[added to the 4.1 stable tree] af_unix: Fix splice-bind deadlock

[added to the 4.1 stable tree] af_unix: Fix splice-bind deadlock

[Sasha Levin]

From: Rainer Weikusat <rweikusat@mobileactivedefense.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit c845acb324aa85a39650a14e7696982ceea75dc1 ]

On 2015/11/06, Dmitry Vyukov reported a deadlock involving the splice
system call and AF_UNIX sockets,

http://lists.openwall.net/netdev/2015/11/06/24

The situation was analyzed as

(a while ago) A: socketpair()
B: splice() from a pipe to /mnt/regular_file
	does sb_start_write() on /mnt
C: try to freeze /mnt
	wait for B to finish with /mnt
A: bind() try to bind our socket to /mnt/new_socket_name
	lock our socket, see it not bound yet
	decide that it needs to create something in /mnt
	try to do sb_start_write() on /mnt, block (it's
	waiting for C).
D: splice() from the same pipe to our socket
	lock the pipe, see that socket is connected
	try to lock the socket, block waiting for A
B:	get around to actually feeding a chunk from
	pipe to file, try to lock the pipe.  Deadlock.

on 2015/11/10 by Al Viro,

http://lists.openwall.net/netdev/2015/11/10/4

The patch fixes this by removing the kern_path_create related code from
unix_mknod and executing it as part of unix_bind prior acquiring the
readlock of the socket in question. This means that A (as used above)
will sb_start_write on /mnt before it acquires the readlock, hence, it
won't indirectly block B which first did a sb_start_write and then
waited for a thread trying to acquire the readlock. Consequently, A
being blocked by C waiting for B won't cause a deadlock anymore
(effectively, both A and B acquire two locks in opposite order in the
situation described above).

Dmitry Vyukov(<dvyukov@google.com>) tested the original patch.

Signed-off-by: Rainer Weikusat <rweikusat@mobileactivedefense.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/unix/af_unix.c | 66 +++++++++++++++++++++++++++++++++---------------------
 1 file changed, 40 insertions(+), 26 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 535a642..03da879 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -935,32 +935,20 @@ fail:
 	return NULL;
 }
 
-static int unix_mknod(const char *sun_path, umode_t mode, struct path *res)
+static int unix_mknod(struct dentry *dentry, struct path *path, umode_t mode,
+		      struct path *res)
 {
-	struct dentry *dentry;
-	struct path path;
-	int err = 0;
-	/*
-	 * Get the parent directory, calculate the hash for last
-	 * component.
-	 */
-	dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0);
-	err = PTR_ERR(dentry);
-	if (IS_ERR(dentry))
-		return err;
+	int err;
 
-	/*
-	 * All right, let's create it.
-	 */
-	err = security_path_mknod(&path, dentry, mode, 0);
+	err = security_path_mknod(path, dentry, mode, 0);
 	if (!err) {
-		err = vfs_mknod(d_inode(path.dentry), dentry, mode, 0);
+		err = vfs_mknod(d_inode(path->dentry), dentry, mode, 0);
 		if (!err) {
-			res->mnt = mntget(path.mnt);
+			res->mnt = mntget(path->mnt);
 			res->dentry = dget(dentry);
 		}
 	}
-	done_path_create(&path, dentry);
+
 	return err;
 }
 
@@ -971,10 +959,12 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	struct unix_sock *u = unix_sk(sk);
 	struct sockaddr_un *sunaddr = (struct sockaddr_un *)uaddr;
 	char *sun_path = sunaddr->sun_path;
-	int err;
+	int err, name_err;
 	unsigned int hash;
 	struct unix_address *addr;
 	struct hlist_head *list;
+	struct path path;
+	struct dentry *dentry;
 
 	err = -EINVAL;
 	if (sunaddr->sun_family != AF_UNIX)
@@ -990,14 +980,34 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		goto out;
 	addr_len = err;
 
+	name_err = 0;
+	dentry = NULL;
+	if (sun_path[0]) {
+		/* Get the parent directory, calculate the hash for last
+		 * component.
+		 */
+		dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0);
+
+		if (IS_ERR(dentry)) {
+			/* delay report until after 'already bound' check */
+			name_err = PTR_ERR(dentry);
+			dentry = NULL;
+		}
+	}
+
 	err = mutex_lock_interruptible(&u->readlock);
 	if (err)
-		goto out;
+		goto out_path;
 
 	err = -EINVAL;
 	if (u->addr)
 		goto out_up;
 
+	if (name_err) {
+		err = name_err == -EEXIST ? -EADDRINUSE : name_err;
+		goto out_up;
+	}
+
 	err = -ENOMEM;
 	addr = kmalloc(sizeof(*addr)+addr_len, GFP_KERNEL);
 	if (!addr)
@@ -1008,11 +1018,11 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	addr->hash = hash ^ sk->sk_type;
 	atomic_set(&addr->refcnt, 1);
 
-	if (sun_path[0]) {
-		struct path path;
+	if (dentry) {
+		struct path u_path;
 		umode_t mode = S_IFSOCK |
 		       (SOCK_INODE(sock)->i_mode & ~current_umask());
-		err = unix_mknod(sun_path, mode, &path);
+		err = unix_mknod(dentry, &path, mode, &u_path);
 		if (err) {
 			if (err == -EEXIST)
 				err = -EADDRINUSE;
@@ -1020,9 +1030,9 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 			goto out_up;
 		}
 		addr->hash = UNIX_HASH_SIZE;
-		hash = d_backing_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE-1);
+		hash = d_backing_inode(dentry)->i_ino & (UNIX_HASH_SIZE - 1);
 		spin_lock(&unix_table_lock);
-		u->path = path;
+		u->path = u_path;
 		list = &unix_socket_table[hash];
 	} else {
 		spin_lock(&unix_table_lock);
@@ -1045,6 +1055,10 @@ out_unlock:
 	spin_unlock(&unix_table_lock);
 out_up:
 	mutex_unlock(&u->readlock);
+out_path:
+	if (dentry)
+		done_path_create(&path, dentry);
+
 out:
 	return err;
 }
-- 
2.5.0

[added to the 4.1 stable tree] percpu: fix synchronization between chunk->map_extend_work and chunk destruction

[Sasha Levin]

From: Tejun Heo <tj@kernel.org>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 4f996e234dad488e5d9ba0858bc1bae12eff82c3 ]

Atomic allocations can trigger async map extensions which is serviced
by chunk->map_extend_work.  pcpu_balance_work which is responsible for
destroying idle chunks wasn't synchronizing properly against
chunk->map_extend_work and may end up freeing the chunk while the work
item is still in flight.

This patch fixes the bug by rolling async map extension operations
into pcpu_balance_work.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-and-tested-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Reported-by: Vlastimil Babka <vbabka@suse.cz>
Reported-by: Sasha Levin <sasha.levin@oracle.com>
Cc: stable@vger.kernel.org # v3.18+
Fixes: 9c824b6a172c ("percpu: make sure chunk->map array has available space")
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 mm/percpu.c | 57 ++++++++++++++++++++++++++++++++++++---------------------
 1 file changed, 36 insertions(+), 21 deletions(-)

diff --git a/mm/percpu.c b/mm/percpu.c
index 2dd7448..4c2615e 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -110,7 +110,7 @@ struct pcpu_chunk {
 	int			map_used;	/* # of map entries used before the sentry */
 	int			map_alloc;	/* # of map entries allocated */
 	int			*map;		/* allocation map */
-	struct work_struct	map_extend_work;/* async ->map[] extension */
+	struct list_head	map_extend_list;/* on pcpu_map_extend_chunks */
 
 	void			*data;		/* chunk data */
 	int			first_free;	/* no free below this */
@@ -164,6 +164,9 @@ static DEFINE_MUTEX(pcpu_alloc_mutex);	/* chunk create/destroy, [de]pop */
 
 static struct list_head *pcpu_slot __read_mostly; /* chunk list slots */
 
+/* chunks which need their map areas extended, protected by pcpu_lock */
+static LIST_HEAD(pcpu_map_extend_chunks);
+
 /*
  * The number of empty populated pages, protected by pcpu_lock.  The
  * reserved chunk doesn't contribute to the count.
@@ -397,13 +400,19 @@ static int pcpu_need_to_extend(struct pcpu_chunk *chunk, bool is_atomic)
 {
 	int margin, new_alloc;
 
+	lockdep_assert_held(&pcpu_lock);
+
 	if (is_atomic) {
 		margin = 3;
 
 		if (chunk->map_alloc <
-		    chunk->map_used + PCPU_ATOMIC_MAP_MARGIN_LOW &&
-		    pcpu_async_enabled)
-			schedule_work(&chunk->map_extend_work);
+		    chunk->map_used + PCPU_ATOMIC_MAP_MARGIN_LOW) {
+			if (list_empty(&chunk->map_extend_list)) {
+				list_add_tail(&chunk->map_extend_list,
+					      &pcpu_map_extend_chunks);
+				pcpu_schedule_balance_work();
+			}
+		}
 	} else {
 		margin = PCPU_ATOMIC_MAP_MARGIN_HIGH;
 	}
@@ -469,20 +478,6 @@ out_unlock:
 	return 0;
 }
 
-static void pcpu_map_extend_workfn(struct work_struct *work)
-{
-	struct pcpu_chunk *chunk = container_of(work, struct pcpu_chunk,
-						map_extend_work);
-	int new_alloc;
-
-	spin_lock_irq(&pcpu_lock);
-	new_alloc = pcpu_need_to_extend(chunk, false);
-	spin_unlock_irq(&pcpu_lock);
-
-	if (new_alloc)
-		pcpu_extend_area_map(chunk, new_alloc);
-}
-
 /**
  * pcpu_fit_in_area - try to fit the requested allocation in a candidate area
  * @chunk: chunk the candidate area belongs to
@@ -742,7 +737,7 @@ static struct pcpu_chunk *pcpu_alloc_chunk(void)
 	chunk->map_used = 1;
 
 	INIT_LIST_HEAD(&chunk->list);
-	INIT_WORK(&chunk->map_extend_work, pcpu_map_extend_workfn);
+	INIT_LIST_HEAD(&chunk->map_extend_list);
 	chunk->free_size = pcpu_unit_size;
 	chunk->contig_hint = pcpu_unit_size;
 
@@ -1131,6 +1126,7 @@ static void pcpu_balance_workfn(struct work_struct *work)
 		if (chunk == list_first_entry(free_head, struct pcpu_chunk, list))
 			continue;
 
+		list_del_init(&chunk->map_extend_list);
 		list_move(&chunk->list, &to_free);
 	}
 
@@ -1148,6 +1144,25 @@ static void pcpu_balance_workfn(struct work_struct *work)
 		pcpu_destroy_chunk(chunk);
 	}
 
+	/* service chunks which requested async area map extension */
+	do {
+		int new_alloc = 0;
+
+		spin_lock_irq(&pcpu_lock);
+
+		chunk = list_first_entry_or_null(&pcpu_map_extend_chunks,
+					struct pcpu_chunk, map_extend_list);
+		if (chunk) {
+			list_del_init(&chunk->map_extend_list);
+			new_alloc = pcpu_need_to_extend(chunk, false);
+		}
+
+		spin_unlock_irq(&pcpu_lock);
+
+		if (new_alloc)
+			pcpu_extend_area_map(chunk, new_alloc);
+	} while (chunk);
+
 	/*
 	 * Ensure there are certain number of free populated pages for
 	 * atomic allocs.  Fill up from the most packed so that atomic
@@ -1646,7 +1661,7 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 	 */
 	schunk = memblock_virt_alloc(pcpu_chunk_struct_size, 0);
 	INIT_LIST_HEAD(&schunk->list);
-	INIT_WORK(&schunk->map_extend_work, pcpu_map_extend_workfn);
+	INIT_LIST_HEAD(&schunk->map_extend_list);
 	schunk->base_addr = base_addr;
 	schunk->map = smap;
 	schunk->map_alloc = ARRAY_SIZE(smap);
@@ -1676,7 +1691,7 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 	if (dyn_size) {
 		dchunk = memblock_virt_alloc(pcpu_chunk_struct_size, 0);
 		INIT_LIST_HEAD(&dchunk->list);
-		INIT_WORK(&dchunk->map_extend_work, pcpu_map_extend_workfn);
+		INIT_LIST_HEAD(&dchunk->map_extend_list);
 		dchunk->base_addr = base_addr;
 		dchunk->map = dmap;
 		dchunk->map_alloc = ARRAY_SIZE(dmap);
-- 
2.5.0

[added to the 4.1 stable tree] percpu: fix synchronization between synchronous map extension and chunk destruction

[Sasha Levin]

From: Tejun Heo <tj@kernel.org>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 6710e594f71ccaad8101bc64321152af7cd9ea28 ]

For non-atomic allocations, pcpu_alloc() can try to extend the area
map synchronously after dropping pcpu_lock; however, the extension
wasn't synchronized against chunk destruction and the chunk might get
freed while extension is in progress.

This patch fixes the bug by putting most of non-atomic allocations
under pcpu_alloc_mutex to synchronize against pcpu_balance_work which
is responsible for async chunk management including destruction.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-and-tested-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Reported-by: Vlastimil Babka <vbabka@suse.cz>
Reported-by: Sasha Levin <sasha.levin@oracle.com>
Cc: stable@vger.kernel.org # v3.18+
Fixes: 1a4d76076cda ("percpu: implement asynchronous chunk population")
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 mm/percpu.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/mm/percpu.c b/mm/percpu.c
index 4c2615e..b976175 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -160,7 +160,7 @@ static struct pcpu_chunk *pcpu_reserved_chunk;
 static int pcpu_reserved_chunk_limit;
 
 static DEFINE_SPINLOCK(pcpu_lock);	/* all internal data structures */
-static DEFINE_MUTEX(pcpu_alloc_mutex);	/* chunk create/destroy, [de]pop */
+static DEFINE_MUTEX(pcpu_alloc_mutex);	/* chunk create/destroy, [de]pop, map ext */
 
 static struct list_head *pcpu_slot __read_mostly; /* chunk list slots */
 
@@ -446,6 +446,8 @@ static int pcpu_extend_area_map(struct pcpu_chunk *chunk, int new_alloc)
 	size_t old_size = 0, new_size = new_alloc * sizeof(new[0]);
 	unsigned long flags;
 
+	lockdep_assert_held(&pcpu_alloc_mutex);
+
 	new = pcpu_mem_zalloc(new_size);
 	if (!new)
 		return -ENOMEM;
@@ -892,6 +894,9 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
 		return NULL;
 	}
 
+	if (!is_atomic)
+		mutex_lock(&pcpu_alloc_mutex);
+
 	spin_lock_irqsave(&pcpu_lock, flags);
 
 	/* serve reserved allocations from the reserved chunk if available */
@@ -964,12 +969,9 @@ restart:
 	if (is_atomic)
 		goto fail;
 
-	mutex_lock(&pcpu_alloc_mutex);
-
 	if (list_empty(&pcpu_slot[pcpu_nr_slots - 1])) {
 		chunk = pcpu_create_chunk();
 		if (!chunk) {
-			mutex_unlock(&pcpu_alloc_mutex);
 			err = "failed to allocate new chunk";
 			goto fail;
 		}
@@ -980,7 +982,6 @@ restart:
 		spin_lock_irqsave(&pcpu_lock, flags);
 	}
 
-	mutex_unlock(&pcpu_alloc_mutex);
 	goto restart;
 
 area_found:
@@ -990,8 +991,6 @@ area_found:
 	if (!is_atomic) {
 		int page_start, page_end, rs, re;
 
-		mutex_lock(&pcpu_alloc_mutex);
-
 		page_start = PFN_DOWN(off);
 		page_end = PFN_UP(off + size);
 
@@ -1002,7 +1001,6 @@ area_found:
 
 			spin_lock_irqsave(&pcpu_lock, flags);
 			if (ret) {
-				mutex_unlock(&pcpu_alloc_mutex);
 				pcpu_free_area(chunk, off, &occ_pages);
 				err = "failed to populate";
 				goto fail_unlock;
@@ -1042,6 +1040,8 @@ fail:
 		/* see the flag handling in pcpu_blance_workfn() */
 		pcpu_atomic_alloc_failed = true;
 		pcpu_schedule_balance_work();
+	} else {
+		mutex_unlock(&pcpu_alloc_mutex);
 	}
 	return NULL;
 }
-- 
2.5.0

[added to the 4.1 stable tree] cgroup: remove redundant cleanup in css_create

[Sasha Levin]

From: Wenwei Tao <ww.tao0320@gmail.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit b00c52dae6d9ee8d0f2407118ef6544ae5524781 ]

When create css failed, before call css_free_rcu_fn, we remove the css
id and exit the percpu_ref, but we will do these again in
css_free_work_fn, so they are redundant.  Especially the css id, that
would cause problem if we remove it twice, since it may be assigned to
another css after the first remove.

tj: This was broken by two commits updating the free path without
    synchronizing the creation failure path.  This can be easily
    triggered by trying to create more than 64k memory cgroups.

Signed-off-by: Wenwei Tao <ww.tao0320@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Fixes: 9a1049da9bd2 ("percpu-refcount: require percpu_ref to be exited explicitly")
Fixes: 01e586598b22 ("cgroup: release css->id after css_free")
Cc: stable@vger.kernel.org # v3.17+
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 kernel/cgroup.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 359da3a..530fecf 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4563,7 +4563,7 @@ static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss,
 
 	err = cgroup_idr_alloc(&ss->css_idr, NULL, 2, 0, GFP_NOWAIT);
 	if (err < 0)
-		goto err_free_percpu_ref;
+		goto err_free_css;
 	css->id = err;
 
 	if (visible) {
@@ -4595,9 +4595,6 @@ err_list_del:
 	list_del_rcu(&css->sibling);
 	cgroup_clear_dir(css->cgroup, 1 << css->ss->id);
 err_free_id:
-	cgroup_idr_remove(&ss->css_idr, css->id);
-err_free_percpu_ref:
-	percpu_ref_exit(&css->refcnt);
 err_free_css:
 	call_rcu(&css->rcu_head, css_free_rcu_fn);
 	return err;
-- 
2.5.0

[added to the 4.1 stable tree] dmaengine: at_xdmac: align descriptors on 64 bits

[Sasha Levin]

From: Ludovic Desroches <ludovic.desroches@atmel.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 4a9723e8df68cfce4048517ee32e37f78854b6fb ]

Having descriptors aligned on 64 bits allows update CNDA and CUBC in an
atomic way.

Signed-off-by: Ludovic Desroches <ludovic.desroches@atmel.com>
Fixes: e1f7c9eee707 ("dmaengine: at_xdmac: creation of the atmel
eXtended DMA Controller driver")
Cc: stable@vger.kernel.org #v4.1 and later
Reviewed-by: Nicolas Ferre <nicolas.ferre@atmel.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/dma/at_xdmac.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index ffa809f..690d811 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -238,7 +238,7 @@ struct at_xdmac_lld {
 	u32		mbr_cfg;	/* Configuration Register */
 };
 
-
+/* 64-bit alignment needed to update CNDA and CUBC registers in an atomic way. */
 struct at_xdmac_desc {
 	struct at_xdmac_lld		lld;
 	enum dma_transfer_direction	direction;
@@ -249,7 +249,7 @@ struct at_xdmac_desc {
 	unsigned int			xfer_size;
 	struct list_head		descs_list;
 	struct list_head		xfer_node;
-};
+} __aligned(sizeof(u64));
 
 static inline void __iomem *at_xdmac_chan_reg_base(struct at_xdmac *atxdmac, unsigned int chan_nb)
 {
-- 
2.5.0

[added to the 4.1 stable tree] dmaengine: at_xdmac: fix residue corruption

[Sasha Levin]

From: Ludovic Desroches <ludovic.desroches@atmel.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 53398f488821c2b5b15291e3debec6ad33f75d3d ]

An unexpected value of CUBC can lead to a corrupted residue. A more
complex sequence is needed to detect an inaccurate value for NCA or CUBC.

Signed-off-by: Ludovic Desroches <ludovic.desroches@atmel.com>
Fixes: e1f7c9eee707 ("dmaengine: at_xdmac: creation of the atmel
eXtended DMA Controller driver")
Cc: stable@vger.kernel.org #v4.1 and later
Reviewed-by: Nicolas Ferre <nicolas.ferre@atmel.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/dma/at_xdmac.c | 54 ++++++++++++++++++++++++++++++--------------------
 1 file changed, 32 insertions(+), 22 deletions(-)

diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index 690d811..2c413e5 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -930,6 +930,7 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 	u32			cur_nda, check_nda, cur_ubc, mask, value;
 	u8			dwidth = 0;
 	unsigned long		flags;
+	bool			initd;
 
 	ret = dma_cookie_status(chan, cookie, txstate);
 	if (ret == DMA_COMPLETE)
@@ -965,34 +966,43 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 	}
 
 	/*
-	 * When processing the residue, we need to read two registers but we
-	 * can't do it in an atomic way. AT_XDMAC_CNDA is used to find where
-	 * we stand in the descriptor list and AT_XDMAC_CUBC is used
-	 * to know how many data are remaining for the current descriptor.
-	 * Since the dma channel is not paused to not loose data, between the
-	 * AT_XDMAC_CNDA and AT_XDMAC_CUBC read, we may have change of
-	 * descriptor.
-	 * For that reason, after reading AT_XDMAC_CUBC, we check if we are
-	 * still using the same descriptor by reading a second time
-	 * AT_XDMAC_CNDA. If AT_XDMAC_CNDA has changed, it means we have to
-	 * read again AT_XDMAC_CUBC.
+	 * The easiest way to compute the residue should be to pause the DMA
+	 * but doing this can lead to miss some data as some devices don't
+	 * have FIFO.
+	 * We need to read several registers because:
+	 * - DMA is running therefore a descriptor change is possible while
+	 * reading these registers
+	 * - When the block transfer is done, the value of the CUBC register
+	 * is set to its initial value until the fetch of the next descriptor.
+	 * This value will corrupt the residue calculation so we have to skip
+	 * it.
+	 *
+	 * INITD --------                    ------------
+	 *              |____________________|
+	 *       _______________________  _______________
+	 * NDA       @desc2             \/   @desc3
+	 *       _______________________/\_______________
+	 *       __________  ___________  _______________
+	 * CUBC       0    \/ MAX desc1 \/  MAX desc2
+	 *       __________/\___________/\_______________
+	 *
+	 * Since descriptors are aligned on 64 bits, we can assume that
+	 * the update of NDA and CUBC is atomic.
 	 * Memory barriers are used to ensure the read order of the registers.
-	 * A max number of retries is set because unlikely it can never ends if
-	 * we are transferring a lot of data with small buffers.
+	 * A max number of retries is set because unlikely it could never ends.
 	 */
-	cur_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc;
-	rmb();
-	cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC);
 	for (retry = 0; retry < AT_XDMAC_RESIDUE_MAX_RETRIES; retry++) {
-		rmb();
 		check_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc;
-
-		if (likely(cur_nda == check_nda))
-			break;
-
-		cur_nda = check_nda;
+		rmb();
+		initd = !!(at_xdmac_chan_read(atchan, AT_XDMAC_CC) & AT_XDMAC_CC_INITD);
 		rmb();
 		cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC);
+		rmb();
+		cur_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc;
+		rmb();
+
+		if ((check_nda == cur_nda) && initd)
+			break;
 	}
 
 	if (unlikely(retry >= AT_XDMAC_RESIDUE_MAX_RETRIES)) {
-- 
2.5.0

[added to the 4.1 stable tree] dmaengine: at_xdmac: double FIFO flush needed to compute residue

[Sasha Levin]

From: Ludovic Desroches <ludovic.desroches@atmel.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 9295c41d77ca93aac79cfca6fa09fa1ca5cab66f ]

Due to the way CUBC register is updated, a double flush is needed to
compute an accurate residue. First flush aim is to get data from the DMA
FIFO and second one ensures that we won't report data which are not in
memory.

Signed-off-by: Ludovic Desroches <ludovic.desroches@atmel.com>
Fixes: e1f7c9eee707 ("dmaengine: at_xdmac: creation of the atmel
eXtended DMA Controller driver")
Cc: stable@vger.kernel.org #v4.1 and later
Reviewed-by: Nicolas Ferre <nicolas.ferre@atmel.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/dma/at_xdmac.c | 24 +++++++++++++++++++++++-
 1 file changed, 23 insertions(+), 1 deletion(-)

diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index 2c413e5..c5e6c82 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -955,7 +955,16 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 	residue = desc->xfer_size;
 	/*
 	 * Flush FIFO: only relevant when the transfer is source peripheral
-	 * synchronized.
+	 * synchronized. Flush is needed before reading CUBC because data in
+	 * the FIFO are not reported by CUBC. Reporting a residue of the
+	 * transfer length while we have data in FIFO can cause issue.
+	 * Usecase: atmel USART has a timeout which means I have received
+	 * characters but there is no more character received for a while. On
+	 * timeout, it requests the residue. If the data are in the DMA FIFO,
+	 * we will return a residue of the transfer length. It means no data
+	 * received. If an application is waiting for these data, it will hang
+	 * since we won't have another USART timeout without receiving new
+	 * data.
 	 */
 	mask = AT_XDMAC_CC_TYPE | AT_XDMAC_CC_DSYNC;
 	value = AT_XDMAC_CC_TYPE_PER_TRAN | AT_XDMAC_CC_DSYNC_PER2MEM;
@@ -1011,6 +1020,19 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 	}
 
 	/*
+	 * Flush FIFO: only relevant when the transfer is source peripheral
+	 * synchronized. Another flush is needed here because CUBC is updated
+	 * when the controller sends the data write command. It can lead to
+	 * report data that are not written in the memory or the device. The
+	 * FIFO flush ensures that data are really written.
+	 */
+	if ((desc->lld.mbr_cfg & mask) == value) {
+		at_xdmac_write(atxdmac, AT_XDMAC_GSWF, atchan->mask);
+		while (!(at_xdmac_chan_read(atchan, AT_XDMAC_CIS) & AT_XDMAC_CIS_FIS))
+			cpu_relax();
+	}
+
+	/*
 	 * Remove size of all microblocks already transferred and the current
 	 * one. Then add the remaining size to transfer of the current
 	 * microblock.
-- 
2.5.0

[added to the 4.1 stable tree] clk: rockchip: initialize flags of clk_init_data in mmc-phase clock

[Sasha Levin]

From: Heiko Stuebner <heiko@sntech.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 595144c1141c951a3c6bb9004ae6a2bc29aad66f ]

The flags element of clk_init_data was never initialized for mmc-
phase-clocks resulting in the element containing a random value
and thus possibly enabling unwanted clock flags.

Fixes: 89bf26cbc1a0 ("clk: rockchip: Add support for the mmc clock phases using the framework")
Cc: stable@vger.kernel.org
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/clk/rockchip/clk-mmc-phase.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/clk/rockchip/clk-mmc-phase.c b/drivers/clk/rockchip/clk-mmc-phase.c
index c842e3b..2c111c2 100644
--- a/drivers/clk/rockchip/clk-mmc-phase.c
+++ b/drivers/clk/rockchip/clk-mmc-phase.c
@@ -131,6 +131,7 @@ struct clk *rockchip_clk_register_mmc(const char *name,
 	if (!mmc_clock)
 		return NULL;
 
+	init.flags = 0;
 	init.num_parents = num_parents;
 	init.parent_names = parent_names;
 	init.ops = &rockchip_mmc_clk_ops;
-- 
2.5.0

[added to the 4.1 stable tree] usb: dwc3: exynos: Fix deferred probing storm.

[Sasha Levin]

From: "Steinar H. Gunderson" <sesse@google.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 4879efb34f7d49235fac334d76d9c6a77a021413 ]

dwc3-exynos has two problems during init if the regulators are slow
to come up (for instance if the I2C bus driver is not on the initramfs)
and return probe deferral. First, every time this happens, the driver
leaks the USB phys created; they need to be deallocated on error.

Second, since the phy devices are created before the regulators fail,
this means that there's a new device to re-trigger deferred probing,
which causes it to essentially go into a busy loop of re-probing the
device until the regulators come up.

Move the phy creation to after the regulators have succeeded, and also
fix cleanup on failure. On my ODROID XU4 system (with Debian's initramfs
which doesn't contain the I2C driver), this reduces the number of probe
attempts (for each of the two controllers) from more than 2000 to eight.

Signed-off-by: Steinar H. Gunderson <sesse@google.com>
Reviewed-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Reviewed-by: Vivek Gautam <gautam.vivek@samsung.com>
Fixes: d720f057fda4 ("usb: dwc3: exynos: add nop transceiver support")
Cc: <stable@vger.kernel.org>
Signed-off-by: Felipe Balbi <felipe.balbi@linux.intel.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/usb/dwc3/dwc3-exynos.c | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/drivers/usb/dwc3/dwc3-exynos.c b/drivers/usb/dwc3/dwc3-exynos.c
index 7bd0a95..0a465a9 100644
--- a/drivers/usb/dwc3/dwc3-exynos.c
+++ b/drivers/usb/dwc3/dwc3-exynos.c
@@ -128,12 +128,6 @@ static int dwc3_exynos_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, exynos);
 
-	ret = dwc3_exynos_register_phys(exynos);
-	if (ret) {
-		dev_err(dev, "couldn't register PHYs\n");
-		return ret;
-	}
-
 	exynos->dev	= dev;
 
 	exynos->clk = devm_clk_get(dev, "usbdrd30");
@@ -183,20 +177,29 @@ static int dwc3_exynos_probe(struct platform_device *pdev)
 		goto err3;
 	}
 
+	ret = dwc3_exynos_register_phys(exynos);
+	if (ret) {
+		dev_err(dev, "couldn't register PHYs\n");
+		goto err4;
+	}
+
 	if (node) {
 		ret = of_platform_populate(node, NULL, NULL, dev);
 		if (ret) {
 			dev_err(dev, "failed to add dwc3 core\n");
-			goto err4;
+			goto err5;
 		}
 	} else {
 		dev_err(dev, "no device node, failed to add dwc3 core\n");
 		ret = -ENODEV;
-		goto err4;
+		goto err5;
 	}
 
 	return 0;
 
+err5:
+	platform_device_unregister(exynos->usb2_phy);
+	platform_device_unregister(exynos->usb3_phy);
 err4:
 	regulator_disable(exynos->vdd10);
 err3:
-- 
2.5.0

[added to the 4.1 stable tree] usb: gadget: fix spinlock dead lock in gadgetfs

[Sasha Levin]

From: Bin Liu <b-liu@ti.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit d246dcb2331c5783743720e6510892eb1d2801d9 ]

[   40.467381] =============================================
[   40.473013] [ INFO: possible recursive locking detected ]
[   40.478651] 4.6.0-08691-g7f3db9a #37 Not tainted
[   40.483466] ---------------------------------------------
[   40.489098] usb/733 is trying to acquire lock:
[   40.493734]  (&(&dev->lock)->rlock){-.....}, at: [<bf129288>] ep0_complete+0x18/0xdc [gadgetfs]
[   40.502882]
[   40.502882] but task is already holding lock:
[   40.508967]  (&(&dev->lock)->rlock){-.....}, at: [<bf12a420>] ep0_read+0x20/0x5e0 [gadgetfs]
[   40.517811]
[   40.517811] other info that might help us debug this:
[   40.524623]  Possible unsafe locking scenario:
[   40.524623]
[   40.530798]        CPU0
[   40.533346]        ----
[   40.535894]   lock(&(&dev->lock)->rlock);
[   40.540088]   lock(&(&dev->lock)->rlock);
[   40.544284]
[   40.544284]  *** DEADLOCK ***
[   40.544284]
[   40.550461]  May be due to missing lock nesting notation
[   40.550461]
[   40.557544] 2 locks held by usb/733:
[   40.561271]  #0:  (&f->f_pos_lock){+.+.+.}, at: [<c02a6114>] __fdget_pos+0x40/0x48
[   40.569219]  #1:  (&(&dev->lock)->rlock){-.....}, at: [<bf12a420>] ep0_read+0x20/0x5e0 [gadgetfs]
[   40.578523]
[   40.578523] stack backtrace:
[   40.583075] CPU: 0 PID: 733 Comm: usb Not tainted 4.6.0-08691-g7f3db9a #37
[   40.590246] Hardware name: Generic AM33XX (Flattened Device Tree)
[   40.596625] [<c010ffbc>] (unwind_backtrace) from [<c010c1bc>] (show_stack+0x10/0x14)
[   40.604718] [<c010c1bc>] (show_stack) from [<c04207fc>] (dump_stack+0xb0/0xe4)
[   40.612267] [<c04207fc>] (dump_stack) from [<c01886ec>] (__lock_acquire+0xf68/0x1994)
[   40.620440] [<c01886ec>] (__lock_acquire) from [<c0189528>] (lock_acquire+0xd8/0x238)
[   40.628621] [<c0189528>] (lock_acquire) from [<c06ad6b4>] (_raw_spin_lock_irqsave+0x38/0x4c)
[   40.637440] [<c06ad6b4>] (_raw_spin_lock_irqsave) from [<bf129288>] (ep0_complete+0x18/0xdc [gadgetfs])
[   40.647339] [<bf129288>] (ep0_complete [gadgetfs]) from [<bf10a728>] (musb_g_giveback+0x118/0x1b0 [musb_hdrc])
[   40.657842] [<bf10a728>] (musb_g_giveback [musb_hdrc]) from [<bf108768>] (musb_g_ep0_queue+0x16c/0x188 [musb_hdrc])
[   40.668772] [<bf108768>] (musb_g_ep0_queue [musb_hdrc]) from [<bf12a944>] (ep0_read+0x544/0x5e0 [gadgetfs])
[   40.678963] [<bf12a944>] (ep0_read [gadgetfs]) from [<c0284470>] (__vfs_read+0x20/0x110)
[   40.687414] [<c0284470>] (__vfs_read) from [<c0285324>] (vfs_read+0x88/0x114)
[   40.694864] [<c0285324>] (vfs_read) from [<c0286150>] (SyS_read+0x44/0x9c)
[   40.702051] [<c0286150>] (SyS_read) from [<c0107820>] (ret_fast_syscall+0x0/0x1c)

This is caused by the spinlock bug in ep0_read().
Fix the two other deadlock sources in gadgetfs_setup() too.

Cc: <stable@vger.kernel.org> # v3.16+
Signed-off-by: Bin Liu <b-liu@ti.com>
Signed-off-by: Felipe Balbi <felipe.balbi@linux.intel.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/usb/gadget/legacy/inode.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index 2030565..bccc578 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -934,8 +934,11 @@ ep0_read (struct file *fd, char __user *buf, size_t len, loff_t *ptr)
 			struct usb_ep		*ep = dev->gadget->ep0;
 			struct usb_request	*req = dev->req;
 
-			if ((retval = setup_req (ep, req, 0)) == 0)
-				retval = usb_ep_queue (ep, req, GFP_ATOMIC);
+			if ((retval = setup_req (ep, req, 0)) == 0) {
+				spin_unlock_irq (&dev->lock);
+				retval = usb_ep_queue (ep, req, GFP_KERNEL);
+				spin_lock_irq (&dev->lock);
+			}
 			dev->state = STATE_DEV_CONNECTED;
 
 			/* assume that was SET_CONFIGURATION */
@@ -1453,8 +1456,11 @@ delegate:
 							w_length);
 				if (value < 0)
 					break;
+
+				spin_unlock (&dev->lock);
 				value = usb_ep_queue (gadget->ep0, dev->req,
-							GFP_ATOMIC);
+							GFP_KERNEL);
+				spin_lock (&dev->lock);
 				if (value < 0) {
 					clean_req (gadget->ep0, dev->req);
 					break;
@@ -1477,11 +1483,14 @@ delegate:
 	if (value >= 0 && dev->state != STATE_DEV_SETUP) {
 		req->length = value;
 		req->zero = value < w_length;
-		value = usb_ep_queue (gadget->ep0, req, GFP_ATOMIC);
+
+		spin_unlock (&dev->lock);
+		value = usb_ep_queue (gadget->ep0, req, GFP_KERNEL);
 		if (value < 0) {
 			DBG (dev, "ep_queue --> %d\n", value);
 			req->status = 0;
 		}
+		return value;
 	}
 
 	/* device stalls when value < 0 */
-- 
2.5.0

[added to the 4.1 stable tree] HID: elo: kill not flush the work

[Sasha Levin]

From: Oliver Neukum <oneukum@suse.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit ed596a4a88bd161f868ccba078557ee7ede8a6ef ]

Flushing a work that reschedules itself is not a sensible operation. It needs
to be killed. Failure to do so leads to a kernel panic in the timer code.

CC: stable@vger.kernel.org
Signed-off-by: Oliver Neukum <ONeukum@suse.com>
Reviewed-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/hid/hid-elo.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hid/hid-elo.c b/drivers/hid/hid-elo.c
index 4e49462..d0c8a1c 100644
--- a/drivers/hid/hid-elo.c
+++ b/drivers/hid/hid-elo.c
@@ -259,7 +259,7 @@ static void elo_remove(struct hid_device *hdev)
 	struct elo_priv *priv = hid_get_drvdata(hdev);
 
 	hid_hw_stop(hdev);
-	flush_workqueue(wq);
+	cancel_delayed_work_sync(&priv->work);
 	kfree(priv);
 }
 
-- 
2.5.0

[added to the 4.1 stable tree] xhci: Fix handling timeouted commands on hosts in weird states.

[Sasha Levin]

From: Mathias Nyman <mathias.nyman@linux.intel.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 3425aa03f484d45dc21e0e791c2f6c74ea656421 ]

If commands timeout we mark them for abortion, then stop the command
ring, and turn the commands to no-ops and finally restart the command
ring.

If the host is working properly the no-op commands will finish and
pending completions are called.
If we notice the host is failing, driver clears the command ring and
completes, deletes and frees all pending commands.

There are two separate cases reported where host is believed to work
properly but is not. In the first case we successfully stop the ring
but no abort or stop command ring event is ever sent and host locks up.

The second case is if a host is removed, command times out and driver
believes the ring is stopped, and assumes it will be restarted, but
actually ends up timing out on the same command forever.
If one of the pending commands has the xhci->mutex held it will block
xhci_stop() in the remove codepath which otherwise would cleanup pending
commands.

Add a check that clears all pending commands in case host is removed,
or we are stuck timing out on the same command. Also restart the
command timeout timer when stopping the command ring to ensure we
recive an ring stop/abort event.

Cc: stable <stable@vger.kernel.org>
Tested-by: Joe Lawrence <joe.lawrence@stratus.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/usb/host/xhci-ring.c | 27 ++++++++++++++++++++++-----
 1 file changed, 22 insertions(+), 5 deletions(-)

diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 6fe0377..6ef2551 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -289,6 +289,14 @@ static int xhci_abort_cmd_ring(struct xhci_hcd *xhci)
 
 	temp_64 = xhci_read_64(xhci, &xhci->op_regs->cmd_ring);
 	xhci->cmd_ring_state = CMD_RING_STATE_ABORTED;
+
+	/*
+	 * Writing the CMD_RING_ABORT bit should cause a cmd completion event,
+	 * however on some host hw the CMD_RING_RUNNING bit is correctly cleared
+	 * but the completion event in never sent. Use the cmd timeout timer to
+	 * handle those cases. Use twice the time to cover the bit polling retry
+	 */
+	mod_timer(&xhci->cmd_timer, jiffies + (2 * XHCI_CMD_DEFAULT_TIMEOUT));
 	xhci_write_64(xhci, temp_64 | CMD_RING_ABORT,
 			&xhci->op_regs->cmd_ring);
 
@@ -313,6 +321,7 @@ static int xhci_abort_cmd_ring(struct xhci_hcd *xhci)
 
 		xhci_err(xhci, "Stopped the command ring failed, "
 				"maybe the host is dead\n");
+		del_timer(&xhci->cmd_timer);
 		xhci->xhc_state |= XHCI_STATE_DYING;
 		xhci_quiesce(xhci);
 		xhci_halt(xhci);
@@ -1252,22 +1261,21 @@ void xhci_handle_command_timeout(unsigned long data)
 	int ret;
 	unsigned long flags;
 	u64 hw_ring_state;
-	struct xhci_command *cur_cmd = NULL;
+	bool second_timeout = false;
 	xhci = (struct xhci_hcd *) data;
 
 	/* mark this command to be cancelled */
 	spin_lock_irqsave(&xhci->lock, flags);
 	if (xhci->current_cmd) {
-		cur_cmd = xhci->current_cmd;
-		cur_cmd->status = COMP_CMD_ABORT;
+		if (xhci->current_cmd->status == COMP_CMD_ABORT)
+			second_timeout = true;
+		xhci->current_cmd->status = COMP_CMD_ABORT;
 	}
 
-
 	/* Make sure command ring is running before aborting it */
 	hw_ring_state = xhci_read_64(xhci, &xhci->op_regs->cmd_ring);
 	if ((xhci->cmd_ring_state & CMD_RING_STATE_RUNNING) &&
 	    (hw_ring_state & CMD_RING_RUNNING))  {
-
 		spin_unlock_irqrestore(&xhci->lock, flags);
 		xhci_dbg(xhci, "Command timeout\n");
 		ret = xhci_abort_cmd_ring(xhci);
@@ -1279,6 +1287,15 @@ void xhci_handle_command_timeout(unsigned long data)
 		}
 		return;
 	}
+
+	/* command ring failed to restart, or host removed. Bail out */
+	if (second_timeout || xhci->xhc_state & XHCI_STATE_REMOVING) {
+		spin_unlock_irqrestore(&xhci->lock, flags);
+		xhci_dbg(xhci, "command timed out twice, ring start fail?\n");
+		xhci_cleanup_command_queue(xhci);
+		return;
+	}
+
 	/* command timeout on stopped ring, ring can't be aborted */
 	xhci_dbg(xhci, "Command timeout on stopped ring\n");
 	xhci_handle_stopped_cmd_ring(xhci, xhci->current_cmd);
-- 
2.5.0

[added to the 4.1 stable tree] usb: xhci-plat: properly handle probe deferral for devm_clk_get()

[Sasha Levin]

From: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit de95c40d5beaa47f6dc8fe9ac4159b4672b51523 ]

On some platforms, the clocks might be registered by a platform
driver. When this is the case, the clock platform driver may very well
be probed after xhci-plat, in which case the first probe() invocation
of xhci-plat will receive -EPROBE_DEFER as the return value of
devm_clk_get().

The current code handles that as a normal error, and simply assumes
that this means that the system doesn't have a clock for the XHCI
controller, and continues probing without calling
clk_prepare_enable(). Unfortunately, this doesn't work on systems
where the XHCI controller does have a clock, but that clock is
provided by another platform driver. In order to fix this situation,
we handle the -EPROBE_DEFER error condition specially, and abort the
XHCI controller probe(). It will be retried later automatically, the
clock will be available, devm_clk_get() will succeed, and the probe()
will continue with the clock prepared and enabled as expected.

In practice, such issue is seen on the ARM64 Marvell 7K/8K platform,
where the clocks are registered by a platform driver.

Cc: <stable@vger.kernel.org>
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/usb/host/xhci-plat.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c
index 783e8191..7606710 100644
--- a/drivers/usb/host/xhci-plat.c
+++ b/drivers/usb/host/xhci-plat.c
@@ -116,6 +116,9 @@ static int xhci_plat_probe(struct platform_device *pdev)
 		ret = clk_prepare_enable(clk);
 		if (ret)
 			goto put_hcd;
+	} else if (PTR_ERR(clk) == -EPROBE_DEFER) {
+		ret = -EPROBE_DEFER;
+		goto put_hcd;
 	}
 
 	if (of_device_is_compatible(pdev->dev.of_node,
-- 
2.5.0

[added to the 4.1 stable tree] usb: quirks: Fix sorting

[Sasha Levin]

From: Hans de Goede <hdegoede@redhat.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 81099f97bd31e25ff2719a435b1860fc3876122f ]

Properly sort all the entries by vendor id.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/usb/core/quirks.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 017c1de..34aa57b 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -44,6 +44,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* Creative SB Audigy 2 NX */
 	{ USB_DEVICE(0x041e, 0x3020), .driver_info = USB_QUIRK_RESET_RESUME },
 
+	/* USB3503 */
+	{ USB_DEVICE(0x0424, 0x3503), .driver_info = USB_QUIRK_RESET_RESUME },
+
 	/* Microsoft Wireless Laser Mouse 6000 Receiver */
 	{ USB_DEVICE(0x045e, 0x00e1), .driver_info = USB_QUIRK_RESET_RESUME },
 
@@ -170,6 +173,10 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* MAYA44USB sound device */
 	{ USB_DEVICE(0x0a92, 0x0091), .driver_info = USB_QUIRK_RESET_RESUME },
 
+	/* ASUS Base Station(T100) */
+	{ USB_DEVICE(0x0b05, 0x17e0), .driver_info =
+			USB_QUIRK_IGNORE_REMOTE_WAKEUP },
+
 	/* Action Semiconductor flash disk */
 	{ USB_DEVICE(0x10d6, 0x2200), .driver_info =
 			USB_QUIRK_STRING_FETCH_255 },
@@ -185,16 +192,6 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x1908, 0x1315), .driver_info =
 			USB_QUIRK_HONOR_BNUMINTERFACES },
 
-	/* INTEL VALUE SSD */
-	{ USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME },
-
-	/* USB3503 */
-	{ USB_DEVICE(0x0424, 0x3503), .driver_info = USB_QUIRK_RESET_RESUME },
-
-	/* ASUS Base Station(T100) */
-	{ USB_DEVICE(0x0b05, 0x17e0), .driver_info =
-			USB_QUIRK_IGNORE_REMOTE_WAKEUP },
-
 	/* Protocol and OTG Electrical Test Device */
 	{ USB_DEVICE(0x1a0a, 0x0200), .driver_info =
 			USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL },
@@ -205,6 +202,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* Blackmagic Design UltraStudio SDI */
 	{ USB_DEVICE(0x1edb, 0xbd4f), .driver_info = USB_QUIRK_NO_LPM },
 
+	/* INTEL VALUE SSD */
+	{ USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME },
+
 	{ }  /* terminating entry must be last */
 };
 
-- 
2.5.0

[added to the 4.1 stable tree] usb: quirks: Add no-lpm quirk for Acer C120 LED Projector

[Sasha Levin]

From: Hans de Goede <hdegoede@redhat.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 32cb0b37098f4beeff5ad9e325f11b42a6ede56c ]

The Acer C120 LED Projector is a USB-3 connected pico projector which
takes both its power and video data from USB-3.

