From d101a125954eae1d397adda94ca6319485a50493 Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <miklos@szeredi.hu>
Date: Sat, 26 Mar 2016 16:14:37 -0400
Subject: fs: add file_dentry()

This series fixes bugs in nfs and ext4 due to 4bacc9c9234c ("overlayfs:
Make f_path always point to the overlay and f_inode to the underlay").

Regular files opened on overlayfs will result in the file being opened on
the underlying filesystem, while f_path points to the overlayfs
mount/dentry.

This confuses filesystems which get the dentry from struct file and assume
it's theirs.

Add a new helper, file_dentry() [*], to get the filesystem's own dentry
from the file.  This checks file->f_path.dentry->d_flags against
DCACHE_OP_REAL, and returns file->f_path.dentry if DCACHE_OP_REAL is not
set (this is the common, non-overlayfs case).

In the uncommon case it will call into overlayfs's ->d_real() to get the
underlying dentry, matching file_inode(file).

The reason we need to check against the inode is that if the file is copied
up while being open, d_real() would return the upper dentry, while the open
file comes from the lower dentry.

[*] If possible, it's better simply to use file_inode() instead.

Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Tested-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Reviewed-by: Trond Myklebust <trond.myklebust@primarydata.com>
Cc: <stable@vger.kernel.org> # v4.2
Cc: David Howells <dhowells@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Daniel Axtens <dja@axtens.net>
---
 include/linux/dcache.h | 10 ++++++++++
 include/linux/fs.h     | 10 ++++++++++
 2 files changed, 20 insertions(+)

(limited to 'include')

diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 7cb043d8f4e8..4bb4de8d95ea 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -161,6 +161,7 @@ struct dentry_operations {
 	struct vfsmount *(*d_automount)(struct path *);
 	int (*d_manage)(struct dentry *, bool);
 	struct inode *(*d_select_inode)(struct dentry *, unsigned);
+	struct dentry *(*d_real)(struct dentry *, struct inode *);
 } ____cacheline_aligned;
 
 /*
@@ -229,6 +230,7 @@ struct dentry_operations {
 #define DCACHE_OP_SELECT_INODE		0x02000000 /* Unioned entry: dcache op selects inode */
 
 #define DCACHE_ENCRYPTED_WITH_KEY	0x04000000 /* dir is encrypted with a valid key */
+#define DCACHE_OP_REAL			0x08000000
 
 extern seqlock_t rename_lock;
 
@@ -555,4 +557,12 @@ static inline struct dentry *d_backing_dentry(struct dentry *upper)
 	return upper;
 }
 
+static inline struct dentry *d_real(struct dentry *dentry)
+{
+	if (unlikely(dentry->d_flags & DCACHE_OP_REAL))
+		return dentry->d_op->d_real(dentry, NULL);
+	else
+		return dentry;
+}
+
 #endif	/* __LINUX_DCACHE_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 35d99266ca9a..b2ed2311b021 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1241,6 +1241,16 @@ static inline struct inode *file_inode(const struct file *f)
 	return f->f_inode;
 }
 
+static inline struct dentry *file_dentry(const struct file *file)
+{
+	struct dentry *dentry = file->f_path.dentry;
+
+	if (unlikely(dentry->d_flags & DCACHE_OP_REAL))
+		return dentry->d_op->d_real(dentry, file_inode(file));
+	else
+		return dentry;
+}
+
 static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl)
 {
 	return locks_lock_inode_wait(file_inode(filp), fl);
-- 
cgit v1.2.3


From 743bc4b069517d3bae69349a1a23511eaaae5ede Mon Sep 17 00:00:00 2001
From: John Youn <johnyoun@synopsys.com>
Date: Mon, 28 Mar 2016 16:12:21 -0700
Subject: usb: ch9: Fix SSP Device Cap wFunctionalitySupport type

The wFunctionalitySupport field should be __le16.

Signed-off-by: John Youn <johnyoun@synopsys.com>
Signed-off-by: Felipe Balbi <felipe.balbi@linux.intel.com>
---
 include/uapi/linux/usb/ch9.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/usb/ch9.h b/include/uapi/linux/usb/ch9.h
index 06d6c6228a7a..d5ce71607972 100644
--- a/include/uapi/linux/usb/ch9.h
+++ b/include/uapi/linux/usb/ch9.h
@@ -899,7 +899,7 @@ struct usb_ssp_cap_descriptor {
 	__le32 bmAttributes;
 #define USB_SSP_SUBLINK_SPEED_ATTRIBS	(0x1f << 0) /* sublink speed entries */
 #define USB_SSP_SUBLINK_SPEED_IDS	(0xf << 5)  /* speed ID entries */
-	__u16  wFunctionalitySupport;
+	__le16  wFunctionalitySupport;
 #define USB_SSP_MIN_SUBLINK_SPEED_ATTRIBUTE_ID	(0xf)
 #define USB_SSP_MIN_RX_LANE_COUNT		(0xf << 8)
 #define USB_SSP_MIN_TX_LANE_COUNT		(0xf << 12)
-- 
cgit v1.2.3


From 90195c3651800f9a7c14956f90c2b4eb0bc8f1fb Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Tue, 23 Feb 2016 10:22:50 +0100
Subject: gpu: ipu-cpmem: modify ipu_cpmem_set_yuv_planar_full for better
 control

Let ipu_cpmem_set_yuv_planar_full take a DRM_FORMAT instead of a
V4L2_PIXFMT and allow better control over U/V stride, U offset and
V offset settings in the CPMEM.

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 include/video/imx-ipu-v3.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index eeba75395f7d..aa921052e7a6 100644
--- a/include/video/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -194,8 +194,9 @@ int ipu_cpmem_set_format_rgb(struct ipuv3_channel *ch,
 int ipu_cpmem_set_format_passthrough(struct ipuv3_channel *ch, int width);
 void ipu_cpmem_set_yuv_interleaved(struct ipuv3_channel *ch, u32 pixel_format);
 void ipu_cpmem_set_yuv_planar_full(struct ipuv3_channel *ch,
-				   u32 pixel_format, int stride,
-				   int u_offset, int v_offset);
+				   unsigned int uv_stride,
+				   unsigned int u_offset,
+				   unsigned int v_offset);
 void ipu_cpmem_set_yuv_planar(struct ipuv3_channel *ch,
 			      u32 pixel_format, int stride, int height);
 int ipu_cpmem_set_fmt(struct ipuv3_channel *ch, u32 drm_fourcc);
-- 
cgit v1.2.3


From 2bbe32f7398c9b38916983b5823e11d6aaa10be2 Mon Sep 17 00:00:00 2001
From: Liu Ying <gnuiyl@gmail.com>
Date: Mon, 14 Mar 2016 16:10:09 +0800
Subject: gpu: ipu-v3: ipu-dmfc: Make function ipu_dmfc_init_channel() return
 void

Since the function ipu_dmfc_init_channel() always returns zero, we may
change the return type to void to simplify the code.

Signed-off-by: Liu Ying <gnuiyl@gmail.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 include/video/imx-ipu-v3.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index aa921052e7a6..8555d3728b52 100644
--- a/include/video/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -237,7 +237,7 @@ void ipu_dmfc_disable_channel(struct dmfc_channel *dmfc);
 int ipu_dmfc_alloc_bandwidth(struct dmfc_channel *dmfc,
 		unsigned long bandwidth_mbs, int burstsize);
 void ipu_dmfc_free_bandwidth(struct dmfc_channel *dmfc);
-int ipu_dmfc_init_channel(struct dmfc_channel *dmfc, int width);
+void ipu_dmfc_init_channel(struct dmfc_channel *dmfc, int width);
 struct dmfc_channel *ipu_dmfc_get(struct ipu_soc *ipu, int ipuv3_channel);
 void ipu_dmfc_put(struct dmfc_channel *dmfc);
 
-- 
cgit v1.2.3


From 27630c206bb00a252d21576d92f57bdcc3ab9455 Mon Sep 17 00:00:00 2001
From: Liu Ying <gnuiyl@gmail.com>
Date: Mon, 14 Mar 2016 16:10:10 +0800
Subject: gpu: ipu-v3: ipu-dmfc: Rename ipu_dmfc_init_channel to
 ipu_dmfc_config_wait4eot

The function name 'ipu_dmfc_config_wait4eot' matches the implementation of
the function better than 'ipu_dmfc_init_channel', since it only touches the
wait4eot bits.

Signed-off-by: Liu Ying <gnuiyl@gmail.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 include/video/imx-ipu-v3.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index 8555d3728b52..ad66589f2ae6 100644
--- a/include/video/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -237,7 +237,7 @@ void ipu_dmfc_disable_channel(struct dmfc_channel *dmfc);
 int ipu_dmfc_alloc_bandwidth(struct dmfc_channel *dmfc,
 		unsigned long bandwidth_mbs, int burstsize);
 void ipu_dmfc_free_bandwidth(struct dmfc_channel *dmfc);
-void ipu_dmfc_init_channel(struct dmfc_channel *dmfc, int width);
+void ipu_dmfc_config_wait4eot(struct dmfc_channel *dmfc, int width);
 struct dmfc_channel *ipu_dmfc_get(struct ipu_soc *ipu, int ipuv3_channel);
 void ipu_dmfc_put(struct dmfc_channel *dmfc);
 
-- 
cgit v1.2.3


From 0f5dcf8de974db5970d48d12a202997baa2846a1 Mon Sep 17 00:00:00 2001
From: Mark Fasheh <mfasheh@suse.de>
Date: Tue, 29 Mar 2016 17:19:55 -0700
Subject: btrfs: Add qgroup tracing

This patch adds tracepoints to the qgroup code on both the reporting side
(insert_dirty_extents) and the accounting side. Taken together it allows us
to see what qgroup operations have happened, and what their result was.

