ctx);
 				cpu_ctx_sched_in(cpuctx, EVENT_ALL, task);
 			}
 			perf_pmu_enable(cpuctx->ctx.pmu);
@@ -542,15 +544,17 @@ static inline void perf_cgroup_sched_out(struct task_struct *task,
 	rcu_read_lock();
 	/*
 	 * we come here when we know perf_cgroup_events > 0
+	 * we do not need to pass the ctx here because we know
+	 * we are holding the rcu lock
 	 */
-	cgrp1 = perf_cgroup_from_task(task);
+	cgrp1 = perf_cgroup_from_task(task, NULL);
 
 	/*
 	 * next is NULL when called from perf_event_enable_on_exec()
 	 * that will systematically cause a cgroup_switch()
 	 */
 	if (next)
-		cgrp2 = perf_cgroup_from_task(next);
+		cgrp2 = perf_cgroup_from_task(next, NULL);
 
 	/*
 	 * only schedule out current cgroup events if we know
@@ -572,11 +576,13 @@ static inline void perf_cgroup_sched_in(struct task_struct *prev,
 	rcu_read_lock();
 	/*
 	 * we come here when we know perf_cgroup_events > 0
+	 * we do not need to pass the ctx here because we know
+	 * we are holding the rcu lock
 	 */
-	cgrp1 = perf_cgroup_from_task(task);
+	cgrp1 = perf_cgroup_from_task(task, NULL);
 
 	/* prev can never be NULL */
-	cgrp2 = perf_cgroup_from_task(prev);
+	cgrp2 = perf_cgroup_from_task(prev, NULL);
 
 	/*
 	 * only need to schedule in cgroup events if we are changing
-- 
cgit v1.2.3


From 90eec103b96e30401c0b846045bf8a1c7159b6da Mon Sep 17 00:00:00 2001
From: Peter Zijlstra
Date: Mon, 16 Nov 2015 11:08:45 +0100
Subject: treewide: Remove old email address

There were still a number of references to my old Red Hat email
address in the kernel source. Remove these while keeping the
Red Hat copyright notices intact.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/blackfin/kernel/perf_event.c | 2 +-
 arch/sh/kernel/perf_event.c       | 2 +-
 arch/sparc/kernel/perf_event.c    | 2 +-
 arch/tile/kernel/perf_event.c     | 2 +-
 arch/x86/kernel/cpu/perf_event.c  | 2 +-
 arch/x86/kernel/cpu/perf_event.h  | 2 +-
 arch/x86/kernel/irq_work.c        | 2 +-
 include/asm-generic/tlb.h         | 2 +-
 include/linux/jump_label.h        | 2 +-
 include/linux/lockdep.h           | 2 +-
 include/linux/proportions.h       | 2 +-
 include/linux/uprobes.h           | 2 +-
 kernel/events/callchain.c         | 2 +-
 kernel/events/core.c              | 2 +-
 kernel/events/ring_buffer.c       | 2 +-
 kernel/events/uprobes.c           | 2 +-
 kernel/irq_work.c                 | 2 +-
 kernel/jump_label.c               | 2 +-
 kernel/locking/lockdep.c          | 2 +-
 kernel/locking/lockdep_proc.c     | 2 +-
 kernel/sched/clock.c              | 2 +-
 kernel/sched/fair.c               | 2 +-
 kernel/trace/trace_event_perf.c   | 2 +-
 lib/btree.c                       | 2 +-
 lib/proportions.c                 | 2 +-
 mm/page-writeback.c               | 2 +-
 26 files changed, 26 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/arch/blackfin/kernel/perf_event.c b/arch/blackfin/kernel/perf_event.c
index 1e9c8b0bf486..170d786807c4 100644
--- a/arch/blackfin/kernel/perf_event.c
+++ b/arch/blackfin/kernel/perf_event.c
@@ -14,7 +14,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *
  * ppc:
diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c
index 7cfd7f153966..4dca18347ee9 100644
--- a/arch/sh/kernel/perf_event.c
+++ b/arch/sh/kernel/perf_event.c
@@ -10,7 +10,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *
  * ppc:
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index b0da5aedb336..3091267c5cc3 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -9,7 +9,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  */
 
 #include <linux/perf_event.h>
diff --git a/arch/tile/kernel/perf_event.c b/arch/tile/kernel/perf_event.c
index bb509cee3b59..8767060d70fb 100644
--- a/arch/tile/kernel/perf_event.c
+++ b/arch/tile/kernel/perf_event.c
@@ -21,7 +21,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *  Copyright (C) 2009 Google, Inc., Stephane Eranian
  */
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 4562cf070c27..2bf79d7c97df 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -5,7 +5,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *  Copyright (C) 2009 Google, Inc., Stephane Eranian
  *
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index ffa7a92025e1..ab18b8a91583 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -5,7 +5,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *  Copyright (C) 2009 Google, Inc., Stephane Eranian
  *
diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c
index dc5fa6a1e8d6..3512ba607361 100644
--- a/arch/x86/kernel/irq_work.c
+++ b/arch/x86/kernel/irq_work.c
@@ -1,7 +1,7 @@
 /*
  * x86 specific code for irq_work
  *
- * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra
  */
 
 #include <linux/kernel.h>
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index db284bff29dc..9dbb739cafa0 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -5,7 +5,7 @@
  * Copyright 2001 Red Hat, Inc.
  * Based on code from mm/memory.c Copyright Linus Torvalds and others.
  *
- * Copyright 2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright 2011 Red Hat, Inc., Peter Zijlstra
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 8dde55974f18..0536524bb9eb 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -5,7 +5,7 @@
  * Jump label support
  *
  * Copyright (C) 2009-2012 Jason Baron <jbaron@redhat.com>
- * Copyright (C) 2011-2012 Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra
  *
  * DEPRECATED API:
  *
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 70400dc7660f..c57e424d914b 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -2,7 +2,7 @@
  * Runtime locking correctness validator
  *
  *  Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
- *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
  *
  * see Documentation/locking/lockdep-design.txt for more details.
  */
diff --git a/include/linux/proportions.h b/include/linux/proportions.h
index 5440f64d2942..21221338ad18 100644
--- a/include/linux/proportions.h
+++ b/include/linux/proportions.h
@@ -1,7 +1,7 @@
 /*
  * FLoating proportions
  *
- *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
  *
  * This file contains the public data structure and API definitions.
  */
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index 0bdc72f36905..4a29c75b146e 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -21,7 +21,7 @@
  * Authors:
  *	Srikar Dronamraju
  *	Jim Keniston
- * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra
  */
 
 #include <linux/errno.h>
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index d659487254d5..9c418002b8c1 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -3,7 +3,7 @@
  *
  *  Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
  *  Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar
- *  Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra
  *  Copyright  ©  2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
  *
  * For licensing details see kernel-base/COPYING
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1ac857aff7b0..5854fcf7f05a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3,7 +3,7 @@
  *
  *  Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
  *  Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar
- *  Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra
  *  Copyright  ©  2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
  *
  * For licensing details see kernel-base/COPYING
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index b5d1ea79c595..adfdc0536117 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -3,7 +3,7 @@
  *
  *  Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
  *  Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar
- *  Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra
  *  Copyright  ©  2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
  *
  * For licensing details see kernel-base/COPYING
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 4e5e9798aa0c..7dad84913abf 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -19,7 +19,7 @@
  * Authors:
  *	Srikar Dronamraju
  *	Jim Keniston
- * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra
  */
 
 #include <linux/kernel.h>
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index cbf9fb899d92..bcf107ce0854 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra
  *
  * Provides a framework for enqueueing and running callbacks from hardirq
  * context. The enqueueing is NMI-safe.
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index f7dd15d537f9..05254eeb4b4e 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -2,7 +2,7 @@
  * jump label support
  *
  * Copyright (C) 2009 Jason Baron <jbaron@redhat.com>
- * Copyright (C) 2011 Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2011 Peter Zijlstra
  *
  */
 #include <linux/memory.h>
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index deae3907ac1e..60ace56618f6 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -6,7 +6,7 @@
  * Started by Ingo Molnar:
  *
  *  Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
- *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
  *
  * this code maps all the lock dependencies as they occur in a live kernel
  * and will warn about the following classes of locking bugs:
diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c
index d83d798bef95..dbb61a302548 100644
--- a/kernel/locking/lockdep_proc.c
+++ b/kernel/locking/lockdep_proc.c
@@ -6,7 +6,7 @@
  * Started by Ingo Molnar:
  *
  *  Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
- *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
  *
  * Code for /proc/lockdep and /proc/lockdep_stats:
  *
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index c0a205101c23..caf4041f5b0a 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -1,7 +1,7 @@
 /*
  * sched_clock for unstable cpu clocks
  *
- *  Copyright (C) 2008 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008 Red Hat, Inc., Peter Zijlstra
  *
  *  Updates and enhancements:
  *    Copyright (C) 2008 Red Hat, Inc. Steven Rostedt <srostedt@redhat.com>
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f04fda8f669c..90e26b11deaa 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -17,7 +17,7 @@
  *  Copyright (C) 2007, Thomas Gleixner <tglx@linutronix.de>
  *
  *  Adaptive scheduling granularity, math enhancements by Peter Zijlstra
- *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
  */
 
 #include <linux/latencytop.h>
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index abfc903e741e..cc9f7a9319be 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -1,7 +1,7 @@
 /*
  * trace event based perf event profiling/tracing
  *
- * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra
  * Copyright (C) 2009-2010 Frederic Weisbecker <fweisbec@gmail.com>
  */
 
diff --git a/lib/btree.c b/lib/btree.c
index 4264871ea1a0..f93a945274af 100644
--- a/lib/btree.c
+++ b/lib/btree.c
@@ -5,7 +5,7 @@
  *
  * Copyright (c) 2007-2008 Joern Engel <joern@logfs.org>
  * Bits and pieces stolen from Peter Zijlstra's code, which is
- * Copyright 2007, Red Hat Inc. Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright 2007, Red Hat Inc. Peter Zijlstra
  * GPLv2
  *
  * see http://programming.kicks-ass.net/kernel-patches/vma_lookup/btree.patch
diff --git a/lib/proportions.c b/lib/proportions.c
index 6f724298f67a..efa54f259ea9 100644
--- a/lib/proportions.c
+++ b/lib/proportions.c
@@ -1,7 +1,7 @@
 /*
  * Floating proportions
  *
- *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
  *
  * Description:
  *
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 3e4d65445fa7..d15d88c8efa1 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2,7 +2,7 @@
  * mm/page-writeback.c
  *
  * Copyright (C) 2002, Linus Torvalds.
- * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
  *
  * Contains functions related to writing back dirty pages at the
  * address_space level.
-- 
cgit v1.2.3


From c86b3de8c8b02d7e474fdc002c8df533b844524c Mon Sep 17 00:00:00 2001
From: Arnd Bergmann
Date: Tue, 17 Nov 2015 17:48:52 +0100
Subject: thermal: fix thermal_zone_bind_cooling_device prototype

When the prototype for thermal_zone_bind_cooling_device
changed, the static inline wrapper function was left alone,
which in theory can cause build warnings:

I have seen this error in the past:
drivers/thermal/db8500_thermal.c: In function 'db8500_cdev_bind':
drivers/thermal/db8500_thermal.c:78:9: error: too many arguments to function 'thermal_zone_bind_cooling_device'
   ret = thermal_zone_bind_cooling_device(thermal, i, cdev,

while this one no longer shows up, there is no doubt that
the prototype is still wrong, so let's just fix it anyway.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Fixes: 6cd9e9f629f1 ("thermal: of: fix cooling device weights in device tree")
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 include/linux/thermal.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 4014a59828fc..613c29bd6baf 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -438,7 +438,8 @@ static inline void thermal_zone_device_unregister(
 static inline int thermal_zone_bind_cooling_device(
 	struct thermal_zone_device *tz, int trip,
 	struct thermal_cooling_device *cdev,
-	unsigned long upper, unsigned long lower)
+	unsigned long upper, unsigned long lower,
+	unsigned int weight)
 { return -ENODEV; }
 static inline int thermal_zone_unbind_cooling_device(
 	struct thermal_zone_device *tz, int trip,
-- 
cgit v1.2.3


From 91ab4b4d16e6649fbbf65f303c0c4e20ed680bd1 Mon Sep 17 00:00:00 2001
From: Jeff Layton
Date: Thu, 19 Nov 2015 14:30:26 -0500
Subject: nfs: use sliding delay when LAYOUTGET gets NFS4ERR_DELAY

When LAYOUTGET gets NFS4ERR_DELAY, we currently will wait 15s before
retrying the call. That is a _very_ long time, so add a timeout value to
struct nfs4_layoutget and pass nfs4_async_handle_error a pointer to it.
This allows the RPC engine to use a sliding delay window, instead of a
15s delay.

Signed-off-by: Jeff Layton <jeff.layton@primarydata.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 fs/nfs/nfs4proc.c       | 2 +-
 include/linux/nfs_xdr.h | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 765a03559363..89818036f035 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -7866,7 +7866,7 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
 			spin_unlock(&inode->i_lock);
 		goto out_restart;
 	}
-	if (nfs4_async_handle_error(task, server, state, NULL) == -EAGAIN)
+	if (nfs4_async_handle_error(task, server, state, &lgp->timeout) == -EAGAIN)
 		goto out_restart;
 out:
 	dprintk("<-- %s\n", __func__);
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 570d630f98ae..11bbae44f4cb 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -251,6 +251,7 @@ struct nfs4_layoutget {
 	struct nfs4_layoutget_res res;
 	struct rpc_cred *cred;
 	gfp_t gfp_flags;
+	long timeout;
 };
 
 struct nfs4_getdeviceinfo_args {
-- 
cgit v1.2.3


From fbc416ff86183e2203cdf975e2881d7c164b0271 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann
Date: Fri, 20 Nov 2015 12:12:21 +0100
Subject: arm64: fix building without CONFIG_UID16

As reported by Michal Simek, building an ARM64 kernel with CONFIG_UID16
disabled currently fails because the system call table still needs to
reference the individual function entry points that are provided by
kernel/sys_ni.c in this case, and the declarations are hidden inside
of #ifdef CONFIG_UID16:

arch/arm64/include/asm/unistd32.h:57:8: error: 'sys_lchown16' undeclared here (not in a function)
 __SYSCALL(__NR_lchown, sys_lchown16)

I believe this problem only exists on ARM64, because older architectures
tend to not need declarations when their system call table is built
in assembly code, while newer architectures tend to not need UID16
support. ARM64 only uses these system calls for compatibility with
32-bit ARM binaries.

This changes the CONFIG_UID16 check into CONFIG_HAVE_UID16, which is
set unconditionally on ARM64 with CONFIG_COMPAT, so we see the
declarations whenever we need them, but otherwise the behavior is
unchanged.

Fixes: af1839eb4bd4 ("Kconfig: clean up the long arch list for the UID16 config option")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Will Deacon <will.deacon@arm.com>
Cc: stable@vger.kernel.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 include/linux/syscalls.h | 2 +-
 include/linux/types.h    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index a156b82dd14c..c2b66a277e98 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -524,7 +524,7 @@ asmlinkage long sys_chown(const char __user *filename,
 asmlinkage long sys_lchown(const char __user *filename,
 				uid_t user, gid_t group);
 asmlinkage long sys_fchown(unsigned int fd, uid_t user, gid_t group);
-#ifdef CONFIG_UID16
+#ifdef CONFIG_HAVE_UID16
 asmlinkage long sys_chown16(const char __user *filename,
 				old_uid_t user, old_gid_t group);
 asmlinkage long sys_lchown16(const char __user *filename,
diff --git a/include/linux/types.h b/include/linux/types.h
index 70d8500bddf1..70dd3dfde631 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -35,7 +35,7 @@ typedef __kernel_gid16_t        gid16_t;
 
 typedef unsigned long		uintptr_t;
 
-#ifdef CONFIG_UID16
+#ifdef CONFIG_HAVE_UID16
 /* This is defined by include/asm-{arch}/posix_types.h */
 typedef __kernel_old_uid_t	old_uid_t;
 typedef __kernel_old_gid_t	old_gid_t;
-- 
cgit v1.2.3


From c9da161c6517ba12154059d3b965c2cbaf16f90f Mon Sep 17 00:00:00 2001
From: Daniel Borkmann
Date: Tue, 24 Nov 2015 21:28:15 +0100
Subject: bpf: fix clearing on persistent program array maps

Currently, when having map file descriptors pointing to program arrays,
there's still the issue that we unconditionally flush program array
contents via bpf_fd_array_map_clear() in bpf_map_release(). This happens
when such a file descriptor is released and is independent of the map's
refcount.

Having this flush independent of the refcount is for a reason: there
can be arbitrary complex dependency chains among tail calls, also circular
ones (direct or indirect, nesting limit determined during runtime), and
we need to make sure that the map drops all references to eBPF programs
it holds, so that the map's refcount can eventually drop to zero and
initiate its freeing. Btw, a walk of the whole dependency graph would
not be possible for various reasons, one being complexity and another
one inconsistency, i.e. new programs can be added to parts of the graph
at any time, so there's no guaranteed consistent state for the time of
such a walk.

Now, the program array pinning itself works, but the issue is that each
derived file descriptor on close would nevertheless call unconditionally
into bpf_fd_array_map_clear(). Instead, keep track of users and postpone
this flush until the last reference to a user is dropped. As this only
concerns a subset of references (f.e. a prog array could hold a program
that itself has reference on the prog array holding it, etc), we need to
track them separately.

Short analysis on the refcounting: on map creation time usercnt will be
one, so there's no change in behaviour for bpf_map_release(), if unpinned.
If we already fail in map_create(), we are immediately freed, and no
file descriptor has been made public yet. In bpf_obj_pin_user(), we need
to probe for a possible map in bpf_fd_probe_obj() already with a usercnt
reference, so before we drop the reference on the fd with fdput().
Therefore, if actual pinning fails, we need to drop that reference again
in bpf_any_put(), otherwise we keep holding it. When last reference
drops on the inode, the bpf_any_put() in bpf_evict_inode() will take
care of dropping the usercnt again. In the bpf_obj_get_user() case, the
bpf_any_get() will grab a reference on the usercnt, still at a time when
we have the reference on the path. Should we later on fail to grab a new
file descriptor, bpf_any_put() will drop it, otherwise we hold it until
bpf_map_release() time.

Joint work with Alexei.

Fixes: b2197755b263 ("bpf: add support for persistent maps/progs")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/bpf.h   |  5 ++++-
 kernel/bpf/inode.c    |  6 +++---
 kernel/bpf/syscall.c  | 36 +++++++++++++++++++++++++-----------
 kernel/bpf/verifier.c |  3 +--
 4 files changed, 33 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index de464e6683b6..83d1926c61e4 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -40,6 +40,7 @@ struct bpf_map {
 	struct user_struct *user;
 	const struct bpf_map_ops *ops;
 	struct work_struct work;
+	atomic_t usercnt;
 };
 
 struct bpf_map_type_list {
@@ -167,8 +168,10 @@ struct bpf_prog *bpf_prog_get(u32 ufd);
 void bpf_prog_put(struct bpf_prog *prog);
 void bpf_prog_put_rcu(struct bpf_prog *prog);
 
-struct bpf_map *bpf_map_get(u32 ufd);
+struct bpf_map *bpf_map_get_with_uref(u32 ufd);
 struct bpf_map *__bpf_map_get(struct fd f);
+void bpf_map_inc(struct bpf_map *map, bool uref);
+void bpf_map_put_with_uref(struct bpf_map *map);
 void bpf_map_put(struct bpf_map *map);
 
 extern int sysctl_unprivileged_bpf_disabled;
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index be6d726e31c9..5a8a797d50b7 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -34,7 +34,7 @@ static void *bpf_any_get(void *raw, enum bpf_type type)
 		atomic_inc(&((struct bpf_prog *)raw)->aux->refcnt);
 		break;
 	case BPF_TYPE_MAP:
-		atomic_inc(&((struct bpf_map *)raw)->refcnt);
+		bpf_map_inc(raw, true);
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -51,7 +51,7 @@ static void bpf_any_put(void *raw, enum bpf_type type)
 		bpf_prog_put(raw);
 		break;
 	case BPF_TYPE_MAP:
-		bpf_map_put(raw);
+		bpf_map_put_with_uref(raw);
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -64,7 +64,7 @@ static void *bpf_fd_probe_obj(u32 ufd, enum bpf_type *type)
 	void *raw;
 
 	*type = BPF_TYPE_MAP;
-	raw = bpf_map_get(ufd);
+	raw = bpf_map_get_with_uref(ufd);
 	if (IS_ERR(raw)) {
 		*type = BPF_TYPE_PROG;
 		raw = bpf_prog_get(ufd);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 0d3313d02a7e..4a8f3c1d7da6 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -82,6 +82,14 @@ static void bpf_map_free_deferred(struct work_struct *work)
 	map->ops->map_free(map);
 }
 
+static void bpf_map_put_uref(struct bpf_map *map)
+{
+	if (atomic_dec_and_test(&map->usercnt)) {
+		if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY)
+			bpf_fd_array_map_clear(map);
+	}
+}
+
 /* decrement map refcnt and schedule it for freeing via workqueue
  * (unrelying map implementation ops->map_free() might sleep)
  */
@@ -93,17 +101,15 @@ void bpf_map_put(struct bpf_map *map)
 	}
 }
 
-static int bpf_map_release(struct inode *inode, struct file *filp)
+void bpf_map_put_with_uref(struct bpf_map *map)
 {
-	struct bpf_map *map = filp->private_data;
-
-	if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY)
-		/* prog_array stores refcnt-ed bpf_prog pointers
-		 * release them all when user space closes prog_array_fd
-		 */
-		bpf_fd_array_map_clear(map);
-
+	bpf_map_put_uref(map);
 	bpf_map_put(map);
+}
+
+static int bpf_map_release(struct inode *inode, struct file *filp)
+{
+	bpf_map_put_with_uref(filp->private_data);
 	return 0;
 }
 
@@ -142,6 +148,7 @@ static int map_create(union bpf_attr *attr)
 		return PTR_ERR(map);
 
 	atomic_set(&map->refcnt, 1);
+	atomic_set(&map->usercnt, 1);
 
 	err = bpf_map_charge_memlock(map);
 	if (err)
@@ -174,7 +181,14 @@ struct bpf_map *__bpf_map_get(struct fd f)
 	return f.file->private_data;
 }
 
-struct bpf_map *bpf_map_get(u32 ufd)
+void bpf_map_inc(struct bpf_map *map, bool uref)
+{
+	atomic_inc(&map->refcnt);
+	if (uref)
+		atomic_inc(&map->usercnt);
+}
+
+struct bpf_map *bpf_map_get_with_uref(u32 ufd)
 {
 	struct fd f = fdget(ufd);
 	struct bpf_map *map;
@@ -183,7 +197,7 @@ struct bpf_map *bpf_map_get(u32 ufd)
 	if (IS_ERR(map))
 		return map;
 
-	atomic_inc(&map->refcnt);
+	bpf_map_inc(map, true);
 	fdput(f);
 
 	return map;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c6073056badf..a7945d10b378 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2021,8 +2021,7 @@ static int replace_map_fd_with_map_ptr(struct verifier_env *env)
 			 * will be used by the valid program until it's unloaded
 			 * and all maps are released in free_bpf_prog_info()
 			 */
-			atomic_inc(&map->refcnt);
-
+			bpf_map_inc(map, false);
 			fdput(f);
 next_insn:
 			insn++;
-- 
cgit v1.2.3


From 7c7a0e945349a3d0d497d7f32db6ed33d4031110 Mon Sep 17 00:00:00 2001
From: Gabriele Paoloni
Date: Wed, 11 Nov 2015 09:12:25 +0800
Subject: ARM/PCI: Move align_resource function pointer to pci_host_bridge
 structure

Commit b3a72384fe29 ("ARM/PCI: Replace pci_sys_data->align_resource with
global function pointer") introduced an ARM-specific align_resource()
function pointer.  This is not portable to other arches and doesn't work
for platforms with two different PCIe host bridge controllers.

Move the function pointer to the pci_host_bridge structure so each host
bridge driver can specify its own align_resource() function.

Signed-off-by: Gabriele Paoloni <gabriele.paoloni@huawei.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>---
 arch/arm/kernel/bios32.c | 19 +++++++++++--------
 drivers/pci/pci.h        |  2 --
 include/linux/pci.h      |  9 +++++++++
 3 files changed, 20 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c
index 6551d28c27e6..066f7f9ba411 100644
--- a/arch/arm/kernel/bios32.c
+++ b/arch/arm/kernel/bios32.c
@@ -17,11 +17,6 @@
 #include <asm/mach/pci.h>
 
 static int debug_pci;
-static resource_size_t (*align_resource)(struct pci_dev *dev,
-		  const struct resource *res,
-		  resource_size_t start,
-		  resource_size_t size,
-		  resource_size_t align) = NULL;
 
 /*
  * We can't use pci_get_device() here since we are
@@ -461,7 +456,6 @@ static void pcibios_init_hw(struct device *parent, struct hw_pci *hw,
 		sys->busnr   = busnr;
 		sys->swizzle = hw->swizzle;
 		sys->map_irq = hw->map_irq;
-		align_resource = hw->align_resource;
 		INIT_LIST_HEAD(&sys->resources);
 
 		if (hw->private_data)
@@ -470,6 +464,8 @@ static void pcibios_init_hw(struct device *parent, struct hw_pci *hw,
 		ret = hw->setup(nr, sys);
 
 		if (ret > 0) {
+			struct pci_host_bridge *host_bridge;
+
 			ret = pcibios_init_resources(nr, sys);
 			if (ret)  {
 				kfree(sys);
@@ -491,6 +487,9 @@ static void pcibios_init_hw(struct device *parent, struct hw_pci *hw,
 			busnr = sys->bus->busn_res.end + 1;
 
 			list_add(&sys->node, head);
+
+			host_bridge = pci_find_host_bridge(sys->bus);
+			host_bridge->align_resource = hw->align_resource;
 		} else {
 			kfree(sys);
 			if (ret < 0)
@@ -578,14 +577,18 @@ resource_size_t pcibios_align_resource(void *data, const struct resource *res,
 {
 	struct pci_dev *dev = data;
 	resource_size_t start = res->start;
+	struct pci_host_bridge *host_bridge;
 
 	if (res->flags & IORESOURCE_IO && start & 0x300)
 		start = (start + 0x3ff) & ~0x3ff;
 
 	start = (start + align - 1) & ~(align - 1);
 
-	if (align_resource)
-		return align_resource(dev, res, start, size, align);
+	host_bridge = pci_find_host_bridge(dev->bus);
+
+	if (host_bridge->align_resource)
+		return host_bridge->align_resource(dev, res,
+				start, size, align);
 
 	return start;
 }
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index fd2f03fa53f3..d390fc1475ec 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -337,6 +337,4 @@ static inline int pci_dev_specific_reset(struct pci_dev *dev, int probe)
 }
 #endif
 
-struct pci_host_bridge *pci_find_host_bridge(struct pci_bus *bus);
-
 #endif /* DRIVERS_PCI_H */
diff --git a/include/linux/pci.h b/include/linux/pci.h
index e828e7b4afec..6ae25aae88fd 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -412,9 +412,18 @@ struct pci_host_bridge {
 	void (*release_fn)(struct pci_host_bridge *);
 	void *release_data;
 	unsigned int ignore_reset_delay:1;	/* for entire hierarchy */
+	/* Resource alignment requirements */
+	resource_size_t (*align_resource)(struct pci_dev *dev,
+			const struct resource *res,
+			resource_size_t start,
+			resource_size_t size,
+			resource_size_t align);
 };
 
 #define	to_pci_host_bridge(n) container_of(n, struct pci_host_bridge, dev)
+
+struct pci_host_bridge *pci_find_host_bridge(struct pci_bus *bus);
+
 void pci_set_host_bridge_release(struct pci_host_bridge *bridge,
 		     void (*release_fn)(struct pci_host_bridge *),
 		     void *release_data);
-- 
cgit v1.2.3


From ca369d51b3e1649be4a72addd6d6a168cfb3f537 Mon Sep 17 00:00:00 2001
From: Martin K. Petersen
Date: Fri, 13 Nov 2015 16:46:48 -0500
Subject: block/sd: Fix device-imposed transfer length limits

Commit 4f258a46346c ("sd: Fix maximum I/O size for BLOCK_PC requests")
had the unfortunate side-effect of removing an implicit clamp to
BLK_DEF_MAX_SECTORS for REQ_TYPE_FS requests in the block layer
code. This caused problems for some SMR drives.

Debugging this issue revealed a few problems with the existing
infrastructure since the block layer didn't know how to deal with
device-imposed limits, only limits set by the I/O controller.

 - Introduce a new queue limit, max_dev_sectors, which is used by the
   ULD to signal the maximum sectors for a REQ_TYPE_FS request.

 - Ensure that max_dev_sectors is correctly stacked and taken into
   account when overriding max_sectors through sysfs.

 - Rework sd_read_block_limits() so it saves the max_xfer and opt_xfer
   values for later processing.

 - In sd_revalidate() set the queue's max_dev_sectors based on the
   MAXIMUM TRANSFER LENGTH value in the Block Limits VPD. If this value
   is not reported, fall back to a cap based on the CDB TRANSFER LENGTH
   field size.

 - In sd_revalidate(), use OPTIMAL TRANSFER LENGTH from the Block Limits
   VPD--if reported and sane--to signal the preferred device transfer
   size for FS requests. Otherwise use BLK_DEF_MAX_SECTORS.

 - blk_limits_max_hw_sectors() is no longer used and can be removed.