In combination with some hubs this device does not play well with
lpm, so disable lpm for it.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/usb/core/quirks.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 34aa57b..f28b537 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -196,6 +196,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x1a0a, 0x0200), .driver_info =
 			USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL },
 
+	/* Acer C120 LED Projector */
+	{ USB_DEVICE(0x1de1, 0xc102), .driver_info = USB_QUIRK_NO_LPM },
+
 	/* Blackmagic Design Intensity Shuttle */
 	{ USB_DEVICE(0x1edb, 0xbd3b), .driver_info = USB_QUIRK_NO_LPM },
 
-- 
2.5.0

[added to the 4.1 stable tree] USB: xhci: Add broken streams quirk for Frescologic device id 1009

[Sasha Levin]

From: Hans de Goede <hdegoede@redhat.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit d95815ba6a0f287213118c136e64d8c56daeaeab ]

I got one of these cards for testing uas with, it seems that with streams
it dma-s all over the place, corrupting memory. On my first tests it
managed to dma over the BIOS of the motherboard somehow and completely
bricked it.

Tests on another motherboard show that it does work with streams disabled.

Cc: stable@vger.kernel.org
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/usb/host/xhci-pci.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index c6027ac..54caaf8 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -37,6 +37,7 @@
 /* Device for a quirk */
 #define PCI_VENDOR_ID_FRESCO_LOGIC	0x1b73
 #define PCI_DEVICE_ID_FRESCO_LOGIC_PDK	0x1000
+#define PCI_DEVICE_ID_FRESCO_LOGIC_FL1009	0x1009
 #define PCI_DEVICE_ID_FRESCO_LOGIC_FL1400	0x1400
 
 #define PCI_VENDOR_ID_ETRON		0x1b6f
@@ -108,6 +109,10 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 		xhci->quirks |= XHCI_TRUST_TX_LENGTH;
 	}
 
+	if (pdev->vendor == PCI_VENDOR_ID_FRESCO_LOGIC &&
+			pdev->device == PCI_DEVICE_ID_FRESCO_LOGIC_FL1009)
+		xhci->quirks |= XHCI_BROKEN_STREAMS;
+
 	if (pdev->vendor == PCI_VENDOR_ID_NEC)
 		xhci->quirks |= XHCI_NEC_HOST;
 
-- 
2.5.0

[added to the 4.1 stable tree] usb: musb: Ensure rx reinit occurs for shared_fifo endpoints

[Sasha Levin]

From: Andrew Goodbody <andrew.goodbody@cambrionix.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit f3eec0cf784e0d6c47822ca6b66df3d5812af7e6 ]

shared_fifo endpoints would only get a previous tx state cleared
out, the rx state was only cleared for non shared_fifo endpoints
Change this so that the rx state is cleared for all endpoints.
This addresses an issue that resulted in rx packets being dropped
silently.

Signed-off-by: Andrew Goodbody <andrew.goodbody@cambrionix.com>
Cc: stable@vger.kernel.org
Signed-off-by: Bin Liu <b-liu@ti.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/usb/musb/musb_host.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c
index c3d5fc9..383a657 100644
--- a/drivers/usb/musb/musb_host.c
+++ b/drivers/usb/musb/musb_host.c
@@ -583,14 +583,13 @@ musb_rx_reinit(struct musb *musb, struct musb_qh *qh, struct musb_hw_ep *ep)
 		musb_writew(ep->regs, MUSB_TXCSR, 0);
 
 	/* scrub all previous state, clearing toggle */
-	} else {
-		csr = musb_readw(ep->regs, MUSB_RXCSR);
-		if (csr & MUSB_RXCSR_RXPKTRDY)
-			WARNING("rx%d, packet/%d ready?\n", ep->epnum,
-				musb_readw(ep->regs, MUSB_RXCOUNT));
-
-		musb_h_flush_rxfifo(ep, MUSB_RXCSR_CLRDATATOG);
 	}
+	csr = musb_readw(ep->regs, MUSB_RXCSR);
+	if (csr & MUSB_RXCSR_RXPKTRDY)
+		WARNING("rx%d, packet/%d ready?\n", ep->epnum,
+			musb_readw(ep->regs, MUSB_RXCOUNT));
+
+	musb_h_flush_rxfifo(ep, MUSB_RXCSR_CLRDATATOG);
 
 	/* target addr and (for multipoint) hub addr/port */
 	if (musb->is_multipoint) {
-- 
2.5.0

[added to the 4.1 stable tree] usb: musb: Stop bulk endpoint while queue is rotated

[Sasha Levin]

From: Andrew Goodbody <andrew.goodbody@cambrionix.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 7b2c17f829545df27a910e8d82e133c21c9a8c9c ]

Ensure that the endpoint is stopped by clearing REQPKT before
clearing DATAERR_NAKTIMEOUT before rotating the queue on the
dedicated bulk endpoint.
This addresses an issue where a race could result in the endpoint
receiving data before it was reprogrammed resulting in a warning
about such data from musb_rx_reinit before it was thrown away.
The data thrown away was a valid packet that had been correctly
ACKed which meant the host and device got out of sync.

Signed-off-by: Andrew Goodbody <andrew.goodbody@cambrionix.com>
Cc: stable@vger.kernel.org
Signed-off-by: Bin Liu <b-liu@ti.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/usb/musb/musb_host.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c
index 383a657..06853d7 100644
--- a/drivers/usb/musb/musb_host.c
+++ b/drivers/usb/musb/musb_host.c
@@ -949,9 +949,15 @@ static void musb_bulk_nak_timeout(struct musb *musb, struct musb_hw_ep *ep,
 	if (is_in) {
 		dma = is_dma_capable() ? ep->rx_channel : NULL;
 
-		/* clear nak timeout bit */
+		/*
+		 * Need to stop the transaction by clearing REQPKT first
+		 * then the NAK Timeout bit ref MUSBMHDRC USB 2.0 HIGH-SPEED
+		 * DUAL-ROLE CONTROLLER Programmer's Guide, section 9.2.2
+		 */
 		rx_csr = musb_readw(epio, MUSB_RXCSR);
 		rx_csr |= MUSB_RXCSR_H_WZC_BITS;
+		rx_csr &= ~MUSB_RXCSR_H_REQPKT;
+		musb_writew(epio, MUSB_RXCSR, rx_csr);
 		rx_csr &= ~MUSB_RXCSR_DATAERROR;
 		musb_writew(epio, MUSB_RXCSR, rx_csr);
 
-- 
2.5.0

[added to the 4.1 stable tree] usb: host: ehci-tegra: Grab the correct UTMI pads reset

[Sasha Levin]

From: Thierry Reding <treding@nvidia.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit f8a15a9650694feaa0dabf197b0c94d37cd3fb42 ]

There are three EHCI controllers on Tegra SoCs, each with its own reset
line. However, the first controller contains a set of UTMI configuration
registers that are shared with its siblings. These registers will only
be reset as part of the first controller's reset. For proper operation
it must be ensured that the UTMI configuration registers are reset
before any of the EHCI controllers are enabled, irrespective of the
probe order.

Commit a47cc24cd1e5 ("USB: EHCI: tegra: Fix probe order issue leading to
broken USB") introduced code that ensures the first controller is always
reset before setting up any of the controllers, and is never again reset
afterwards.

This code, however, grabs the wrong reset. Each EHCI controller has two
reset controls attached: 1) the USB controller reset and 2) the UTMI
pads reset (really the first controller's reset). In order to reset the
UTMI pads registers the code must grab the second reset, but instead it
grabbing the first.

Fixes: a47cc24cd1e5 ("USB: EHCI: tegra: Fix probe order issue leading to broken USB")
Acked-by: Jon Hunter <jonathanh@nvidia.com>
Cc: stable@vger.kernel.org
Signed-off-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/usb/host/ehci-tegra.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/host/ehci-tegra.c b/drivers/usb/host/ehci-tegra.c
index ff9af29..d888a00 100644
--- a/drivers/usb/host/ehci-tegra.c
+++ b/drivers/usb/host/ehci-tegra.c
@@ -89,7 +89,7 @@ static int tegra_reset_usb_controller(struct platform_device *pdev)
 	if (!usb1_reset_attempted) {
 		struct reset_control *usb1_reset;
 
-		usb1_reset = of_reset_control_get(phy_np, "usb");
+		usb1_reset = of_reset_control_get(phy_np, "utmi-pads");
 		if (IS_ERR(usb1_reset)) {
 			dev_warn(&pdev->dev,
 				 "can't get utmi-pads reset from the PHY\n");
-- 
2.5.0

[added to the 4.1 stable tree] scsi: fix race between simultaneous decrements of ->host_failed

[Sasha Levin]

From: Wei Fang <fangwei1@huawei.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 72d8c36ec364c82bf1bf0c64dfa1041cfaf139f7 ]

sas_ata_strategy_handler() adds the works of the ata error handler to
system_unbound_wq. This workqueue asynchronously runs work items, so the
ata error handler will be performed concurrently on different CPUs. In
this case, ->host_failed will be decreased simultaneously in
scsi_eh_finish_cmd() on different CPUs, and become abnormal.

It will lead to permanently inequality between ->host_failed and
->host_busy, and scsi error handler thread won't start running. IO
errors after that won't be handled.

Since all scmds must have been handled in the strategy handler, just
remove the decrement in scsi_eh_finish_cmd() and zero ->host_busy after
the strategy handler to fix this race.

Fixes: 50824d6c5657 ("[SCSI] libsas: async ata-eh")
Cc: stable@vger.kernel.org
Signed-off-by: Wei Fang <fangwei1@huawei.com>
Reviewed-by: James Bottomley <jejb@linux.vnet.ibm.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 Documentation/scsi/scsi_eh.txt | 8 ++++++--
 drivers/ata/libata-eh.c        | 2 +-
 drivers/scsi/scsi_error.c      | 4 +++-
 3 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/Documentation/scsi/scsi_eh.txt b/Documentation/scsi/scsi_eh.txt
index 8638f61..37eca00 100644
--- a/Documentation/scsi/scsi_eh.txt
+++ b/Documentation/scsi/scsi_eh.txt
@@ -263,19 +263,23 @@ scmd->allowed.
 
  3. scmd recovered
     ACTION: scsi_eh_finish_cmd() is invoked to EH-finish scmd
-	- shost->host_failed--
 	- clear scmd->eh_eflags
 	- scsi_setup_cmd_retry()
 	- move from local eh_work_q to local eh_done_q
     LOCKING: none
+    CONCURRENCY: at most one thread per separate eh_work_q to
+		 keep queue manipulation lockless
 
  4. EH completes
     ACTION: scsi_eh_flush_done_q() retries scmds or notifies upper
-	    layer of failure.
+	    layer of failure. May be called concurrently but must have
+	    a no more than one thread per separate eh_work_q to
+	    manipulate the queue locklessly
 	- scmd is removed from eh_done_q and scmd->eh_entry is cleared
 	- if retry is necessary, scmd is requeued using
           scsi_queue_insert()
 	- otherwise, scsi_finish_command() is invoked for scmd
+	- zero shost->host_failed
     LOCKING: queue or finish function performs appropriate locking
 
 
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index cb0508a..5ab6fa9 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -606,7 +606,7 @@ void ata_scsi_error(struct Scsi_Host *host)
 	ata_scsi_port_error_handler(host, ap);
 
 	/* finish or retry handled scmd's and clean up */
-	WARN_ON(host->host_failed || !list_empty(&eh_work_q));
+	WARN_ON(!list_empty(&eh_work_q));
 
 	DPRINTK("EXIT\n");
 }
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index c6b93d2..841fdf7 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -1122,7 +1122,6 @@ static int scsi_eh_action(struct scsi_cmnd *scmd, int rtn)
  */
 void scsi_eh_finish_cmd(struct scsi_cmnd *scmd, struct list_head *done_q)
 {
-	scmd->device->host->host_failed--;
 	scmd->eh_eflags = 0;
 	list_move_tail(&scmd->eh_entry, done_q);
 }
@@ -2216,6 +2215,9 @@ int scsi_error_handler(void *data)
 		else
 			scsi_unjam_host(shost);
 
+		/* All scmds have been handled */
+		shost->host_failed = 0;
+
 		/*
 		 * Note - if the above fails completely, the action is to take
 		 * individual devices offline and flush the queue of any
-- 
2.5.0

[added to the 4.1 stable tree] ARM: 8578/1: mm: ensure pmd_present only checks the valid bit

[Sasha Levin]

From: Will Deacon <will.deacon@arm.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 624531886987f0f1b5d01fb598034d039198e090 ]

In a subsequent patch, pmd_mknotpresent will clear the valid bit of the
pmd entry, resulting in a not-present entry from the hardware's
perspective. Unfortunately, pmd_present simply checks for a non-zero pmd
value and will therefore continue to return true even after a
pmd_mknotpresent operation. Since pmd_mknotpresent is only used for
managing huge entries, this is only an issue for the 3-level case.

This patch fixes the 3-level pmd_present implementation to take into
account the valid bit. For bisectability, the change is made before the
fix to pmd_mknotpresent.

[catalin.marinas@arm.com: comment update regarding pmd_mknotpresent patch]

Fixes: 8d9625070073 ("ARM: mm: Transparent huge page support for LPAE systems.")
Cc: <stable@vger.kernel.org> # 3.11+
Cc: Russell King <linux@armlinux.org.uk>
Cc: Steve Capper <Steve.Capper@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 arch/arm/include/asm/pgtable-2level.h | 1 +
 arch/arm/include/asm/pgtable-3level.h | 1 +
 arch/arm/include/asm/pgtable.h        | 1 -
 3 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h
index bfd662e..89b5a0a 100644
--- a/arch/arm/include/asm/pgtable-2level.h
+++ b/arch/arm/include/asm/pgtable-2level.h
@@ -164,6 +164,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 
 #define pmd_large(pmd)		(pmd_val(pmd) & 2)
 #define pmd_bad(pmd)		(pmd_val(pmd) & 2)
+#define pmd_present(pmd)	(pmd_val(pmd))
 
 #define copy_pmd(pmdpd,pmdps)		\
 	do {				\
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index a745a2a..e3dad00 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -212,6 +212,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 						: !!(pmd_val(pmd) & (val)))
 #define pmd_isclear(pmd, val)	(!(pmd_val(pmd) & (val)))
 
+#define pmd_present(pmd)	(pmd_isset((pmd), L_PMD_SECT_VALID))
 #define pmd_young(pmd)		(pmd_isset((pmd), PMD_SECT_AF))
 #define pte_special(pte)	(pte_isset((pte), L_PTE_SPECIAL))
 static inline pte_t pte_mkspecial(pte_t pte)
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index f403541..7fa12e0 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -182,7 +182,6 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 #define pgd_offset_k(addr)	pgd_offset(&init_mm, addr)
 
 #define pmd_none(pmd)		(!pmd_val(pmd))
-#define pmd_present(pmd)	(pmd_val(pmd))
 
 static inline pte_t *pmd_page_vaddr(pmd_t pmd)
 {
-- 
2.5.0

[added to the 4.1 stable tree] ARM: 8579/1: mm: Fix definition of pmd_mknotpresent

[Sasha Levin]

From: Steve Capper <steve.capper@arm.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 56530f5d2ddc9b9fade7ef8db9cb886e9dc689b5 ]

Currently pmd_mknotpresent will use a zero entry to respresent an
invalidated pmd.

Unfortunately this definition clashes with pmd_none, thus it is
possible for a race condition to occur if zap_pmd_range sees pmd_none
whilst __split_huge_pmd_locked is running too with pmdp_invalidate
just called.

This patch fixes the race condition by modifying pmd_mknotpresent to
create non-zero faulting entries (as is done in other architectures),
removing the ambiguity with pmd_none.

[catalin.marinas@arm.com: using L_PMD_SECT_VALID instead of PMD_TYPE_SECT]

Fixes: 8d9625070073 ("ARM: mm: Transparent huge page support for LPAE systems.")
Cc: <stable@vger.kernel.org> # 3.11+
Reported-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Will Deacon <will.deacon@arm.com>
Cc: Russell King <linux@armlinux.org.uk>
Signed-off-by: Steve Capper <steve.capper@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 arch/arm/include/asm/pgtable-3level.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index e3dad00..fd929b5 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -258,10 +258,10 @@ PMD_BIT_FUNC(mkyoung,   |= PMD_SECT_AF);
 #define pfn_pmd(pfn,prot)	(__pmd(((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)))
 #define mk_pmd(page,prot)	pfn_pmd(page_to_pfn(page),prot)
 
-/* represent a notpresent pmd by zero, this is used by pmdp_invalidate */
+/* represent a notpresent pmd by faulting entry, this is used by pmdp_invalidate */
 static inline pmd_t pmd_mknotpresent(pmd_t pmd)
 {
-	return __pmd(0);
+	return __pmd(pmd_val(pmd) & ~L_PMD_SECT_VALID);
 }
 
 static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
-- 
2.5.0

[added to the 4.1 stable tree] crypto: vmx - Increase priority of aes-cbc cipher

[Sasha Levin]

From: Anton Blanchard <anton@samba.org>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 12d3f49e1ffbbf8cbbb60acae5a21103c5c841ac ]

All of the VMX AES ciphers (AES, AES-CBC and AES-CTR) are set at
priority 1000. Unfortunately this means we never use AES-CBC and
AES-CTR, because the base AES-CBC cipher that is implemented on
top of AES inherits its priority.

To fix this, AES-CBC and AES-CTR have to be a higher priority. Set
them to 2000.

Testing on a POWER8 with:

cryptsetup benchmark --cipher aes --key-size 256

Shows decryption speed increase from 402.4 MB/s to 3069.2 MB/s,
over 7x faster. Thanks to Mike Strosaker for helping me debug
this issue.

Fixes: 8c755ace357c ("crypto: vmx - Adding CBC routines for VMX module")
Cc: stable@vger.kernel.org
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/crypto/vmx/aes_cbc.c | 2 +-
 drivers/crypto/vmx/aes_ctr.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/crypto/vmx/aes_cbc.c b/drivers/crypto/vmx/aes_cbc.c
index c8e7f65..f508cea 100644
--- a/drivers/crypto/vmx/aes_cbc.c
+++ b/drivers/crypto/vmx/aes_cbc.c
@@ -167,7 +167,7 @@ struct crypto_alg p8_aes_cbc_alg = {
     .cra_name = "cbc(aes)",
     .cra_driver_name = "p8_aes_cbc",
     .cra_module = THIS_MODULE,
-    .cra_priority = 1000,
+    .cra_priority = 2000,
     .cra_type = &crypto_blkcipher_type,
     .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | CRYPTO_ALG_NEED_FALLBACK,
     .cra_alignmask = 0,
diff --git a/drivers/crypto/vmx/aes_ctr.c b/drivers/crypto/vmx/aes_ctr.c
index 266e708..d8fa3b4 100644
--- a/drivers/crypto/vmx/aes_ctr.c
+++ b/drivers/crypto/vmx/aes_ctr.c
@@ -151,7 +151,7 @@ struct crypto_alg p8_aes_ctr_alg = {
     .cra_name = "ctr(aes)",
     .cra_driver_name = "p8_aes_ctr",
     .cra_module = THIS_MODULE,
-    .cra_priority = 1000,
+    .cra_priority = 2000,
     .cra_type = &crypto_blkcipher_type,
     .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | CRYPTO_ALG_NEED_FALLBACK,
     .cra_alignmask = 0,
-- 
2.5.0

[added to the 4.1 stable tree] crypto: ux500 - memmove the right size

[Sasha Levin]

From: Linus Walleij <linus.walleij@linaro.org>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 19ced623db2fe91604d69f7d86b03144c5107739 ]

The hash buffer is really HASH_BLOCK_SIZE bytes, someone
must have thought that memmove takes n*u32 words by mistake.
Tests work as good/bad as before after this patch.

Cc: Joakim Bech <joakim.bech@linaro.org>
Cc: stable@vger.kernel.org
Reported-by: David Binderman <linuxdev.baldrick@gmail.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/crypto/ux500/hash/hash_core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/crypto/ux500/hash/hash_core.c b/drivers/crypto/ux500/hash/hash_core.c
index 5f5f360..c5e6222 100644
--- a/drivers/crypto/ux500/hash/hash_core.c
+++ b/drivers/crypto/ux500/hash/hash_core.c
@@ -797,7 +797,7 @@ static int hash_process_data(struct hash_device_data *device_data,
 						&device_data->state);
 				memmove(req_ctx->state.buffer,
 					device_data->state.buffer,
-					HASH_BLOCK_SIZE / sizeof(u32));
+					HASH_BLOCK_SIZE);
 				if (ret) {
 					dev_err(device_data->dev,
 						"%s: hash_resume_state() failed!\n",
@@ -848,7 +848,7 @@ static int hash_process_data(struct hash_device_data *device_data,
 
 			memmove(device_data->state.buffer,
 				req_ctx->state.buffer,
-				HASH_BLOCK_SIZE / sizeof(u32));
+				HASH_BLOCK_SIZE);
 			if (ret) {
 				dev_err(device_data->dev, "%s: hash_save_state() failed!\n",
 					__func__);
-- 
2.5.0

[added to the 4.1 stable tree] ipmi: Remove smi_msg from waiting_rcv_msgs list before handle_one_recv_msg()

[Sasha Levin]

From: Junichi Nomura <j-nomura@ce.jp.nec.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit ae4ea9a2460c7fee2ae8feeb4dfe96f5f6c3e562 ]

Commit 7ea0ed2b5be8 ("ipmi: Make the message handler easier to use for
SMI interfaces") changed handle_new_recv_msgs() to call handle_one_recv_msg()
for a smi_msg while the smi_msg is still connected to waiting_rcv_msgs list.
That could lead to following list corruption problems:

1) low-level function treats smi_msg as not connected to list

  handle_one_recv_msg() could end up calling smi_send(), which
  assumes the msg is not connected to list.

  For example, the following sequence could corrupt list by
  doing list_add_tail() for the entry still connected to other list.

    handle_new_recv_msgs()
      msg = list_entry(waiting_rcv_msgs)
      handle_one_recv_msg(msg)
        handle_ipmb_get_msg_cmd(msg)
          smi_send(msg)
            spin_lock(xmit_msgs_lock)
            list_add_tail(msg)
            spin_unlock(xmit_msgs_lock)

2) race between multiple handle_new_recv_msgs() instances

  handle_new_recv_msgs() once releases waiting_rcv_msgs_lock before calling
  handle_one_recv_msg() then retakes the lock and list_del() it.

  If others call handle_new_recv_msgs() during the window shown below
  list_del() will be done twice for the same smi_msg.

  handle_new_recv_msgs()
    spin_lock(waiting_rcv_msgs_lock)
    msg = list_entry(waiting_rcv_msgs)
    spin_unlock(waiting_rcv_msgs_lock)
  |
  | handle_one_recv_msg(msg)
  |
    spin_lock(waiting_rcv_msgs_lock)
    list_del(msg)
    spin_unlock(waiting_rcv_msgs_lock)

Fixes: 7ea0ed2b5be8 ("ipmi: Make the message handler easier to use for SMI interfaces")
Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
[Added a comment to describe why this works.]
Signed-off-by: Corey Minyard <cminyard@mvista.com>
Cc: stable@vger.kernel.org # 3.19
Tested-by: Ye Feng <yefeng.yl@alibaba-inc.com>

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/char/ipmi/ipmi_msghandler.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index bf75f63..4bc508c 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -3813,6 +3813,7 @@ static void handle_new_recv_msgs(ipmi_smi_t intf)
 	while (!list_empty(&intf->waiting_rcv_msgs)) {
 		smi_msg = list_entry(intf->waiting_rcv_msgs.next,
 				     struct ipmi_smi_msg, link);
+		list_del(&smi_msg->link);
 		if (!run_to_completion)
 			spin_unlock_irqrestore(&intf->waiting_rcv_msgs_lock,
 					       flags);
@@ -3822,11 +3823,14 @@ static void handle_new_recv_msgs(ipmi_smi_t intf)
 		if (rv > 0) {
 			/*
 			 * To preserve message order, quit if we
-			 * can't handle a message.
+			 * can't handle a message.  Add the message
+			 * back at the head, this is safe because this
+			 * tasklet is the only thing that pulls the
+			 * messages.
 			 */
+			list_add(&smi_msg->link, &intf->waiting_rcv_msgs);
 			break;
 		} else {
-			list_del(&smi_msg->link);
 			if (rv == 0)
 				/* Message handled */
 				ipmi_free_smi_msg(smi_msg);
-- 
2.5.0

[added to the 4.1 stable tree] drm/radeon: fix asic initialization for virtualized environments

[Sasha Levin]

From: Alex Deucher <alexander.deucher@amd.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 05082b8bbd1a0ffc74235449c4b8930a8c240f85 ]

When executing in a PCI passthrough based virtuzliation environment, the
hypervisor will usually attempt to send a PCIe bus reset signal to the
ASIC when the VM reboots. In this scenario, the card is not correctly
initialized, but we still consider it to be posted. Therefore, in a
passthrough based environemnt we should always post the card to guarantee
it is in a good state for driver initialization.

Ported from amdgpu commit:
amdgpu: fix asic initialization for virtualized environments

Cc: Andres Rodriguez <andres.rodriguez@amd.com>
Cc: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/gpu/drm/radeon/radeon_device.c | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 604c44d..83b3eb2 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -630,6 +630,23 @@ void radeon_gtt_location(struct radeon_device *rdev, struct radeon_mc *mc)
 /*
  * GPU helpers function.
  */
+
+/**
+ * radeon_device_is_virtual - check if we are running is a virtual environment
+ *
+ * Check if the asic has been passed through to a VM (all asics).
+ * Used at driver startup.
+ * Returns true if virtual or false if not.
+ */
+static bool radeon_device_is_virtual(void)
+{
+#ifdef CONFIG_X86
+	return boot_cpu_has(X86_FEATURE_HYPERVISOR);
+#else
+	return false;
+#endif
+}
+
 /**
  * radeon_card_posted - check if the hw has already been initialized
  *
@@ -643,6 +660,10 @@ bool radeon_card_posted(struct radeon_device *rdev)
 {
 	uint32_t reg;
 
+	/* for pass through, always force asic_init */
+	if (radeon_device_is_virtual())
+		return false;
+
 	/* required for EFI mode on macbook2,1 which uses an r5xx asic */
 	if (efi_enabled(EFI_BOOT) &&
 	    (rdev->pdev->subsystem_vendor == PCI_VENDOR_ID_APPLE) &&
-- 
2.5.0

[added to the 4.1 stable tree] usb: common: otg-fsm: add license to usb-otg-fsm

[Sasha Levin]

From: Oscar <oscar@naiandei.net>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit ea1d39a31d3b1b6060b6e83e5a29c069a124c68a ]

Fix warning about tainted kernel because usb-otg-fsm has no license.
WARNING: with this patch usb-otg-fsm module can be loaded
but then the kernel will hang. Tested with a udoo quad board.

Cc: <stable@vger.kernel.org> #v4.1+
Signed-off-by: Oscar <oscar@naiandei.net>
Signed-off-by: Peter Chen <peter.chen@nxp.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/usb/common/usb-otg-fsm.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/usb/common/usb-otg-fsm.c b/drivers/usb/common/usb-otg-fsm.c
index 61d538a..4f4f06a 100644
--- a/drivers/usb/common/usb-otg-fsm.c
+++ b/drivers/usb/common/usb-otg-fsm.c
@@ -21,6 +21,7 @@
  * 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+#include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/mutex.h>
@@ -365,3 +366,4 @@ int otg_statemachine(struct otg_fsm *fsm)
 	return state_changed;
 }
 EXPORT_SYMBOL_GPL(otg_statemachine);
+MODULE_LICENSE("GPL");
-- 
2.5.0

[added to the 4.1 stable tree] MIPS: KVM: Fix modular KVM under QEMU

[Sasha Levin]

From: James Hogan <james.hogan@imgtec.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 797179bc4fe06c89e47a9f36f886f68640b423f8 ]

Copy __kvm_mips_vcpu_run() into unmapped memory, so that we can never
get a TLB refill exception in it when KVM is built as a module.

This was observed to happen with the host MIPS kernel running under
QEMU, due to a not entirely transparent optimisation in the QEMU TLB
handling where TLB entries replaced with TLBWR are copied to a separate
part of the TLB array. Code in those pages continue to be executable,
but those mappings persist only until the next ASID switch, even if they
are marked global.

An ASID switch happens in __kvm_mips_vcpu_run() at exception level after
switching to the guest exception base. Subsequent TLB mapped kernel
instructions just prior to switching to the guest trigger a TLB refill
exception, which enters the guest exception handlers without updating
EPC. This appears as a guest triggered TLB refill on a host kernel
mapped (host KSeg2) address, which is not handled correctly as user
(guest) mode accesses to kernel (host) segments always generate address
error exceptions.

Signed-off-by: James Hogan <james.hogan@imgtec.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: kvm@vger.kernel.org
Cc: linux-mips@linux-mips.org
Cc: <stable@vger.kernel.org> # 3.10.x-
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 arch/mips/include/asm/kvm_host.h |  1 +
 arch/mips/kvm/interrupt.h        |  1 +
 arch/mips/kvm/locore.S           |  1 +
 arch/mips/kvm/mips.c             | 11 ++++++++++-
 4 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index 3585af0..ab518d1 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -370,6 +370,7 @@ struct kvm_mips_tlb {
 #define KVM_MIPS_GUEST_TLB_SIZE	64
 struct kvm_vcpu_arch {
 	void *host_ebase, *guest_ebase;
+	int (*vcpu_run)(struct kvm_run *run, struct kvm_vcpu *vcpu);
 	unsigned long host_stack;
 	unsigned long host_gp;
 
diff --git a/arch/mips/kvm/interrupt.h b/arch/mips/kvm/interrupt.h
index 4ab4bdf..2143884 100644
--- a/arch/mips/kvm/interrupt.h
+++ b/arch/mips/kvm/interrupt.h
@@ -28,6 +28,7 @@
 #define MIPS_EXC_MAX                12
 /* XXXSL More to follow */
 
+extern char __kvm_mips_vcpu_run_end[];
 extern char mips32_exception[], mips32_exceptionEnd[];
 extern char mips32_GuestException[], mips32_GuestExceptionEnd[];
 
diff --git a/arch/mips/kvm/locore.S b/arch/mips/kvm/locore.S
index d1ee95a..ae01e7f 100644
--- a/arch/mips/kvm/locore.S
+++ b/arch/mips/kvm/locore.S
@@ -235,6 +235,7 @@ FEXPORT(__kvm_mips_load_k0k1)
 
 	/* Jump to guest */
 	eret
+EXPORT(__kvm_mips_vcpu_run_end)
 
 VECTOR(MIPSX(exception), unknown)
 /* Find out what mode we came from and jump to the proper handler. */
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index ace4ed7..485fdc4 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -312,6 +312,15 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 	memcpy(gebase + offset, mips32_GuestException,
 	       mips32_GuestExceptionEnd - mips32_GuestException);
 
+#ifdef MODULE
+	offset += mips32_GuestExceptionEnd - mips32_GuestException;
+	memcpy(gebase + offset, (char *)__kvm_mips_vcpu_run,
+	       __kvm_mips_vcpu_run_end - (char *)__kvm_mips_vcpu_run);
+	vcpu->arch.vcpu_run = gebase + offset;
+#else
+	vcpu->arch.vcpu_run = __kvm_mips_vcpu_run;
+#endif
+
 	/* Invalidate the icache for these ranges */
 	local_flush_icache_range((unsigned long)gebase,
 				(unsigned long)gebase + ALIGN(size, PAGE_SIZE));
@@ -401,7 +410,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	/* Disable hardware page table walking while in guest */
 	htw_stop();
 
-	r = __kvm_mips_vcpu_run(run, vcpu);
+	r = vcpu->arch.vcpu_run(run, vcpu);
 
 	/* Re-enable HTW before enabling interrupts */
 	htw_start();
-- 
2.5.0

[added to the 4.1 stable tree] spi: sun4i: fix FIFO limit

[Sasha Levin]

From: Michal Suchanek <hramrach@gmail.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 6d9fe44bd73d567d04d3a68a2d2fa521ab9532f2 ]

When testing SPI without DMA I noticed that filling the FIFO on the
spi controller causes timeout.

Always leave room for one byte in the FIFO.

Signed-off-by: Michal Suchanek <hramrach@gmail.com>
Acked-by: Maxime Ripard <maxime.ripard@free-electrons.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
Cc: stable@vger.kernel.org
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/spi/spi-sun4i.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/spi/spi-sun4i.c b/drivers/spi/spi-sun4i.c
index fbb0a4d..c854248 100644
--- a/drivers/spi/spi-sun4i.c
+++ b/drivers/spi/spi-sun4i.c
@@ -176,7 +176,10 @@ static int sun4i_spi_transfer_one(struct spi_master *master,
 
 	/* We don't support transfer larger than the FIFO */
 	if (tfr->len > SUN4I_FIFO_DEPTH)
-		return -EINVAL;
+		return -EMSGSIZE;
+
+	if (tfr->tx_buf && tfr->len >= SUN4I_FIFO_DEPTH)
+		return -EMSGSIZE;
 
 	reinit_completion(&sspi->done);
 	sspi->tx_buf = tfr->tx_buf;
@@ -269,8 +272,12 @@ static int sun4i_spi_transfer_one(struct spi_master *master,
 	sun4i_spi_write(sspi, SUN4I_BURST_CNT_REG, SUN4I_BURST_CNT(tfr->len));
 	sun4i_spi_write(sspi, SUN4I_XMIT_CNT_REG, SUN4I_XMIT_CNT(tx_len));
 
-	/* Fill the TX FIFO */
-	sun4i_spi_fill_fifo(sspi, SUN4I_FIFO_DEPTH);
+	/*
+	 * Fill the TX FIFO
+	 * Filling the FIFO fully causes timeout for some reason
+	 * at least on spi2 on A10s
+	 */
+	sun4i_spi_fill_fifo(sspi, SUN4I_FIFO_DEPTH - 1);
 
 	/* Enable the interrupts */
 	sun4i_spi_write(sspi, SUN4I_INT_CTL_REG, SUN4I_INT_CTL_TC);
-- 
2.5.0

[added to the 4.1 stable tree] spi: sunxi: fix transfer timeout

[Sasha Levin]

From: Michal Suchanek <hramrach@gmail.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 719bd6542044efd9b338a53dba1bef45f40ca169 ]

The trasfer timeout is fixed at 1000 ms. Reading a 4Mbyte flash over
1MHz SPI bus takes way longer than that. Calculate the timeout from the
actual time the transfer is supposed to take and multiply by 2 for good
measure.

Signed-off-by: Michal Suchanek <hramrach@gmail.com>
Acked-by: Maxime Ripard <maxime.ripard@free-electrons.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
Cc: stable@vger.kernel.org
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/spi/spi-sun4i.c | 10 +++++++++-
 drivers/spi/spi-sun6i.c | 10 +++++++++-
 2 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/drivers/spi/spi-sun4i.c b/drivers/spi/spi-sun4i.c
index c854248..39d7c7c 100644
--- a/drivers/spi/spi-sun4i.c
+++ b/drivers/spi/spi-sun4i.c
@@ -170,6 +170,7 @@ static int sun4i_spi_transfer_one(struct spi_master *master,
 {
 	struct sun4i_spi *sspi = spi_master_get_devdata(master);
 	unsigned int mclk_rate, div, timeout;
+	unsigned int start, end, tx_time;
 	unsigned int tx_len = 0;
 	int ret = 0;
 	u32 reg;
@@ -286,9 +287,16 @@ static int sun4i_spi_transfer_one(struct spi_master *master,
 	reg = sun4i_spi_read(sspi, SUN4I_CTL_REG);
 	sun4i_spi_write(sspi, SUN4I_CTL_REG, reg | SUN4I_CTL_XCH);
 
+	tx_time = max(tfr->len * 8 * 2 / (tfr->speed_hz / 1000), 100U);
+	start = jiffies;
 	timeout = wait_for_completion_timeout(&sspi->done,
-					      msecs_to_jiffies(1000));
+					      msecs_to_jiffies(tx_time));
+	end = jiffies;
 	if (!timeout) {
+		dev_warn(&master->dev,
+			 "%s: timeout transferring %u bytes@%iHz for %i(%i)ms",
+			 dev_name(&spi->dev), tfr->len, tfr->speed_hz,
+			 jiffies_to_msecs(end - start), tx_time);
 		ret = -ETIMEDOUT;
 		goto out;
 	}
diff --git a/drivers/spi/spi-sun6i.c b/drivers/spi/spi-sun6i.c
index ac48f59..e77add0 100644
--- a/drivers/spi/spi-sun6i.c
+++ b/drivers/spi/spi-sun6i.c
@@ -160,6 +160,7 @@ static int sun6i_spi_transfer_one(struct spi_master *master,
 {
 	struct sun6i_spi *sspi = spi_master_get_devdata(master);
 	unsigned int mclk_rate, div, timeout;
+	unsigned int start, end, tx_time;
 	unsigned int tx_len = 0;
 	int ret = 0;
 	u32 reg;
@@ -269,9 +270,16 @@ static int sun6i_spi_transfer_one(struct spi_master *master,
 	reg = sun6i_spi_read(sspi, SUN6I_TFR_CTL_REG);
 	sun6i_spi_write(sspi, SUN6I_TFR_CTL_REG, reg | SUN6I_TFR_CTL_XCH);
 
+	tx_time = max(tfr->len * 8 * 2 / (tfr->speed_hz / 1000), 100U);
+	start = jiffies;
 	timeout = wait_for_completion_timeout(&sspi->done,
-					      msecs_to_jiffies(1000));
+					      msecs_to_jiffies(tx_time));
+	end = jiffies;
 	if (!timeout) {
+		dev_warn(&master->dev,
+			 "%s: timeout transferring %u bytes@%iHz for %i(%i)ms",
+			 dev_name(&spi->dev), tfr->len, tfr->speed_hz,
+			 jiffies_to_msecs(end - start), tx_time);
 		ret = -ETIMEDOUT;
 		goto out;
 	}
-- 
2.5.0

[added to the 4.1 stable tree] kprobes/x86: Clear TF bit in fault on single-stepping

[Sasha Levin]

From: Masami Hiramatsu <mhiramat@kernel.org>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit dcfc47248d3f7d28df6f531e6426b933de94370d ]

Fix kprobe_fault_handler() to clear the TF (trap flag) bit of
the flags register in the case of a fault fixup on single-stepping.

If we put a kprobe on the instruction which caused a
page fault (e.g. actual mov instructions in copy_user_*),
that fault happens on the single-stepping buffer. In this
case, kprobes resets running instance so that the CPU can
retry execution on the original ip address.

However, current code forgets to reset the TF bit. Since this
fault happens with TF bit set for enabling single-stepping,
when it retries, it causes a debug exception and kprobes
can not handle it because it already reset itself.

On the most of x86-64 platform, it can be easily reproduced
by using kprobe tracer. E.g.

  # cd /sys/kernel/debug/tracing
  # echo p copy_user_enhanced_fast_string+5 > kprobe_events
  # echo 1 > events/kprobes/enable

And you'll see a kernel panic on do_debug(), since the debug
trap is not handled by kprobes.

To fix this problem, we just need to clear the TF bit when
resetting running kprobe.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Reviewed-by: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
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>
Cc: systemtap@sourceware.org
Cc: stable@vger.kernel.org # All the way back to ancient kernels
Link: http://lkml.kernel.org/r/20160611140648.25885.37482.stgit@devbox
[ Updated the comments. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 arch/x86/kernel/kprobes/core.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 1deffe6..023c442 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -959,7 +959,19 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 		 * normal page fault.
 		 */
 		regs->ip = (unsigned long)cur->addr;
+		/*
+		 * Trap flag (TF) has been set here because this fault
+		 * happened where the single stepping will be done.
+		 * So clear it by resetting the current kprobe:
+		 */
+		regs->flags &= ~X86_EFLAGS_TF;
+
+		/*
+		 * If the TF flag was set before the kprobe hit,
+		 * don't touch it:
+		 */
 		regs->flags |= kcb->kprobe_old_flags;
+
 		if (kcb->kprobe_status == KPROBE_REENTER)
 			restore_previous_kprobe(kcb);
 		else
-- 
2.5.0

[added to the 4.1 stable tree] kernel/sysrq, watchdog, sched/core: Reset watchdog on all CPUs while processing sysrq-w

[Sasha Levin]

From: Andrey Ryabinin <aryabinin@virtuozzo.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 57675cb976eff977aefb428e68e4e0236d48a9ff ]

Lengthy output of sysrq-w may take a lot of time on slow serial console.

Currently we reset NMI-watchdog on the current CPU to avoid spurious
lockup messages. Sometimes this doesn't work since softlockup watchdog
might trigger on another CPU which is waiting for an IPI to proceed.
We reset softlockup watchdogs on all CPUs, but we do this only after
listing all tasks, and this may be too late on a busy system.

So, reset watchdogs CPUs earlier, in for_each_process_thread() loop.

Signed-off-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: <stable@vger.kernel.org>
Link: http://lkml.kernel.org/r/1465474805-14641-1-git-send-email-aryabinin@virtuozzo.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 kernel/sched/core.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 3b0f4c0..98e6071 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4568,14 +4568,16 @@ void show_state_filter(unsigned long state_filter)
 		/*
 		 * reset the NMI-timeout, listing all files on a slow
 		 * console might take a lot of time:
+		 * Also, reset softlockup watchdogs on all CPUs, because
+		 * another CPU might be blocked waiting for us to process
+		 * an IPI.
 		 */
 		touch_nmi_watchdog();
+		touch_all_softlockup_watchdogs();
 		if (!state_filter || (p->state & state_filter))
 			sched_show_task(p);
 	}
 
-	touch_all_softlockup_watchdogs();
-
 #ifdef CONFIG_SCHED_DEBUG
 	sysrq_sched_debug_show();
 #endif
-- 
2.5.0

[added to the 4.1 stable tree] power_supply: power_supply_read_temp only if use_cnt > 0

[Sasha Levin]

From: Rhyland Klein <rklein@nvidia.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 5bc28b93a36e3cb3acc2870fb75cb6ffb182fece ]

Change power_supply_read_temp() to use power_supply_get_property()
so that it will check the use_cnt and ensure it is > 0. The use_cnt
will be incremented at the end of __power_supply_register, so this
will block to case where get_property can be called before the supply
is fully registered. This fixes the issue show in the stack below:

[    1.452598] power_supply_read_temp+0x78/0x80
[    1.458680] thermal_zone_get_temp+0x5c/0x11c
[    1.464765] thermal_zone_device_update+0x34/0xb4
[    1.471195] thermal_zone_device_register+0x87c/0x8cc
[    1.477974] __power_supply_register+0x364/0x424
[    1.484317] power_supply_register_no_ws+0x10/0x18
[    1.490833] bq27xxx_battery_setup+0x10c/0x164
[    1.497003] bq27xxx_battery_i2c_probe+0xd0/0x1b0
[    1.503435] i2c_device_probe+0x174/0x240
[    1.509172] driver_probe_device+0x1fc/0x29c
[    1.515167] __driver_attach+0xa4/0xa8
[    1.520643] bus_for_each_dev+0x58/0x98
[    1.526204] driver_attach+0x20/0x28
[    1.531505] bus_add_driver+0x1c8/0x22c
[    1.537067] driver_register+0x68/0x108
[    1.542630] i2c_register_driver+0x38/0x7c
[    1.548457] bq27xxx_battery_i2c_driver_init+0x18/0x20
[    1.555321] do_one_initcall+0x38/0x12c
[    1.560886] kernel_init_freeable+0x148/0x1ec
[    1.566972] kernel_init+0x10/0xfc
[    1.572101] ret_from_fork+0x10/0x40

Also make the same change to ps_get_max_charge_cntl_limit() and
ps_get_cur_chrage_cntl_limit() to be safe. Lastly, change the return
value of power_supply_get_property() to -EAGAIN from -ENODEV if
use_cnt <= 0.

Fixes: 297d716f6260 ("power_supply: Change ownership from driver to core")
Cc: stable@vger.kernel.org
Signed-off-by: Rhyland Klein <rklein@nvidia.com>
Reviewed-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Signed-off-by: Sebastian Reichel <sre@kernel.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/power/power_supply_core.c | 27 ++++++++++++++++-----------
 1 file changed, 16 insertions(+), 11 deletions(-)

diff --git a/drivers/power/power_supply_core.c b/drivers/power/power_supply_core.c
index 4bc0c7f..b2bf48c 100644
--- a/drivers/power/power_supply_core.c
+++ b/drivers/power/power_supply_core.c
@@ -526,11 +526,12 @@ static int power_supply_read_temp(struct thermal_zone_device *tzd,
 
 	WARN_ON(tzd == NULL);
 	psy = tzd->devdata;
-	ret = psy->desc->get_property(psy, POWER_SUPPLY_PROP_TEMP, &val);
+	ret = power_supply_get_property(psy, POWER_SUPPLY_PROP_TEMP, &val);
+	if (ret)
+		return ret;
 
 	/* Convert tenths of degree Celsius to milli degree Celsius. */
-	if (!ret)
-		*temp = val.intval * 100;
+	*temp = val.intval * 100;
 
 	return ret;
 }
@@ -573,10 +574,12 @@ static int ps_get_max_charge_cntl_limit(struct thermal_cooling_device *tcd,
 	int ret;
 
 	psy = tcd->devdata;
-	ret = psy->desc->get_property(psy,
-		POWER_SUPPLY_PROP_CHARGE_CONTROL_LIMIT_MAX, &val);
-	if (!ret)
-		*state = val.intval;
+	ret = power_supply_get_property(psy,
+			POWER_SUPPLY_PROP_CHARGE_CONTROL_LIMIT_MAX, &val);
+	if (ret)
+		return ret;
+
+	*state = val.intval;
 
 	return ret;
 }
@@ -589,10 +592,12 @@ static int ps_get_cur_chrage_cntl_limit(struct thermal_cooling_device *tcd,
 	int ret;
 
 	psy = tcd->devdata;
-	ret = psy->desc->get_property(psy,
-		POWER_SUPPLY_PROP_CHARGE_CONTROL_LIMIT, &val);
-	if (!ret)
-		*state = val.intval;
+	ret = power_supply_get_property(psy,
+			POWER_SUPPLY_PROP_CHARGE_CONTROL_LIMIT, &val);
+	if (ret)
+		return ret;
+
+	*state = val.intval;
 
 	return ret;
 }
-- 
2.5.0

[added to the 4.1 stable tree] drm/i915/ilk: Don't disable SSC source if it's in use

[Sasha Levin]

From: Lyude <cpaul@redhat.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 476490a945e1f0f6bd58e303058d2d8ca93a974c ]

Thanks to Ville Syrjälä for pointing me towards the cause of this issue.