Signed-off-by: Mark Fasheh <mfasheh@suse.de>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 include/trace/events/btrfs.h | 89 +++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 88 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index d866f21efbbf..467a4d205ff6 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -23,7 +23,7 @@ struct map_lookup;
 struct extent_buffer;
 struct btrfs_work;
 struct __btrfs_workqueue;
-struct btrfs_qgroup_operation;
+struct btrfs_qgroup_extent_record;
 
 #define show_ref_type(type)						\
 	__print_symbolic(type,						\
@@ -1231,6 +1231,93 @@ DEFINE_EVENT(btrfs__qgroup_delayed_ref, btrfs_qgroup_free_delayed_ref,
 
 	TP_ARGS(ref_root, reserved)
 );
+
+DECLARE_EVENT_CLASS(btrfs_qgroup_extent,
+	TP_PROTO(struct btrfs_qgroup_extent_record *rec),
+
+	TP_ARGS(rec),
+
+	TP_STRUCT__entry(
+		__field(	u64,  bytenr		)
+		__field(	u64,  num_bytes		)
+	),
+
+	TP_fast_assign(
+		__entry->bytenr		= rec->bytenr,
+		__entry->num_bytes	= rec->num_bytes;
+	),
+
+	TP_printk("bytenr = %llu, num_bytes = %llu",
+		  (unsigned long long)__entry->bytenr,
+		  (unsigned long long)__entry->num_bytes)
+);
+
+DEFINE_EVENT(btrfs_qgroup_extent, btrfs_qgroup_account_extents,
+
+	TP_PROTO(struct btrfs_qgroup_extent_record *rec),
+
+	TP_ARGS(rec)
+);
+
+DEFINE_EVENT(btrfs_qgroup_extent, btrfs_qgroup_insert_dirty_extent,
+
+	TP_PROTO(struct btrfs_qgroup_extent_record *rec),
+
+	TP_ARGS(rec)
+);
+
+TRACE_EVENT(btrfs_qgroup_account_extent,
+
+	TP_PROTO(u64 bytenr, u64 num_bytes, u64 nr_old_roots, u64 nr_new_roots),
+
+	TP_ARGS(bytenr, num_bytes, nr_old_roots, nr_new_roots),
+
+	TP_STRUCT__entry(
+		__field(	u64,  bytenr			)
+		__field(	u64,  num_bytes			)
+		__field(	u64,  nr_old_roots		)
+		__field(	u64,  nr_new_roots		)
+	),
+
+	TP_fast_assign(
+		__entry->bytenr		= bytenr;
+		__entry->num_bytes	= num_bytes;
+		__entry->nr_old_roots	= nr_old_roots;
+		__entry->nr_new_roots	= nr_new_roots;
+	),
+
+	TP_printk("bytenr = %llu, num_bytes = %llu, nr_old_roots = %llu, "
+		  "nr_new_roots = %llu",
+		  __entry->bytenr,
+		  __entry->num_bytes,
+		  __entry->nr_old_roots,
+		  __entry->nr_new_roots)
+);
+
+TRACE_EVENT(qgroup_update_counters,
+
+	TP_PROTO(u64 qgid, u64 cur_old_count, u64 cur_new_count),
+
+	TP_ARGS(qgid, cur_old_count, cur_new_count),
+
+	TP_STRUCT__entry(
+		__field(	u64,  qgid			)
+		__field(	u64,  cur_old_count		)
+		__field(	u64,  cur_new_count		)
+	),
+
+	TP_fast_assign(
+		__entry->qgid		= qgid;
+		__entry->cur_old_count	= cur_old_count;
+		__entry->cur_new_count	= cur_new_count;
+	),
+
+	TP_printk("qgid = %llu, cur_old_count = %llu, cur_new_count = %llu",
+		  __entry->qgid,
+		  __entry->cur_old_count,
+		  __entry->cur_new_count)
+);
+
 #endif /* _TRACE_BTRFS_H */
 
 /* This part must be outside protection */
-- 
cgit v1.2.3


From 09cbfeaf1a5a67bfb3201e0c83c810cecb2efa5a Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Fri, 1 Apr 2016 15:29:47 +0300
Subject: mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros

PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.

This promise never materialized.  And unlikely will.

We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE.  And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.

Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.

Let's stop pretending that pages in page cache are special.  They are
not.

The changes are pretty straight-forward:

 - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;

 - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;

 - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};

 - page_cache_get() -> get_page();

 - page_cache_release() -> put_page();

This patch contains automated changes generated with coccinelle using
script below.  For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.

The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.

There are few places in the code where coccinelle didn't reach.  I'll
fix them manually in a separate patch.  Comments and documentation also
will be addressed with the separate patch.

virtual patch

@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E

@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E

@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT

@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE

@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK

@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)

@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)

@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/bio.h          |  2 +-
 include/linux/blkdev.h       |  2 +-
 include/linux/buffer_head.h  |  4 ++--
 include/linux/ceph/libceph.h |  4 ++--
 include/linux/f2fs_fs.h      |  4 ++--
 include/linux/fs.h           |  4 ++--
 include/linux/nfs_page.h     |  2 +-
 include/linux/pagemap.h      | 14 +++++++-------
 include/linux/swap.h         |  2 +-
 9 files changed, 19 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/linux/bio.h b/include/linux/bio.h
index 88bc64f00bb5..6b7481f62218 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -41,7 +41,7 @@
 #endif
 
 #define BIO_MAX_PAGES		256
-#define BIO_MAX_SIZE		(BIO_MAX_PAGES << PAGE_CACHE_SHIFT)
+#define BIO_MAX_SIZE		(BIO_MAX_PAGES << PAGE_SHIFT)
 #define BIO_MAX_SECTORS		(BIO_MAX_SIZE >> 9)
 
 /*
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 7e5d7e018bea..669e419d6234 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1372,7 +1372,7 @@ unsigned char *read_dev_sector(struct block_device *, sector_t, Sector *);
 
 static inline void put_dev_sector(Sector p)
 {
-	page_cache_release(p.v);
+	put_page(p.v);
 }
 
 static inline bool __bvec_gap_to_prev(struct request_queue *q,
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index c67f052cc5e5..d48daa3f6f20 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -43,7 +43,7 @@ enum bh_state_bits {
 			 */
 };
 
-#define MAX_BUF_PER_PAGE (PAGE_CACHE_SIZE / 512)
+#define MAX_BUF_PER_PAGE (PAGE_SIZE / 512)
 
 struct page;
 struct buffer_head;
@@ -263,7 +263,7 @@ void buffer_init(void);
 static inline void attach_page_buffers(struct page *page,
 		struct buffer_head *head)
 {
-	page_cache_get(page);
+	get_page(page);
 	SetPagePrivate(page);
 	set_page_private(page, (unsigned long)head);
 }
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index e7975e4681e1..db92a8d4926e 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -176,8 +176,8 @@ extern void ceph_put_snap_context(struct ceph_snap_context *sc);
  */
 static inline int calc_pages_for(u64 off, u64 len)
 {
-	return ((off+len+PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT) -
-		(off >> PAGE_CACHE_SHIFT);
+	return ((off+len+PAGE_SIZE-1) >> PAGE_SHIFT) -
+		(off >> PAGE_SHIFT);
 }
 
 extern struct kmem_cache *ceph_inode_cachep;
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index 9eb215a155e0..b90e9bdbd1dd 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -262,7 +262,7 @@ struct f2fs_node {
 /*
  * For NAT entries
  */
-#define NAT_ENTRY_PER_BLOCK (PAGE_CACHE_SIZE / sizeof(struct f2fs_nat_entry))
+#define NAT_ENTRY_PER_BLOCK (PAGE_SIZE / sizeof(struct f2fs_nat_entry))
 
 struct f2fs_nat_entry {
 	__u8 version;		/* latest version of cached nat entry */
@@ -282,7 +282,7 @@ struct f2fs_nat_block {
  * Not allow to change this.
  */
 #define SIT_VBLOCK_MAP_SIZE 64
-#define SIT_ENTRY_PER_BLOCK (PAGE_CACHE_SIZE / sizeof(struct f2fs_sit_entry))
+#define SIT_ENTRY_PER_BLOCK (PAGE_SIZE / sizeof(struct f2fs_sit_entry))
 
 /*
  * Note that f2fs_sit_entry->vblocks has the following bit-field information.
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 14a97194b34b..304991a80e23 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -929,7 +929,7 @@ static inline struct file *get_file(struct file *f)
 /* Page cache limit. The filesystems should put that into their s_maxbytes 
    limits, otherwise bad things can happen in VM. */ 
 #if BITS_PER_LONG==32
-#define MAX_LFS_FILESIZE	(((loff_t)PAGE_CACHE_SIZE << (BITS_PER_LONG-1))-1) 
+#define MAX_LFS_FILESIZE	(((loff_t)PAGE_SIZE << (BITS_PER_LONG-1))-1)
 #elif BITS_PER_LONG==64
 #define MAX_LFS_FILESIZE 	((loff_t)0x7fffffffffffffffLL)
 #endif
@@ -2067,7 +2067,7 @@ extern int generic_update_time(struct inode *, struct timespec *, int);
 /* /sys/fs */
 extern struct kobject *fs_kobj;
 
-#define MAX_RW_COUNT (INT_MAX & PAGE_CACHE_MASK)
+#define MAX_RW_COUNT (INT_MAX & PAGE_MASK)
 
 #ifdef CONFIG_MANDATORY_FILE_LOCKING
 extern int locks_mandatory_locked(struct file *);
diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h
index f2f650f136ee..efada239205e 100644
--- a/include/linux/nfs_page.h
+++ b/include/linux/nfs_page.h
@@ -184,7 +184,7 @@ nfs_list_entry(struct list_head *head)
 static inline
 loff_t req_offset(struct nfs_page *req)
 {
-	return (((loff_t)req->wb_index) << PAGE_CACHE_SHIFT) + req->wb_offset;
+	return (((loff_t)req->wb_index) << PAGE_SHIFT) + req->wb_offset;
 }
 
 #endif /* _LINUX_NFS_PAGE_H */
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 1ebd65c91422..f396ccb900cc 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -390,13 +390,13 @@ static inline pgoff_t page_to_pgoff(struct page *page)
 		return page->index << compound_order(page);
 
 	if (likely(!PageTransTail(page)))
-		return page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+		return page->index;
 
 	/*
 	 *  We don't initialize ->index for tail pages: calculate based on
 	 *  head page
 	 */
-	pgoff = compound_head(page)->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+	pgoff = compound_head(page)->index;
 	pgoff += page - compound_head(page);
 	return pgoff;
 }
@@ -406,12 +406,12 @@ static inline pgoff_t page_to_pgoff(struct page *page)
  */
 static inline loff_t page_offset(struct page *page)
 {
-	return ((loff_t)page->index) << PAGE_CACHE_SHIFT;
+	return ((loff_t)page->index) << PAGE_SHIFT;
 }
 
 static inline loff_t page_file_offset(struct page *page)
 {
-	return ((loff_t)page_file_index(page)) << PAGE_CACHE_SHIFT;
+	return ((loff_t)page_file_index(page)) << PAGE_SHIFT;
 }
 
 extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma,
@@ -425,7 +425,7 @@ static inline pgoff_t linear_page_index(struct vm_area_struct *vma,
 		return linear_hugepage_index(vma, address);
 	pgoff = (address - vma->vm_start) >> PAGE_SHIFT;
 	pgoff += vma->vm_pgoff;
-	return pgoff >> (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+	return pgoff;
 }
 
 extern void __lock_page(struct page *page);
@@ -671,8 +671,8 @@ static inline int add_to_page_cache(struct page *page,
 
 static inline unsigned long dir_pages(struct inode *inode)
 {
-	return (unsigned long)(inode->i_size + PAGE_CACHE_SIZE - 1) >>
-			       PAGE_CACHE_SHIFT;
+	return (unsigned long)(inode->i_size + PAGE_SIZE - 1) >>
+			       PAGE_SHIFT;
 }
 
 #endif /* _LINUX_PAGEMAP_H */
diff --git a/include/linux/swap.h b/include/linux/swap.h
index d18b65c53dbb..3d980ea1c946 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -435,7 +435,7 @@ struct backing_dev_info;
 /* only sparc can not include linux/pagemap.h in this file
  * so leave page_cache_release and release_pages undeclared... */
 #define free_page_and_swap_cache(page) \
-	page_cache_release(page)
+	put_page(page)
 #define free_pages_and_swap_cache(pages, nr) \
 	release_pages((pages), (nr), false);
 
-- 
cgit v1.2.3


From ea1754a084760e68886f5b725c8eaada9cc57155 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Fri, 1 Apr 2016 15:29:48 +0300
Subject: mm, fs: remove remaining PAGE_CACHE_* and page_cache_{get,release}
 usage