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=93581
Reviewed-by: Christoph Hellwig <hch@lst.de>
Tested-by: sweeneygj@gmx.com
Tested-by: Arzeets <anatol.pomozov@gmail.com>
Tested-by: David Eisner <david.eisner@oriel.oxon.org>
Tested-by: Mario Kicherer <dev@kicherer.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 block/blk-settings.c   | 36 ++++++++++++++++--------------------
 block/blk-sysfs.c      |  3 +++
 drivers/scsi/sd.c      | 46 ++++++++++++++++++++++++++++++----------------
 drivers/scsi/sd.h      |  1 +
 include/linux/blkdev.h |  2 +-
 5 files changed, 51 insertions(+), 37 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-settings.c b/block/blk-settings.c
index 7d8f129a1516..dd4973583978 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -91,7 +91,8 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
 	lim->virt_boundary_mask = 0;
 	lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
-	lim->max_sectors = lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS;
+	lim->max_sectors = lim->max_dev_sectors = lim->max_hw_sectors =
+		BLK_SAFE_MAX_SECTORS;
 	lim->chunk_sectors = 0;
 	lim->max_write_same_sectors = 0;
 	lim->max_discard_sectors = 0;
@@ -127,6 +128,7 @@ void blk_set_stacking_limits(struct queue_limits *lim)
 	lim->max_hw_sectors = UINT_MAX;
 	lim->max_segment_size = UINT_MAX;
 	lim->max_sectors = UINT_MAX;
+	lim->max_dev_sectors = UINT_MAX;
 	lim->max_write_same_sectors = UINT_MAX;
 }
 EXPORT_SYMBOL(blk_set_stacking_limits);
@@ -214,8 +216,8 @@ void blk_queue_bounce_limit(struct request_queue *q, u64 max_addr)
 EXPORT_SYMBOL(blk_queue_bounce_limit);
 
 /**
- * blk_limits_max_hw_sectors - set hard and soft limit of max sectors for request
- * @limits: the queue limits
+ * blk_queue_max_hw_sectors - set max sectors for a request for this queue
+ * @q:  the request queue for the device
  * @max_hw_sectors:  max hardware sectors in the usual 512b unit
  *
  * Description:
@@ -224,13 +226,19 @@ EXPORT_SYMBOL(blk_queue_bounce_limit);
  *    the device driver based upon the capabilities of the I/O
  *    controller.
  *
+ *    max_dev_sectors is a hard limit imposed by the storage device for
+ *    READ/WRITE requests. It is set by the disk driver.
+ *
  *    max_sectors is a soft limit imposed by the block layer for
  *    filesystem type requests.  This value can be overridden on a
  *    per-device basis in /sys/block/<device>/queue/max_sectors_kb.
  *    The soft limit can not exceed max_hw_sectors.
  **/
-void blk_limits_max_hw_sectors(struct queue_limits *limits, unsigned int max_hw_sectors)
+void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_sectors)
 {
+	struct queue_limits *limits = &q->limits;
+	unsigned int max_sectors;
+
 	if ((max_hw_sectors << 9) < PAGE_CACHE_SIZE) {
 		max_hw_sectors = 1 << (PAGE_CACHE_SHIFT - 9);
 		printk(KERN_INFO "%s: set to minimum %d\n",
@@ -238,22 +246,9 @@ void blk_limits_max_hw_sectors(struct queue_limits *limits, unsigned int max_hw_
 	}
 
 	limits->max_hw_sectors = max_hw_sectors;
-	limits->max_sectors = min_t(unsigned int, max_hw_sectors,
-				    BLK_DEF_MAX_SECTORS);
-}
-EXPORT_SYMBOL(blk_limits_max_hw_sectors);
-
-/**
- * blk_queue_max_hw_sectors - set max sectors for a request for this queue
- * @q:  the request queue for the device
- * @max_hw_sectors:  max hardware sectors in the usual 512b unit
- *
- * Description:
- *    See description for blk_limits_max_hw_sectors().
- **/
-void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_sectors)
-{
-	blk_limits_max_hw_sectors(&q->limits, max_hw_sectors);
+	max_sectors = min_not_zero(max_hw_sectors, limits->max_dev_sectors);
+	max_sectors = min_t(unsigned int, max_sectors, BLK_DEF_MAX_SECTORS);
+	limits->max_sectors = max_sectors;
 }
 EXPORT_SYMBOL(blk_queue_max_hw_sectors);
 
@@ -527,6 +522,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 
 	t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors);
 	t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors);
+	t->max_dev_sectors = min_not_zero(t->max_dev_sectors, b->max_dev_sectors);
 	t->max_write_same_sectors = min(t->max_write_same_sectors,
 					b->max_write_same_sectors);
 	t->bounce_pfn = min_not_zero(t->bounce_pfn, b->bounce_pfn);
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 3e44a9da2a13..55c637b9c42b 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -205,6 +205,9 @@ queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
 	if (ret < 0)
 		return ret;
 
+	max_hw_sectors_kb = min_not_zero(max_hw_sectors_kb, (unsigned long)
+					 q->limits.max_dev_sectors >> 1);
+
 	if (max_sectors_kb > max_hw_sectors_kb || max_sectors_kb < page_kb)
 		return -EINVAL;
 
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index e868d39c39bb..7af47ed10d90 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -2238,11 +2238,8 @@ got_data:
 		}
 	}
 
-	if (sdkp->capacity > 0xffffffff) {
+	if (sdkp->capacity > 0xffffffff)
 		sdp->use_16_for_rw = 1;
-		sdkp->max_xfer_blocks = SD_MAX_XFER_BLOCKS;
-	} else
-		sdkp->max_xfer_blocks = SD_DEF_XFER_BLOCKS;
 
 	/* Rescale capacity to 512-byte units */
 	if (sector_size == 4096)
@@ -2559,7 +2556,6 @@ static void sd_read_block_limits(struct scsi_disk *sdkp)
 {
 	unsigned int sector_sz = sdkp->device->sector_size;
 	const int vpd_len = 64;
-	u32 max_xfer_length;
 	unsigned char *buffer = kmalloc(vpd_len, GFP_KERNEL);
 
 	if (!buffer ||
@@ -2567,14 +2563,11 @@ static void sd_read_block_limits(struct scsi_disk *sdkp)
 	    scsi_get_vpd_page(sdkp->device, 0xb0, buffer, vpd_len))
 		goto out;
 
-	max_xfer_length = get_unaligned_be32(&buffer[8]);
-	if (max_xfer_length)
-		sdkp->max_xfer_blocks = max_xfer_length;
-
 	blk_queue_io_min(sdkp->disk->queue,
 			 get_unaligned_be16(&buffer[6]) * sector_sz);
-	blk_queue_io_opt(sdkp->disk->queue,
-			 get_unaligned_be32(&buffer[12]) * sector_sz);
+
+	sdkp->max_xfer_blocks = get_unaligned_be32(&buffer[8]);
+	sdkp->opt_xfer_blocks = get_unaligned_be32(&buffer[12]);
 
 	if (buffer[3] == 0x3c) {
 		unsigned int lba_count, desc_count;
@@ -2723,6 +2716,11 @@ static int sd_try_extended_inquiry(struct scsi_device *sdp)
 	return 0;
 }
 
+static inline u32 logical_to_sectors(struct scsi_device *sdev, u32 blocks)
+{
+	return blocks << (ilog2(sdev->sector_size) - 9);
+}
+
 /**
  *	sd_revalidate_disk - called the first time a new disk is seen,
  *	performs disk spin up, read_capacity, etc.
@@ -2732,8 +2730,9 @@ static int sd_revalidate_disk(struct gendisk *disk)
 {
 	struct scsi_disk *sdkp = scsi_disk(disk);
 	struct scsi_device *sdp = sdkp->device;
+	struct request_queue *q = sdkp->disk->queue;
 	unsigned char *buffer;
-	unsigned int max_xfer;
+	unsigned int dev_max, rw_max;
 
 	SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp,
 				      "sd_revalidate_disk\n"));
@@ -2781,11 +2780,26 @@ static int sd_revalidate_disk(struct gendisk *disk)
 	 */
 	sd_set_flush_flag(sdkp);
 
-	max_xfer = sdkp->max_xfer_blocks;
-	max_xfer <<= ilog2(sdp->sector_size) - 9;
+	/* Initial block count limit based on CDB TRANSFER LENGTH field size. */
+	dev_max = sdp->use_16_for_rw ? SD_MAX_XFER_BLOCKS : SD_DEF_XFER_BLOCKS;
+
+	/* Some devices report a maximum block count for READ/WRITE requests. */
+	dev_max = min_not_zero(dev_max, sdkp->max_xfer_blocks);
+	q->limits.max_dev_sectors = logical_to_sectors(sdp, dev_max);
+
+	/*
+	 * Use the device's preferred I/O size for reads and writes
+	 * unless the reported value is unreasonably large (or garbage).
+	 */
+	if (sdkp->opt_xfer_blocks && sdkp->opt_xfer_blocks <= dev_max &&
+	    sdkp->opt_xfer_blocks <= SD_DEF_XFER_BLOCKS)
+		rw_max = q->limits.io_opt =
+			logical_to_sectors(sdp, sdkp->opt_xfer_blocks);
+	else
+		rw_max = BLK_DEF_MAX_SECTORS;
 
-	sdkp->disk->queue->limits.max_sectors =
-		min_not_zero(queue_max_hw_sectors(sdkp->disk->queue), max_xfer);
+	/* Combine with controller limits */
+	q->limits.max_sectors = min(rw_max, queue_max_hw_sectors(q));
 
 	set_capacity(disk, sdkp->capacity);
 	sd_config_write_same(sdkp);
diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
index 63ba5ca7f9a1..5f2a84aff29f 100644
--- a/drivers/scsi/sd.h
+++ b/drivers/scsi/sd.h
@@ -67,6 +67,7 @@ struct scsi_disk {
 	atomic_t	openers;
 	sector_t	capacity;	/* size in 512-byte sectors */
 	u32		max_xfer_blocks;
+	u32		opt_xfer_blocks;
 	u32		max_ws_blocks;
 	u32		max_unmap_blocks;
 	u32		unmap_granularity;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 38a5ff772a37..9dacb745fa96 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -253,6 +253,7 @@ struct queue_limits {
 	unsigned long		virt_boundary_mask;
 
 	unsigned int		max_hw_sectors;
+	unsigned int		max_dev_sectors;
 	unsigned int		chunk_sectors;
 	unsigned int		max_sectors;
 	unsigned int		max_segment_size;
@@ -948,7 +949,6 @@ extern struct request_queue *blk_init_allocated_queue(struct request_queue *,
 extern void blk_cleanup_queue(struct request_queue *);
 extern void blk_queue_make_request(struct request_queue *, make_request_fn *);
 extern void blk_queue_bounce_limit(struct request_queue *, u64);
-extern void blk_limits_max_hw_sectors(struct queue_limits *, unsigned int);
 extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int);
 extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int);
 extern void blk_queue_max_segments(struct request_queue *, unsigned short);
-- 
cgit v1.2.3


From 3a66d7dca186ebdef9b0bf55e216778fa598062c Mon Sep 17 00:00:00 2001
From: Bart Van Assche
Date: Thu, 22 Oct 2015 16:02:14 -0700
Subject: kref: Remove kref_put_spinlock_irqsave()

The last user is gone. Hence remove this function.

Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Joern Engel <joern@logfs.org>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 include/linux/kref.h | 33 ---------------------------------
 1 file changed, 33 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kref.h b/include/linux/kref.h
index 484604d184be..e15828fd71f1 100644
--- a/include/linux/kref.h
+++ b/include/linux/kref.h
@@ -19,7 +19,6 @@
 #include <linux/atomic.h>
 #include <linux/kernel.h>
 #include <linux/mutex.h>
-#include <linux/spinlock.h>
 
 struct kref {
 	atomic_t refcount;
@@ -99,38 +98,6 @@ static inline int kref_put(struct kref *kref, void (*release)(struct kref *kref)
 	return kref_sub(kref, 1, release);
 }
 
-/**
- * kref_put_spinlock_irqsave - decrement refcount for object.
- * @kref: object.
- * @release: pointer to the function that will clean up the object when the
- *	     last reference to the object is released.
- *	     This pointer is required, and it is not acceptable to pass kfree
- *	     in as this function.
- * @lock: lock to take in release case
- *
- * Behaves identical to kref_put with one exception.  If the reference count
- * drops to zero, the lock will be taken atomically wrt dropping the reference
- * count.  The release function has to call spin_unlock() without _irqrestore.
- */
-static inline int kref_put_spinlock_irqsave(struct kref *kref,
-		void (*release)(struct kref *kref),
-		spinlock_t *lock)
-{
-	unsigned long flags;
-
-	WARN_ON(release == NULL);
-	if (atomic_add_unless(&kref->refcount, -1, 1))
-		return 0;
-	spin_lock_irqsave(lock, flags);
-	if (atomic_dec_and_test(&kref->refcount)) {
-		release(kref);
-		local_irq_restore(flags);
-		return 1;
-	}
-	spin_unlock_irqrestore(lock, flags);
-	return 0;
-}
-
 static inline int kref_put_mutex(struct kref *kref,
 				 void (*release)(struct kref *kref),
 				 struct mutex *lock)
-- 
cgit v1.2.3


From 08236c6bb2980561fba657c58fdc76f2865f236c Mon Sep 17 00:00:00 2001
From: Matias Bjørling
Date: Sat, 28 Nov 2015 16:49:27 +0100
Subject: lightnvm: unconverted ppa returned in get_bb_tbl

The get_bb_tbl function takes ppa as a generic address, which is
converted to the ppa device address within the device driver. When
the update_bbtbl callback is called from get_bb_tbl, the device
specific ppa is used, instead of the generic ppa.

Make sure to pass the generic ppa.

Signed-off-by: Matias Bjørling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 drivers/lightnvm/gennvm.c    | 3 +--
 drivers/nvme/host/lightnvm.c | 4 +++-
 include/linux/lightnvm.h     | 2 +-
 3 files changed, 5 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/lightnvm/gennvm.c b/drivers/lightnvm/gennvm.c
index 3969a9875e59..35dde84b71e9 100644
--- a/drivers/lightnvm/gennvm.c
+++ b/drivers/lightnvm/gennvm.c
@@ -75,7 +75,6 @@ static int gennvm_block_bb(struct ppa_addr ppa, int nr_blocks, u8 *blks,
 	struct nvm_block *blk;
 	int i;
 
-	ppa = dev_to_generic_addr(gn->dev, ppa);
 	lun = &gn->luns[(dev->nr_luns * ppa.g.ch) + ppa.g.lun];
 
 	for (i = 0; i < nr_blocks; i++) {
@@ -187,7 +186,7 @@ static int gennvm_blocks_init(struct nvm_dev *dev, struct gen_nvm *gn)
 			ppa.g.lun = lun->vlun.id;
 			ppa = generic_to_dev_addr(dev, ppa);
 
-			ret = dev->ops->get_bb_tbl(dev->q, ppa,
+			ret = dev->ops->get_bb_tbl(dev, ppa,
 						dev->blks_per_lun,
 						gennvm_block_bb, gn);
 			if (ret)
diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index b9e5cc74053f..06c336410235 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -355,10 +355,11 @@ out:
 	return ret;
 }
 
-static int nvme_nvm_get_bb_tbl(struct request_queue *q, struct ppa_addr ppa,
+static int nvme_nvm_get_bb_tbl(struct nvm_dev *nvmdev, struct ppa_addr ppa,
 				int nr_blocks, nvm_bb_update_fn *update_bbtbl,
 				void *priv)
 {
+	struct request_queue *q = nvmdev->q;
 	struct nvme_ns *ns = q->queuedata;
 	struct nvme_dev *dev = ns->dev;
 	struct nvme_nvm_command c = {};
@@ -402,6 +403,7 @@ static int nvme_nvm_get_bb_tbl(struct request_queue *q, struct ppa_addr ppa,
 		goto out;
 	}
 
+	ppa = dev_to_generic_addr(nvmdev, ppa);
 	ret = update_bbtbl(ppa, nr_blocks, bb_tbl->blk, priv);
 	if (ret) {
 		ret = -EINTR;
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index 3db5552b17d5..c6916aec43b6 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -179,7 +179,7 @@ typedef int (nvm_bb_update_fn)(struct ppa_addr, int, u8 *, void *);
 typedef int (nvm_id_fn)(struct request_queue *, struct nvm_id *);
 typedef int (nvm_get_l2p_tbl_fn)(struct request_queue *, u64, u32,
 				nvm_l2p_update_fn *, void *);
-typedef int (nvm_op_bb_tbl_fn)(struct request_queue *, struct ppa_addr, int,
+typedef int (nvm_op_bb_tbl_fn)(struct nvm_dev *, struct ppa_addr, int,
 				nvm_bb_update_fn *, void *);
 typedef int (nvm_op_set_bb_fn)(struct request_queue *, struct nvm_rq *, int);
 typedef int (nvm_submit_io_fn)(struct request_queue *, struct nvm_rq *);
-- 
cgit v1.2.3


From bf4e6b4e757488dee1b6a581f49c7ac34cd217f8 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke
Date: Thu, 26 Nov 2015 08:46:57 +0100
Subject: block: Always check queue limits for cloned requests

When a cloned request is retried on other queues it always needs
to be checked against the queue limits of that queue.
Otherwise the calculations for nr_phys_segments might be wrong,
leading to a crash in scsi_init_sgtable().

To clarify this the patch renames blk_rq_check_limits()
to blk_cloned_rq_check_limits() and removes the symbol
export, as the new function should only be used for
cloned requests and never exported.

Cc: Mike Snitzer <snitzer@redhat.com>
Cc: Ewan Milne <emilne@redhat.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Fixes: e2a60da74 ("block: Clean up special command handling logic")
Cc: stable@vger.kernel.org # 3.7+
Acked-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-core.c       | 21 +++++++--------------
 include/linux/blkdev.h |  1 -
 2 files changed, 7 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-core.c b/block/blk-core.c
index 5131993b23a1..a0af4043dda2 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2114,7 +2114,8 @@ blk_qc_t submit_bio(int rw, struct bio *bio)
 EXPORT_SYMBOL(submit_bio);
 
 /**
- * blk_rq_check_limits - Helper function to check a request for the queue limit
+ * blk_cloned_rq_check_limits - Helper function to check a cloned request
+ *                              for new the queue limits
  * @q:  the queue
  * @rq: the request being checked
  *
@@ -2125,20 +2126,13 @@ EXPORT_SYMBOL(submit_bio);
  *    after it is inserted to @q, it should be checked against @q before
  *    the insertion using this generic function.
  *
- *    This function should also be useful for request stacking drivers
- *    in some cases below, so export this function.
  *    Request stacking drivers like request-based dm may change the queue
- *    limits while requests are in the queue (e.g. dm's table swapping).
- *    Such request stacking drivers should check those requests against
- *    the new queue limits again when they dispatch those requests,
- *    although such checkings are also done against the old queue limits
- *    when submitting requests.
+ *    limits when retrying requests on other queues. Those requests need
+ *    to be checked against the new queue limits again during dispatch.
  */
-int blk_rq_check_limits(struct request_queue *q, struct request *rq)
+static int blk_cloned_rq_check_limits(struct request_queue *q,
+				      struct request *rq)
 {
-	if (!rq_mergeable(rq))
-		return 0;
-
 	if (blk_rq_sectors(rq) > blk_queue_get_max_sectors(q, rq->cmd_flags)) {
 		printk(KERN_ERR "%s: over max size limit.\n", __func__);
 		return -EIO;
@@ -2158,7 +2152,6 @@ int blk_rq_check_limits(struct request_queue *q, struct request *rq)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(blk_rq_check_limits);
 
 /**
  * blk_insert_cloned_request - Helper for stacking drivers to submit a request
@@ -2170,7 +2163,7 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 	unsigned long flags;
 	int where = ELEVATOR_INSERT_BACK;
 
-	if (blk_rq_check_limits(q, rq))
+	if (blk_cloned_rq_check_limits(q, rq))
 		return -EIO;
 
 	if (rq->rq_disk &&
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c0d2b7927c1f..c06f8eaa42ff 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -773,7 +773,6 @@ extern void blk_rq_set_block_pc(struct request *);
 extern void blk_requeue_request(struct request_queue *, struct request *);
 extern void blk_add_request_payload(struct request *rq, struct page *page,
 		unsigned int len);
-extern int blk_rq_check_limits(struct request_queue *q, struct request *rq);
 extern int blk_lld_busy(struct request_queue *q);
 extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
 			     struct bio_set *bs, gfp_t gfp_mask,
-- 
cgit v1.2.3


From 880621c2605b82eb5af91a2c94223df6f5a3fb64 Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl
Date: Sun, 22 Nov 2015 17:46:09 +0100
Subject: packet: Allow packets with only a header (but no payload)

Commit 9c7077622dd91 ("packet: make packet_snd fail on len smaller
than l2 header") added validation for the packet size in packet_snd.
This change enforces that every packet needs a header (with at least
hard_header_len bytes) plus a payload with at least one byte. Before
this change the payload was optional.

This fixes PPPoE connections which do not have a "Service" or
"Host-Uniq" configured (which is violating the spec, but is still
widely used in real-world setups). Those are currently failing with the
following message: "pppd: packet size is too short (24 <= 24)"

Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 3 ++-
 net/packet/af_packet.c    | 4 ++--
 2 files changed, 4 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 67bfac1abfc1..3b5d134e945a 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1398,7 +1398,8 @@ enum netdev_priv_flags {
  *	@dma:		DMA channel
  *	@mtu:		Interface MTU value
  *	@type:		Interface hardware type
- *	@hard_header_len: Hardware header length
+ *	@hard_header_len: Hardware header length, which means that this is the
+ *			  minimum size of a packet.
  *
  *	@needed_headroom: Extra headroom the hardware may need, but not in all
  *			  cases can this be guaranteed
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 1cf928fb573e..992396aa635c 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2329,8 +2329,8 @@ static void tpacket_destruct_skb(struct sk_buff *skb)
 static bool ll_header_truncated(const struct net_device *dev, int len)
 {
 	/* net device doesn't like empty head */
-	if (unlikely(len <= dev->hard_header_len)) {
-		net_warn_ratelimited("%s: packet size is too short (%d <= %d)\n",
+	if (unlikely(len < dev->hard_header_len)) {
+		net_warn_ratelimited("%s: packet size is too short (%d < %d)\n",
 				     current->comm, len, dev->hard_header_len);
 		return true;
 	}
-- 
cgit v1.2.3


From 9cd3e072b0be17446e37d7414eac8a3499e0601e Mon Sep 17 00:00:00 2001
From: Eric Dumazet
Date: Sun, 29 Nov 2015 20:03:10 -0800
Subject: net: rename SOCK_ASYNC_NOSPACE and SOCK_ASYNC_WAITDATA

This patch is a cleanup to make following patch easier to
review.

Goal is to move SOCK_ASYNC_NOSPACE and SOCK_ASYNC_WAITDATA
from (struct socket)->flags to a (struct socket_wq)->flags
to benefit from RCU protection in sock_wake_async()

To ease backports, we rename both constants.

Two new helpers, sk_set_bit(int nr, struct sock *sk)
and sk_clear_bit(int net, struct sock *sk) are added so that
following patch can change their implementation.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 crypto/algif_aead.c          |  4 ++--
 crypto/algif_skcipher.c      |  6 +++---
 drivers/net/macvtap.c        |  4 ++--
 drivers/net/tun.c            |  4 ++--
 fs/dlm/lowcomms.c            |  4 ++--
 include/linux/net.h          |  6 +++---
 include/net/sock.h           | 10 ++++++++++
 net/bluetooth/af_bluetooth.c |  6 +++---
 net/caif/caif_socket.c       |  4 ++--
 net/core/datagram.c          |  2 +-
 net/core/sock.c              |  8 ++++----
 net/core/stream.c            |  4 ++--
 net/dccp/proto.c             |  3 +--
 net/decnet/af_decnet.c       |  8 ++++----
 net/ipv4/tcp.c               |  7 +++----
 net/iucv/af_iucv.c           |  2 +-
 net/nfc/llcp_sock.c          |  2 +-
 net/rxrpc/ar-output.c        |  2 +-
 net/sctp/socket.c            |  2 +-
 net/socket.c                 |  4 ++--
 net/sunrpc/xprtsock.c        | 14 +++++++-------
 net/unix/af_unix.c           |  6 +++---
 22 files changed, 60 insertions(+), 52 deletions(-)

(limited to 'include/linux')

diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c
index 0aa6fdfb448a..6d4d4569447e 100644
--- a/crypto/algif_aead.c
+++ b/crypto/algif_aead.c
@@ -125,7 +125,7 @@ static int aead_wait_for_data(struct sock *sk, unsigned flags)
 	if (flags & MSG_DONTWAIT)
 		return -EAGAIN;
 
-	set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+	sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 
 	for (;;) {
 		if (signal_pending(current))
@@ -139,7 +139,7 @@ static int aead_wait_for_data(struct sock *sk, unsigned flags)
 	}
 	finish_wait(sk_sleep(sk), &wait);
 
-	clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+	sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 
 	return err;
 }
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index af31a0ee4057..ca9efe17db1a 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -212,7 +212,7 @@ static int skcipher_wait_for_wmem(struct sock *sk, unsigned flags)
 	if (flags & MSG_DONTWAIT)
 		return -EAGAIN;
 
-	set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+	sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
 	for (;;) {
 		if (signal_pending(current))
@@ -258,7 +258,7 @@ static int skcipher_wait_for_data(struct sock *sk, unsigned flags)
 		return -EAGAIN;
 	}
 
-	set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+	sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 
 	for (;;) {
 		if (signal_pending(current))
@@ -272,7 +272,7 @@ static int skcipher_wait_for_data(struct sock *sk, unsigned flags)
 	}
 	finish_wait(sk_sleep(sk), &wait);
 
-	clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+	sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 
 	return err;
 }
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 54036ae0a388..0fc521941c71 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -498,7 +498,7 @@ static void macvtap_sock_write_space(struct sock *sk)
 	wait_queue_head_t *wqueue;
 
 	if (!sock_writeable(sk) ||
-	    !test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags))
+	    !test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags))
 		return;
 
 	wqueue = sk_sleep(sk);
@@ -585,7 +585,7 @@ static unsigned int macvtap_poll(struct file *file, poll_table * wait)
 		mask |= POLLIN | POLLRDNORM;
 
 	if (sock_writeable(&q->sk) ||
-	    (!test_and_set_bit(SOCK_ASYNC_NOSPACE, &q->sock.flags) &&
+	    (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &q->sock.flags) &&
 	     sock_writeable(&q->sk)))
 		mask |= POLLOUT | POLLWRNORM;
 
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index b1878faea397..f0db770e8b2f 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1040,7 +1040,7 @@ static unsigned int tun_chr_poll(struct file *file, poll_table *wait)
 		mask |= POLLIN | POLLRDNORM;
 
 	if (sock_writeable(sk) ||
-	    (!test_and_set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
+	    (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
 	     sock_writeable(sk)))
 		mask |= POLLOUT | POLLWRNORM;
 
@@ -1488,7 +1488,7 @@ static void tun_sock_write_space(struct sock *sk)
 	if (!sock_writeable(sk))
 		return;
 
-	if (!test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags))
+	if (!test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags))
 		return;
 
 	wqueue = sk_sleep(sk);
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 87e9d796cf7d..3a37bd3f9637 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -421,7 +421,7 @@ static void lowcomms_write_space(struct sock *sk)
 
 	if (test_and_clear_bit(CF_APP_LIMITED, &con->flags)) {
 		con->sock->sk->sk_write_pending--;
-		clear_bit(SOCK_ASYNC_NOSPACE, &con->sock->flags);
+		clear_bit(SOCKWQ_ASYNC_NOSPACE, &con->sock->flags);
 	}
 
 	if (!test_and_set_bit(CF_WRITE_PENDING, &con->flags))
@@ -1448,7 +1448,7 @@ static void send_to_sock(struct connection *con)
 					      msg_flags);
 			if (ret == -EAGAIN || ret == 0) {
 				if (ret == -EAGAIN &&
-				    test_bit(SOCK_ASYNC_NOSPACE, &con->sock->flags) &&
+				    test_bit(SOCKWQ_ASYNC_NOSPACE, &con->sock->flags) &&
 				    !test_and_set_bit(CF_APP_LIMITED, &con->flags)) {
 					/* Notify TCP that we're limited by the
 					 * application window size.
diff --git a/include/linux/net.h b/include/linux/net.h
index 70ac5e28e6b7..f514e4dd5521 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -34,8 +34,8 @@ struct inode;
 struct file;
 struct net;
 
-#define SOCK_ASYNC_NOSPACE	0
-#define SOCK_ASYNC_WAITDATA	1
+#define SOCKWQ_ASYNC_NOSPACE	0
+#define SOCKWQ_ASYNC_WAITDATA	1
 #define SOCK_NOSPACE		2
 #define SOCK_PASSCRED		3
 #define SOCK_PASSSEC		4
@@ -96,7 +96,7 @@ struct socket_wq {
  *  struct socket - general BSD socket
  *  @state: socket state (%SS_CONNECTED, etc)
  *  @type: socket type (%SOCK_STREAM, etc)
- *  @flags: socket flags (%SOCK_ASYNC_NOSPACE, etc)
+ *  @flags: socket flags (%SOCK_NOSPACE, etc)
  *  @ops: protocol specific socket operations
  *  @file: File back pointer for gc
  *  @sk: internal networking protocol agnostic socket representation
diff --git a/include/net/sock.h b/include/net/sock.h
index 7f89e4ba18d1..c155d09d8af4 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2005,6 +2005,16 @@ static inline unsigned long sock_wspace(struct sock *sk)
 	return amt;
 }
 
+static inline void sk_set_bit(int nr, struct sock *sk)
+{
+	set_bit(nr, &sk->sk_socket->flags);
+}
+
+static inline void sk_clear_bit(int nr, struct sock *sk)
+{
+	clear_bit(nr, &sk->sk_socket->flags);
+}
+
 static inline void sk_wake_async(struct sock *sk, int how, int band)
 {
 	if (sock_flag(sk, SOCK_FASYNC))
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index a3bffd1ec2b4..70306cc9d814 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -271,11 +271,11 @@ static long bt_sock_data_wait(struct sock *sk, long timeo)
 		if (signal_pending(current) || !timeo)
 			break;
 
-		set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+		sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 		release_sock(sk);
 		timeo = schedule_timeout(timeo);
 		lock_sock(sk);
-		clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+		sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 	}
 
 	__set_current_state(TASK_RUNNING);
@@ -441,7 +441,7 @@ unsigned int bt_sock_poll(struct file *file, struct socket *sock,
 	if (!test_bit(BT_SK_SUSPEND, &bt_sk(sk)->flags) && sock_writeable(sk))
 		mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
 	else
-		set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+		sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
 	return mask;
 }
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index cc858919108e..aa209b1066c9 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -323,7 +323,7 @@ static long caif_stream_data_wait(struct sock *sk, long timeo)
 			!timeo)
 			break;
 