Unfortunately one of the sideaffects of having the refclk for a DPLL set
to SSC is that as long as it's set to SSC, the GPU will prevent us from
powering down any of the pipes or transcoders using it. A couple of
BIOSes enable SSC in both PCH_DREF_CONTROL and in the DPLL
configurations. This causes issues on the first modeset, since we don't
expect SSC to be left on and as a result, can't successfully power down
the pipes or the transcoders using it. Here's an example from this Dell
OptiPlex 990:

[drm:intel_modeset_init] SSC enabled by BIOS, overriding VBT which says disabled
[drm:intel_modeset_init] 2 display pipes available.
[drm:intel_update_cdclk] Current CD clock rate: 400000 kHz
[drm:intel_update_max_cdclk] Max CD clock rate: 400000 kHz
[drm:intel_update_max_cdclk] Max dotclock rate: 360000 kHz
vgaarb: device changed decodes: PCI:0000:00:02.0,olddecodes=io+mem,decodes=io+mem:owns=io+mem
[drm:intel_crt_reset] crt adpa set to 0xf40000
[drm:intel_dp_init_connector] Adding DP connector on port C
[drm:intel_dp_aux_init] registering DPDDC-C bus for card0-DP-1
[drm:ironlake_init_pch_refclk] has_panel 0 has_lvds 0 has_ck505 0
[drm:ironlake_init_pch_refclk] Disabling SSC entirely
… later we try committing the first modeset …
[drm:intel_dump_pipe_config] [CRTC:26][modeset] config ffff88041b02e800 for pipe A
[drm:intel_dump_pipe_config] cpu_transcoder: A
…
[drm:intel_dump_pipe_config] dpll_hw_state: dpll: 0xc4016001, dpll_md: 0x0, fp0: 0x20e08, fp1: 0x30d07
[drm:intel_dump_pipe_config] planes on this crtc
[drm:intel_dump_pipe_config] STANDARD PLANE:23 plane: 0.0 idx: 0 enabled
[drm:intel_dump_pipe_config]     FB:42, fb = 800x600 format = 0x34325258
[drm:intel_dump_pipe_config]     scaler:0 src (0, 0) 800x600 dst (0, 0) 800x600
[drm:intel_dump_pipe_config] CURSOR PLANE:25 plane: 0.1 idx: 1 disabled, scaler_id = 0
[drm:intel_dump_pipe_config] STANDARD PLANE:27 plane: 0.1 idx: 2 disabled, scaler_id = 0
[drm:intel_get_shared_dpll] CRTC:26 allocated PCH DPLL A
[drm:intel_get_shared_dpll] using PCH DPLL A for pipe A
[drm:ilk_audio_codec_disable] Disable audio codec on port C, pipe A
[drm:intel_disable_pipe] disabling pipe A
------------[ cut here ]------------
WARNING: CPU: 1 PID: 130 at drivers/gpu/drm/i915/intel_display.c:1146 intel_disable_pipe+0x297/0x2d0 [i915]
pipe_off wait timed out
…
---[ end trace 94fc8aa03ae139e8 ]---
[drm:intel_dp_link_down]
[drm:ironlake_crtc_disable [i915]] *ERROR* failed to disable transcoder A

Later modesets succeed since they reset the DPLL's configuration anyway,
but this is enough to get stuck with a big fat warning in dmesg.

A better solution would be to add refcounts for the SSC source, but for
now leaving the source clock on should suffice.

Changes since v4:
 - Fix calculation of final for systems with LVDS panels (fixes BUG() on
   CI test suite)
Changes since v3:
 - Move temp variable into loop
 - Move checks for using_ssc_source to after we've figured out has_ck505
 - Add using_ssc_source to debug output
Changes since v2:
 - Fix debug output for when we disable the CPU source
Changes since v1:
 - Leave the SSC source clock on instead of just shutting it off on all
   of the DPLL configurations.

Cc: stable@vger.kernel.org
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Lyude <cpaul@redhat.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/1465916649-10228-1-git-send-email-cpaul@redhat.com
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/gpu/drm/i915/intel_display.c | 48 +++++++++++++++++++++++++-----------
 1 file changed, 34 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 5632373..5250596 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -7129,12 +7129,14 @@ static void ironlake_init_pch_refclk(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_encoder *encoder;
+	int i;
 	u32 val, final;
 	bool has_lvds = false;
 	bool has_cpu_edp = false;
 	bool has_panel = false;
 	bool has_ck505 = false;
 	bool can_ssc = false;
+	bool using_ssc_source = false;
 
 	/* We need to take the global config into account */
 	for_each_intel_encoder(dev, encoder) {
@@ -7161,8 +7163,22 @@ static void ironlake_init_pch_refclk(struct drm_device *dev)
 		can_ssc = true;
 	}
 
-	DRM_DEBUG_KMS("has_panel %d has_lvds %d has_ck505 %d\n",
-		      has_panel, has_lvds, has_ck505);
+	/* Check if any DPLLs are using the SSC source */
+	for (i = 0; i < dev_priv->num_shared_dpll; i++) {
+		u32 temp = I915_READ(PCH_DPLL(i));
+
+		if (!(temp & DPLL_VCO_ENABLE))
+			continue;
+
+		if ((temp & PLL_REF_INPUT_MASK) ==
+		    PLLB_REF_INPUT_SPREADSPECTRUMIN) {
+			using_ssc_source = true;
+			break;
+		}
+	}
+
+	DRM_DEBUG_KMS("has_panel %d has_lvds %d has_ck505 %d using_ssc_source %d\n",
+		      has_panel, has_lvds, has_ck505, using_ssc_source);
 
 	/* Ironlake: try to setup display ref clock before DPLL
 	 * enabling. This is only under driver's control after
@@ -7199,9 +7215,9 @@ static void ironlake_init_pch_refclk(struct drm_device *dev)
 				final |= DREF_CPU_SOURCE_OUTPUT_NONSPREAD;
 		} else
 			final |= DREF_CPU_SOURCE_OUTPUT_DISABLE;
-	} else {
-		final |= DREF_SSC_SOURCE_DISABLE;
-		final |= DREF_CPU_SOURCE_OUTPUT_DISABLE;
+	} else if (using_ssc_source) {
+		final |= DREF_SSC_SOURCE_ENABLE;
+		final |= DREF_SSC1_ENABLE;
 	}
 
 	if (final == val)
@@ -7247,7 +7263,7 @@ static void ironlake_init_pch_refclk(struct drm_device *dev)
 		POSTING_READ(PCH_DREF_CONTROL);
 		udelay(200);
 	} else {
-		DRM_DEBUG_KMS("Disabling SSC entirely\n");
+		DRM_DEBUG_KMS("Disabling CPU source output\n");
 
 		val &= ~DREF_CPU_SOURCE_OUTPUT_MASK;
 
@@ -7258,16 +7274,20 @@ static void ironlake_init_pch_refclk(struct drm_device *dev)
 		POSTING_READ(PCH_DREF_CONTROL);
 		udelay(200);
 
-		/* Turn off the SSC source */
-		val &= ~DREF_SSC_SOURCE_MASK;
-		val |= DREF_SSC_SOURCE_DISABLE;
+		if (!using_ssc_source) {
+			DRM_DEBUG_KMS("Disabling SSC source\n");
 
-		/* Turn off SSC1 */
-		val &= ~DREF_SSC1_ENABLE;
+			/* Turn off the SSC source */
+			val &= ~DREF_SSC_SOURCE_MASK;
+			val |= DREF_SSC_SOURCE_DISABLE;
 
-		I915_WRITE(PCH_DREF_CONTROL, val);
-		POSTING_READ(PCH_DREF_CONTROL);
-		udelay(200);
+			/* Turn off SSC1 */
+			val &= ~DREF_SSC1_ENABLE;
+
+			I915_WRITE(PCH_DREF_CONTROL, val);
+			POSTING_READ(PCH_DREF_CONTROL);
+			udelay(200);
+		}
 	}
 
 	BUG_ON(val != final);
-- 
2.5.0

[added to the 4.1 stable tree] drm/dp/mst: Always clear proposed vcpi table for port.

[Sasha Levin]

From: Andrey Grodzovsky <Andrey.Grodzovsky@amd.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit fd2d2bac6e79b0be91ab86a6075a0c46ffda658a ]

Not clearing mst manager's proposed vcpis table for destroyed connectors when the manager is stopped leaves it pointing to unrefernced memory, this causes pagefault when the manager is restarted when plugging back a branch.

Fixes: 91a25e463130 ("drm/dp/mst: deallocate payload on port destruction")
Signed-off-by: Andrey Grodzovsky <Andrey.Grodzovsky@amd.com>
Reviewed-by: Lyude <cpaul@redhat.com>
Cc: stable@vger.kernel.org
Cc: Mykola Lysenko <Mykola.Lysenko@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/gpu/drm/drm_dp_mst_topology.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index 10b8839..52dea77 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -2862,11 +2862,9 @@ static void drm_dp_destroy_connector_work(struct work_struct *work)
 		drm_dp_port_teardown_pdt(port, port->pdt);
 
 		if (!port->input && port->vcpi.vcpi > 0) {
-			if (mgr->mst_state) {
-				drm_dp_mst_reset_vcpi_slots(mgr, port);
-				drm_dp_update_payload_part1(mgr);
-				drm_dp_mst_put_payload_id(mgr, port->vcpi.vcpi);
-			}
+			drm_dp_mst_reset_vcpi_slots(mgr, port);
+			drm_dp_update_payload_part1(mgr);
+			drm_dp_mst_put_payload_id(mgr, port->vcpi.vcpi);
 		}
 
 		kref_put(&port->kref, drm_dp_free_mst_port);
-- 
2.5.0

[added to the 4.1 stable tree] nfsd4/rpc: move backchannel create logic into rpc code

[Sasha Levin]

From: "J. Bruce Fields" <bfields@redhat.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit d50039ea5ee63c589b0434baa5ecf6e5075bb6f9 ]

Also simplify the logic a bit.

Cc: stable@vger.kernel.org
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Acked-by: Trond Myklebust <trondmy@primarydata.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 fs/nfsd/nfs4callback.c      | 18 +-----------------
 include/linux/sunrpc/clnt.h |  2 --
 net/sunrpc/clnt.c           | 12 ++++++++++--
 3 files changed, 11 insertions(+), 21 deletions(-)

diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 5694cfb..29c4bff 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -710,22 +710,6 @@ static struct rpc_cred *get_backchannel_cred(struct nfs4_client *clp, struct rpc
 	}
 }
 
-static struct rpc_clnt *create_backchannel_client(struct rpc_create_args *args)
-{
-	struct rpc_xprt *xprt;
-
-	if (args->protocol != XPRT_TRANSPORT_BC_TCP)
-		return rpc_create(args);
-
-	xprt = args->bc_xprt->xpt_bc_xprt;
-	if (xprt) {
-		xprt_get(xprt);
-		return rpc_create_xprt(args, xprt);
-	}
-
-	return rpc_create(args);
-}
-
 static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *conn, struct nfsd4_session *ses)
 {
 	int maxtime = max_cb_time(clp->net);
@@ -768,7 +752,7 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c
 		args.authflavor = ses->se_cb_sec.flavor;
 	}
 	/* Create RPC client */
-	client = create_backchannel_client(&args);
+	client = rpc_create(&args);
 	if (IS_ERR(client)) {
 		dprintk("NFSD: couldn't create callback client: %ld\n",
 			PTR_ERR(client));
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 598ba80..ee29cb4 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -134,8 +134,6 @@ struct rpc_create_args {
 #define RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT	(1UL << 9)
 
 struct rpc_clnt *rpc_create(struct rpc_create_args *args);
-struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args,
-					struct rpc_xprt *xprt);
 struct rpc_clnt	*rpc_bind_new_program(struct rpc_clnt *,
 				const struct rpc_program *, u32);
 void rpc_task_reset_client(struct rpc_task *task, struct rpc_clnt *clnt);
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index e6ce151..16e831d 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -442,7 +442,7 @@ out_no_rpciod:
 	return ERR_PTR(err);
 }
 
-struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args,
+static struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args,
 					struct rpc_xprt *xprt)
 {
 	struct rpc_clnt *clnt = NULL;
@@ -474,7 +474,6 @@ struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args,
 
 	return clnt;
 }
-EXPORT_SYMBOL_GPL(rpc_create_xprt);
 
 /**
  * rpc_create - create an RPC client and transport with one call
@@ -500,6 +499,15 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args)
 	};
 	char servername[48];
 
+	if (args->bc_xprt) {
+		WARN_ON(args->protocol != XPRT_TRANSPORT_BC_TCP);
+		xprt = args->bc_xprt->xpt_bc_xprt;
+		if (xprt) {
+			xprt_get(xprt);
+			return rpc_create_xprt(args, xprt);
+		}
+	}
+
 	if (args->flags & RPC_CLNT_CREATE_INFINITE_SLOTS)
 		xprtargs.flags |= XPRT_CREATE_INFINITE_SLOTS;
 	if (args->flags & RPC_CLNT_CREATE_NO_IDLE_TIMEOUT)
-- 
2.5.0

[added to the 4.1 stable tree] base: make module_create_drivers_dir race-free

[Sasha Levin]

From: Jiri Slaby <jslaby@suse.cz>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 7e1b1fc4dabd6ec8e28baa0708866e13fa93c9b3 ]

Modules which register drivers via standard path (driver_register) in
parallel can cause a warning:
WARNING: CPU: 2 PID: 3492 at ../fs/sysfs/dir.c:31 sysfs_warn_dup+0x62/0x80
sysfs: cannot create duplicate filename '/module/saa7146/drivers'
Modules linked in: hexium_gemini(+) mxb(+) ...
...
Call Trace:
...
 [<ffffffff812e63a2>] sysfs_warn_dup+0x62/0x80
 [<ffffffff812e6487>] sysfs_create_dir_ns+0x77/0x90
 [<ffffffff8140f2c4>] kobject_add_internal+0xb4/0x340
 [<ffffffff8140f5b8>] kobject_add+0x68/0xb0
 [<ffffffff8140f631>] kobject_create_and_add+0x31/0x70
 [<ffffffff8157a703>] module_add_driver+0xc3/0xd0
 [<ffffffff8155e5d4>] bus_add_driver+0x154/0x280
 [<ffffffff815604c0>] driver_register+0x60/0xe0
 [<ffffffff8145bed0>] __pci_register_driver+0x60/0x70
 [<ffffffffa0273e14>] saa7146_register_extension+0x64/0x90 [saa7146]
 [<ffffffffa0033011>] hexium_init_module+0x11/0x1000 [hexium_gemini]
...

As can be (mostly) seen, driver_register causes this call sequence:
  -> bus_add_driver
    -> module_add_driver
      -> module_create_drivers_dir
The last one creates "drivers" directory in /sys/module/<...>. When
this is done in parallel, the directory is attempted to be created
twice at the same time.

This can be easily reproduced by loading mxb and hexium_gemini in
parallel:
while :; do
  modprobe mxb &
  modprobe hexium_gemini
  wait
  rmmod mxb hexium_gemini saa7146_vv saa7146
done

saa7146 calls pci_register_driver for both mxb and hexium_gemini,
which means /sys/module/saa7146/drivers is to be created for both of
them.

Fix this by a new mutex in module_create_drivers_dir which makes the
test-and-create "drivers" dir atomic.

I inverted the condition and removed 'return' to avoid multiple
unlocks or a goto.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Fixes: fe480a2675ed (Modules: only add drivers/ direcory if needed)
Cc: v2.6.21+ <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/base/module.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/base/module.c b/drivers/base/module.c
index db930d3..2a21578 100644
--- a/drivers/base/module.c
+++ b/drivers/base/module.c
@@ -24,10 +24,12 @@ static char *make_driver_name(struct device_driver *drv)
 
 static void module_create_drivers_dir(struct module_kobject *mk)
 {
-	if (!mk || mk->drivers_dir)
-		return;
+	static DEFINE_MUTEX(drivers_dir_mutex);
 
-	mk->drivers_dir = kobject_create_and_add("drivers", &mk->kobj);
+	mutex_lock(&drivers_dir_mutex);
+	if (mk && !mk->drivers_dir)
+		mk->drivers_dir = kobject_create_and_add("drivers", &mk->kobj);
+	mutex_unlock(&drivers_dir_mutex);
 }
 
 void module_add_driver(struct module *mod, struct device_driver *drv)
-- 
2.5.0

[added to the 4.1 stable tree] kvm: Fix irq route entries exceeding KVM_MAX_IRQ_ROUTES

[Sasha Levin]

From: Xiubo Li <lixiubo@cmss.chinamobile.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit caf1ff26e1aa178133df68ac3d40815fed2187d9 ]

These days, we experienced one guest crash with 8 cores and 3 disks,
with qemu error logs as bellow:

qemu-system-x86_64: /build/qemu-2.0.0/kvm-all.c:984:
kvm_irqchip_commit_routes: Assertion `ret == 0' failed.

And then we found one patch(bdf026317d) in qemu tree, which said
could fix this bug.

Execute the following script will reproduce the BUG quickly:

irq_affinity.sh
========================================================================

vda_irq_num=25
vdb_irq_num=27
while [ 1 ]
do
    for irq in {1,2,4,8,10,20,40,80}
        do
            echo $irq > /proc/irq/$vda_irq_num/smp_affinity
            echo $irq > /proc/irq/$vdb_irq_num/smp_affinity
            dd if=/dev/vda of=/dev/zero bs=4K count=100 iflag=direct
            dd if=/dev/vdb of=/dev/zero bs=4K count=100 iflag=direct
        done
done
========================================================================

The following qemu log is added in the qemu code and is displayed when
this bug reproduced:

kvm_irqchip_commit_routes: max gsi: 1008, nr_allocated_irq_routes: 1024,
irq_routes->nr: 1024, gsi_count: 1024.

That's to say when irq_routes->nr == 1024, there are 1024 routing entries,
but in the kernel code when routes->nr >= 1024, will just return -EINVAL;

The nr is the number of the routing entries which is in of
[1 ~ KVM_MAX_IRQ_ROUTES], not the index in [0 ~ KVM_MAX_IRQ_ROUTES - 1].

This patch fix the BUG above.

Cc: stable@vger.kernel.org
Signed-off-by: Xiubo Li <lixiubo@cmss.chinamobile.com>
Signed-off-by: Wei Tang <tangwei@cmss.chinamobile.com>
Signed-off-by: Zhang Zhuoyu <zhangzhuoyu@cmss.chinamobile.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 virt/kvm/kvm_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index c2f87ff0..d93deb5 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2622,7 +2622,7 @@ static long kvm_vm_ioctl(struct file *filp,
 		if (copy_from_user(&routing, argp, sizeof(routing)))
 			goto out;
 		r = -EINVAL;
-		if (routing.nr >= KVM_MAX_IRQ_ROUTES)
+		if (routing.nr > KVM_MAX_IRQ_ROUTES)
 			goto out;
 		if (routing.flags)
 			goto out;
-- 
2.5.0

[added to the 4.1 stable tree] memory: omap-gpmc: Fix omap gpmc EXTRADELAY timing

[Sasha Levin]

From: "Ocquidant, Sebastien" <sebastienocquidant@eaton.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 8f50b8e57442d28e41bb736c173d8a2490549a82 ]

In the omap gpmc driver it can be noticed that GPMC_CONFIG4_OEEXTRADELAY
is overwritten by the WEEXTRADELAY value from the device tree and
GPMC_CONFIG4_WEEXTRADELAY is not updated by the value from the device
tree.

As a consequence, the memory accesses cannot be configured properly when
the extra delay are needed for OE and WE.

Fix the update of GPMC_CONFIG4_WEEXTRADELAY with the value from the
device tree file and prevents GPMC_CONFIG4_OEXTRADELAY
being overwritten by the WEXTRADELAY value from the device tree.

Cc: stable@vger.kernel.org
Signed-off-by: Ocquidant, Sebastien <sebastienocquidant@eaton.com>
Signed-off-by: Roger Quadros <rogerq@ti.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/memory/omap-gpmc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/memory/omap-gpmc.c b/drivers/memory/omap-gpmc.c
index c94ea0d..2c51acc 100644
--- a/drivers/memory/omap-gpmc.c
+++ b/drivers/memory/omap-gpmc.c
@@ -394,7 +394,7 @@ static void gpmc_cs_bool_timings(int cs, const struct gpmc_bool_timings *p)
 	gpmc_cs_modify_reg(cs, GPMC_CS_CONFIG4,
 			   GPMC_CONFIG4_OEEXTRADELAY, p->oe_extra_delay);
 	gpmc_cs_modify_reg(cs, GPMC_CS_CONFIG4,
-			   GPMC_CONFIG4_OEEXTRADELAY, p->we_extra_delay);
+			   GPMC_CONFIG4_WEEXTRADELAY, p->we_extra_delay);
 	gpmc_cs_modify_reg(cs, GPMC_CS_CONFIG6,
 			   GPMC_CONFIG6_CYCLE2CYCLESAMECSEN,
 			   p->cycle2cyclesamecsen);
-- 
2.5.0

[added to the 4.1 stable tree] cgroup: set css->id to -1 during init

[Sasha Levin]

From: Tejun Heo <tj@kernel.org>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 8fa3b8d689a54d6d04ff7803c724fb7aca6ce98e ]

If percpu_ref initialization fails during css_create(), the free path
can end up trying to free css->id of zero.  As ID 0 is unused, it
doesn't cause a critical breakage but it does trigger a warning
message.  Fix it by setting css->id to -1 from init_and_link_css().

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Wenwei Tao <ww.tao0320@gmail.com>
Fixes: 01e586598b22 ("cgroup: release css->id after css_free")
Cc: stable@vger.kernel.org # v4.0+
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 kernel/cgroup.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 530fecf..d01c604 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4478,6 +4478,7 @@ static void init_and_link_css(struct cgroup_subsys_state *css,
 	memset(css, 0, sizeof(*css));
 	css->cgroup = cgrp;
 	css->ss = ss;
+	css->id = -1;
 	INIT_LIST_HEAD(&css->sibling);
 	INIT_LIST_HEAD(&css->children);
 	css->serial_nr = css_serial_nr_next++;
-- 
2.5.0

[added to the 4.1 stable tree] KEYS: potential uninitialized variable

[Sasha Levin]

From: Dan Carpenter <dan.carpenter@oracle.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 38327424b40bcebe2de92d07312c89360ac9229a ]

If __key_link_begin() failed then "edit" would be uninitialized.  I've
added a check to fix that.

This allows a random user to crash the kernel, though it's quite
difficult to achieve.  There are three ways it can be done as the user
would have to cause an error to occur in __key_link():

 (1) Cause the kernel to run out of memory.  In practice, this is difficult
     to achieve without ENOMEM cropping up elsewhere and aborting the
     attempt.

 (2) Revoke the destination keyring between the keyring ID being looked up
     and it being tested for revocation.  In practice, this is difficult to
     time correctly because the KEYCTL_REJECT function can only be used
     from the request-key upcall process.  Further, users can only make use
     of what's in /sbin/request-key.conf, though this does including a
     rejection debugging test - which means that the destination keyring
     has to be the caller's session keyring in practice.

 (3) Have just enough key quota available to create a key, a new session
     keyring for the upcall and a link in the session keyring, but not then
     sufficient quota to create a link in the nominated destination keyring
     so that it fails with EDQUOT.

The bug can be triggered using option (3) above using something like the
following:

	echo 80 >/proc/sys/kernel/keys/root_maxbytes
	keyctl request2 user debug:fred negate @t

The above sets the quota to something much lower (80) to make the bug
easier to trigger, but this is dependent on the system.  Note also that
the name of the keyring created contains a random number that may be
between 1 and 10 characters in size, so may throw the test off by
changing the amount of quota used.

Assuming the failure occurs, something like the following will be seen:

	kfree_debugcheck: out of range ptr 6b6b6b6b6b6b6b68h
	------------[ cut here ]------------
	kernel BUG at ../mm/slab.c:2821!
	...
	RIP: 0010:[<ffffffff811600f9>] kfree_debugcheck+0x20/0x25
	RSP: 0018:ffff8804014a7de8  EFLAGS: 00010092
	RAX: 0000000000000034 RBX: 6b6b6b6b6b6b6b68 RCX: 0000000000000000
	RDX: 0000000000040001 RSI: 00000000000000f6 RDI: 0000000000000300
	RBP: ffff8804014a7df0 R08: 0000000000000001 R09: 0000000000000000
	R10: ffff8804014a7e68 R11: 0000000000000054 R12: 0000000000000202
	R13: ffffffff81318a66 R14: 0000000000000000 R15: 0000000000000001
	...
	Call Trace:
	  kfree+0xde/0x1bc
	  assoc_array_cancel_edit+0x1f/0x36
	  __key_link_end+0x55/0x63
	  key_reject_and_link+0x124/0x155
	  keyctl_reject_key+0xb6/0xe0
	  keyctl_negate_key+0x10/0x12
	  SyS_keyctl+0x9f/0xe7
	  do_syscall_64+0x63/0x13a
	  entry_SYSCALL64_slow_path+0x25/0x25

Fixes: f70e2e06196a ('KEYS: Do preallocation for __key_link()')
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 security/keys/key.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/security/keys/key.c b/security/keys/key.c
index aee2ec5..970b58e 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -578,7 +578,7 @@ int key_reject_and_link(struct key *key,
 
 	mutex_unlock(&key_construction_mutex);
 
-	if (keyring)
+	if (keyring && link_ret == 0)
 		__key_link_end(keyring, &key->index_key, edit);
 
 	/* wake up anyone waiting for a key to be constructed */
-- 
2.5.0

[added to the 4.1 stable tree] ALSA: hda - Fix possible race on regmap bypass flip

[Sasha Levin]

From: Takashi Iwai <tiwai@suse.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 3194ed497939c6448005542e3ca4fa2386968fa0 ]

HD-audio driver uses regmap cache bypass feature for reading a raw
value without the cache.  But this is racy since both the cached and
the uncached reads may occur concurrently.  The former is done via the
normal control API access while the latter comes from the proc file
read.

Even though the regmap itself has the protection against the
concurrent accesses, the flag set/reset is done without the
protection, so it may lead to inconsistent state of bypass flag that
doesn't match with the current read and occasionally result in a
kernel WARNING like:
  WARNING: CPU: 3 PID: 2731 at drivers/base/regmap/regcache.c:499 regcache_cache_only+0x78/0x93

One way to work around such a problem is to wrap with a mutex.  But in
this case, the solution is simpler: for the uncached read, we just
skip the regmap and directly calls its accessor.  The verb execution
there is protected by itself, so basically it's safe to call
individually.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=116171
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 include/sound/hda_regmap.h |  2 ++
 sound/hda/hdac_device.c    | 10 ++++------
 sound/hda/hdac_regmap.c    | 40 ++++++++++++++++++++++++++++------------
 3 files changed, 34 insertions(+), 18 deletions(-)

diff --git a/include/sound/hda_regmap.h b/include/sound/hda_regmap.h
index df70590..2f48d64 100644
--- a/include/sound/hda_regmap.h
+++ b/include/sound/hda_regmap.h
@@ -17,6 +17,8 @@ int snd_hdac_regmap_add_vendor_verb(struct hdac_device *codec,
 				    unsigned int verb);
 int snd_hdac_regmap_read_raw(struct hdac_device *codec, unsigned int reg,
 			     unsigned int *val);
+int snd_hdac_regmap_read_raw_uncached(struct hdac_device *codec,
+				      unsigned int reg, unsigned int *val);
 int snd_hdac_regmap_write_raw(struct hdac_device *codec, unsigned int reg,
 			      unsigned int val);
 int snd_hdac_regmap_update_raw(struct hdac_device *codec, unsigned int reg,
diff --git a/sound/hda/hdac_device.c b/sound/hda/hdac_device.c
index 961ca32..37f2dac 100644
--- a/sound/hda/hdac_device.c
+++ b/sound/hda/hdac_device.c
@@ -261,13 +261,11 @@ EXPORT_SYMBOL_GPL(_snd_hdac_read_parm);
 int snd_hdac_read_parm_uncached(struct hdac_device *codec, hda_nid_t nid,
 				int parm)
 {
-	int val;
+	unsigned int cmd, val;
 
-	if (codec->regmap)
-		regcache_cache_bypass(codec->regmap, true);
-	val = snd_hdac_read_parm(codec, nid, parm);
-	if (codec->regmap)
-		regcache_cache_bypass(codec->regmap, false);
+	cmd = snd_hdac_regmap_encode_verb(nid, AC_VERB_PARAMETERS) | parm;
+	if (snd_hdac_regmap_read_raw_uncached(codec, cmd, &val) < 0)
+		return -1;
 	return val;
 }
 EXPORT_SYMBOL_GPL(snd_hdac_read_parm_uncached);
diff --git a/sound/hda/hdac_regmap.c b/sound/hda/hdac_regmap.c
index b0ed870..c785e5a 100644
--- a/sound/hda/hdac_regmap.c
+++ b/sound/hda/hdac_regmap.c
@@ -420,14 +420,30 @@ int snd_hdac_regmap_write_raw(struct hdac_device *codec, unsigned int reg,
 EXPORT_SYMBOL_GPL(snd_hdac_regmap_write_raw);
 
 static int reg_raw_read(struct hdac_device *codec, unsigned int reg,
-			unsigned int *val)
+			unsigned int *val, bool uncached)
 {
-	if (!codec->regmap)
+	if (uncached || !codec->regmap)
 		return hda_reg_read(codec, reg, val);
 	else
 		return regmap_read(codec->regmap, reg, val);
 }
 
+static int __snd_hdac_regmap_read_raw(struct hdac_device *codec,
+				      unsigned int reg, unsigned int *val,
+				      bool uncached)
+{
+	int err;
+
+	err = reg_raw_read(codec, reg, val, uncached);
+	if (err == -EAGAIN) {
+		err = snd_hdac_power_up_pm(codec);
+		if (!err)
+			err = reg_raw_read(codec, reg, val, uncached);
+		snd_hdac_power_down_pm(codec);
+	}
+	return err;
+}
+
 /**
  * snd_hdac_regmap_read_raw - read a pseudo register with power mgmt
  * @codec: the codec object
@@ -439,19 +455,19 @@ static int reg_raw_read(struct hdac_device *codec, unsigned int reg,
 int snd_hdac_regmap_read_raw(struct hdac_device *codec, unsigned int reg,
 			     unsigned int *val)
 {
-	int err;
-
-	err = reg_raw_read(codec, reg, val);
-	if (err == -EAGAIN) {
-		err = snd_hdac_power_up_pm(codec);
-		if (!err)
-			err = reg_raw_read(codec, reg, val);
-		snd_hdac_power_down_pm(codec);
-	}
-	return err;
+	return __snd_hdac_regmap_read_raw(codec, reg, val, false);
 }
 EXPORT_SYMBOL_GPL(snd_hdac_regmap_read_raw);
 
+/* Works like snd_hdac_regmap_read_raw(), but this doesn't read from the
+ * cache but always via hda verbs.
+ */
+int snd_hdac_regmap_read_raw_uncached(struct hdac_device *codec,
+				      unsigned int reg, unsigned int *val)
+{
+	return __snd_hdac_regmap_read_raw(codec, reg, val, true);
+}
+
 /**
  * snd_hdac_regmap_update_raw - update a pseudo register with power mgmt
  * @codec: the codec object
-- 
2.5.0

[added to the 4.1 stable tree] ALSA: hdac_regmap - fix the register access for runtime PM

[Sasha Levin]

From: Jaroslav Kysela <perex@perex.cz>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 8198868f0a283eb23e264951632ce61ec2f82228 ]

Call path:

  1) snd_hdac_power_up_pm()
  2) snd_hdac_power_up()
  3) pm_runtime_get_sync()
  4) __pm_runtime_resume()
  5) rpm_resume()

The rpm_resume() returns 1 when the device is already active.
Because the return value is unmodified, the hdac regmap read/write
functions should allow this value for the retry I/O operation, too.

Signed-off-by: Jaroslav Kysela <perex@perex.cz>
Cc: <stable@vger.kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 sound/hda/hdac_regmap.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/hda/hdac_regmap.c b/sound/hda/hdac_regmap.c
index c785e5a..f3eb78e 100644
--- a/sound/hda/hdac_regmap.c
+++ b/sound/hda/hdac_regmap.c
@@ -411,7 +411,7 @@ int snd_hdac_regmap_write_raw(struct hdac_device *codec, unsigned int reg,
 	err = reg_raw_write(codec, reg, val);
 	if (err == -EAGAIN) {
 		err = snd_hdac_power_up_pm(codec);
-		if (!err)
+		if (err >= 0)
 			err = reg_raw_write(codec, reg, val);
 		snd_hdac_power_down_pm(codec);
 	}
@@ -437,7 +437,7 @@ static int __snd_hdac_regmap_read_raw(struct hdac_device *codec,
 	err = reg_raw_read(codec, reg, val, uncached);
 	if (err == -EAGAIN) {
 		err = snd_hdac_power_up_pm(codec);
-		if (!err)
+		if (err >= 0)
 			err = reg_raw_read(codec, reg, val, uncached);
 		snd_hdac_power_down_pm(codec);
 	}
-- 
2.5.0

[added to the 4.1 stable tree] btrfs: account for non-CoW'd blocks in btrfs_abort_transaction

[Sasha Levin]

From: Jeff Mahoney <jeffm@suse.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 64c12921e11b3a0c10d088606e328c58e29274d8 ]

The test for !trans->blocks_used in btrfs_abort_transaction is
insufficient to determine whether it's safe to drop the transaction
handle on the floor.  btrfs_cow_block, informed by should_cow_block,
can return blocks that have already been CoW'd in the current
transaction.  trans->blocks_used is only incremented for new block
allocations. If an operation overlaps the blocks in the current
transaction entirely and must abort the transaction, we'll happily
let it clean up the trans handle even though it may have modified
the blocks and will commit an incomplete operation.

In the long-term, I'd like to do closer tracking of when the fs
is actually modified so we can still recover as gracefully as possible,
but that approach will need some discussion.  In the short term,
since this is the only code using trans->blocks_used, let's just
switch it to a bool indicating whether any blocks were used and set
it when should_cow_block returns false.

Cc: stable@vger.kernel.org # 3.4+
Signed-off-by: Jeff Mahoney <jeffm@suse.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 fs/btrfs/ctree.c       | 5 ++++-
 fs/btrfs/extent-tree.c | 2 +-
 fs/btrfs/super.c       | 2 +-
 fs/btrfs/transaction.c | 1 -
 fs/btrfs/transaction.h | 2 +-
 5 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 0f11ebc..844c883 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1548,6 +1548,7 @@ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans,
 		       trans->transid, root->fs_info->generation);
 
 	if (!should_cow_block(trans, root, buf)) {
+		trans->dirty = true;
 		*cow_ret = buf;
 		return 0;
 	}
@@ -2767,8 +2768,10 @@ again:
 			 * then we don't want to set the path blocking,
 			 * so we test it here
 			 */
-			if (!should_cow_block(trans, root, b))
+			if (!should_cow_block(trans, root, b)) {
+				trans->dirty = true;
 				goto cow_done;
+			}
 
 			/*
 			 * must have write locks on this node and the
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index d1ae132..2771bc3 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -7504,7 +7504,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		set_extent_dirty(&trans->transaction->dirty_pages, buf->start,
 			 buf->start + buf->len - 1, GFP_NOFS);
 	}
-	trans->blocks_used++;
+	trans->dirty = true;
 	/* this returns a buffer locked for blocking */
 	return buf;
 }
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 70734d8..a40b454 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -262,7 +262,7 @@ void __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
 	trans->aborted = errno;
 	/* Nothing used. The other threads that have joined this
 	 * transaction may be able to continue. */
-	if (!trans->blocks_used && list_empty(&trans->new_bgs)) {
+	if (!trans->dirty && list_empty(&trans->new_bgs)) {
 		const char *errstr;
 
 		errstr = btrfs_decode_error(errno);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 00d18c2..6d43b2a 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -507,7 +507,6 @@ again:
 
 	h->transid = cur_trans->transid;
 	h->transaction = cur_trans;
-	h->blocks_used = 0;
 	h->bytes_reserved = 0;
 	h->root = root;
 	h->delayed_ref_updates = 0;
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 0b24755..4ce102b 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -105,7 +105,6 @@ struct btrfs_trans_handle {
 	u64 qgroup_reserved;
 	unsigned long use_count;
 	unsigned long blocks_reserved;
-	unsigned long blocks_used;
 	unsigned long delayed_ref_updates;
 	struct btrfs_transaction *transaction;
 	struct btrfs_block_rsv *block_rsv;
@@ -115,6 +114,7 @@ struct btrfs_trans_handle {
 	bool allocating_chunk;
 	bool reloc_reserved;
 	bool sync;
+	bool dirty;
 	unsigned int type;
 	/*
 	 * this root is only needed to validate that the root passed to
-- 
2.5.0

[added to the 4.1 stable tree] IB/mlx4: Properly initialize GRH TClass and FlowLabel in AHs

[Sasha Levin]

From: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 8c5122e45a10a9262f872b53f151a592e870f905 ]

When this code was reworked for IBoE support the order of assignments
for the sl_tclass_flowlabel got flipped around resulting in
TClass & FlowLabel being permanently set to 0 in the packet headers.

This breaks IB routers that rely on these headers, but only affects
kernel users - libmlx4 does this properly for user space.

Cc: stable@vger.kernel.org
Fixes: fa417f7b520e ("IB/mlx4: Add support for IBoE")
Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/infiniband/hw/mlx4/ah.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/mlx4/ah.c b/drivers/infiniband/hw/mlx4/ah.c
index 33fdd50..9fa27b0 100644
--- a/drivers/infiniband/hw/mlx4/ah.c
+++ b/drivers/infiniband/hw/mlx4/ah.c
@@ -47,6 +47,7 @@ static struct ib_ah *create_ib_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr,
 
 	ah->av.ib.port_pd = cpu_to_be32(to_mpd(pd)->pdn | (ah_attr->port_num << 24));
 	ah->av.ib.g_slid  = ah_attr->src_path_bits;
+	ah->av.ib.sl_tclass_flowlabel = cpu_to_be32(ah_attr->sl << 28);
 	if (ah_attr->ah_flags & IB_AH_GRH) {
 		ah->av.ib.g_slid   |= 0x80;
 		ah->av.ib.gid_index = ah_attr->grh.sgid_index;
@@ -64,7 +65,6 @@ static struct ib_ah *create_ib_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr,
 		       !(1 << ah->av.ib.stat_rate & dev->caps.stat_rate_support))
 			--ah->av.ib.stat_rate;
 	}
-	ah->av.ib.sl_tclass_flowlabel = cpu_to_be32(ah_attr->sl << 28);
 
 	return &ah->ibah;
 }
-- 
2.5.0

[added to the 4.1 stable tree] can: c_can: Update D_CAN TX and RX functions to 32 bit - fix Altera Cyclone access

[Sasha Levin]

From: Thor Thayer <tthayer@opensource.altera.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 427460c83cdf55069eee49799a0caef7dde8df69 ]

When testing CAN write floods on Altera's CycloneV, the first 2 bytes
are sometimes 0x00, 0x00 or corrupted instead of the values sent. Also
observed bytes 4 & 5 were corrupted in some cases.

The D_CAN Data registers are 32 bits and changing from 16 bit writes to
32 bit writes fixes the problem.

Testing performed on Altera CycloneV (D_CAN).  Requesting tests on other
C_CAN & D_CAN platforms.

Reported-by: Richard Andrysek <richard.andrysek@gomtec.de>
Signed-off-by: Thor Thayer <tthayer@opensource.altera.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/net/can/c_can/c_can.c | 38 +++++++++++++++++++++++++++++++-------
 1 file changed, 31 insertions(+), 7 deletions(-)

diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c
index 5d214d1..c076414 100644
--- a/drivers/net/can/c_can/c_can.c
+++ b/drivers/net/can/c_can/c_can.c
@@ -332,9 +332,23 @@ static void c_can_setup_tx_object(struct net_device *dev, int iface,
 
 	priv->write_reg(priv, C_CAN_IFACE(MSGCTRL_REG, iface), ctrl);
 
-	for (i = 0; i < frame->can_dlc; i += 2) {
-		priv->write_reg(priv, C_CAN_IFACE(DATA1_REG, iface) + i / 2,
-				frame->data[i] | (frame->data[i + 1] << 8));
+	if (priv->type == BOSCH_D_CAN) {
+		u32 data = 0, dreg = C_CAN_IFACE(DATA1_REG, iface);
+
+		for (i = 0; i < frame->can_dlc; i += 4, dreg += 2) {
+			data = (u32)frame->data[i];
+			data |= (u32)frame->data[i + 1] << 8;
+			data |= (u32)frame->data[i + 2] << 16;
+			data |= (u32)frame->data[i + 3] << 24;
+			priv->write_reg32(priv, dreg, data);
+		}
+	} else {
+		for (i = 0; i < frame->can_dlc; i += 2) {
+			priv->write_reg(priv,
+					C_CAN_IFACE(DATA1_REG, iface) + i / 2,
+					frame->data[i] |
+					(frame->data[i + 1] << 8));
+		}
 	}
 }
 
@@ -402,10 +416,20 @@ static int c_can_read_msg_object(struct net_device *dev, int iface, u32 ctrl)
 	} else {
 		int i, dreg = C_CAN_IFACE(DATA1_REG, iface);
 
-		for (i = 0; i < frame->can_dlc; i += 2, dreg ++) {
-			data = priv->read_reg(priv, dreg);
-			frame->data[i] = data;
-			frame->data[i + 1] = data >> 8;
+		if (priv->type == BOSCH_D_CAN) {
+			for (i = 0; i < frame->can_dlc; i += 4, dreg += 2) {
+				data = priv->read_reg32(priv, dreg);
+				frame->data[i] = data;
+				frame->data[i + 1] = data >> 8;
+				frame->data[i + 2] = data >> 16;
+				frame->data[i + 3] = data >> 24;
+			}
+		} else {
+			for (i = 0; i < frame->can_dlc; i += 2, dreg++) {
+				data = priv->read_reg(priv, dreg);
+				frame->data[i] = data;
+				frame->data[i + 1] = data >> 8;
+			}
 		}
 	}
 
-- 
2.5.0

[added to the 4.1 stable tree] can: at91_can: RX queue could get stuck at high bus load

[Sasha Levin]

From: Wolfgang Grandegger <wg@grandegger.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 43200a4480cbbe660309621817f54cbb93907108 ]

At high bus load it could happen that "at91_poll()" enters with all RX
message boxes filled up. If then at the end the "quota" is exceeded as
well, "rx_next" will not be reset to the first RX mailbox and hence the
interrupts remain disabled.

Signed-off-by: Wolfgang Grandegger <wg@grandegger.com>
Tested-by: Amr Bekhit <amrbekhit@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/net/can/at91_can.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c
index f4e40aa..35233aa 100644
--- a/drivers/net/can/at91_can.c
+++ b/drivers/net/can/at91_can.c
@@ -733,9 +733,10 @@ static int at91_poll_rx(struct net_device *dev, int quota)
 
 	/* upper group completed, look again in lower */
 	if (priv->rx_next > get_mb_rx_low_last(priv) &&
-	    quota > 0 && mb > get_mb_rx_last(priv)) {
+	    mb > get_mb_rx_last(priv)) {
 		priv->rx_next = get_mb_rx_first(priv);
-		goto again;
+		if (quota > 0)
+			goto again;
 	}
 
 	return received;
-- 
2.5.0

[added to the 4.1 stable tree] tracing: Handle NULL formats in hold_module_trace_bprintk_format()

[Sasha Levin]

From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 70c8217acd4383e069fe1898bbad36ea4fcdbdcc ]

If a task uses a non constant string for the format parameter in
trace_printk(), then the trace_printk_fmt variable is set to NULL. This
variable is then saved in the __trace_printk_fmt section.

The function hold_module_trace_bprintk_format() checks to see if duplicate
formats are used by modules, and reuses them if so (saves them to the list
if it is new). But this function calls lookup_format() that does a strcmp()
to the value (which is now NULL) and can cause a kernel oops.

This wasn't an issue till 3debb0a9ddb ("tracing: Fix trace_printk() to print
when not using bprintk()") which added "__used" to the trace_printk_fmt
variable, and before that, the kernel simply optimized it out (no NULL value
was saved).

The fix is simply to handle the NULL pointer in lookup_format() and have the
caller ignore the value if it was NULL.