Mostly direct substitution with occasional adjustment or removing
outdated comments.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/backing-dev-defs.h | 2 +-
 include/linux/mm.h               | 2 +-
 include/linux/mm_types.h         | 2 +-
 include/linux/nfs_page.h         | 4 ++--
 include/linux/nilfs2_fs.h        | 4 ++--
 include/linux/pagemap.h          | 3 +--
 include/linux/sunrpc/svc.h       | 2 +-
 include/linux/swap.h             | 2 +-
 8 files changed, 10 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index 1b4d69f68c33..3f103076d0bf 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -135,7 +135,7 @@ struct bdi_writeback {
 
 struct backing_dev_info {
 	struct list_head bdi_list;
-	unsigned long ra_pages;	/* max readahead in PAGE_CACHE_SIZE units */
+	unsigned long ra_pages;	/* max readahead in PAGE_SIZE units */
 	unsigned int capabilities; /* Device capabilities */
 	congested_fn *congested_fn; /* Function pointer if device is md/dm */
 	void *congested_data;	/* Pointer to aux data for congested func */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index ed6407d1b7b5..ffcff53e3b2b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -623,7 +623,7 @@ void do_set_pte(struct vm_area_struct *vma, unsigned long address,
  *
  * A page may belong to an inode's memory mapping. In this case, page->mapping
  * is the pointer to the inode, and page->index is the file offset of the page,
- * in units of PAGE_CACHE_SIZE.
+ * in units of PAGE_SIZE.
  *
  * If pagecache pages are not associated with an inode, they are said to be
  * anonymous pages. These may become associated with the swapcache, and in that
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 944b2b37313b..c2d75b4fa86c 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -341,7 +341,7 @@ struct vm_area_struct {
 
 	/* Information about our backing store: */
 	unsigned long vm_pgoff;		/* Offset (within vm_file) in PAGE_SIZE
-					   units, *not* PAGE_CACHE_SIZE */
+					   units */
 	struct file * vm_file;		/* File we map to (can be NULL). */
 	void * vm_private_data;		/* was vm_pte (shared mem) */
 
diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h
index efada239205e..957049f72290 100644
--- a/include/linux/nfs_page.h
+++ b/include/linux/nfs_page.h
@@ -41,8 +41,8 @@ struct nfs_page {
 	struct page		*wb_page;	/* page to read in/write out */
 	struct nfs_open_context	*wb_context;	/* File state context info */
 	struct nfs_lock_context	*wb_lock_context;	/* lock context info */
-	pgoff_t			wb_index;	/* Offset >> PAGE_CACHE_SHIFT */
-	unsigned int		wb_offset,	/* Offset & ~PAGE_CACHE_MASK */
+	pgoff_t			wb_index;	/* Offset >> PAGE_SHIFT */
+	unsigned int		wb_offset,	/* Offset & ~PAGE_MASK */
 				wb_pgbase,	/* Start of page data */
 				wb_bytes;	/* Length of request */
 	struct kref		wb_kref;	/* reference count */
diff --git a/include/linux/nilfs2_fs.h b/include/linux/nilfs2_fs.h
index 9abb763e4b86..e9fcf90b270d 100644
--- a/include/linux/nilfs2_fs.h
+++ b/include/linux/nilfs2_fs.h
@@ -331,7 +331,7 @@ static inline unsigned nilfs_rec_len_from_disk(__le16 dlen)
 {
 	unsigned len = le16_to_cpu(dlen);
 
-#if !defined(__KERNEL__) || (PAGE_CACHE_SIZE >= 65536)
+#if !defined(__KERNEL__) || (PAGE_SIZE >= 65536)
 	if (len == NILFS_MAX_REC_LEN)
 		return 1 << 16;
 #endif
@@ -340,7 +340,7 @@ static inline unsigned nilfs_rec_len_from_disk(__le16 dlen)
 
 static inline __le16 nilfs_rec_len_to_disk(unsigned len)
 {
-#if !defined(__KERNEL__) || (PAGE_CACHE_SIZE >= 65536)
+#if !defined(__KERNEL__) || (PAGE_SIZE >= 65536)
 	if (len == (1 << 16))
 		return cpu_to_le16(NILFS_MAX_REC_LEN);
 	else if (len > (1 << 16))
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index f396ccb900cc..b3fc0370c14f 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -535,8 +535,7 @@ extern void add_page_wait_queue(struct page *page, wait_queue_t *waiter);
 /*
  * Fault a userspace page into pagetables.  Return non-zero on a fault.
  *
- * This assumes that two userspace pages are always sufficient.  That's
- * not true if PAGE_CACHE_SIZE > PAGE_SIZE.
+ * This assumes that two userspace pages are always sufficient.
  */
 static inline int fault_in_pages_writeable(char __user *uaddr, int size)
 {
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index cc0fc712bb82..7ca44fb5b675 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -129,7 +129,7 @@ static inline void svc_get(struct svc_serv *serv)
  *
  * These happen to all be powers of 2, which is not strictly
  * necessary but helps enforce the real limitation, which is
- * that they should be multiples of PAGE_CACHE_SIZE.
+ * that they should be multiples of PAGE_SIZE.
  *
  * For UDP transports, a block plus NFS,RPC, and UDP headers
  * has to fit into the IP datagram limit of 64K.  The largest
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 3d980ea1c946..2b83359c19ca 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -433,7 +433,7 @@ struct backing_dev_info;
 #define si_swapinfo(val) \
 	do { (val)->freeswap = (val)->totalswap = 0; } while (0)
 /* only sparc can not include linux/pagemap.h in this file
- * so leave page_cache_release and release_pages undeclared... */
+ * so leave put_page and release_pages undeclared... */
 #define free_page_and_swap_cache(page) \
 	put_page(page)
 #define free_pages_and_swap_cache(pages, nr) \
-- 
cgit v1.2.3


From 1fa64f198b9f8d6ec0f7aec7c18dc94684391140 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Fri, 1 Apr 2016 15:29:49 +0300
Subject: mm: drop PAGE_CACHE_* and page_cache_{get,release} definition

All users gone.  We can remove these macros.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/pagemap.h | 15 ---------------
 1 file changed, 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index b3fc0370c14f..7e1ab155c67c 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -86,21 +86,6 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask)
 				(__force unsigned long)mask;
 }
 
-/*
- * The page cache can be done in larger chunks than
- * one page, because it allows for more efficient
- * throughput (it can then be mapped into user
- * space in smaller chunks for same flexibility).
- *
- * Or rather, it _will_ be done in larger chunks.
- */
-#define PAGE_CACHE_SHIFT	PAGE_SHIFT
-#define PAGE_CACHE_SIZE		PAGE_SIZE
-#define PAGE_CACHE_MASK		PAGE_MASK
-#define PAGE_CACHE_ALIGN(addr)	(((addr)+PAGE_CACHE_SIZE-1)&PAGE_CACHE_MASK)
-
-#define page_cache_get(page)		get_page(page)
-#define page_cache_release(page)	put_page(page)
 void release_pages(struct page **pages, int nr, bool cold);
 
 /*
-- 
cgit v1.2.3


From 749b48faaf64d1081d7216068ff3da92c230bad0 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 1 Apr 2016 10:12:49 -0400
Subject: drm/ttm: use phys_addr_t for ttm_bus_placement
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fixes ttm on platforms like PPC460 where the CPU
is in 32-bit mode, but the physical addresses are
>32 bits.

Extracted from a patch by Hans Verkuil.

Tested-by: Julian Margetson <runaway@candw.ms>
Acked-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Cc: Thomas Hellstrom <thellstrom@vmware.com>
Cc: Julian Margetson <runaway@candw.ms>
Cc: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 include/drm/ttm/ttm_bo_api.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index afae2316bd43..055a08ddac02 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -92,7 +92,7 @@ struct ttm_placement {
  */
 struct ttm_bus_placement {
 	void		*addr;
-	unsigned long	base;
+	phys_addr_t	base;
 	unsigned long	size;
 	unsigned long	offset;
 	bool		is_iomem;
-- 
cgit v1.2.3


From 84ea3a18c06c7ae94b76f763c462bf1e0ce4dc79 Mon Sep 17 00:00:00 2001
From: Luis de Bethencourt <luisbg@osg.samsung.com>
Date: Fri, 18 Mar 2016 16:09:29 +0000
Subject: mac80211: add doc for RX_FLAG_DUP_VALIDATED flag

Add documentation for the flag for duplication check.

Fixes the following warning when running make htmldocs:
warning: Enum value 'RX_FLAG_DUP_VALIDATED' not described in enum 'mac80211_rx_flags'

Signed-off-by: Luis de Bethencourt <luisbg@osg.samsung.com>
[fix description]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 0c09da34b67a..e385eb3076a1 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1001,6 +1001,8 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info)
  *	flag indicates that the PN was verified for replay protection.
  *	Note that this flag is also currently only supported when a frame
  *	is also decrypted (ie. @RX_FLAG_DECRYPTED must be set)
+ * @RX_FLAG_DUP_VALIDATED: The driver should set this flag if it did
+ *	de-duplication by itself.
  * @RX_FLAG_FAILED_FCS_CRC: Set this flag if the FCS check failed on
  *	the frame.
  * @RX_FLAG_FAILED_PLCP_CRC: Set this flag if the PCLP check failed on
-- 
cgit v1.2.3


From 5ddfe0858ea7848c5d4efe3f4319e7543522e0ee Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Fri, 1 Apr 2016 08:57:36 +0200
Subject: scsi: Do not attach VPD to devices that don't support it

The patch "scsi: rescan VPD attributes" introduced a regression in which
devices that don't support VPD were being scanned for VPD attributes
anyway.  This could cause issues for some devices and should be avoided
so the check for scsi_level has been moved out of scsi_add_lun and into
scsi_attach_vpd so that all callers will not scan VPD for devices that
don't support it.