-		set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+		sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 		release_sock(sk);
 		timeo = schedule_timeout(timeo);
 		lock_sock(sk);
@@ -331,7 +331,7 @@ static long caif_stream_data_wait(struct sock *sk, long timeo)
 		if (sock_flag(sk, SOCK_DEAD))
 			break;
 
-		clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+		sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 	}
 
 	finish_wait(sk_sleep(sk), &wait);
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 617088aee21d..d62af69ad844 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -785,7 +785,7 @@ unsigned int datagram_poll(struct file *file, struct socket *sock,
 	if (sock_writeable(sk))
 		mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
 	else
-		set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+		sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
 	return mask;
 }
diff --git a/net/core/sock.c b/net/core/sock.c
index 1e4dd54bfb5a..9d79569935a3 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1815,7 +1815,7 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo)
 {
 	DEFINE_WAIT(wait);
 
-	clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+	sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 	for (;;) {
 		if (!timeo)
 			break;
@@ -1861,7 +1861,7 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
 		if (sk_wmem_alloc_get(sk) < sk->sk_sndbuf)
 			break;
 
-		set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+		sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 		err = -EAGAIN;
 		if (!timeo)
@@ -2048,9 +2048,9 @@ int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb)
 	DEFINE_WAIT(wait);
 
 	prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
-	set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+	sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 	rc = sk_wait_event(sk, timeo, skb_peek_tail(&sk->sk_receive_queue) != skb);
-	clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+	sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 	finish_wait(sk_sleep(sk), &wait);
 	return rc;
 }
diff --git a/net/core/stream.c b/net/core/stream.c
index d70f77a0c889..43309428644d 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -126,7 +126,7 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
 		current_timeo = vm_wait = (prandom_u32() % (HZ / 5)) + 2;
 
 	while (1) {
-		set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+		sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
 		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
 
@@ -139,7 +139,7 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
 		}
 		if (signal_pending(current))
 			goto do_interrupted;
-		clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+		sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 		if (sk_stream_memory_free(sk) && !vm_wait)
 			break;
 
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index b5cf13a28009..41e65804ddf5 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -339,8 +339,7 @@ unsigned int dccp_poll(struct file *file, struct socket *sock,
 			if (sk_stream_is_writeable(sk)) {
 				mask |= POLLOUT | POLLWRNORM;
 			} else {  /* send SIGIO later */
-				set_bit(SOCK_ASYNC_NOSPACE,
-					&sk->sk_socket->flags);
+				sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 				set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 
 				/* Race breaker. If space is freed after
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 675cf94e04f8..eebf5ac8ce18 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -1747,9 +1747,9 @@ static int dn_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 		}
 
 		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
-		set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+		sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 		sk_wait_event(sk, &timeo, dn_data_ready(sk, queue, flags, target));
-		clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+		sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 		finish_wait(sk_sleep(sk), &wait);
 	}
 
@@ -2004,10 +2004,10 @@ static int dn_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 			}
 
 			prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
-			set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+			sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 			sk_wait_event(sk, &timeo,
 				      !dn_queue_too_long(scp, queue, flags));
-			clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+			sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 			finish_wait(sk_sleep(sk), &wait);
 			continue;
 		}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index c1728771cf89..c82cca18c90f 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -517,8 +517,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 			if (sk_stream_is_writeable(sk)) {
 				mask |= POLLOUT | POLLWRNORM;
 			} else {  /* send SIGIO later */
-				set_bit(SOCK_ASYNC_NOSPACE,
-					&sk->sk_socket->flags);
+				sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 				set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 
 				/* Race breaker. If space is freed after
@@ -906,7 +905,7 @@ static ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
 			goto out_err;
 	}
 
-	clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+	sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
 	mss_now = tcp_send_mss(sk, &size_goal, flags);
 	copied = 0;
@@ -1134,7 +1133,7 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 	}
 
 	/* This should be in poll */
-	clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+	sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
 	mss_now = tcp_send_mss(sk, &size_goal, flags);
 
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index fcb2752419c6..435608c4306d 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1483,7 +1483,7 @@ unsigned int iucv_sock_poll(struct file *file, struct socket *sock,
 	if (sock_writeable(sk) && iucv_below_msglim(sk))
 		mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
 	else
-		set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+		sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
 	return mask;
 }
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index b7de0da46acd..ecf0a0196f18 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -572,7 +572,7 @@ static unsigned int llcp_sock_poll(struct file *file, struct socket *sock,
 	if (sock_writeable(sk) && sk->sk_state == LLCP_CONNECTED)
 		mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
 	else
-		set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+		sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
 	pr_debug("mask 0x%x\n", mask);
 
diff --git a/net/rxrpc/ar-output.c b/net/rxrpc/ar-output.c
index a40d3afe93b7..14c4e12c47b0 100644
--- a/net/rxrpc/ar-output.c
+++ b/net/rxrpc/ar-output.c
@@ -531,7 +531,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
 	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
 
 	/* this should be in poll */
-	clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+	sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
 	if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
 		return -EPIPE;
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 897c01c029ca..2353985d689c 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -6458,7 +6458,7 @@ unsigned int sctp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	if (sctp_writeable(sk)) {
 		mask |= POLLOUT | POLLWRNORM;
 	} else {
-		set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+		sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 		/*
 		 * Since the socket is not locked, the buffer
 		 * might be made available after the writeable check and
diff --git a/net/socket.c b/net/socket.c
index dd2c247c99e3..16be908205fc 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1072,11 +1072,11 @@ int sock_wake_async(struct socket *sock, int how, int band)
 	}
 	switch (how) {
 	case SOCK_WAKE_WAITD:
-		if (test_bit(SOCK_ASYNC_WAITDATA, &sock->flags))
+		if (test_bit(SOCKWQ_ASYNC_WAITDATA, &sock->flags))
 			break;
 		goto call_kill;
 	case SOCK_WAKE_SPACE:
-		if (!test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sock->flags))
+		if (!test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sock->flags))
 			break;
 		/* fall through */
 	case SOCK_WAKE_IO:
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 1d1a70498910..2ffaf6a79499 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -398,7 +398,7 @@ static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen,
 	if (unlikely(!sock))
 		return -ENOTSOCK;
 
-	clear_bit(SOCK_ASYNC_NOSPACE, &sock->flags);
+	clear_bit(SOCKWQ_ASYNC_NOSPACE, &sock->flags);
 	if (base != 0) {
 		addr = NULL;
 		addrlen = 0;
@@ -442,7 +442,7 @@ static void xs_nospace_callback(struct rpc_task *task)
 	struct sock_xprt *transport = container_of(task->tk_rqstp->rq_xprt, struct sock_xprt, xprt);
 
 	transport->inet->sk_write_pending--;
-	clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);
+	clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags);
 }
 
 /**
@@ -467,7 +467,7 @@ static int xs_nospace(struct rpc_task *task)
 
 	/* Don't race with disconnect */
 	if (xprt_connected(xprt)) {
-		if (test_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags)) {
+		if (test_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags)) {
 			/*
 			 * Notify TCP that we're limited by the application
 			 * window size
@@ -478,7 +478,7 @@ static int xs_nospace(struct rpc_task *task)
 			xprt_wait_for_buffer_space(task, xs_nospace_callback);
 		}
 	} else {
-		clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);
+		clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags);
 		ret = -ENOTCONN;
 	}
 
@@ -626,7 +626,7 @@ process_status:
 	case -EPERM:
 		/* When the server has died, an ICMP port unreachable message
 		 * prompts ECONNREFUSED. */
-		clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);
+		clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags);
 	}
 
 	return status;
@@ -715,7 +715,7 @@ static int xs_tcp_send_request(struct rpc_task *task)
 	case -EADDRINUSE:
 	case -ENOBUFS:
 	case -EPIPE:
-		clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);
+		clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags);
 	}
 
 	return status;
@@ -1618,7 +1618,7 @@ static void xs_write_space(struct sock *sk)
 
 	if (unlikely(!(xprt = xprt_from_sock(sk))))
 		return;
-	if (test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sock->flags) == 0)
+	if (test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sock->flags) == 0)
 		return;
 
 	xprt_write_space(xprt);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 6ced74690eee..45aebd966978 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2191,7 +2191,7 @@ static long unix_stream_data_wait(struct sock *sk, long timeo,
 		    !timeo)
 			break;
 
-		set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+		sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 		unix_state_unlock(sk);
 		timeo = freezable_schedule_timeout(timeo);
 		unix_state_lock(sk);
@@ -2199,7 +2199,7 @@ static long unix_stream_data_wait(struct sock *sk, long timeo,
 		if (sock_flag(sk, SOCK_DEAD))
 			break;
 
-		clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+		sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 	}
 
 	finish_wait(sk_sleep(sk), &wait);
@@ -2683,7 +2683,7 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock,
 	if (writable)
 		mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
 	else
-		set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+		sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
 	return mask;
 }
-- 
cgit v1.2.3


From ceb5d58b217098a657f3850b7a2640f995032e62 Mon Sep 17 00:00:00 2001
From: Eric Dumazet
Date: Sun, 29 Nov 2015 20:03:11 -0800
Subject: net: fix sock_wake_async() rcu protection

Dmitry provided a syzkaller (http://github.com/google/syzkaller)
triggering a fault in sock_wake_async() when async IO is requested.

Said program stressed af_unix sockets, but the issue is generic
and should be addressed in core networking stack.

The problem is that by the time sock_wake_async() is called,
we should not access the @flags field of 'struct socket',
as the inode containing this socket might be freed without
further notice, and without RCU grace period.

We already maintain an RCU protected structure, "struct socket_wq"
so moving SOCKWQ_ASYNC_NOSPACE & SOCKWQ_ASYNC_WAITDATA into it
is the safe route.

It also reduces number of cache lines needing dirtying, so might
provide a performance improvement anyway.

In followup patches, we might move remaining flags (SOCK_NOSPACE,
SOCK_PASSCRED, SOCK_PASSSEC) to save 8 bytes and let 'struct socket'
being mostly read and let it being shared between cpus.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/net.h |  7 ++++++-
 include/net/sock.h  | 23 ++++++++++++++++-------
 net/core/stream.c   |  2 +-
 net/sctp/socket.c   | 24 ++++++++++++++----------
 net/socket.c        | 21 +++++++--------------
 5 files changed, 44 insertions(+), 33 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/net.h b/include/linux/net.h
index f514e4dd5521..0b4ac7da583a 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -34,6 +34,10 @@ struct inode;
 struct file;
 struct net;
 
+/* Historically, SOCKWQ_ASYNC_NOSPACE & SOCKWQ_ASYNC_WAITDATA were located
+ * in sock->flags, but moved into sk->sk_wq->flags to be RCU protected.
+ * Eventually all flags will be in sk->sk_wq_flags.
+ */
 #define SOCKWQ_ASYNC_NOSPACE	0
 #define SOCKWQ_ASYNC_WAITDATA	1
 #define SOCK_NOSPACE		2
@@ -89,6 +93,7 @@ struct socket_wq {
 	/* Note: wait MUST be first field of socket_wq */
 	wait_queue_head_t	wait;
 	struct fasync_struct	*fasync_list;
+	unsigned long		flags; /* %SOCKWQ_ASYNC_NOSPACE, etc */
 	struct rcu_head		rcu;
 } ____cacheline_aligned_in_smp;
 
@@ -202,7 +207,7 @@ enum {
 	SOCK_WAKE_URG,
 };
 
-int sock_wake_async(struct socket *sk, int how, int band);
+int sock_wake_async(struct socket_wq *sk_wq, int how, int band);
 int sock_register(const struct net_proto_family *fam);
 void sock_unregister(int family);
 int __sock_create(struct net *net, int family, int type, int proto,
diff --git a/include/net/sock.h b/include/net/sock.h
index c155d09d8af4..0434138c5f95 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -384,8 +384,10 @@ struct sock {
 	int			sk_rcvbuf;
 
 	struct sk_filter __rcu	*sk_filter;
-	struct socket_wq __rcu	*sk_wq;
-
+	union {
+		struct socket_wq __rcu	*sk_wq;
+		struct socket_wq	*sk_wq_raw;
+	};
 #ifdef CONFIG_XFRM
 	struct xfrm_policy	*sk_policy[2];
 #endif
@@ -2005,20 +2007,27 @@ static inline unsigned long sock_wspace(struct sock *sk)
 	return amt;
 }
 
+/* Note:
+ *  We use sk->sk_wq_raw, from contexts knowing this
+ *  pointer is not NULL and cannot disappear/change.
+ */
 static inline void sk_set_bit(int nr, struct sock *sk)
 {
-	set_bit(nr, &sk->sk_socket->flags);
+	set_bit(nr, &sk->sk_wq_raw->flags);
 }
 
 static inline void sk_clear_bit(int nr, struct sock *sk)
 {
-	clear_bit(nr, &sk->sk_socket->flags);
+	clear_bit(nr, &sk->sk_wq_raw->flags);
 }
 
-static inline void sk_wake_async(struct sock *sk, int how, int band)
+static inline void sk_wake_async(const struct sock *sk, int how, int band)
 {
-	if (sock_flag(sk, SOCK_FASYNC))
-		sock_wake_async(sk->sk_socket, how, band);
+	if (sock_flag(sk, SOCK_FASYNC)) {
+		rcu_read_lock();
+		sock_wake_async(rcu_dereference(sk->sk_wq), how, band);
+		rcu_read_unlock();
+	}
 }
 
 /* Since sk_{r,w}mem_alloc sums skb->truesize, even a small frame might
diff --git a/net/core/stream.c b/net/core/stream.c
index 43309428644d..b96f7a79e544 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -39,7 +39,7 @@ void sk_stream_write_space(struct sock *sk)
 			wake_up_interruptible_poll(&wq->wait, POLLOUT |
 						POLLWRNORM | POLLWRBAND);
 		if (wq && wq->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN))
-			sock_wake_async(sock, SOCK_WAKE_SPACE, POLL_OUT);
+			sock_wake_async(wq, SOCK_WAKE_SPACE, POLL_OUT);
 		rcu_read_unlock();
 	}
 }
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 2353985d689c..5e35ef34008b 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -6801,26 +6801,30 @@ no_packet:
 static void __sctp_write_space(struct sctp_association *asoc)
 {
 	struct sock *sk = asoc->base.sk;
-	struct socket *sock = sk->sk_socket;
 
-	if ((sctp_wspace(asoc) > 0) && sock) {
-		if (waitqueue_active(&asoc->wait))
-			wake_up_interruptible(&asoc->wait);
+	if (sctp_wspace(asoc) <= 0)
+		return;
+
+	if (waitqueue_active(&asoc->wait))
+		wake_up_interruptible(&asoc->wait);
 
-		if (sctp_writeable(sk)) {
-			wait_queue_head_t *wq = sk_sleep(sk);
+	if (sctp_writeable(sk)) {
+		struct socket_wq *wq;
 
-			if (wq && waitqueue_active(wq))
-				wake_up_interruptible(wq);
+		rcu_read_lock();
+		wq = rcu_dereference(sk->sk_wq);
+		if (wq) {
+			if (waitqueue_active(&wq->wait))
+				wake_up_interruptible(&wq->wait);
 
 			/* Note that we try to include the Async I/O support
 			 * here by modeling from the current TCP/UDP code.
 			 * We have not tested with it yet.
 			 */
 			if (!(sk->sk_shutdown & SEND_SHUTDOWN))
-				sock_wake_async(sock,
-						SOCK_WAKE_SPACE, POLL_OUT);
+				sock_wake_async(wq, SOCK_WAKE_SPACE, POLL_OUT);
 		}
+		rcu_read_unlock();
 	}
 }
 
diff --git a/net/socket.c b/net/socket.c
index 16be908205fc..456fadb3d819 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1056,27 +1056,20 @@ static int sock_fasync(int fd, struct file *filp, int on)
 	return 0;
 }
 
-/* This function may be called only under socket lock or callback_lock or rcu_lock */
+/* This function may be called only under rcu_lock */
 
-int sock_wake_async(struct socket *sock, int how, int band)
+int sock_wake_async(struct socket_wq *wq, int how, int band)
 {
-	struct socket_wq *wq;
-
-	if (!sock)
-		return -1;
-	rcu_read_lock();
-	wq = rcu_dereference(sock->wq);
-	if (!wq || !wq->fasync_list) {
-		rcu_read_unlock();
+	if (!wq || !wq->fasync_list)
 		return -1;
-	}
+
 	switch (how) {
 	case SOCK_WAKE_WAITD:
-		if (test_bit(SOCKWQ_ASYNC_WAITDATA, &sock->flags))
+		if (test_bit(SOCKWQ_ASYNC_WAITDATA, &wq->flags))
 			break;
 		goto call_kill;
 	case SOCK_WAKE_SPACE:
-		if (!test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sock->flags))
+		if (!test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &wq->flags))
 			break;
 		/* fall through */
 	case SOCK_WAKE_IO:
@@ -1086,7 +1079,7 @@ call_kill:
 	case SOCK_WAKE_URG:
 		kill_fasync(&wq->fasync_list, SIGURG, band);
 	}
-	rcu_read_unlock();
+
 	return 0;
 }
 EXPORT_SYMBOL(sock_wake_async);
-- 
cgit v1.2.3


From 64031e3e8a5c042840c5123af695eec89f9e6a24 Mon Sep 17 00:00:00 2001
From: Hanjun Guo
Date: Wed, 2 Dec 2015 15:44:22 +0800
Subject: ACPI / property: fix compile error for
 acpi_node_get_property_reference() when CONFIG_ACPI=n

In commit 60ba032ed76e ("ACPI / property: Drop size_prop from
acpi_dev_get_property_reference()"), the argument "const char *cells_name"
was dropped, but forgot to update the stub function in no-ACPI case,
it will lead to compile error when CONFIG_ACPI=n, easliy remove
"const char *cells_name" to fix it.

Fixes: 60ba032ed76e "ACPI / property: Drop size_prop from acpi_dev_get_property_reference()"
Reported-by: Kejian Yan <yankejian@huawei.com>
Signed-off-by: Hanjun Guo <hanjun.guo@linaro.org>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/acpi.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 865d948c60e6..9e6f4bb4692f 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -782,8 +782,8 @@ static inline int acpi_dev_get_property(struct acpi_device *adev,
 }
 
 static inline int acpi_node_get_property_reference(struct fwnode_handle *fwnode,
-				const char *name, const char *cells_name,
-				size_t index, struct acpi_reference_args *args)
+				const char *name, size_t index,
+				struct acpi_reference_args *args)
 {
 	return -ENXIO;
 }
-- 
cgit v1.2.3


From 69030dd1c3671625c6f766af0b64a4bb4409ac3b Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada
Date: Tue, 1 Dec 2015 16:52:14 -0800
Subject: cpufreq: use last policy after online for drivers with ->setpolicy

For cpufreq drivers which use setpolicy interface, after offline->online
the policy is set to default. This can be reproduced by setting the
default policy of intel_pstate or longrun to ondemand and then change to
"performance". After offline and online, the setpolicy will be called with
the policy=ondemand.

For drivers using governors this condition is handled by storing
last_governor, during offline and restoring during online. The same should
be done for drivers using setpolicy interface. Storing last_policy during
offline and restoring during online.

Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/cpufreq.c | 14 ++++++++++----
 include/linux/cpufreq.h   |  1 +
 2 files changed, 11 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index a83c995a62df..8412ce5f93a7 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -976,10 +976,14 @@ static int cpufreq_init_policy(struct cpufreq_policy *policy)
 
 	new_policy.governor = gov;
 
-	/* Use the default policy if its valid. */
-	if (cpufreq_driver->setpolicy)
-		cpufreq_parse_governor(gov->name, &new_policy.policy, NULL);
-
+	/* Use the default policy if there is no last_policy. */
+	if (cpufreq_driver->setpolicy) {
+		if (policy->last_policy)
+			new_policy.policy = policy->last_policy;
+		else
+			cpufreq_parse_governor(gov->name, &new_policy.policy,
+					       NULL);
+	}
 	/* set default policy */
 	return cpufreq_set_policy(policy, &new_policy);
 }
@@ -1330,6 +1334,8 @@ static void cpufreq_offline_prepare(unsigned int cpu)
 		if (has_target())
 			strncpy(policy->last_governor, policy->governor->name,
 				CPUFREQ_NAME_LEN);
+		else
+			policy->last_policy = policy->policy;
 	} else if (cpu == policy->cpu) {
 		/* Nominate new CPU */
 		policy->cpu = cpumask_any(policy->cpus);
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index ef4c5b1a860f..177c7680c1a8 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -77,6 +77,7 @@ struct cpufreq_policy {
 	unsigned int		suspend_freq; /* freq to set during suspend */
 
 	unsigned int		policy; /* see above */
+	unsigned int		last_policy; /* policy before unplug */
 	struct cpufreq_governor	*governor; /* see below */
 	void			*governor_data;
 	bool			governor_enabled; /* governor start/stop flag */
-- 
cgit v1.2.3


From 45f6fad84cc305103b28d73482b344d7f5b76f39 Mon Sep 17 00:00:00 2001
From: Eric Dumazet
Date: Sun, 29 Nov 2015 19:37:57 -0800
Subject: ipv6: add complete rcu protection around np->opt

This patch addresses multiple problems :

UDP/RAW sendmsg() need to get a stable struct ipv6_txoptions
while socket is not locked : Other threads can change np->opt
concurrently. Dmitry posted a syzkaller
(http://github.com/google/syzkaller) program desmonstrating
use-after-free.

Starting with TCP/DCCP lockless listeners, tcp_v6_syn_recv_sock()
and dccp_v6_request_recv_sock() also need to use RCU protection
to dereference np->opt once (before calling ipv6_dup_options())

This patch adds full RCU protection to np->opt

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ipv6.h             |  2 +-
 include/net/ipv6.h               | 21 ++++++++++++++++++++-
 net/dccp/ipv6.c                  | 33 +++++++++++++++++++++------------
 net/ipv6/af_inet6.c              | 13 +++++++++----
 net/ipv6/datagram.c              |  4 +++-
 net/ipv6/exthdrs.c               |  3 ++-
 net/ipv6/inet6_connection_sock.c | 11 ++++++++---
 net/ipv6/ipv6_sockglue.c         | 33 ++++++++++++++++++++++-----------
 net/ipv6/raw.c                   |  8 ++++++--
 net/ipv6/syncookies.c            |  2 +-
 net/ipv6/tcp_ipv6.c              | 28 +++++++++++++++++-----------
 net/ipv6/udp.c                   |  8 ++++++--
 net/l2tp/l2tp_ip6.c              |  8 ++++++--
 13 files changed, 122 insertions(+), 52 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 0ef2a97ccdb5..402753bccafa 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -227,7 +227,7 @@ struct ipv6_pinfo {
 	struct ipv6_ac_socklist	*ipv6_ac_list;
 	struct ipv6_fl_socklist __rcu *ipv6_fl_list;
 
-	struct ipv6_txoptions	*opt;
+	struct ipv6_txoptions __rcu	*opt;
 	struct sk_buff		*pktoptions;
 	struct sk_buff		*rxpmtu;
 	struct inet6_cork	cork;
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index ea5a13ef85a6..9a5c9f013784 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -205,6 +205,7 @@ extern rwlock_t ip6_ra_lock;
  */
 
 struct ipv6_txoptions {
+	atomic_t		refcnt;
 	/* Length of this structure */
 	int			tot_len;
 
@@ -217,7 +218,7 @@ struct ipv6_txoptions {
 	struct ipv6_opt_hdr	*dst0opt;
 	struct ipv6_rt_hdr	*srcrt;	/* Routing Header */
 	struct ipv6_opt_hdr	*dst1opt;
-
+	struct rcu_head		rcu;
 	/* Option buffer, as read by IPV6_PKTOPTIONS, starts here. */
 };
 
@@ -252,6 +253,24 @@ struct ipv6_fl_socklist {
 	struct rcu_head			rcu;
 };
 
+static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np)
+{
+	struct ipv6_txoptions *opt;
+
+	rcu_read_lock();
+	opt = rcu_dereference(np->opt);
+	if (opt && !atomic_inc_not_zero(&opt->refcnt))
+		opt = NULL;
+	rcu_read_unlock();
+	return opt;
+}
+
+static inline void txopt_put(struct ipv6_txoptions *opt)
+{
+	if (opt && atomic_dec_and_test(&opt->refcnt))
+		kfree_rcu(opt, rcu);
+}
+
 struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label);
 struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space,
 					 struct ip6_flowlabel *fl,
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index db5fc2440a23..e7e0b9bc2a43 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -202,7 +202,9 @@ static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req
 	security_req_classify_flow(req, flowi6_to_flowi(&fl6));
 
 
-	final_p = fl6_update_dst(&fl6, np->opt, &final);
+	rcu_read_lock();
+	final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final);
+	rcu_read_unlock();
 
 	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
@@ -219,7 +221,10 @@ static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req
 							 &ireq->ir_v6_loc_addr,
 							 &ireq->ir_v6_rmt_addr);
 		fl6.daddr = ireq->ir_v6_rmt_addr;
-		err = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass);
+		rcu_read_lock();
+		err = ip6_xmit(sk, skb, &fl6, rcu_dereference(np->opt),
+			       np->tclass);
+		rcu_read_unlock();
 		err = net_xmit_eval(err);
 	}
 
@@ -387,6 +392,7 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk,
 	struct inet_request_sock *ireq = inet_rsk(req);
 	struct ipv6_pinfo *newnp;
 	const struct ipv6_pinfo *np = inet6_sk(sk);
+	struct ipv6_txoptions *opt;
 	struct inet_sock *newinet;
 	struct dccp6_sock *newdp6;
 	struct sock *newsk;
@@ -488,13 +494,15 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk,
 	 * Yes, keeping reference count would be much more clever, but we make
 	 * one more one thing there: reattach optmem to newsk.
 	 */
-	if (np->opt != NULL)
-		newnp->opt = ipv6_dup_options(newsk, np->opt);
-
+	opt = rcu_dereference(np->opt);
+	if (opt) {
+		opt = ipv6_dup_options(newsk, opt);
+		RCU_INIT_POINTER(newnp->opt, opt);
+	}
 	inet_csk(newsk)->icsk_ext_hdr_len = 0;
-	if (newnp->opt != NULL)
-		inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen +
-						     newnp->opt->opt_flen);
+	if (opt)
+		inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen +
+						    opt->opt_flen;
 
 	dccp_sync_mss(newsk, dst_mtu(dst));
 
@@ -757,6 +765,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct dccp_sock *dp = dccp_sk(sk);
 	struct in6_addr *saddr = NULL, *final_p, final;
+	struct ipv6_txoptions *opt;
 	struct flowi6 fl6;
 	struct dst_entry *dst;
 	int addr_type;
@@ -856,7 +865,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	fl6.fl6_sport = inet->inet_sport;
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-	final_p = fl6_update_dst(&fl6, np->opt, &final);
+	opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+	final_p = fl6_update_dst(&fl6, opt, &final);
 
 	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
@@ -876,9 +886,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	__ip6_dst_store(sk, dst, NULL, NULL);
 
 	icsk->icsk_ext_hdr_len = 0;
-	if (np->opt != NULL)
-		icsk->icsk_ext_hdr_len = (np->opt->opt_flen +
-					  np->opt->opt_nflen);
+	if (opt)
+		icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen;
 
 	inet->inet_dport = usin->sin6_port;
 
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 44bb66bde0e2..38d66ddfb937 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -428,9 +428,11 @@ void inet6_destroy_sock(struct sock *sk)
 
 	/* Free tx options */
 
-	opt = xchg(&np->opt, NULL);
-	if (opt)
-		sock_kfree_s(sk, opt, opt->tot_len);
+	opt = xchg((__force struct ipv6_txoptions **)&np->opt, NULL);
+	if (opt) {
+		atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+		txopt_put(opt);
+	}
 }
 EXPORT_SYMBOL_GPL(inet6_destroy_sock);
 
@@ -659,7 +661,10 @@ int inet6_sk_rebuild_header(struct sock *sk)
 		fl6.fl6_sport = inet->inet_sport;
 		security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-		final_p = fl6_update_dst(&fl6, np->opt, &final);
+		rcu_read_lock();
+		final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt),
+					 &final);
+		rcu_read_unlock();
 
 		dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 		if (IS_ERR(dst)) {
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index d70b0238f468..517c55b01ba8 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -167,8 +167,10 @@ ipv4_connected:
 
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-	opt = flowlabel ? flowlabel->opt : np->opt;
+	rcu_read_lock();
+	opt = flowlabel ? flowlabel->opt : rcu_dereference(np->opt);
 	final_p = fl6_update_dst(&fl6, opt, &final);
+	rcu_read_unlock();
 
 	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 	err = 0;
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index ce203b0402be..ea7c4d64a00a 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -727,6 +727,7 @@ ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt)
 			*((char **)&opt2->dst1opt) += dif;
 		if (opt2->srcrt)
 			*((char **)&opt2->srcrt) += dif;
+		atomic_set(&opt2->refcnt, 1);
 	}
 	return opt2;
 }
@@ -790,7 +791,7 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt,
 		return ERR_PTR(-ENOBUFS);
 
 	memset(opt2, 0, tot_len);
-
+	atomic_set(&opt2->refcnt, 1);
 	opt2->tot_len = tot_len;
 	p = (char *)(opt2 + 1);
 
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 5d1c7cee2cb2..3ff5208772bb 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -78,7 +78,9 @@ struct dst_entry *inet6_csk_route_req(const struct sock *sk,
 	memset(fl6, 0, sizeof(*fl6));
 	fl6->flowi6_proto = proto;
 	fl6->daddr = ireq->ir_v6_rmt_addr;
-	final_p = fl6_update_dst(fl6, np->opt, &final);
+	rcu_read_lock();
+	final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
+	rcu_read_unlock();
 	fl6->saddr = ireq->ir_v6_loc_addr;
 	fl6->flowi6_oif = ireq->ir_iif;
 	fl6->flowi6_mark = ireq->ir_mark;
@@ -142,7 +144,9 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk,
 	fl6->fl6_dport = inet->inet_dport;
 	security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
 