Link: http://lkml.kernel.org/r/1464769870-18344-1-git-send-email-zhengjun.xing@intel.com

Reported-by: xingzhen <zhengjun.xing@intel.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Fixes: 3debb0a9ddb ("tracing: Fix trace_printk() to print when not using bprintk()")
Cc: stable@vger.kernel.org # v3.5+
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 kernel/trace/trace_printk.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index 6d6c041..fc0c74f 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -36,6 +36,10 @@ struct trace_bprintk_fmt {
 static inline struct trace_bprintk_fmt *lookup_format(const char *fmt)
 {
 	struct trace_bprintk_fmt *pos;
+
+	if (!fmt)
+		return ERR_PTR(-EINVAL);
+
 	list_for_each_entry(pos, &trace_bprintk_fmt_list, list) {
 		if (!strcmp(pos->fmt, fmt))
 			return pos;
@@ -57,7 +61,8 @@ void hold_module_trace_bprintk_format(const char **start, const char **end)
 	for (iter = start; iter < end; iter++) {
 		struct trace_bprintk_fmt *tb_fmt = lookup_format(*iter);
 		if (tb_fmt) {
-			*iter = tb_fmt->fmt;
+			if (!IS_ERR(tb_fmt))
+				*iter = tb_fmt->fmt;
 			continue;
 		}
 
-- 
2.5.0

[added to the 4.1 stable tree] drm: atmel-hlcdc: actually disable scaling when no scaling is required

[Sasha Levin]

From: Boris Brezillon <boris.brezillon@free-electrons.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 1b7e38b92b0bbd363369f5160f13f4d26140972d ]

The driver is only enabling scaling, but never disabling it, thus, if you
enable the scaling feature once it stays enabled forever.

Signed-off-by: Boris Brezillon <boris.brezillon@free-electrons.com>
Reported-by: Alex Vazquez <avazquez.dev@gmail.com>
Reviewed-by: Nicolas Ferre <nicolas.ferre@atmel.com>
Fixes: 1a396789f65a ("drm: add Atmel HLCDC Display Controller support")
Cc: <stable@vger.kernel.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
index be9fa82..767d0ea 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
@@ -335,6 +335,8 @@ atmel_hlcdc_plane_update_pos_and_size(struct atmel_hlcdc_plane *plane,
 
 		atmel_hlcdc_layer_update_cfg(&plane->layer, 13, 0xffffffff,
 					     factor_reg);
+	} else {
+		atmel_hlcdc_layer_update_cfg(&plane->layer, 13, 0xffffffff, 0);
 	}
 }
 
-- 
2.5.0

[added to the 4.1 stable tree] arm64: mm: remove page_mapping check in __sync_icache_dcache

[Sasha Levin]

From: Shaokun Zhang <zhangshaokun@hisilicon.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 20c27a4270c775d7ed661491af8ac03264d60fc6 ]

__sync_icache_dcache unconditionally skips the cache maintenance for
anonymous pages, under the assumption that flushing is only required in
the presence of D-side aliases [see 7249b79f6b4cc ("arm64: Do not flush
the D-cache for anonymous pages")].

Unfortunately, this breaks migration of anonymous pages holding
self-modifying code, where userspace cannot be reasonably expected to
reissue maintenance instructions in response to a migration.

This patch fixes the problem by removing the broken page_mapping(page)
check from the cache syncing code, otherwise we may end up fetching and
executing stale instructions from the PoU.

Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: <stable@vger.kernel.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Shaokun Zhang <zhangshaokun@hisilicon.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 arch/arm64/mm/flush.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index b6f14e8..bfb8eb16 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -74,10 +74,6 @@ void __sync_icache_dcache(pte_t pte, unsigned long addr)
 {
 	struct page *page = pte_page(pte);
 
-	/* no flushing needed for anonymous pages */
-	if (!page_mapping(page))
-		return;
-
 	if (!test_and_set_bit(PG_dcache_clean, &page->flags)) {
 		__flush_dcache_area(page_address(page),
 				PAGE_SIZE << compound_order(page));
-- 
2.5.0

[added to the 4.1 stable tree] pinctrl: imx: Do not treat a PIN without MUX register as an error

[Sasha Levin]

From: Alexander Shiyan <shc_work@mail.ru>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit ba562d5e54fd3136bfea0457add3675850247774 ]

Some PINs do not have a MUX register, it is not an error.
It is necessary to allow the continuation of the PINs configuration,
otherwise the whole PIN-group will be configured incorrectly.

Cc: stable@vger.kernel.org
Signed-off-by: Alexander Shiyan <shc_work@mail.ru>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/pinctrl/freescale/pinctrl-imx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/freescale/pinctrl-imx.c b/drivers/pinctrl/freescale/pinctrl-imx.c
index e261f1c..09c05bf 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx.c
@@ -205,9 +205,9 @@ static int imx_pmx_set(struct pinctrl_dev *pctldev, unsigned selector,
 		pin_reg = &info->pin_regs[pin_id];
 
 		if (pin_reg->mux_reg == -1) {
-			dev_err(ipctl->dev, "Pin(%s) does not support mux function\n",
+			dev_dbg(ipctl->dev, "Pin(%s) does not support mux function\n",
 				info->pins[pin_id].name);
-			return -EINVAL;
+			continue;
 		}
 
 		if (info->flags & SHARE_MUX_CONF_REG) {
-- 
2.5.0

[added to the 4.1 stable tree] pinctrl: single: Fix missing flush of posted write for a wakeirq

[Sasha Levin]

From: Tony Lindgren <tony@atomide.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 0ac3c0a4025f41748a083bdd4970cb3ede802b15 ]

With many repeated suspend resume cycles, the pin specific wakeirq
may not always work on omaps. This is because the write to enable the
pin interrupt may not have reached the device over the interconnect
before suspend happens.

Let's fix the issue with a flush of posted write with a readback.

Cc: stable@vger.kernel.org
Reported-by: Nishanth Menon <nm@ti.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/pinctrl/pinctrl-single.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c
index 13b45f2..11bf750 100644
--- a/drivers/pinctrl/pinctrl-single.c
+++ b/drivers/pinctrl/pinctrl-single.c
@@ -1576,6 +1576,9 @@ static inline void pcs_irq_set(struct pcs_soc_data *pcs_soc,
 		else
 			mask &= ~soc_mask;
 		pcs->write(mask, pcswi->reg);
+
+		/* flush posted write */
+		mask = pcs->read(pcswi->reg);
 		raw_spin_unlock(&pcs->lock);
 	}
 
-- 
2.5.0

[added to the 4.1 stable tree] ubi: Make recover_peb power cut aware

[Sasha Levin]

From: Richard Weinberger <richard@nod.at>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 972228d87445dc46c0a01f5f3de673ac017626f7 ]

recover_peb() was never power cut aware,
if a power cut happened right after writing the VID header
upon next attach UBI would blindly use the new partial written
PEB and all data from the old PEB is lost.

In order to make recover_peb() power cut aware, write the new
VID with a proper crc and copy_flag set such that the UBI attach
process will detect whether the new PEB is completely written
or not.
We cannot directly use ubi_eba_atomic_leb_change() since we'd
have to unlock the LEB which is facing a write error.

Cc: stable@vger.kernel.org
Reported-by: Jörg Pfähler <pfaehler@isse.de>
Reviewed-by: Jörg Pfähler <pfaehler@isse.de>
Signed-off-by: Richard Weinberger <richard@nod.at>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/mtd/ubi/eba.c | 22 +++++++++++++++-------
 1 file changed, 15 insertions(+), 7 deletions(-)

diff --git a/drivers/mtd/ubi/eba.c b/drivers/mtd/ubi/eba.c
index 1c73ba6..f109aee 100644
--- a/drivers/mtd/ubi/eba.c
+++ b/drivers/mtd/ubi/eba.c
@@ -575,6 +575,7 @@ static int recover_peb(struct ubi_device *ubi, int pnum, int vol_id, int lnum,
 	int err, idx = vol_id2idx(ubi, vol_id), new_pnum, data_size, tries = 0;
 	struct ubi_volume *vol = ubi->volumes[idx];
 	struct ubi_vid_hdr *vid_hdr;
+	uint32_t crc;
 
 	vid_hdr = ubi_zalloc_vid_hdr(ubi, GFP_NOFS);
 	if (!vid_hdr)
@@ -599,14 +600,8 @@ retry:
 		goto out_put;
 	}
 
-	vid_hdr->sqnum = cpu_to_be64(ubi_next_sqnum(ubi));
-	err = ubi_io_write_vid_hdr(ubi, new_pnum, vid_hdr);
-	if (err) {
-		up_read(&ubi->fm_eba_sem);
-		goto write_error;
-	}
+	ubi_assert(vid_hdr->vol_type == UBI_VID_DYNAMIC);
 
-	data_size = offset + len;
 	mutex_lock(&ubi->buf_mutex);
 	memset(ubi->peb_buf + offset, 0xFF, len);
 
@@ -621,6 +616,19 @@ retry:
 
 	memcpy(ubi->peb_buf + offset, buf, len);
 
+	data_size = offset + len;
+	crc = crc32(UBI_CRC32_INIT, ubi->peb_buf, data_size);
+	vid_hdr->sqnum = cpu_to_be64(ubi_next_sqnum(ubi));
+	vid_hdr->copy_flag = 1;
+	vid_hdr->data_size = cpu_to_be32(data_size);
+	vid_hdr->data_crc = cpu_to_be32(crc);
+	err = ubi_io_write_vid_hdr(ubi, new_pnum, vid_hdr);
+	if (err) {
+		mutex_unlock(&ubi->buf_mutex);
+		up_read(&ubi->fm_eba_sem);
+		goto write_error;
+	}
+
 	err = ubi_io_write_data(ubi, ubi->peb_buf, new_pnum, 0, data_size);
 	if (err) {
 		mutex_unlock(&ubi->buf_mutex);
-- 
2.5.0

[added to the 4.1 stable tree] mm: Export migrate_page_move_mapping and migrate_page_copy

[Sasha Levin]

From: Richard Weinberger <richard@nod.at>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 1118dce773d84f39ebd51a9fe7261f9169cb056e ]

Export these symbols such that UBIFS can implement
->migratepage.

Cc: stable@vger.kernel.org
Signed-off-by: Richard Weinberger <richard@nod.at>
Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 mm/migrate.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/mm/migrate.c b/mm/migrate.c
index fe71f91..2599977 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -389,6 +389,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
 
 	return MIGRATEPAGE_SUCCESS;
 }
+EXPORT_SYMBOL(migrate_page_move_mapping);
 
 /*
  * The expected number of remaining references is the same as that
@@ -549,6 +550,7 @@ void migrate_page_copy(struct page *newpage, struct page *page)
 	if (PageWriteback(newpage))
 		end_page_writeback(newpage);
 }
+EXPORT_SYMBOL(migrate_page_copy);
 
 /************************************************************
  *                    Migration functions
-- 
2.5.0

[added to the 4.1 stable tree] UBIFS: Implement ->migratepage()

[Sasha Levin]

From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 4ac1c17b2044a1b4b2fbed74451947e905fc2992 ]

During page migrations UBIFS might get confused
and the following assert triggers:
[  213.480000] UBIFS assert failed in ubifs_set_page_dirty at 1451 (pid 436)
[  213.490000] CPU: 0 PID: 436 Comm: drm-stress-test Not tainted 4.4.4-00176-geaa802524636-dirty #1008
[  213.490000] Hardware name: Allwinner sun4i/sun5i Families
[  213.490000] [<c0015e70>] (unwind_backtrace) from [<c0012cdc>] (show_stack+0x10/0x14)
[  213.490000] [<c0012cdc>] (show_stack) from [<c02ad834>] (dump_stack+0x8c/0xa0)
[  213.490000] [<c02ad834>] (dump_stack) from [<c0236ee8>] (ubifs_set_page_dirty+0x44/0x50)
[  213.490000] [<c0236ee8>] (ubifs_set_page_dirty) from [<c00fa0bc>] (try_to_unmap_one+0x10c/0x3a8)
[  213.490000] [<c00fa0bc>] (try_to_unmap_one) from [<c00fadb4>] (rmap_walk+0xb4/0x290)
[  213.490000] [<c00fadb4>] (rmap_walk) from [<c00fb1bc>] (try_to_unmap+0x64/0x80)
[  213.490000] [<c00fb1bc>] (try_to_unmap) from [<c010dc28>] (migrate_pages+0x328/0x7a0)
[  213.490000] [<c010dc28>] (migrate_pages) from [<c00d0cb0>] (alloc_contig_range+0x168/0x2f4)
[  213.490000] [<c00d0cb0>] (alloc_contig_range) from [<c010ec00>] (cma_alloc+0x170/0x2c0)
[  213.490000] [<c010ec00>] (cma_alloc) from [<c001a958>] (__alloc_from_contiguous+0x38/0xd8)
[  213.490000] [<c001a958>] (__alloc_from_contiguous) from [<c001ad44>] (__dma_alloc+0x23c/0x274)
[  213.490000] [<c001ad44>] (__dma_alloc) from [<c001ae08>] (arm_dma_alloc+0x54/0x5c)
[  213.490000] [<c001ae08>] (arm_dma_alloc) from [<c035cecc>] (drm_gem_cma_create+0xb8/0xf0)
[  213.490000] [<c035cecc>] (drm_gem_cma_create) from [<c035cf20>] (drm_gem_cma_create_with_handle+0x1c/0xe8)
[  213.490000] [<c035cf20>] (drm_gem_cma_create_with_handle) from [<c035d088>] (drm_gem_cma_dumb_create+0x3c/0x48)
[  213.490000] [<c035d088>] (drm_gem_cma_dumb_create) from [<c0341ed8>] (drm_ioctl+0x12c/0x444)
[  213.490000] [<c0341ed8>] (drm_ioctl) from [<c0121adc>] (do_vfs_ioctl+0x3f4/0x614)
[  213.490000] [<c0121adc>] (do_vfs_ioctl) from [<c0121d30>] (SyS_ioctl+0x34/0x5c)
[  213.490000] [<c0121d30>] (SyS_ioctl) from [<c000f2c0>] (ret_fast_syscall+0x0/0x34)

UBIFS is using PagePrivate() which can have different meanings across
filesystems. Therefore the generic page migration code cannot handle this
case correctly.
We have to implement our own migration function which basically does a
plain copy but also duplicates the page private flag.
UBIFS is not a block device filesystem and cannot use buffer_migrate_page().

Cc: stable@vger.kernel.org
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
[rw: Massaged changelog, build fixes, etc...]
Signed-off-by: Richard Weinberger <richard@nod.at>
Acked-by: Christoph Hellwig <hch@lst.de>

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 fs/ubifs/file.c | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 35efc10..75e9b2d 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -53,6 +53,7 @@
 #include <linux/mount.h>
 #include <linux/namei.h>
 #include <linux/slab.h>
+#include <linux/migrate.h>
 
 static int read_block(struct inode *inode, void *addr, unsigned int block,
 		      struct ubifs_data_node *dn)
@@ -1420,6 +1421,26 @@ static int ubifs_set_page_dirty(struct page *page)
 	return ret;
 }
 
+#ifdef CONFIG_MIGRATION
+static int ubifs_migrate_page(struct address_space *mapping,
+		struct page *newpage, struct page *page, enum migrate_mode mode)
+{
+	int rc;
+
+	rc = migrate_page_move_mapping(mapping, newpage, page, NULL, mode, 0);
+	if (rc != MIGRATEPAGE_SUCCESS)
+		return rc;
+
+	if (PagePrivate(page)) {
+		ClearPagePrivate(page);
+		SetPagePrivate(newpage);
+	}
+
+	migrate_page_copy(newpage, page);
+	return MIGRATEPAGE_SUCCESS;
+}
+#endif
+
 static int ubifs_releasepage(struct page *page, gfp_t unused_gfp_flags)
 {
 	/*
@@ -1556,6 +1577,9 @@ const struct address_space_operations ubifs_file_address_operations = {
 	.write_end      = ubifs_write_end,
 	.invalidatepage = ubifs_invalidatepage,
 	.set_page_dirty = ubifs_set_page_dirty,
+#ifdef CONFIG_MIGRATION
+	.migratepage	= ubifs_migrate_page,
+#endif
 	.releasepage    = ubifs_releasepage,
 };
 
-- 
2.5.0

[added to the 4.1 stable tree] can: fix handling of unmodifiable configuration options fix

[Sasha Levin]

From: Oliver Hartkopp <socketcan@hartkopp.net>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit bce271f255dae8335dc4d2ee2c4531e09cc67f5a ]

With upstream commit bb208f144cf3f59 (can: fix handling of unmodifiable
configuration options) a new can_validate() function was introduced.

When invoking 'ip link set can0 type can' without any configuration data
can_validate() tries to validate the content without taking into account that
there's totally no content. This patch adds a check for missing content.

Reported-by: ajneu <ajneu1@gmail.com>
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Cc: <stable@vger.kernel.org>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/net/can/dev.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index 910c12e..348dd50 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -798,6 +798,9 @@ static int can_validate(struct nlattr *tb[], struct nlattr *data[])
 	 * - control mode with CAN_CTRLMODE_FD set
 	 */
 
+	if (!data)
+		return 0;
+
 	if (data[IFLA_CAN_CTRLMODE]) {
 		struct can_ctrlmode *cm = nla_data(data[IFLA_CAN_CTRLMODE]);
 
-- 
2.5.0

[added to the 4.1 stable tree] can: fix oops caused by wrong rtnl dellink usage

[Sasha Levin]

From: Oliver Hartkopp <socketcan@hartkopp.net>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 25e1ed6e64f52a692ba3191c4fde650aab3ecc07 ]

For 'real' hardware CAN devices the netlink interface is used to set CAN
specific communication parameters. Real CAN hardware can not be created nor
removed with the ip tool ...

This patch adds a private dellink function for the CAN device driver interface
that does just nothing.

It's a follow up to commit 993e6f2fd ("can: fix oops caused by wrong rtnl
newlink usage") but for dellink.

Reported-by: ajneu <ajneu1@gmail.com>
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Cc: <stable@vger.kernel.org>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/net/can/dev.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index 348dd50..ad535a8 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -1011,6 +1011,11 @@ static int can_newlink(struct net *src_net, struct net_device *dev,
 	return -EOPNOTSUPP;
 }
 
+static void can_dellink(struct net_device *dev, struct list_head *head)
+{
+	return;
+}
+
 static struct rtnl_link_ops can_link_ops __read_mostly = {
 	.kind		= "can",
 	.maxtype	= IFLA_CAN_MAX,
@@ -1019,6 +1024,7 @@ static struct rtnl_link_ops can_link_ops __read_mostly = {
 	.validate	= can_validate,
 	.newlink	= can_newlink,
 	.changelink	= can_changelink,
+	.dellink	= can_dellink,
 	.get_size	= can_get_size,
 	.fill_info	= can_fill_info,
 	.get_xstats_size = can_get_xstats_size,
-- 
2.5.0

[added to the 4.1 stable tree] xen/pciback: Fix conf_space read/write overlap check.

[Sasha Levin]

From: Andrey Grodzovsky <andrey2805@gmail.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 02ef871ecac290919ea0c783d05da7eedeffc10e ]

Current overlap check is evaluating to false a case where a filter
field is fully contained (proper subset) of a r/w request.  This
change applies classical overlap check instead to include all the
scenarios.

More specifically, for (Hilscher GmbH CIFX 50E-DP(M/S)) device driver
the logic is such that the entire confspace is read and written in 4
byte chunks. In this case as an example, CACHE_LINE_SIZE,
LATENCY_TIMER and PCI_BIST are arriving together in one call to
xen_pcibk_config_write() with offset == 0xc and size == 4.  With the
exsisting overlap check the LATENCY_TIMER field (offset == 0xd, length
== 1) is fully contained in the write request and hence is excluded
from write, which is incorrect.

Signed-off-by: Andrey Grodzovsky <andrey2805@gmail.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Reviewed-by: Jan Beulich <JBeulich@suse.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/xen/xen-pciback/conf_space.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/xen/xen-pciback/conf_space.c b/drivers/xen/xen-pciback/conf_space.c
index 9c23420..47a4177 100644
--- a/drivers/xen/xen-pciback/conf_space.c
+++ b/drivers/xen/xen-pciback/conf_space.c
@@ -183,8 +183,7 @@ int xen_pcibk_config_read(struct pci_dev *dev, int offset, int size,
 		field_start = OFFSET(cfg_entry);
 		field_end = OFFSET(cfg_entry) + field->size;
 
-		if ((req_start >= field_start && req_start < field_end)
-		    || (req_end > field_start && req_end <= field_end)) {
+		 if (req_end > field_start && field_end > req_start) {
 			err = conf_space_read(dev, cfg_entry, field_start,
 					      &tmp_val);
 			if (err)
@@ -230,8 +229,7 @@ int xen_pcibk_config_write(struct pci_dev *dev, int offset, int size, u32 value)
 		field_start = OFFSET(cfg_entry);
 		field_end = OFFSET(cfg_entry) + field->size;
 
-		if ((req_start >= field_start && req_start < field_end)
-		    || (req_end > field_start && req_end <= field_end)) {
+		 if (req_end > field_start && field_end > req_start) {
 			tmp_val = 0;
 
 			err = xen_pcibk_config_read(dev, field_start,
-- 
2.5.0

[added to the 4.1 stable tree] Input: wacom_w8001 - w8001_MAX_LENGTH should be 13

[Sasha Levin]

From: Ping Cheng <pinglinux@gmail.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 12afb34400eb2b301f06b2aa3535497d14faee59 ]

Somehow the patch that added two-finger touch support forgot to update
W8001_MAX_LENGTH from 11 to 13.

Signed-off-by: Ping Cheng <pingc@wacom.com>
Reviewed-by: Peter Hutterer <peter.hutterer@who-t.net>
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/input/touchscreen/wacom_w8001.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/input/touchscreen/wacom_w8001.c b/drivers/input/touchscreen/wacom_w8001.c
index 2792ca3..3ed0ce1 100644
--- a/drivers/input/touchscreen/wacom_w8001.c
+++ b/drivers/input/touchscreen/wacom_w8001.c
@@ -27,7 +27,7 @@ MODULE_AUTHOR("Jaya Kumar <jayakumar.lkml@gmail.com>");
 MODULE_DESCRIPTION(DRIVER_DESC);
 MODULE_LICENSE("GPL");
 
-#define W8001_MAX_LENGTH	11
+#define W8001_MAX_LENGTH	13
 #define W8001_LEAD_MASK		0x80
 #define W8001_LEAD_BYTE		0x80
 #define W8001_TAB_MASK		0x40
-- 
2.5.0

[added to the 4.1 stable tree] Input: elantech - add more IC body types to the list

[Sasha Levin]

From: Dmitry Torokhov <dmitry.torokhov@gmail.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 226ba707744a51acb4244724e09caacb1d96aed9 ]

The touchpad in HP Pavilion 14-ab057ca reports it's version as 12 and
according to Elan both 11 and 12 are valid IC types and should be
identified as hw_version 4.

Reported-by: Patrick Lessard <Patrick.Lessard@cogeco.com>
Tested-by: Patrick Lessard <Patrick.Lessard@cogeco.com>
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/input/mouse/elantech.c | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c
index 0f5b400..c3c5d49 100644
--- a/drivers/input/mouse/elantech.c
+++ b/drivers/input/mouse/elantech.c
@@ -1550,13 +1550,7 @@ static int elantech_set_properties(struct elantech_data *etd)
 		case 5:
 			etd->hw_version = 3;
 			break;
-		case 6:
-		case 7:
-		case 8:
-		case 9:
-		case 10:
-		case 13:
-		case 14:
+		case 6 ... 14:
 			etd->hw_version = 4;
 			break;
 		default:
-- 
2.5.0

[added to the 4.1 stable tree] drm/nouveau: fix for disabled fbdev emulation

[Sasha Levin]

From: Dmitrii Tcvetkov <demfloro@demfloro.ru>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 52dfcc5ccfbb6697ac3cac7f7ff1e712760e1216 ]

Hello,

after this commit:

commit f045f459d925138fe7d6193a8c86406bda7e49da
Author: Ben Skeggs <bskeggs@redhat.com>
Date:   Thu Jun 2 12:23:31 2016 +1000
    drm/nouveau/fbcon: fix out-of-bounds memory accesses

kernel started to oops when loading nouveau module when using GTX 780 Ti
video adapter. This patch fixes the problem.

Bug report: https://bugzilla.kernel.org/show_bug.cgi?id=120591

Signed-off-by: Dmitrii Tcvetkov <demfloro@demfloro.ru>
Suggested-by: Ilia Mirkin <imirkin@alum.mit.edu>
Fixes: f045f459d925 ("nouveau_fbcon_init()")
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/gpu/drm/nouveau/nouveau_fbcon.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
index cf43f77..bb29f1e 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
@@ -572,7 +572,8 @@ nouveau_fbcon_init(struct drm_device *dev)
 	if (ret)
 		goto fini;
 
-	fbcon->helper.fbdev->pixmap.buf_align = 4;
+	if (fbcon->helper.fbdev)
+		fbcon->helper.fbdev->pixmap.buf_align = 4;
 	return 0;
 
 fini:
-- 
2.5.0

[added to the 4.1 stable tree] Input: vmmouse - remove port reservation

[Sasha Levin]

From: Sinclair Yeh <syeh@vmware.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 60842ef8128e7bf58c024814cd0dc14319232b6c ]

The VMWare EFI BIOS will expose port 0x5658 as an ACPI resource.  This
causes the port to be reserved by the APCI module as the system comes up,
making it unavailable to be reserved again by other drivers, thus
preserving this VMWare port for special use in a VMWare guest.

This port is designed to be shared among multiple VMWare services, such as
the VMMOUSE.  Because of this, VMMOUSE should not try to reserve this port
on its own.

The VMWare non-EFI BIOS does not do this to preserve compatibility with
existing/legacy VMs.  It is known that there is small chance a VM may be
configured such that these ports get reserved by other non-VMWare devices,
and if this ever happens, the result is undefined.

Signed-off-by: Sinclair Yeh <syeh@vmware.com>
Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com>
Cc: <stable@vger.kernel.org> # 4.1-
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/input/mouse/vmmouse.c | 22 ++--------------------
 1 file changed, 2 insertions(+), 20 deletions(-)

diff --git a/drivers/input/mouse/vmmouse.c b/drivers/input/mouse/vmmouse.c
index a3f0f5a..0f58678 100644
--- a/drivers/input/mouse/vmmouse.c
+++ b/drivers/input/mouse/vmmouse.c
@@ -355,18 +355,11 @@ int vmmouse_detect(struct psmouse *psmouse, bool set_properties)
 		return -ENXIO;
 	}
 
-	if (!request_region(VMMOUSE_PROTO_PORT, 4, "vmmouse")) {
-		psmouse_dbg(psmouse, "VMMouse port in use.\n");
-		return -EBUSY;
-	}
-
 	/* Check if the device is present */
 	response = ~VMMOUSE_PROTO_MAGIC;
 	VMMOUSE_CMD(GETVERSION, 0, version, response, dummy1, dummy2);
-	if (response != VMMOUSE_PROTO_MAGIC || version == 0xffffffffU) {
-		release_region(VMMOUSE_PROTO_PORT, 4);
+	if (response != VMMOUSE_PROTO_MAGIC || version == 0xffffffffU)
 		return -ENXIO;
-	}
 
 	if (set_properties) {
 		psmouse->vendor = VMMOUSE_VENDOR;
@@ -374,8 +367,6 @@ int vmmouse_detect(struct psmouse *psmouse, bool set_properties)
 		psmouse->model = version;
 	}
 
-	release_region(VMMOUSE_PROTO_PORT, 4);
-
 	return 0;
 }
 
@@ -394,7 +385,6 @@ static void vmmouse_disconnect(struct psmouse *psmouse)
 	psmouse_reset(psmouse);
 	input_unregister_device(priv->abs_dev);
 	kfree(priv);
-	release_region(VMMOUSE_PROTO_PORT, 4);
 }
 
 /**
@@ -438,15 +428,10 @@ int vmmouse_init(struct psmouse *psmouse)
 	struct input_dev *rel_dev = psmouse->dev, *abs_dev;
 	int error;
 
-	if (!request_region(VMMOUSE_PROTO_PORT, 4, "vmmouse")) {
-		psmouse_dbg(psmouse, "VMMouse port in use.\n");
-		return -EBUSY;
-	}
-
 	psmouse_reset(psmouse);
 	error = vmmouse_enable(psmouse);
 	if (error)
-		goto release_region;
+		return error;
 
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
 	abs_dev = input_allocate_device();
@@ -502,8 +487,5 @@ init_fail:
 	kfree(priv);
 	psmouse->private = NULL;
 
-release_region:
-	release_region(VMMOUSE_PROTO_PORT, 4);
-
 	return error;
 }
-- 
2.5.0

[added to the 4.1 stable tree] cifs: dynamic allocation of ntlmssp blob

[Sasha Levin]

From: Jerome Marchand <jmarchan@redhat.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit b8da344b74c822e966c6d19d6b2321efe82c5d97 ]

In sess_auth_rawntlmssp_authenticate(), the ntlmssp blob is allocated
statically and its size is an "empirical" 5*sizeof(struct
_AUTHENTICATE_MESSAGE) (320B on x86_64). I don't know where this value
comes from or if it was ever appropriate, but it is currently
insufficient: the user and domain name in UTF16 could take 1kB by
themselves. Because of that, build_ntlmssp_auth_blob() might corrupt
memory (out-of-bounds write). The size of ntlmssp_blob in
SMB2_sess_setup() is too small too (sizeof(struct _NEGOTIATE_MESSAGE)
+ 500).

This patch allocates the blob dynamically in
build_ntlmssp_auth_blob().

Signed-off-by: Jerome Marchand <jmarchan@redhat.com>
Signed-off-by: Steve French <smfrench@gmail.com>
CC: Stable <stable@vger.kernel.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 fs/cifs/ntlmssp.h |  2 +-
 fs/cifs/sess.c    | 76 ++++++++++++++++++++++++++++++-------------------------
 fs/cifs/smb2pdu.c | 10 ++------
 3 files changed, 45 insertions(+), 43 deletions(-)

diff --git a/fs/cifs/ntlmssp.h b/fs/cifs/ntlmssp.h
index 848249f..3079b38 100644
--- a/fs/cifs/ntlmssp.h
+++ b/fs/cifs/ntlmssp.h
@@ -133,6 +133,6 @@ typedef struct _AUTHENTICATE_MESSAGE {
 
 int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len, struct cifs_ses *ses);
 void build_ntlmssp_negotiate_blob(unsigned char *pbuffer, struct cifs_ses *ses);
-int build_ntlmssp_auth_blob(unsigned char *pbuffer, u16 *buflen,
+int build_ntlmssp_auth_blob(unsigned char **pbuffer, u16 *buflen,
 			struct cifs_ses *ses,
 			const struct nls_table *nls_cp);
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index 8ffda50..5f9229d 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -364,19 +364,43 @@ void build_ntlmssp_negotiate_blob(unsigned char *pbuffer,
 	sec_blob->DomainName.MaximumLength = 0;
 }
 
-/* We do not malloc the blob, it is passed in pbuffer, because its
-   maximum possible size is fixed and small, making this approach cleaner.
-   This function returns the length of the data in the blob */
-int build_ntlmssp_auth_blob(unsigned char *pbuffer,
+static int size_of_ntlmssp_blob(struct cifs_ses *ses)
+{
+	int sz = sizeof(AUTHENTICATE_MESSAGE) + ses->auth_key.len
+		- CIFS_SESS_KEY_SIZE + CIFS_CPHTXT_SIZE + 2;
+
+	if (ses->domainName)
+		sz += 2 * strnlen(ses->domainName, CIFS_MAX_DOMAINNAME_LEN);
+	else
+		sz += 2;
+
+	if (ses->user_name)
+		sz += 2 * strnlen(ses->user_name, CIFS_MAX_USERNAME_LEN);
+	else
+		sz += 2;
+
+	return sz;
+}
+
+int build_ntlmssp_auth_blob(unsigned char **pbuffer,
 					u16 *buflen,
 				   struct cifs_ses *ses,
 				   const struct nls_table *nls_cp)
 {
 	int rc;
-	AUTHENTICATE_MESSAGE *sec_blob = (AUTHENTICATE_MESSAGE *)pbuffer;
+	AUTHENTICATE_MESSAGE *sec_blob;
 	__u32 flags;
 	unsigned char *tmp;
 
+	rc = setup_ntlmv2_rsp(ses, nls_cp);
+	if (rc) {
+		cifs_dbg(VFS, "Error %d during NTLMSSP authentication\n", rc);
+		*buflen = 0;
+		goto setup_ntlmv2_ret;
+	}
+	*pbuffer = kmalloc(size_of_ntlmssp_blob(ses), GFP_KERNEL);
+	sec_blob = (AUTHENTICATE_MESSAGE *)*pbuffer;
+
 	memcpy(sec_blob->Signature, NTLMSSP_SIGNATURE, 8);
 	sec_blob->MessageType = NtLmAuthenticate;
 
@@ -391,7 +415,7 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer,
 			flags |= NTLMSSP_NEGOTIATE_KEY_XCH;
 	}
 
-	tmp = pbuffer + sizeof(AUTHENTICATE_MESSAGE);
+	tmp = *pbuffer + sizeof(AUTHENTICATE_MESSAGE);
 	sec_blob->NegotiateFlags = cpu_to_le32(flags);
 
 	sec_blob->LmChallengeResponse.BufferOffset =
@@ -399,13 +423,9 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer,
 	sec_blob->LmChallengeResponse.Length = 0;
 	sec_blob->LmChallengeResponse.MaximumLength = 0;
 
-	sec_blob->NtChallengeResponse.BufferOffset = cpu_to_le32(tmp - pbuffer);
+	sec_blob->NtChallengeResponse.BufferOffset =
+				cpu_to_le32(tmp - *pbuffer);
 	if (ses->user_name != NULL) {
-		rc = setup_ntlmv2_rsp(ses, nls_cp);
-		if (rc) {
-			cifs_dbg(VFS, "Error %d during NTLMSSP authentication\n", rc);
-			goto setup_ntlmv2_ret;
-		}
 		memcpy(tmp, ses->auth_key.response + CIFS_SESS_KEY_SIZE,
 				ses->auth_key.len - CIFS_SESS_KEY_SIZE);
 		tmp += ses->auth_key.len - CIFS_SESS_KEY_SIZE;
@@ -423,7 +443,7 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer,
 	}
 
 	if (ses->domainName == NULL) {
-		sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - pbuffer);
+		sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - *pbuffer);
 		sec_blob->DomainName.Length = 0;
 		sec_blob->DomainName.MaximumLength = 0;
 		tmp += 2;
@@ -432,14 +452,14 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer,
 		len = cifs_strtoUTF16((__le16 *)tmp, ses->domainName,
 				      CIFS_MAX_USERNAME_LEN, nls_cp);
 		len *= 2; /* unicode is 2 bytes each */
-		sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - pbuffer);
+		sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - *pbuffer);
 		sec_blob->DomainName.Length = cpu_to_le16(len);
 		sec_blob->DomainName.MaximumLength = cpu_to_le16(len);
 		tmp += len;
 	}
 
 	if (ses->user_name == NULL) {
-		sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - pbuffer);
+		sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - *pbuffer);
 		sec_blob->UserName.Length = 0;
 		sec_blob->UserName.MaximumLength = 0;
 		tmp += 2;
@@ -448,13 +468,13 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer,
 		len = cifs_strtoUTF16((__le16 *)tmp, ses->user_name,
 				      CIFS_MAX_USERNAME_LEN, nls_cp);
 		len *= 2; /* unicode is 2 bytes each */
-		sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - pbuffer);
+		sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - *pbuffer);
 		sec_blob->UserName.Length = cpu_to_le16(len);
 		sec_blob->UserName.MaximumLength = cpu_to_le16(len);
 		tmp += len;
 	}
 
-	sec_blob->WorkstationName.BufferOffset = cpu_to_le32(tmp - pbuffer);
+	sec_blob->WorkstationName.BufferOffset = cpu_to_le32(tmp - *pbuffer);
 	sec_blob->WorkstationName.Length = 0;
 	sec_blob->WorkstationName.MaximumLength = 0;
 	tmp += 2;
@@ -463,19 +483,19 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer,
 		(ses->ntlmssp->server_flags & NTLMSSP_NEGOTIATE_EXTENDED_SEC))
 			&& !calc_seckey(ses)) {
 		memcpy(tmp, ses->ntlmssp->ciphertext, CIFS_CPHTXT_SIZE);
-		sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - pbuffer);
+		sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - *pbuffer);
 		sec_blob->SessionKey.Length = cpu_to_le16(CIFS_CPHTXT_SIZE);
 		sec_blob->SessionKey.MaximumLength =
 				cpu_to_le16(CIFS_CPHTXT_SIZE);
 		tmp += CIFS_CPHTXT_SIZE;
 	} else {
-		sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - pbuffer);
+		sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - *pbuffer);
 		sec_blob->SessionKey.Length = 0;
 		sec_blob->SessionKey.MaximumLength = 0;
 	}
 
+	*buflen = tmp - *pbuffer;
 setup_ntlmv2_ret:
-	*buflen = tmp - pbuffer;
 	return rc;
 }
 
@@ -1266,7 +1286,7 @@ sess_auth_rawntlmssp_authenticate(struct sess_data *sess_data)
 	struct cifs_ses *ses = sess_data->ses;
 	__u16 bytes_remaining;
 	char *bcc_ptr;
-	char *ntlmsspblob = NULL;
+	unsigned char *ntlmsspblob = NULL;
 	u16 blob_len;
 
 	cifs_dbg(FYI, "rawntlmssp session setup authenticate phase\n");
@@ -1279,19 +1299,7 @@ sess_auth_rawntlmssp_authenticate(struct sess_data *sess_data)
 	/* Build security blob before we assemble the request */
 	pSMB = (SESSION_SETUP_ANDX *)sess_data->iov[0].iov_base;
 	smb_buf = (struct smb_hdr *)pSMB;
-	/*
-	 * 5 is an empirical value, large enough to hold
-	 * authenticate message plus max 10 of av paris,
-	 * domain, user, workstation names, flags, etc.
-	 */
-	ntlmsspblob = kzalloc(5*sizeof(struct _AUTHENTICATE_MESSAGE),
-				GFP_KERNEL);
-	if (!ntlmsspblob) {
-		rc = -ENOMEM;
-		goto out;
-	}
-
-	rc = build_ntlmssp_auth_blob(ntlmsspblob,
+	rc = build_ntlmssp_auth_blob(&ntlmsspblob,
 					&blob_len, ses, sess_data->nls_cp);
 	if (rc)
 		goto out_free_ntlmsspblob;
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 14e845e..1a6191d 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -532,7 +532,7 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses,
 	u16 blob_length = 0;
 	struct key *spnego_key = NULL;
 	char *security_blob = NULL;
-	char *ntlmssp_blob = NULL;
+	unsigned char *ntlmssp_blob = NULL;
 	bool use_spnego = false; /* else use raw ntlmssp */
 
 	cifs_dbg(FYI, "Session Setup\n");
@@ -657,13 +657,7 @@ ssetup_ntlmssp_authenticate:
 		iov[1].iov_len = blob_length;
 	} else if (phase == NtLmAuthenticate) {
 		req->hdr.SessionId = ses->Suid;
-		ntlmssp_blob = kzalloc(sizeof(struct _NEGOTIATE_MESSAGE) + 500,
-				       GFP_KERNEL);
-		if (ntlmssp_blob == NULL) {
-			rc = -ENOMEM;
-			goto ssetup_exit;
-		}
-		rc = build_ntlmssp_auth_blob(ntlmssp_blob, &blob_length, ses,
+		rc = build_ntlmssp_auth_blob(&ntlmssp_blob, &blob_length, ses,
 					     nls_cp);
 		if (rc) {
 			cifs_dbg(FYI, "build_ntlmssp_auth_blob failed %d\n",
-- 
2.5.0

[added to the 4.1 stable tree] HID: hiddev: validate num_values for HIDIOCGUSAGES, HIDIOCSUSAGES commands

[Sasha Levin]

From: Scott Bauer <sbauer@plzdonthack.me>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 93a2001bdfd5376c3dc2158653034c20392d15c5 ]

This patch validates the num_values parameter from userland during the
HIDIOCGUSAGES and HIDIOCSUSAGES commands. Previously, if the report id was set
to HID_REPORT_ID_UNKNOWN, we would fail to validate the num_values parameter
leading to a heap overflow.

Cc: stable@vger.kernel.org
Signed-off-by: Scott Bauer <sbauer@plzdonthack.me>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/hid/usbhid/hiddev.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c
index 2f1ddca..700145b 100644
--- a/drivers/hid/usbhid/hiddev.c
+++ b/drivers/hid/usbhid/hiddev.c
@@ -516,13 +516,13 @@ static noinline int hiddev_ioctl_usage(struct hiddev *hiddev, unsigned int cmd,
 					goto inval;
 			} else if (uref->usage_index >= field->report_count)
 				goto inval;
-
-			else if ((cmd == HIDIOCGUSAGES || cmd == HIDIOCSUSAGES) &&
-				 (uref_multi->num_values > HID_MAX_MULTI_USAGES ||
-				  uref->usage_index + uref_multi->num_values > field->report_count))
-				goto inval;
 		}
 
+		if ((cmd == HIDIOCGUSAGES || cmd == HIDIOCSUSAGES) &&
+		    (uref_multi->num_values > HID_MAX_MULTI_USAGES ||
+		     uref->usage_index + uref_multi->num_values > field->report_count))
+			goto inval;
+
 		switch (cmd) {
 		case HIDIOCGUSAGE:
 			uref->value = field->value[uref->usage_index];
-- 
2.5.0

[added to the 4.1 stable tree] ALSA: hda - remove one pin from ALC292_STANDARD_PINS

[Sasha Levin]

From: Hui Wang <hui.wang@canonical.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 21e9d017b88ea0baa367ef0b6516d794fa23e85e ]

One more Dell laptop with alc293 codec needs
ALC293_FIXUP_DELL1_MIC_NO_PRESENCE, but the pin 0x1e does not match
the corresponding one in the ALC292_STANDARD_PINS. To use this macro
for this machine, we need to remove pin 0x1e from it.