[mkp: Merge fix]

Fixes: 09e2b0b14690 ("scsi: rescan VPD attributes")
Cc: <stable@vger.kernel.org> #v4.5+
Suggested-by: Alexander Duyck <aduyck@mirantis.com>
Signed-off-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 include/scsi/scsi_device.h | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

(limited to 'include')

diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index c067019ed12a..74d79bde7075 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -516,6 +516,31 @@ static inline int scsi_device_tpgs(struct scsi_device *sdev)
 	return sdev->inquiry ? (sdev->inquiry[5] >> 4) & 0x3 : 0;
 }
 
+/**
+ * scsi_device_supports_vpd - test if a device supports VPD pages
+ * @sdev: the &struct scsi_device to test
+ *
+ * If the 'try_vpd_pages' flag is set it takes precedence.
+ * Otherwise we will assume VPD pages are supported if the
+ * SCSI level is at least SPC-3 and 'skip_vpd_pages' is not set.
+ */
+static inline int scsi_device_supports_vpd(struct scsi_device *sdev)
+{
+	/* Attempt VPD inquiry if the device blacklist explicitly calls
+	 * for it.
+	 */
+	if (sdev->try_vpd_pages)
+		return 1;
+	/*
+	 * Although VPD inquiries can go to SCSI-2 type devices,
+	 * some USB ones crash on receiving them, and the pages
+	 * we currently ask for are for SPC-3 and beyond
+	 */
+	if (sdev->scsi_level > SCSI_SPC_2 && !sdev->skip_vpd_pages)
+		return 1;
+	return 0;
+}
+
 #define MODULE_ALIAS_SCSI_DEVICE(type) \
 	MODULE_ALIAS("scsi:t-" __stringify(type) "*")
 #define SCSI_DEVICE_MODALIAS_FMT "scsi:t-0x%02x"
-- 
cgit v1.2.3


From b70bb984489363aadd5ccc94d919629d9e264d36 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 15 Mar 2016 22:37:17 +0100
Subject: iommu: provide of_xlate pointer unconditionally

iommu drivers that support the standard DT bindings use a of_xlate
callback pointer, but that is only part of struct iommu_ops when
CONFIG_OF_IOMMU is enabled, leading to build errors in randconfig
builds when that is not provided:

drivers/iommu/mtk_iommu.c:497:2: error: unknown field 'of_xlate' specified in initializer
  .of_xlate = mtk_iommu_of_xlate,
  ^
drivers/iommu/mtk_iommu.c:497:14: error: initialization from incompatible pointer type [-Werror=incompatible-pointer-types]
  .of_xlate = mtk_iommu_of_xlate,
              ^~~~~~~~~~~~~~~~~~
drivers/iommu/mtk_iommu.c:497:14: note: (near initialization for 'mtk_iommu_ops.domain_get_attr')

We can work around it by adding more #ifdefs in each driver, but
it seems nicer to just allow setting the pointer even if it is
unused. This makes the driver code look nicer, and it gives better
compile-time coverage when test building on other architectures.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Fixes: 0df4fabe208d ("iommu/mediatek: Add mt8173 IOMMU driver")
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 include/linux/iommu.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index a5c539fa5d2b..ef7a6ecd8584 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -195,9 +195,7 @@ struct iommu_ops {
 	/* Get the number of windows per domain */
 	u32 (*domain_get_windows)(struct iommu_domain *domain);
 
-#ifdef CONFIG_OF_IOMMU
 	int (*of_xlate)(struct device *dev, struct of_phandle_args *args);
-#endif
 
 	unsigned long pgsize_bitmap;
 	void *priv;
-- 
cgit v1.2.3


From 95272c29378ee7dc15f43fa2758cb28a5913a06d Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Thu, 31 Mar 2016 09:38:51 +0200
Subject: compiler-gcc: disable -ftracer for __noclone functions

-ftracer can duplicate asm blocks causing compilation to fail in
noclone functions.  For example, KVM declares a global variable
in an asm like

    asm("2: ... \n
         .pushsection data \n
         .global vmx_return \n
         vmx_return: .long 2b");

and -ftracer causes a double declaration.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Michal Marek <mmarek@suse.cz>
Cc: stable@vger.kernel.org
Cc: kvm@vger.kernel.org
Reported-by: Linda Walsh <lkml@tlinx.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/compiler-gcc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 22ab246feed3..eeae401a2412 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -199,7 +199,7 @@
 #define unreachable() __builtin_unreachable()
 
 /* Mark a function definition as prohibited from being cloned. */
-#define __noclone	__attribute__((__noclone__))
+#define __noclone	__attribute__((__noclone__, __optimize__("no-tracer")))
 
 #endif /* GCC_VERSION >= 40500 */
 
-- 
cgit v1.2.3


From eb8e97715f29a1240cdf67b0df725be27433259f Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Fri, 1 Apr 2016 14:30:32 -0300
Subject: sctp: use list_* in sctp_list_dequeue

Use list_* helpers in sctp_list_dequeue, more readable.

Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/sctp.h | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 65521cfdcade..03fb33efcae2 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -386,11 +386,9 @@ static inline struct list_head *sctp_list_dequeue(struct list_head *list)
 {
 	struct list_head *result = NULL;
 
-	if (list->next != list) {
+	if (!list_empty(list)) {
 		result = list->next;
-		list->next = result->next;
-		list->next->prev = list;
-		INIT_LIST_HEAD(result);
+		list_del_init(result);
 	}
 	return result;
 }
-- 
cgit v1.2.3


From 18fcf49f87f4b280d3cd695fc77766004b223af5 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Mon, 4 Apr 2016 10:32:48 -0700
Subject: net_sched: fix a memory leak in tc action

Fixes: ddf97ccdd7cb ("net_sched: add network namespace support for tc actions")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Tested-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/act_api.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/net/act_api.h b/include/net/act_api.h
index 2a19fe111c78..03e322b30218 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -135,6 +135,7 @@ void tcf_hashinfo_destroy(const struct tc_action_ops *ops,
 static inline void tc_action_net_exit(struct tc_action_net *tn)
 {
 	tcf_hashinfo_destroy(tn->ops, tn->hinfo);
+	kfree(tn->hinfo);
 }
 
 int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb,
-- 
cgit v1.2.3


From c12d2da56d0e07d230968ee2305aaa86b93a6832 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Mon, 4 Apr 2016 10:24:58 +0200
Subject: mm/gup: Remove the macro overload API migration helpers from the
 get_user*() APIs

The pkeys changes brought about a truly hideous set of macros in:

  cde70140fed8 ("mm/gup: Overload get_user_pages() functions")

... which macros are (ab-)using the fact that __VA_ARGS__ can be used
to shift parameter positions in macro arguments without breaking the
build and so can be used to call separate C functions depending on
the number of arguments of the macro.

This allowed easy migration of these 3 GUP APIs, as both these variants
worked at the C level:

  old:
	ret = get_user_pages(current, current->mm, address, 1, 1, 0, &page, NULL);

  new:
	ret = get_user_pages(address, 1, 1, 0, &page, NULL);

... while we also generated a (functionally harmless but noticeable) build
time warning if the old API was used. As there are over 300 uses of these
APIs, this trick eased the migration of the API and avoided excessive
migration pain in linux-next.

Now, with its work done, get rid of all of that complication and ugliness:

    3 files changed, 16 insertions(+), 140 deletions(-)

... where the linecount of the migration hack was further inflated by the
fact that there are NOMMU variants of these GUP APIs as well.

Much of the conversion was done in linux-next over the past couple of months,
and Linus recently removed all remaining old API uses from the upstream tree
in the following upstrea commit:

  cb107161df3c ("Convert straggling drivers to new six-argument get_user_pages()")

There was one more old-API usage in mm/gup.c, in the CONFIG_HAVE_GENERIC_RCU_GUP
code path that ARM, ARM64 and PowerPC uses.

After this commit any old API usage will break the build.

[ Also fixed a PowerPC/HAVE_GENERIC_RCU_GUP warning reported by Stephen Rothwell. ]

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dave Hansen <dave@sr71.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Cc: linux-mm@kvack.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/mm.h | 64 +++---------------------------------------------------
 1 file changed, 3 insertions(+), 61 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index ed6407d1b7b5..d6508a025a31 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1250,78 +1250,20 @@ long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
 			    unsigned long start, unsigned long nr_pages,
 			    int write, int force, struct page **pages,
 			    struct vm_area_struct **vmas);
-long get_user_pages6(unsigned long start, unsigned long nr_pages,
+long get_user_pages(unsigned long start, unsigned long nr_pages,
 			    int write, int force, struct page **pages,
 			    struct vm_area_struct **vmas);
-long get_user_pages_locked6(unsigned long start, unsigned long nr_pages,
+long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
 		    int write, int force, struct page **pages, int *locked);
 long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
 			       unsigned long start, unsigned long nr_pages,
 			       int write, int force, struct page **pages,
 			       unsigned int gup_flags);
-long get_user_pages_unlocked5(unsigned long start, unsigned long nr_pages,
+long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
 		    int write, int force, struct page **pages);
 int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 			struct page **pages);
 
-/* suppress warnings from use in EXPORT_SYMBOL() */
-#ifndef __DISABLE_GUP_DEPRECATED
-#define __gup_deprecated __deprecated
-#else
-#define __gup_deprecated
-#endif
-/*
- * These macros provide backward-compatibility with the old
- * get_user_pages() variants which took tsk/mm.  These
- * functions/macros provide both compile-time __deprecated so we
- * can catch old-style use and not break the build.  The actual
- * functions also have WARN_ON()s to let us know at runtime if
- * the get_user_pages() should have been the "remote" variant.
- *
- * These are hideous, but temporary.
- *
- * If you run into one of these __deprecated warnings, look
- * at how you are calling get_user_pages().  If you are calling
- * it with current/current->mm as the first two arguments,
- * simply remove those arguments.  The behavior will be the same
- * as it is now.  If you are calling it on another task, use
- * get_user_pages_remote() instead.
- *
- * Any questions?  Ask Dave Hansen <dave@sr71.net>
- */
-long
-__gup_deprecated
-get_user_pages8(struct task_struct *tsk, struct mm_struct *mm,
-		unsigned long start, unsigned long nr_pages,
-		int write, int force, struct page **pages,
-		struct vm_area_struct **vmas);
-#define GUP_MACRO(_1, _2, _3, _4, _5, _6, _7, _8, get_user_pages, ...)	\
-	get_user_pages
-#define get_user_pages(...) GUP_MACRO(__VA_ARGS__,	\
-		get_user_pages8, x,			\
-		get_user_pages6, x, x, x, x, x)(__VA_ARGS__)
-
-__gup_deprecated
-long get_user_pages_locked8(struct task_struct *tsk, struct mm_struct *mm,
-		unsigned long start, unsigned long nr_pages,
-		int write, int force, struct page **pages,
-		int *locked);
-#define GUPL_MACRO(_1, _2, _3, _4, _5, _6, _7, _8, get_user_pages_locked, ...)	\
-	get_user_pages_locked
-#define get_user_pages_locked(...) GUPL_MACRO(__VA_ARGS__,	\
-		get_user_pages_locked8,	x,			\
-		get_user_pages_locked6, x, x, x, x)(__VA_ARGS__)
-
-__gup_deprecated
-long get_user_pages_unlocked7(struct task_struct *tsk, struct mm_struct *mm,
-		unsigned long start, unsigned long nr_pages,
-		int write, int force, struct page **pages);
-#define GUPU_MACRO(_1, _2, _3, _4, _5, _6, _7, get_user_pages_unlocked, ...)	\
-	get_user_pages_unlocked
-#define get_user_pages_unlocked(...) GUPU_MACRO(__VA_ARGS__,	\
-		get_user_pages_unlocked7, x,			\
-		get_user_pages_unlocked5, x, x, x, x)(__VA_ARGS__)
-
 /* Container for pinned pfns / pages */
 struct frame_vector {
 	unsigned int nr_allocated;	/* Number of frames we have space for */
-- 
cgit v1.2.3


From c00bbcf8628969e103d4a7b351a53746f1025576 Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Tue, 29 Mar 2016 16:43:45 +0100
Subject: virtio: add VIRTIO_CONFIG_S_NEEDS_RESET device status bit

The VIRTIO 1.0 specification added the DEVICE_NEEDS_RESET device status
bit in "VIRTIO-98: Add DEVICE_NEEDS_RESET".  This patch defines the
device status bit in the uapi header file so that both the kernel and
userspace applications can use it.