-	final_p = fl6_update_dst(fl6, np->opt, &final);
+	rcu_read_lock();
+	final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
+	rcu_read_unlock();
 
 	dst = __inet6_csk_dst_check(sk, np->dst_cookie);
 	if (!dst) {
@@ -175,7 +179,8 @@ int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl_unused
 	/* Restore final destination back after routing done */
 	fl6.daddr = sk->sk_v6_daddr;
 
-	res = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass);
+	res = ip6_xmit(sk, skb, &fl6, rcu_dereference(np->opt),
+		       np->tclass);
 	rcu_read_unlock();
 	return res;
 }
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 63e6956917c9..4449ad1f8114 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -111,7 +111,8 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk,
 			icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie);
 		}
 	}
-	opt = xchg(&inet6_sk(sk)->opt, opt);
+	opt = xchg((__force struct ipv6_txoptions **)&inet6_sk(sk)->opt,
+		   opt);
 	sk_dst_reset(sk);
 
 	return opt;
@@ -231,9 +232,12 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 				sk->sk_socket->ops = &inet_dgram_ops;
 				sk->sk_family = PF_INET;
 			}
-			opt = xchg(&np->opt, NULL);
-			if (opt)
-				sock_kfree_s(sk, opt, opt->tot_len);
+			opt = xchg((__force struct ipv6_txoptions **)&np->opt,
+				   NULL);
+			if (opt) {
+				atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+				txopt_put(opt);
+			}
 			pktopt = xchg(&np->pktoptions, NULL);
 			kfree_skb(pktopt);
 
@@ -403,7 +407,8 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW))
 			break;
 
-		opt = ipv6_renew_options(sk, np->opt, optname,
+		opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+		opt = ipv6_renew_options(sk, opt, optname,
 					 (struct ipv6_opt_hdr __user *)optval,
 					 optlen);
 		if (IS_ERR(opt)) {
@@ -432,8 +437,10 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		retv = 0;
 		opt = ipv6_update_options(sk, opt);
 sticky_done:
-		if (opt)
-			sock_kfree_s(sk, opt, opt->tot_len);
+		if (opt) {
+			atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+			txopt_put(opt);
+		}
 		break;
 	}
 
@@ -486,6 +493,7 @@ sticky_done:
 			break;
 
 		memset(opt, 0, sizeof(*opt));
+		atomic_set(&opt->refcnt, 1);
 		opt->tot_len = sizeof(*opt) + optlen;
 		retv = -EFAULT;
 		if (copy_from_user(opt+1, optval, optlen))
@@ -502,8 +510,10 @@ update:
 		retv = 0;
 		opt = ipv6_update_options(sk, opt);
 done:
-		if (opt)
-			sock_kfree_s(sk, opt, opt->tot_len);
+		if (opt) {
+			atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+			txopt_put(opt);
+		}
 		break;
 	}
 	case IPV6_UNICAST_HOPS:
@@ -1110,10 +1120,11 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 	case IPV6_RTHDR:
 	case IPV6_DSTOPTS:
 	{
+		struct ipv6_txoptions *opt;
 
 		lock_sock(sk);
-		len = ipv6_getsockopt_sticky(sk, np->opt,
-					     optname, optval, len);
+		opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+		len = ipv6_getsockopt_sticky(sk, opt, optname, optval, len);
 		release_sock(sk);
 		/* check if ipv6_getsockopt_sticky() returns err code */
 		if (len < 0)
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index dc65ec198f7c..99140986e887 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -733,6 +733,7 @@ static int raw6_getfrag(void *from, char *to, int offset, int len, int odd,
 
 static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 {
+	struct ipv6_txoptions *opt_to_free = NULL;
 	struct ipv6_txoptions opt_space;
 	DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
 	struct in6_addr *daddr, *final_p, final;
@@ -839,8 +840,10 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		if (!(opt->opt_nflen|opt->opt_flen))
 			opt = NULL;
 	}
-	if (!opt)
-		opt = np->opt;
+	if (!opt) {
+		opt = txopt_get(np);
+		opt_to_free = opt;
+		}
 	if (flowlabel)
 		opt = fl6_merge_options(&opt_space, flowlabel, opt);
 	opt = ipv6_fixup_options(&opt_space, opt);
@@ -906,6 +909,7 @@ done:
 	dst_release(dst);
 out:
 	fl6_sock_release(flowlabel);
+	txopt_put(opt_to_free);
 	return err < 0 ? err : len;
 do_confirm:
 	dst_confirm(dst);
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index bb8f2fa1c7fb..eaf7ac496d50 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -222,7 +222,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 		memset(&fl6, 0, sizeof(fl6));
 		fl6.flowi6_proto = IPPROTO_TCP;
 		fl6.daddr = ireq->ir_v6_rmt_addr;
-		final_p = fl6_update_dst(&fl6, np->opt, &final);
+		final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final);
 		fl6.saddr = ireq->ir_v6_loc_addr;
 		fl6.flowi6_oif = sk->sk_bound_dev_if;
 		fl6.flowi6_mark = ireq->ir_mark;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index c5429a636f1a..6a50bb4a0dae 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -120,6 +120,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct in6_addr *saddr = NULL, *final_p, final;
+	struct ipv6_txoptions *opt;
 	struct flowi6 fl6;
 	struct dst_entry *dst;
 	int addr_type;
@@ -235,7 +236,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	fl6.fl6_dport = usin->sin6_port;
 	fl6.fl6_sport = inet->inet_sport;
 
-	final_p = fl6_update_dst(&fl6, np->opt, &final);
+	opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+	final_p = fl6_update_dst(&fl6, opt, &final);
 
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
@@ -263,9 +265,9 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 		tcp_fetch_timewait_stamp(sk, dst);
 
 	icsk->icsk_ext_hdr_len = 0;
-	if (np->opt)
-		icsk->icsk_ext_hdr_len = (np->opt->opt_flen +
-					  np->opt->opt_nflen);
+	if (opt)
+		icsk->icsk_ext_hdr_len = opt->opt_flen +
+					 opt->opt_nflen;
 
 	tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
 
@@ -461,7 +463,8 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
 		if (np->repflow && ireq->pktopts)
 			fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
 
-		err = ip6_xmit(sk, skb, fl6, np->opt, np->tclass);
+		err = ip6_xmit(sk, skb, fl6, rcu_dereference(np->opt),
+			       np->tclass);
 		err = net_xmit_eval(err);
 	}
 
@@ -972,6 +975,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 	struct inet_request_sock *ireq;
 	struct ipv6_pinfo *newnp;
 	const struct ipv6_pinfo *np = inet6_sk(sk);
+	struct ipv6_txoptions *opt;
 	struct tcp6_sock *newtcp6sk;
 	struct inet_sock *newinet;
 	struct tcp_sock *newtp;
@@ -1098,13 +1102,15 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 	   but we make one more one thing there: reattach optmem
 	   to newsk.
 	 */
-	if (np->opt)
-		newnp->opt = ipv6_dup_options(newsk, np->opt);
-
+	opt = rcu_dereference(np->opt);
+	if (opt) {
+		opt = ipv6_dup_options(newsk, opt);
+		RCU_INIT_POINTER(newnp->opt, opt);
+	}
 	inet_csk(newsk)->icsk_ext_hdr_len = 0;
-	if (newnp->opt)
-		inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen +
-						     newnp->opt->opt_flen);
+	if (opt)
+		inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen +
+						    opt->opt_flen;
 
 	tcp_ca_openreq_child(newsk, dst);
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 01bcb49619ee..9da3287a3923 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1110,6 +1110,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
 	struct in6_addr *daddr, *final_p, final;
 	struct ipv6_txoptions *opt = NULL;
+	struct ipv6_txoptions *opt_to_free = NULL;
 	struct ip6_flowlabel *flowlabel = NULL;
 	struct flowi6 fl6;
 	struct dst_entry *dst;
@@ -1263,8 +1264,10 @@ do_udp_sendmsg:
 			opt = NULL;
 		connected = 0;
 	}
-	if (!opt)
-		opt = np->opt;
+	if (!opt) {
+		opt = txopt_get(np);
+		opt_to_free = opt;
+	}
 	if (flowlabel)
 		opt = fl6_merge_options(&opt_space, flowlabel, opt);
 	opt = ipv6_fixup_options(&opt_space, opt);
@@ -1373,6 +1376,7 @@ release_dst:
 out:
 	dst_release(dst);
 	fl6_sock_release(flowlabel);
+	txopt_put(opt_to_free);
 	if (!err)
 		return len;
 	/*
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index aca38d8aed8e..a2c8747d2936 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -486,6 +486,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	DECLARE_SOCKADDR(struct sockaddr_l2tpip6 *, lsa, msg->msg_name);
 	struct in6_addr *daddr, *final_p, final;
 	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct ipv6_txoptions *opt_to_free = NULL;
 	struct ipv6_txoptions *opt = NULL;
 	struct ip6_flowlabel *flowlabel = NULL;
 	struct dst_entry *dst = NULL;
@@ -575,8 +576,10 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 			opt = NULL;
 	}
 
-	if (opt == NULL)
-		opt = np->opt;
+	if (!opt) {
+		opt = txopt_get(np);
+		opt_to_free = opt;
+	}
 	if (flowlabel)
 		opt = fl6_merge_options(&opt_space, flowlabel, opt);
 	opt = ipv6_fixup_options(&opt_space, opt);
@@ -631,6 +634,7 @@ done:
 	dst_release(dst);
 out:
 	fl6_sock_release(flowlabel);
+	txopt_put(opt_to_free);
 
 	return err < 0 ? err : len;
 
-- 
cgit v1.2.3


From 1f7dd3e5a6e4f093017fff12232572ee1aa4639b Mon Sep 17 00:00:00 2001
From: Tejun Heo
Date: Thu, 3 Dec 2015 10:18:21 -0500
Subject: cgroup: fix handling of multi-destination migration from
 subtree_control enabling

Consider the following v2 hierarchy.

  P0 (+memory) --- P1 (-memory) --- A
                                 \- B
       
P0 has memory enabled in its subtree_control while P1 doesn't.  If
both A and B contain processes, they would belong to the memory css of
P1.  Now if memory is enabled on P1's subtree_control, memory csses
should be created on both A and B and A's processes should be moved to
the former and B's processes the latter.  IOW, enabling controllers
can cause atomic migrations into different csses.

The core cgroup migration logic has been updated accordingly but the
controller migration methods haven't and still assume that all tasks
migrate to a single target css; furthermore, the methods were fed the
css in which subtree_control was updated which is the parent of the
target csses.  pids controller depends on the migration methods to
move charges and this made the controller attribute charges to the
wrong csses often triggering the following warning by driving a
counter negative.

 WARNING: CPU: 1 PID: 1 at kernel/cgroup_pids.c:97 pids_cancel.constprop.6+0x31/0x40()
 Modules linked in:
 CPU: 1 PID: 1 Comm: systemd Not tainted 4.4.0-rc1+ #29
 ...
  ffffffff81f65382 ffff88007c043b90 ffffffff81551ffc 0000000000000000
  ffff88007c043bc8 ffffffff810de202 ffff88007a752000 ffff88007a29ab00
  ffff88007c043c80 ffff88007a1d8400 0000000000000001 ffff88007c043bd8
 Call Trace:
  [<ffffffff81551ffc>] dump_stack+0x4e/0x82
  [<ffffffff810de202>] warn_slowpath_common+0x82/0xc0
  [<ffffffff810de2fa>] warn_slowpath_null+0x1a/0x20
  [<ffffffff8118e031>] pids_cancel.constprop.6+0x31/0x40
  [<ffffffff8118e0fd>] pids_can_attach+0x6d/0xf0
  [<ffffffff81188a4c>] cgroup_taskset_migrate+0x6c/0x330
  [<ffffffff81188e05>] cgroup_migrate+0xf5/0x190
  [<ffffffff81189016>] cgroup_attach_task+0x176/0x200
  [<ffffffff8118949d>] __cgroup_procs_write+0x2ad/0x460
  [<ffffffff81189684>] cgroup_procs_write+0x14/0x20
  [<ffffffff811854e5>] cgroup_file_write+0x35/0x1c0
  [<ffffffff812e26f1>] kernfs_fop_write+0x141/0x190
  [<ffffffff81265f88>] __vfs_write+0x28/0xe0
  [<ffffffff812666fc>] vfs_write+0xac/0x1a0
  [<ffffffff81267019>] SyS_write+0x49/0xb0
  [<ffffffff81bcef32>] entry_SYSCALL_64_fastpath+0x12/0x76

This patch fixes the bug by removing @css parameter from the three
migration methods, ->can_attach, ->cancel_attach() and ->attach() and
updating cgroup_taskset iteration helpers also return the destination
css in addition to the task being migrated.  All controllers are
updated accordingly.

* Controllers which don't care whether there are one or multiple
  target csses can be converted trivially.  cpu, io, freezer, perf,
  netclassid and netprio fall in this category.

* cpuset's current implementation assumes that there's single source
  and destination and thus doesn't support v2 hierarchy already.  The
  only change made by this patchset is how that single destination css
  is obtained.

* memory migration path already doesn't do anything on v2.  How the
  single destination css is obtained is updated and the prep stage of
  mem_cgroup_can_attach() is reordered to accomodate the change.

* pids is the only controller which was affected by this bug.  It now
  correctly handles multi-destination migrations and no longer causes
  counter underflow from incorrect accounting.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-and-tested-by: Daniel Wagner <daniel.wagner@bmw-carit.de>
Cc: Aleksa Sarai <cyphar@cyphar.com>
---
 block/blk-cgroup.c           |  6 +++---
 include/linux/cgroup-defs.h  |  9 +++------
 include/linux/cgroup.h       | 33 +++++++++++++++++++++-----------
 kernel/cgroup.c              | 43 +++++++++++++++++++++++++++++++++---------
 kernel/cgroup_freezer.c      |  6 +++---
 kernel/cgroup_pids.c         | 16 ++++++++--------
 kernel/cpuset.c              | 33 ++++++++++++++++++++------------
 kernel/events/core.c         |  6 +++---
 kernel/sched/core.c          | 12 ++++++------
 mm/memcontrol.c              | 45 ++++++++++++++++++++++----------------------
 net/core/netclassid_cgroup.c | 11 ++++++-----
 net/core/netprio_cgroup.c    |  9 +++++----
 12 files changed, 137 insertions(+), 92 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 5bcdfc10c23a..5a37188b559f 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1127,15 +1127,15 @@ void blkcg_exit_queue(struct request_queue *q)
  * of the main cic data structures.  For now we allow a task to change
  * its cgroup only if it's the only owner of its ioc.
  */
-static int blkcg_can_attach(struct cgroup_subsys_state *css,
-			    struct cgroup_taskset *tset)
+static int blkcg_can_attach(struct cgroup_taskset *tset)
 {
 	struct task_struct *task;
+	struct cgroup_subsys_state *dst_css;
 	struct io_context *ioc;
 	int ret = 0;
 
 	/* task_lock() is needed to avoid races with exit_io_context() */
-	cgroup_taskset_for_each(task, tset) {
+	cgroup_taskset_for_each(task, dst_css, tset) {
 		task_lock(task);
 		ioc = task->io_context;
 		if (ioc && atomic_read(&ioc->nr_tasks) > 1)
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 869fd4a3d28e..06b77f9dd3f2 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -422,12 +422,9 @@ struct cgroup_subsys {
 	void (*css_reset)(struct cgroup_subsys_state *css);
 	void (*css_e_css_changed)(struct cgroup_subsys_state *css);
 
-	int (*can_attach)(struct cgroup_subsys_state *css,
-			  struct cgroup_taskset *tset);
-	void (*cancel_attach)(struct cgroup_subsys_state *css,
-			      struct cgroup_taskset *tset);
-	void (*attach)(struct cgroup_subsys_state *css,
-		       struct cgroup_taskset *tset);
+	int (*can_attach)(struct cgroup_taskset *tset);
+	void (*cancel_attach)(struct cgroup_taskset *tset);
+	void (*attach)(struct cgroup_taskset *tset);
 	int (*can_fork)(struct task_struct *task, void **priv_p);
 	void (*cancel_fork)(struct task_struct *task, void *priv);
 	void (*fork)(struct task_struct *task, void *priv);
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index f64083030ad5..cb91b44f5f78 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -120,8 +120,10 @@ struct cgroup_subsys_state *css_rightmost_descendant(struct cgroup_subsys_state
 struct cgroup_subsys_state *css_next_descendant_post(struct cgroup_subsys_state *pos,
 						     struct cgroup_subsys_state *css);
 
-struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset);
-struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset);
+struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset,
+					 struct cgroup_subsys_state **dst_cssp);
+struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset,
+					struct cgroup_subsys_state **dst_cssp);
 
 void css_task_iter_start(struct cgroup_subsys_state *css,
 			 struct css_task_iter *it);
@@ -236,30 +238,39 @@ void css_task_iter_end(struct css_task_iter *it);
 /**
  * cgroup_taskset_for_each - iterate cgroup_taskset
  * @task: the loop cursor
+ * @dst_css: the destination css
  * @tset: taskset to iterate
  *
  * @tset may contain multiple tasks and they may belong to multiple
- * processes.  When there are multiple tasks in @tset, if a task of a
- * process is in @tset, all tasks of the process are in @tset.  Also, all
- * are guaranteed to share the same source and destination csses.
+ * processes.
+ *
+ * On the v2 hierarchy, there may be tasks from multiple processes and they
+ * may not share the source or destination csses.
+ *
+ * On traditional hierarchies, when there are multiple tasks in @tset, if a
+ * task of a process is in @tset, all tasks of the process are in @tset.
+ * Also, all are guaranteed to share the same source and destination csses.
  *
  * Iteration is not in any specific order.
  */
-#define cgroup_taskset_for_each(task, tset)				\
-	for ((task) = cgroup_taskset_first((tset)); (task);		\
-	     (task) = cgroup_taskset_next((tset)))
+#define cgroup_taskset_for_each(task, dst_css, tset)			\
+	for ((task) = cgroup_taskset_first((tset), &(dst_css));		\
+	     (task);							\
+	     (task) = cgroup_taskset_next((tset), &(dst_css)))
 
 /**
  * cgroup_taskset_for_each_leader - iterate group leaders in a cgroup_taskset
  * @leader: the loop cursor
+ * @dst_css: the destination css
  * @tset: takset to iterate
  *
  * Iterate threadgroup leaders of @tset.  For single-task migrations, @tset
  * may not contain any.
  */
-#define cgroup_taskset_for_each_leader(leader, tset)			\
-	for ((leader) = cgroup_taskset_first((tset)); (leader);		\
-	     (leader) = cgroup_taskset_next((tset)))			\
+#define cgroup_taskset_for_each_leader(leader, dst_css, tset)		\
+	for ((leader) = cgroup_taskset_first((tset), &(dst_css));	\
+	     (leader);							\
+	     (leader) = cgroup_taskset_next((tset), &(dst_css)))	\
 		if ((leader) != (leader)->group_leader)			\
 			;						\
 		else
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 5cea63fe4095..470f6536b9e8 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2237,6 +2237,9 @@ struct cgroup_taskset {
 	struct list_head	src_csets;
 	struct list_head	dst_csets;
 
+	/* the subsys currently being processed */
+	int			ssid;
+
 	/*
 	 * Fields for cgroup_taskset_*() iteration.
 	 *
@@ -2299,25 +2302,29 @@ static void cgroup_taskset_add(struct task_struct *task,
 /**
  * cgroup_taskset_first - reset taskset and return the first task
  * @tset: taskset of interest
+ * @dst_cssp: output variable for the destination css
  *
  * @tset iteration is initialized and the first task is returned.
  */
-struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset)
+struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset,
+					 struct cgroup_subsys_state **dst_cssp)
 {
 	tset->cur_cset = list_first_entry(tset->csets, struct css_set, mg_node);
 	tset->cur_task = NULL;
 
-	return cgroup_taskset_next(tset);
+	return cgroup_taskset_next(tset, dst_cssp);
 }
 
 /**
  * cgroup_taskset_next - iterate to the next task in taskset
  * @tset: taskset of interest
+ * @dst_cssp: output variable for the destination css
  *
  * Return the next task in @tset.  Iteration must have been initialized
  * with cgroup_taskset_first().
  */
-struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset)
+struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset,
+					struct cgroup_subsys_state **dst_cssp)
 {
 	struct css_set *cset = tset->cur_cset;
 	struct task_struct *task = tset->cur_task;
@@ -2332,6 +2339,18 @@ struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset)
 		if (&task->cg_list != &cset->mg_tasks) {
 			tset->cur_cset = cset;
 			tset->cur_task = task;
+
+			/*
+			 * This function may be called both before and
+			 * after cgroup_taskset_migrate().  The two cases
+			 * can be distinguished by looking at whether @cset
+			 * has its ->mg_dst_cset set.
+			 */
+			if (cset->mg_dst_cset)
+				*dst_cssp = cset->mg_dst_cset->subsys[tset->ssid];
+			else
+				*dst_cssp = cset->subsys[tset->ssid];
+
 			return task;
 		}
 
@@ -2367,7 +2386,8 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset,
 	/* check that we can legitimately attach to the cgroup */
 	for_each_e_css(css, i, dst_cgrp) {
 		if (css->ss->can_attach) {
-			ret = css->ss->can_attach(css, tset);
+			tset->ssid = i;
+			ret = css->ss->can_attach(tset);
 			if (ret) {
 				failed_css = css;
 				goto out_cancel_attach;
@@ -2400,9 +2420,12 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset,
 	 */
 	tset->csets = &tset->dst_csets;
 
-	for_each_e_css(css, i, dst_cgrp)
-		if (css->ss->attach)
-			css->ss->attach(css, tset);
+	for_each_e_css(css, i, dst_cgrp) {
+		if (css->ss->attach) {
+			tset->ssid = i;
+			css->ss->attach(tset);
+		}
+	}
 
 	ret = 0;
 	goto out_release_tset;
@@ -2411,8 +2434,10 @@ out_cancel_attach:
 	for_each_e_css(css, i, dst_cgrp) {
 		if (css == failed_css)
 			break;
-		if (css->ss->cancel_attach)
-			css->ss->cancel_attach(css, tset);
+		if (css->ss->cancel_attach) {
+			tset->ssid = i;
+			css->ss->cancel_attach(tset);
+		}
 	}
 out_release_tset:
 	spin_lock_bh(&css_set_lock);
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index ff02a8e51bb3..2d3df82c54f2 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -155,10 +155,10 @@ static void freezer_css_free(struct cgroup_subsys_state *css)
  * @freezer->lock.  freezer_attach() makes the new tasks conform to the
  * current state and all following state changes can see the new tasks.
  */
-static void freezer_attach(struct cgroup_subsys_state *new_css,
-			   struct cgroup_taskset *tset)
+static void freezer_attach(struct cgroup_taskset *tset)
 {
 	struct task_struct *task;
+	struct cgroup_subsys_state *new_css;
 
 	mutex_lock(&freezer_mutex);
 
@@ -172,7 +172,7 @@ static void freezer_attach(struct cgroup_subsys_state *new_css,
 	 * current state before executing the following - !frozen tasks may
 	 * be visible in a FROZEN cgroup and frozen tasks in a THAWED one.
 	 */
-	cgroup_taskset_for_each(task, tset) {
+	cgroup_taskset_for_each(task, new_css, tset) {
 		struct freezer *freezer = css_freezer(new_css);
 
 		if (!(freezer->state & CGROUP_FREEZING)) {
diff --git a/kernel/cgroup_pids.c b/kernel/cgroup_pids.c
index de3359a48dbb..8e27fc5dbb20 100644
--- a/kernel/cgroup_pids.c
+++ b/kernel/cgroup_pids.c
@@ -162,13 +162,13 @@ revert:
 	return -EAGAIN;
 }
 
-static int pids_can_attach(struct cgroup_subsys_state *css,
-			   struct cgroup_taskset *tset)
+static int pids_can_attach(struct cgroup_taskset *tset)
 {
-	struct pids_cgroup *pids = css_pids(css);
 	struct task_struct *task;
+	struct cgroup_subsys_state *dst_css;
 
-	cgroup_taskset_for_each(task, tset) {
+	cgroup_taskset_for_each(task, dst_css, tset) {
+		struct pids_cgroup *pids = css_pids(dst_css);
 		struct cgroup_subsys_state *old_css;
 		struct pids_cgroup *old_pids;
 
@@ -187,13 +187,13 @@ static int pids_can_attach(struct cgroup_subsys_state *css,
 	return 0;
 }
 
-static void pids_cancel_attach(struct cgroup_subsys_state *css,
-			       struct cgroup_taskset *tset)
+static void pids_cancel_attach(struct cgroup_taskset *tset)
 {
-	struct pids_cgroup *pids = css_pids(css);
 	struct task_struct *task;
+	struct cgroup_subsys_state *dst_css;
 
-	cgroup_taskset_for_each(task, tset) {
+	cgroup_taskset_for_each(task, dst_css, tset) {
+		struct pids_cgroup *pids = css_pids(dst_css);
 		struct cgroup_subsys_state *old_css;
 		struct pids_cgroup *old_pids;
 
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 10ae73611d80..02a8ea5c9963 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1429,15 +1429,16 @@ static int fmeter_getrate(struct fmeter *fmp)
 static struct cpuset *cpuset_attach_old_cs;
 
 /* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */
-static int cpuset_can_attach(struct cgroup_subsys_state *css,
-			     struct cgroup_taskset *tset)
+static int cpuset_can_attach(struct cgroup_taskset *tset)
 {
-	struct cpuset *cs = css_cs(css);
+	struct cgroup_subsys_state *css;
+	struct cpuset *cs;
 	struct task_struct *task;
 	int ret;
 
 	/* used later by cpuset_attach() */
-	cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset));
+	cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css));
+	cs = css_cs(css);
 
 	mutex_lock(&cpuset_mutex);
 
@@ -1447,7 +1448,7 @@ static int cpuset_can_attach(struct cgroup_subsys_state *css,
 	    (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)))
 		goto out_unlock;
 
-	cgroup_taskset_for_each(task, tset) {
+	cgroup_taskset_for_each(task, css, tset) {
 		ret = task_can_attach(task, cs->cpus_allowed);
 		if (ret)
 			goto out_unlock;
@@ -1467,9 +1468,14 @@ out_unlock:
 	return ret;
 }
 
-static void cpuset_cancel_attach(struct cgroup_subsys_state *css,
-				 struct cgroup_taskset *tset)
+static void cpuset_cancel_attach(struct cgroup_taskset *tset)
 {
+	struct cgroup_subsys_state *css;
+	struct cpuset *cs;
+
+	cgroup_taskset_first(tset, &css);
+	cs = css_cs(css);
+
 	mutex_lock(&cpuset_mutex);
 	css_cs(css)->attach_in_progress--;
 	mutex_unlock(&cpuset_mutex);
@@ -1482,16 +1488,19 @@ static void cpuset_cancel_attach(struct cgroup_subsys_state *css,
  */
 static cpumask_var_t cpus_attach;
 
-static void cpuset_attach(struct cgroup_subsys_state *css,
-			  struct cgroup_taskset *tset)
+static void cpuset_attach(struct cgroup_taskset *tset)
 {
 	/* static buf protected by cpuset_mutex */
 	static nodemask_t cpuset_attach_nodemask_to;
 	struct task_struct *task;
 	struct task_struct *leader;
-	struct cpuset *cs = css_cs(css);
+	struct cgroup_subsys_state *css;
+	struct cpuset *cs;
 	struct cpuset *oldcs = cpuset_attach_old_cs;
 
+	cgroup_taskset_first(tset, &css);
+	cs = css_cs(css);
+
 	mutex_lock(&cpuset_mutex);
 
 	/* prepare for attach */
@@ -1502,7 +1511,7 @@ static void cpuset_attach(struct cgroup_subsys_state *css,
 
 	guarantee_online_mems(cs, &cpuset_attach_nodemask_to);
 
-	cgroup_taskset_for_each(task, tset) {
+	cgroup_taskset_for_each(task, css, tset) {
 		/*
 		 * can_attach beforehand should guarantee that this doesn't
 		 * fail.  TODO: have a better way to handle failure here
@@ -1518,7 +1527,7 @@ static void cpuset_attach(struct cgroup_subsys_state *css,
 	 * sleep and should be moved outside migration path proper.
 	 */
 	cpuset_attach_nodemask_to = cs->effective_mems;
-	cgroup_taskset_for_each_leader(leader, tset) {
+	cgroup_taskset_for_each_leader(leader, css, tset) {
 		struct mm_struct *mm = get_task_mm(leader);
 
 		if (mm) {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 36babfd20648..026305dfe523 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -9456,12 +9456,12 @@ static int __perf_cgroup_move(void *info)
 	return 0;
 }
 
-static void perf_cgroup_attach(struct cgroup_subsys_state *css,
-			       struct cgroup_taskset *tset)
+static void perf_cgroup_attach(struct cgroup_taskset *tset)
 {
 	struct task_struct *task;
+	struct cgroup_subsys_state *css;
 
-	cgroup_taskset_for_each(task, tset)
+	cgroup_taskset_for_each(task, css, tset)
 		task_function_call(task, __perf_cgroup_move, task);
 }
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 4d568ac9319e..a9db4819e586 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8217,12 +8217,12 @@ static void cpu_cgroup_fork(struct task_struct *task, void *private)
 	sched_move_task(task);
 }
 
-static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css,
-				 struct cgroup_taskset *tset)
+static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
 {
 	struct task_struct *task;
+	struct cgroup_subsys_state *css;
 
-	cgroup_taskset_for_each(task, tset) {
+	cgroup_taskset_for_each(task, css, tset) {
 #ifdef CONFIG_RT_GROUP_SCHED
 		if (!sched_rt_can_attach(css_tg(css), task))
 			return -EINVAL;
@@ -8235,12 +8235,12 @@ static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css,
 	return 0;
 }
 
-static void cpu_cgroup_attach(struct cgroup_subsys_state *css,
-			      struct cgroup_taskset *tset)
+static void cpu_cgroup_attach(struct cgroup_taskset *tset)
 {
 	struct task_struct *task;
+	struct cgroup_subsys_state *css;
 