BugLink: https://bugs.launchpad.net/bugs/1476888
Cc: <stable@vger.kernel.org>
Signed-off-by: Hui Wang <hui.wang@canonical.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 sound/pci/hda/patch_realtek.c | 26 +++++++++++++++++++-------
 1 file changed, 19 insertions(+), 7 deletions(-)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index a62872f..e5ed8df 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -5635,8 +5635,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
 	{0x15, 0x0221401f}, \
 	{0x1a, 0x411111f0}, \
 	{0x1b, 0x411111f0}, \
-	{0x1d, 0x40700001}, \
-	{0x1e, 0x411111f0}
+	{0x1d, 0x40700001}
 
 #define ALC298_STANDARD_PINS \
 	{0x18, 0x411111f0}, \
@@ -5920,35 +5919,48 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 		{0x13, 0x411111f0},
 		{0x16, 0x01014020},
 		{0x18, 0x411111f0},
-		{0x19, 0x01a19030}),
+		{0x19, 0x01a19030},
+		{0x1e, 0x411111f0}),
 	SND_HDA_PIN_QUIRK(0x10ec0292, 0x1028, "Dell", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE,
 		ALC292_STANDARD_PINS,
 		{0x12, 0x90a60140},
 		{0x13, 0x411111f0},
 		{0x16, 0x01014020},
 		{0x18, 0x02a19031},
-		{0x19, 0x01a1903e}),
+		{0x19, 0x01a1903e},
+		{0x1e, 0x411111f0}),
 	SND_HDA_PIN_QUIRK(0x10ec0292, 0x1028, "Dell", ALC269_FIXUP_DELL3_MIC_NO_PRESENCE,
 		ALC292_STANDARD_PINS,
 		{0x12, 0x90a60140},
 		{0x13, 0x411111f0},
 		{0x16, 0x411111f0},
 		{0x18, 0x411111f0},
-		{0x19, 0x411111f0}),
+		{0x19, 0x411111f0},
+		{0x1e, 0x411111f0}),
 	SND_HDA_PIN_QUIRK(0x10ec0293, 0x1028, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE,
 		ALC292_STANDARD_PINS,
 		{0x12, 0x40000000},
 		{0x13, 0x90a60140},
 		{0x16, 0x21014020},
 		{0x18, 0x411111f0},
-		{0x19, 0x21a19030}),
+		{0x19, 0x21a19030},
+		{0x1e, 0x411111f0}),
 	SND_HDA_PIN_QUIRK(0x10ec0293, 0x1028, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE,
 		ALC292_STANDARD_PINS,
 		{0x12, 0x40000000},
 		{0x13, 0x90a60140},
 		{0x16, 0x411111f0},
 		{0x18, 0x411111f0},
-		{0x19, 0x411111f0}),
+		{0x19, 0x411111f0},
+		{0x1e, 0x411111f0}),
+	SND_HDA_PIN_QUIRK(0x10ec0293, 0x1028, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE,
+		ALC292_STANDARD_PINS,
+		{0x12, 0x40000000},
+		{0x13, 0x90a60140},
+		{0x16, 0x21014020},
+		{0x18, 0x411111f0},
+		{0x19, 0x21a19030},
+		{0x1e, 0x411111ff}),
 	SND_HDA_PIN_QUIRK(0x10ec0298, 0x1028, "Dell", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE,
 		ALC298_STANDARD_PINS,
 		{0x12, 0x90a60130},
-- 
2.5.0

[added to the 4.1 stable tree] ALSA: hda / realtek - add two more Thinkpad IDs (5050,5053) for tpt460 fixup

[Sasha Levin]

From: Jaroslav Kysela <perex@perex.cz>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 0f087ee3f3b86a4507db4ff1d2d5a3880e4cfd16 ]

  See: https://bugzilla.redhat.com/show_bug.cgi?id=1349539
  See: https://bugzilla.kernel.org/show_bug.cgi?id=120961

Signed-off-by: Jaroslav Kysela <perex@perex.cz>
Cc: <stable@vger.kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 sound/pci/hda/patch_realtek.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index e5ed8df..abf8d34 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -5504,6 +5504,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x503c, "Thinkpad L450", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x504a, "ThinkPad X260", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x504b, "Thinkpad", ALC293_FIXUP_LENOVO_SPK_NOISE),
+	SND_PCI_QUIRK(0x17aa, 0x5050, "Thinkpad T560p", ALC292_FIXUP_TPT460),
+	SND_PCI_QUIRK(0x17aa, 0x5053, "Thinkpad T460", ALC292_FIXUP_TPT460),
 	SND_PCI_QUIRK(0x17aa, 0x5109, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x17aa, 0x3bf8, "Quanta FL1", ALC269_FIXUP_PCM_44K),
 	SND_PCI_QUIRK(0x17aa, 0x9e54, "LENOVO NB", ALC269_FIXUP_LENOVO_EAPD),
-- 
2.5.0

[added to the 4.1 stable tree] ALSA: dummy: Fix a use-after-free at closing

[Sasha Levin]

From: Takashi Iwai <tiwai@suse.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit d5dbbe6569481bf12dcbe3e12cff72c5f78d272c ]

syzkaller fuzzer spotted a potential use-after-free case in snd-dummy
driver when hrtimer is used as backend:
> ==================================================================
> BUG: KASAN: use-after-free in rb_erase+0x1b17/0x2010 at addr ffff88005e5b6f68
>  Read of size 8 by task syz-executor/8984
> =============================================================================
> BUG kmalloc-192 (Not tainted): kasan: bad access detected
> -----------------------------------------------------------------------------
>
> Disabling lock debugging due to kernel taint
> INFO: Allocated in 0xbbbbbbbbbbbbbbbb age=18446705582212484632
> ....
> [<      none      >] dummy_hrtimer_create+0x49/0x1a0 sound/drivers/dummy.c:464
> ....
> INFO: Freed in 0xfffd8e09 age=18446705496313138713 cpu=2164287125 pid=-1
> [<      none      >] dummy_hrtimer_free+0x68/0x80 sound/drivers/dummy.c:481
> ....
> Call Trace:
>  [<ffffffff8179e59e>] __asan_report_load8_noabort+0x3e/0x40 mm/kasan/report.c:333
>  [<     inline     >] rb_set_parent include/linux/rbtree_augmented.h:111
>  [<     inline     >] __rb_erase_augmented include/linux/rbtree_augmented.h:218
>  [<ffffffff82ca5787>] rb_erase+0x1b17/0x2010 lib/rbtree.c:427
>  [<ffffffff82cb02e8>] timerqueue_del+0x78/0x170 lib/timerqueue.c:86
>  [<ffffffff814d0c80>] __remove_hrtimer+0x90/0x220 kernel/time/hrtimer.c:903
>  [<     inline     >] remove_hrtimer kernel/time/hrtimer.c:945
>  [<ffffffff814d23da>] hrtimer_try_to_cancel+0x22a/0x570 kernel/time/hrtimer.c:1046
>  [<ffffffff814d2742>] hrtimer_cancel+0x22/0x40 kernel/time/hrtimer.c:1066
>  [<ffffffff85420531>] dummy_hrtimer_stop+0x91/0xb0 sound/drivers/dummy.c:417
>  [<ffffffff854228bf>] dummy_pcm_trigger+0x17f/0x1e0 sound/drivers/dummy.c:507
>  [<ffffffff85392170>] snd_pcm_do_stop+0x160/0x1b0 sound/core/pcm_native.c:1106
>  [<ffffffff85391b26>] snd_pcm_action_single+0x76/0x120 sound/core/pcm_native.c:956
>  [<ffffffff85391e01>] snd_pcm_action+0x231/0x290 sound/core/pcm_native.c:974
>  [<     inline     >] snd_pcm_stop sound/core/pcm_native.c:1139
>  [<ffffffff8539754d>] snd_pcm_drop+0x12d/0x1d0 sound/core/pcm_native.c:1784
>  [<ffffffff8539d3be>] snd_pcm_common_ioctl1+0xfae/0x2150 sound/core/pcm_native.c:2805
>  [<ffffffff8539ee91>] snd_pcm_capture_ioctl1+0x2a1/0x5e0 sound/core/pcm_native.c:2976
>  [<ffffffff8539f2ec>] snd_pcm_kernel_ioctl+0x11c/0x160 sound/core/pcm_native.c:3020
>  [<ffffffff853d9a44>] snd_pcm_oss_sync+0x3a4/0xa30 sound/core/oss/pcm_oss.c:1693
>  [<ffffffff853da27d>] snd_pcm_oss_release+0x1ad/0x280 sound/core/oss/pcm_oss.c:2483
>  .....

A workaround is to call hrtimer_cancel() in dummy_hrtimer_sync() which
is called certainly before other blocking ops.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Tested-by: Dmitry Vyukov <dvyukov@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 sound/drivers/dummy.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/drivers/dummy.c b/sound/drivers/dummy.c
index c5d5217..4df5dc1 100644
--- a/sound/drivers/dummy.c
+++ b/sound/drivers/dummy.c
@@ -420,6 +420,7 @@ static int dummy_hrtimer_stop(struct snd_pcm_substream *substream)
 
 static inline void dummy_hrtimer_sync(struct dummy_hrtimer_pcm *dpcm)
 {
+	hrtimer_cancel(&dpcm->timer);
 	tasklet_kill(&dpcm->tasklet);
 }
 
-- 
2.5.0

[added to the 4.1 stable tree] pNFS: Tighten up locking around DS commit buckets

[Sasha Levin]

From: Trond Myklebust <trond.myklebust@primarydata.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 27571297a7e9a2a845c232813a7ba7e1227f5ec6 ]

I'm not aware of any bugreports around this issue, but the locking
around the pnfs_commit_bucket is inconsistent at best. This patch
tightens it up by ensuring that the 'bucket->committing' list is always
changed atomically w.r.t. the 'bucket->clseg' layout segment tracking.

Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 fs/nfs/pnfs_nfs.c | 50 ++++++++++++++++++++++++++++++++------------------
 1 file changed, 32 insertions(+), 18 deletions(-)

diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index 1705c78..b28214c 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -124,11 +124,12 @@ pnfs_generic_scan_ds_commit_list(struct pnfs_commit_bucket *bucket,
 	if (ret) {
 		cinfo->ds->nwritten -= ret;
 		cinfo->ds->ncommitting += ret;
-		bucket->clseg = bucket->wlseg;
-		if (list_empty(src))
+		if (bucket->clseg == NULL)
+			bucket->clseg = pnfs_get_lseg(bucket->wlseg);
+		if (list_empty(src)) {
+			pnfs_put_lseg_locked(bucket->wlseg);
 			bucket->wlseg = NULL;
-		else
-			pnfs_get_lseg(bucket->clseg);
+		}
 	}
 	return ret;
 }
@@ -182,19 +183,23 @@ static void pnfs_generic_retry_commit(struct nfs_commit_info *cinfo, int idx)
 	struct pnfs_ds_commit_info *fl_cinfo = cinfo->ds;
 	struct pnfs_commit_bucket *bucket;
 	struct pnfs_layout_segment *freeme;
+	LIST_HEAD(pages);
 	int i;
 
+	spin_lock(cinfo->lock);
 	for (i = idx; i < fl_cinfo->nbuckets; i++) {
 		bucket = &fl_cinfo->buckets[i];
 		if (list_empty(&bucket->committing))
 			continue;
-		nfs_retry_commit(&bucket->committing, bucket->clseg, cinfo, i);
-		spin_lock(cinfo->lock);
 		freeme = bucket->clseg;
 		bucket->clseg = NULL;
+		list_splice_init(&bucket->committing, &pages);
 		spin_unlock(cinfo->lock);
+		nfs_retry_commit(&pages, freeme, cinfo, i);
 		pnfs_put_lseg(freeme);
+		spin_lock(cinfo->lock);
 	}
+	spin_unlock(cinfo->lock);
 }
 
 static unsigned int
@@ -216,10 +221,6 @@ pnfs_generic_alloc_ds_commits(struct nfs_commit_info *cinfo,
 		if (!data)
 			break;
 		data->ds_commit_index = i;
-		spin_lock(cinfo->lock);
-		data->lseg = bucket->clseg;
-		bucket->clseg = NULL;
-		spin_unlock(cinfo->lock);
 		list_add(&data->pages, list);
 		nreq++;
 	}
@@ -229,6 +230,22 @@ pnfs_generic_alloc_ds_commits(struct nfs_commit_info *cinfo,
 	return nreq;
 }
 
+static inline
+void pnfs_fetch_commit_bucket_list(struct list_head *pages,
+		struct nfs_commit_data *data,
+		struct nfs_commit_info *cinfo)
+{
+	struct pnfs_commit_bucket *bucket;
+
+	bucket = &cinfo->ds->buckets[data->ds_commit_index];
+	spin_lock(cinfo->lock);
+	list_splice_init(pages, &bucket->committing);
+	data->lseg = bucket->clseg;
+	bucket->clseg = NULL;
+	spin_unlock(cinfo->lock);
+
+}
+
 /* This follows nfs_commit_list pretty closely */
 int
 pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
@@ -243,7 +260,7 @@ pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
 	if (!list_empty(mds_pages)) {
 		data = nfs_commitdata_alloc();
 		if (data != NULL) {
-			data->lseg = NULL;
+			data->ds_commit_index = -1;
 			list_add(&data->pages, &list);
 			nreq++;
 		} else {
@@ -265,19 +282,16 @@ pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
 
 	list_for_each_entry_safe(data, tmp, &list, pages) {
 		list_del_init(&data->pages);
-		if (!data->lseg) {
+		if (data->ds_commit_index < 0) {
 			nfs_init_commit(data, mds_pages, NULL, cinfo);
 			nfs_initiate_commit(NFS_CLIENT(inode), data,
 					    NFS_PROTO(data->inode),
 					    data->mds_ops, how, 0);
 		} else {
-			struct pnfs_commit_bucket *buckets;
+			LIST_HEAD(pages);
 
-			buckets = cinfo->ds->buckets;
-			nfs_init_commit(data,
-					&buckets[data->ds_commit_index].committing,
-					data->lseg,
-					cinfo);
+			pnfs_fetch_commit_bucket_list(&pages, data, cinfo);
+			nfs_init_commit(data, &pages, data->lseg, cinfo);
 			initiate_commit(data, how);
 		}
 	}
-- 
2.5.0

[added to the 4.1 stable tree] nfs: avoid race that crashes nfs_init_commit

[Sasha Levin]

From: Weston Andros Adamson <dros@monkey.org>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit ade8febde0271513360bac44883dbebad44276c3 ]

Since the patch "NFS: Allow multiple commit requests in flight per file"
we can run multiple simultaneous commits on the same inode.  This
introduced a race over collecting pages to commit that made it possible
to call nfs_init_commit() with an empty list - which causes crashes like
the one below.

The fix is to catch this race and avoid calling nfs_init_commit and
initiate_commit when there is no work to do.

Here is the crash:

[600522.076832] BUG: unable to handle kernel NULL pointer dereference at 0000000000000040
[600522.078475] IP: [<ffffffffa0479e72>] nfs_init_commit+0x22/0x130 [nfs]
[600522.078745] PGD 4272b1067 PUD 4272cb067 PMD 0
[600522.078972] Oops: 0000 [#1] SMP
[600522.079204] Modules linked in: nfsv3 nfs_layout_flexfiles rpcsec_gss_krb5 nfsv4 dns_resolver nfs fscache dcdbas ip6t_rpfilter ip6t_REJECT nf_reject_ipv6 xt_conntrack ebtable_nat ebtable_broute bridge stp llc ebtable_filter ebtables ip6table_nat nf_conntrack_ipv6 nf_defrag_ipv6 nf_nat_ipv6 ip6table_mangle ip6table_security ip6table_raw ip6table_filter ip6_tables iptable_nat nf_conntrack_ipv4 nf_defrag_ipv4 nf_nat_ipv4 nf_nat nf_conntrack iptable_mangle iptable_security iptable_raw vmw_vsock_vmci_transport vsock bonding ipmi_devintf ipmi_msghandler coretemp crct10dif_pclmul crc32_pclmul ghash_clmulni_intel ppdev vmw_balloon parport_pc parport acpi_cpufreq vmw_vmci i2c_piix4 shpchp nfsd auth_rpcgss nfs_acl lockd grace sunrpc xfs libcrc32c vmwgfx drm_kms_helper ttm drm crc32c_intel serio_raw vmxnet3
[600522.081380]  vmw_pvscsi ata_generic pata_acpi
[600522.081809] CPU: 3 PID: 15667 Comm: /usr/bin/python Not tainted 4.1.9-100.pd.88.el7.x86_64 #1
[600522.082281] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 09/30/2014
[600522.082814] task: ffff8800bbbfa780 ti: ffff88042ae84000 task.ti: ffff88042ae84000
[600522.083378] RIP: 0010:[<ffffffffa0479e72>]  [<ffffffffa0479e72>] nfs_init_commit+0x22/0x130 [nfs]
[600522.083973] RSP: 0018:ffff88042ae87438  EFLAGS: 00010246
[600522.084571] RAX: 0000000000000000 RBX: ffff880003485e40 RCX: ffff88042ae87588
[600522.085188] RDX: 0000000000000000 RSI: ffff88042ae874b0 RDI: ffff880003485e40
[600522.085756] RBP: ffff88042ae87448 R08: ffff880003486010 R09: ffff88042ae874b0
[600522.086332] R10: 0000000000000000 R11: 0000000000000005 R12: ffff88042ae872d0
[600522.086905] R13: ffff88042ae874b0 R14: ffff880003485e40 R15: ffff88042704c840
[600522.087484] FS:  00007f4728ff2740(0000) GS:ffff88043fd80000(0000) knlGS:0000000000000000
[600522.088070] CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[600522.088663] CR2: 0000000000000040 CR3: 000000042b6aa000 CR4: 00000000001406e0
[600522.089327] Stack:
[600522.089926]  0000000000000001 ffff88042ae87588 ffff88042ae874f8 ffffffffa04f09fa
[600522.090549]  0000000000017840 0000000000017840 ffff88042ae87588 ffff8803258d9930
[600522.091169]  ffff88042ae87578 ffffffffa0563d80 0000000000000000 ffff88042704c840
[600522.091789] Call Trace:
[600522.092420]  [<ffffffffa04f09fa>] pnfs_generic_commit_pagelist+0x1da/0x320 [nfsv4]
[600522.093052]  [<ffffffffa0563d80>] ? ff_layout_commit_prepare_v3+0x30/0x30 [nfs_layout_flexfiles]
[600522.093696]  [<ffffffffa0562645>] ff_layout_commit_pagelist+0x15/0x20 [nfs_layout_flexfiles]
[600522.094359]  [<ffffffffa047bc78>] nfs_generic_commit_list+0xe8/0x120 [nfs]
[600522.095032]  [<ffffffffa047bd6a>] nfs_commit_inode+0xba/0x110 [nfs]
[600522.095719]  [<ffffffffa046ac54>] nfs_release_page+0x44/0xd0 [nfs]
[600522.096410]  [<ffffffff811a8122>] try_to_release_page+0x32/0x50
[600522.097109]  [<ffffffff811bd4f1>] shrink_page_list+0x961/0xb30
[600522.097812]  [<ffffffff811bdced>] shrink_inactive_list+0x1cd/0x550
[600522.098530]  [<ffffffff811bea65>] shrink_lruvec+0x635/0x840
[600522.099250]  [<ffffffff811bed60>] shrink_zone+0xf0/0x2f0
[600522.099974]  [<ffffffff811bf312>] do_try_to_free_pages+0x192/0x470
[600522.100709]  [<ffffffff811bf6ca>] try_to_free_pages+0xda/0x170
[600522.101464]  [<ffffffff811b2198>] __alloc_pages_nodemask+0x588/0x970
[600522.102235]  [<ffffffff811fbbd5>] alloc_pages_vma+0xb5/0x230
[600522.103000]  [<ffffffff813a1589>] ? cpumask_any_but+0x39/0x50
[600522.103774]  [<ffffffff811d6115>] wp_page_copy.isra.55+0x95/0x490
[600522.104558]  [<ffffffff810e3438>] ? __wake_up+0x48/0x60
[600522.105357]  [<ffffffff811d7d3b>] do_wp_page+0xab/0x4f0
[600522.106137]  [<ffffffff810a1bbb>] ? release_task+0x36b/0x470
[600522.106902]  [<ffffffff8126dbd7>] ? eventfd_ctx_read+0x67/0x1c0
[600522.107659]  [<ffffffff811da2a8>] handle_mm_fault+0xc78/0x1900
[600522.108431]  [<ffffffff81067ef1>] __do_page_fault+0x181/0x420
[600522.109173]  [<ffffffff811446a6>] ? __audit_syscall_exit+0x1e6/0x280
[600522.109893]  [<ffffffff810681c0>] do_page_fault+0x30/0x80
[600522.110594]  [<ffffffff81024f36>] ? syscall_trace_leave+0xc6/0x120
[600522.111288]  [<ffffffff81790a58>] page_fault+0x28/0x30
[600522.111947] Code: 5d c3 0f 1f 80 00 00 00 00 0f 1f 44 00 00 55 4c 8d 87 d0 01 00 00 48 89 e5 53 48 89 fb 48 83 ec 08 4c 8b 0e 49 8b 41 18 4c 39 ce <48> 8b 40 40 4c 8b 50 30 74 24 48 8b 87 d0 01 00 00 48 8b 7e 08
[600522.113343] RIP  [<ffffffffa0479e72>] nfs_init_commit+0x22/0x130 [nfs]
[600522.114003]  RSP <ffff88042ae87438>
[600522.114636] CR2: 0000000000000040

Fixes: af7cf057 (NFS: Allow multiple commit requests in flight per file)
CC: stable@vger.kernel.org
Signed-off-by: Weston Andros Adamson <dros@primarydata.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 fs/nfs/pnfs_nfs.c | 28 ++++++++++++++++++++++++++++
 fs/nfs/write.c    |  4 ++++
 2 files changed, 32 insertions(+)

diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index b28214c..8bd645a 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -246,6 +246,23 @@ void pnfs_fetch_commit_bucket_list(struct list_head *pages,
 
 }
 
+/* Helper function for pnfs_generic_commit_pagelist to catch an empty
+ * page list. This can happen when two commits race. */
+static bool
+pnfs_generic_commit_cancel_empty_pagelist(struct list_head *pages,
+					  struct nfs_commit_data *data,
+					  struct nfs_commit_info *cinfo)
+{
+	if (list_empty(pages)) {
+		if (atomic_dec_and_test(&cinfo->mds->rpcs_out))
+			wake_up_atomic_t(&cinfo->mds->rpcs_out);
+		nfs_commitdata_release(data);
+		return true;
+	}
+
+	return false;
+}
+
 /* This follows nfs_commit_list pretty closely */
 int
 pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
@@ -283,6 +300,11 @@ pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
 	list_for_each_entry_safe(data, tmp, &list, pages) {
 		list_del_init(&data->pages);
 		if (data->ds_commit_index < 0) {
+			/* another commit raced with us */
+			if (pnfs_generic_commit_cancel_empty_pagelist(mds_pages,
+				data, cinfo))
+				continue;
+
 			nfs_init_commit(data, mds_pages, NULL, cinfo);
 			nfs_initiate_commit(NFS_CLIENT(inode), data,
 					    NFS_PROTO(data->inode),
@@ -291,6 +313,12 @@ pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
 			LIST_HEAD(pages);
 
 			pnfs_fetch_commit_bucket_list(&pages, data, cinfo);
+
+			/* another commit raced with us */
+			if (pnfs_generic_commit_cancel_empty_pagelist(&pages,
+				data, cinfo))
+				continue;
+
 			nfs_init_commit(data, &pages, data->lseg, cinfo);
 			initiate_commit(data, how);
 		}
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index d9851a6..f98cd9a 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1653,6 +1653,10 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how,
 {
 	struct nfs_commit_data	*data;
 
+	/* another commit raced with us */
+	if (list_empty(head))
+		return 0;
+
 	data = nfs_commitdata_alloc();
 
 	if (!data)
-- 
2.5.0

[added to the 4.1 stable tree] pnfs_nfs: fix _cancel_empty_pagelist

[Sasha Levin]

From: Weston Andros Adamson <dros@monkey.org>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 5e3a98883e7ebdd1440f829a9e9dd5c3d2c5903b ]

pnfs_generic_commit_cancel_empty_pagelist calls nfs_commitdata_release,
but that is wrong: nfs_commitdata_release puts the open context, something
that isn't valid until nfs_init_commit is called, which is never the case
when pnfs_generic_commit_cancel_empty_pagelist is called.

This was introduced in "nfs: avoid race that crashes nfs_init_commit".

Signed-off-by: Weston Andros Adamson <dros@primarydata.com>
Cc: stable@vger.kernel.org
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 fs/nfs/pnfs_nfs.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index 8bd645a..19c1bcf 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -247,7 +247,11 @@ void pnfs_fetch_commit_bucket_list(struct list_head *pages,
 }
 
 /* Helper function for pnfs_generic_commit_pagelist to catch an empty
- * page list. This can happen when two commits race. */
+ * page list. This can happen when two commits race.
+ *
+ * This must be called instead of nfs_init_commit - call one or the other, but
+ * not both!
+ */
 static bool
 pnfs_generic_commit_cancel_empty_pagelist(struct list_head *pages,
 					  struct nfs_commit_data *data,
@@ -256,7 +260,11 @@ pnfs_generic_commit_cancel_empty_pagelist(struct list_head *pages,
 	if (list_empty(pages)) {
 		if (atomic_dec_and_test(&cinfo->mds->rpcs_out))
 			wake_up_atomic_t(&cinfo->mds->rpcs_out);
-		nfs_commitdata_release(data);
+		/* don't call nfs_commitdata_release - it tries to put
+		 * the open_context which is not acquired until nfs_init_commit
+		 * which has not been called on @data */
+		WARN_ON_ONCE(data->context);
+		nfs_commit_free(data);
 		return true;
 	}
 
-- 
2.5.0

[added to the 4.1 stable tree] Fix reconnect to not defer smb3 session reconnect long after socket reconnect

[Sasha Levin]

From: Steve French <smfrench@gmail.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 4fcd1813e6404dd4420c7d12fb483f9320f0bf93 ]

Azure server blocks clients that open a socket and don't do anything on it.
In our reconnect scenarios, we can reconnect the tcp session and
detect the socket is available but we defer the negprot and SMB3 session
setup and tree connect reconnection until the next i/o is requested, but
this looks suspicous to some servers who expect SMB3 negprog and session
setup soon after a socket is created.

In the echo thread, reconnect SMB3 sessions and tree connections
that are disconnected.  A later patch will replay persistent (and
resilient) handle opens.

CC: Stable <stable@vger.kernel.org>
Signed-off-by: Steve French <steve.french@primarydata.com>
Acked-by: Pavel Shilovsky <pshilovsky@samba.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 fs/cifs/connect.c |  4 +++-
 fs/cifs/smb2pdu.c | 27 +++++++++++++++++++++++++++
 2 files changed, 30 insertions(+), 1 deletion(-)

diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index de626b9..17998d1 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -414,7 +414,9 @@ cifs_echo_request(struct work_struct *work)
 	 * server->ops->need_neg() == true. Also, no need to ping if
 	 * we got a response recently.
 	 */
-	if (!server->ops->need_neg || server->ops->need_neg(server) ||
+
+	if (server->tcpStatus == CifsNeedReconnect ||
+	    server->tcpStatus == CifsExiting || server->tcpStatus == CifsNew ||
 	    (server->ops->can_echo && !server->ops->can_echo(server)) ||
 	    time_before(jiffies, server->lstrp + SMB_ECHO_INTERVAL - HZ))
 		goto requeue_echo;
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 1a6191d..8f527c8 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -1626,6 +1626,33 @@ SMB2_echo(struct TCP_Server_Info *server)
 
 	cifs_dbg(FYI, "In echo request\n");
 
+	if (server->tcpStatus == CifsNeedNegotiate) {
+		struct list_head *tmp, *tmp2;
+		struct cifs_ses *ses;
+		struct cifs_tcon *tcon;
+
+		cifs_dbg(FYI, "Need negotiate, reconnecting tcons\n");
+		spin_lock(&cifs_tcp_ses_lock);
+		list_for_each(tmp, &server->smb_ses_list) {
+			ses = list_entry(tmp, struct cifs_ses, smb_ses_list);
+			list_for_each(tmp2, &ses->tcon_list) {
+				tcon = list_entry(tmp2, struct cifs_tcon,
+						  tcon_list);
+				/* add check for persistent handle reconnect */
+				if (tcon && tcon->need_reconnect) {
+					spin_unlock(&cifs_tcp_ses_lock);
+					rc = smb2_reconnect(SMB2_ECHO, tcon);
+					spin_lock(&cifs_tcp_ses_lock);
+				}
+			}
+		}
+		spin_unlock(&cifs_tcp_ses_lock);
+	}
+
+	/* if no session, renegotiate failed above */
+	if (server->tcpStatus == CifsNeedNegotiate)
+		return -EIO;
+
 	rc = small_smb2_init(SMB2_ECHO, NULL, (void **)&req);
 	if (rc)
 		return rc;
-- 
2.5.0

[added to the 4.1 stable tree] File names with trailing period or space need special case conversion

[Sasha Levin]

From: Steve French <smfrench@gmail.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 45e8a2583d97ca758a55c608f78c4cef562644d1 ]

POSIX allows files with trailing spaces or a trailing period but
SMB3 does not, so convert these using the normal Services For Mac
mapping as we do for other reserved characters such as
	: < > | ? *
This is similar to what Macs do for the same problem over SMB3.

CC: Stable <stable@vger.kernel.org>
Signed-off-by: Steve French <steve.french@primarydata.com>
Acked-by: Pavel Shilovsky <pshilovsky@samba.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 fs/cifs/cifs_unicode.c | 33 +++++++++++++++++++++++++++++----
 fs/cifs/cifs_unicode.h |  2 ++
 2 files changed, 31 insertions(+), 4 deletions(-)

diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c
index 5a53ac6..02b071bf 100644
--- a/fs/cifs/cifs_unicode.c
+++ b/fs/cifs/cifs_unicode.c
@@ -101,6 +101,12 @@ convert_sfm_char(const __u16 src_char, char *target)
 	case SFM_SLASH:
 		*target = '\\';
 		break;
+	case SFM_SPACE:
+		*target = ' ';
+		break;
+	case SFM_PERIOD:
+		*target = '.';
+		break;
 	default:
 		return false;
 	}
@@ -404,7 +410,7 @@ static __le16 convert_to_sfu_char(char src_char)
 	return dest_char;
 }
 
-static __le16 convert_to_sfm_char(char src_char)
+static __le16 convert_to_sfm_char(char src_char, bool end_of_string)
 {
 	__le16 dest_char;
 
@@ -427,6 +433,18 @@ static __le16 convert_to_sfm_char(char src_char)
 	case '|':
 		dest_char = cpu_to_le16(SFM_PIPE);
 		break;
+	case '.':
+		if (end_of_string)
+			dest_char = cpu_to_le16(SFM_PERIOD);
+		else
+			dest_char = 0;
+		break;
+	case ' ':
+		if (end_of_string)
+			dest_char = cpu_to_le16(SFM_SPACE);
+		else
+			dest_char = 0;
+		break;
 	default:
 		dest_char = 0;
 	}
@@ -469,9 +487,16 @@ cifsConvertToUTF16(__le16 *target, const char *source, int srclen,
 		/* see if we must remap this char */
 		if (map_chars == SFU_MAP_UNI_RSVD)
 			dst_char = convert_to_sfu_char(src_char);
-		else if (map_chars == SFM_MAP_UNI_RSVD)
-			dst_char = convert_to_sfm_char(src_char);
-		else
+		else if (map_chars == SFM_MAP_UNI_RSVD) {
+			bool end_of_string;
+
+			if (i == srclen - 1)
+				end_of_string = true;
+			else
+				end_of_string = false;
+
+			dst_char = convert_to_sfm_char(src_char, end_of_string);
+		} else
 			dst_char = 0;
 		/*
 		 * FIXME: We can not handle remapping backslash (UNI_SLASH)
diff --git a/fs/cifs/cifs_unicode.h b/fs/cifs/cifs_unicode.h
index bdc52cb..479bc0a 100644
--- a/fs/cifs/cifs_unicode.h
+++ b/fs/cifs/cifs_unicode.h
@@ -64,6 +64,8 @@
 #define SFM_LESSTHAN    ((__u16) 0xF023)
 #define SFM_PIPE        ((__u16) 0xF027)
 #define SFM_SLASH       ((__u16) 0xF026)
+#define SFM_PERIOD	((__u16) 0xF028)
+#define SFM_SPACE	((__u16) 0xF029)
 
 /*
  * Mapping mechanism to use when one of the seven reserved characters is
-- 
2.5.0

[added to the 4.1 stable tree] USB: EHCI: declare hostpc register as zero-length array

[Sasha Levin]

From: Alan Stern <stern@rowland.harvard.edu>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 7e8b3dfef16375dbfeb1f36a83eb9f27117c51fd ]

The HOSTPC extension registers found in some EHCI implementations form
a variable-length array, with one element for each port.  Therefore
the hostpc field in struct ehci_regs should be declared as a
zero-length array, not a single-element array.

This fixes a problem reported by UBSAN.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Reported-by: Wilfried Klaebe <linux-kernel@lebenslange-mailadresse.de>
Tested-by: Wilfried Klaebe <linux-kernel@lebenslange-mailadresse.de>
CC: <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 include/linux/usb/ehci_def.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/usb/ehci_def.h b/include/linux/usb/ehci_def.h
index 966889a..e479033 100644
--- a/include/linux/usb/ehci_def.h
+++ b/include/linux/usb/ehci_def.h
@@ -180,11 +180,11 @@ struct ehci_regs {
  * PORTSCx
  */
 	/* HOSTPC: offset 0x84 */
-	u32		hostpc[1];	/* HOSTPC extension */
+	u32		hostpc[0];	/* HOSTPC extension */
 #define HOSTPC_PHCD	(1<<22)		/* Phy clock disable */
 #define HOSTPC_PSPD	(3<<25)		/* Port speed detection */
 
-	u32		reserved5[16];
+	u32		reserved5[17];
 
 	/* USBMODE_EX: offset 0xc8 */
 	u32		usbmode_ex;	/* USB Device mode extension */
-- 
2.5.0

[added to the 4.1 stable tree] tmpfs: don't undo fallocate past its last page

[Sasha Levin]

From: Anthony Romano <anthony.romano@coreos.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit b9b4bb26af017dbe930cd4df7f9b2fc3a0497bfe ]

When fallocate is interrupted it will undo a range that extends one byte
past its range of allocated pages.  This can corrupt an in-use page by
zeroing out its first byte.  Instead, undo using the inclusive byte
range.

Fixes: 1635f6a74152f1d ("tmpfs: undo fallocation on failure")
Link: http://lkml.kernel.org/r/1462713387-16724-1-git-send-email-anthony.romano@coreos.com
Signed-off-by: Anthony Romano <anthony.romano@coreos.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Brandon Philips <brandon@ifup.co>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 mm/shmem.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/shmem.c b/mm/shmem.c
index 47d536e..86c150bf 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2139,7 +2139,7 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 			/* Remove the !PageUptodate pages we added */
 			shmem_undo_range(inode,
 				(loff_t)start << PAGE_CACHE_SHIFT,
-				(loff_t)index << PAGE_CACHE_SHIFT, true);
+				((loff_t)index << PAGE_CACHE_SHIFT) - 1, true);
 			goto undone;
 		}
 
-- 
2.5.0

Re: [added to the 4.1 stable tree] tmpfs: don't undo fallocate past its last page

[Vlastimil Babka]

On 07/12/2016 04:52 AM, Sasha Levin wrote:
> From: Anthony Romano <anthony.romano@coreos.com>
>
> This patch has been added to the 4.1 stable tree. If you have any
> objections, please let us know.

Hugh says the patch is broken, shouldn't go to stable without the fix:
http://marc.info/?l=linux-mm&m=146819440406829&w=2

> ===============
>
> [ Upstream commit b9b4bb26af017dbe930cd4df7f9b2fc3a0497bfe ]
>
> When fallocate is interrupted it will undo a range that extends one byte
> past its range of allocated pages.  This can corrupt an in-use page by
> zeroing out its first byte.  Instead, undo using the inclusive byte
> range.
>
> Fixes: 1635f6a74152f1d ("tmpfs: undo fallocation on failure")
> Link: http://lkml.kernel.org/r/1462713387-16724-1-git-send-email-anthony.romano@coreos.com
> Signed-off-by: Anthony Romano <anthony.romano@coreos.com>
> Cc: Vlastimil Babka <vbabka@suse.cz>
> Cc: Hugh Dickins <hughd@google.com>
> Cc: Brandon Philips <brandon@ifup.co>
> Cc: <stable@vger.kernel.org>
> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
> Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
> ---
>  mm/shmem.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/mm/shmem.c b/mm/shmem.c
> index 47d536e..86c150bf 100644
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -2139,7 +2139,7 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
>  			/* Remove the !PageUptodate pages we added */
>  			shmem_undo_range(inode,
>  				(loff_t)start << PAGE_CACHE_SHIFT,
> -				(loff_t)index << PAGE_CACHE_SHIFT, true);
> +				((loff_t)index << PAGE_CACHE_SHIFT) - 1, true);
>  			goto undone;
>  		}
>
>

Re: [added to the 4.1 stable tree] tmpfs: don't undo fallocate past its last page

[Hugh Dickins]

On Tue, 12 Jul 2016, Vlastimil Babka wrote:
> On 07/12/2016 04:52 AM, Sasha Levin wrote:
> > From: Anthony Romano <anthony.romano@coreos.com>
> > 
> > This patch has been added to the 4.1 stable tree. If you have any
> > objections, please let us know.
> 
> Hugh says the patch is broken, shouldn't go to stable without the fix:
> http://marc.info/?l=linux-mm&m=146819440406829&w=2

Thanks, Vlastimil: yes, this patch here should not go in without
upstream commit 7f556567036cb7f89aabe2f0954b08566b4efb53
("tmpfs: fix regression hang in fallocate undo")
on top.  And of course the same applies to 3.18.

Hugh

> 
> > ===============
> > 
> > [ Upstream commit b9b4bb26af017dbe930cd4df7f9b2fc3a0497bfe ]
> > 
> > When fallocate is interrupted it will undo a range that extends one byte
> > past its range of allocated pages.  This can corrupt an in-use page by
> > zeroing out its first byte.  Instead, undo using the inclusive byte
> > range.
> > 
> > Fixes: 1635f6a74152f1d ("tmpfs: undo fallocation on failure")
> > Link:
> > http://lkml.kernel.org/r/1462713387-16724-1-git-send-email-anthony.romano@coreos.com
> > Signed-off-by: Anthony Romano <anthony.romano@coreos.com>
> > Cc: Vlastimil Babka <vbabka@suse.cz>
> > Cc: Hugh Dickins <hughd@google.com>
> > Cc: Brandon Philips <brandon@ifup.co>
> > Cc: <stable@vger.kernel.org>
> > Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
> > Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
> > Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
> > ---
> >  mm/shmem.c | 2 +-
> >  1 file changed, 1 insertion(+), 1 deletion(-)
> > 
> > diff --git a/mm/shmem.c b/mm/shmem.c
> > index 47d536e..86c150bf 100644
> > --- a/mm/shmem.c
> > +++ b/mm/shmem.c
> > @@ -2139,7 +2139,7 @@ static long shmem_fallocate(struct file *file, int
> > mode, loff_t offset,
> >  			/* Remove the !PageUptodate pages we added */
> >  			shmem_undo_range(inode,
> >  				(loff_t)start << PAGE_CACHE_SHIFT,
> > -				(loff_t)index << PAGE_CACHE_SHIFT, true);
> > +				((loff_t)index << PAGE_CACHE_SHIFT) - 1,
> > true);
> >  			goto undone;
> >  		}
> > 

Re: [added to the 4.1 stable tree] tmpfs: don't undo fallocate past its last page

[Sasha Levin]

On 07/12/2016 07:58 AM, Hugh Dickins wrote:
> On Tue, 12 Jul 2016, Vlastimil Babka wrote:
>> > On 07/12/2016 04:52 AM, Sasha Levin wrote:
>>> > > From: Anthony Romano <anthony.romano@coreos.com>
>>> > > 
>>> > > This patch has been added to the 4.1 stable tree. If you have any
>>> > > objections, please let us know.
>> > 
>> > Hugh says the patch is broken, shouldn't go to stable without the fix:
>> > http://marc.info/?l=linux-mm&m=146819440406829&w=2
> Thanks, Vlastimil: yes, this patch here should not go in without
> upstream commit 7f556567036cb7f89aabe2f0954b08566b4efb53
> ("tmpfs: fix regression hang in fallocate undo")
> on top.  And of course the same applies to 3.18.

Added to both 4.1 and 3.18, thanks!

[added to the 4.1 stable tree] mm/swap.c: flush lru pvecs on compound page arrival

[Sasha Levin]

From: Lukasz Odzioba <lukasz.odzioba@intel.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 8f182270dfec432e93fae14f9208a6b9af01009f ]

Currently we can have compound pages held on per cpu pagevecs, which
leads to a lot of memory unavailable for reclaim when needed.  In the
systems with hundreads of processors it can be GBs of memory.

On of the way of reproducing the problem is to not call munmap
explicitly on all mapped regions (i.e.  after receiving SIGTERM).  After
that some pages (with THP enabled also huge pages) may end up on
lru_add_pvec, example below.

  void main() {
  #pragma omp parallel
  {
	size_t size = 55 * 1000 * 1000; // smaller than  MEM/CPUS
	void *p = mmap(NULL, size, PROT_READ | PROT_WRITE,
		MAP_PRIVATE | MAP_ANONYMOUS , -1, 0);
	if (p != MAP_FAILED)
		memset(p, 0, size);
	//munmap(p, size); // uncomment to make the problem go away
  }
  }

When we run it with THP enabled it will leave significant amount of
memory on lru_add_pvec.  This memory will be not reclaimed if we hit
OOM, so when we run above program in a loop:

	for i in `seq 100`; do ./a.out; done

many processes (95% in my case) will be killed by OOM.

The primary point of the LRU add cache is to save the zone lru_lock
contention with a hope that more pages will belong to the same zone and
so their addition can be batched.  The huge page is already a form of
batched addition (it will add 512 worth of memory in one go) so skipping
the batching seems like a safer option when compared to a potential
excess in the caching which can be quite large and much harder to fix
because lru_add_drain_all is way to expensive and it is not really clear
what would be a good moment to call it.

Similarly we can reproduce the problem on lru_deactivate_pvec by adding:
madvise(p, size, MADV_FREE); after memset.

This patch flushes lru pvecs on compound page arrival making the problem
less severe - after applying it kill rate of above example drops to 0%,
due to reducing maximum amount of memory held on pvec from 28MB (with
THP) to 56kB per CPU.

Suggested-by: Michal Hocko <mhocko@suse.com>
Link: http://lkml.kernel.org/r/1466180198-18854-1-git-send-email-lukasz.odzioba@intel.com
Signed-off-by: Lukasz Odzioba <lukasz.odzioba@intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Kirill Shutemov <kirill.shutemov@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Cc: Ming Li <mingli199x@qq.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 mm/swap.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/mm/swap.c b/mm/swap.c
index a7251a8..b523f0a 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -483,7 +483,7 @@ void rotate_reclaimable_page(struct page *page)
 		page_cache_get(page);
 		local_irq_save(flags);
 		pvec = this_cpu_ptr(&lru_rotate_pvecs);
-		if (!pagevec_add(pvec, page))
+		if (!pagevec_add(pvec, page) || PageCompound(page))
 			pagevec_move_tail(pvec);
 		local_irq_restore(flags);
 	}
@@ -539,7 +539,7 @@ void activate_page(struct page *page)
 		struct pagevec *pvec = &get_cpu_var(activate_page_pvecs);
 
 		page_cache_get(page);
-		if (!pagevec_add(pvec, page))
+		if (!pagevec_add(pvec, page) || PageCompound(page))
 			pagevec_lru_move_fn(pvec, __activate_page, NULL);
 		put_cpu_var(activate_page_pvecs);
 	}
@@ -631,9 +631,8 @@ static void __lru_cache_add(struct page *page)
 	struct pagevec *pvec = &get_cpu_var(lru_add_pvec);
 
 	page_cache_get(page);
-	if (!pagevec_space(pvec))
+	if (!pagevec_space(pvec) || PageCompound(page))
 		__pagevec_lru_add(pvec);
-	pagevec_add(pvec, page);
 	put_cpu_var(lru_add_pvec);
 }
 
@@ -846,7 +845,7 @@ void deactivate_file_page(struct page *page)
 	if (likely(get_page_unless_zero(page))) {
 		struct pagevec *pvec = &get_cpu_var(lru_deactivate_file_pvecs);
 
-		if (!pagevec_add(pvec, page))
+		if (!pagevec_add(pvec, page) || PageCompound(page))
 			pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL);
 		put_cpu_var(lru_deactivate_file_pvecs);
 	}
-- 
2.5.0

[added to the 4.1 stable tree] mm, compaction: skip compound pages by order in free scanner

[Sasha Levin]

From: Vlastimil Babka <vbabka@suse.cz>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 9fcd6d2e052eef525e94a9ae58dbe7ed4df4f5a7 ]

The compaction free scanner is looking for PageBuddy() pages and
skipping all others.  For large compound pages such as THP or hugetlbfs,
we can save a lot of iterations if we skip them at once using their
compound_order().  This is generally unsafe and we can read a bogus
value of order due to a race, but if we are careful, the only danger is
skipping too much.

When tested with stress-highalloc from mmtests on 4GB system with 1GB
hugetlbfs pages, the vmstat compact_free_scanned count decreased by at
least 15%.

Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Mel Gorman <mgorman@suse.de>
Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Michal Nazarewicz <mina86@mina86.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 mm/compaction.c | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/mm/compaction.c b/mm/compaction.c
index 3dcf93c..ac3ebfd 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -431,6 +431,24 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 
 		if (!valid_page)
 			valid_page = page;
+
+		/*
+		 * For compound pages such as THP and hugetlbfs, we can save
+		 * potentially a lot of iterations if we skip them at once.
+		 * The check is racy, but we can consider only valid values
+		 * and the only danger is skipping too much.
+		 */
+		if (PageCompound(page)) {
+			unsigned int comp_order = compound_order(page);
+
+			if (likely(comp_order < MAX_ORDER)) {
+				blockpfn += (1UL << comp_order) - 1;
+				cursor += (1UL << comp_order) - 1;
+			}
+
+			goto isolate_fail;
+		}
+
 		if (!PageBuddy(page))
 			goto isolate_fail;
 
@@ -490,6 +508,13 @@ isolate_fail:
 
 	}
 
+	/*
+	 * There is a tiny chance that we have read bogus compound_order(),
+	 * so be careful to not go outside of the pageblock.
+	 */
+	if (unlikely(blockpfn > end_pfn))
+		blockpfn = end_pfn;
+
 	trace_mm_compaction_isolate_freepages(*start_pfn, blockpfn,
 					nr_scanned, total_isolated);
 
-- 
2.5.0

[added to the 4.1 stable tree] mm, compaction: abort free scanner if split fails

[Sasha Levin]

From: David Rientjes <rientjes@google.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit a4f04f2c6955aff5e2c08dcb40aca247ff4d7370 ]

If the memory compaction free scanner cannot successfully split a free
page (only possible due to per-zone low watermark), terminate the free
scanner rather than continuing to scan memory needlessly.  If the
watermark is insufficient for a free page of order <= cc->order, then
terminate the scanner since all future splits will also likely fail.

This prevents the compaction freeing scanner from scanning all memory on
very large zones (very noticeable for zones > 128GB, for instance) when
all splits will likely fail while holding zone->lock.

compaction_alloc() iterating a 128GB zone has been benchmarked to take
over 400ms on some systems whereas any free page isolated and ready to
be split ends up failing in split_free_page() because of the low
watermark check and thus the iteration continues.

The next time compaction occurs, the freeing scanner will likely start
at the end of the zone again since no success was made previously and we
get the same lengthy iteration until the zone is brought above the low
watermark.  All thp page faults can take >400ms in such a state without
this fix.