The bit is currently unused by the virtio guest drivers and vhost.
According to the spec "a good implementation will try to recover by
issuing a reset".  This is not attempted here because it requires
auditing the virtio drivers to ensure there are no resource leaks or
crashes if the device needs to be reset mid-operation.

See "2.1 Device Status Field" in the VIRTIO 1.0 specification for
details.

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/uapi/linux/virtio_config.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h
index c18264df9504..4cb65bbfa654 100644
--- a/include/uapi/linux/virtio_config.h
+++ b/include/uapi/linux/virtio_config.h
@@ -40,6 +40,8 @@
 #define VIRTIO_CONFIG_S_DRIVER_OK	4
 /* Driver has finished configuring features */
 #define VIRTIO_CONFIG_S_FEATURES_OK	8
+/* Device entered invalid state, driver must reset it */
+#define VIRTIO_CONFIG_S_NEEDS_RESET	0x40
 /* We've given up on this device. */
 #define VIRTIO_CONFIG_S_FAILED		0x80
 
-- 
cgit v1.2.3


From a0ca153f98db8cf25298565a09e11fe9d82846ad Mon Sep 17 00:00:00 2001
From: Alexander Duyck <aduyck@mirantis.com>
Date: Tue, 5 Apr 2016 09:13:39 -0700
Subject: GRE: Disable segmentation offloads w/ CSUM and we are encapsulated
 via FOU

This patch fixes an issue I found in which we were dropping frames if we
had enabled checksums on GRE headers that were encapsulated by either FOU
or GUE.  Without this patch I was barely able to get 1 Gb/s of throughput.
With this patch applied I am now at least getting around 6 Gb/s.

The issue is due to the fact that with FOU or GUE applied we do not provide
a transport offset pointing to the GRE header, nor do we offload it in
software as the GRE header is completely skipped by GSO and treated like a
VXLAN or GENEVE type header.  As such we need to prevent the stack from
generating it and also prevent GRE from generating it via any interface we
create.

Fixes: c3483384ee511 ("gro: Allow tunnel stacking in the case of FOU/GUE")
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index cb0d5d09c2e4..8395308a2445 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2120,7 +2120,10 @@ struct napi_gro_cb {
 	/* Used in foo-over-udp, set in udp[46]_gro_receive */
 	u8	is_ipv6:1;
 
-	/* 7 bit hole */
+	/* Used in GRE, set in fou/gue_gro_receive */
+	u8	is_fou:1;
+
+	/* 6 bit hole */
 
 	/* used to support CHECKSUM_COMPLETE for tunneling protocols */
 	__wsum	csum;
-- 
cgit v1.2.3


From ba6f5e33bdbb9ed2014b778fbbaecf20060ca989 Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Wed, 6 Apr 2016 15:15:19 -0300
Subject: sctp: avoid refreshing heartbeat timer too often

Currently on high rate SCTP streams the heartbeat timer refresh can
consume quite a lot of resources as timer updates are costly and it
contains a random factor, which a) is also costly and b) invalidates
mod_timer() optimization for not editing a timer to the same value.
It may even cause the timer to be slightly advanced, for no good reason.

As suggested by David Laight this patch now removes this timer update
from hot path by leaving the timer on and re-evaluating upon its
expiration if the heartbeat is still needed or not, similarly to what is
done for TCP. If it's not needed anymore the timer is re-scheduled to
the new timeout, considering the time already elapsed.

For this, we now record the last tx timestamp per transport, updated in
the same spots as hb timer was restarted on tx. Also split up
sctp_transport_reset_timers into sctp_transport_reset_t3_rtx and
sctp_transport_reset_hb_timer, so we can re-arm T3 without re-arming the
heartbeat one.

On loopback with MTU of 65535 and data chunks with 1636, so that we
have a considerable amount of chunks without stressing system calls,
netperf -t SCTP_STREAM -l 30, perf looked like this before:

Samples: 103K of event 'cpu-clock', Event count (approx.): 25833000000
  Overhead  Command  Shared Object      Symbol
+    6,15%  netperf  [kernel.vmlinux]   [k] copy_user_enhanced_fast_string
-    5,43%  netperf  [kernel.vmlinux]   [k] _raw_write_unlock_irqrestore
   - _raw_write_unlock_irqrestore
      - 96,54% _raw_spin_unlock_irqrestore
         - 36,14% mod_timer
            + 97,24% sctp_transport_reset_timers
            + 2,76% sctp_do_sm
         + 33,65% __wake_up_sync_key
         + 28,77% sctp_ulpq_tail_event
         + 1,40% del_timer
      - 1,84% mod_timer
         + 99,03% sctp_transport_reset_timers
         + 0,97% sctp_do_sm
      + 1,50% sctp_ulpq_tail_event

And after this patch, now with netperf -l 60:

Samples: 230K of event 'cpu-clock', Event count (approx.): 57707250000
  Overhead  Command  Shared Object      Symbol
+    5,65%  netperf  [kernel.vmlinux]   [k] memcpy_erms
+    5,59%  netperf  [kernel.vmlinux]   [k] copy_user_enhanced_fast_string
-    5,05%  netperf  [kernel.vmlinux]   [k] _raw_spin_unlock_irqrestore
   - _raw_spin_unlock_irqrestore
      + 49,89% __wake_up_sync_key
      + 45,68% sctp_ulpq_tail_event
      - 2,85% mod_timer
         + 76,51% sctp_transport_reset_t3_rtx
         + 23,49% sctp_do_sm
      + 1,55% del_timer
+    2,50%  netperf  [sctp]             [k] sctp_datamsg_from_user
+    2,26%  netperf  [sctp]             [k] sctp_sendmsg

Throughput-wise, from 6800mbps without the patch to 7050mbps with it,
~3.7%.

Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/structs.h | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 6df1ce7a411c..5a404c354f4c 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -847,6 +847,11 @@ struct sctp_transport {
 	 */
 	ktime_t last_time_heard;
 
+	/* When was the last time that we sent a chunk using this
+	 * transport? We use this to check for idle transports
+	 */
+	unsigned long last_time_sent;
+
 	/* Last time(in jiffies) when cwnd is reduced due to the congestion
 	 * indication based on ECNE chunk.
 	 */
@@ -952,7 +957,8 @@ void sctp_transport_route(struct sctp_transport *, union sctp_addr *,
 			  struct sctp_sock *);
 void sctp_transport_pmtu(struct sctp_transport *, struct sock *sk);
 void sctp_transport_free(struct sctp_transport *);
-void sctp_transport_reset_timers(struct sctp_transport *);
+void sctp_transport_reset_t3_rtx(struct sctp_transport *);
+void sctp_transport_reset_hb_timer(struct sctp_transport *);
 int sctp_transport_hold(struct sctp_transport *);
 void sctp_transport_put(struct sctp_transport *);
 void sctp_transport_update_rto(struct sctp_transport *, __u32);
-- 
cgit v1.2.3


From 9ab179d83b4e31ea277a123492e419067c2f129a Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Thu, 7 Apr 2016 11:10:06 -0700
Subject: net: vrf: Fix dst reference counting

Vivek reported a kernel exception deleting a VRF with an active
connection through it. The root cause is that the socket has a cached
reference to a dst that is destroyed. Converting the dst_destroy to
dst_release and letting proper reference counting kick in does not
work as the dst has a reference to the device which needs to be released
as well.

I talked to Hannes about this at netdev and he pointed out the ipv4 and
ipv6 dst handling has dst_ifdown for just this scenario. Rather than
continuing with the reinvented dst wheel in VRF just remove it and
leverage the ipv4 and ipv6 versions.

Fixes: 193125dbd8eb2 ("net: Introduce VRF device driver")
Fixes: 35402e3136634 ("net: Add IPv6 support to VRF device")

Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_route.h | 3 +++
 include/net/route.h     | 3 +++
 2 files changed, 6 insertions(+)

(limited to 'include')

diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 295d291269e2..54c779416eec 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -101,6 +101,9 @@ void fib6_force_start_gc(struct net *net);
 struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
 				    const struct in6_addr *addr, bool anycast);
 
+struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev,
+			       int flags);
+
 /*
  *	support functions for ND
  *
diff --git a/include/net/route.h b/include/net/route.h
index 9b0a523bb428..6de665bf1750 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -209,6 +209,9 @@ unsigned int inet_addr_type_dev_table(struct net *net,
 void ip_rt_multicast_event(struct in_device *);
 int ip_rt_ioctl(struct net *, unsigned int cmd, void __user *arg);
 void ip_rt_get_source(u8 *src, struct sk_buff *skb, struct rtable *rt);
+struct rtable *rt_dst_alloc(struct net_device *dev,
+			     unsigned int flags, u16 type,
+			     bool nopolicy, bool noxfrm, bool will_cache);
 
 struct in_ifaddr;
 void fib_add_ifaddr(struct in_ifaddr *);
-- 
cgit v1.2.3


From 1ecf689013b598918cd9a261a078e64571b60f90 Mon Sep 17 00:00:00 2001
From: stephen hemminger <stephen@networkplumber.org>
Date: Mon, 11 Apr 2016 13:39:08 -0700
Subject: devlink: add missing install of header

The new devlink.h in uapi was not being installed by
make headers_install

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/Kbuild | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index b71fd0b5cbad..813ffb2e22c9 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -96,6 +96,7 @@ header-y += cyclades.h
 header-y += cycx_cfm.h
 header-y += dcbnl.h
 header-y += dccp.h
+header-y += devlink.h
 header-y += dlmconstants.h
 header-y += dlm_device.h
 header-y += dlm.h
-- 
cgit v1.2.3


From b32e4482aadfd1322357f46d4ed8a990603664d9 Mon Sep 17 00:00:00 2001
From: Jaegeuk Kim <jaegeuk@kernel.org>
Date: Mon, 11 Apr 2016 15:51:57 -0700
Subject: fscrypto: don't let data integrity writebacks fail with ENOMEM

This patch fixes the issue introduced by the ext4 crypto fix in a same manner.
For F2FS, however, we flush the pending IOs and wait for a while to acquire free
memory.

Fixes: c9af28fdd4492 ("ext4 crypto: don't let data integrity writebacks fail with ENOMEM")
Cc: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 include/linux/fscrypto.h | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/fscrypto.h b/include/linux/fscrypto.h
index cd91f75de49b..6027f6bbb061 100644
--- a/include/linux/fscrypto.h
+++ b/include/linux/fscrypto.h
@@ -263,9 +263,9 @@ static inline void fscrypt_set_d_op(struct dentry *dentry)
 extern struct kmem_cache *fscrypt_info_cachep;
 int fscrypt_initialize(void);
 
-extern struct fscrypt_ctx *fscrypt_get_ctx(struct inode *);
+extern struct fscrypt_ctx *fscrypt_get_ctx(struct inode *, gfp_t);
 extern void fscrypt_release_ctx(struct fscrypt_ctx *);
-extern struct page *fscrypt_encrypt_page(struct inode *, struct page *);
+extern struct page *fscrypt_encrypt_page(struct inode *, struct page *, gfp_t);
 extern int fscrypt_decrypt_page(struct page *);
 extern void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *, struct bio *);
 extern void fscrypt_pullback_bio_page(struct page **, bool);
@@ -299,7 +299,8 @@ extern int fscrypt_fname_usr_to_disk(struct inode *, const struct qstr *,
 #endif
 
 /* crypto.c */
-static inline struct fscrypt_ctx *fscrypt_notsupp_get_ctx(struct inode *i)
+static inline struct fscrypt_ctx *fscrypt_notsupp_get_ctx(struct inode *i,
+							gfp_t f)
 {
 	return ERR_PTR(-EOPNOTSUPP);
 }
@@ -310,7 +311,7 @@ static inline void fscrypt_notsupp_release_ctx(struct fscrypt_ctx *c)
 }
 
 static inline struct page *fscrypt_notsupp_encrypt_page(struct inode *i,
-						struct page *p)
+						struct page *p, gfp_t f)
 {
 	return ERR_PTR(-EOPNOTSUPP);
 }
-- 
cgit v1.2.3


From 1363074667a6b7d0507527742ccd7bbed5e3ceaa Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Tue, 12 Apr 2016 12:27:09 +0200
Subject: USB: uas: Add a new NO_REPORT_LUNS quirk

Add a new NO_REPORT_LUNS quirk and set it for Seagate drives with
an usb-id of: 0bc2:331a, as these will fail to respond to a
REPORT_LUNS command.