-	cgroup_taskset_for_each(task, tset)
+	cgroup_taskset_for_each(task, css, tset)
 		sched_move_task(task);
 }
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 9acfb165eb52..c92a65b2b4ab 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4779,23 +4779,18 @@ static void mem_cgroup_clear_mc(void)
 	spin_unlock(&mc.lock);
 }
 
-static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
-				 struct cgroup_taskset *tset)
+static int mem_cgroup_can_attach(struct cgroup_taskset *tset)
 {
-	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+	struct cgroup_subsys_state *css;
+	struct mem_cgroup *memcg;
 	struct mem_cgroup *from;
 	struct task_struct *leader, *p;
 	struct mm_struct *mm;
 	unsigned long move_flags;
 	int ret = 0;
 
-	/*
-	 * We are now commited to this value whatever it is. Changes in this
-	 * tunable will only affect upcoming migrations, not the current one.
-	 * So we need to save it, and keep it going.
-	 */
-	move_flags = READ_ONCE(memcg->move_charge_at_immigrate);
-	if (!move_flags)
+	/* charge immigration isn't supported on the default hierarchy */
+	if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
 		return 0;
 
 	/*
@@ -4805,13 +4800,23 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
 	 * multiple.
 	 */
 	p = NULL;
-	cgroup_taskset_for_each_leader(leader, tset) {
+	cgroup_taskset_for_each_leader(leader, css, tset) {
 		WARN_ON_ONCE(p);
 		p = leader;
+		memcg = mem_cgroup_from_css(css);
 	}
 	if (!p)
 		return 0;
 
+	/*
+	 * We are now commited to this value whatever it is. Changes in this
+	 * tunable will only affect upcoming migrations, not the current one.
+	 * So we need to save it, and keep it going.
+	 */
+	move_flags = READ_ONCE(memcg->move_charge_at_immigrate);
+	if (!move_flags)
+		return 0;
+
 	from = mem_cgroup_from_task(p);
 
 	VM_BUG_ON(from == memcg);
@@ -4842,8 +4847,7 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
 	return ret;
 }
 
-static void mem_cgroup_cancel_attach(struct cgroup_subsys_state *css,
-				     struct cgroup_taskset *tset)
+static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset)
 {
 	if (mc.to)
 		mem_cgroup_clear_mc();
@@ -4985,10 +4989,10 @@ retry:
 	atomic_dec(&mc.from->moving_account);
 }
 
-static void mem_cgroup_move_task(struct cgroup_subsys_state *css,
-				 struct cgroup_taskset *tset)
+static void mem_cgroup_move_task(struct cgroup_taskset *tset)
 {
-	struct task_struct *p = cgroup_taskset_first(tset);
+	struct cgroup_subsys_state *css;
+	struct task_struct *p = cgroup_taskset_first(tset, &css);
 	struct mm_struct *mm = get_task_mm(p);
 
 	if (mm) {
@@ -5000,17 +5004,14 @@ static void mem_cgroup_move_task(struct cgroup_subsys_state *css,
 		mem_cgroup_clear_mc();
 }
 #else	/* !CONFIG_MMU */
-static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
-				 struct cgroup_taskset *tset)
+static int mem_cgroup_can_attach(struct cgroup_taskset *tset)
 {
 	return 0;
 }
-static void mem_cgroup_cancel_attach(struct cgroup_subsys_state *css,
-				     struct cgroup_taskset *tset)
+static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset)
 {
 }
-static void mem_cgroup_move_task(struct cgroup_subsys_state *css,
-				 struct cgroup_taskset *tset)
+static void mem_cgroup_move_task(struct cgroup_taskset *tset)
 {
 }
 #endif
diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c
index 6441f47b1a8f..81cb3c72efe8 100644
--- a/net/core/netclassid_cgroup.c
+++ b/net/core/netclassid_cgroup.c
@@ -67,14 +67,15 @@ static int update_classid(const void *v, struct file *file, unsigned n)
 	return 0;
 }
 
-static void cgrp_attach(struct cgroup_subsys_state *css,
-			struct cgroup_taskset *tset)
+static void cgrp_attach(struct cgroup_taskset *tset)
 {
-	struct cgroup_cls_state *cs = css_cls_state(css);
-	void *v = (void *)(unsigned long)cs->classid;
 	struct task_struct *p;
+	struct cgroup_subsys_state *css;
+
+	cgroup_taskset_for_each(p, css, tset) {
+		struct cgroup_cls_state *cs = css_cls_state(css);
+		void *v = (void *)(unsigned long)cs->classid;
 
-	cgroup_taskset_for_each(p, tset) {
 		task_lock(p);
 		iterate_fd(p->files, 0, update_classid, v);
 		task_unlock(p);
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index cbd0a199bf52..40fd09fe06ae 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -218,13 +218,14 @@ static int update_netprio(const void *v, struct file *file, unsigned n)
 	return 0;
 }
 
-static void net_prio_attach(struct cgroup_subsys_state *css,
-			    struct cgroup_taskset *tset)
+static void net_prio_attach(struct cgroup_taskset *tset)
 {
 	struct task_struct *p;
-	void *v = (void *)(unsigned long)css->cgroup->id;
+	struct cgroup_subsys_state *css;
+
+	cgroup_taskset_for_each(p, css, tset) {
+		void *v = (void *)(unsigned long)css->cgroup->id;
 
-	cgroup_taskset_for_each(p, tset) {
 		task_lock(p);
 		iterate_fd(p->files, 0, update_netprio, v);
 		task_unlock(p);
-- 
cgit v1.2.3


From ae5515d66362b9d96cdcfce504567f0b8b7bd83e Mon Sep 17 00:00:00 2001
From: Alex Williamson
Date: Fri, 4 Dec 2015 08:38:42 -0700
Subject: Revert: "vfio: Include No-IOMMU mode"

Revert commit 033291eccbdb ("vfio: Include No-IOMMU mode") due to lack
of a user.  This was originally intended to fill a need for the DPDK
driver, but uptake has been slow so rather than support an unproven
kernel interface revert it and revisit when userspace catches up.

Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/Kconfig        |  15 ----
 drivers/vfio/pci/vfio_pci.c |   8 +-
 drivers/vfio/vfio.c         | 186 ++------------------------------------------
 include/linux/vfio.h        |   3 -
 include/uapi/linux/vfio.h   |   7 --
 5 files changed, 10 insertions(+), 209 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig
index da6e2ce77495..850d86ca685b 100644
--- a/drivers/vfio/Kconfig
+++ b/drivers/vfio/Kconfig
@@ -31,21 +31,6 @@ menuconfig VFIO
 
 	  If you don't know what to do here, say N.
 
-menuconfig VFIO_NOIOMMU
-	bool "VFIO No-IOMMU support"
-	depends on VFIO
-	help
-	  VFIO is built on the ability to isolate devices using the IOMMU.
-	  Only with an IOMMU can userspace access to DMA capable devices be
-	  considered secure.  VFIO No-IOMMU mode enables IOMMU groups for
-	  devices without IOMMU backing for the purpose of re-using the VFIO
-	  infrastructure in a non-secure mode.  Use of this mode will result
-	  in an unsupportable kernel and will therefore taint the kernel.
-	  Device assignment to virtual machines is also not possible with
-	  this mode since there is no IOMMU to provide DMA translation.
-
-	  If you don't know what to do here, say N.
-
 source "drivers/vfio/pci/Kconfig"
 source "drivers/vfio/platform/Kconfig"
 source "virt/lib/Kconfig"
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 2760a7ba3f30..56bf6dbb93db 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -940,13 +940,13 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (pdev->hdr_type != PCI_HEADER_TYPE_NORMAL)
 		return -EINVAL;
 
-	group = vfio_iommu_group_get(&pdev->dev);
+	group = iommu_group_get(&pdev->dev);
 	if (!group)
 		return -EINVAL;
 
 	vdev = kzalloc(sizeof(*vdev), GFP_KERNEL);
 	if (!vdev) {
-		vfio_iommu_group_put(group, &pdev->dev);
+		iommu_group_put(group);
 		return -ENOMEM;
 	}
 
@@ -957,7 +957,7 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	ret = vfio_add_group_dev(&pdev->dev, &vfio_pci_ops, vdev);
 	if (ret) {
-		vfio_iommu_group_put(group, &pdev->dev);
+		iommu_group_put(group);
 		kfree(vdev);
 		return ret;
 	}
@@ -993,7 +993,7 @@ static void vfio_pci_remove(struct pci_dev *pdev)
 	if (!vdev)
 		return;
 
-	vfio_iommu_group_put(pdev->dev.iommu_group, &pdev->dev);
+	iommu_group_put(pdev->dev.iommu_group);
 	kfree(vdev);
 
 	if (vfio_pci_is_vga(pdev)) {
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 9da0703e09d0..6070b793cbcb 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -62,7 +62,6 @@ struct vfio_container {
 	struct rw_semaphore		group_lock;
 	struct vfio_iommu_driver	*iommu_driver;
 	void				*iommu_data;
-	bool				noiommu;
 };
 
 struct vfio_unbound_dev {
@@ -85,7 +84,6 @@ struct vfio_group {
 	struct list_head		unbound_list;
 	struct mutex			unbound_lock;
 	atomic_t			opened;
-	bool				noiommu;
 };
 
 struct vfio_device {
@@ -97,147 +95,6 @@ struct vfio_device {
 	void				*device_data;
 };
 
-#ifdef CONFIG_VFIO_NOIOMMU
-static bool noiommu __read_mostly;
-module_param_named(enable_unsafe_noiommu_support,
-		   noiommu, bool, S_IRUGO | S_IWUSR);
-MODULE_PARM_DESC(enable_unsafe_noiommu_mode, "Enable UNSAFE, no-IOMMU mode.  This mode provides no device isolation, no DMA translation, no host kernel protection, cannot be used for device assignment to virtual machines, requires RAWIO permissions, and will taint the kernel.  If you do not know what this is for, step away. (default: false)");
-#endif
-
-/*
- * vfio_iommu_group_{get,put} are only intended for VFIO bus driver probe
- * and remove functions, any use cases other than acquiring the first
- * reference for the purpose of calling vfio_add_group_dev() or removing
- * that symmetric reference after vfio_del_group_dev() should use the raw
- * iommu_group_{get,put} functions.  In particular, vfio_iommu_group_put()
- * removes the device from the dummy group and cannot be nested.
- */
-struct iommu_group *vfio_iommu_group_get(struct device *dev)
-{
-	struct iommu_group *group;
-	int __maybe_unused ret;
-
-	group = iommu_group_get(dev);
-
-#ifdef CONFIG_VFIO_NOIOMMU
-	/*
-	 * With noiommu enabled, an IOMMU group will be created for a device
-	 * that doesn't already have one and doesn't have an iommu_ops on their
-	 * bus.  We use iommu_present() again in the main code to detect these
-	 * fake groups.
-	 */
-	if (group || !noiommu || iommu_present(dev->bus))
-		return group;
-
-	group = iommu_group_alloc();
-	if (IS_ERR(group))
-		return NULL;
-
-	iommu_group_set_name(group, "vfio-noiommu");
-	ret = iommu_group_add_device(group, dev);
-	iommu_group_put(group);
-	if (ret)
-		return NULL;
-
-	/*
-	 * Where to taint?  At this point we've added an IOMMU group for a
-	 * device that is not backed by iommu_ops, therefore any iommu_
-	 * callback using iommu_ops can legitimately Oops.  So, while we may
-	 * be about to give a DMA capable device to a user without IOMMU
-	 * protection, which is clearly taint-worthy, let's go ahead and do
-	 * it here.
-	 */
-	add_taint(TAINT_USER, LOCKDEP_STILL_OK);
-	dev_warn(dev, "Adding kernel taint for vfio-noiommu group on device\n");
-#endif
-
-	return group;
-}
-EXPORT_SYMBOL_GPL(vfio_iommu_group_get);
-
-void vfio_iommu_group_put(struct iommu_group *group, struct device *dev)
-{
-#ifdef CONFIG_VFIO_NOIOMMU
-	if (!iommu_present(dev->bus))
-		iommu_group_remove_device(dev);
-#endif
-
-	iommu_group_put(group);
-}
-EXPORT_SYMBOL_GPL(vfio_iommu_group_put);
-
-#ifdef CONFIG_VFIO_NOIOMMU
-static void *vfio_noiommu_open(unsigned long arg)
-{
-	if (arg != VFIO_NOIOMMU_IOMMU)
-		return ERR_PTR(-EINVAL);
-	if (!capable(CAP_SYS_RAWIO))
-		return ERR_PTR(-EPERM);
-
-	return NULL;
-}
-
-static void vfio_noiommu_release(void *iommu_data)
-{
-}
-
-static long vfio_noiommu_ioctl(void *iommu_data,
-			       unsigned int cmd, unsigned long arg)
-{
-	if (cmd == VFIO_CHECK_EXTENSION)
-		return arg == VFIO_NOIOMMU_IOMMU ? 1 : 0;
-
-	return -ENOTTY;
-}
-
-static int vfio_iommu_present(struct device *dev, void *unused)
-{
-	return iommu_present(dev->bus) ? 1 : 0;
-}
-
-static int vfio_noiommu_attach_group(void *iommu_data,
-				     struct iommu_group *iommu_group)
-{
-	return iommu_group_for_each_dev(iommu_group, NULL,
-					vfio_iommu_present) ? -EINVAL : 0;
-}
-
-static void vfio_noiommu_detach_group(void *iommu_data,
-				      struct iommu_group *iommu_group)
-{
-}
-
-static struct vfio_iommu_driver_ops vfio_noiommu_ops = {
-	.name = "vfio-noiommu",
-	.owner = THIS_MODULE,
-	.open = vfio_noiommu_open,
-	.release = vfio_noiommu_release,
-	.ioctl = vfio_noiommu_ioctl,
-	.attach_group = vfio_noiommu_attach_group,
-	.detach_group = vfio_noiommu_detach_group,
-};
-
-static struct vfio_iommu_driver vfio_noiommu_driver = {
-	.ops = &vfio_noiommu_ops,
-};
-
-/*
- * Wrap IOMMU drivers, the noiommu driver is the one and only driver for
- * noiommu groups (and thus containers) and not available for normal groups.
- */
-#define vfio_for_each_iommu_driver(con, pos)				\
-	for (pos = con->noiommu ? &vfio_noiommu_driver :		\
-	     list_first_entry(&vfio.iommu_drivers_list,			\
-			      struct vfio_iommu_driver, vfio_next);	\
-	     (con->noiommu ? pos != NULL :				\
-			&pos->vfio_next != &vfio.iommu_drivers_list);	\
-	      pos = con->noiommu ? NULL : list_next_entry(pos, vfio_next))
-#else
-#define vfio_for_each_iommu_driver(con, pos)				\
-	list_for_each_entry(pos, &vfio.iommu_drivers_list, vfio_next)
-#endif
-
-
 /**
  * IOMMU driver registration
  */
@@ -342,8 +199,7 @@ static void vfio_group_unlock_and_free(struct vfio_group *group)
 /**
  * Group objects - create, release, get, put, search
  */
-static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group,
-					    bool noiommu)
+static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group)
 {
 	struct vfio_group *group, *tmp;
 	struct device *dev;
@@ -361,7 +217,6 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group,
 	atomic_set(&group->container_users, 0);
 	atomic_set(&group->opened, 0);
 	group->iommu_group = iommu_group;
-	group->noiommu = noiommu;
 
 	group->nb.notifier_call = vfio_iommu_group_notifier;
 
@@ -397,8 +252,7 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group,
 
 	dev = device_create(vfio.class, NULL,
 			    MKDEV(MAJOR(vfio.group_devt), minor),
-			    group, "%s%d", noiommu ? "noiommu-" : "",
-			    iommu_group_id(iommu_group));
+			    group, "%d", iommu_group_id(iommu_group));
 	if (IS_ERR(dev)) {
 		vfio_free_group_minor(minor);
 		vfio_group_unlock_and_free(group);
@@ -786,8 +640,7 @@ int vfio_add_group_dev(struct device *dev,
 
 	group = vfio_group_get_from_iommu(iommu_group);
 	if (!group) {
-		group = vfio_create_group(iommu_group,
-					  !iommu_present(dev->bus));
+		group = vfio_create_group(iommu_group);
 		if (IS_ERR(group)) {
 			iommu_group_put(iommu_group);
 			return PTR_ERR(group);
@@ -999,7 +852,8 @@ static long vfio_ioctl_check_extension(struct vfio_container *container,
 		 */
 		if (!driver) {
 			mutex_lock(&vfio.iommu_drivers_lock);
-			vfio_for_each_iommu_driver(container, driver) {
+			list_for_each_entry(driver, &vfio.iommu_drivers_list,
+					    vfio_next) {
 				if (!try_module_get(driver->ops->owner))
 					continue;
 
@@ -1068,7 +922,7 @@ static long vfio_ioctl_set_iommu(struct vfio_container *container,
 	}
 
 	mutex_lock(&vfio.iommu_drivers_lock);
-	vfio_for_each_iommu_driver(container, driver) {
+	list_for_each_entry(driver, &vfio.iommu_drivers_list, vfio_next) {
 		void *data;
 
 		if (!try_module_get(driver->ops->owner))
@@ -1333,9 +1187,6 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd)
 	if (atomic_read(&group->container_users))
 		return -EINVAL;
 
-	if (group->noiommu && !capable(CAP_SYS_RAWIO))
-		return -EPERM;
-
 	f = fdget(container_fd);
 	if (!f.file)
 		return -EBADF;
@@ -1351,13 +1202,6 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd)
 
 	down_write(&container->group_lock);
 
-	/* Real groups and fake groups cannot mix */
-	if (!list_empty(&container->group_list) &&
-	    container->noiommu != group->noiommu) {
-		ret = -EPERM;
-		goto unlock_out;
-	}
-
 	driver = container->iommu_driver;
 	if (driver) {
 		ret = driver->ops->attach_group(container->iommu_data,
@@ -1367,7 +1211,6 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd)
 	}
 
 	group->container = container;
-	container->noiommu = group->noiommu;
 	list_add(&group->container_next, &container->group_list);
 
 	/* Get a reference on the container and mark a user within the group */
@@ -1398,9 +1241,6 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf)
 	    !group->container->iommu_driver || !vfio_group_viable(group))
 		return -EINVAL;
 
-	if (group->noiommu && !capable(CAP_SYS_RAWIO))
-		return -EPERM;
-
 	device = vfio_device_get_from_name(group, buf);
 	if (!device)
 		return -ENODEV;
@@ -1443,10 +1283,6 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf)
 
 	fd_install(ret, filep);
 
-	if (group->noiommu)
-		dev_warn(device->dev, "vfio-noiommu device opened by user "
-			 "(%s:%d)\n", current->comm, task_pid_nr(current));
-
 	return ret;
 }
 
@@ -1535,11 +1371,6 @@ static int vfio_group_fops_open(struct inode *inode, struct file *filep)
 	if (!group)
 		return -ENODEV;
 
-	if (group->noiommu && !capable(CAP_SYS_RAWIO)) {
-		vfio_group_put(group);
-		return -EPERM;
-	}
-
 	/* Do we need multiple instances of the group open?  Seems not. */
 	opened = atomic_cmpxchg(&group->opened, 0, 1);
 	if (opened) {
@@ -1702,11 +1533,6 @@ struct vfio_group *vfio_group_get_external_user(struct file *filep)
 	if (!atomic_inc_not_zero(&group->container_users))
 		return ERR_PTR(-EINVAL);
 
-	if (group->noiommu) {
-		atomic_dec(&group->container_users);
-		return ERR_PTR(-EPERM);
-	}
-
 	if (!group->container->iommu_driver ||
 			!vfio_group_viable(group)) {
 		atomic_dec(&group->container_users);
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index 610a86a892b8..ddb440975382 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -44,9 +44,6 @@ struct vfio_device_ops {
 	void	(*request)(void *device_data, unsigned int count);
 };
 
-extern struct iommu_group *vfio_iommu_group_get(struct device *dev);
-extern void vfio_iommu_group_put(struct iommu_group *group, struct device *dev);
-
 extern int vfio_add_group_dev(struct device *dev,
 			      const struct vfio_device_ops *ops,
 			      void *device_data);
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 751b69f858c8..9fd7b5d8df2f 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -38,13 +38,6 @@
 
 #define VFIO_SPAPR_TCE_v2_IOMMU		7
 
-/*
- * The No-IOMMU IOMMU offers no translation or isolation for devices and
- * supports no ioctls outside of VFIO_CHECK_EXTENSION.  Use of VFIO's No-IOMMU
- * code will taint the host kernel and should be used with extreme caution.
- */
-#define VFIO_NOIOMMU_IOMMU		8
-
 /*
  * The IOCTL interface is designed for extensibility by embedding the
  * structure length (argsz) and flags into structures passed between
-- 
cgit v1.2.3


From 3cf92222a39cc7842c373dd90a0c204fa7d7cced Mon Sep 17 00:00:00 2001
From: Herbert Xu
Date: Thu, 3 Dec 2015 20:41:29 +0800
Subject: rhashtable: Prevent spurious EBUSY errors on insertion

Thomas and Phil observed that under stress rhashtable insertion
sometimes failed with EBUSY, even though this error should only
ever been seen when we're under attack and our hash chain length
has grown to an unacceptable level, even after a rehash.

It turns out that the logic for detecting whether there is an
existing rehash is faulty.  In particular, when two threads both
try to grow the same table at the same time, one of them may see
the newly grown table and thus erroneously conclude that it had
been rehashed.  This is what leads to the EBUSY error.

This patch fixes this by remembering the current last table we
used during insertion so that rhashtable_insert_rehash can detect
when another thread has also done a resize/rehash.  When this is
detected we will give up our resize/rehash and simply retry the
insertion with the new table.

Reported-by: Thomas Graf <tgraf@suug.ch>
Reported-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Tested-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h | 18 +++++++++++-------
 lib/rhashtable.c           | 45 ++++++++++++++++++++++++++++++---------------
 2 files changed, 41 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 843ceca9a21e..e50b31d18462 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -19,6 +19,7 @@
 
 #include <linux/atomic.h>
 #include <linux/compiler.h>
+#include <linux/err.h>
 #include <linux/errno.h>
 #include <linux/jhash.h>
 #include <linux/list_nulls.h>
@@ -339,10 +340,11 @@ static inline int lockdep_rht_bucket_is_held(const struct bucket_table *tbl,
 int rhashtable_init(struct rhashtable *ht,
 		    const struct rhashtable_params *params);
 
-int rhashtable_insert_slow(struct rhashtable *ht, const void *key,
-			   struct rhash_head *obj,
-			   struct bucket_table *old_tbl);
-int rhashtable_insert_rehash(struct rhashtable *ht);
+struct bucket_table *rhashtable_insert_slow(struct rhashtable *ht,
+					    const void *key,
+					    struct rhash_head *obj,
+					    struct bucket_table *old_tbl);
+int rhashtable_insert_rehash(struct rhashtable *ht, struct bucket_table *tbl);
 
 int rhashtable_walk_init(struct rhashtable *ht, struct rhashtable_iter *iter);
 void rhashtable_walk_exit(struct rhashtable_iter *iter);
@@ -598,9 +600,11 @@ restart:
 
 	new_tbl = rht_dereference_rcu(tbl->future_tbl, ht);
 	if (unlikely(new_tbl)) {
-		err = rhashtable_insert_slow(ht, key, obj, new_tbl);
-		if (err == -EAGAIN)
+		tbl = rhashtable_insert_slow(ht, key, obj, new_tbl);
+		if (!IS_ERR_OR_NULL(tbl))
 			goto slow_path;
+
+		err = PTR_ERR(tbl);
 		goto out;
 	}
 
@@ -611,7 +615,7 @@ restart:
 	if (unlikely(rht_grow_above_100(ht, tbl))) {
 slow_path:
 		spin_unlock_bh(lock);
-		err = rhashtable_insert_rehash(ht);
+		err = rhashtable_insert_rehash(ht, tbl);
 		rcu_read_unlock();
 		if (err)
 			return err;
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index a54ff8949f91..2ff7ed91663a 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -389,33 +389,31 @@ static bool rhashtable_check_elasticity(struct rhashtable *ht,
 	return false;
 }
 
-int rhashtable_insert_rehash(struct rhashtable *ht)
+int rhashtable_insert_rehash(struct rhashtable *ht,
+			     struct bucket_table *tbl)
 {
 	struct bucket_table *old_tbl;
 	struct bucket_table *new_tbl;
-	struct bucket_table *tbl;
 	unsigned int size;
 	int err;
 
 	old_tbl = rht_dereference_rcu(ht->tbl, ht);
-	tbl = rhashtable_last_table(ht, old_tbl);
 
 	size = tbl->size;
 
+	err = -EBUSY;
+
 	if (rht_grow_above_75(ht, tbl))
 		size *= 2;
 	/* Do not schedule more than one rehash */
 	else if (old_tbl != tbl)
-		return -EBUSY;
+		goto fail;
+
+	err = -ENOMEM;
 
 	new_tbl = bucket_table_alloc(ht, size, GFP_ATOMIC);
-	if (new_tbl == NULL) {
-		/* Schedule async resize/rehash to try allocation
-		 * non-atomic context.
-		 */
-		schedule_work(&ht->run_work);
-		return -ENOMEM;
-	}
+	if (new_tbl == NULL)
+		goto fail;
 
 	err = rhashtable_rehash_attach(ht, tbl, new_tbl);
 	if (err) {
@@ -426,12 +424,24 @@ int rhashtable_insert_rehash(struct rhashtable *ht)
 		schedule_work(&ht->run_work);
 
 	return err;
+
+fail:
+	/* Do not fail the insert if someone else did a rehash. */
+	if (likely(rcu_dereference_raw(tbl->future_tbl)))
+		return 0;
+
+	/* Schedule async rehash to retry allocation in process context. */
+	if (err == -ENOMEM)
+		schedule_work(&ht->run_work);
+
+	return err;
 }
 EXPORT_SYMBOL_GPL(rhashtable_insert_rehash);
 
-int rhashtable_insert_slow(struct rhashtable *ht, const void *key,
-			   struct rhash_head *obj,
-			   struct bucket_table *tbl)
+struct bucket_table *rhashtable_insert_slow(struct rhashtable *ht,
+					    const void *key,
+					    struct rhash_head *obj,
+					    struct bucket_table *tbl)
 {
 	struct rhash_head *head;
 	unsigned int hash;
@@ -467,7 +477,12 @@ int rhashtable_insert_slow(struct rhashtable *ht, const void *key,
 exit:
 	spin_unlock(rht_bucket_lock(tbl, hash));
 
-	return err;
+	if (err == 0)
+		return NULL;
+	else if (err == -EAGAIN)
+		return tbl;
+	else
+		return ERR_PTR(err);
 }
 EXPORT_SYMBOL_GPL(rhashtable_insert_slow);
 
-- 
cgit v1.2.3


From 326fcfa5acca446b3f71e99f6d19881145556e5c Mon Sep 17 00:00:00 2001
From: Felix Fietkau
Date: Sat, 5 Dec 2015 13:58:11 +0100
Subject: net: remove unnecessary semicolon in netdev_alloc_pcpu_stats()

This semicolon causes a build error if the function call is wrapped in
parentheses.

Fixes: aabc92bbe3cf ("net: add __netdev_alloc_pcpu_stats() to indicate gfp flags")
Reported-by: Imre Kaloz <kaloz@openwrt.org>
Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Acked-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 3b5d134e945a..3143c847bddb 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2084,7 +2084,7 @@ struct pcpu_sw_netstats {
 })
 
 #define netdev_alloc_pcpu_stats(type)					\
-	__netdev_alloc_pcpu_stats(type, GFP_KERNEL);
+	__netdev_alloc_pcpu_stats(type, GFP_KERNEL)
 
 #include <linux/notifier.h>
 
-- 
cgit v1.2.3


From ea013a9b205b47b1fcbc72522146fad560af0712 Mon Sep 17 00:00:00 2001
From: Andreas Werner
Date: Fri, 4 Dec 2015 18:12:49 +0100
Subject: libata-eh.c: Introduce new ata port flag for controller which lockup
 on read log page

Some controller lockup on a ata_read_log_page.
Add new ata port flag ATA_FLAG_NO_LOG_PAGE which can used
to blacklist a controller.

If this flag is set, any attempt to read a log page returns an error
without actually issuing the command.

Signed-off-by: Andreas Werner <andreas.werner@men.de>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 drivers/ata/libata-eh.c | 8 ++++++++
 include/linux/libata.h  | 1 +
 2 files changed, 9 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index cb0508af1459..961acc788f44 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -1505,12 +1505,20 @@ static const char *ata_err_string(unsigned int err_mask)
 unsigned int ata_read_log_page(struct ata_device *dev, u8 log,
 			       u8 page, void *buf, unsigned int sectors)
 {
+	unsigned long ap_flags = dev->link->ap->flags;
 	struct ata_taskfile tf;
 	unsigned int err_mask;
 	bool dma = false;
 
 	DPRINTK("read log page - log 0x%x, page 0x%x\n", log, page);
 
+	/*
+	 * Return error without actually issuing the command on controllers
+	 * which e.g. lockup on a read log page.
+	 */
+	if (ap_flags & ATA_FLAG_NO_LOG_PAGE)
+		return AC_ERR_DEV;
+
 retry:
 	ata_tf_init(dev, &tf);
 	if (dev->dma_mode && ata_id_has_read_log_dma_ext(dev->id) &&
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 83577f8fd15b..600c1e0626a5 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -210,6 +210,7 @@ enum {
 	ATA_FLAG_SLAVE_POSS	= (1 << 0), /* host supports slave dev */
 					    /* (doesn't imply presence) */
 	ATA_FLAG_SATA		= (1 << 1),
+	ATA_FLAG_NO_LOG_PAGE	= (1 << 5), /* do not issue log page read */
 	ATA_FLAG_NO_ATAPI	= (1 << 6), /* No ATAPI support */
 	ATA_FLAG_PIO_DMA	= (1 << 7), /* PIO cmds via DMA */
 	ATA_FLAG_PIO_LBA48	= (1 << 8), /* Host DMA engine is LBA28 only */
-- 
cgit v1.2.3


From 57b4bd06ff0372fe1e3617889c4b37fbd500364a Mon Sep 17 00:00:00 2001
From: Matias Bjørling
Date: Sun, 6 Dec 2015 11:25:47 +0100
Subject: lightnvm: comments on constants

It is not obvious what NVM_IO_* and NVM_BLK_T_* are used for. Make sure
to comment them appropriately as the other constants.