Link: http://lkml.kernel.org/r/alpine.DEB.2.10.1606211820350.97086@chino.kir.corp.google.com
Signed-off-by: David Rientjes <rientjes@google.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 mm/compaction.c | 39 +++++++++++++++++++++------------------
 1 file changed, 21 insertions(+), 18 deletions(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index ac3ebfd..32c719a 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -480,25 +480,23 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 
 		/* Found a free page, break it into order-0 pages */
 		isolated = split_free_page(page);
+		if (!isolated)
+			break;
+
 		total_isolated += isolated;
+		cc->nr_freepages += isolated;
 		for (i = 0; i < isolated; i++) {
 			list_add(&page->lru, freelist);
 			page++;
 		}
-
-		/* If a page was split, advance to the end of it */
-		if (isolated) {
-			cc->nr_freepages += isolated;
-			if (!strict &&
-				cc->nr_migratepages <= cc->nr_freepages) {
-				blockpfn += isolated;
-				break;
-			}
-
-			blockpfn += isolated - 1;
-			cursor += isolated - 1;
-			continue;
+		if (!strict && cc->nr_migratepages <= cc->nr_freepages) {
+			blockpfn += isolated;
+			break;
 		}
+		/* Advance to the end of split page */
+		blockpfn += isolated - 1;
+		cursor += isolated - 1;
+		continue;
 
 isolate_fail:
 		if (strict)
@@ -508,6 +506,9 @@ isolate_fail:
 
 	}
 
+	if (locked)
+		spin_unlock_irqrestore(&cc->zone->lock, flags);
+
 	/*
 	 * There is a tiny chance that we have read bogus compound_order(),
 	 * so be careful to not go outside of the pageblock.
@@ -529,9 +530,6 @@ isolate_fail:
 	if (strict && blockpfn < end_pfn)
 		total_isolated = 0;
 
-	if (locked)
-		spin_unlock_irqrestore(&cc->zone->lock, flags);
-
 	/* Update the pageblock-skip if the whole pageblock was scanned */
 	if (blockpfn == end_pfn)
 		update_pageblock_skip(cc, valid_page, total_isolated, false);
@@ -955,6 +953,7 @@ static void isolate_freepages(struct compact_control *cc)
 				block_end_pfn = block_start_pfn,
 				block_start_pfn -= pageblock_nr_pages,
 				isolate_start_pfn = block_start_pfn) {
+		unsigned long isolated;
 
 		/*
 		 * This can iterate a massively long zone without finding any
@@ -979,8 +978,12 @@ static void isolate_freepages(struct compact_control *cc)
 			continue;
 
 		/* Found a block suitable for isolating free pages from. */
-		isolate_freepages_block(cc, &isolate_start_pfn,
-					block_end_pfn, freelist, false);
+		isolated = isolate_freepages_block(cc, &isolate_start_pfn,
+						block_end_pfn, freelist, false);
+		/* If isolation failed early, do not continue needlessly */
+		if (!isolated && isolate_start_pfn < block_end_pfn &&
+		    cc->nr_migratepages > cc->nr_freepages)
+			break;
 
 		/*
 		 * Remember where the free scanner should restart next time,
-- 
2.5.0

[added to the 4.1 stable tree] fs/nilfs2: fix potential underflow in call to crc32_le

[Sasha Levin]

From: Torsten Hilbrich <torsten.hilbrich@secunet.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 63d2f95d63396059200c391ca87161897b99e74a ]

The value `bytes' comes from the filesystem which is about to be
mounted.  We cannot trust that the value is always in the range we
expect it to be.

Check its value before using it to calculate the length for the crc32_le
call.  It value must be larger (or equal) sumoff + 4.

This fixes a kernel bug when accidentially mounting an image file which
had the nilfs2 magic value 0x3434 at the right offset 0x406 by chance.
The bytes 0x01 0x00 were stored at 0x408 and were interpreted as a
s_bytes value of 1.  This caused an underflow when substracting sumoff +
4 (20) in the call to crc32_le.

  BUG: unable to handle kernel paging request at ffff88021e600000
  IP:  crc32_le+0x36/0x100
  ...
  Call Trace:
    nilfs_valid_sb.part.5+0x52/0x60 [nilfs2]
    nilfs_load_super_block+0x142/0x300 [nilfs2]
    init_nilfs+0x60/0x390 [nilfs2]
    nilfs_mount+0x302/0x520 [nilfs2]
    mount_fs+0x38/0x160
    vfs_kern_mount+0x67/0x110
    do_mount+0x269/0xe00
    SyS_mount+0x9f/0x100
    entry_SYSCALL_64_fastpath+0x16/0x71

Link: http://lkml.kernel.org/r/1466778587-5184-2-git-send-email-konishi.ryusuke@lab.ntt.co.jp
Signed-off-by: Torsten Hilbrich <torsten.hilbrich@secunet.com>
Tested-by: Torsten Hilbrich <torsten.hilbrich@secunet.com>
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 fs/nilfs2/the_nilfs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index 69bd801..37e49cb 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -443,7 +443,7 @@ static int nilfs_valid_sb(struct nilfs_super_block *sbp)
 	if (!sbp || le16_to_cpu(sbp->s_magic) != NILFS_SUPER_MAGIC)
 		return 0;
 	bytes = le16_to_cpu(sbp->s_bytes);
-	if (bytes > BLOCK_SIZE)
+	if (bytes < sumoff + 4 || bytes > BLOCK_SIZE)
 		return 0;
 	crc = crc32_le(le32_to_cpu(sbp->s_crc_seed), (unsigned char *)sbp,
 		       sumoff);
-- 
2.5.0

[added to the 4.1 stable tree] powerpc/tm: Always reclaim in start_thread() for exec() class syscalls

[Sasha Levin]

From: Cyril Bur <cyrilbur@gmail.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 8e96a87c5431c256feb65bcfc5aec92d9f7839b6 ]

Userspace can quite legitimately perform an exec() syscall with a
suspended transaction. exec() does not return to the old process, rather
it load a new one and starts that, the expectation therefore is that the
new process starts not in a transaction. Currently exec() is not treated
any differently to any other syscall which creates problems.

Firstly it could allow a new process to start with a suspended
transaction for a binary that no longer exists. This means that the
checkpointed state won't be valid and if the suspended transaction were
ever to be resumed and subsequently aborted (a possibility which is
exceedingly likely as exec()ing will likely doom the transaction) the
new process will jump to invalid state.

Secondly the incorrect attempt to keep the transactional state while
still zeroing state for the new process creates at least two TM Bad
Things. The first triggers on the rfid to return to userspace as
start_thread() has given the new process a 'clean' MSR but the suspend
will still be set in the hardware MSR. The second TM Bad Thing triggers
in __switch_to() as the processor is still transactionally suspended but
__switch_to() wants to zero the TM sprs for the new process.

This is an example of the outcome of calling exec() with a suspended
transaction. Note the first 700 is likely the first TM bad thing
decsribed earlier only the kernel can't report it as we've loaded
userspace registers. c000000000009980 is the rfid in
fast_exception_return()

  Bad kernel stack pointer 3fffcfa1a370 at c000000000009980
  Oops: Bad kernel stack pointer, sig: 6 [#1]
  CPU: 0 PID: 2006 Comm: tm-execed Not tainted
  NIP: c000000000009980 LR: 0000000000000000 CTR: 0000000000000000
  REGS: c00000003ffefd40 TRAP: 0700   Not tainted
  MSR: 8000000300201031 <SF,ME,IR,DR,LE,TM[SE]>  CR: 00000000  XER: 00000000
  CFAR: c0000000000098b4 SOFTE: 0
  PACATMSCRATCH: b00000010000d033
  GPR00: 0000000000000000 00003fffcfa1a370 0000000000000000 0000000000000000
  GPR04: 0000000000000000 0000000000000000 0000000000000000 0000000000000000
  GPR08: 0000000000000000 0000000000000000 0000000000000000 0000000000000000
  GPR12: 00003fff966611c0 0000000000000000 0000000000000000 0000000000000000
  NIP [c000000000009980] fast_exception_return+0xb0/0xb8
  LR [0000000000000000]           (null)
  Call Trace:
  Instruction dump:
  f84d0278 e9a100d8 7c7b03a6 e84101a0 7c4ff120 e8410170 7c5a03a6 e8010070
  e8410080 e8610088 e8810090 e8210078 <4c000024> 48000000 e8610178 88ed023b

  Kernel BUG at c000000000043e80 [verbose debug info unavailable]
  Unexpected TM Bad Thing exception at c000000000043e80 (msr 0x201033)
  Oops: Unrecoverable exception, sig: 6 [#2]
  CPU: 0 PID: 2006 Comm: tm-execed Tainted: G      D
  task: c0000000fbea6d80 ti: c00000003ffec000 task.ti: c0000000fb7ec000
  NIP: c000000000043e80 LR: c000000000015a24 CTR: 0000000000000000
  REGS: c00000003ffef7e0 TRAP: 0700   Tainted: G      D
  MSR: 8000000300201033 <SF,ME,IR,DR,RI,LE,TM[SE]>  CR: 28002828  XER: 00000000
  CFAR: c000000000015a20 SOFTE: 0
  PACATMSCRATCH: b00000010000d033
  GPR00: 0000000000000000 c00000003ffefa60 c000000000db5500 c0000000fbead000
  GPR04: 8000000300001033 2222222222222222 2222222222222222 00000000ff160000
  GPR08: 0000000000000000 800000010000d033 c0000000fb7e3ea0 c00000000fe00004
  GPR12: 0000000000002200 c00000000fe00000 0000000000000000 0000000000000000
  GPR16: 0000000000000000 0000000000000000 0000000000000000 0000000000000000
  GPR20: 0000000000000000 0000000000000000 c0000000fbea7410 00000000ff160000
  GPR24: c0000000ffe1f600 c0000000fbea8700 c0000000fbea8700 c0000000fbead000
  GPR28: c000000000e20198 c0000000fbea6d80 c0000000fbeab680 c0000000fbea6d80
  NIP [c000000000043e80] tm_restore_sprs+0xc/0x1c
  LR [c000000000015a24] __switch_to+0x1f4/0x420
  Call Trace:
  Instruction dump:
  7c800164 4e800020 7c0022a6 f80304a8 7c0222a6 f80304b0 7c0122a6 f80304b8
  4e800020 e80304a8 7c0023a6 e80304b0 <7c0223a6> e80304b8 7c0123a6 4e800020

This fixes CVE-2016-5828.

Fixes: bc2a9408fa65 ("powerpc: Hook in new transactional memory code")
Cc: stable@vger.kernel.org # v3.9+
Signed-off-by: Cyril Bur <cyrilbur@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 arch/powerpc/kernel/process.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index c8c8275..dd02390 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1240,6 +1240,16 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 		current->thread.regs = regs - 1;
 	}
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	/*
+	 * Clear any transactional state, we're exec()ing. The cause is
+	 * not important as there will never be a recheckpoint so it's not
+	 * user visible.
+	 */
+	if (MSR_TM_SUSPENDED(mfmsr()))
+		tm_reclaim_current(0);
+#endif
+
 	memset(regs->gpr, 0, sizeof(regs->gpr));
 	regs->ctr = 0;
 	regs->link = 0;
-- 
2.5.0

[added to the 4.1 stable tree] KVM: arm/arm64: Stop leaking vcpu pid references

[Sasha Levin]

From: James Morse <james.morse@arm.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 591d215afcc2f94e8e2c69a63c924c044677eb31 ]

kvm provides kvm_vcpu_uninit(), which amongst other things, releases the
last reference to the struct pid of the task that was last running the vcpu.

On arm64 built with CONFIG_DEBUG_KMEMLEAK, starting a guest with kvmtool,
then killing it with SIGKILL results (after some considerable time) in:
> cat /sys/kernel/debug/kmemleak
> unreferenced object 0xffff80007d5ea080 (size 128):
>  comm "lkvm", pid 2025, jiffies 4294942645 (age 1107.776s)
>  hex dump (first 32 bytes):
>    01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
>    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
>  backtrace:
>    [<ffff8000001b30ec>] create_object+0xfc/0x278
>    [<ffff80000071da34>] kmemleak_alloc+0x34/0x70
>    [<ffff80000019fa2c>] kmem_cache_alloc+0x16c/0x1d8
>    [<ffff8000000d0474>] alloc_pid+0x34/0x4d0
>    [<ffff8000000b5674>] copy_process.isra.6+0x79c/0x1338
>    [<ffff8000000b633c>] _do_fork+0x74/0x320
>    [<ffff8000000b66b0>] SyS_clone+0x18/0x20
>    [<ffff800000085cb0>] el0_svc_naked+0x24/0x28
>    [<ffffffffffffffff>] 0xffffffffffffffff

On x86 kvm_vcpu_uninit() is called on the path from kvm_arch_destroy_vm(),
on arm no equivalent call is made. Add the call to kvm_arch_vcpu_free().

Signed-off-by: James Morse <james.morse@arm.com>
Fixes: 749cf76c5a36 ("KVM: ARM: Initial skeleton to compile KVM support")
Cc: <stable@vger.kernel.org> # 3.10+
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 arch/arm/kvm/arm.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index d6223cb..5414081 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -257,6 +257,7 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 	kvm_mmu_free_memory_caches(vcpu);
 	kvm_timer_vcpu_terminate(vcpu);
 	kvm_vgic_vcpu_destroy(vcpu);
+	kvm_vcpu_uninit(vcpu);
 	kmem_cache_free(kvm_vcpu_cache, vcpu);
 }
 
-- 
2.5.0

[added to the 4.1 stable tree] make nfs_atomic_open() call d_drop() on all ->open_context() errors.

[Sasha Levin]

From: Al Viro <viro@ZenIV.linux.org.uk>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit d20cb71dbf3487f24549ede1a8e2d67579b4632e ]

In "NFSv4: Move dentry instantiation into the NFSv4-specific atomic open code"
unconditional d_drop() after the ->open_context() had been removed.  It had
been correct for success cases (there ->open_context() itself had been doing
dcache manipulations), but not for error ones.  Only one of those (ENOENT)
got a compensatory d_drop() added in that commit, but in fact it should've
been done for all errors.  As it is, the case of O_CREAT non-exclusive open
on a hashed negative dentry racing with e.g. symlink creation from another
client ended up with ->open_context() getting an error and proceeding to
call nfs_lookup().  On a hashed dentry, which would've instantly triggered
BUG_ON() in d_materialise_unique() (or, these days, its equivalent in
d_splice_alias()).

Cc: stable@vger.kernel.org # v3.10+
Tested-by: Oleg Drokin <green@linuxhacker.ru>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 fs/nfs/dir.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index b2c8b31..aadb4af 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1542,9 +1542,9 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
 		err = PTR_ERR(inode);
 		trace_nfs_atomic_open_exit(dir, ctx, open_flags, err);
 		put_nfs_open_context(ctx);
+		d_drop(dentry);
 		switch (err) {
 		case -ENOENT:
-			d_drop(dentry);
 			d_add(dentry, NULL);
 			nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
 			break;
-- 
2.5.0

[added to the 4.1 stable tree] USB: don't free bandwidth_mutex too early

[Sasha Levin]

From: Alan Stern <stern@rowland.harvard.edu>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit ab2a4bf83902c170d29ba130a8abb5f9d90559e1 ]

The USB core contains a bug that can show up when a USB-3 host
controller is removed.  If the primary (USB-2) hcd structure is
released before the shared (USB-3) hcd, the core will try to do a
double-free of the common bandwidth_mutex.

The problem was described in graphical form by Chung-Geol Kim, who
first reported it:

=================================================
     At *remove USB(3.0) Storage
     sequence <1> --> <5> ((Problem Case))
=================================================
                                  VOLD
------------------------------------|------------
                                 (uevent)
                            ________|_________
                           |<1>               |
                           |dwc3_otg_sm_work  |
                           |usb_put_hcd       |
                           |peer_hcd(kref=2)|
                           |__________________|
                            ________|_________
                           |<2>               |
                           |New USB BUS #2    |
                           |                  |
                           |peer_hcd(kref=1)  |
                           |                  |
                         --(Link)-bandXX_mutex|
                         | |__________________|
                         |
    ___________________  |
   |<3>                | |
   |dwc3_otg_sm_work   | |
   |usb_put_hcd        | |
   |primary_hcd(kref=1)| |
   |___________________| |
    _________|_________  |
   |<4>                | |
   |New USB BUS #1     | |
   |hcd_release        | |
   |primary_hcd(kref=0)| |
   |                   | |
   |bandXX_mutex(free) |<-
   |___________________|
                               (( VOLD ))
                            ______|___________
                           |<5>               |
                           |      SCSI        |
                           |usb_put_hcd       |
                           |peer_hcd(kref=0)  |
                           |*hcd_release      |
                           |bandXX_mutex(free*)|<- double free
                           |__________________|

=================================================

This happens because hcd_release() frees the bandwidth_mutex whenever
it sees a primary hcd being released (which is not a very good idea
in any case), but in the course of releasing the primary hcd, it
changes the pointers in the shared hcd in such a way that the shared
hcd will appear to be primary when it gets released.

This patch fixes the problem by changing hcd_release() so that it
deallocates the bandwidth_mutex only when the _last_ hcd structure
referencing it is released.  The patch also removes an unnecessary
test, so that when an hcd is released, both the shared_hcd and
primary_hcd pointers in the hcd's peer will be cleared.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Reported-by: Chung-Geol Kim <chunggeol.kim@samsung.com>
Tested-by: Chung-Geol Kim <chunggeol.kim@samsung.com>
CC: <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/usb/core/hcd.c | 17 +++++++----------
 1 file changed, 7 insertions(+), 10 deletions(-)

diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index e47cfcd..3a49ba2 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -2522,26 +2522,23 @@ EXPORT_SYMBOL_GPL(usb_create_hcd);
  * Don't deallocate the bandwidth_mutex until the last shared usb_hcd is
  * deallocated.
  *
- * Make sure to only deallocate the bandwidth_mutex when the primary HCD is
- * freed.  When hcd_release() is called for either hcd in a peer set
- * invalidate the peer's ->shared_hcd and ->primary_hcd pointers to
- * block new peering attempts
+ * Make sure to deallocate the bandwidth_mutex only when the last HCD is
+ * freed.  When hcd_release() is called for either hcd in a peer set,
+ * invalidate the peer's ->shared_hcd and ->primary_hcd pointers.
  */
 static void hcd_release(struct kref *kref)
 {
 	struct usb_hcd *hcd = container_of (kref, struct usb_hcd, kref);
 
 	mutex_lock(&usb_port_peer_mutex);
-	if (usb_hcd_is_primary_hcd(hcd)) {
-		kfree(hcd->address0_mutex);
-		kfree(hcd->bandwidth_mutex);
-	}
 	if (hcd->shared_hcd) {
 		struct usb_hcd *peer = hcd->shared_hcd;
 
 		peer->shared_hcd = NULL;
-		if (peer->primary_hcd == hcd)
-			peer->primary_hcd = NULL;
+		peer->primary_hcd = NULL;
+	} else {
+		kfree(hcd->address0_mutex);
+		kfree(hcd->bandwidth_mutex);
 	}
 	mutex_unlock(&usb_port_peer_mutex);
 	kfree(hcd);
-- 
2.5.0

[added to the 4.1 stable tree] ARC: unwind: ensure that .debug_frame is generated (vs. .eh_frame)

[Sasha Levin]

From: Vineet Gupta <vgupta@synopsys.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit f52e126cc7476196f44f3c313b7d9f0699a881fc ]

With recent binutils update to support dwarf CFI pseudo-ops in gas, we
now get .eh_frame vs. .debug_frame. Although the call frame info is
exactly the same in both, the CIE differs, which the current kernel
unwinder can't cope with.

This broke both the kernel unwinder as well as loadable modules (latter
because of a new unhandled relo R_ARC_32_PCREL from .rela.eh_frame in
the module loader)

The ideal solution would be to switch unwinder to .eh_frame.
For now however we can make do by just ensureing .debug_frame is
generated by removing -fasynchronous-unwind-tables

 .eh_frame    generated with -gdwarf-2 -fasynchronous-unwind-tables
 .debug_frame generated with -gdwarf-2

Fixes STAR 9001058196

Cc: stable@vger.kernel.org
Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 arch/arc/Makefile | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index 2f21e1e..305dbdf 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -34,7 +34,6 @@ cflags-$(atleast_gcc44)			+= -fsection-anchors
 cflags-$(CONFIG_ARC_HAS_LLSC)		+= -mlock
 cflags-$(CONFIG_ARC_HAS_SWAPE)		+= -mswape
 cflags-$(CONFIG_ARC_HAS_RTSC)		+= -mrtsc
-cflags-$(CONFIG_ARC_DW2_UNWIND)		+= -fasynchronous-unwind-tables
 
 # By default gcc 4.8 generates dwarf4 which kernel unwinder can't grok
 ifeq ($(atleast_gcc48),y)
-- 
2.5.0

[added to the 4.1 stable tree] arc: unwind: warn only once if DW2_UNWIND is disabled

[Sasha Levin]

From: Alexey Brodkin <Alexey.Brodkin@synopsys.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 9bd54517ee86cb164c734f72ea95aeba4804f10b ]

If CONFIG_ARC_DW2_UNWIND is disabled every time arc_unwind_core()
gets called following message gets printed in debug console:
----------------->8---------------
CONFIG_ARC_DW2_UNWIND needs to be enabled
----------------->8---------------

That message makes sense if user indeed wants to see a backtrace or
get nice function call-graphs in perf but what if user disabled
unwinder for the purpose? Why pollute his debug console?

So instead we'll warn user about possibly missing feature once and
let him decide if that was what he or she really wanted.

Signed-off-by: Alexey Brodkin <abrodkin@synopsys.com>
Cc: stable@vger.kernel.org
Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 arch/arc/kernel/stacktrace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c
index 92320d6..5086cc7 100644
--- a/arch/arc/kernel/stacktrace.c
+++ b/arch/arc/kernel/stacktrace.c
@@ -144,7 +144,7 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs,
 	 * prelogue is setup (callee regs saved and then fp set and not other
 	 * way around
 	 */
-	pr_warn("CONFIG_ARC_DW2_UNWIND needs to be enabled\n");
+	pr_warn_once("CONFIG_ARC_DW2_UNWIND needs to be enabled\n");
 	return 0;
 
 #endif
-- 
2.5.0

[added to the 4.1 stable tree] Revert "s390/kdump: Clear subchannel ID to signal non-CCW/SCSI IPL"

[Sasha Levin]

From: Michael Holzheu <holzheu@linux.vnet.ibm.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 5419447e2142d6ed68c9f5c1a28630b3a290a845 ]

This reverts commit 852ffd0f4e23248b47531058e531066a988434b5.

There are use cases where an intermediate boot kernel (1) uses kexec
to boot the final production kernel (2). For this scenario we should
provide the original boot information to the production kernel (2).
Therefore clearing the boot information during kexec() should not
be done.

Cc: stable@vger.kernel.org # v3.17+
Reported-by: Steffen Maier <maier@linux.vnet.ibm.com>
Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 arch/s390/kernel/ipl.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index 52fbef9..7963c6a 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -2044,13 +2044,6 @@ void s390_reset_system(void (*fn_pre)(void),
 	S390_lowcore.program_new_psw.addr =
 		PSW_ADDR_AMODE | (unsigned long) s390_base_pgm_handler;
 
-	/*
-	 * Clear subchannel ID and number to signal new kernel that no CCW or
-	 * SCSI IPL has been done (for kexec and kdump)
-	 */
-	S390_lowcore.subchannel_id = 0;
-	S390_lowcore.subchannel_nr = 0;
-
 	/* Store status at absolute zero */
 	store_status();
 
-- 
2.5.0

[added to the 4.1 stable tree] NFS: Fix another OPEN_DOWNGRADE bug

[Sasha Levin]

From: Trond Myklebust <trond.myklebust@primarydata.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit e547f2628327fec6afd2e03b46f113f614cca05b ]

Olga Kornievskaia reports that the following test fails to trigger
an OPEN_DOWNGRADE on the wire, and only triggers the final CLOSE.

	fd0 = open(foo, RDRW)   -- should be open on the wire for "both"
	fd1 = open(foo, RDONLY)  -- should be open on the wire for "read"
	close(fd0) -- should trigger an open_downgrade
	read(fd1)
	close(fd1)

The issue is that we're missing a check for whether or not the current
state transitioned from an O_RDWR state as opposed to having transitioned
from a combination of O_RDONLY and O_WRONLY.

Reported-by: Olga Kornievskaia <aglo@umich.edu>
Fixes: cd9288ffaea4 ("NFSv4: Fix another bug in the close/open_downgrade code")
Cc: stable@vger.kernel.org # 2.6.33+
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 fs/nfs/nfs4proc.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 8470620..eef16ec 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2715,12 +2715,11 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
 			call_close |= is_wronly;
 		else if (is_wronly)
 			calldata->arg.fmode |= FMODE_WRITE;
+		if (calldata->arg.fmode != (FMODE_READ|FMODE_WRITE))
+			call_close |= is_rdwr;
 	} else if (is_rdwr)
 		calldata->arg.fmode |= FMODE_READ|FMODE_WRITE;
 
-	if (calldata->arg.fmode == 0)
-		call_close |= is_rdwr;
-
 	if (!nfs4_valid_open_stateid(state))
 		call_close = 0;
 	spin_unlock(&state->owner->so_lock);
-- 
2.5.0

[added to the 4.1 stable tree] namespace: update event counter when umounting a deleted dentry

[Sasha Levin]

From: Andrey Ulanov <andreyu@google.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit e06b933e6ded42384164d28a2060b7f89243b895 ]

- m_start() in fs/namespace.c expects that ns->event is incremented each
  time a mount added or removed from ns->list.
- umount_tree() removes items from the list but does not increment event
  counter, expecting that it's done before the function is called.
- There are some codepaths that call umount_tree() without updating
  "event" counter. e.g. from __detach_mounts().
- When this happens m_start may reuse a cached mount structure that no
  longer belongs to ns->list (i.e. use after free which usually leads
  to infinite loop).

This change fixes the above problem by incrementing global event counter
before invoking umount_tree().

Change-Id: I622c8e84dcb9fb63542372c5dbf0178ee86bb589
Cc: stable@vger.kernel.org
Signed-off-by: Andrey Ulanov <andreyu@google.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 fs/namespace.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/namespace.c b/fs/namespace.c
index 6257268..556721f 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1551,6 +1551,7 @@ void __detach_mounts(struct dentry *dentry)
 		goto out_unlock;
 
 	lock_mount_hash();
+	event++;
 	while (!hlist_empty(&mp->m_list)) {
 		mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list);
 		if (mnt->mnt.mnt_flags & MNT_UMOUNT) {
-- 
2.5.0

[added to the 4.1 stable tree] locks: use file_inode()

[Sasha Levin]

From: Miklos Szeredi <mszeredi@redhat.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 6343a2120862f7023006c8091ad95c1f16a32077 ]

(Another one for the f_path debacle.)

ltp fcntl33 testcase caused an Oops in selinux_file_send_sigiotask.

The reason is that generic_add_lease() used filp->f_path.dentry->inode
while all the others use file_inode().  This makes a difference for files
opened on overlayfs since the former will point to the overlay inode the
latter to the underlying inode.

So generic_add_lease() added the lease to the overlay inode and
generic_delete_lease() removed it from the underlying inode.  When the file
was released the lease remained on the overlay inode's lock list, resulting
in use after free.

Reported-by: Eryu Guan <eguan@redhat.com>
Fixes: 4bacc9c9234c ("overlayfs: Make f_path always point to the overlay and f_inode to the underlay")
Cc: <stable@vger.kernel.org>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Reviewed-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 fs/locks.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/locks.c b/fs/locks.c
index 8501eec..3c234b9fb 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1596,7 +1596,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 {
 	struct file_lock *fl, *my_fl = NULL, *lease;
 	struct dentry *dentry = filp->f_path.dentry;
-	struct inode *inode = dentry->d_inode;
+	struct inode *inode = file_inode(filp);
 	struct file_lock_context *ctx;
 	bool is_deleg = (*flp)->fl_flags & FL_DELEG;
 	int error;
-- 
2.5.0

[added to the 4.1 stable tree] PCI: Allow a NULL "parent" pointer in pci_bus_assign_domain_nr()

[Sasha Levin]

From: Krzysztof Hałasa <khalasa@piap.pl>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 54c6e2dd00c313d0add58e5befe62fe6f286d03b ]

pci_create_root_bus() passes a "parent" pointer to
pci_bus_assign_domain_nr().  When CONFIG_PCI_DOMAINS_GENERIC is defined,
pci_bus_assign_domain_nr() dereferences that pointer.  Many callers of
pci_create_root_bus() supply a NULL "parent" pointer, which leads to a NULL
pointer dereference error.

7c674700098c ("PCI: Move domain assignment from arm64 to generic code")
moved the "parent" dereference from arm64 to generic code.  Only arm64 used
that code (because only arm64 defined CONFIG_PCI_DOMAINS_GENERIC), and it
always supplied a valid "parent" pointer.  Other arches supplied NULL
"parent" pointers but didn't defined CONFIG_PCI_DOMAINS_GENERIC, so they
used a no-op version of pci_bus_assign_domain_nr().

8c7d14746abc ("ARM/PCI: Move to generic PCI domains") defined
CONFIG_PCI_DOMAINS_GENERIC on ARM, and many ARM platforms use
pci_common_init(), which supplies a NULL "parent" pointer.
These platforms (cns3xxx, dove, footbridge, iop13xx, etc.) crash
with a NULL pointer dereference like this while probing PCI:

  Unable to handle kernel NULL pointer dereference at virtual address 000000a4
  PC is at pci_bus_assign_domain_nr+0x10/0x84
  LR is at pci_create_root_bus+0x48/0x2e4
  Kernel panic - not syncing: Attempted to kill init!

[bhelgaas: changelog, add "Reported:" and "Fixes:" tags]
Reported: http://forum.doozan.com/read.php?2,17868,22070,quote=1
Fixes: 8c7d14746abc ("ARM/PCI: Move to generic PCI domains")
Fixes: 7c674700098c ("PCI: Move domain assignment from arm64 to generic code")
Signed-off-by: Krzysztof Hałasa <khalasa@piap.pl>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
CC: stable@vger.kernel.org	# v4.0+

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/pci/pci.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index c44393f..4e720ed 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -4520,8 +4520,10 @@ int pci_get_new_domain_nr(void)
 void pci_bus_assign_domain_nr(struct pci_bus *bus, struct device *parent)
 {
 	static int use_dt_domains = -1;
-	int domain = of_get_pci_domain_nr(parent->of_node);
+	int domain = -1;
 
+	if (parent)
+		domain = of_get_pci_domain_nr(parent->of_node);
 	/*
 	 * Check DT domain and use_dt_domains values.
 	 *
-- 
2.5.0

[added to the 4.1 stable tree] ASoC: samsung: pass DMA channels as pointers

[Sasha Levin]

From: Arnd Bergmann <arnd@arndb.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit b9a1a743818ea3265abf98f9431623afa8c50c86 ]

ARM64 allmodconfig produces a bunch of warnings when building the
samsung ASoC code:

sound/soc/samsung/dmaengine.c: In function 'samsung_asoc_init_dma_data':
sound/soc/samsung/dmaengine.c:53:32: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast]
   playback_data->filter_data = (void *)playback->channel;
sound/soc/samsung/dmaengine.c:60:31: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast]
   capture_data->filter_data = (void *)capture->channel;

We could easily shut up the warning by adding an intermediate cast,
but there is a bigger underlying problem: The use of IORESOURCE_DMA
to pass data from platform code to device drivers is dubious to start
with, as what we really want is a pointer that can be passed into
a filter function.

Note that on s3c64xx, the pl08x DMA data is already a pointer, but
gets cast to resource_size_t so we can pass it as a resource, and it
then gets converted back to a pointer. In contrast, the data we pass
for s3c24xx is an index into a device specific table, and we artificially
convert that into a pointer for the filter function.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 arch/arm/mach-s3c64xx/dev-audio.c        | 41 ++++++++++++++-----------
 arch/arm/mach-s3c64xx/include/mach/dma.h | 52 ++++++++++++++++----------------
 arch/arm/plat-samsung/devs.c             | 11 +++++--
 include/linux/platform_data/asoc-s3c.h   |  4 +++
 sound/soc/samsung/ac97.c                 | 26 +++-------------
 sound/soc/samsung/dma.h                  |  2 +-
 sound/soc/samsung/dmaengine.c            |  4 +--
 sound/soc/samsung/i2s.c                  | 26 +++-------------
 sound/soc/samsung/pcm.c                  | 20 +++---------
 sound/soc/samsung/s3c2412-i2s.c          |  4 +--
 sound/soc/samsung/s3c24xx-i2s.c          |  4 +--
 sound/soc/samsung/spdif.c                | 10 ++----
 12 files changed, 84 insertions(+), 120 deletions(-)

diff --git a/arch/arm/mach-s3c64xx/dev-audio.c b/arch/arm/mach-s3c64xx/dev-audio.c
index ff780a8..9a42736 100644
--- a/arch/arm/mach-s3c64xx/dev-audio.c
+++ b/arch/arm/mach-s3c64xx/dev-audio.c
@@ -54,12 +54,12 @@ static int s3c64xx_i2s_cfg_gpio(struct platform_device *pdev)
 
 static struct resource s3c64xx_iis0_resource[] = {
 	[0] = DEFINE_RES_MEM(S3C64XX_PA_IIS0, SZ_256),
-	[1] = DEFINE_RES_DMA(DMACH_I2S0_OUT),
-	[2] = DEFINE_RES_DMA(DMACH_I2S0_IN),
 };
 
-static struct s3c_audio_pdata i2sv3_pdata = {
+static struct s3c_audio_pdata i2s0_pdata = {
 	.cfg_gpio = s3c64xx_i2s_cfg_gpio,
+	.dma_playback = DMACH_I2S0_OUT,
+	.dma_capture = DMACH_I2S0_IN,
 };
 
 struct platform_device s3c64xx_device_iis0 = {
@@ -68,15 +68,19 @@ struct platform_device s3c64xx_device_iis0 = {
 	.num_resources	  = ARRAY_SIZE(s3c64xx_iis0_resource),
 	.resource	  = s3c64xx_iis0_resource,
 	.dev = {
-		.platform_data = &i2sv3_pdata,
+		.platform_data = &i2s0_pdata,
 	},
 };
 EXPORT_SYMBOL(s3c64xx_device_iis0);
 
 static struct resource s3c64xx_iis1_resource[] = {
 	[0] = DEFINE_RES_MEM(S3C64XX_PA_IIS1, SZ_256),
-	[1] = DEFINE_RES_DMA(DMACH_I2S1_OUT),
-	[2] = DEFINE_RES_DMA(DMACH_I2S1_IN),
+};
+
+static struct s3c_audio_pdata i2s1_pdata = {
+	.cfg_gpio = s3c64xx_i2s_cfg_gpio,
+	.dma_playback = DMACH_I2S1_OUT,
+	.dma_capture = DMACH_I2S1_IN,
 };
 
 struct platform_device s3c64xx_device_iis1 = {
@@ -85,19 +89,19 @@ struct platform_device s3c64xx_device_iis1 = {
 	.num_resources	  = ARRAY_SIZE(s3c64xx_iis1_resource),
 	.resource	  = s3c64xx_iis1_resource,
 	.dev = {
-		.platform_data = &i2sv3_pdata,
+		.platform_data = &i2s1_pdata,
 	},
 };
 EXPORT_SYMBOL(s3c64xx_device_iis1);
 
 static struct resource s3c64xx_iisv4_resource[] = {
 	[0] = DEFINE_RES_MEM(S3C64XX_PA_IISV4, SZ_256),
-	[1] = DEFINE_RES_DMA(DMACH_HSI_I2SV40_TX),
-	[2] = DEFINE_RES_DMA(DMACH_HSI_I2SV40_RX),
 };
 
 static struct s3c_audio_pdata i2sv4_pdata = {
 	.cfg_gpio = s3c64xx_i2s_cfg_gpio,
+	.dma_playback = DMACH_HSI_I2SV40_TX,
+	.dma_capture = DMACH_HSI_I2SV40_RX,
 	.type = {
 		.i2s = {
 			.quirks = QUIRK_PRI_6CHAN,
@@ -142,12 +146,12 @@ static int s3c64xx_pcm_cfg_gpio(struct platform_device *pdev)
 
 static struct resource s3c64xx_pcm0_resource[] = {
 	[0] = DEFINE_RES_MEM(S3C64XX_PA_PCM0, SZ_256),
-	[1] = DEFINE_RES_DMA(DMACH_PCM0_TX),
-	[2] = DEFINE_RES_DMA(DMACH_PCM0_RX),
 };
 
 static struct s3c_audio_pdata s3c_pcm0_pdata = {
 	.cfg_gpio = s3c64xx_pcm_cfg_gpio,
+	.dma_capture = DMACH_PCM0_RX,
+	.dma_playback = DMACH_PCM0_TX,
 };
 
 struct platform_device s3c64xx_device_pcm0 = {
@@ -163,12 +167,12 @@ EXPORT_SYMBOL(s3c64xx_device_pcm0);
 
 static struct resource s3c64xx_pcm1_resource[] = {
 	[0] = DEFINE_RES_MEM(S3C64XX_PA_PCM1, SZ_256),
-	[1] = DEFINE_RES_DMA(DMACH_PCM1_TX),
-	[2] = DEFINE_RES_DMA(DMACH_PCM1_RX),
 };
 
 static struct s3c_audio_pdata s3c_pcm1_pdata = {
 	.cfg_gpio = s3c64xx_pcm_cfg_gpio,
+	.dma_playback = DMACH_PCM1_TX,
+	.dma_capture = DMACH_PCM1_RX,
 };
 
 struct platform_device s3c64xx_device_pcm1 = {
@@ -196,13 +200,14 @@ static int s3c64xx_ac97_cfg_gpe(struct platform_device *pdev)
 
 static struct resource s3c64xx_ac97_resource[] = {
 	[0] = DEFINE_RES_MEM(S3C64XX_PA_AC97, SZ_256),
-	[1] = DEFINE_RES_DMA(DMACH_AC97_PCMOUT),
-	[2] = DEFINE_RES_DMA(DMACH_AC97_PCMIN),
-	[3] = DEFINE_RES_DMA(DMACH_AC97_MICIN),
-	[4] = DEFINE_RES_IRQ(IRQ_AC97),
+	[1] = DEFINE_RES_IRQ(IRQ_AC97),
 };
 
-static struct s3c_audio_pdata s3c_ac97_pdata;
+static struct s3c_audio_pdata s3c_ac97_pdata = {
+	.dma_playback = DMACH_AC97_PCMOUT,
+	.dma_capture = DMACH_AC97_PCMIN,
+	.dma_capture_mic = DMACH_AC97_MICIN,
+};
 
 static u64 s3c64xx_ac97_dmamask = DMA_BIT_MASK(32);
 
diff --git a/arch/arm/mach-s3c64xx/include/mach/dma.h b/arch/arm/mach-s3c64xx/include/mach/dma.h
index 096e140..9c739ea 100644
--- a/arch/arm/mach-s3c64xx/include/mach/dma.h
+++ b/arch/arm/mach-s3c64xx/include/mach/dma.h
@@ -14,38 +14,38 @@
 #define S3C64XX_DMA_CHAN(name)		((unsigned long)(name))
 
 /* DMA0/SDMA0 */
-#define DMACH_UART0		S3C64XX_DMA_CHAN("uart0_tx")
-#define DMACH_UART0_SRC2	S3C64XX_DMA_CHAN("uart0_rx")
-#define DMACH_UART1		S3C64XX_DMA_CHAN("uart1_tx")
-#define DMACH_UART1_SRC2	S3C64XX_DMA_CHAN("uart1_rx")
-#define DMACH_UART2		S3C64XX_DMA_CHAN("uart2_tx")
-#define DMACH_UART2_SRC2	S3C64XX_DMA_CHAN("uart2_rx")
-#define DMACH_UART3		S3C64XX_DMA_CHAN("uart3_tx")
-#define DMACH_UART3_SRC2	S3C64XX_DMA_CHAN("uart3_rx")
-#define DMACH_PCM0_TX		S3C64XX_DMA_CHAN("pcm0_tx")
-#define DMACH_PCM0_RX		S3C64XX_DMA_CHAN("pcm0_rx")
-#define DMACH_I2S0_OUT		S3C64XX_DMA_CHAN("i2s0_tx")
-#define DMACH_I2S0_IN		S3C64XX_DMA_CHAN("i2s0_rx")
+#define DMACH_UART0		"uart0_tx"
+#define DMACH_UART0_SRC2	"uart0_rx"
+#define DMACH_UART1		"uart1_tx"
+#define DMACH_UART1_SRC2	"uart1_rx"
+#define DMACH_UART2		"uart2_tx"
+#define DMACH_UART2_SRC2	"uart2_rx"
+#define DMACH_UART3		"uart3_tx"
+#define DMACH_UART3_SRC2	"uart3_rx"
+#define DMACH_PCM0_TX		"pcm0_tx"
+#define DMACH_PCM0_RX		"pcm0_rx"
+#define DMACH_I2S0_OUT		"i2s0_tx"
+#define DMACH_I2S0_IN		"i2s0_rx"
 #define DMACH_SPI0_TX		S3C64XX_DMA_CHAN("spi0_tx")
 #define DMACH_SPI0_RX		S3C64XX_DMA_CHAN("spi0_rx")
-#define DMACH_HSI_I2SV40_TX	S3C64XX_DMA_CHAN("i2s2_tx")
-#define DMACH_HSI_I2SV40_RX	S3C64XX_DMA_CHAN("i2s2_rx")
+#define DMACH_HSI_I2SV40_TX	"i2s2_tx"
+#define DMACH_HSI_I2SV40_RX	"i2s2_rx"
 
 /* DMA1/SDMA1 */
-#define DMACH_PCM1_TX		S3C64XX_DMA_CHAN("pcm1_tx")
-#define DMACH_PCM1_RX		S3C64XX_DMA_CHAN("pcm1_rx")
-#define DMACH_I2S1_OUT		S3C64XX_DMA_CHAN("i2s1_tx")
-#define DMACH_I2S1_IN		S3C64XX_DMA_CHAN("i2s1_rx")
+#define DMACH_PCM1_TX		"pcm1_tx"
+#define DMACH_PCM1_RX		"pcm1_rx"
+#define DMACH_I2S1_OUT		"i2s1_tx"
+#define DMACH_I2S1_IN		"i2s1_rx"
 #define DMACH_SPI1_TX		S3C64XX_DMA_CHAN("spi1_tx")
 #define DMACH_SPI1_RX		S3C64XX_DMA_CHAN("spi1_rx")
-#define DMACH_AC97_PCMOUT	S3C64XX_DMA_CHAN("ac97_out")
-#define DMACH_AC97_PCMIN	S3C64XX_DMA_CHAN("ac97_in")
-#define DMACH_AC97_MICIN	S3C64XX_DMA_CHAN("ac97_mic")
-#define DMACH_PWM		S3C64XX_DMA_CHAN("pwm")
-#define DMACH_IRDA		S3C64XX_DMA_CHAN("irda")
-#define DMACH_EXTERNAL		S3C64XX_DMA_CHAN("external")
-#define DMACH_SECURITY_RX	S3C64XX_DMA_CHAN("sec_rx")
-#define DMACH_SECURITY_TX	S3C64XX_DMA_CHAN("sec_tx")
+#define DMACH_AC97_PCMOUT	"ac97_out"
+#define DMACH_AC97_PCMIN	"ac97_in"
+#define DMACH_AC97_MICIN	"ac97_mic"
+#define DMACH_PWM		"pwm"
+#define DMACH_IRDA		"irda"
+#define DMACH_EXTERNAL		"external"
+#define DMACH_SECURITY_RX	"sec_rx"
+#define DMACH_SECURITY_TX	"sec_tx"
 
 enum dma_ch {
 	DMACH_MAX = 32
diff --git a/arch/arm/plat-samsung/devs.c b/arch/arm/plat-samsung/devs.c
index 83c7d15..8b67db8c 100644
--- a/arch/arm/plat-samsung/devs.c
+++ b/arch/arm/plat-samsung/devs.c
@@ -65,6 +65,7 @@
 #include <linux/platform_data/usb-ohci-s3c2410.h>
 #include <plat/usb-phy.h>
 #include <plat/regs-spi.h>
+#include <linux/platform_data/asoc-s3c.h>
 #include <linux/platform_data/spi-s3c64xx.h>
 
 static u64 samsung_device_dma_mask = DMA_BIT_MASK(32);
@@ -74,9 +75,12 @@ static u64 samsung_device_dma_mask = DMA_BIT_MASK(32);
 static struct resource s3c_ac97_resource[] = {
 	[0] = DEFINE_RES_MEM(S3C2440_PA_AC97, S3C2440_SZ_AC97),
 	[1] = DEFINE_RES_IRQ(IRQ_S3C244X_AC97),
-	[2] = DEFINE_RES_DMA_NAMED(DMACH_PCM_OUT, "PCM out"),
-	[3] = DEFINE_RES_DMA_NAMED(DMACH_PCM_IN, "PCM in"),
-	[4] = DEFINE_RES_DMA_NAMED(DMACH_MIC_IN, "Mic in"),
+};
+
+static struct s3c_audio_pdata s3c_ac97_pdata = {
+	.dma_playback = (void *)DMACH_PCM_OUT,
+	.dma_capture = (void *)DMACH_PCM_IN,
+	.dma_capture_mic = (void *)DMACH_MIC_IN,
 };
 
 struct platform_device s3c_device_ac97 = {
@@ -87,6 +91,7 @@ struct platform_device s3c_device_ac97 = {
 	.dev		= {
 		.dma_mask		= &samsung_device_dma_mask,
 		.coherent_dma_mask	= DMA_BIT_MASK(32),
+		.platform_data		= &s3c_ac97_pdata,
 	}
 };
 #endif /* CONFIG_CPU_S3C2440 */
diff --git a/include/linux/platform_data/asoc-s3c.h b/include/linux/platform_data/asoc-s3c.h
index 5e0bc77..33f88b4 100644
--- a/include/linux/platform_data/asoc-s3c.h
+++ b/include/linux/platform_data/asoc-s3c.h
@@ -39,6 +39,10 @@ struct samsung_i2s {
  */
 struct s3c_audio_pdata {
 	int (*cfg_gpio)(struct platform_device *);
+	void *dma_playback;
+	void *dma_capture;
+	void *dma_play_sec;
+	void *dma_capture_mic;
 	union {
 		struct samsung_i2s i2s;
 	} type;
diff --git a/sound/soc/samsung/ac97.c b/sound/soc/samsung/ac97.c
index e414550..9c52193 100644
--- a/sound/soc/samsung/ac97.c
+++ b/sound/soc/samsung/ac97.c
@@ -324,7 +324,7 @@ static const struct snd_soc_component_driver s3c_ac97_component = {
 
 static int s3c_ac97_probe(struct platform_device *pdev)
 {
-	struct resource *mem_res, *dmatx_res, *dmarx_res, *dmamic_res, *irq_res;
+	struct resource *mem_res, *irq_res;
 	struct s3c_audio_pdata *ac97_pdata;
 	int ret;
 