Cc: stable@vger.kernel.org
Reported-and-tested-by: David Webb <djw@noc.ac.uk>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb_usual.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/usb_usual.h b/include/linux/usb_usual.h
index 7f5f78bd15ad..245f57dbbb61 100644
--- a/include/linux/usb_usual.h
+++ b/include/linux/usb_usual.h
@@ -79,6 +79,8 @@
 		/* Cannot handle MI_REPORT_SUPPORTED_OPERATION_CODES */	\
 	US_FLAG(MAX_SECTORS_240,	0x08000000)		\
 		/* Sets max_sectors to 240 */			\
+	US_FLAG(NO_REPORT_LUNS,	0x10000000)			\
+		/* Cannot handle REPORT_LUNS */			\
 
 #define US_FLAG(name, value)	US_FL_##name = value ,
 enum { US_DO_ALL_FLAGS };
-- 
cgit v1.2.3


From cba2e47abcbd80e3f46f460899290402f98090ec Mon Sep 17 00:00:00 2001
From: Toshi Kani <toshi.kani@hpe.com>
Date: Tue, 12 Apr 2016 18:10:52 -0600
Subject: pmem: fix BUG() error in pmem.h:48 on X86_32

After 'commit fc0c2028135c ("x86, pmem: use memcpy_mcsafe()
for memcpy_from_pmem()")', probing a PMEM device hits the BUG()
error below on X86_32 kernel.

 kernel BUG at include/linux/pmem.h:48!

memcpy_from_pmem() calls arch_memcpy_from_pmem(), which is
unimplemented since CONFIG_ARCH_HAS_PMEM_API is undefined on
X86_32.

Fix the BUG() error by adding default_memcpy_from_pmem().

Acked-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Toshi Kani <toshi.kani@hpe.com>
Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
---
 include/linux/pmem.h | 22 ++++++++++++++++------
 1 file changed, 16 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/pmem.h b/include/linux/pmem.h
index ac6d872ce067..57d146fe44dd 100644
--- a/include/linux/pmem.h
+++ b/include/linux/pmem.h
@@ -72,6 +72,18 @@ static inline void arch_invalidate_pmem(void __pmem *addr, size_t size)
 }
 #endif
 
+static inline bool arch_has_pmem_api(void)
+{
+	return IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API);
+}
+
+static inline int default_memcpy_from_pmem(void *dst, void __pmem const *src,
+		size_t size)
+{
+	memcpy(dst, (void __force *) src, size);
+	return 0;
+}
+
 /*
  * memcpy_from_pmem - read from persistent memory with error handling
  * @dst: destination buffer
@@ -83,12 +95,10 @@ static inline void arch_invalidate_pmem(void __pmem *addr, size_t size)
 static inline int memcpy_from_pmem(void *dst, void __pmem const *src,
 		size_t size)
 {
-	return arch_memcpy_from_pmem(dst, src, size);
-}
-
-static inline bool arch_has_pmem_api(void)
-{
-	return IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API);
+	if (arch_has_pmem_api())
+		return arch_memcpy_from_pmem(dst, src, size);
+	else
+		return default_memcpy_from_pmem(dst, src, size);
 }
 
 /**
-- 
cgit v1.2.3


From 34dbbcdbf63360661ff7bda6c5f52f99ac515f92 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Thu, 14 Apr 2016 11:22:00 -0700
Subject: Make file credentials available to the seqfile interfaces

A lot of seqfile users seem to be using things like %pK that uses the
credentials of the current process, but that is actually completely
wrong for filesystem interfaces.

The unix semantics for permission checking files is to check permissions
at _open_ time, not at read or write time, and that is not just a small
detail: passing off stdin/stdout/stderr to a suid application and making
the actual IO happen in privileged context is a classic exploit
technique.

So if we want to be able to look at permissions at read time, we need to
use the file open credentials, not the current ones.  Normal file
accesses can just use "f_cred" (or any of the helper functions that do
that, like file_ns_capable()), but the seqfile interfaces do not have
any such options.

It turns out that seq_file _does_ save away the user_ns information of
the file, though.  Since user_ns is just part of the full credential
information, replace that special case with saving off the cred pointer
instead, and suddenly seq_file has all the permission information it
needs.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/seq_file.h | 13 ++++---------
 1 file changed, 4 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h
index dde00defbaa5..f3d45dd42695 100644
--- a/include/linux/seq_file.h
+++ b/include/linux/seq_file.h
@@ -7,13 +7,10 @@
 #include <linux/mutex.h>
 #include <linux/cpumask.h>
 #include <linux/nodemask.h>
+#include <linux/fs.h>
+#include <linux/cred.h>
 
 struct seq_operations;
-struct file;
-struct path;
-struct inode;
-struct dentry;
-struct user_namespace;
 
 struct seq_file {
 	char *buf;
@@ -27,9 +24,7 @@ struct seq_file {
 	struct mutex lock;
 	const struct seq_operations *op;
 	int poll_event;
-#ifdef CONFIG_USER_NS
-	struct user_namespace *user_ns;
-#endif
+	const struct file *file;
 	void *private;
 };
 
@@ -147,7 +142,7 @@ int seq_release_private(struct inode *, struct file *);
 static inline struct user_namespace *seq_user_ns(struct seq_file *seq)
 {
 #ifdef CONFIG_USER_NS
-	return seq->user_ns;
+	return seq->file->f_cred->user_ns;
 #else
 	extern struct user_namespace init_user_ns;
 	return &init_user_ns;
-- 
cgit v1.2.3


From 33c162a980fe03498fcecb917f618ad7e7c55e61 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Mon, 11 Apr 2016 15:29:36 -0700
Subject: ipv6: datagram: Update dst cache of a connected datagram sk during
 pmtu update

There is a case in connected UDP socket such that
getsockopt(IPV6_MTU) will return a stale MTU value. The reproducible
sequence could be the following:
1. Create a connected UDP socket
2. Send some datagrams out
3. Receive a ICMPV6_PKT_TOOBIG
4. No new outgoing datagrams to trigger the sk_dst_check()
   logic to update the sk->sk_dst_cache.
5. getsockopt(IPV6_MTU) returns the mtu from the invalid
   sk->sk_dst_cache instead of the newly created RTF_CACHE clone.

This patch updates the sk->sk_dst_cache for a connected datagram sk
during pmtu-update code path.

Note that the sk->sk_v6_daddr is used to do the route lookup
instead of skb->data (i.e. iph).  It is because a UDP socket can become
connected after sending out some datagrams in un-connected state.  or
It can be connected multiple times to different destinations.  Hence,
iph may not be related to where sk is currently connected to.

It is done under '!sock_owned_by_user(sk)' condition because
the user may make another ip6_datagram_connect()  (i.e changing
the sk->sk_v6_daddr) while dst lookup is happening in the pmtu-update
code path.

For the sock_owned_by_user(sk) == true case, the next patch will
introduce a release_cb() which will update the sk->sk_dst_cache.

Test:

Server (Connected UDP Socket):
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Route Details:
[root@arch-fb-vm1 ~]# ip -6 r show | egrep '2fac'
2fac::/64 dev eth0  proto kernel  metric 256  pref medium
2fac:face::/64 via 2fac::face dev eth0  metric 1024  pref medium

A simple python code to create a connected UDP socket:

import socket
import errno

HOST = '2fac::1'
PORT = 8080

s = socket.socket(socket.AF_INET6, socket.SOCK_DGRAM)
s.bind((HOST, PORT))
s.connect(('2fac:face::face', 53))
print("connected")
while True:
    try:
	data = s.recv(1024)
    except socket.error as se:
	if se.errno == errno.EMSGSIZE:
		pmtu = s.getsockopt(41, 24)
		print("PMTU:%d" % pmtu)
		break
s.close()

Python program output after getting a ICMPV6_PKT_TOOBIG:
[root@arch-fb-vm1 ~]# python2 ~/devshare/kernel/tasks/fib6/udp-connect-53-8080.py
connected
PMTU:1300

Cache routes after recieving TOOBIG:
[root@arch-fb-vm1 ~]# ip -6 r show table cache
2fac:face::face via 2fac::face dev eth0  metric 0
    cache  expires 463sec mtu 1300 pref medium

Client (Send the ICMPV6_PKT_TOOBIG):
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
scapy is used to generate the TOOBIG message.  Here is the scapy script I have
used:

>>> p=Ether(src='da:75:4d:36:ac:32', dst='52:54:00:12:34:66', type=0x86dd)/IPv6(src='2fac::face', dst='2fac::1')/ICMPv6PacketTooBig(mtu=1300)/IPv6(src='2fac::
1',dst='2fac:face::face', nh='UDP')/UDP(sport=8080,dport=53)
>>> sendp(p, iface='qemubr0')

Fixes: 45e4fd26683c ("ipv6: Only create RTF_CACHE routes after encountering pmtu exception")
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Reported-by: Wei Wang <weiwan@google.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Wei Wang <weiwan@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index d0aeb97aec5d..fd02e90b1289 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -959,6 +959,7 @@ int compat_ipv6_getsockopt(struct sock *sk, int level, int optname,
 int ip6_datagram_connect(struct sock *sk, struct sockaddr *addr, int addr_len);
 int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *addr,
 				 int addr_len);
+int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr);
 
 int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len,
 		    int *addr_len);
-- 
cgit v1.2.3


From e646b657f6983017783914a951039e323120dc55 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Mon, 11 Apr 2016 15:29:37 -0700
Subject: ipv6: udp: Do a route lookup and update during release_cb

This patch adds a release_cb for UDPv6.  It does a route lookup
and updates sk->sk_dst_cache if it is needed.  It picks up the
left-over job from ip6_sk_update_pmtu() if the sk was owned
by user during the pmtu update.

It takes a rcu_read_lock to protect the __sk_dst_get() operations
because another thread may do ip6_dst_store() without taking the
sk lock (e.g. sendmsg).