Signed-off-by: Matias Bjørling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 include/linux/lightnvm.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index c6916aec43b6..935ef3844c05 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -50,9 +50,16 @@ enum {
 	NVM_IO_DUAL_ACCESS	= 0x1,
 	NVM_IO_QUAD_ACCESS	= 0x2,
 
+	/* NAND Access Modes */
 	NVM_IO_SUSPEND		= 0x80,
 	NVM_IO_SLC_MODE		= 0x100,
 	NVM_IO_SCRAMBLE_DISABLE	= 0x200,
+
+	/* Block Types */
+	NVM_BLK_T_FREE		= 0x0,
+	NVM_BLK_T_BAD		= 0x1,
+	NVM_BLK_T_DEV		= 0x2,
+	NVM_BLK_T_HOST		= 0x4,
 };
 
 struct nvm_id_group {
-- 
cgit v1.2.3


From 16f26c3aa9b9c36a9d1092ae3258461d1008481e Mon Sep 17 00:00:00 2001
From: Matias Bjørling
Date: Sun, 6 Dec 2015 11:25:48 +0100
Subject: lightnvm: replace req queue with nvmdev for lld

In the case where a request queue is passed to the low lever lightnvm
device drive integration, the device driver might pass its admin
commands through another queue. Instead pass nvm_dev, and let the
low level drive the appropriate queue.

Reported-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Matias Bjørling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 drivers/block/null_blk.c     |  9 +++++----
 drivers/lightnvm/core.c      |  7 +++----
 drivers/lightnvm/gennvm.c    |  8 ++++----
 drivers/lightnvm/rrpc.c      |  2 +-
 drivers/nvme/host/lightnvm.c | 24 +++++++++++++-----------
 include/linux/lightnvm.h     | 14 +++++++-------
 6 files changed, 33 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 0c3940ec5e62..7981b7407305 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -444,8 +444,9 @@ static void null_lnvm_end_io(struct request *rq, int error)
 	blk_put_request(rq);
 }
 
-static int null_lnvm_submit_io(struct request_queue *q, struct nvm_rq *rqd)
+static int null_lnvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd)
 {
+	struct request_queue *q = dev->q;
 	struct request *rq;
 	struct bio *bio = rqd->bio;
 
@@ -470,7 +471,7 @@ static int null_lnvm_submit_io(struct request_queue *q, struct nvm_rq *rqd)
 	return 0;
 }
 
-static int null_lnvm_id(struct request_queue *q, struct nvm_id *id)
+static int null_lnvm_id(struct nvm_dev *dev, struct nvm_id *id)
 {
 	sector_t size = gb * 1024 * 1024 * 1024ULL;
 	sector_t blksize;
@@ -523,7 +524,7 @@ static int null_lnvm_id(struct request_queue *q, struct nvm_id *id)
 	return 0;
 }
 
-static void *null_lnvm_create_dma_pool(struct request_queue *q, char *name)
+static void *null_lnvm_create_dma_pool(struct nvm_dev *dev, char *name)
 {
 	mempool_t *virtmem_pool;
 
@@ -541,7 +542,7 @@ static void null_lnvm_destroy_dma_pool(void *pool)
 	mempool_destroy(pool);
 }
 
-static void *null_lnvm_dev_dma_alloc(struct request_queue *q, void *pool,
+static void *null_lnvm_dev_dma_alloc(struct nvm_dev *dev, void *pool,
 				gfp_t mem_flags, dma_addr_t *dma_handler)
 {
 	return mempool_alloc(pool, mem_flags);
diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c
index 86ce887b2ed6..4a8d1fe34c4e 100644
--- a/drivers/lightnvm/core.c
+++ b/drivers/lightnvm/core.c
@@ -74,7 +74,7 @@ EXPORT_SYMBOL(nvm_unregister_target);
 void *nvm_dev_dma_alloc(struct nvm_dev *dev, gfp_t mem_flags,
 							dma_addr_t *dma_handler)
 {
-	return dev->ops->dev_dma_alloc(dev->q, dev->ppalist_pool, mem_flags,
+	return dev->ops->dev_dma_alloc(dev, dev->ppalist_pool, mem_flags,
 								dma_handler);
 }
 EXPORT_SYMBOL(nvm_dev_dma_alloc);
@@ -246,7 +246,7 @@ static int nvm_init(struct nvm_dev *dev)
 	if (!dev->q || !dev->ops)
 		return ret;
 
-	if (dev->ops->identity(dev->q, &dev->identity)) {
+	if (dev->ops->identity(dev, &dev->identity)) {
 		pr_err("nvm: device could not be identified\n");
 		goto err;
 	}
@@ -326,8 +326,7 @@ int nvm_register(struct request_queue *q, char *disk_name,
 	}
 
 	if (dev->ops->max_phys_sect > 1) {
-		dev->ppalist_pool = dev->ops->create_dma_pool(dev->q,
-								"ppalist");
+		dev->ppalist_pool = dev->ops->create_dma_pool(dev, "ppalist");
 		if (!dev->ppalist_pool) {
 			pr_err("nvm: could not create ppa pool\n");
 			ret = -ENOMEM;
diff --git a/drivers/lightnvm/gennvm.c b/drivers/lightnvm/gennvm.c
index ce6025487a5c..52b513a65946 100644
--- a/drivers/lightnvm/gennvm.c
+++ b/drivers/lightnvm/gennvm.c
@@ -195,7 +195,7 @@ static int gennvm_blocks_init(struct nvm_dev *dev, struct gen_nvm *gn)
 	}
 
 	if (dev->ops->get_l2p_tbl) {
-		ret = dev->ops->get_l2p_tbl(dev->q, 0, dev->total_pages,
+		ret = dev->ops->get_l2p_tbl(dev, 0, dev->total_pages,
 							gennvm_block_map, dev);
 		if (ret) {
 			pr_err("gennvm: could not read L2P table.\n");
@@ -346,7 +346,7 @@ static int gennvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd)
 	gennvm_generic_to_addr_mode(dev, rqd);
 
 	rqd->dev = dev;
-	return dev->ops->submit_io(dev->q, rqd);
+	return dev->ops->submit_io(dev, rqd);
 }
 
 static void gennvm_blk_set_type(struct nvm_dev *dev, struct ppa_addr *ppa,
@@ -382,7 +382,7 @@ static void gennvm_mark_blk_bad(struct nvm_dev *dev, struct nvm_rq *rqd)
 	if (!dev->ops->set_bb_tbl)
 		return;
 
-	if (dev->ops->set_bb_tbl(dev->q, rqd, 1))
+	if (dev->ops->set_bb_tbl(dev, rqd, 1))
 		return;
 
 	gennvm_addr_to_generic_mode(dev, rqd);
@@ -450,7 +450,7 @@ static int gennvm_erase_blk(struct nvm_dev *dev, struct nvm_block *blk,
 
 	gennvm_generic_to_addr_mode(dev, &rqd);
 
-	ret = dev->ops->erase_block(dev->q, &rqd);
+	ret = dev->ops->erase_block(dev, &rqd);
 
 	if (plane_cnt)
 		nvm_dev_dma_free(dev, rqd.ppa_list, rqd.dma_ppa_list);
diff --git a/drivers/lightnvm/rrpc.c b/drivers/lightnvm/rrpc.c
index cf1a4a515b76..134e4faba482 100644
--- a/drivers/lightnvm/rrpc.c
+++ b/drivers/lightnvm/rrpc.c
@@ -1016,7 +1016,7 @@ static int rrpc_map_init(struct rrpc *rrpc)
 		return 0;
 
 	/* Bring up the mapping table from device */
-	ret = dev->ops->get_l2p_tbl(dev->q, 0, dev->total_pages,
+	ret = dev->ops->get_l2p_tbl(dev, 0, dev->total_pages,
 							rrpc_l2p_update, rrpc);
 	if (ret) {
 		pr_err("nvm: rrpc: could not read L2P table.\n");
diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index 762c9a7cbfa6..15f2acb4d5cd 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -271,9 +271,9 @@ static int init_grps(struct nvm_id *nvm_id, struct nvme_nvm_id *nvme_nvm_id)
 	return 0;
 }
 
-static int nvme_nvm_identity(struct request_queue *q, struct nvm_id *nvm_id)
+static int nvme_nvm_identity(struct nvm_dev *nvmdev, struct nvm_id *nvm_id)
 {
-	struct nvme_ns *ns = q->queuedata;
+	struct nvme_ns *ns = nvmdev->q->queuedata;
 	struct nvme_dev *dev = ns->dev;
 	struct nvme_nvm_id *nvme_nvm_id;
 	struct nvme_nvm_command c = {};
@@ -308,10 +308,10 @@ out:
 	return ret;
 }
 
-static int nvme_nvm_get_l2p_tbl(struct request_queue *q, u64 slba, u32 nlb,
+static int nvme_nvm_get_l2p_tbl(struct nvm_dev *nvmdev, u64 slba, u32 nlb,
 				nvm_l2p_update_fn *update_l2p, void *priv)
 {
-	struct nvme_ns *ns = q->queuedata;
+	struct nvme_ns *ns = nvmdev->q->queuedata;
 	struct nvme_dev *dev = ns->dev;
 	struct nvme_nvm_command c = {};
 	u32 len = queue_max_hw_sectors(dev->admin_q) << 9;
@@ -415,10 +415,10 @@ out:
 	return ret;
 }
 
-static int nvme_nvm_set_bb_tbl(struct request_queue *q, struct nvm_rq *rqd,
+static int nvme_nvm_set_bb_tbl(struct nvm_dev *nvmdev, struct nvm_rq *rqd,
 								int type)
 {
-	struct nvme_ns *ns = q->queuedata;
+	struct nvme_ns *ns = nvmdev->q->queuedata;
 	struct nvme_dev *dev = ns->dev;
 	struct nvme_nvm_command c = {};
 	int ret = 0;
@@ -463,8 +463,9 @@ static void nvme_nvm_end_io(struct request *rq, int error)
 	blk_mq_free_request(rq);
 }
 
-static int nvme_nvm_submit_io(struct request_queue *q, struct nvm_rq *rqd)
+static int nvme_nvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd)
 {
+	struct request_queue *q = dev->q;
 	struct nvme_ns *ns = q->queuedata;
 	struct request *rq;
 	struct bio *bio = rqd->bio;
@@ -502,8 +503,9 @@ static int nvme_nvm_submit_io(struct request_queue *q, struct nvm_rq *rqd)
 	return 0;
 }
 
-static int nvme_nvm_erase_block(struct request_queue *q, struct nvm_rq *rqd)
+static int nvme_nvm_erase_block(struct nvm_dev *dev, struct nvm_rq *rqd)
 {
+	struct request_queue *q = dev->q;
 	struct nvme_ns *ns = q->queuedata;
 	struct nvme_nvm_command c = {};
 
@@ -515,9 +517,9 @@ static int nvme_nvm_erase_block(struct request_queue *q, struct nvm_rq *rqd)
 	return nvme_submit_sync_cmd(q, (struct nvme_command *)&c, NULL, 0);
 }
 
-static void *nvme_nvm_create_dma_pool(struct request_queue *q, char *name)
+static void *nvme_nvm_create_dma_pool(struct nvm_dev *nvmdev, char *name)
 {
-	struct nvme_ns *ns = q->queuedata;
+	struct nvme_ns *ns = nvmdev->q->queuedata;
 	struct nvme_dev *dev = ns->dev;
 
 	return dma_pool_create(name, dev->dev, PAGE_SIZE, PAGE_SIZE, 0);
@@ -530,7 +532,7 @@ static void nvme_nvm_destroy_dma_pool(void *pool)
 	dma_pool_destroy(dma_pool);
 }
 
-static void *nvme_nvm_dev_dma_alloc(struct request_queue *q, void *pool,
+static void *nvme_nvm_dev_dma_alloc(struct nvm_dev *dev, void *pool,
 				    gfp_t mem_flags, dma_addr_t *dma_handler)
 {
 	return dma_pool_alloc(pool, mem_flags, dma_handler);
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index 935ef3844c05..034117b3be5f 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -183,17 +183,17 @@ struct nvm_block;
 
 typedef int (nvm_l2p_update_fn)(u64, u32, __le64 *, void *);
 typedef int (nvm_bb_update_fn)(struct ppa_addr, int, u8 *, void *);
-typedef int (nvm_id_fn)(struct request_queue *, struct nvm_id *);
-typedef int (nvm_get_l2p_tbl_fn)(struct request_queue *, u64, u32,
+typedef int (nvm_id_fn)(struct nvm_dev *, struct nvm_id *);
+typedef int (nvm_get_l2p_tbl_fn)(struct nvm_dev *, u64, u32,
 				nvm_l2p_update_fn *, void *);
 typedef int (nvm_op_bb_tbl_fn)(struct nvm_dev *, struct ppa_addr, int,
 				nvm_bb_update_fn *, void *);
-typedef int (nvm_op_set_bb_fn)(struct request_queue *, struct nvm_rq *, int);
-typedef int (nvm_submit_io_fn)(struct request_queue *, struct nvm_rq *);
-typedef int (nvm_erase_blk_fn)(struct request_queue *, struct nvm_rq *);
-typedef void *(nvm_create_dma_pool_fn)(struct request_queue *, char *);
+typedef int (nvm_op_set_bb_fn)(struct nvm_dev *, struct nvm_rq *, int);
+typedef int (nvm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *);
+typedef int (nvm_erase_blk_fn)(struct nvm_dev *, struct nvm_rq *);
+typedef void *(nvm_create_dma_pool_fn)(struct nvm_dev *, char *);
 typedef void (nvm_destroy_dma_pool_fn)(void *);
-typedef void *(nvm_dev_dma_alloc_fn)(struct request_queue *, void *, gfp_t,
+typedef void *(nvm_dev_dma_alloc_fn)(struct nvm_dev *, void *, gfp_t,
 								dma_addr_t *);
 typedef void (nvm_dev_dma_free_fn)(void *, void*, dma_addr_t);
 
-- 
cgit v1.2.3


From 4639d60d2bfb7f5007b5d93788fd93c19b63f000 Mon Sep 17 00:00:00 2001
From: Tomer Tayar
Date: Mon, 7 Dec 2015 06:25:56 -0500
Subject: qed: Fix corner case for chain in-between pages

The amount of chain next pointer elements between the producer
and the consumer indices depends on which pages they currently
point to. The current calculation is based only on their difference,
and it can lead to a number of free elements which is higher by 1
than the actual value.

Signed-off-by: Tomer Tayar <Tomer.Tayar@qlogic.com>
Signed-off-by: Manish Chopra <manish.chopra@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/qed/qed_chain.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h
index b920c3605c46..41b9049b57e2 100644
--- a/include/linux/qed/qed_chain.h
+++ b/include/linux/qed/qed_chain.h
@@ -111,7 +111,8 @@ static inline u16 qed_chain_get_elem_left(struct qed_chain *p_chain)
 	used = ((u32)0x10000u + (u32)(p_chain->prod_idx)) -
 		(u32)p_chain->cons_idx;
 	if (p_chain->mode == QED_CHAIN_MODE_NEXT_PTR)
-		used -= (used / p_chain->elem_per_page);
+		used -= p_chain->prod_idx / p_chain->elem_per_page -
+			p_chain->cons_idx / p_chain->elem_per_page;
 
 	return p_chain->capacity - used;
 }
-- 
cgit v1.2.3


From 76a9a3642a0b72d5687d680150580d55b6ea9804 Mon Sep 17 00:00:00 2001
From: Tomer Tayar
Date: Mon, 7 Dec 2015 06:25:57 -0500
Subject: qed: fix handling of concurrent ramrods.

Concurrent non-blocking slowpath ramrods can be completed
out-of-order on the completion chain. Recycling completed elements,
while previously sent elements are still completion pending,
can lead to overriding of active elements on the chain. Furthermore,
sending pending slowpath ramrods currently lacks the update of the
chain element physical pointer.

This patch:
* Ensures that ramrods are sent to the FW with
  consecutive echo values.
* Handles out-of-order completions by freeing only first
  successive completed entries.
* Updates the chain element physical pointer when copying
  a pending element into a free element for sending.

Signed-off-by: Tomer Tayar <Tomer.Tayar@qlogic.com>
Signed-off-by: Manish Chopra <manish.chopra@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_sp.h  |  8 +++-
 drivers/net/ethernet/qlogic/qed/qed_spq.c | 63 +++++++++++++++++++++++--------
 include/linux/qed/common_hsi.h            |  2 +
 3 files changed, 56 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp.h b/drivers/net/ethernet/qlogic/qed/qed_sp.h
index 31a1f1eb4f56..287fadfab52d 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_sp.h
@@ -124,8 +124,12 @@ struct qed_spq {
 	dma_addr_t		p_phys;
 	struct qed_spq_entry	*p_virt;
 
-	/* Used as index for completions (returns on EQ by FW) */
-	u16			echo_idx;
+#define SPQ_RING_SIZE \
+	(CORE_SPQE_PAGE_SIZE_BYTES / sizeof(struct slow_path_element))
+
+	/* Bitmap for handling out-of-order completions */
+	DECLARE_BITMAP(p_comp_bitmap, SPQ_RING_SIZE);
+	u8			comp_bitmap_idx;
 
 	/* Statistics */
 	u32			unlimited_pending_count;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c
index 7c0b8459666e..3dd548ab8df1 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_spq.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c
@@ -112,8 +112,6 @@ static int
 qed_spq_fill_entry(struct qed_hwfn *p_hwfn,
 		   struct qed_spq_entry *p_ent)
 {
-	p_ent->elem.hdr.echo = 0;
-	p_hwfn->p_spq->echo_idx++;
 	p_ent->flags = 0;
 
 	switch (p_ent->comp_mode) {
@@ -195,10 +193,12 @@ static int qed_spq_hw_post(struct qed_hwfn *p_hwfn,
 			   struct qed_spq *p_spq,
 			   struct qed_spq_entry *p_ent)
 {
-	struct qed_chain		*p_chain = &p_hwfn->p_spq->chain;
+	struct qed_chain *p_chain = &p_hwfn->p_spq->chain;
+	u16 echo = qed_chain_get_prod_idx(p_chain);
 	struct slow_path_element	*elem;
 	struct core_db_data		db;
 
+	p_ent->elem.hdr.echo	= cpu_to_le16(echo);
 	elem = qed_chain_produce(p_chain);
 	if (!elem) {
 		DP_NOTICE(p_hwfn, "Failed to produce from SPQ chain\n");
@@ -437,7 +437,9 @@ void qed_spq_setup(struct qed_hwfn *p_hwfn)
 	p_spq->comp_count		= 0;
 	p_spq->comp_sent_count		= 0;
 	p_spq->unlimited_pending_count	= 0;
-	p_spq->echo_idx			= 0;
+
+	bitmap_zero(p_spq->p_comp_bitmap, SPQ_RING_SIZE);
+	p_spq->comp_bitmap_idx = 0;
 
 	/* SPQ cid, cannot fail */
 	qed_cxt_acquire_cid(p_hwfn, PROTOCOLID_CORE, &p_spq->cid);
@@ -582,26 +584,32 @@ qed_spq_add_entry(struct qed_hwfn *p_hwfn,
 	struct qed_spq *p_spq = p_hwfn->p_spq;
 
 	if (p_ent->queue == &p_spq->unlimited_pending) {
-		struct qed_spq_entry *p_en2;
 
 		if (list_empty(&p_spq->free_pool)) {
 			list_add_tail(&p_ent->list, &p_spq->unlimited_pending);
 			p_spq->unlimited_pending_count++;
 
 			return 0;
-		}
+		} else {
+			struct qed_spq_entry *p_en2;
 
-		p_en2 = list_first_entry(&p_spq->free_pool,
-					 struct qed_spq_entry,
-					 list);
-		list_del(&p_en2->list);
+			p_en2 = list_first_entry(&p_spq->free_pool,
+						 struct qed_spq_entry,
+						 list);
+			list_del(&p_en2->list);
+
+			/* Copy the ring element physical pointer to the new
+			 * entry, since we are about to override the entire ring
+			 * entry and don't want to lose the pointer.
+			 */
+			p_ent->elem.data_ptr = p_en2->elem.data_ptr;
 
-		/* Strcut assignment */
-		*p_en2 = *p_ent;
+			*p_en2 = *p_ent;
 
-		kfree(p_ent);
+			kfree(p_ent);
 
-		p_ent = p_en2;
+			p_ent = p_en2;
+		}
 	}
 
 	/* entry is to be placed in 'pending' queue */
@@ -777,13 +785,38 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn,
 	list_for_each_entry_safe(p_ent, tmp, &p_spq->completion_pending,
 				 list) {
 		if (p_ent->elem.hdr.echo == echo) {
+			u16 pos = le16_to_cpu(echo) % SPQ_RING_SIZE;
+
 			list_del(&p_ent->list);
 
-			qed_chain_return_produced(&p_spq->chain);
+			/* Avoid overriding of SPQ entries when getting
+			 * out-of-order completions, by marking the completions
+			 * in a bitmap and increasing the chain consumer only
+			 * for the first successive completed entries.
+			 */
+			bitmap_set(p_spq->p_comp_bitmap, pos, SPQ_RING_SIZE);
+
+			while (test_bit(p_spq->comp_bitmap_idx,
+					p_spq->p_comp_bitmap)) {
+				bitmap_clear(p_spq->p_comp_bitmap,
+					     p_spq->comp_bitmap_idx,
+					     SPQ_RING_SIZE);
+				p_spq->comp_bitmap_idx++;
+				qed_chain_return_produced(&p_spq->chain);
+			}
+
 			p_spq->comp_count++;
 			found = p_ent;
 			break;
 		}
+
+		/* This is relatively uncommon - depends on scenarios
+		 * which have mutliple per-PF sent ramrods.
+		 */
+		DP_VERBOSE(p_hwfn, QED_MSG_SPQ,
+			   "Got completion for echo %04x - doesn't match echo %04x in completion pending list\n",
+			   le16_to_cpu(echo),
+			   le16_to_cpu(p_ent->elem.hdr.echo));
 	}
 
 	/* Release lock before callback, as callback may post
diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h
index 6a4347639c03..1d1ba2c5ee7a 100644
--- a/include/linux/qed/common_hsi.h
+++ b/include/linux/qed/common_hsi.h
@@ -9,6 +9,8 @@
 #ifndef __COMMON_HSI__
 #define __COMMON_HSI__
 
+#define CORE_SPQE_PAGE_SIZE_BYTES                       4096
+
 #define FW_MAJOR_VERSION	8
 #define FW_MINOR_VERSION	4
 #define FW_REVISION_VERSION	2
-- 
cgit v1.2.3


From a5e14ba334e202c58e45ef47414ec94c585c1a8c Mon Sep 17 00:00:00 2001
From: Sagi Grimberg
Date: Wed, 28 Oct 2015 13:28:15 +0200
Subject: mlx4: Expose correct max_sge_rd limit

mlx4 devices (ConnectX-2, ConnectX-3) has a limitation
where rdma read work queue entries cannot exceed 512 bytes.
A rdma_read wqe needs to fit in 512 bytes:
- wqe control segment (16 bytes)
- rdma segment (16 bytes)
- scatter elements (16 bytes each)

So max_sge_rd should be: (512 - 16 - 16) / 16 = 30.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/hw/mlx4/main.c |  2 +-
 include/linux/mlx4/device.h       | 11 +++++++++++
 2 files changed, 12 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index f567160a4a56..97d6878f9938 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -456,7 +456,7 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
 	props->max_qp_wr	   = dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE;
 	props->max_sge		   = min(dev->dev->caps.max_sq_sg,
 					 dev->dev->caps.max_rq_sg);
-	props->max_sge_rd = props->max_sge;
+	props->max_sge_rd	   = MLX4_MAX_SGE_RD;
 	props->max_cq		   = dev->dev->quotas.cq;
 	props->max_cqe		   = dev->dev->caps.max_cqes;
 	props->max_mr		   = dev->dev->quotas.mpt;
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 7501626ab529..d3133be12d92 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -426,6 +426,17 @@ enum {
 	MLX4_MAX_FAST_REG_PAGES = 511,
 };
 
+enum {
+	/*
+	 * Max wqe size for rdma read is 512 bytes, so this
+	 * limits our max_sge_rd as the wqe needs to fit:
+	 * - ctrl segment (16 bytes)
+	 * - rdma segment (16 bytes)
+	 * - scatter elements (16 bytes each)
+	 */
+	MLX4_MAX_SGE_RD	= (512 - 16 - 16) / 16
+};
+
 enum {
 	MLX4_DEV_PMC_SUBTYPE_GUID_INFO	 = 0x14,
 	MLX4_DEV_PMC_SUBTYPE_PORT_INFO	 = 0x15,
-- 
cgit v1.2.3


From 4c3141e09cfa6460bfcd5e90f73e498db654c917 Mon Sep 17 00:00:00 2001
From: Carlo Caione
Date: Tue, 1 Dec 2015 17:24:17 +0100
Subject: of/irq: Export of_irq_find_parent again

of_irq_find_parent was made static since it had no users outside of
of_irq.c. Export it again since we are going to use it again.

Signed-off-by: Carlo Caione <carlo@endlessm.com>
[robh: move of_irq_find_parent to correct ifdef section]
Signed-off-by: Rob Herring <robh@kernel.org>
---
 drivers/of/irq.c       | 3 ++-
 include/linux/of_irq.h | 6 ++++++
 2 files changed, 8 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index 902b89be7217..4fa916dffc91 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -53,7 +53,7 @@ EXPORT_SYMBOL_GPL(irq_of_parse_and_map);
  * Returns a pointer to the interrupt parent node, or NULL if the interrupt
  * parent could not be determined.
  */
-static struct device_node *of_irq_find_parent(struct device_node *child)
+struct device_node *of_irq_find_parent(struct device_node *child)
 {
 	struct device_node *p;
 	const __be32 *parp;
@@ -77,6 +77,7 @@ static struct device_node *of_irq_find_parent(struct device_node *child)
 
 	return p;
 }
+EXPORT_SYMBOL_GPL(of_irq_find_parent);
 
 /**
  * of_irq_parse_raw - Low level interrupt tree parsing
diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h
index 039f2eec49ce..f648acf27ed7 100644
--- a/include/linux/of_irq.h
+++ b/include/linux/of_irq.h
@@ -46,6 +46,7 @@ extern int of_irq_get(struct device_node *dev, int index);
 extern int of_irq_get_byname(struct device_node *dev, const char *name);
 extern int of_irq_to_resource_table(struct device_node *dev,
 		struct resource *res, int nr_irqs);
+extern struct device_node *of_irq_find_parent(struct device_node *child);
 extern struct irq_domain *of_msi_get_domain(struct device *dev,
 					    struct device_node *np,
 					    enum irq_domain_bus_token token);
@@ -70,6 +71,11 @@ static inline int of_irq_to_resource_table(struct device_node *dev,
 {
 	return 0;
 }
+static inline void *of_irq_find_parent(struct device_node *child)
+{
+	return NULL;
+}
+
 static inline struct irq_domain *of_msi_get_domain(struct device *dev,
 						   struct device_node *np,
 						   enum irq_domain_bus_token token)
-- 
cgit v1.2.3


From eaddb5725357e9f05ffe5d271630f8197d089da4 Mon Sep 17 00:00:00 2001
From: Rob Herring
Date: Wed, 9 Dec 2015 09:11:10 -0600
Subject: of/irq: move of_msi_map_rid declaration to the correct ifdef section

In checking fixes for of_irq_find_parent declaration location, I found
that of_msi_map_rid is also wrong. of_msi_map_rid is not implemented for
Sparc, so it should not be in the Sparc specific section of the header.
Move it to just depend on OF_IRQ.

Cc: Frank Rowand <frowand.list@gmail.com>
Signed-off-by: Rob Herring <robh@kernel.org>
---
 include/linux/of_irq.h | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h
index f648acf27ed7..1e0deb8e8494 100644
--- a/include/linux/of_irq.h
+++ b/include/linux/of_irq.h
@@ -53,6 +53,7 @@ extern struct irq_domain *of_msi_get_domain(struct device *dev,
 extern struct irq_domain *of_msi_map_get_device_domain(struct device *dev,
 						       u32 rid);
 extern void of_msi_configure(struct device *dev, struct device_node *np);
+u32 of_msi_map_rid(struct device *dev, struct device_node *msi_np, u32 rid_in);
 #else
 static inline int of_irq_count(struct device_node *dev)
 {
@@ -90,6 +91,11 @@ static inline struct irq_domain *of_msi_map_get_device_domain(struct device *dev
 static inline void of_msi_configure(struct device *dev, struct device_node *np)
 {
 }
+static inline u32 of_msi_map_rid(struct device *dev,
+				 struct device_node *msi_np, u32 rid_in)
+{
+	return rid_in;
+}
 #endif
 
 #if defined(CONFIG_OF_IRQ) || defined(CONFIG_SPARC)
@@ -99,7 +105,6 @@ static inline void of_msi_configure(struct device *dev, struct device_node *np)
  * so declare it here regardless of the CONFIG_OF_IRQ setting.
  */
 extern unsigned int irq_of_parse_and_map(struct device_node *node, int index);
-u32 of_msi_map_rid(struct device *dev, struct device_node *msi_np, u32 rid_in);
 
 #else /* !CONFIG_OF && !CONFIG_SPARC */
 static inline unsigned int irq_of_parse_and_map(struct device_node *dev,
@@ -107,12 +112,6 @@ static inline unsigned int irq_of_parse_and_map(struct device_node *dev,
 {
 	return 0;
 }
-
-static inline u32 of_msi_map_rid(struct device *dev,
-				 struct device_node *msi_np, u32 rid_in)
-{
-	return rid_in;
-}
 #endif /* !CONFIG_OF */
 
 #endif /* __OF_IRQ_H */
-- 
cgit v1.2.3


From d7e35dfa2531b53618b9e6edcd8752ce988ac555 Mon Sep 17 00:00:00 2001
From: Sasha Levin
Date: Thu, 3 Dec 2015 22:04:01 -0500
Subject: bitops.h: correctly handle rol32 with 0 byte shift

ROL on a 32 bit integer with a shift of 32 or more is undefined and the
result is arch-dependent. Avoid this by handling the trivial case of
roling by 0 correctly.