@@ -335,24 +335,6 @@ static int s3c_ac97_probe(struct platform_device *pdev)
 	}
 
 	/* Check for availability of necessary resource */
-	dmatx_res = platform_get_resource(pdev, IORESOURCE_DMA, 0);
-	if (!dmatx_res) {
-		dev_err(&pdev->dev, "Unable to get AC97-TX dma resource\n");
-		return -ENXIO;
-	}
-
-	dmarx_res = platform_get_resource(pdev, IORESOURCE_DMA, 1);
-	if (!dmarx_res) {
-		dev_err(&pdev->dev, "Unable to get AC97-RX dma resource\n");
-		return -ENXIO;
-	}
-
-	dmamic_res = platform_get_resource(pdev, IORESOURCE_DMA, 2);
-	if (!dmamic_res) {
-		dev_err(&pdev->dev, "Unable to get AC97-MIC dma resource\n");
-		return -ENXIO;
-	}
-
 	irq_res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
 	if (!irq_res) {
 		dev_err(&pdev->dev, "AC97 IRQ not provided!\n");
@@ -364,11 +346,11 @@ static int s3c_ac97_probe(struct platform_device *pdev)
 	if (IS_ERR(s3c_ac97.regs))
 		return PTR_ERR(s3c_ac97.regs);
 
-	s3c_ac97_pcm_out.channel = dmatx_res->start;
+	s3c_ac97_pcm_out.slave = ac97_pdata->dma_playback;
 	s3c_ac97_pcm_out.dma_addr = mem_res->start + S3C_AC97_PCM_DATA;
-	s3c_ac97_pcm_in.channel = dmarx_res->start;
+	s3c_ac97_pcm_in.slave = ac97_pdata->dma_capture;
 	s3c_ac97_pcm_in.dma_addr = mem_res->start + S3C_AC97_PCM_DATA;
-	s3c_ac97_mic_in.channel = dmamic_res->start;
+	s3c_ac97_mic_in.slave = ac97_pdata->dma_capture_mic;
 	s3c_ac97_mic_in.dma_addr = mem_res->start + S3C_AC97_MIC_DATA;
 
 	init_completion(&s3c_ac97.done);
diff --git a/sound/soc/samsung/dma.h b/sound/soc/samsung/dma.h
index 0e85dcf..085ef30 100644
--- a/sound/soc/samsung/dma.h
+++ b/sound/soc/samsung/dma.h
@@ -15,7 +15,7 @@
 #include <sound/dmaengine_pcm.h>
 
 struct s3c_dma_params {
-	int channel;				/* Channel ID */
+	void *slave;				/* Channel ID */
 	dma_addr_t dma_addr;
 	int dma_size;			/* Size of the DMA transfer */
 	char *ch_name;
diff --git a/sound/soc/samsung/dmaengine.c b/sound/soc/samsung/dmaengine.c
index 506f5bf..727008d 100644
--- a/sound/soc/samsung/dmaengine.c
+++ b/sound/soc/samsung/dmaengine.c
@@ -50,14 +50,14 @@ void samsung_asoc_init_dma_data(struct snd_soc_dai *dai,
 
 	if (playback) {
 		playback_data = &playback->dma_data;
-		playback_data->filter_data = (void *)playback->channel;
+		playback_data->filter_data = playback->slave;
 		playback_data->chan_name = playback->ch_name;
 		playback_data->addr = playback->dma_addr;
 		playback_data->addr_width = playback->dma_size;
 	}
 	if (capture) {
 		capture_data = &capture->dma_data;
-		capture_data->filter_data = (void *)capture->channel;
+		capture_data->filter_data = capture->slave;
 		capture_data->chan_name = capture->ch_name;
 		capture_data->addr = capture->dma_addr;
 		capture_data->addr_width = capture->dma_size;
diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c
index 5e8ccb0..9456c78 100644
--- a/sound/soc/samsung/i2s.c
+++ b/sound/soc/samsung/i2s.c
@@ -1260,27 +1260,14 @@ static int samsung_i2s_probe(struct platform_device *pdev)
 	pri_dai->lock = &pri_dai->spinlock;
 
 	if (!np) {
-		res = platform_get_resource(pdev, IORESOURCE_DMA, 0);
-		if (!res) {
-			dev_err(&pdev->dev,
-				"Unable to get I2S-TX dma resource\n");
-			return -ENXIO;
-		}
-		pri_dai->dma_playback.channel = res->start;
-
-		res = platform_get_resource(pdev, IORESOURCE_DMA, 1);
-		if (!res) {
-			dev_err(&pdev->dev,
-				"Unable to get I2S-RX dma resource\n");
-			return -ENXIO;
-		}
-		pri_dai->dma_capture.channel = res->start;
-
 		if (i2s_pdata == NULL) {
 			dev_err(&pdev->dev, "Can't work without s3c_audio_pdata\n");
 			return -EINVAL;
 		}
 
+		pri_dai->dma_playback.slave = i2s_pdata->dma_playback;
+		pri_dai->dma_capture.slave = i2s_pdata->dma_capture;
+
 		if (&i2s_pdata->type)
 			i2s_cfg = &i2s_pdata->type.i2s;
 
@@ -1341,11 +1328,8 @@ static int samsung_i2s_probe(struct platform_device *pdev)
 		sec_dai->dma_playback.dma_addr = regs_base + I2STXDS;
 		sec_dai->dma_playback.ch_name = "tx-sec";
 
-		if (!np) {
-			res = platform_get_resource(pdev, IORESOURCE_DMA, 2);
-			if (res)
-				sec_dai->dma_playback.channel = res->start;
-		}
+		if (!np)
+			sec_dai->dma_playback.slave = i2s_pdata->dma_play_sec;
 
 		sec_dai->dma_playback.dma_size = 4;
 		sec_dai->addr = pri_dai->addr;
diff --git a/sound/soc/samsung/pcm.c b/sound/soc/samsung/pcm.c
index b320a9d..c77f324 100644
--- a/sound/soc/samsung/pcm.c
+++ b/sound/soc/samsung/pcm.c
@@ -486,7 +486,7 @@ static const struct snd_soc_component_driver s3c_pcm_component = {
 static int s3c_pcm_dev_probe(struct platform_device *pdev)
 {
 	struct s3c_pcm_info *pcm;
-	struct resource *mem_res, *dmatx_res, *dmarx_res;
+	struct resource *mem_res;
 	struct s3c_audio_pdata *pcm_pdata;
 	int ret;
 
@@ -499,18 +499,6 @@ static int s3c_pcm_dev_probe(struct platform_device *pdev)
 	pcm_pdata = pdev->dev.platform_data;
 
 	/* Check for availability of necessary resource */
-	dmatx_res = platform_get_resource(pdev, IORESOURCE_DMA, 0);
-	if (!dmatx_res) {
-		dev_err(&pdev->dev, "Unable to get PCM-TX dma resource\n");
-		return -ENXIO;
-	}
-
-	dmarx_res = platform_get_resource(pdev, IORESOURCE_DMA, 1);
-	if (!dmarx_res) {
-		dev_err(&pdev->dev, "Unable to get PCM-RX dma resource\n");
-		return -ENXIO;
-	}
-
 	mem_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!mem_res) {
 		dev_err(&pdev->dev, "Unable to get register resource\n");
@@ -568,8 +556,10 @@ static int s3c_pcm_dev_probe(struct platform_device *pdev)
 	s3c_pcm_stereo_out[pdev->id].dma_addr = mem_res->start
 							+ S3C_PCM_TXFIFO;
 
-	s3c_pcm_stereo_in[pdev->id].channel = dmarx_res->start;
-	s3c_pcm_stereo_out[pdev->id].channel = dmatx_res->start;
+	if (pcm_pdata) {
+		s3c_pcm_stereo_in[pdev->id].slave = pcm_pdata->dma_capture;
+		s3c_pcm_stereo_out[pdev->id].slave = pcm_pdata->dma_playback;
+	}
 
 	pcm->dma_capture = &s3c_pcm_stereo_in[pdev->id];
 	pcm->dma_playback = &s3c_pcm_stereo_out[pdev->id];
diff --git a/sound/soc/samsung/s3c2412-i2s.c b/sound/soc/samsung/s3c2412-i2s.c
index 2b766d2..77d27c8 100644
--- a/sound/soc/samsung/s3c2412-i2s.c
+++ b/sound/soc/samsung/s3c2412-i2s.c
@@ -34,13 +34,13 @@
 #include "s3c2412-i2s.h"
 
 static struct s3c_dma_params s3c2412_i2s_pcm_stereo_out = {
-	.channel	= DMACH_I2S_OUT,
+	.slave		= (void *)(uintptr_t)DMACH_I2S_OUT,
 	.ch_name	= "tx",
 	.dma_size	= 4,
 };
 
 static struct s3c_dma_params s3c2412_i2s_pcm_stereo_in = {
-	.channel	= DMACH_I2S_IN,
+	.slave		= (void *)(uintptr_t)DMACH_I2S_IN,
 	.ch_name	= "rx",
 	.dma_size	= 4,
 };
diff --git a/sound/soc/samsung/s3c24xx-i2s.c b/sound/soc/samsung/s3c24xx-i2s.c
index 5bf7236..9da3a77 100644
--- a/sound/soc/samsung/s3c24xx-i2s.c
+++ b/sound/soc/samsung/s3c24xx-i2s.c
@@ -32,13 +32,13 @@
 #include "s3c24xx-i2s.h"
 
 static struct s3c_dma_params s3c24xx_i2s_pcm_stereo_out = {
-	.channel	= DMACH_I2S_OUT,
+	.slave		= (void *)(uintptr_t)DMACH_I2S_OUT,
 	.ch_name	= "tx",
 	.dma_size	= 2,
 };
 
 static struct s3c_dma_params s3c24xx_i2s_pcm_stereo_in = {
-	.channel	= DMACH_I2S_IN,
+	.slave		= (void *)(uintptr_t)DMACH_I2S_IN,
 	.ch_name	= "rx",
 	.dma_size	= 2,
 };
diff --git a/sound/soc/samsung/spdif.c b/sound/soc/samsung/spdif.c
index 36dbc0e9..9dd7ee6 100644
--- a/sound/soc/samsung/spdif.c
+++ b/sound/soc/samsung/spdif.c
@@ -359,7 +359,7 @@ static const struct snd_soc_component_driver samsung_spdif_component = {
 static int spdif_probe(struct platform_device *pdev)
 {
 	struct s3c_audio_pdata *spdif_pdata;
-	struct resource *mem_res, *dma_res;
+	struct resource *mem_res;
 	struct samsung_spdif_info *spdif;
 	int ret;
 
@@ -367,12 +367,6 @@ static int spdif_probe(struct platform_device *pdev)
 
 	dev_dbg(&pdev->dev, "Entered %s\n", __func__);
 
-	dma_res = platform_get_resource(pdev, IORESOURCE_DMA, 0);
-	if (!dma_res) {
-		dev_err(&pdev->dev, "Unable to get dma resource.\n");
-		return -ENXIO;
-	}
-
 	mem_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!mem_res) {
 		dev_err(&pdev->dev, "Unable to get register resource.\n");
@@ -432,7 +426,7 @@ static int spdif_probe(struct platform_device *pdev)
 
 	spdif_stereo_out.dma_size = 2;
 	spdif_stereo_out.dma_addr = mem_res->start + DATA_OUTBUF;
-	spdif_stereo_out.channel = dma_res->start;
+	spdif_stereo_out.slave = spdif_pdata ? spdif_pdata->dma_playback : NULL;
 
 	spdif->dma_playback = &spdif_stereo_out;
 
-- 
2.5.0

[added to the 4.1 stable tree] dm snapshot: disallow the COW and origin devices from being identical

[Sasha Levin]

From: DingXiang <dingxiang@huawei.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 4df2bf466a9c9c92f40d27c4aa9120f4e8227bfc ]

Otherwise loading a "snapshot" table using the same device for the
origin and COW devices, e.g.:

echo "0 20971520 snapshot 253:3 253:3 P 8" | dmsetup create snap

will trigger:

BUG: unable to handle kernel NULL pointer dereference at 0000000000000098
[ 1958.979934] IP: [<ffffffffa040efba>] dm_exception_store_set_chunk_size+0x7a/0x110 [dm_snapshot]
[ 1958.989655] PGD 0
[ 1958.991903] Oops: 0000 [#1] SMP
...
[ 1959.059647] CPU: 9 PID: 3556 Comm: dmsetup Tainted: G          IO    4.5.0-rc5.snitm+ #150
...
[ 1959.083517] task: ffff8800b9660c80 ti: ffff88032a954000 task.ti: ffff88032a954000
[ 1959.091865] RIP: 0010:[<ffffffffa040efba>]  [<ffffffffa040efba>] dm_exception_store_set_chunk_size+0x7a/0x110 [dm_snapshot]
[ 1959.104295] RSP: 0018:ffff88032a957b30  EFLAGS: 00010246
[ 1959.110219] RAX: 0000000000000000 RBX: 0000000000000008 RCX: 0000000000000001
[ 1959.118180] RDX: 0000000000000000 RSI: 0000000000000008 RDI: ffff880329334a00
[ 1959.126141] RBP: ffff88032a957b50 R08: 0000000000000000 R09: 0000000000000001
[ 1959.134102] R10: 000000000000000a R11: f000000000000000 R12: ffff880330884d80
[ 1959.142061] R13: 0000000000000008 R14: ffffc90001c13088 R15: ffff880330884d80
[ 1959.150021] FS:  00007f8926ba3840(0000) GS:ffff880333440000(0000) knlGS:0000000000000000
[ 1959.159047] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 1959.165456] CR2: 0000000000000098 CR3: 000000032f48b000 CR4: 00000000000006e0
[ 1959.173415] Stack:
[ 1959.175656]  ffffc90001c13040 ffff880329334a00 ffff880330884ed0 ffff88032a957bdc
[ 1959.183946]  ffff88032a957bb8 ffffffffa040f225 ffff880329334a30 ffff880300000000
[ 1959.192233]  ffffffffa04133e0 ffff880329334b30 0000000830884d58 00000000569c58cf
[ 1959.200521] Call Trace:
[ 1959.203248]  [<ffffffffa040f225>] dm_exception_store_create+0x1d5/0x240 [dm_snapshot]
[ 1959.211986]  [<ffffffffa040d310>] snapshot_ctr+0x140/0x630 [dm_snapshot]
[ 1959.219469]  [<ffffffffa0005c44>] ? dm_split_args+0x64/0x150 [dm_mod]
[ 1959.226656]  [<ffffffffa0005ea7>] dm_table_add_target+0x177/0x440 [dm_mod]
[ 1959.234328]  [<ffffffffa0009203>] table_load+0x143/0x370 [dm_mod]
[ 1959.241129]  [<ffffffffa00090c0>] ? retrieve_status+0x1b0/0x1b0 [dm_mod]
[ 1959.248607]  [<ffffffffa0009e35>] ctl_ioctl+0x255/0x4d0 [dm_mod]
[ 1959.255307]  [<ffffffff813304e2>] ? memzero_explicit+0x12/0x20
[ 1959.261816]  [<ffffffffa000a0c3>] dm_ctl_ioctl+0x13/0x20 [dm_mod]
[ 1959.268615]  [<ffffffff81215eb6>] do_vfs_ioctl+0xa6/0x5c0
[ 1959.274637]  [<ffffffff81120d2f>] ? __audit_syscall_entry+0xaf/0x100
[ 1959.281726]  [<ffffffff81003176>] ? do_audit_syscall_entry+0x66/0x70
[ 1959.288814]  [<ffffffff81216449>] SyS_ioctl+0x79/0x90
[ 1959.294450]  [<ffffffff8167e4ae>] entry_SYSCALL_64_fastpath+0x12/0x71
...
[ 1959.323277] RIP  [<ffffffffa040efba>] dm_exception_store_set_chunk_size+0x7a/0x110 [dm_snapshot]
[ 1959.333090]  RSP <ffff88032a957b30>
[ 1959.336978] CR2: 0000000000000098
[ 1959.344121] ---[ end trace b049991ccad1169e ]---

Fixes: https://bugzilla.redhat.com/show_bug.cgi?id=1195899
Cc: stable@vger.kernel.org
Signed-off-by: Ding Xiang <dingxiang@huawei.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/md/dm-snap.c          |  9 +++++++++
 drivers/md/dm-table.c         | 36 ++++++++++++++++++++++++------------
 include/linux/device-mapper.h |  2 ++
 3 files changed, 35 insertions(+), 12 deletions(-)

diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 11ec9d2..38f3755 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -1099,6 +1099,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	int i;
 	int r = -EINVAL;
 	char *origin_path, *cow_path;
+	dev_t origin_dev, cow_dev;
 	unsigned args_used, num_flush_bios = 1;
 	fmode_t origin_mode = FMODE_READ;
 
@@ -1129,11 +1130,19 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		ti->error = "Cannot get origin device";
 		goto bad_origin;
 	}
+	origin_dev = s->origin->bdev->bd_dev;
 
 	cow_path = argv[0];
 	argv++;
 	argc--;
 
+	cow_dev = dm_get_dev_t(cow_path);
+	if (cow_dev && cow_dev == origin_dev) {
+		ti->error = "COW device cannot be the same as origin device";
+		r = -EINVAL;
+		goto bad_cow;
+	}
+
 	r = dm_get_device(ti, cow_path, dm_table_get_mode(ti->table), &s->cow);
 	if (r) {
 		ti->error = "Cannot get COW device";
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 16ba55a..e411ccb 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -365,6 +365,26 @@ static int upgrade_mode(struct dm_dev_internal *dd, fmode_t new_mode,
 }
 
 /*
+ * Convert the path to a device
+ */
+dev_t dm_get_dev_t(const char *path)
+{
+	dev_t uninitialized_var(dev);
+	struct block_device *bdev;
+
+	bdev = lookup_bdev(path);
+	if (IS_ERR(bdev))
+		dev = name_to_dev_t(path);
+	else {
+		dev = bdev->bd_dev;
+		bdput(bdev);
+	}
+
+	return dev;
+}
+EXPORT_SYMBOL_GPL(dm_get_dev_t);
+
+/*
  * Add a device to the list, or just increment the usage count if
  * it's already present.
  */
@@ -372,23 +392,15 @@ int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode,
 		  struct dm_dev **result)
 {
 	int r;
-	dev_t uninitialized_var(dev);
+	dev_t dev;
 	struct dm_dev_internal *dd;
 	struct dm_table *t = ti->table;
-	struct block_device *bdev;
 
 	BUG_ON(!t);
 
-	/* convert the path to a device */
-	bdev = lookup_bdev(path);
-	if (IS_ERR(bdev)) {
-		dev = name_to_dev_t(path);
-		if (!dev)
-			return -ENODEV;
-	} else {
-		dev = bdev->bd_dev;
-		bdput(bdev);
-	}
+	dev = dm_get_dev_t(path);
+	if (!dev)
+		return -ENODEV;
 
 	dd = find_device(&t->devices, dev);
 	if (!dd) {
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 51cc1de..30c8971b 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -127,6 +127,8 @@ struct dm_dev {
 	char name[16];
 };
 
+dev_t dm_get_dev_t(const char *path);
+
 /*
  * Constructors should call these functions to ensure destination devices
  * are opened/closed correctly.
-- 
2.5.0

[added to the 4.1 stable tree] ALSA: usb-audio: Minor code cleanup in create_fixed_stream_quirk()

[Sasha Levin]

From: Takashi Iwai <tiwai@suse.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 902eb7fd1e4af3ac69b9b30f8373f118c92b9729 ]

Just a minor code cleanup: unify the error paths.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 sound/usb/quirks.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 194fa7f6..dcd4b23 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -164,23 +164,18 @@ static int create_fixed_stream_quirk(struct snd_usb_audio *chip,
 	stream = (fp->endpoint & USB_DIR_IN)
 		? SNDRV_PCM_STREAM_CAPTURE : SNDRV_PCM_STREAM_PLAYBACK;
 	err = snd_usb_add_audio_stream(chip, stream, fp);
-	if (err < 0) {
-		kfree(fp);
-		kfree(rate_table);
-		return err;
-	}
+	if (err < 0)
+		goto error;
 	if (fp->iface != get_iface_desc(&iface->altsetting[0])->bInterfaceNumber ||
 	    fp->altset_idx >= iface->num_altsetting) {
-		kfree(fp);
-		kfree(rate_table);
-		return -EINVAL;
+		err = -EINVAL;
+		goto error;
 	}
 	alts = &iface->altsetting[fp->altset_idx];
 	altsd = get_iface_desc(alts);
 	if (altsd->bNumEndpoints < 1) {
-		kfree(fp);
-		kfree(rate_table);
-		return -EINVAL;
+		err = -EINVAL;
+		goto error;
 	}
 
 	fp->protocol = altsd->bInterfaceProtocol;
@@ -193,6 +188,11 @@ static int create_fixed_stream_quirk(struct snd_usb_audio *chip,
 	snd_usb_init_pitch(chip, fp->iface, alts, fp);
 	snd_usb_init_sample_rate(chip, fp->iface, alts, fp, fp->rate_max);
 	return 0;
+
+ error:
+	kfree(fp);
+	kfree(rate_table);
+	return err;
 }
 
 static int create_auto_pcm_quirk(struct snd_usb_audio *chip,
-- 
2.5.0

[added to the 4.1 stable tree] ALSA: usb-audio: Fix double-free in error paths after snd_usb_add_audio_stream() call

[Sasha Levin]

From: Vladis Dronov <vdronov@redhat.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 836b34a935abc91e13e63053d0a83b24dfb5ea78 ]

create_fixed_stream_quirk(), snd_usb_parse_audio_interface() and
create_uaxx_quirk() functions allocate the audioformat object by themselves
and free it upon error before returning. However, once the object is linked
to a stream, it's freed again in snd_usb_audio_pcm_free(), thus it'll be
double-freed, eventually resulting in a memory corruption.

This patch fixes these failures in the error paths by unlinking the audioformat
object before freeing it.

Based on a patch by Takashi Iwai <tiwai@suse.de>

[Note for stable backports:
 this patch requires the commit 902eb7fd1e4a ('ALSA: usb-audio: Minor
 code cleanup in create_fixed_stream_quirk()')]

Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1283358
Reported-by: Ralf Spenneberg <ralf@spenneberg.net>
Cc: <stable@vger.kernel.org> # see the note above
Signed-off-by: Vladis Dronov <vdronov@redhat.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 sound/usb/quirks.c | 4 ++++
 sound/usb/stream.c | 6 +++++-
 2 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index dcd4b23..e27df0d 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -147,6 +147,7 @@ static int create_fixed_stream_quirk(struct snd_usb_audio *chip,
 		usb_audio_err(chip, "cannot memdup\n");
 		return -ENOMEM;
 	}
+	INIT_LIST_HEAD(&fp->list);
 	if (fp->nr_rates > MAX_NR_RATES) {
 		kfree(fp);
 		return -EINVAL;
@@ -190,6 +191,7 @@ static int create_fixed_stream_quirk(struct snd_usb_audio *chip,
 	return 0;
 
  error:
+	list_del(&fp->list); /* unlink for avoiding double-free */
 	kfree(fp);
 	kfree(rate_table);
 	return err;
@@ -465,6 +467,7 @@ static int create_uaxx_quirk(struct snd_usb_audio *chip,
 	fp->ep_attr = get_endpoint(alts, 0)->bmAttributes;
 	fp->datainterval = 0;
 	fp->maxpacksize = le16_to_cpu(get_endpoint(alts, 0)->wMaxPacketSize);
+	INIT_LIST_HEAD(&fp->list);
 
 	switch (fp->maxpacksize) {
 	case 0x120:
@@ -488,6 +491,7 @@ static int create_uaxx_quirk(struct snd_usb_audio *chip,
 		? SNDRV_PCM_STREAM_CAPTURE : SNDRV_PCM_STREAM_PLAYBACK;
 	err = snd_usb_add_audio_stream(chip, stream, fp);
 	if (err < 0) {
+		list_del(&fp->list); /* unlink for avoiding double-free */
 		kfree(fp);
 		return err;
 	}
diff --git a/sound/usb/stream.c b/sound/usb/stream.c
index 310a382..25e8075 100644
--- a/sound/usb/stream.c
+++ b/sound/usb/stream.c
@@ -315,7 +315,9 @@ static struct snd_pcm_chmap_elem *convert_chmap(int channels, unsigned int bits,
 /*
  * add this endpoint to the chip instance.
  * if a stream with the same endpoint already exists, append to it.
- * if not, create a new pcm stream.
+ * if not, create a new pcm stream. note, fp is added to the substream
+ * fmt_list and will be freed on the chip instance release. do not free
+ * fp or do remove it from the substream fmt_list to avoid double-free.
  */
 int snd_usb_add_audio_stream(struct snd_usb_audio *chip,
 			     int stream,
@@ -668,6 +670,7 @@ int snd_usb_parse_audio_interface(struct snd_usb_audio *chip, int iface_no)
 					* (fp->maxpacksize & 0x7ff);
 		fp->attributes = parse_uac_endpoint_attributes(chip, alts, protocol, iface_no);
 		fp->clock = clock;
+		INIT_LIST_HEAD(&fp->list);
 
 		/* some quirks for attributes here */
 
@@ -716,6 +719,7 @@ int snd_usb_parse_audio_interface(struct snd_usb_audio *chip, int iface_no)
 		dev_dbg(&dev->dev, "%u:%d: add audio endpoint %#x\n", iface_no, altno, fp->endpoint);
 		err = snd_usb_add_audio_stream(chip, stream, fp);
 		if (err < 0) {
+			list_del(&fp->list); /* unlink for avoiding double-free */
 			kfree(fp->rate_table);
 			kfree(fp->chmap);
 			kfree(fp);
-- 
2.5.0

[added to the 4.1 stable tree] tpm: fix the cleanup of struct tpm_chip

[Sasha Levin]

From: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 8e0ee3c9faed7ca68807ea45141775856c438ac0 ]

If the initialization fails before tpm_chip_register(), put_device()
will be not called, which causes release callback not to be called.
This patch fixes the issue by adding put_device() to devres list of
the parent device.

Fixes: 313d21eeab ("tpm: device class for tpm")
Signed-off-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
cc: stable@vger.kernel.org
Reviewed-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/char/tpm/tpm-chip.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c
index 1082d4b..591629c 100644
--- a/drivers/char/tpm/tpm-chip.c
+++ b/drivers/char/tpm/tpm-chip.c
@@ -133,6 +133,8 @@ struct tpm_chip *tpmm_chip_alloc(struct device *dev,
 	chip->cdev.owner = chip->pdev->driver->owner;
 	chip->cdev.kobj.parent = &chip->dev.kobj;
 
+	devm_add_action(dev, (void (*)(void *)) put_device, &chip->dev);
+
 	return chip;
 }
 EXPORT_SYMBOL_GPL(tpmm_chip_alloc);
@@ -168,7 +170,7 @@ static int tpm_dev_add_device(struct tpm_chip *chip)
 static void tpm_dev_del_device(struct tpm_chip *chip)
 {
 	cdev_del(&chip->cdev);
-	device_unregister(&chip->dev);
+	device_del(&chip->dev);
 }
 
 static int tpm1_chip_register(struct tpm_chip *chip)
-- 
2.5.0

[added to the 4.1 stable tree] HID: logitech: fix Dual Action gamepad support

[Sasha Levin]

From: Grazvydas Ignotas <notasas@gmail.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 5d74325a2201376a95520a4a38a1ce2c65761c49 ]

The patch that added Logitech Dual Action gamepad support forgot to
update the special driver list for the device. This caused the logitech
driver not to probe unless kernel module load order was favorable.
Update the special driver list to fix it. Thanks to Simon Wood for the
idea.

Cc: Vitaly Katraew <zawullon@gmail.com>
Fixes: 56d0c8b7c8fb ("HID: add support for Logitech Dual Action gamepads")
Signed-off-by: Grazvydas Ignotas <notasas@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/hid/hid-core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index bc23db1..bf039db 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1864,6 +1864,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_ELITE_KBD) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_CORDLESS_DESKTOP_LX500) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_EXTREME_3D) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_DUAL_ACTION) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_WHEEL) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_RUMBLEPAD_CORD) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_RUMBLEPAD) },
-- 
2.5.0

[added to the 4.1 stable tree] 8250: use callbacks to access UART_DLL/UART_DLM

[Sasha Levin]

From: Sebastian Frias <sf84@laposte.net>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 0b41ce991052022c030fd868e03877700220b090 ]

Some UART HW has a single register combining UART_DLL/UART_DLM
(this was probably forgotten in the change that introduced the
callbacks, commit b32b19b8ffc05cbd3bf91c65e205f6a912ca15d9)

Fixes: b32b19b8ffc0 ("[SERIAL] 8250: set divisor register correctly ...")

Signed-off-by: Sebastian Frias <sf84@laposte.net>
Reviewed-by: Peter Hurley <peter@hurleysoftware.com>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/tty/serial/8250/8250_core.c | 18 ++++++------------
 1 file changed, 6 insertions(+), 12 deletions(-)

diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index b4fd8de..a64d53f 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -791,22 +791,16 @@ static int size_fifo(struct uart_8250_port *up)
  */
 static unsigned int autoconfig_read_divisor_id(struct uart_8250_port *p)
 {
-	unsigned char old_dll, old_dlm, old_lcr;
-	unsigned int id;
+	unsigned char old_lcr;
+	unsigned int id, old_dl;
 
 	old_lcr = serial_in(p, UART_LCR);
 	serial_out(p, UART_LCR, UART_LCR_CONF_MODE_A);
+	old_dl = serial_dl_read(p);
+	serial_dl_write(p, 0);
+	id = serial_dl_read(p);
+	serial_dl_write(p, old_dl);
 
-	old_dll = serial_in(p, UART_DLL);
-	old_dlm = serial_in(p, UART_DLM);
-
-	serial_out(p, UART_DLL, 0);
-	serial_out(p, UART_DLM, 0);
-
-	id = serial_in(p, UART_DLL) | serial_in(p, UART_DLM) << 8;
-
-	serial_out(p, UART_DLL, old_dll);
-	serial_out(p, UART_DLM, old_dlm);
 	serial_out(p, UART_LCR, old_lcr);
 
 	return id;
-- 
2.5.0

[added to the 4.1 stable tree] mtip32xx: Fix for rmmod crash when drive is in FTL rebuild

[Sasha Levin]

From: Asai Thambi SP <asamymuthupa@micron.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 59cf70e236c96594d9f1e065755d8fce9df5356b ]

When FTL rebuild is in progress, alloc_disk() initializes the disk
but device node will be created by add_disk() only after successful
completion of FTL rebuild. So, skip deletion of device node in
removal path when FTL rebuild is in progress.

Signed-off-by: Selvan Mani <smani@micron.com>
Signed-off-by: Asai Thambi S P <asamymuthupa@micron.com>
Cc: stable@vger.kernel.org
Signed-off-by: Jens Axboe <axboe@fb.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/block/mtip32xx/mtip32xx.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 2af8b29..09212c1 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -3004,10 +3004,8 @@ restart_eh:
 		}
 
 		if (test_bit(MTIP_PF_REBUILD_BIT, &port->flags)) {
-			if (mtip_ftl_rebuild_poll(dd) < 0)
-				set_bit(MTIP_DDF_REBUILD_FAILED_BIT,
-							&dd->dd_flag);
-			clear_bit(MTIP_PF_REBUILD_BIT, &port->flags);
+			if (mtip_ftl_rebuild_poll(dd) == 0)
+				clear_bit(MTIP_PF_REBUILD_BIT, &port->flags);
 		}
 	}
 
@@ -3887,7 +3885,6 @@ static int mtip_block_initialize(struct driver_data *dd)
 
 	mtip_hw_debugfs_init(dd);
 
-skip_create_disk:
 	memset(&dd->tags, 0, sizeof(dd->tags));
 	dd->tags.ops = &mtip_mq_ops;
 	dd->tags.nr_hw_queues = 1;
@@ -3917,6 +3914,7 @@ skip_create_disk:
 	dd->disk->queue		= dd->queue;
 	dd->queue->queuedata	= dd;
 
+skip_create_disk:
 	/* Initialize the protocol layer. */
 	wait_for_rebuild = mtip_hw_get_identify(dd);
 	if (wait_for_rebuild < 0) {
@@ -4078,7 +4076,8 @@ static int mtip_block_remove(struct driver_data *dd)
 		dd->bdev = NULL;
 	}
 	if (dd->disk) {
-		del_gendisk(dd->disk);
+		if (test_bit(MTIP_DDF_INIT_DONE_BIT, &dd->dd_flag))
+			del_gendisk(dd->disk);
 		if (dd->disk->queue) {
 			blk_cleanup_queue(dd->queue);
 			blk_mq_free_tag_set(&dd->tags);
@@ -4119,7 +4118,8 @@ static int mtip_block_shutdown(struct driver_data *dd)
 		dev_info(&dd->pdev->dev,
 			"Shutting down %s ...\n", dd->disk->disk_name);
 
-		del_gendisk(dd->disk);
+		if (test_bit(MTIP_DDF_INIT_DONE_BIT, &dd->dd_flag))
+			del_gendisk(dd->disk);
 		if (dd->disk->queue) {
 			blk_cleanup_queue(dd->queue);
 			blk_mq_free_tag_set(&dd->tags);
-- 
2.5.0

[added to the 4.1 stable tree] mtip32xx: Fix broken service thread handling

[Sasha Levin]

From: Asai Thambi SP <asamymuthupa@micron.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 1b899eb4833d3394f37272d38b4b1a26eac30feb ]

commit cfc05bd31384c4898bf2437a4de5557f3cf9803a upstream.

Service thread does not detect the need for taskfile error hanlding. Fixed the
flag condition to process taskfile error.

Signed-off-by: Selvan Mani <smani@micron.com>
Signed-off-by: Asai Thambi S P <asamymuthupa@micron.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/block/mtip32xx/mtip32xx.c | 12 ++++++++++--
 drivers/block/mtip32xx/mtip32xx.h |  5 +++++
 2 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 09212c1..eecaa02 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -2946,9 +2946,15 @@ static int mtip_service_thread(void *data)
 		 * is in progress nor error handling is active
 		 */
 		wait_event_interruptible(port->svc_wait, (port->flags) &&
-			!(port->flags & MTIP_PF_PAUSE_IO));
+			(port->flags & MTIP_PF_SVC_THD_WORK));
 
-		set_bit(MTIP_PF_SVC_THD_ACTIVE_BIT, &port->flags);
+		if (kthread_should_stop() ||
+			test_bit(MTIP_PF_SVC_THD_STOP_BIT, &port->flags))
+			goto st_out;
+
+		if (unlikely(test_bit(MTIP_DDF_REMOVE_PENDING_BIT,
+				&dd->dd_flag)))
+			goto st_out;
 
 		if (kthread_should_stop() ||
 			test_bit(MTIP_PF_SVC_THD_STOP_BIT, &port->flags))
@@ -2962,6 +2968,8 @@ static int mtip_service_thread(void *data)
 				&dd->dd_flag)))
 			goto st_out;
 
+		set_bit(MTIP_PF_SVC_THD_ACTIVE_BIT, &port->flags);
+
 restart_eh:
 		/* Demux bits: start with error handling */
 		if (test_bit(MTIP_PF_EH_ACTIVE_BIT, &port->flags)) {
diff --git a/drivers/block/mtip32xx/mtip32xx.h b/drivers/block/mtip32xx/mtip32xx.h
index 7669526..578ad36 100644
--- a/drivers/block/mtip32xx/mtip32xx.h
+++ b/drivers/block/mtip32xx/mtip32xx.h
@@ -145,6 +145,11 @@ enum {
 	MTIP_PF_SR_CLEANUP_BIT      = 7,
 	MTIP_PF_SVC_THD_STOP_BIT    = 8,
 
+	MTIP_PF_SVC_THD_WORK	= ((1 << MTIP_PF_EH_ACTIVE_BIT) |
+				  (1 << MTIP_PF_ISSUE_CMDS_BIT) |
+				  (1 << MTIP_PF_REBUILD_BIT) |
+				  (1 << MTIP_PF_SVC_THD_STOP_BIT)),
+
 	/* below are bit numbers in 'dd_flag' defined in driver_data */
 	MTIP_DDF_SEC_LOCK_BIT	    = 0,
 	MTIP_DDF_REMOVE_PENDING_BIT = 1,
-- 
2.5.0

[added to the 4.1 stable tree] ALSA: pcm: Avoid "BUG:" string for warnings again

[Sasha Levin]

From: Takashi Iwai <tiwai@suse.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 0ab1ace856205d10cbc1924b2d931c01ffd216a6 ]

The commit [d507941beb1e: ALSA: pcm: Correct PCM BUG error message]
made the warning prefix back to "BUG:" due to its previous wrong
prefix.  But a kernel message containing "BUG:" seems taken as an Oops
message wrongly by some brain-dead daemons, and it annoys users in the
end.  Instead of teaching daemons, change the string again to a more
reasonable one.

Fixes: 507941beb1e ('ALSA: pcm: Correct PCM BUG error message')
Cc: <stable@vger.kernel.org> # v3.19+
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 sound/core/pcm_lib.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c
index 7d45645..253a2da 100644
--- a/sound/core/pcm_lib.c
+++ b/sound/core/pcm_lib.c
@@ -322,7 +322,7 @@ static int snd_pcm_update_hw_ptr0(struct snd_pcm_substream *substream,
 			char name[16];
 			snd_pcm_debug_name(substream, name, sizeof(name));
 			pcm_err(substream->pcm,
-				"BUG: %s, pos = %ld, buffer size = %ld, period size = %ld\n",
+				"invalid position: %s, pos = %ld, buffer size = %ld, period size = %ld\n",
 				name, pos, runtime->buffer_size,
 				runtime->period_size);
 		}
-- 
2.5.0

[added to the 4.1 stable tree] hwmon: (max1111) Return -ENODEV from max1111_read_channel if not instantiated

[Sasha Levin]

From: Guenter Roeck <linux@roeck-us.net>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 3c2e2266a5bd2d1cef258e6e54dca1d99946379f ]

arm:pxa_defconfig can result in the following crash if the max1111 driver
is not instantiated.

Unhandled fault: page domain fault (0x01b) at 0x00000000
pgd = c0004000
[00000000] *pgd=00000000
Internal error: : 1b [#1] PREEMPT ARM
Modules linked in:
CPU: 0 PID: 300 Comm: kworker/0:1 Not tainted 4.5.0-01301-g1701f680407c #10
Hardware name: SHARP Akita
Workqueue: events sharpsl_charge_toggle
task: c390a000 ti: c391e000 task.ti: c391e000
PC is at max1111_read_channel+0x20/0x30
LR is at sharpsl_pm_pxa_read_max1111+0x2c/0x3c
pc : [<c03aaab0>]    lr : [<c0024b50>]    psr: 20000013
...
[<c03aaab0>] (max1111_read_channel) from [<c0024b50>]
					(sharpsl_pm_pxa_read_max1111+0x2c/0x3c)
[<c0024b50>] (sharpsl_pm_pxa_read_max1111) from [<c00262e0>]
					(spitzpm_read_devdata+0x5c/0xc4)
[<c00262e0>] (spitzpm_read_devdata) from [<c0024094>]
					(sharpsl_check_battery_temp+0x78/0x110)
[<c0024094>] (sharpsl_check_battery_temp) from [<c0024f9c>]
					(sharpsl_charge_toggle+0x48/0x110)
[<c0024f9c>] (sharpsl_charge_toggle) from [<c004429c>]
					(process_one_work+0x14c/0x48c)
[<c004429c>] (process_one_work) from [<c0044618>] (worker_thread+0x3c/0x5d4)
[<c0044618>] (worker_thread) from [<c004a238>] (kthread+0xd0/0xec)
[<c004a238>] (kthread) from [<c000a670>] (ret_from_fork+0x14/0x24)

This can occur because the SPI controller driver (SPI_PXA2XX) is built as
module and thus not necessarily loaded. While building SPI_PXA2XX into the
kernel would make the problem disappear, it appears prudent to ensure that
the driver is instantiated before accessing its data structures.

Cc: Arnd Bergmann <arnd@arndb.de>
Cc: stable@vger.kernel.org
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/hwmon/max1111.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/hwmon/max1111.c b/drivers/hwmon/max1111.c
index f67d71e..159f50d 100644
--- a/drivers/hwmon/max1111.c
+++ b/drivers/hwmon/max1111.c
@@ -85,6 +85,9 @@ static struct max1111_data *the_max1111;
 
 int max1111_read_channel(int channel)
 {
+	if (!the_max1111 || !the_max1111->spi)
+		return -ENODEV;
+
 	return max1111_read(&the_max1111->spi->dev, channel);
 }
 EXPORT_SYMBOL(max1111_read_channel);
@@ -258,6 +261,9 @@ static int max1111_remove(struct spi_device *spi)
 {
 	struct max1111_data *data = spi_get_drvdata(spi);
 
+#ifdef CONFIG_SHARPSL_PM
+	the_max1111 = NULL;
+#endif
 	hwmon_device_unregister(data->hwmon_dev);
 	sysfs_remove_group(&spi->dev.kobj, &max1110_attr_group);
 	sysfs_remove_group(&spi->dev.kobj, &max1111_attr_group);
-- 
2.5.0

[added to the 4.1 stable tree] PKCS#7: pkcs7_validate_trust(): initialize the _trusted output argument

[Sasha Levin]

From: Nicolai Stange <nicstange@gmail.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit e54358915d0a00399c11c2c23ae1be674cba188a ]

Despite what the DocBook comment to pkcs7_validate_trust() says, the
*_trusted argument is never set to false.

pkcs7_validate_trust() only positively sets *_trusted upon encountering
a trusted PKCS#7 SignedInfo block.

This is quite unfortunate since its callers, system_verify_data() for
example, depend on pkcs7_validate_trust() clearing *_trusted on non-trust.

Indeed, UBSAN splats when attempting to load the uninitialized local
variable 'trusted' from system_verify_data() in pkcs7_validate_trust():

  UBSAN: Undefined behaviour in crypto/asymmetric_keys/pkcs7_trust.c:194:14
  load of value 82 is not a valid value for type '_Bool'
  [...]
  Call Trace:
    [<ffffffff818c4d35>] dump_stack+0xbc/0x117
    [<ffffffff818c4c79>] ? _atomic_dec_and_lock+0x169/0x169
    [<ffffffff8194113b>] ubsan_epilogue+0xd/0x4e
    [<ffffffff819419fa>] __ubsan_handle_load_invalid_value+0x111/0x158
    [<ffffffff819418e9>] ? val_to_string.constprop.12+0xcf/0xcf
    [<ffffffff818334a4>] ? x509_request_asymmetric_key+0x114/0x370
    [<ffffffff814b83f0>] ? kfree+0x220/0x370
    [<ffffffff818312c2>] ? public_key_verify_signature_2+0x32/0x50
    [<ffffffff81835e04>] pkcs7_validate_trust+0x524/0x5f0
    [<ffffffff813c391a>] system_verify_data+0xca/0x170
    [<ffffffff813c3850>] ? top_trace_array+0x9b/0x9b
    [<ffffffff81510b29>] ? __vfs_read+0x279/0x3d0
    [<ffffffff8129372f>] mod_verify_sig+0x1ff/0x290
    [...]

The implication is that pkcs7_validate_trust() effectively grants trust
when it really shouldn't have.

Fix this by explicitly setting *_trusted to false at the very beginning
of pkcs7_validate_trust().

Cc: <stable@vger.kernel.org>
Signed-off-by: Nicolai Stange <nicstange@gmail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 crypto/asymmetric_keys/pkcs7_trust.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/crypto/asymmetric_keys/pkcs7_trust.c b/crypto/asymmetric_keys/pkcs7_trust.c
index 0f6463b..44c8447e 100644
--- a/crypto/asymmetric_keys/pkcs7_trust.c
+++ b/crypto/asymmetric_keys/pkcs7_trust.c
@@ -174,6 +174,8 @@ int pkcs7_validate_trust(struct pkcs7_message *pkcs7,
 	int cached_ret = -ENOKEY;
 	int ret;
 
+	*_trusted = false;
+
 	for (p = pkcs7->certs; p; p = p->next)
 		p->seen = false;
 
-- 
2.5.0

[added to the 4.1 stable tree] ALSA: timer: Use mod_timer() for rearming the system timer

[Sasha Levin]

From: Takashi Iwai <tiwai@suse.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 4a07083ed613644c96c34a7dd2853dc5d7c70902 ]

ALSA system timer backend stops the timer via del_timer() without sync
and leaves del_timer_sync() at the close instead.  This is because of
the restriction by the design of ALSA timer: namely, the stop callback
may be called from the timer handler, and calling the sync shall lead
to a hangup.  However, this also triggers a kernel BUG() when the
timer is rearmed immediately after stopping without sync:
 kernel BUG at kernel/time/timer.c:966!
 Call Trace:
  <IRQ>
  [<ffffffff8239c94e>] snd_timer_s_start+0x13e/0x1a0
  [<ffffffff8239e1f4>] snd_timer_interrupt+0x504/0xec0
  [<ffffffff8122fca0>] ? debug_check_no_locks_freed+0x290/0x290
  [<ffffffff8239ec64>] snd_timer_s_function+0xb4/0x120
  [<ffffffff81296b72>] call_timer_fn+0x162/0x520
  [<ffffffff81296add>] ? call_timer_fn+0xcd/0x520
  [<ffffffff8239ebb0>] ? snd_timer_interrupt+0xec0/0xec0
  ....

It's the place where add_timer() checks the pending timer.  It's clear
that this may happen after the immediate restart without sync in our
cases.

So, the workaround here is just to use mod_timer() instead of
add_timer().  This looks like a band-aid fix, but it's a right move,
as snd_timer_interrupt() takes care of the continuous rearm of timer.

Reported-by: Jiri Slaby <jslaby@suse.cz>
Cc: <stable@vger.kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 sound/core/timer.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/core/timer.c b/sound/core/timer.c
index bf48e71..1782555 100644
--- a/sound/core/timer.c
+++ b/sound/core/timer.c
@@ -1051,8 +1051,8 @@ static int snd_timer_s_start(struct snd_timer * timer)
 		njiff += timer->sticks - priv->correction;
 		priv->correction = 0;
 	}
-	priv->last_expires = priv->tlist.expires = njiff;
-	add_timer(&priv->tlist);
+	priv->last_expires = njiff;
+	mod_timer(&priv->tlist, njiff);
 	return 0;
 }
 
-- 
2.5.0

[added to the 4.1 stable tree] mm: fix invalid node in alloc_migrate_target()

[Sasha Levin]

From: Xishi Qiu <qiuxishi@huawei.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 6f25a14a7053b69917e2ebea0d31dd444cd31fd5 ]

It is incorrect to use next_node to find a target node, it will return
MAX_NUMNODES or invalid node.  This will lead to crash in buddy system
allocation.