Fixes: 45e4fd26683c ("ipv6: Only create RTF_CACHE routes after encountering pmtu exception")
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Reported-by: Wei Wang <weiwan@google.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Wei Wang <weiwan@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index fd02e90b1289..1be050ada8c5 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -960,6 +960,7 @@ int ip6_datagram_connect(struct sock *sk, struct sockaddr *addr, int addr_len);
 int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *addr,
 				 int addr_len);
 int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr);
+void ip6_datagram_release_cb(struct sock *sk);
 
 int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len,
 		    int *addr_len);
-- 
cgit v1.2.3


From d894ba18d4e449b3a7f6eb491f16c9e02933736e Mon Sep 17 00:00:00 2001
From: Craig Gallek <kraig@google.com>
Date: Tue, 12 Apr 2016 13:11:25 -0400
Subject: soreuseport: fix ordering for mixed v4/v6 sockets
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

With the SO_REUSEPORT socket option, it is possible to create sockets
in the AF_INET and AF_INET6 domains which are bound to the same IPv4 address.
This is only possible with SO_REUSEPORT and when not using IPV6_V6ONLY on
the AF_INET6 sockets.

Prior to the commits referenced below, an incoming IPv4 packet would
always be routed to a socket of type AF_INET when this mixed-mode was used.
After those changes, the same packet would be routed to the most recently
bound socket (if this happened to be an AF_INET6 socket, it would
have an IPv4 mapped IPv6 address).

The change in behavior occurred because the recent SO_REUSEPORT optimizations
short-circuit the socket scoring logic as soon as they find a match.  They
did not take into account the scoring logic that favors AF_INET sockets
over AF_INET6 sockets in the event of a tie.

To fix this problem, this patch changes the insertion order of AF_INET
and AF_INET6 addresses in the TCP and UDP socket lists when the sockets
have SO_REUSEPORT set.  AF_INET sockets will be inserted at the head of the
list and AF_INET6 sockets with SO_REUSEPORT set will always be inserted at
the tail of the list.  This will force AF_INET sockets to always be
considered first.

Fixes: e32ea7e74727 ("soreuseport: fast reuseport UDP socket selection")
Fixes: 125e80b88687 ("soreuseport: fast reuseport TCP socket selection")

Reported-by: Maciej Żenczykowski <maze@google.com>
Signed-off-by: Craig Gallek <kraig@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rculist_nulls.h | 39 +++++++++++++++++++++++++++++++++++++++
 include/net/sock.h            |  6 +++++-
 2 files changed, 44 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h
index 1c33dd7da4a7..4ae95f7e8597 100644
--- a/include/linux/rculist_nulls.h
+++ b/include/linux/rculist_nulls.h
@@ -98,6 +98,45 @@ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n,
 	if (!is_a_nulls(first))
 		first->pprev = &n->next;
 }
+
+/**
+ * hlist_nulls_add_tail_rcu
+ * @n: the element to add to the hash list.
+ * @h: the list to add to.
+ *
+ * Description:
+ * Adds the specified element to the end of the specified hlist_nulls,
+ * while permitting racing traversals.  NOTE: tail insertion requires
+ * list traversal.
+ *
+ * The caller must take whatever precautions are necessary
+ * (such as holding appropriate locks) to avoid racing
+ * with another list-mutation primitive, such as hlist_nulls_add_head_rcu()
+ * or hlist_nulls_del_rcu(), running on this same list.
+ * However, it is perfectly legal to run concurrently with
+ * the _rcu list-traversal primitives, such as
+ * hlist_nulls_for_each_entry_rcu(), used to prevent memory-consistency
+ * problems on Alpha CPUs.  Regardless of the type of CPU, the
+ * list-traversal primitive must be guarded by rcu_read_lock().
+ */
+static inline void hlist_nulls_add_tail_rcu(struct hlist_nulls_node *n,
+					struct hlist_nulls_head *h)
+{
+	struct hlist_nulls_node *i, *last = NULL;
+
+	for (i = hlist_nulls_first_rcu(h); !is_a_nulls(i);
+	     i = hlist_nulls_next_rcu(i))
+		last = i;
+
+	if (last) {
+		n->next = last->next;
+		n->pprev = &last->next;
+		rcu_assign_pointer(hlist_nulls_next_rcu(last), n);
+	} else {
+		hlist_nulls_add_head_rcu(n, h);
+	}
+}
+
 /**
  * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type
  * @tpos:	the type * to use as a loop cursor.
diff --git a/include/net/sock.h b/include/net/sock.h
index 255d3e03727b..121ffc115c4f 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -630,7 +630,11 @@ static inline void sk_add_node_rcu(struct sock *sk, struct hlist_head *list)
 
 static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
 {
-	hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list);
+	if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&
+	    sk->sk_family == AF_INET6)
+		hlist_nulls_add_tail_rcu(&sk->sk_nulls_node, list);
+	else
+		hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list);
 }
 
 static inline void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
-- 
cgit v1.2.3


From cb92148b58a49455f3a7204eba3aee09a8b7683c Mon Sep 17 00:00:00 2001
From: Hariprasad Shenai <hariprasad@chelsio.com>
Date: Fri, 15 Apr 2016 13:00:11 -0500
Subject: PCI: Add pci_set_vpd_size() to set VPD size

After 104daa71b396 ("PCI: Determine actual VPD size on first access"), the
PCI core computes the valid VPD size by parsing the VPD starting at offset
0x0.  We don't attempt to read past that valid size because that causes
some devices to crash.

However, some devices do have data past that valid size.  For example,
Chelsio adapters contain two VPD structures, and the driver needs both of
them.

Add pci_set_vpd_size().  If a driver knows it is safe to read past the end
of the VPD data structure at offset 0, it can use pci_set_vpd_size() to
allow access to as much data as it needs.

[bhelgaas: changelog, split patches, rename to pci_set_vpd_size() and
return int (not ssize_t)]
Fixes: 104daa71b396 ("PCI: Determine actual VPD size on first access")
Tested-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Casey Leedom <leedom@chelsio.com>
Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 include/linux/pci.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/pci.h b/include/linux/pci.h
index 004b8133417d..932ec74909c6 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1111,6 +1111,7 @@ void pci_unlock_rescan_remove(void);
 /* Vital product data routines */
 ssize_t pci_read_vpd(struct pci_dev *dev, loff_t pos, size_t count, void *buf);
 ssize_t pci_write_vpd(struct pci_dev *dev, loff_t pos, size_t count, const void *buf);
+int pci_set_vpd_size(struct pci_dev *dev, size_t len);
 
 /* Helper functions for low-level code (drivers/pci/setup-[bus,res].c) */
 resource_size_t pcibios_retrieve_fw_addr(struct pci_dev *dev, int idx);
-- 
cgit v1.2.3


From 67245ff332064c01b760afa7a384ccda024bfd24 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sat, 16 Apr 2016 15:16:07 -0700
Subject: devpts: clean up interface to pty drivers

This gets rid of the horrible notion of having that

    struct inode *ptmx_inode

be the linchpin of the interface between the pty code and devpts.

By de-emphasizing the ptmx inode, a lot of things actually get cleaner,
and we will have a much saner way forward.  In particular, this will
allow us to associate with any particular devpts instance at open-time,
and not be artificially tied to one particular ptmx inode.

The patch itself is actually fairly straightforward, and apart from some
locking and return path cleanups it's pretty mechanical:

 - the interfaces that devpts exposes all take "struct pts_fs_info *"
   instead of "struct inode *ptmx_inode" now.

   NOTE! The "struct pts_fs_info" thing is a completely opaque structure
   as far as the pty driver is concerned: it's still declared entirely
   internally to devpts. So the pty code can't actually access it in any
   way, just pass it as a "cookie" to the devpts code.

 - the "look up the pts fs info" is now a single clear operation, that
   also does the reference count increment on the pts superblock.

   So "devpts_add/del_ref()" is gone, and replaced by a "lookup and get
   ref" operation (devpts_get_ref(inode)), along with a "put ref" op
   (devpts_put_ref()).

 - the pty master "tty->driver_data" field now contains the pts_fs_info,
   not the ptmx inode.

 - because we don't care about the ptmx inode any more as some kind of
   base index, the ref counting can now drop the inode games - it just
   gets the ref on the superblock.

 - the pts_fs_info now has a back-pointer to the super_block. That's so
   that we can easily look up the information we actually need. Although
   quite often, the pts fs info was actually all we wanted, and not having
   to look it up based on some magical inode makes things more
   straightforward.

In particular, now that "devpts_get_ref(inode)" operation should really
be the *only* place we need to look up what devpts instance we're
associated with, and we do it exactly once, at ptmx_open() time.

The other side of this is that one ptmx node could now be associated
with multiple different devpts instances - you could have a single
/dev/ptmx node, and then have multiple mount namespaces with their own
instances of devpts mounted on /dev/pts/.  And that's all perfectly sane
in a model where we just look up the pts instance at open time.

This will eventually allow us to get rid of our odd single-vs-multiple
pts instance model, but this patch in itself changes no semantics, only
an internal binding model.

Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Peter Anvin <hpa@zytor.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Peter Hurley <peter@hurleysoftware.com>
Cc: Serge Hallyn <serge.hallyn@ubuntu.com>
Cc: Willy Tarreau <w@1wt.eu>
Cc: Aurelien Jarno <aurelien@aurel32.net>
Cc: Alan Cox <gnomes@lxorguk.ukuu.org.uk>
Cc: Jann Horn <jann@thejh.net>
Cc: Greg KH <greg@kroah.com>
Cc: Jiri Slaby <jslaby@suse.com>
Cc: Florian Weimer <fw@deneb.enyo.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/devpts_fs.h | 34 ++++++++++------------------------
 1 file changed, 10 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/include/linux/devpts_fs.h b/include/linux/devpts_fs.h
index e0ee0b3000b2..358a4db72a27 100644
--- a/include/linux/devpts_fs.h
+++ b/include/linux/devpts_fs.h
@@ -15,38 +15,24 @@
 
 #include <linux/errno.h>
 
+struct pts_fs_info;
+
 #ifdef CONFIG_UNIX98_PTYS
 
-int devpts_new_index(struct inode *ptmx_inode);
-void devpts_kill_index(struct inode *ptmx_inode, int idx);
-void devpts_add_ref(struct inode *ptmx_inode);
-void devpts_del_ref(struct inode *ptmx_inode);
+/* Look up a pts fs info and get a ref to it */
+struct pts_fs_info *devpts_get_ref(struct inode *, struct file *);
+void devpts_put_ref(struct pts_fs_info *);
+
+int devpts_new_index(struct pts_fs_info *);
+void devpts_kill_index(struct pts_fs_info *, int);
+
 /* mknod in devpts */
-struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index,
-		void *priv);
+struct inode *devpts_pty_new(struct pts_fs_info *, dev_t, int, void *);
 /* get private structure */
 void *devpts_get_priv(struct inode *pts_inode);
 /* unlink */
 void devpts_pty_kill(struct inode *inode);
 
-#else
-
-/* Dummy stubs in the no-pty case */
-static inline int devpts_new_index(struct inode *ptmx_inode) { return -EINVAL; }
-static inline void devpts_kill_index(struct inode *ptmx_inode, int idx) { }
-static inline void devpts_add_ref(struct inode *ptmx_inode) { }
-static inline void devpts_del_ref(struct inode *ptmx_inode) { }
-static inline struct inode *devpts_pty_new(struct inode *ptmx_inode,
-		dev_t device, int index, void *priv)
-{
-	return ERR_PTR(-EINVAL);
-}
-static inline void *devpts_get_priv(struct inode *pts_inode)
-{
-	return NULL;
-}
-static inline void devpts_pty_kill(struct inode *inode) { }
-
 #endif
 
 
-- 
cgit v1.2.3


From 2309236c13feae619572324efd3e910e66ef6bd0 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Date: Mon, 18 Apr 2016 14:37:10 +0300
Subject: cls_cgroup: get sk_classid only from full sockets

skb->sk could point to timewait or request socket which has no sk_classid.
Detected as "BUG: KASAN: slab-out-of-bounds in cls_cgroup_classify".

Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/cls_cgroup.h | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/cls_cgroup.h b/include/net/cls_cgroup.h
index c0a92e2c286d..74c9693d4941 100644
--- a/include/net/cls_cgroup.h
+++ b/include/net/cls_cgroup.h
@@ -17,6 +17,7 @@
 #include <linux/hardirq.h>
 #include <linux/rcupdate.h>
 #include <net/sock.h>
+#include <net/inet_sock.h>
 
 #ifdef CONFIG_CGROUP_NET_CLASSID
 struct cgroup_cls_state {
@@ -63,11 +64,13 @@ static inline u32 task_get_classid(const struct sk_buff *skb)
 	 * softirqs always disables bh.
 	 */
 	if (in_serving_softirq()) {
+		struct sock *sk = skb_to_full_sk(skb);
+
 		/* If there is an sock_cgroup_classid we'll use that. */
-		if (!skb->sk)
+		if (!sk || !sk_fullsock(sk))
 			return 0;
 
-		classid = sock_cgroup_classid(&skb->sk->sk_cgrp_data);
+		classid = sock_cgroup_classid(&sk->sk_cgrp_data);
 	}
 
 	return classid;
-- 
cgit v1.2.3


From 1d0fd42fa31d18ba0a3e0dd008c9e93e1cebe451 Mon Sep 17 00:00:00 2001
From: Wei Ni <wni@nvidia.com>
Date: Thu, 3 Mar 2016 17:33:46 +0800
Subject: thermal: consistently use int for trip temp

The commit 17e8351a7739 consistently use int for temperature,
however it missed a few in trip temperature and thermal_core.

In current codes, the trip->temperature used "unsigned long"
and zone->temperature used"int", if the temperature is negative
value, it will get wrong result when compare temperature with
trip temperature.

This patch can fix it.

Signed-off-by: Wei Ni <wni@nvidia.com>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 include/linux/thermal.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index a55d0523f75d..1b8a5a7876ce 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -352,8 +352,8 @@ struct thermal_zone_of_device_ops {
 
 struct thermal_trip {
 	struct device_node *np;
-	unsigned long int temperature;
-	unsigned long int hysteresis;
+	int temperature;
+	int hysteresis;
 	enum thermal_trip_type type;
 };
 
-- 
cgit v1.2.3


From fba7cd681b6155e2d93e7862fcd6f970336b83c3 Mon Sep 17 00:00:00 2001
From: Romain Perier <romain.perier@free-electrons.com>
Date: Thu, 14 Apr 2016 15:36:03 +0200
Subject: asm-generic/futex: Re-enable preemption in
 futex_atomic_cmpxchg_inatomic()

The recent decoupling of pagefault disable and preempt disable added an
explicit preempt_disable/enable() pair to the futex_atomic_cmpxchg_inatomic()
implementation in asm-generic/futex.h. But it forgot to add preempt_enable()
calls to the error handling code pathes, which results in a preemption count
imbalance.

This is observable on boot when the test for atomic_cmpxchg() is calling
futex_atomic_cmpxchg_inatomic() on a NULL pointer.

Add the missing preempt_enable() calls to the error handling code pathes.

[ tglx: Massaged changelog ]

Fixes: d9b9ff8c1889 ("sched/preempt, futex: Disable preemption in UP futex_atomic_cmpxchg_inatomic() explicitly")
Signed-off-by: Romain Perier <romain.perier@free-electrons.com>
Cc: linux-arch@vger.kernel.org
Cc: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: http://lkml.kernel.org/r/1460640963-690-1-git-send-email-romain.perier@free-electrons.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/asm-generic/futex.h | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/asm-generic/futex.h b/include/asm-generic/futex.h
index e56272c919b5..bf2d34c9d804 100644
--- a/include/asm-generic/futex.h
+++ b/include/asm-generic/futex.h
@@ -108,11 +108,15 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	u32 val;
 
 	preempt_disable();
-	if (unlikely(get_user(val, uaddr) != 0))
+	if (unlikely(get_user(val, uaddr) != 0)) {
+		preempt_enable();
 		return -EFAULT;
+	}
 
-	if (val == oldval && unlikely(put_user(newval, uaddr) != 0))
+	if (val == oldval && unlikely(put_user(newval, uaddr) != 0)) {
+		preempt_enable();
 		return -EFAULT;
+	}
 
 	*uval = val;
 	preempt_enable();
-- 
cgit v1.2.3


From cfea5a688eb37bcd1081255df9f9f777f4e61999 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Tue, 19 Apr 2016 22:39:29 -0700
Subject: tcp: Merge tx_flags and tskey in tcp_shifted_skb

After receiving sacks, tcp_shifted_skb() will collapse
skbs if possible.  tx_flags and tskey also have to be
merged.

This patch reuses the tcp_skb_collapse_tstamp() to handle
them.

BPF Output Before:
~~~~~
<no-output-due-to-missing-tstamp-event>

BPF Output After:
~~~~~
<...>-2024  [007] d.s.    88.644374: : ee_data:14599

Packetdrill Script:
~~~~~
+0 `sysctl -q -w net.ipv4.tcp_min_tso_segs=10`
+0 `sysctl -q -w net.ipv4.tcp_no_metrics_save=1`
+0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+0 bind(3, ..., ...) = 0
+0 listen(3, 1) = 0

0.100 < S 0:0(0) win 32792 <mss 1460,sackOK,nop,nop,nop,wscale 7>
0.100 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 7>
0.200 < . 1:1(0) ack 1 win 257
0.200 accept(3, ..., ...) = 4
+0 setsockopt(4, SOL_TCP, TCP_NODELAY, [1], 4) = 0

0.200 write(4, ..., 1460) = 1460
+0 setsockopt(4, SOL_SOCKET, 37, [2688], 4) = 0
0.200 write(4, ..., 13140) = 13140

0.200 > P. 1:1461(1460) ack 1
0.200 > . 1461:8761(7300) ack 1
0.200 > P. 8761:14601(5840) ack 1

0.300 < . 1:1(0) ack 1 win 257 <sack 1461:14601,nop,nop>
0.300 > P. 1:1461(1460) ack 1
0.400 < . 1:1(0) ack 14601 win 257

0.400 close(4) = 0
0.400 > F. 14601:14601(0) ack 1
0.500 < F. 1:1(0) ack 14602 win 257
0.500 > . 14602:14602(0) ack 2

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Tested-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index b91370f61be6..6db10228113f 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -552,6 +552,8 @@ void tcp_send_ack(struct sock *sk);
 void tcp_send_delayed_ack(struct sock *sk);
 void tcp_send_loss_probe(struct sock *sk);
 bool tcp_schedule_loss_probe(struct sock *sk);
+void tcp_skb_collapse_tstamp(struct sk_buff *skb,
+			     const struct sk_buff *next_skb);
 
 /* tcp_input.c */
 void tcp_resume_early_retransmit(struct sock *sk);
-- 
cgit v1.2.3


From 4bfd2e6e53435a214888fd35e230157a38ffc6a0 Mon Sep 17 00:00:00 2001
From: Daniel Jurgens <danielj@mellanox.com>
Date: Wed, 20 Apr 2016 16:01:16 +0300
Subject: net/mlx4_core: Avoid repeated calls to pci enable/disable

Maintain the PCI status and provide wrappers for enabling and disabling
the PCI device.  Performing the actions more than once without doing
its opposite results in warning logs.

This occurred when EEH hotplugged the device causing a warning for
disabling an already disabled device.

Fixes: 2ba5fbd62b25 ('net/mlx4_core: Handle AER flow properly')
Signed-off-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/mlx4/device.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 8541a913f6a3..d1f904c8b2cb 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -828,6 +828,11 @@ struct mlx4_vf_dev {
 	u8			n_ports;
 };
 
+enum mlx4_pci_status {
+	MLX4_PCI_STATUS_DISABLED,
+	MLX4_PCI_STATUS_ENABLED,
+};
+
 struct mlx4_dev_persistent {
 	struct pci_dev	       *pdev;
 	struct mlx4_dev	       *dev;
@@ -841,6 +846,8 @@ struct mlx4_dev_persistent {
 	u8		state;
 	struct mutex	interface_state_mutex; /* protect SW state */
 	u8	interface_state;
+	struct mutex		pci_status_mutex; /* sync pci state */
+	enum mlx4_pci_status	pci_status;
 };
 
 struct mlx4_dev {
-- 
cgit v1.2.3


From 221004c66a58949a0f25c937a6789c0839feb530 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhc@lemote.com>
Date: Tue, 19 Apr 2016 19:19:11 +0800
Subject: drm: Loongson-3 doesn't fully support wc memory

Signed-off-by: Huacai Chen <chenhc@lemote.com>
Cc: stable@vger.kernel.org
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 include/drm/drm_cache.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/drm/drm_cache.h b/include/drm/drm_cache.h
index 461a0558bca4..cebecff536a3 100644
--- a/include/drm/drm_cache.h
+++ b/include/drm/drm_cache.h
@@ -39,6 +39,8 @@ static inline bool drm_arch_can_wc_memory(void)
 {
 #if defined(CONFIG_PPC) && !defined(CONFIG_NOT_COHERENT_CACHE)
 	return false;
+#elif defined(CONFIG_MIPS) && defined(CONFIG_CPU_LOONGSON3)
+	return false;
 #else
 	return true;
 #endif
-- 
cgit v1.2.3


From 987aedb5d6f6e10c5203c6d0aab9a60ec22c7e93 Mon Sep 17 00:00:00 2001
From: Andre Przywara <andre.przywara@arm.com>
Date: Mon, 11 Apr 2016 10:17:46 +0100
Subject: generic syscalls: wire up preadv2 and pwritev2 syscalls

These new syscalls are implemented as generic code, so enable them for
architectures like arm64 which use the generic syscall table.

Signed-off-by: Andre Przywara <andre.przywara@arm.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 include/uapi/asm-generic/unistd.h | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 2622b33fb2ec..6e0f5f01734c 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -717,9 +717,13 @@ __SYSCALL(__NR_membarrier, sys_membarrier)
 __SYSCALL(__NR_mlock2, sys_mlock2)
 #define __NR_copy_file_range 285
 __SYSCALL(__NR_copy_file_range, sys_copy_file_range)
+#define __NR_preadv2 286
+__SYSCALL(__NR_preadv2, sys_preadv2)
+#define __NR_pwritev2 287
+__SYSCALL(__NR_pwritev2, sys_pwritev2)
 
 #undef __NR_syscalls
-#define __NR_syscalls 286
+#define __NR_syscalls 288
 
 /*
  * All syscalls below here should go away really,
-- 
cgit v1.2.3