The trivial solution of checking if shift is 0 breaks gcc's detection
of this code as a ROL instruction, which is unacceptable.

This bug was reported and fixed in GCC
(https://gcc.gnu.org/bugzilla/show_bug.cgi?id=57157):

	The standard rotate idiom,

	  (x << n) | (x >> (32 - n))

	is recognized by gcc (for concreteness, I discuss only the case that x
	is an uint32_t here).

	However, this is portable C only for n in the range 0 < n < 32. For n
	== 0, we get x >> 32 which gives undefined behaviour according to the
	C standard (6.5.7, Bitwise shift operators). To portably support n ==
	0, one has to write the rotate as something like

	  (x << n) | (x >> ((-n) & 31))

	And this is apparently not recognized by gcc.

Note that this is broken on older GCCs and will result in slower ROL.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/bitops.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index 2b8ed123ad36..defeaac0745f 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -107,7 +107,7 @@ static inline __u64 ror64(__u64 word, unsigned int shift)
  */
 static inline __u32 rol32(__u32 word, unsigned int shift)
 {
-	return (word << shift) | (word >> (32 - shift));
+	return (word << shift) | (word >> ((-shift) & 31));
 }
 
 /**
-- 
cgit v1.2.3


From ecb7deceff2a51d3be50518969bc06411f485a62 Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi
Date: Wed, 9 Dec 2015 10:18:10 +0200
Subject: dmaengine: edma: DT: Change memcpy channel array from 16bit to 32bit
 type

This change makes the DT file to be easier to read since the memcpy
channels array does not need the '/bits/ 16' to be specified, which might
confuse some people.

Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Rob Herring <robh@kernel.org>
Acked-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 Documentation/devicetree/bindings/dma/ti-edma.txt |  5 ++---
 drivers/dma/edma.c                                | 22 ++++++++++------------
 include/linux/platform_data/edma.h                |  2 +-
 3 files changed, 13 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/devicetree/bindings/dma/ti-edma.txt b/Documentation/devicetree/bindings/dma/ti-edma.txt
index d3d0a4fb1c73..ae8b8f1d6e69 100644
--- a/Documentation/devicetree/bindings/dma/ti-edma.txt
+++ b/Documentation/devicetree/bindings/dma/ti-edma.txt
@@ -22,8 +22,7 @@ Required properties:
 Optional properties:
 - ti,hwmods:	Name of the hwmods associated to the eDMA CC
 - ti,edma-memcpy-channels: List of channels allocated to be used for memcpy, iow
-		these channels will be SW triggered channels. The list must
-		contain 16 bits numbers, see example.
+		these channels will be SW triggered channels. See example.
 - ti,edma-reserved-slot-ranges: PaRAM slot ranges which should not be used by
 		the driver, they are allocated to be used by for example the
 		DSP. See example.
@@ -56,7 +55,7 @@ edma: edma@49000000 {
 	ti,tptcs = <&edma_tptc0 7>, <&edma_tptc1 7>, <&edma_tptc2 0>;
 
 	/* Channel 20 and 21 is allocated for memcpy */
-	ti,edma-memcpy-channels = /bits/ 16 <20 21>;
+	ti,edma-memcpy-channels = <20 21>;
 	/* The following PaRAM slots are reserved: 35-45 and 100-110 */
 	ti,edma-reserved-slot-ranges = /bits/ 16 <35 10>,
 				       /bits/ 16 <100 10>;
diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c
index 6b03e4e84e6b..3da20291db56 100644
--- a/drivers/dma/edma.c
+++ b/drivers/dma/edma.c
@@ -1752,16 +1752,14 @@ static enum dma_status edma_tx_status(struct dma_chan *chan,
 	return ret;
 }
 
-static bool edma_is_memcpy_channel(int ch_num, u16 *memcpy_channels)
+static bool edma_is_memcpy_channel(int ch_num, s32 *memcpy_channels)
 {
-	s16 *memcpy_ch = memcpy_channels;
-
 	if (!memcpy_channels)
 		return false;
-	while (*memcpy_ch != -1) {
-		if (*memcpy_ch == ch_num)
+	while (*memcpy_channels != -1) {
+		if (*memcpy_channels == ch_num)
 			return true;
-		memcpy_ch++;
+		memcpy_channels++;
 	}
 	return false;
 }
@@ -1775,7 +1773,7 @@ static void edma_dma_init(struct edma_cc *ecc, bool legacy_mode)
 {
 	struct dma_device *s_ddev = &ecc->dma_slave;
 	struct dma_device *m_ddev = NULL;
-	s16 *memcpy_channels = ecc->info->memcpy_channels;
+	s32 *memcpy_channels = ecc->info->memcpy_channels;
 	int i, j;
 
 	dma_cap_zero(s_ddev->cap_mask);
@@ -1996,16 +1994,16 @@ static struct edma_soc_info *edma_setup_info_from_dt(struct device *dev,
 	prop = of_find_property(dev->of_node, "ti,edma-memcpy-channels", &sz);
 	if (prop) {
 		const char pname[] = "ti,edma-memcpy-channels";
-		size_t nelm = sz / sizeof(s16);
-		s16 *memcpy_ch;
+		size_t nelm = sz / sizeof(s32);
+		s32 *memcpy_ch;
 
-		memcpy_ch = devm_kcalloc(dev, nelm + 1, sizeof(s16),
+		memcpy_ch = devm_kcalloc(dev, nelm + 1, sizeof(s32),
 					 GFP_KERNEL);
 		if (!memcpy_ch)
 			return ERR_PTR(-ENOMEM);
 
-		ret = of_property_read_u16_array(dev->of_node, pname,
-						 (u16 *)memcpy_ch, nelm);
+		ret = of_property_read_u32_array(dev->of_node, pname,
+						 (u32 *)memcpy_ch, nelm);
 		if (ret)
 			return ERR_PTR(ret);
 
diff --git a/include/linux/platform_data/edma.h b/include/linux/platform_data/edma.h
index e2878baeb90e..4299f4ba03bd 100644
--- a/include/linux/platform_data/edma.h
+++ b/include/linux/platform_data/edma.h
@@ -72,7 +72,7 @@ struct edma_soc_info {
 	struct edma_rsv_info	*rsv;
 
 	/* List of channels allocated for memcpy, terminated with -1 */
-	s16			*memcpy_channels;
+	s32			*memcpy_channels;
 
 	s8	(*queue_priority_mapping)[2];
 	const s16	(*xbar_chans)[2];
-- 
cgit v1.2.3


From 633c9a840d0bf1cce690f3165bdacd8ab412949e Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso
Date: Wed, 9 Dec 2015 12:08:26 +0100
Subject: netfilter: nfnetlink: avoid recurrent netns lookups in call_batch

Pass the net pointer to the call_batch callback functions so we can skip
recurrent lookups.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Tested-by: Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
---
 include/linux/netfilter/nfnetlink.h |  2 +-
 net/netfilter/nf_tables_api.c       | 96 +++++++++++++++++--------------------
 net/netfilter/nfnetlink.c           |  2 +-
 3 files changed, 47 insertions(+), 53 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h
index 249d1bb01e03..5646b24bfc64 100644
--- a/include/linux/netfilter/nfnetlink.h
+++ b/include/linux/netfilter/nfnetlink.h
@@ -14,7 +14,7 @@ struct nfnl_callback {
 	int (*call_rcu)(struct sock *nl, struct sk_buff *skb, 
 		    const struct nlmsghdr *nlh,
 		    const struct nlattr * const cda[]);
-	int (*call_batch)(struct sock *nl, struct sk_buff *skb,
+	int (*call_batch)(struct net *net, struct sock *nl, struct sk_buff *skb,
 			  const struct nlmsghdr *nlh,
 			  const struct nlattr * const cda[]);
 	const struct nla_policy *policy;	/* netlink attribute policy */
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 93cc4737018f..f1002dcfa1c9 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -89,6 +89,7 @@ nf_tables_afinfo_lookup(struct net *net, int family, bool autoload)
 }
 
 static void nft_ctx_init(struct nft_ctx *ctx,
+			 struct net *net,
 			 const struct sk_buff *skb,
 			 const struct nlmsghdr *nlh,
 			 struct nft_af_info *afi,
@@ -96,7 +97,7 @@ static void nft_ctx_init(struct nft_ctx *ctx,
 			 struct nft_chain *chain,
 			 const struct nlattr * const *nla)
 {
-	ctx->net	= sock_net(skb->sk);
+	ctx->net	= net;
 	ctx->afi	= afi;
 	ctx->table	= table;
 	ctx->chain	= chain;
@@ -672,15 +673,14 @@ err:
 	return ret;
 }
 
-static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb,
-			      const struct nlmsghdr *nlh,
+static int nf_tables_newtable(struct net *net, struct sock *nlsk,
+			      struct sk_buff *skb, const struct nlmsghdr *nlh,
 			      const struct nlattr * const nla[])
 {
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	const struct nlattr *name;
 	struct nft_af_info *afi;
 	struct nft_table *table;
-	struct net *net = sock_net(skb->sk);
 	int family = nfmsg->nfgen_family;
 	u32 flags = 0;
 	struct nft_ctx ctx;
@@ -706,7 +706,7 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb,
 		if (nlh->nlmsg_flags & NLM_F_REPLACE)
 			return -EOPNOTSUPP;
 
-		nft_ctx_init(&ctx, skb, nlh, afi, table, NULL, nla);
+		nft_ctx_init(&ctx, net, skb, nlh, afi, table, NULL, nla);
 		return nf_tables_updtable(&ctx);
 	}
 
@@ -730,7 +730,7 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb,
 	INIT_LIST_HEAD(&table->sets);
 	table->flags = flags;
 
-	nft_ctx_init(&ctx, skb, nlh, afi, table, NULL, nla);
+	nft_ctx_init(&ctx, net, skb, nlh, afi, table, NULL, nla);
 	err = nft_trans_table_add(&ctx, NFT_MSG_NEWTABLE);
 	if (err < 0)
 		goto err3;
@@ -810,18 +810,17 @@ out:
 	return err;
 }
 
-static int nf_tables_deltable(struct sock *nlsk, struct sk_buff *skb,
-			      const struct nlmsghdr *nlh,
+static int nf_tables_deltable(struct net *net, struct sock *nlsk,
+			      struct sk_buff *skb, const struct nlmsghdr *nlh,
 			      const struct nlattr * const nla[])
 {
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	struct nft_af_info *afi;
 	struct nft_table *table;
-	struct net *net = sock_net(skb->sk);
 	int family = nfmsg->nfgen_family;
 	struct nft_ctx ctx;
 
-	nft_ctx_init(&ctx, skb, nlh, NULL, NULL, NULL, nla);
+	nft_ctx_init(&ctx, net, skb, nlh, NULL, NULL, NULL, nla);
 	if (family == AF_UNSPEC || nla[NFTA_TABLE_NAME] == NULL)
 		return nft_flush(&ctx, family);
 
@@ -1221,8 +1220,8 @@ static void nf_tables_chain_destroy(struct nft_chain *chain)
 	}
 }
 
-static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
-			      const struct nlmsghdr *nlh,
+static int nf_tables_newchain(struct net *net, struct sock *nlsk,
+			      struct sk_buff *skb, const struct nlmsghdr *nlh,
 			      const struct nlattr * const nla[])
 {
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
@@ -1232,7 +1231,6 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 	struct nft_chain *chain;
 	struct nft_base_chain *basechain = NULL;
 	struct nlattr *ha[NFTA_HOOK_MAX + 1];
-	struct net *net = sock_net(skb->sk);
 	int family = nfmsg->nfgen_family;
 	struct net_device *dev = NULL;
 	u8 policy = NF_ACCEPT;
@@ -1313,7 +1311,7 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 				return PTR_ERR(stats);
 		}
 
-		nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla);
+		nft_ctx_init(&ctx, net, skb, nlh, afi, table, chain, nla);
 		trans = nft_trans_alloc(&ctx, NFT_MSG_NEWCHAIN,
 					sizeof(struct nft_trans_chain));
 		if (trans == NULL) {
@@ -1461,7 +1459,7 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 	if (err < 0)
 		goto err1;
 
-	nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla);
+	nft_ctx_init(&ctx, net, skb, nlh, afi, table, chain, nla);
 	err = nft_trans_chain_add(&ctx, NFT_MSG_NEWCHAIN);
 	if (err < 0)
 		goto err2;
@@ -1476,15 +1474,14 @@ err1:
 	return err;
 }
 
-static int nf_tables_delchain(struct sock *nlsk, struct sk_buff *skb,
-			      const struct nlmsghdr *nlh,
+static int nf_tables_delchain(struct net *net, struct sock *nlsk,
+			      struct sk_buff *skb, const struct nlmsghdr *nlh,
 			      const struct nlattr * const nla[])
 {
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	struct nft_af_info *afi;
 	struct nft_table *table;
 	struct nft_chain *chain;
-	struct net *net = sock_net(skb->sk);
 	int family = nfmsg->nfgen_family;
 	struct nft_ctx ctx;
 
@@ -1506,7 +1503,7 @@ static int nf_tables_delchain(struct sock *nlsk, struct sk_buff *skb,
 	if (chain->use > 0)
 		return -EBUSY;
 
-	nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla);
+	nft_ctx_init(&ctx, net, skb, nlh, afi, table, chain, nla);
 
 	return nft_delchain(&ctx);
 }
@@ -2010,13 +2007,12 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx,
 
 static struct nft_expr_info *info;
 
-static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
-			     const struct nlmsghdr *nlh,
+static int nf_tables_newrule(struct net *net, struct sock *nlsk,
+			     struct sk_buff *skb, const struct nlmsghdr *nlh,
 			     const struct nlattr * const nla[])
 {
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	struct nft_af_info *afi;
-	struct net *net = sock_net(skb->sk);
 	struct nft_table *table;
 	struct nft_chain *chain;
 	struct nft_rule *rule, *old_rule = NULL;
@@ -2075,7 +2071,7 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 			return PTR_ERR(old_rule);
 	}
 
-	nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla);
+	nft_ctx_init(&ctx, net, skb, nlh, afi, table, chain, nla);
 
 	n = 0;
 	size = 0;
@@ -2176,13 +2172,12 @@ err1:
 	return err;
 }
 
-static int nf_tables_delrule(struct sock *nlsk, struct sk_buff *skb,
-			     const struct nlmsghdr *nlh,
+static int nf_tables_delrule(struct net *net, struct sock *nlsk,
+			     struct sk_buff *skb, const struct nlmsghdr *nlh,
 			     const struct nlattr * const nla[])
 {
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	struct nft_af_info *afi;
-	struct net *net = sock_net(skb->sk);
 	struct nft_table *table;
 	struct nft_chain *chain = NULL;
 	struct nft_rule *rule;
@@ -2205,7 +2200,7 @@ static int nf_tables_delrule(struct sock *nlsk, struct sk_buff *skb,
 			return PTR_ERR(chain);
 	}
 
-	nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla);
+	nft_ctx_init(&ctx, net, skb, nlh, afi, table, chain, nla);
 
 	if (chain) {
 		if (nla[NFTA_RULE_HANDLE]) {
@@ -2344,12 +2339,11 @@ static const struct nla_policy nft_set_desc_policy[NFTA_SET_DESC_MAX + 1] = {
 	[NFTA_SET_DESC_SIZE]		= { .type = NLA_U32 },
 };
 
-static int nft_ctx_init_from_setattr(struct nft_ctx *ctx,
+static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, struct net *net,
 				     const struct sk_buff *skb,
 				     const struct nlmsghdr *nlh,
 				     const struct nlattr * const nla[])
 {
-	struct net *net = sock_net(skb->sk);
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	struct nft_af_info *afi = NULL;
 	struct nft_table *table = NULL;
@@ -2371,7 +2365,7 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx,
 			return -ENOENT;
 	}
 
-	nft_ctx_init(ctx, skb, nlh, afi, table, NULL, nla);
+	nft_ctx_init(ctx, net, skb, nlh, afi, table, NULL, nla);
 	return 0;
 }
 
@@ -2623,6 +2617,7 @@ static int nf_tables_getset(struct sock *nlsk, struct sk_buff *skb,
 			    const struct nlmsghdr *nlh,
 			    const struct nlattr * const nla[])
 {
+	struct net *net = sock_net(skb->sk);
 	const struct nft_set *set;
 	struct nft_ctx ctx;
 	struct sk_buff *skb2;
@@ -2630,7 +2625,7 @@ static int nf_tables_getset(struct sock *nlsk, struct sk_buff *skb,
 	int err;
 
 	/* Verify existence before starting dump */
-	err = nft_ctx_init_from_setattr(&ctx, skb, nlh, nla);
+	err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla);
 	if (err < 0)
 		return err;
 
@@ -2693,14 +2688,13 @@ static int nf_tables_set_desc_parse(const struct nft_ctx *ctx,
 	return 0;
 }
 
-static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb,
-			    const struct nlmsghdr *nlh,
+static int nf_tables_newset(struct net *net, struct sock *nlsk,
+			    struct sk_buff *skb, const struct nlmsghdr *nlh,
 			    const struct nlattr * const nla[])
 {
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	const struct nft_set_ops *ops;
 	struct nft_af_info *afi;
-	struct net *net = sock_net(skb->sk);
 	struct nft_table *table;
 	struct nft_set *set;
 	struct nft_ctx ctx;
@@ -2798,7 +2792,7 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb,
 	if (IS_ERR(table))
 		return PTR_ERR(table);
 
-	nft_ctx_init(&ctx, skb, nlh, afi, table, NULL, nla);
+	nft_ctx_init(&ctx, net, skb, nlh, afi, table, NULL, nla);
 
 	set = nf_tables_set_lookup(table, nla[NFTA_SET_NAME]);
 	if (IS_ERR(set)) {
@@ -2882,8 +2876,8 @@ static void nf_tables_set_destroy(const struct nft_ctx *ctx, struct nft_set *set
 	nft_set_destroy(set);
 }
 
-static int nf_tables_delset(struct sock *nlsk, struct sk_buff *skb,
-			    const struct nlmsghdr *nlh,
+static int nf_tables_delset(struct net *net, struct sock *nlsk,
+			    struct sk_buff *skb, const struct nlmsghdr *nlh,
 			    const struct nlattr * const nla[])
 {
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
@@ -2896,7 +2890,7 @@ static int nf_tables_delset(struct sock *nlsk, struct sk_buff *skb,
 	if (nla[NFTA_SET_TABLE] == NULL)
 		return -EINVAL;
 
-	err = nft_ctx_init_from_setattr(&ctx, skb, nlh, nla);
+	err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla);
 	if (err < 0)
 		return err;
 
@@ -3024,7 +3018,7 @@ static const struct nla_policy nft_set_elem_list_policy[NFTA_SET_ELEM_LIST_MAX +
 	[NFTA_SET_ELEM_LIST_SET_ID]	= { .type = NLA_U32 },
 };
 
-static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx,
+static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx, struct net *net,
 				      const struct sk_buff *skb,
 				      const struct nlmsghdr *nlh,
 				      const struct nlattr * const nla[],
@@ -3033,7 +3027,6 @@ static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx,
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	struct nft_af_info *afi;
 	struct nft_table *table;
-	struct net *net = sock_net(skb->sk);
 
 	afi = nf_tables_afinfo_lookup(net, nfmsg->nfgen_family, false);
 	if (IS_ERR(afi))
@@ -3045,7 +3038,7 @@ static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx,
 	if (!trans && (table->flags & NFT_TABLE_INACTIVE))
 		return -ENOENT;
 
-	nft_ctx_init(ctx, skb, nlh, afi, table, NULL, nla);
+	nft_ctx_init(ctx, net, skb, nlh, afi, table, NULL, nla);
 	return 0;
 }
 
@@ -3135,6 +3128,7 @@ static int nf_tables_dump_setelem(const struct nft_ctx *ctx,
 
 static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
 {
+	struct net *net = sock_net(skb->sk);
 	const struct nft_set *set;
 	struct nft_set_dump_args args;
 	struct nft_ctx ctx;
@@ -3150,8 +3144,8 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
 	if (err < 0)
 		return err;
 
-	err = nft_ctx_init_from_elemattr(&ctx, cb->skb, cb->nlh, (void *)nla,
-					 false);
+	err = nft_ctx_init_from_elemattr(&ctx, net, cb->skb, cb->nlh,
+					 (void *)nla, false);
 	if (err < 0)
 		return err;
 
@@ -3212,11 +3206,12 @@ static int nf_tables_getsetelem(struct sock *nlsk, struct sk_buff *skb,
 				const struct nlmsghdr *nlh,
 				const struct nlattr * const nla[])
 {
+	struct net *net = sock_net(skb->sk);
 	const struct nft_set *set;
 	struct nft_ctx ctx;
 	int err;
 
-	err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla, false);
+	err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, false);
 	if (err < 0)
 		return err;
 
@@ -3528,11 +3523,10 @@ err1:
 	return err;
 }
 
-static int nf_tables_newsetelem(struct sock *nlsk, struct sk_buff *skb,
-				const struct nlmsghdr *nlh,
+static int nf_tables_newsetelem(struct net *net, struct sock *nlsk,
+				struct sk_buff *skb, const struct nlmsghdr *nlh,
 				const struct nlattr * const nla[])
 {
-	struct net *net = sock_net(skb->sk);
 	const struct nlattr *attr;
 	struct nft_set *set;
 	struct nft_ctx ctx;
@@ -3541,7 +3535,7 @@ static int nf_tables_newsetelem(struct sock *nlsk, struct sk_buff *skb,
 	if (nla[NFTA_SET_ELEM_LIST_ELEMENTS] == NULL)
 		return -EINVAL;
 
-	err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla, true);
+	err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, true);
 	if (err < 0)
 		return err;
 
@@ -3623,8 +3617,8 @@ err1:
 	return err;
 }
 
-static int nf_tables_delsetelem(struct sock *nlsk, struct sk_buff *skb,
-				const struct nlmsghdr *nlh,
+static int nf_tables_delsetelem(struct net *net, struct sock *nlsk,
+				struct sk_buff *skb, const struct nlmsghdr *nlh,
 				const struct nlattr * const nla[])
 {
 	const struct nlattr *attr;
@@ -3635,7 +3629,7 @@ static int nf_tables_delsetelem(struct sock *nlsk, struct sk_buff *skb,
 	if (nla[NFTA_SET_ELEM_LIST_ELEMENTS] == NULL)
 		return -EINVAL;
 
-	err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla, false);
+	err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, false);
 	if (err < 0)
 		return err;
 
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 46453ab318db..445590f2c673 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -381,7 +381,7 @@ replay:
 				goto ack;
 
 			if (nc->call_batch) {
-				err = nc->call_batch(net->nfnl, skb, nlh,
+				err = nc->call_batch(net, net->nfnl, skb, nlh,
 						     (const struct nlattr **)cda);
 			}
 
-- 
cgit v1.2.3


From 059393c5bdd1420bdf1bed2972f33196dff263ae Mon Sep 17 00:00:00 2001
From: Marc Zyngier
Date: Mon, 7 Dec 2015 10:11:11 +0000
Subject: irqchip/gic-v3: Add missing struct device_node declaration

When the GICv3 header file is used in a C file that doesn't include
any of the OF stuff, we end up with a bunch of ugly warnings.

Let's keep GCC quiet by adding a forward declaration.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Cc: <linux-arm-kernel@lists.infradead.org>
Cc: Jason Cooper <jason@lakedaemon.net>
Link: http://lkml.kernel.org/r/1449483072-17694-2-git-send-email-marc.zyngier@arm.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irqchip/arm-gic-v3.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index c9ae0c6ec050..d5d798b35c1f 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -330,6 +330,7 @@ struct rdists {
 };
 
 struct irq_domain;
+struct device_node;
 int its_cpu_init(void);
 int its_init(struct device_node *node, struct rdists *rdists,
 	     struct irq_domain *domain);
-- 
cgit v1.2.3


From 5e1033561da1152c57b97ee84371dba2b3d64c25 Mon Sep 17 00:00:00 2001
From: James Bottomley
Date: Fri, 11 Dec 2015 09:16:38 -0800
Subject: ses: fix additional element traversal bug

KASAN found that our additional element processing scripts drop off
the end of the VPD page into unallocated space.  The reason is that
not every element has additional information but our traversal
routines think they do, leading to them expecting far more additional
information than is present.  Fix this by adding a gate to the
traversal routine so that it only processes elements that are expected
to have additional information (list is in SES-2 section 6.1.13.1:
Additional Element Status diagnostic page overview)

Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Tested-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Cc: stable@vger.kernel.org
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
---
 drivers/scsi/ses.c        | 10 +++++++++-
 include/linux/enclosure.h |  4 ++++
 2 files changed, 13 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c
index 7d9cec50b77d..044d06410d4c 100644
--- a/drivers/scsi/ses.c
+++ b/drivers/scsi/ses.c
@@ -559,7 +559,15 @@ static void ses_enclosure_data_process(struct enclosure_device *edev,
 			if (desc_ptr)
 				desc_ptr += len;
 
-			if (addl_desc_ptr)
+			if (addl_desc_ptr &&
+			    /* only find additional descriptions for specific devices */
+			    (type_ptr[0] == ENCLOSURE_COMPONENT_DEVICE ||
+			     type_ptr[0] == ENCLOSURE_COMPONENT_ARRAY_DEVICE ||
+			     type_ptr[0] == ENCLOSURE_COMPONENT_SAS_EXPANDER ||
+			     /* these elements are optional */
+			     type_ptr[0] == ENCLOSURE_COMPONENT_SCSI_TARGET_PORT ||
+			     type_ptr[0] == ENCLOSURE_COMPONENT_SCSI_INITIATOR_PORT ||
+			     type_ptr[0] == ENCLOSURE_COMPONENT_CONTROLLER_ELECTRONICS))
 				addl_desc_ptr += addl_desc_ptr[1] + 2;
 
 		}
diff --git a/include/linux/enclosure.h b/include/linux/enclosure.h
index 7be22da321f3..a4cf57cd0f75 100644
--- a/include/linux/enclosure.h
+++ b/include/linux/enclosure.h
@@ -29,7 +29,11 @@
 /* A few generic types ... taken from ses-2 */
 enum enclosure_component_type {
 	ENCLOSURE_COMPONENT_DEVICE = 0x01,
+	ENCLOSURE_COMPONENT_CONTROLLER_ELECTRONICS = 0x07,
+	ENCLOSURE_COMPONENT_SCSI_TARGET_PORT = 0x14,
+	ENCLOSURE_COMPONENT_SCSI_INITIATOR_PORT = 0x15,
 	ENCLOSURE_COMPONENT_ARRAY_DEVICE = 0x17,
+	ENCLOSURE_COMPONENT_SAS_EXPANDER = 0x18,
 };
 
 /* ses-2 common element status */
-- 
cgit v1.2.3


From ad87e03213b552a5c33d5e1e7a19a73768397010 Mon Sep 17 00:00:00 2001
From: Alan Stern
Date: Thu, 10 Dec 2015 15:27:21 -0500
Subject: USB: add quirk for devices with broken LPM

Some USB device / host controller combinations seem to have problems
with Link Power Management.  For example, Steinar found that his xHCI
controller wouldn't handle bandwidth calculations correctly for two
video cards simultaneously when LPM was enabled, even though the bus
had plenty of bandwidth available.

This patch introduces a new quirk flag for devices that should remain
disabled for LPM, and creates quirk entries for Steinar's devices.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Reported-by: Steinar H. Gunderson <sgunderson@bigfoot.com>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hub.c     | 7 ++++++-
 drivers/usb/core/quirks.c  | 6 ++++++
 include/linux/usb/quirks.h | 3 +++
 3 files changed, 15 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 585c3cb07da6..a5cc032ef77a 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -124,6 +124,10 @@ struct usb_hub *usb_hub_to_struct_hub(struct usb_device *hdev)
 
 int usb_device_supports_lpm(struct usb_device *udev)
 {
+	/* Some devices have trouble with LPM */
+	if (udev->quirks & USB_QUIRK_NO_LPM)
+		return 0;
+
 	/* USB 2.1 (and greater) devices indicate LPM support through
 	 * their USB 2.0 Extended Capabilities BOS descriptor.
 	 */
@@ -4512,6 +4516,8 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1,
 		goto fail;
 	}
 
+	usb_detect_quirks(udev);
+
 	if (udev->wusb == 0 && le16_to_cpu(udev->descriptor.bcdUSB) >= 0x0201) {
 		retval = usb_get_bos_descriptor(udev);
 		if (!retval) {
@@ -4710,7 +4716,6 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus,
 		if (status < 0)
 			goto loop;
 
-		usb_detect_quirks(udev);
 		if (udev->quirks & USB_QUIRK_DELAY_INIT)
 			msleep(1000);
 
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index fcd6ac0c667f..6dc810bce295 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -202,6 +202,12 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x1a0a, 0x0200), .driver_info =
 			USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL },
 
+	/* Blackmagic Design Intensity Shuttle */
+	{ USB_DEVICE(0x1edb, 0xbd3b), .driver_info = USB_QUIRK_NO_LPM },
+
+	/* Blackmagic Design UltraStudio SDI */
+	{ USB_DEVICE(0x1edb, 0xbd4f), .driver_info = USB_QUIRK_NO_LPM },
+
 	{ }  /* terminating entry must be last */
 };
 
diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h
index 9948c874e3f1..1d0043dc34e4 100644
--- a/include/linux/usb/quirks.h
+++ b/include/linux/usb/quirks.h
@@ -47,4 +47,7 @@
 /* device generates spurious wakeup, ignore remote wakeup capability */
 #define USB_QUIRK_IGNORE_REMOTE_WAKEUP		BIT(9)
 
+/* device can't handle Link Power Management */
+#define USB_QUIRK_NO_LPM			BIT(10)
+
 #endif /* __LINUX_USB_QUIRKS_H */
-- 
cgit v1.2.3


From 98e89cf02aed11166698dd53c6f14865613babb3 Mon Sep 17 00:00:00 2001
From: Nicolas Iooss
Date: Fri, 11 Dec 2015 13:40:43 -0800
Subject: mm: kmemleak: mark kmemleak_init prototype as __init

The kmemleak_init() definition in mm/kmemleak.c is marked __init but its
prototype in include/linux/kmemleak.h is marked __ref since commit
a6186d89c913 ("kmemleak: Mark the early log buffer as __initdata").

This causes a section mismatch which is reported as a warning when
building with clang -Wsection, because kmemleak_init() is declared in
section .ref.text but defined in .init.text.

Fix this by marking kmemleak_init() prototype __init.

Signed-off-by: Nicolas Iooss <nicolas.iooss_linux@m4x.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kmemleak.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/kmemleak.h b/include/linux/kmemleak.h
index d0a1f99e24e3..4894c6888bc6 100644
--- a/include/linux/kmemleak.h
+++ b/include/linux/kmemleak.h
@@ -25,7 +25,7 @@
 
 #ifdef CONFIG_DEBUG_KMEMLEAK
 
-extern void kmemleak_init(void) __ref;
+extern void kmemleak_init(void) __init;
 extern void kmemleak_alloc(const void *ptr, size_t size, int min_count,
 			   gfp_t gfp) __ref;
 extern void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size,
-- 
cgit v1.2.3


From 86fffe4a61dd972d5a4e23260d530be6da02f614 Mon Sep 17 00:00:00 2001
From: Chris Wilson
Date: Fri, 11 Dec 2015 13:40:46 -0800
Subject: kernel: remove stop_machine() Kconfig dependency

Currently the full stop_machine() routine is only enabled on SMP if
module unloading is enabled, or if the CPUs are hotpluggable.  This
leads to configurations where stop_machine() is broken as it will then
only run the callback on the local CPU with irqs disabled, and not stop
the other CPUs or run the callback on them.

For example, this breaks MTRR setup on x86 in certain configs since
ea8596bb2d8d379 ("kprobes/x86: Remove unused text_poke_smp() and
text_poke_smp_batch() functions") as the MTRR is only established on the
boot CPU.

This patch removes the Kconfig option for STOP_MACHINE and uses the SMP
and HOTPLUG_CPU config options to compile the correct stop_machine() for
the architecture, removing the false dependency on MODULE_UNLOAD in the
process.

Link: https://lkml.org/lkml/2014/10/8/124
References: https://bugs.freedesktop.org/show_bug.cgi?id=84794
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Pranith Kumar <bobby.prani@gmail.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: H. Peter Anvin <hpa@linux.intel.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Iulia Manda <iulia.manda21@gmail.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Chuck Ebbert <cebbert.lkml@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/stop_machine.h | 6 +++---
 init/Kconfig                 | 7 -------
 kernel/stop_machine.c        | 4 ++--
 3 files changed, 5 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h
index 0adedca24c5b..0e1b1540597a 100644
--- a/include/linux/stop_machine.h
+++ b/include/linux/stop_machine.h
@@ -99,7 +99,7 @@ static inline int try_stop_cpus(const struct cpumask *cpumask,
  * grabbing every spinlock (and more).  So the "read" side to such a
  * lock is anything which disables preemption.
  */
-#if defined(CONFIG_STOP_MACHINE) && defined(CONFIG_SMP)
+#if defined(CONFIG_SMP) || defined(CONFIG_HOTPLUG_CPU)
 
 /**
  * stop_machine: freeze the machine on all CPUs and run this function
@@ -118,7 +118,7 @@ int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus);
 
 int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data,
 				   const struct cpumask *cpus);
-#else	 /* CONFIG_STOP_MACHINE && CONFIG_SMP */
+#else	/* CONFIG_SMP || CONFIG_HOTPLUG_CPU */
 
 static inline int stop_machine(cpu_stop_fn_t fn, void *data,
 				 const struct cpumask *cpus)
@@ -137,5 +137,5 @@ static inline int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data,
 	return stop_machine(fn, data, cpus);
 }
 
-#endif	/* CONFIG_STOP_MACHINE && CONFIG_SMP */
+#endif	/* CONFIG_SMP || CONFIG_HOTPLUG_CPU */
 #endif	/* _LINUX_STOP_MACHINE */
diff --git a/init/Kconfig b/init/Kconfig
index c24b6f767bf0..235c7a2c0d20 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -2030,13 +2030,6 @@ config INIT_ALL_POSSIBLE
 	  it was better to provide this option than to break all the archs
 	  and have several arch maintainers pursuing me down dark alleys.
 
-config STOP_MACHINE
-	bool
-	default y
-	depends on (SMP && MODULE_UNLOAD) || HOTPLUG_CPU
-	help
-	  Need stop_machine() primitive.
-
 source "block/Kconfig"
 
 config PREEMPT_NOTIFIERS
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 867bc20e1ef1..a3bbaee77c58 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -531,7 +531,7 @@ static int __init cpu_stop_init(void)
 }
 early_initcall(cpu_stop_init);
 
-#ifdef CONFIG_STOP_MACHINE
+#if defined(CONFIG_SMP) || defined(CONFIG_HOTPLUG_CPU)
 
 static int __stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus)
 {
@@ -631,4 +631,4 @@ int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data,
 	return ret ?: done.ret;
 }
 
-#endif	/* CONFIG_STOP_MACHINE */
+#endif	/* CONFIG_SMP || CONFIG_HOTPLUG_CPU */
-- 
cgit v1.2.3


From dfd01f026058a59a513f8a365b439a0681b803af Mon Sep 17 00:00:00 2001
From: Peter Zijlstra
Date: Sun, 13 Dec 2015 22:11:16 +0100
Subject: sched/wait: Fix the signal handling fix

Jan Stancek reported that I wrecked things for him by fixing things for
Vladimir :/

His report was due to an UNINTERRUPTIBLE wait getting -EINTR, which
should not be possible, however my previous patch made this possible by
unconditionally checking signal_pending().

We cannot use current->state as was done previously, because the
instruction after the store to that variable it can be changed.  We must
instead pass the initial state along and use that.

Fixes: 68985633bccb ("sched/wait: Fix signal handling in bit wait helpers")
Reported-by: Jan Stancek <jstancek@redhat.com>
Reported-by: Chris Mason <clm@fb.com>
Tested-by: Jan Stancek <jstancek@redhat.com>
Tested-by: Vladimir Murzin <vladimir.murzin@arm.com>
Tested-by: Chris Mason <clm@fb.com>
Reviewed-by: Paul Turner <pjt@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: tglx@linutronix.de
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: hpa@zytor.com
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/cifs/inode.c      |  6 +++---
 fs/nfs/inode.c       |  6 +++---
 fs/nfs/internal.h    |  2 +-
 fs/nfs/pagelist.c    |  2 +-
 fs/nfs/pnfs.c        |  4 ++--
 include/linux/wait.h | 10 +++++-----
 kernel/sched/wait.c  | 20 ++++++++++----------
 net/sunrpc/sched.c   |  6 +++---
 8 files changed, 28 insertions(+), 28 deletions(-)

(limited to 'include/linux')

diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 6b66dd5d1540..a329f5ba35aa 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -1831,11 +1831,11 @@ cifs_invalidate_mapping(struct inode *inode)
  * @word: long word containing the bit lock
  */
 static int
-cifs_wait_bit_killable(struct wait_bit_key *key)
+cifs_wait_bit_killable(struct wait_bit_key *key, int mode)
 {
-	if (fatal_signal_pending(current))
-		return -ERESTARTSYS;
 	freezable_schedule_unsafe();
+	if (signal_pending_state(mode, current))
+		return -ERESTARTSYS;
 	return 0;
 }
 
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 31b0a52223a7..c7e8b87da5b2 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -75,11 +75,11 @@ nfs_fattr_to_ino_t(struct nfs_fattr *fattr)
  * nfs_wait_bit_killable - helper for functions that are sleeping on bit locks
  * @word: long word containing the bit lock
  */
-int nfs_wait_bit_killable(struct wait_bit_key *key)
+int nfs_wait_bit_killable(struct wait_bit_key *key, int mode)
 {
-	if (fatal_signal_pending(current))
-		return -ERESTARTSYS;
 	freezable_schedule_unsafe();
+	if (signal_pending_state(mode, current))
+		return -ERESTARTSYS;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(nfs_wait_bit_killable);
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 56cfde26fb9c..9dea85f7f918 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -379,7 +379,7 @@ extern int nfs_drop_inode(struct inode *);
 extern void nfs_clear_inode(struct inode *);
 extern void nfs_evict_inode(struct inode *);
 void nfs_zap_acl_cache(struct inode *inode);
-extern int nfs_wait_bit_killable(struct wait_bit_key *key);
+extern int nfs_wait_bit_killable(struct wait_bit_key *key, int mode);
 
 /* super.c */
 extern const struct super_operations nfs_sops;
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index fe3ddd20ff89..452a011ba0d8 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -129,7 +129,7 @@ __nfs_iocounter_wait(struct nfs_io_counter *c)
 		set_bit(NFS_IO_INPROGRESS, &c->flags);
 		if (atomic_read(&c->io_count) == 0)
 			break;
-		ret = nfs_wait_bit_killable(&q.key);
+		ret = nfs_wait_bit_killable(&q.key, TASK_KILLABLE);
 	} while (atomic_read(&c->io_count) != 0 && !ret);
 	finish_wait(wq, &q.wait);
 	return ret;
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 5a8ae2125b50..bec0384499f7 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1466,11 +1466,11 @@ static bool pnfs_within_mdsthreshold(struct nfs_open_context *ctx,
 }
 
 /* stop waiting if someone clears NFS_LAYOUT_RETRY_LAYOUTGET bit. */
-static int pnfs_layoutget_retry_bit_wait(struct wait_bit_key *key)
+static int pnfs_layoutget_retry_bit_wait(struct wait_bit_key *key, int mode)
 {
 	if (!test_bit(NFS_LAYOUT_RETRY_LAYOUTGET, key->flags))
 		return 1;
-	return nfs_wait_bit_killable(key);
+	return nfs_wait_bit_killable(key, mode);
 }
 
 static bool pnfs_prepare_to_retry_layoutget(struct pnfs_layout_hdr *lo)
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 1e1bf9f963a9..513b36f04dfd 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -145,7 +145,7 @@ __remove_wait_queue(wait_queue_head_t *head, wait_queue_t *old)
 	list_del(&old->task_list);
 }
 
-typedef int wait_bit_action_f(struct wait_bit_key *);
+typedef int wait_bit_action_f(struct wait_bit_key *, int mode);
 void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
 void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key);
 void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
@@ -960,10 +960,10 @@ int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
 	} while (0)
 
 
-extern int bit_wait(struct wait_bit_key *);
-extern int bit_wait_io(struct wait_bit_key *);
-extern int bit_wait_timeout(struct wait_bit_key *);
-extern int bit_wait_io_timeout(struct wait_bit_key *);
+extern int bit_wait(struct wait_bit_key *, int);
+extern int bit_wait_io(struct wait_bit_key *, int);
+extern int bit_wait_timeout(struct wait_bit_key *, int);
+extern int bit_wait_io_timeout(struct wait_bit_key *, int);
 
 /**
  * wait_on_bit - wait for a bit to be cleared
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index f10bd873e684..f15d6b6a538a 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -392,7 +392,7 @@ __wait_on_bit(wait_queue_head_t *wq, struct wait_bit_queue *q,
 	do {
 		prepare_to_wait(wq, &q->wait, mode);
 		if (test_bit(q->key.bit_nr, q->key.flags))
-			ret = (*action)(&q->key);
+			ret = (*action)(&q->key, mode);
 	} while (test_bit(q->key.bit_nr, q->key.flags) && !ret);
 	finish_wait(wq, &q->wait);
 	return ret;
@@ -431,7 +431,7 @@ __wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q,
 		prepare_to_wait_exclusive(wq, &q->wait, mode);
 		if (!test_bit(q->key.bit_nr, q->key.flags))
 			continue;
-		ret = action(&q->key);
+		ret = action(&q->key, mode);
 		if (!ret)
 			continue;
 		abort_exclusive_wait(wq, &q->wait, mode, &q->key);
@@ -581,43 +581,43 @@ void wake_up_atomic_t(atomic_t *p)
 }
 EXPORT_SYMBOL(wake_up_atomic_t);
 
-__sched int bit_wait(struct wait_bit_key *word)
+__sched int bit_wait(struct wait_bit_key *word, int mode)
 {
 	schedule();
-	if (signal_pending(current))
+	if (signal_pending_state(mode, current))
 		return -EINTR;
 	return 0;
 }
 EXPORT_SYMBOL(bit_wait);
 
-__sched int bit_wait_io(struct wait_bit_key *word)
+__sched int bit_wait_io(struct wait_bit_key *word, int mode)
 {
 	io_schedule();
-	if (signal_pending(current))
+	if (signal_pending_state(mode, current))
 		return -EINTR;
 	return 0;
 }
 EXPORT_SYMBOL(bit_wait_io);
 
-__sched int bit_wait_timeout(struct wait_bit_key *word)
+__sched int bit_wait_timeout(struct wait_bit_key *word, int mode)
 {
 	unsigned long now = READ_ONCE(jiffies);
 	if (time_after_eq(now, word->timeout))
 		return -EAGAIN;
 	schedule_timeout(word->timeout - now);
-	if (signal_pending(current))
+	if (signal_pending_state(mode, current))
 		return -EINTR;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(bit_wait_timeout);
 
-__sched int bit_wait_io_timeout(struct wait_bit_key *word)
+__sched int bit_wait_io_timeout(struct wait_bit_key *word, int mode)
 {
 	unsigned long now = READ_ONCE(jiffies);
 	if (time_after_eq(now, word->timeout))
 		return -EAGAIN;
 	io_schedule_timeout(word->timeout - now);
-	if (signal_pending(current))
+	if (signal_pending_state(mode, current))
 		return -EINTR;
 	return 0;
 }
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index f14f24ee9983..73ad57a59989 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -250,11 +250,11 @@ void rpc_destroy_wait_queue(struct rpc_wait_queue *queue)
 }
 EXPORT_SYMBOL_GPL(rpc_destroy_wait_queue);
 
-static int rpc_wait_bit_killable(struct wait_bit_key *key)
+static int rpc_wait_bit_killable(struct wait_bit_key *key, int mode)
 {
-	if (fatal_signal_pending(current))
-		return -ERESTARTSYS;
 	freezable_schedule_unsafe();
+	if (signal_pending_state(mode, current))
+		return -ERESTARTSYS;
 	return 0;
 }
 
-- 
cgit v1.2.3


From 1d5cda4076d930d6d52088ed2c7753f7c564cbd7 Mon Sep 17 00:00:00 2001
From: James Morse
Date: Fri, 18 Dec 2015 14:22:07 -0800
Subject: include/linux/mmdebug.h: should include linux/bug.h

mmdebug.h uses BUILD_BUG_ON_INVALID(), assuming someone else included
linux/bug.h.  Include it ourselves.

This saves build-failures such as:

  arch/arm64/include/asm/pgtable.h: In function 'set_pte_at':
  arch/arm64/include/asm/pgtable.h:281:3: error: implicit declaration of function 'BUILD_BUG_ON_INVALID' [-Werror=implicit-function-declaration]
   VM_WARN_ONCE(!pte_young(pte),

Fixes: 02602a18c32d7 ("bug: completely remove code generated by disabled VM_BUG_ON()")
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmdebug.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h
index 877ef226f90f..772362adf471 100644
--- a/include/linux/mmdebug.h
+++ b/include/linux/mmdebug.h
@@ -1,6 +1,7 @@
 #ifndef LINUX_MM_DEBUG_H
 #define LINUX_MM_DEBUG_H 1
 
+#include <linux/bug.h>
 #include <linux/stringify.h>
 
 struct page;
-- 
cgit v1.2.3


From 1dfddff5fcd869fcab0c52fafae099dfa435a935 Mon Sep 17 00:00:00 2001
From: Bjørn Mork
Date: Wed, 23 Dec 2015 13:42:43 +0100
Subject: net: cdc_ncm: avoid changing RX/TX buffers on MTU changes

NCM buffer sizes are negotiated with the device independently of
the network device MTU.  The RX buffers are allocated by the
usbnet framework based on the rx_urb_size value set by cdc_ncm. A
single RX buffer can hold a number of MTU sized packets.

The default usbnet change_mtu ndo only modifies rx_urb_size if it
is equal to hard_mtu.  And the cdc_ncm driver will set rx_urb_size
and hard_mtu independently of each other, based on dwNtbInMaxSize
and dwNtbOutMaxSize respectively. It was therefore assumed that
usbnet_change_mtu() would never touch rx_urb_size.  This failed to
consider the case where dwNtbInMaxSize and dwNtbOutMaxSize happens
to be equal.

Fix by implementing an NCM specific change_mtu ndo, modifying the
netdev MTU without touching the buffer size settings.

Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_mbim.c  |  2 +-
 drivers/net/usb/cdc_ncm.c   | 31 +++++++++++++++++++++++++++++++
 include/linux/usb/cdc_ncm.h |  1 +
 3 files changed, 33 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c
index 8973abdec9f6..bdd83d95ec0a 100644
--- a/drivers/net/usb/cdc_mbim.c
+++ b/drivers/net/usb/cdc_mbim.c
@@ -100,7 +100,7 @@ static const struct net_device_ops cdc_mbim_netdev_ops = {
 	.ndo_stop             = usbnet_stop,
 	.ndo_start_xmit       = usbnet_start_xmit,
 	.ndo_tx_timeout       = usbnet_tx_timeout,
-	.ndo_change_mtu       = usbnet_change_mtu,
+	.ndo_change_mtu       = cdc_ncm_change_mtu,
 	.ndo_set_mac_address  = eth_mac_addr,
 	.ndo_validate_addr    = eth_validate_addr,
 	.ndo_vlan_rx_add_vid  = cdc_mbim_rx_add_vid,
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 369405271437..e8a1144c5a8b 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -41,6 +41,7 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/ctype.h>
+#include <linux/etherdevice.h>
 #include <linux/ethtool.h>
 #include <linux/workqueue.h>
 #include <linux/mii.h>
@@ -689,6 +690,33 @@ static void cdc_ncm_free(struct cdc_ncm_ctx *ctx)
 	kfree(ctx);
 }
 
+/* we need to override the usbnet change_mtu ndo for two reasons:
+ *  - respect the negotiated maximum datagram size
+ *  - avoid unwanted changes to rx and tx buffers
+ */
+int cdc_ncm_change_mtu(struct net_device *net, int new_mtu)
+{
+	struct usbnet *dev = netdev_priv(net);
+	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
+	int maxmtu = ctx->max_datagram_size - cdc_ncm_eth_hlen(dev);
+
+	if (new_mtu <= 0 || new_mtu > maxmtu)
+		return -EINVAL;
+	net->mtu = new_mtu;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cdc_ncm_change_mtu);
+
+static const struct net_device_ops cdc_ncm_netdev_ops = {
+	.ndo_open	     = usbnet_open,
+	.ndo_stop	     = usbnet_stop,
+	.ndo_start_xmit	     = usbnet_start_xmit,
+	.ndo_tx_timeout	     = usbnet_tx_timeout,
+	.ndo_change_mtu	     = cdc_ncm_change_mtu,
+	.ndo_set_mac_address = eth_mac_addr,
+	.ndo_validate_addr   = eth_validate_addr,
+};
+
 int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting, int drvflags)
 {
 	struct cdc_ncm_ctx *ctx;
@@ -823,6 +851,9 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_
 	/* add our sysfs attrs */
 	dev->net->sysfs_groups[0] = &cdc_ncm_sysfs_attr_group;
 
+	/* must handle MTU changes */
+	dev->net->netdev_ops = &cdc_ncm_netdev_ops;
+
 	return 0;
 
 error2:
diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h
index 1f6526c76ee8..3a375d07d0dc 100644
--- a/include/linux/usb/cdc_ncm.h
+++ b/include/linux/usb/cdc_ncm.h
@@ -138,6 +138,7 @@ struct cdc_ncm_ctx {
 };
 
 u8 cdc_ncm_select_altsetting(struct usb_interface *intf);
+int cdc_ncm_change_mtu(struct net_device *net, int new_mtu);
 int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting, int drvflags);
 void cdc_ncm_unbind(struct usbnet *dev, struct usb_interface *intf);
 struct sk_buff *cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign);
-- 
cgit v1.2.3


From 21491412f2ec6f13d4104de734dec0ba659d092e Mon Sep 17 00:00:00 2001
From: Jens Axboe
Date: Mon, 28 Dec 2015 13:01:22 -0700
Subject: block: add blk_start_queue_async()

We currently only have an inline/sync helper to restart a stopped
queue. If drivers need an async version, they have to roll their
own. Add a generic helper instead.

Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-core.c       | 16 ++++++++++++++++
 include/linux/blkdev.h |  1 +
 2 files changed, 17 insertions(+)

(limited to 'include/linux')

diff --git a/block/blk-core.c b/block/blk-core.c
index c487b94c59e3..33e2f62d5062 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -206,6 +206,22 @@ void blk_delay_queue(struct request_queue *q, unsigned long msecs)
 }
 EXPORT_SYMBOL(blk_delay_queue);
 
+/**
+ * blk_start_queue_async - asynchronously restart a previously stopped queue
+ * @q:    The &struct request_queue in question
+ *
+ * Description:
+ *   blk_start_queue_async() will clear the stop flag on the queue, and
+ *   ensure that the request_fn for the queue is run from an async
+ *   context.
+ **/
+void blk_start_queue_async(struct request_queue *q)
+{
+	queue_flag_clear(QUEUE_FLAG_STOPPED, q);
+	blk_run_queue_async(q);
+}
+EXPORT_SYMBOL(blk_start_queue_async);
+
 /**
  * blk_start_queue - restart a previously stopped queue
  * @q:    The &struct request_queue in question
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 0169ba2e2e64..c70e3588a48c 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -797,6 +797,7 @@ extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t,
 extern int blk_queue_enter(struct request_queue *q, gfp_t gfp);
 extern void blk_queue_exit(struct request_queue *q);
 extern void blk_start_queue(struct request_queue *q);
+extern void blk_start_queue_async(struct request_queue *q);
 extern void blk_stop_queue(struct request_queue *q);
 extern void blk_sync_queue(struct request_queue *q);
 extern void __blk_stop_queue(struct request_queue *q);
-- 
cgit v1.2.3


From 6cdb18ad98a49f7e9b95d538a0614cde827404b8 Mon Sep 17 00:00:00 2001
From: Heiko Carstens
Date: Tue, 29 Dec 2015 14:54:32 -0800
Subject: mm/vmstat: fix overflow in mod_zone_page_state()

mod_zone_page_state() takes a "delta" integer argument.  delta contains
the number of pages that should be added or subtracted from a struct
zone's vm_stat field.

If a zone is larger than 8TB this will cause overflows.  E.g.  for a
zone with a size slightly larger than 8TB the line

    mod_zone_page_state(zone, NR_ALLOC_BATCH, zone->managed_pages);

in mm/page_alloc.c:free_area_init_core() will result in a negative
result for the NR_ALLOC_BATCH entry within the zone's vm_stat, since 8TB
contain 0x8xxxxxxx pages which will be sign extended to a negative
value.

Fix this by changing the delta argument to long type.

This could fix an early boot problem seen on s390, where we have a 9TB
system with only one node.  ZONE_DMA contains 2GB and ZONE_NORMAL the
rest.  The system is trying to allocate a GFP_DMA page but ZONE_DMA is
completely empty, so it tries to reclaim pages in an endless loop.

This was seen on a heavily patched 3.10 kernel.  One possible
explaination seem to be the overflows caused by mod_zone_page_state().
Unfortunately I did not have the chance to verify that this patch
actually fixes the problem, since I don't have access to the system
right now.  However the overflow problem does exist anyway.

Given the description that a system with slightly less than 8TB does
work, this seems to be a candidate for the observed problem.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/vmstat.h |  6 +++---
 mm/vmstat.c            | 10 +++++-----
 2 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 5dbc8b0ee567..3e5d9075960f 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -176,11 +176,11 @@ extern void zone_statistics(struct zone *, struct zone *, gfp_t gfp);
 #define sub_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, -(__d))
 
 #ifdef CONFIG_SMP
-void __mod_zone_page_state(struct zone *, enum zone_stat_item item, int);
+void __mod_zone_page_state(struct zone *, enum zone_stat_item item, long);
 void __inc_zone_page_state(struct page *, enum zone_stat_item);
 void __dec_zone_page_state(struct page *, enum zone_stat_item);
 
-void mod_zone_page_state(struct zone *, enum zone_stat_item, int);
+void mod_zone_page_state(struct zone *, enum zone_stat_item, long);
 void inc_zone_page_state(struct page *, enum zone_stat_item);
 void dec_zone_page_state(struct page *, enum zone_stat_item);
 
@@ -205,7 +205,7 @@ void set_pgdat_percpu_threshold(pg_data_t *pgdat,
  * The functions directly modify the zone and global counters.
  */
 static inline void __mod_zone_page_state(struct zone *zone,
-			enum zone_stat_item item, int delta)
+			enum zone_stat_item item, long delta)
 {
 	zone_page_state_add(delta, zone, item);
 }
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 0d5712b0206c..4ebc17d948cb 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -219,7 +219,7 @@ void set_pgdat_percpu_threshold(pg_data_t *pgdat,
  * particular counter cannot be updated from interrupt context.
  */
 void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
-				int delta)
+			   long delta)
 {
 	struct per_cpu_pageset __percpu *pcp = zone->pageset;
 	s8 __percpu *p = pcp->vm_stat_diff + item;
@@ -318,8 +318,8 @@ EXPORT_SYMBOL(__dec_zone_page_state);
  *     1       Overstepping half of threshold
  *     -1      Overstepping minus half of threshold
 */
-static inline void mod_state(struct zone *zone,
-       enum zone_stat_item item, int delta, int overstep_mode)
+static inline void mod_state(struct zone *zone, enum zone_stat_item item,
+			     long delta, int overstep_mode)
 {
 	struct per_cpu_pageset __percpu *pcp = zone->pageset;
 	s8 __percpu *p = pcp->vm_stat_diff + item;
@@ -357,7 +357,7 @@ static inline void mod_state(struct zone *zone,
 }
 
 void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
-					int delta)
+			 long delta)
 {
 	mod_state(zone, item, delta, 0);
 }
@@ -384,7 +384,7 @@ EXPORT_SYMBOL(dec_zone_page_state);
  * Use interrupt disable to serialize counter updates
  */
 void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
-					int delta)
+			 long delta)
 {
 	unsigned long flags;
 
-- 
cgit v1.2.3


From 570f52412ae9432c56897472791ea8db420cbaf1 Mon Sep 17 00:00:00 2001
From: Sergey Senozhatsky
Date: Fri, 1 Jan 2016 23:03:01 +0900
Subject: sched/core: Check tgid in is_global_init()

Our global init task can have sub-threads, so ->pid check is not reliable
enough for is_global_init(), we need to check tgid instead. This has been
spotted by Oleg and a fix was proposed by Richard a long time ago (see the
link below).

Oleg wrote:

  : Because is_global_init() is only true for the main thread of /sbin/init.
  :
  : Just look at oom_unkillable_task(). It tries to not kill init. But, say,
  : select_bad_process() can happily find a sub-thread of is_global_init()
  : and still kill it.

I recently hit the problem in question; re-sending the patch (to the
best of my knowledge it has never been submitted) with updated function
comment. Credit goes to Oleg and Richard.

Suggested-by: Richard Guy Briggs <rgb@redhat.com>
Reported-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Eric W . Biederman <ebiederm@xmission.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Serge E . Hallyn <serge.hallyn@ubuntu.com>
Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://www.redhat.com/archives/linux-audit/2013-December/msg00086.html
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index edad7a43edea..9cf9dd1c4cbe 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2002,7 +2002,8 @@ static inline int pid_alive(const struct task_struct *p)
 }
 
 /**
- * is_global_init - check if a task structure is init
+ * is_global_init - check if a task structure is init. Since init
+ * is free to have sub-threads we need to check tgid.
  * @tsk: Task structure to be checked.
  *
  * Check if a task structure is the first user space task the kernel created.
@@ -2011,7 +2012,7 @@ static inline int pid_alive(const struct task_struct *p)
  */
 static inline int is_global_init(struct task_struct *tsk)
 {
-	return tsk->pid == 1;
+	return task_tgid_nr(tsk) == 1;
 }
 
 extern struct pid *cad_pid;
-- 
cgit v1.2.3


From be958bdc96f18bc1356177bbb79d46ea0c037b96 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra
Date: Wed, 25 Nov 2015 16:02:07 +0100
Subject: sched/core: Fix unserialized r-m-w scribbling stuff

Some of the sched bitfieds (notably sched_reset_on_fork) can be set
on other than current, this can cause the r-m-w to race with other
updates.

Since all the sched bits are serialized by scheduler locks, pull them
in a separate word.

Reported-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sasha Levin <sasha.levin@oracle.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: akpm@linux-foundation.org
Cc: hannes@cmpxchg.org
Cc: mhocko@kernel.org
Cc: vdavydov@parallels.com
Link: http://lkml.kernel.org/r/20151125150207.GM11639@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9cf9dd1c4cbe..fa39434e3fdd 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1455,14 +1455,15 @@ struct task_struct {
 	/* Used for emulating ABI behavior of previous Linux versions */
 	unsigned int personality;
 
-	unsigned in_execve:1;	/* Tell the LSMs that the process is doing an
-				 * execve */
-	unsigned in_iowait:1;
-
-	/* Revert to default priority/policy when forking */
+	/* scheduler bits, serialized by scheduler locks */
 	unsigned sched_reset_on_fork:1;
 	unsigned sched_contributes_to_load:1;
 	unsigned sched_migrated:1;
+	unsigned :0; /* force alignment to the next boundary */
+
+	/* unserialized, strictly 'current' */
+	unsigned in_execve:1; /* bit to tell LSMs we're in execve */
+	unsigned in_iowait:1;
 #ifdef CONFIG_MEMCG
 	unsigned memcg_may_oom:1;
 #endif
-- 
cgit v1.2.3