Fixes: c8721bbbdd36 ("mm: memory-hotplug: enable memory hotplug to handle hugepage")
Signed-off-by: Xishi Qiu <qiuxishi@huawei.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Joonsoo Kim <js1304@gmail.com>
Cc: David Rientjes <rientjes@google.com>
Cc: "Laura Abbott" <lauraa@codeaurora.org>
Cc: Hui Zhu <zhuhui@xiaomi.com>
Cc: Wang Xiaoqiang <wangxq10@lzu.edu.cn>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 mm/page_isolation.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 303c908..4b640c2 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -300,11 +300,11 @@ struct page *alloc_migrate_target(struct page *page, unsigned long private,
 	 * now as a simple work-around, we use the next node for destination.
 	 */
 	if (PageHuge(page)) {
-		nodemask_t src = nodemask_of_node(page_to_nid(page));
-		nodemask_t dst;
-		nodes_complement(dst, src);
+		int node = next_online_node(page_to_nid(page));
+		if (node == MAX_NUMNODES)
+			node = first_online_node;
 		return alloc_huge_page_node(page_hstate(compound_head(page)),
-					    next_node(page_to_nid(page), dst));
+					    node);
 	}
 
 	if (PageHighMem(page))
-- 
2.5.0

[added to the 4.1 stable tree] powerpc/mm: Fixup preempt underflow with huge pages

[Sasha Levin]

From: Sebastian Siewior <bigeasy@linutronix.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 08a5bb2921e490939f78f38fd0d02858bb709942 ]

hugepd_free() used __get_cpu_var() once. Nothing ensured that the code
accessing the variable did not migrate from one CPU to another and soon
this was noticed by Tiejun Chen in 94b09d755462 ("powerpc/hugetlb:
Replace __get_cpu_var with get_cpu_var"). So we had it fixed.

Christoph Lameter was doing his __get_cpu_var() replaces and forgot
PowerPC. Then he noticed this and sent his fixed up batch again which
got applied as 69111bac42f5 ("powerpc: Replace __get_cpu_var uses").

The careful reader will noticed one little detail: get_cpu_var() got
replaced with this_cpu_ptr(). So now we have a put_cpu_var() which does
a preempt_enable() and nothing that does preempt_disable() so we
underflow the preempt counter.

Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: stable@vger.kernel.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 arch/powerpc/mm/hugetlbpage.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 3385e3d..4d29154 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -472,13 +472,13 @@ static void hugepd_free(struct mmu_gather *tlb, void *hugepte)
 {
 	struct hugepd_freelist **batchp;
 
-	batchp = this_cpu_ptr(&hugepd_freelist_cur);
+	batchp = &get_cpu_var(hugepd_freelist_cur);
 
 	if (atomic_read(&tlb->mm->mm_users) < 2 ||
 	    cpumask_equal(mm_cpumask(tlb->mm),
 			  cpumask_of(smp_processor_id()))) {
 		kmem_cache_free(hugepte_cache, hugepte);
-        put_cpu_var(hugepd_freelist_cur);
+		put_cpu_var(hugepd_freelist_cur);
 		return;
 	}
 
-- 
2.5.0

[added to the 4.1 stable tree] drm: Fix for DP CTS test 4.2.2.5 - I2C DEFER handling

[Sasha Levin]

From: Todd Previte <tprevite@gmail.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 396aa4451e865d1e36d6d4e0686a9303c038b606 ]

For test 4.2.2.5 to pass per the Link CTS Core 1.2 rev1.1 spec, the source
device must attempt at least 7 times to read the EDID when it receives an
I2C defer. The normal DRM code makes only 7 retries, regardless of whether
or not the response is a native defer or an I2C defer. Test 4.2.2.5 fails
since there are native defers interspersed with the I2C defers which
results in less than 7 EDID read attempts.

The solution is to add the numer of defers to the retry counter when an I2C
DEFER is returned such that another read attempt will be made. This situation
should normally only occur in compliance testing, however, as a worse case
real-world scenario, it would result in 13 attempts ( 6 native defers, 7 I2C
defers) for a single transaction to complete. The net result is a slightly
slower response to an EDID read that shouldn't significantly impact overall
performance.

V2:
- Added a check on the number of I2C Defers to limit the number
  of times that the retries variable will be decremented. This
  is to address review feedback regarding possible infinite loops
  from misbehaving sink devices.
V3:
- Fixed the limit value to 7 instead of 8 to get the correct retry
  count.
- Combined the increment of the defer count into the if-statement
V4:
- Removed i915 tag from subject as the patch is not i915-specific
V5:
- Updated the for-loop to add the number of i2c defers to the retry
  counter such that the correct number of retry attempts will be
  made

Signed-off-by: Todd Previte <tprevite@gmail.com>
Cc: dri-devel@lists.freedesktop.org
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/gpu/drm/drm_dp_helper.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index 71dcbc6..7f0356e 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -432,7 +432,7 @@ static u32 drm_dp_i2c_functionality(struct i2c_adapter *adapter)
  */
 static int drm_dp_i2c_do_msg(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg)
 {
-	unsigned int retry;
+	unsigned int retry, defer_i2c;
 	int ret;
 
 	/*
@@ -440,7 +440,7 @@ static int drm_dp_i2c_do_msg(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg)
 	 * is required to retry at least seven times upon receiving AUX_DEFER
 	 * before giving up the AUX transaction.
 	 */
-	for (retry = 0; retry < 7; retry++) {
+	for (retry = 0, defer_i2c = 0; retry < (7 + defer_i2c); retry++) {
 		mutex_lock(&aux->hw_mutex);
 		ret = aux->transfer(aux, msg);
 		mutex_unlock(&aux->hw_mutex);
@@ -499,7 +499,13 @@ static int drm_dp_i2c_do_msg(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg)
 
 		case DP_AUX_I2C_REPLY_DEFER:
 			DRM_DEBUG_KMS("I2C defer\n");
+			/* DP Compliance Test 4.2.2.5 Requirement:
+			 * Must have at least 7 retries for I2C defers on the
+			 * transaction to pass this test
+			 */
 			aux->i2c_defer_count++;
+			if (defer_i2c < 7)
+				defer_i2c++;
 			usleep_range(400, 500);
 			continue;
 
-- 
2.5.0

[added to the 4.1 stable tree] drm/udl: Use unlocked gem unreferencing

[Sasha Levin]

From: Daniel Vetter <daniel.vetter@ffwll.ch>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 72b9ff0612ad8fc969b910cd00ac16b57a1a9ba4 ]

For drm_gem_object_unreference callers are required to hold
dev->struct_mutex, which these paths don't. Enforcing this requirement
has become a bit more strict with

commit ef4c6270bf2867e2f8032e9614d1a8cfc6c71663
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date:   Thu Oct 15 09:36:25 2015 +0200

    drm/gem: Check locking in drm_gem_object_unreference

Cc: stable@vger.kernel.org
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/gpu/drm/udl/udl_fb.c  | 2 +-
 drivers/gpu/drm/udl/udl_gem.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/udl/udl_fb.c b/drivers/gpu/drm/udl/udl_fb.c
index 5fc16ce..cd8d183 100644
--- a/drivers/gpu/drm/udl/udl_fb.c
+++ b/drivers/gpu/drm/udl/udl_fb.c
@@ -546,7 +546,7 @@ static int udlfb_create(struct drm_fb_helper *helper,
 
 	return ret;
 out_gfree:
-	drm_gem_object_unreference(&ufbdev->ufb.obj->base);
+	drm_gem_object_unreference_unlocked(&ufbdev->ufb.obj->base);
 out:
 	return ret;
 }
diff --git a/drivers/gpu/drm/udl/udl_gem.c b/drivers/gpu/drm/udl/udl_gem.c
index 2a0a784..d7528e0 100644
--- a/drivers/gpu/drm/udl/udl_gem.c
+++ b/drivers/gpu/drm/udl/udl_gem.c
@@ -52,7 +52,7 @@ udl_gem_create(struct drm_file *file,
 		return ret;
 	}
 
-	drm_gem_object_unreference(&obj->base);
+	drm_gem_object_unreference_unlocked(&obj->base);
 	*handle_p = handle;
 	return 0;
 }
-- 
2.5.0

[added to the 4.1 stable tree] drm/radeon: add a dpm quirk for sapphire Dual-X R7 370 2G D5

[Sasha Levin]

From: Alex Deucher <alexander.deucher@amd.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit f971f2263deaa4a441e377b385c11aee0f3b3f9a ]

bug:
https://bugs.freedesktop.org/show_bug.cgi?id=94692

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/gpu/drm/radeon/si_dpm.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index c4e0e69..27e8bae 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -2925,6 +2925,7 @@ static struct si_dpm_quirk si_dpm_quirk_list[] = {
 	/* PITCAIRN - https://bugs.freedesktop.org/show_bug.cgi?id=76490 */
 	{ PCI_VENDOR_ID_ATI, 0x6810, 0x1462, 0x3036, 0, 120000 },
 	{ PCI_VENDOR_ID_ATI, 0x6811, 0x174b, 0xe271, 0, 120000 },
+	{ PCI_VENDOR_ID_ATI, 0x6811, 0x174b, 0x2015, 0, 120000 },
 	{ PCI_VENDOR_ID_ATI, 0x6810, 0x174b, 0xe271, 85000, 90000 },
 	{ PCI_VENDOR_ID_ATI, 0x6811, 0x1762, 0x2015, 0, 120000 },
 	{ PCI_VENDOR_ID_ATI, 0x6811, 0x1043, 0x2015, 0, 120000 },
-- 
2.5.0

[added to the 4.1 stable tree] drm/radeon: add a dpm quirk for all R7 370 parts

[Sasha Levin]

From: Alex Deucher <alexander.deucher@amd.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 0e5585dc870af947fab2af96a88c2d8b4270247c ]

Higher mclk values are not stable due to a bug somewhere.
Limit them for now.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/gpu/drm/radeon/si_dpm.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index 27e8bae..f666277 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -2960,6 +2960,10 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev,
 		}
 		++p;
 	}
+	/* limit mclk on all R7 370 parts for stability */
+	if (rdev->pdev->device == 0x6811 &&
+	    rdev->pdev->revision == 0x81)
+		max_mclk = 120000;
 
 	if ((rdev->pm.dpm.new_active_crtc_count > 1) ||
 	    ni_dpm_vblank_too_short(rdev))
-- 
2.5.0

[added to the 4.1 stable tree] tcp: convert cached rtt from usec to jiffies when feeding initial rto

[Sasha Levin]

From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 9bdfb3b79e61c60e1a3e2dc05ad164528afa6b8a ]

Currently it's converted into msecs, thus HZ=1000 intact.

Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Fixes: 740b0f1841f6 ("tcp: switch rtt estimations to usec resolution")
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/ipv4/tcp_metrics.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index a51d63a..9c840c5 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -566,7 +566,7 @@ reset:
 	 */
 	if (crtt > tp->srtt_us) {
 		/* Set RTO like tcp_rtt_estimator(), but from cached RTT. */
-		crtt /= 8 * USEC_PER_MSEC;
+		crtt /= 8 * USEC_PER_SEC / HZ;
 		inet_csk(sk)->icsk_rto = crtt + max(2 * crtt, tcp_rto_min(sk));
 	} else if (tp->srtt_us == 0) {
 		/* RFC6298: 5.7 We've failed to get a valid RTT sample from
-- 
2.5.0

[added to the 4.1 stable tree] tunnel: Clear IPCB(skb)->opt before dst_link_failure called

[Sasha Levin]

From: Bernie Harris <bernie.harris@alliedtelesis.co.nz>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 5146d1f151122e868e594c7b45115d64825aee5f ]

IPCB may contain data from previous layers (in the observed case the
qdisc layer). In the observed scenario, the data was misinterpreted as
ip header options, which later caused the ihl to be set to an invalid
value (<5). This resulted in an infinite loop in the mips implementation
of ip_fast_csum.

This patch clears IPCB(skb)->opt before dst_link_failure can be called for
various types of tunnels. This change only applies to encapsulated ipv4
packets.

The code introduced in 11c21a30 which clears all of IPCB has been removed
to be consistent with these changes, and instead the opt field is cleared
unconditionally in ip_tunnel_xmit. The change in ip_tunnel_xmit applies to
SIT, GRE, and IPIP tunnels.

The relevant vti, l2tp, and pptp functions already contain similar code for
clearing the IPCB.

Signed-off-by: Bernie Harris <bernie.harris@alliedtelesis.co.nz>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/ipv4/ip_tunnel.c  | 3 ++-
 net/ipv4/udp_tunnel.c | 2 ++
 net/ipv6/ip6_gre.c    | 2 ++
 net/ipv6/ip6_tunnel.c | 2 ++
 4 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 626d9e5..35080a7 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -652,6 +652,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
 	connected = (tunnel->parms.iph.daddr != 0);
 
+	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+
 	dst = tnl_params->daddr;
 	if (dst == 0) {
 		/* NBMA tunnel */
@@ -749,7 +751,6 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 				tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
 			tunnel->err_count--;
 
-			memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 			dst_link_failure(skb);
 		} else
 			tunnel->err_count = 0;
diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c
index 6bb98cc..7b534ac 100644
--- a/net/ipv4/udp_tunnel.c
+++ b/net/ipv4/udp_tunnel.c
@@ -90,6 +90,8 @@ int udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb,
 	uh->source = src_port;
 	uh->len = htons(skb->len);
 
+	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+
 	udp_set_csum(nocheck, skb, src, dst, skb->len);
 
 	return iptunnel_xmit(sk, rt, skb, src, dst, IPPROTO_UDP,
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 76be7d3..b1311da 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -783,6 +783,8 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev)
 	__u32 mtu;
 	int err;
 
+	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+
 	if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
 		encap_limit = t->parms.encap_limit;
 
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 5cafd92..6fd0f96 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1124,6 +1124,8 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	u8 tproto;
 	int err;
 
+	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+
 	tproto = ACCESS_ONCE(t->parms.proto);
 	if (tproto != IPPROTO_IPIP && tproto != 0)
 		return -1;
-- 
2.5.0

[added to the 4.1 stable tree] net: jme: fix suspend/resume on JMC260

[Sasha Levin]

From: Diego Viola <diego.viola@gmail.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit ee50c130c82175eaa0820c96b6d3763928af2241 ]

The JMC260 network card fails to suspend/resume because the call to
jme_start_irq() was too early, moving the call to jme_start_irq() after
the call to jme_reset_link() makes it work.

Prior this change suspend/resume would fail unless /sys/power/pm_async=0
was explicitly specified.

Relevant bug report: https://bugzilla.kernel.org/show_bug.cgi?id=112351

Signed-off-by: Diego Viola <diego.viola@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/net/ethernet/jme.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c
index 6e9a792..32d240b 100644
--- a/drivers/net/ethernet/jme.c
+++ b/drivers/net/ethernet/jme.c
@@ -3316,13 +3316,14 @@ jme_resume(struct device *dev)
 		jme_reset_phy_processor(jme);
 	jme_phy_calibration(jme);
 	jme_phy_setEA(jme);
-	jme_start_irq(jme);
 	netif_device_attach(netdev);
 
 	atomic_inc(&jme->link_changing);
 
 	jme_reset_link(jme);
 
+	jme_start_irq(jme);
+
 	return 0;
 }
 
-- 
2.5.0

[added to the 4.1 stable tree] net: qca_spi: Don't clear IFF_BROADCAST

[Sasha Levin]

From: Stefan Wahren <stefan.wahren@i2se.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 2b70bad23c89b121a3e4a00f8968d14ebb78887d ]

Currently qcaspi_netdev_setup accidentally clears IFF_BROADCAST.
So fix this by keeping the flags from ether_setup.

Reported-by: Michael Heimpold <michael.heimpold@i2se.com>
Signed-off-by: Stefan Wahren <stefan.wahren@i2se.com>
Fixes: 291ab06ecf67 (net: qualcomm: new Ethernet over SPI driver for QCA7000)
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/net/ethernet/qualcomm/qca_spi.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
index 97e4df9..412715c 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.c
+++ b/drivers/net/ethernet/qualcomm/qca_spi.c
@@ -811,7 +811,6 @@ qcaspi_netdev_setup(struct net_device *dev)
 	dev->netdev_ops = &qcaspi_netdev_ops;
 	qcaspi_set_ethtool_ops(dev);
 	dev->watchdog_timeo = QCASPI_TX_TIMEOUT;
-	dev->flags = IFF_MULTICAST;
 	dev->tx_queue_len = 100;
 
 	qca = netdev_priv(dev);
-- 
2.5.0

[added to the 4.1 stable tree] net: qca_spi: clear IFF_TX_SKB_SHARING

[Sasha Levin]

From: Stefan Wahren <stefan.wahren@i2se.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit a4690afeb0d2d7ba4d60dfa98a89f3bb1ce60ecd ]

ether_setup sets IFF_TX_SKB_SHARING but this is not supported by
qca_spi as it modifies the skb on xmit.

Signed-off-by: Stefan Wahren <stefan.wahren@i2se.com>
Fixes: 291ab06ecf67 (net: qualcomm: new Ethernet over SPI driver for QCA7000)
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/net/ethernet/qualcomm/qca_spi.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
index 412715c..cba4186 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.c
+++ b/drivers/net/ethernet/qualcomm/qca_spi.c
@@ -811,6 +811,7 @@ qcaspi_netdev_setup(struct net_device *dev)
 	dev->netdev_ops = &qcaspi_netdev_ops;
 	qcaspi_set_ethtool_ops(dev);
 	dev->watchdog_timeo = QCASPI_TX_TIMEOUT;
+	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	dev->tx_queue_len = 100;
 
 	qca = netdev_priv(dev);
-- 
2.5.0

[added to the 4.1 stable tree] sctp: lack the check for ports in sctp_v6_cmp_addr

[Sasha Levin]

From: Xin Long <lucien.xin@gmail.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 40b4f0fd74e46c017814618d67ec9127ff20f157 ]

As the member .cmp_addr of sctp_af_inet6, sctp_v6_cmp_addr should also check
the port of addresses, just like sctp_v4_cmp_addr, cause it's invoked by
sctp_cmp_addr_exact().

Now sctp_v6_cmp_addr just check the port when two addresses have different
family, and lack the port check for two ipv6 addresses. that will make
sctp_hash_cmp() cannot work well.

so fix it by adding ports comparison in sctp_v6_cmp_addr().

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/sctp/ipv6.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 3267a5c..18361cb 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -519,6 +519,8 @@ static int sctp_v6_cmp_addr(const union sctp_addr *addr1,
 		}
 		return 0;
 	}
+	if (addr1->v6.sin6_port != addr2->v6.sin6_port)
+		return 0;
 	if (!ipv6_addr_equal(&addr1->v6.sin6_addr, &addr2->v6.sin6_addr))
 		return 0;
 	/* If this is a linklocal address, compare the scope_id. */
-- 
2.5.0

[added to the 4.1 stable tree] mld, igmp: Fix reserved tailroom calculation

[Sasha Levin]

From: Benjamin Poirier <bpoirier@suse.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 1837b2e2bcd23137766555a63867e649c0b637f0 ]

The current reserved_tailroom calculation fails to take hlen and tlen into
account.

skb:
[__hlen__|__data____________|__tlen___|__extra__]
^                                               ^
head                                            skb_end_offset

In this representation, hlen + data + tlen is the size passed to alloc_skb.
"extra" is the extra space made available in __alloc_skb because of
rounding up by kmalloc. We can reorder the representation like so:

[__hlen__|__data____________|__extra__|__tlen___]
^                                               ^
head                                            skb_end_offset

The maximum space available for ip headers and payload without
fragmentation is min(mtu, data + extra). Therefore,
reserved_tailroom
= data + extra + tlen - min(mtu, data + extra)
= skb_end_offset - hlen - min(mtu, skb_end_offset - hlen - tlen)
= skb_tailroom - min(mtu, skb_tailroom - tlen) ; after skb_reserve(hlen)

Compare the second line to the current expression:
reserved_tailroom = skb_end_offset - min(mtu, skb_end_offset)
and we can see that hlen and tlen are not taken into account.

The min() in the third line can be expanded into:
if mtu < skb_tailroom - tlen:
	reserved_tailroom = skb_tailroom - mtu
else:
	reserved_tailroom = tlen

Depending on hlen, tlen, mtu and the number of multicast address records,
the current code may output skbs that have less tailroom than
dev->needed_tailroom or it may output more skbs than needed because not all
space available is used.

Fixes: 4c672e4b ("ipv6: mld: fix add_grhead skb_over_panic for devs with large MTUs")
Signed-off-by: Benjamin Poirier <bpoirier@suse.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 include/linux/skbuff.h | 24 ++++++++++++++++++++++++
 net/ipv4/igmp.c        |  3 +--
 net/ipv6/mcast.c       |  3 +--
 3 files changed, 26 insertions(+), 4 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 6633b0c..ca2e26a 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1781,6 +1781,30 @@ static inline void skb_reserve(struct sk_buff *skb, int len)
 	skb->tail += len;
 }
 
+/**
+ *	skb_tailroom_reserve - adjust reserved_tailroom
+ *	@skb: buffer to alter
+ *	@mtu: maximum amount of headlen permitted
+ *	@needed_tailroom: minimum amount of reserved_tailroom
+ *
+ *	Set reserved_tailroom so that headlen can be as large as possible but
+ *	not larger than mtu and tailroom cannot be smaller than
+ *	needed_tailroom.
+ *	The required headroom should already have been reserved before using
+ *	this function.
+ */
+static inline void skb_tailroom_reserve(struct sk_buff *skb, unsigned int mtu,
+					unsigned int needed_tailroom)
+{
+	SKB_LINEAR_ASSERT(skb);
+	if (mtu < skb_tailroom(skb) - needed_tailroom)
+		/* use at most mtu */
+		skb->reserved_tailroom = skb_tailroom(skb) - mtu;
+	else
+		/* use up to all available space */
+		skb->reserved_tailroom = needed_tailroom;
+}
+
 #define ENCAP_TYPE_ETHER	0
 #define ENCAP_TYPE_IPPROTO	1
 
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index a3a697f..218abf9 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -353,9 +353,8 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu)
 	skb_dst_set(skb, &rt->dst);
 	skb->dev = dev;
 
-	skb->reserved_tailroom = skb_end_offset(skb) -
-				 min(mtu, skb_end_offset(skb));
 	skb_reserve(skb, hlen);
+	skb_tailroom_reserve(skb, mtu, tlen);
 
 	skb_reset_network_header(skb);
 	pip = ip_hdr(skb);
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 41e3b5e..9a63110 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1574,9 +1574,8 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu)
 		return NULL;
 
 	skb->priority = TC_PRIO_CONTROL;
-	skb->reserved_tailroom = skb_end_offset(skb) -
-				 min(mtu, skb_end_offset(skb));
 	skb_reserve(skb, hlen);
+	skb_tailroom_reserve(skb, mtu, tlen);
 
 	if (__ipv6_get_lladdr(idev, &addr_buf, IFA_F_TENTATIVE)) {
 		/* <draft-ietf-magma-mld-source-05.txt>:
-- 
2.5.0

[added to the 4.1 stable tree] qmi_wwan: add Sierra Wireless EM74xx device ID

[Sasha Levin]

From: Bjørn Mork <bjorn@mork.no>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit bf13c94ccb33c3182efc92ce4989506a0f541243 ]

The MC74xx and EM74xx modules use different IDs by default, according
to the Lenovo EM7455 driver for Windows.

Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/net/usb/qmi_wwan.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index cffb252..8677c6a 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -767,8 +767,10 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1199, 0x9061, 8)},	/* Sierra Wireless Modem */
 	{QMI_FIXED_INTF(0x1199, 0x9070, 8)},	/* Sierra Wireless MC74xx/EM74xx */
 	{QMI_FIXED_INTF(0x1199, 0x9070, 10)},	/* Sierra Wireless MC74xx/EM74xx */
-	{QMI_FIXED_INTF(0x1199, 0x9071, 8)},	/* Sierra Wireless MC74xx/EM74xx */
-	{QMI_FIXED_INTF(0x1199, 0x9071, 10)},	/* Sierra Wireless MC74xx/EM74xx */
+	{QMI_FIXED_INTF(0x1199, 0x9071, 8)},	/* Sierra Wireless MC74xx */
+	{QMI_FIXED_INTF(0x1199, 0x9071, 10)},	/* Sierra Wireless MC74xx */
+	{QMI_FIXED_INTF(0x1199, 0x9079, 8)},	/* Sierra Wireless EM74xx */
+	{QMI_FIXED_INTF(0x1199, 0x9079, 10)},	/* Sierra Wireless EM74xx */
 	{QMI_FIXED_INTF(0x1bbb, 0x011e, 4)},	/* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */
 	{QMI_FIXED_INTF(0x1bbb, 0x0203, 2)},	/* Alcatel L800MA */
 	{QMI_FIXED_INTF(0x2357, 0x0201, 4)},	/* TP-LINK HSUPA Modem MA180 */
-- 
2.5.0

[added to the 4.1 stable tree] ipv6: re-enable fragment header matching in ipv6_find_hdr

[Sasha Levin]

From: Florian Westphal <fw@strlen.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 5d150a985520bbe3cb2aa1ceef24a7e32f20c15f ]

When ipv6_find_hdr is used to find a fragment header
(caller specifies target NEXTHDR_FRAGMENT) we erronously return
-ENOENT for all fragments with nonzero offset.

Before commit 9195bb8e381d, when target was specified, we did not
enter the exthdr walk loop as nexthdr == target so this used to work.

Now we do (so we can skip empty route headers). When we then stumble upon
a frag with nonzero frag_off we must return -ENOENT ("header not found")
only if the caller did not specifically request NEXTHDR_FRAGMENT.

This allows nfables exthdr expression to match ipv6 fragments, e.g. via

nft add rule ip6 filter input frag frag-off gt 0

Fixes: 9195bb8e381d ("ipv6: improve ipv6_find_hdr() to skip empty routing headers")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/ipv6/exthdrs_core.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c
index 5c5d23e..9508a20 100644
--- a/net/ipv6/exthdrs_core.c
+++ b/net/ipv6/exthdrs_core.c
@@ -257,7 +257,11 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
 						*fragoff = _frag_off;
 					return hp->nexthdr;
 				}
-				return -ENOENT;
+				if (!found)
+					return -ENOENT;
+				if (fragoff)
+					*fragoff = _frag_off;
+				break;
 			}
 			hdrlen = 8;
 		} else if (nexthdr == NEXTHDR_AUTH) {
-- 
2.5.0

[added to the 4.1 stable tree] cdc_ncm: toggle altsetting to force reset before setup

[Sasha Levin]

From: Bjørn Mork <bjorn@mork.no>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 48906f62c96cc2cd35753e59310cb70eb08cc6a5 ]

Some devices will silently fail setup unless they are reset first.
This is necessary even if the data interface is already in
altsetting 0, which it will be when the device is probed for the
first time.  Briefly toggling the altsetting forces a function
reset regardless of the initial state.

This fixes a setup problem observed on a number of Huawei devices,
appearing to operate in NTB-32 mode even if we explicitly set them
to NTB-16 mode.

Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/net/usb/cdc_ncm.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 0b481c3..5db25e4 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -843,7 +843,11 @@ advance:
 
 	iface_no = ctx->data->cur_altsetting->desc.bInterfaceNumber;
 
-	/* reset data interface */
+	/* Reset data interface. Some devices will not reset properly
+	 * unless they are configured first.  Toggle the altsetting to
+	 * force a reset
+	 */
+	usb_set_interface(dev->udev, iface_no, data_altsetting);
 	temp = usb_set_interface(dev->udev, iface_no, 0);
 	if (temp) {
 		dev_dbg(&intf->dev, "set interface failed\n");
-- 
2.5.0

[added to the 4.1 stable tree] usbnet: cleanup after bind() in probe()

[Sasha Levin]

From: Oliver Neukum <oneukum@suse.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 1666984c8625b3db19a9abc298931d35ab7bc64b ]

In case bind() works, but a later error forces bailing
in probe() in error cases work and a timer may be scheduled.
They must be killed. This fixes an error case related to
the double free reported in
http://www.spinics.net/lists/netdev/msg367669.html
and needs to go on top of Linus' fix to cdc-ncm.

Signed-off-by: Oliver Neukum <ONeukum@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/net/usb/usbnet.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index e049857..edbb2f3 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -1754,6 +1754,13 @@ out3:
 	if (info->unbind)
 		info->unbind (dev, udev);
 out1:
+	/* subdrivers must undo all they did in bind() if they
+	 * fail it, but we may fail later and a deferred kevent
+	 * may trigger an error resubmitting itself and, worse,
+	 * schedule a timer. So we kill it all just in case.
+	 */
+	cancel_work_sync(&dev->kevent);
+	del_timer_sync(&dev->delay);
 	free_netdev(net);
 out:
 	return status;
-- 
2.5.0

[added to the 4.1 stable tree] udp6: fix UDP/IPv6 encap resubmit path

[Sasha Levin]

From: Bill Sommerfeld <wsommerfeld@google.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 59dca1d8a6725a121dae6c452de0b2611d5865dc ]

IPv4 interprets a negative return value from a protocol handler as a
request to redispatch to a new protocol.  In contrast, IPv6 interprets a
negative value as an error, and interprets a positive value as a request
for redispatch.

UDP for IPv6 was unaware of this difference.  Change __udp6_lib_rcv() to
return a positive value for redispatch.  Note that the socket's
encap_rcv hook still needs to return a negative value to request
dispatch, and in the case of IPv6 packets, adjust IP6CB(skb)->nhoff to
identify the byte containing the next protocol.

Signed-off-by: Bill Sommerfeld <wsommerfeld@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/ipv6/udp.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 7333f35..d28b2a1 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -913,11 +913,9 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 		ret = udpv6_queue_rcv_skb(sk, skb);
 		sock_put(sk);
 
-		/* a return value > 0 means to resubmit the input, but
-		 * it wants the return to be -protocol, or 0
-		 */
+		/* a return value > 0 means to resubmit the input */
 		if (ret > 0)
-			return -ret;
+			return ret;
 
 		return 0;
 	}
-- 
2.5.0

[added to the 4.1 stable tree] packet: Allow packets with only a header (but no payload)

[Sasha Levin]

From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 880621c2605b82eb5af91a2c94223df6f5a3fb64 ]

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>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 include/linux/netdevice.h | 3 ++-
 net/packet/af_packet.c    | 4 ++--
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 05b9a69..f6e5cad 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1372,7 +1372,8 @@ 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 ebc39e6..738c8ba 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2112,8 +2112,8 @@ 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;
 	}
-- 
2.5.0

[added to the 4.1 stable tree] net: validate variable length ll headers

[Sasha Levin]

From: Willem de Bruijn <willemb@google.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 2793a23aacbd754dbbb5cb75093deb7e4103bace ]

Netdevice parameter hard_header_len is variously interpreted both as
an upper and lower bound on link layer header length. The field is
used as upper bound when reserving room at allocation, as lower bound
when validating user input in PF_PACKET.

Clarify the definition to be maximum header length. For validation
of untrusted headers, add an optional validate member to header_ops.

Allow bypassing of validation by passing CAP_SYS_RAWIO, for instance
for deliberate testing of corrupt input. In this case, pad trailing
bytes, as some device drivers expect completely initialized headers.

See also http://comments.gmane.org/gmane.linux.network/401064

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 include/linux/netdevice.h | 22 ++++++++++++++++++++--
 1 file changed, 20 insertions(+), 2 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index f6e5cad..6c86c7e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -265,6 +265,7 @@ struct header_ops {
 	void	(*cache_update)(struct hh_cache *hh,
 				const struct net_device *dev,
 				const unsigned char *haddr);
+	bool	(*validate)(const char *ll_header, unsigned int len);
 };
 
 /* These flag bits are private to the generic network queueing
@@ -1372,8 +1373,7 @@ enum netdev_priv_flags {
  *	@dma:		DMA channel
  *	@mtu:		Interface MTU value
  *	@type:		Interface hardware type
- *	@hard_header_len: Hardware header length, which means that this is the
- *			  minimum size of a packet.
+ *	@hard_header_len: Maximum hardware header length.
  *
  *	@needed_headroom: Extra headroom the hardware may need, but not in all
  *			  cases can this be guaranteed
@@ -2417,6 +2417,24 @@ static inline int dev_parse_header(const struct sk_buff *skb,
 	return dev->header_ops->parse(skb, haddr);
 }
 
+/* ll_header must have at least hard_header_len allocated */
+static inline bool dev_validate_header(const struct net_device *dev,
+				       char *ll_header, int len)
+{
+	if (likely(len >= dev->hard_header_len))
+		return true;
+
+	if (capable(CAP_SYS_RAWIO)) {
+		memset(ll_header + len, 0, dev->hard_header_len - len);
+		return true;
+	}
+
+	if (dev->header_ops && dev->header_ops->validate)
+		return dev->header_ops->validate(ll_header, len);
+
+	return false;
+}
+
 typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr, int len);
 int register_gifconf(unsigned int family, gifconf_func_t *gifconf);
 static inline int unregister_gifconf(unsigned int family)
-- 
2.5.0

[added to the 4.1 stable tree] ax25: add link layer header validation function

[Sasha Levin]

From: Willem de Bruijn <willemb@google.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit ea47781c26510e5d97f80f9aceafe9065bd5e3aa ]

As variable length protocol, AX25 fails link layer header validation
tests based on a minimum length. header_ops.validate allows protocols
to validate headers that are shorter than hard_header_len. Implement
this callback for AX25.

See also http://comments.gmane.org/gmane.linux.network/401064

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/ax25/ax25_ip.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/net/ax25/ax25_ip.c b/net/ax25/ax25_ip.c
index 7c646bb..98d206b 100644
--- a/net/ax25/ax25_ip.c
+++ b/net/ax25/ax25_ip.c
@@ -229,8 +229,23 @@ netdev_tx_t ax25_ip_xmit(struct sk_buff *skb)
 }
 #endif
 
+static bool ax25_validate_header(const char *header, unsigned int len)
+{
+	ax25_digi digi;
+
+	if (!len)
+		return false;
+
+	if (header[0])
+		return true;
+
+	return ax25_addr_parse(header + 1, len - 1, NULL, NULL, &digi, NULL,
+			       NULL);
+}
+
 const struct header_ops ax25_header_ops = {
 	.create = ax25_hard_header,
+	.validate = ax25_validate_header,
 };
 
 EXPORT_SYMBOL(ax25_header_ops);
-- 
2.5.0

[added to the 4.1 stable tree] packet: validate variable length ll headers

[Sasha Levin]

From: Willem de Bruijn <willemb@google.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 9ed988cd591500c040b2a6257bc68543e08ceeef ]

Replace link layer header validation check ll_header_truncate with
more generic dev_validate_header.

Validation based on hard_header_len incorrectly drops valid packets
in variable length protocols, such as AX25. dev_validate_header
calls header_ops.validate for such protocols to ensure correctness
below hard_header_len.

See also http://comments.gmane.org/gmane.linux.network/401064

Fixes 9c7077622dd9 ("packet: make packet_snd fail on len smaller than l2 header")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/packet/af_packet.c | 37 ++++++++++++++++---------------------
 1 file changed, 16 insertions(+), 21 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 738c8ba..68a04847 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1699,6 +1699,10 @@ retry:
 		goto retry;
 	}
 
+	if (!dev_validate_header(dev, skb->data, len)) {
+		err = -EINVAL;
+		goto out_unlock;
+	}
 	if (len > (dev->mtu + dev->hard_header_len + extra_len) &&
 	    !packet_extra_vlan_len_allowed(dev, skb)) {
 		err = -EMSGSIZE;
@@ -2109,18 +2113,6 @@ static void tpacket_destruct_skb(struct sk_buff *skb)
 	sock_wfree(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",
-				     current->comm, len, dev->hard_header_len);
-		return true;
-	}
-
-	return false;
-}
-
 static void tpacket_set_protocol(const struct net_device *dev,
 				 struct sk_buff *skb)
 {
@@ -2203,19 +2195,19 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 		if (unlikely(err < 0))
 			return -EINVAL;
 	} else if (dev->hard_header_len) {
-		if (ll_header_truncated(dev, tp_len))
-			return -EINVAL;
+		int hdrlen = min_t(int, dev->hard_header_len, tp_len);
 
 		skb_push(skb, dev->hard_header_len);
-		err = skb_store_bits(skb, 0, data,
-				dev->hard_header_len);
+		err = skb_store_bits(skb, 0, data, hdrlen);
 		if (unlikely(err))
 			return err;
+		if (!dev_validate_header(dev, skb->data, hdrlen))
+			return -EINVAL;
 		if (!skb->protocol)
 			tpacket_set_protocol(dev, skb);
 
-		data += dev->hard_header_len;
-		to_write -= dev->hard_header_len;
+		data += hdrlen;
+		to_write -= hdrlen;
 	}
 
 	offset = offset_in_page(data);
@@ -2538,9 +2530,6 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		offset = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, len);
 		if (unlikely(offset < 0))
 			goto out_free;
-	} else {
-		if (ll_header_truncated(dev, len))
-			goto out_free;
 	}
 
 	/* Returns -EFAULT on error */
@@ -2548,6 +2537,12 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	if (err)
 		goto out_free;
 
+	if (sock->type == SOCK_RAW &&
+	    !dev_validate_header(dev, skb->data, len)) {
+		err = -EINVAL;
+		goto out_free;
+	}
+
 	sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags);
 
 	if (!gso_type && (len > dev->mtu + reserve + extra_len) &&
-- 
2.5.0

[added to the 4.1 stable tree] sh_eth: fix NULL pointer dereference in sh_eth_ring_format()

[Sasha Levin]

From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit c1b7fca65070bfadca94dd53a4e6b71cd4f69715 ]

In a low memory situation, if netdev_alloc_skb() fails on a first RX ring
loop iteration  in sh_eth_ring_format(), 'rxdesc' is still NULL.  Avoid
kernel oops by adding the 'rxdesc' check after the loop.

Reported-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/net/ethernet/renesas/sh_eth.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 13463c4..51eff9f 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -1173,7 +1173,8 @@ static void sh_eth_ring_format(struct net_device *ndev)
 	mdp->dirty_rx = (u32) (i - mdp->num_rx_ring);
 
 	/* Mark the last entry as wrapping the ring. */
-	rxdesc->status |= cpu_to_edmac(mdp, RD_RDEL);
+	if (rxdesc)
+		rxdesc->status |= cpu_to_edmac(mdp, RD_RDEL);
 
 	memset(mdp->tx_ring, 0, tx_ringsize);
 
-- 
2.5.0

[added to the 4.1 stable tree] sh_eth: fix RX buffer size alignment

[Sasha Levin]

From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit ab8579169b79c062935dade949287113c7c1ba73 ]

Both  Renesas R-Car and RZ/A1 manuals state that RX buffer  length must be
a multiple of 32 bytes, while the driver  only uses 16 byte granularity...

Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/net/ethernet/renesas/sh_eth.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 51eff9f..c93a458 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -1148,8 +1148,8 @@ static void sh_eth_ring_format(struct net_device *ndev)
 
 		/* RX descriptor */
 		rxdesc = &mdp->rx_ring[i];
-		/* The size of the buffer is a multiple of 16 bytes. */
-		rxdesc->buffer_length = ALIGN(mdp->rx_buf_sz, 16);
+		/* The size of the buffer is a multiple of 32 bytes. */
+		rxdesc->buffer_length = ALIGN(mdp->rx_buf_sz, 32);
 		dma_addr = dma_map_single(&ndev->dev, skb->data,
 					  rxdesc->buffer_length,
 					  DMA_FROM_DEVICE);
@@ -1507,7 +1507,7 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota)
 			if (mdp->cd->rpadir)
 				skb_reserve(skb, NET_IP_ALIGN);
 			dma_unmap_single(&ndev->dev, rxdesc->addr,
-					 ALIGN(mdp->rx_buf_sz, 16),
+					 ALIGN(mdp->rx_buf_sz, 32),
 					 DMA_FROM_DEVICE);
 			skb_put(skb, pkt_len);
 			skb->protocol = eth_type_trans(skb, ndev);
@@ -1525,8 +1525,8 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota)
 	for (; mdp->cur_rx - mdp->dirty_rx > 0; mdp->dirty_rx++) {
 		entry = mdp->dirty_rx % mdp->num_rx_ring;
 		rxdesc = &mdp->rx_ring[entry];
-		/* The size of the buffer is 16 byte boundary. */
-		rxdesc->buffer_length = ALIGN(mdp->rx_buf_sz, 16);
+		/* The size of the buffer is 32 byte boundary. */
+		rxdesc->buffer_length = ALIGN(mdp->rx_buf_sz, 32);
 
 		if (mdp->rx_skbuff[entry] == NULL) {
 			skb = netdev_alloc_skb(ndev, skbuff_size);
-- 
2.5.0

[added to the 4.1 stable tree] qlcnic: Remove unnecessary usage of atomic_t

[Sasha Levin]

From: Rajesh Borundia <rajesh.borundia@qlogic.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 5bf93251cee1fb66141d1d2eaff86e04a9397bdf ]

o atomic_t usage is incorrect as we are not implementing
any atomicity.

Signed-off-by: Rajesh Borundia <rajesh.borundia@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/net/ethernet/qlogic/qlcnic/qlcnic.h         | 2 +-
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c | 9 ++++-----
 2 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
index f221126..77472de 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
@@ -1099,7 +1099,7 @@ struct qlcnic_mailbox {
 	unsigned long		status;
 	spinlock_t		queue_lock;	/* Mailbox queue lock */
 	spinlock_t		aen_lock;	/* Mailbox response/AEN lock */
-	atomic_t		rsp_status;
+	u32			rsp_status;
 	u32			num_cmds;
 };
 
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
index 840bf36..98ac613 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
@@ -489,7 +489,7 @@ irqreturn_t qlcnic_83xx_clear_legacy_intr(struct qlcnic_adapter *adapter)
 
 static inline void qlcnic_83xx_notify_mbx_response(struct qlcnic_mailbox *mbx)
 {
-	atomic_set(&mbx->rsp_status, QLC_83XX_MBX_RESPONSE_ARRIVED);
+	mbx->rsp_status = QLC_83XX_MBX_RESPONSE_ARRIVED;
 	complete(&mbx->completion);
 }
 
@@ -508,7 +508,7 @@ static void qlcnic_83xx_poll_process_aen(struct qlcnic_adapter *adapter)
 	if (event &  QLCNIC_MBX_ASYNC_EVENT) {
 		__qlcnic_83xx_process_aen(adapter);
 	} else {
-		if (atomic_read(&mbx->rsp_status) != rsp_status)
+		if (mbx->rsp_status != rsp_status)
 			qlcnic_83xx_notify_mbx_response(mbx);
 	}
 out:
@@ -1023,7 +1023,7 @@ static void qlcnic_83xx_process_aen(struct qlcnic_adapter *adapter)
 		if (event &  QLCNIC_MBX_ASYNC_EVENT) {
 			__qlcnic_83xx_process_aen(adapter);
 		} else {
-			if (atomic_read(&mbx->rsp_status) != rsp_status)
+			if (mbx->rsp_status != rsp_status)
 				qlcnic_83xx_notify_mbx_response(mbx);
 		}
 	}
@@ -4025,7 +4025,6 @@ static void qlcnic_83xx_mailbox_worker(struct work_struct *work)
 	struct qlcnic_adapter *adapter = mbx->adapter;
 	struct qlcnic_mbx_ops *mbx_ops = mbx->ops;
 	struct device *dev = &adapter->pdev->dev;
-	atomic_t *rsp_status = &mbx->rsp_status;
 	struct list_head *head = &mbx->cmd_q;
 	struct qlcnic_hardware_context *ahw;
 	struct qlcnic_cmd_args *cmd = NULL;
@@ -4038,7 +4037,7 @@ static void qlcnic_83xx_mailbox_worker(struct work_struct *work)
 			return;
 		}
 
-		atomic_set(rsp_status, QLC_83XX_MBX_RESPONSE_WAIT);
+		mbx->rsp_status = QLC_83XX_MBX_RESPONSE_WAIT;
 
 		spin_lock(&mbx->queue_lock);
 
-- 
2.5.0

[added to the 4.1 stable tree] qlcnic: Fix mailbox completion handling during spurious interrupt

[Sasha Levin]

From: Rajesh Borundia <rajesh.borundia@qlogic.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 819bfe764dceec2f6b4551768453f374b4c60443 ]

o While the driver is in the middle of a MB completion processing
and it receives a spurious MB interrupt, it is mistaken as a good MB
completion interrupt leading to premature completion of the next MB
request. Fix the driver to guard against this by checking the current
state of MB processing and ignore the spurious interrupt.
Also added a stats counter to record this condition.

Signed-off-by: Rajesh Borundia <rajesh.borundia@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/net/ethernet/qlogic/qlcnic/qlcnic.h         |  1 +
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c | 15 +++++++++++----
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c |  3 ++-
 3 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
index 77472de..d099282 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
@@ -567,6 +567,7 @@ struct qlcnic_adapter_stats {
 	u64  tx_dma_map_error;
 	u64  spurious_intr;
 	u64  mac_filter_limit_overrun;
+	u64  mbx_spurious_intr;
 };
 
 /*
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
index 98ac613..dd618d7 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
@@ -2338,9 +2338,9 @@ static void qlcnic_83xx_handle_link_aen(struct qlcnic_adapter *adapter,
 
 static irqreturn_t qlcnic_83xx_handle_aen(int irq, void *data)
 {
+	u32 mask, resp, event, rsp_status = QLC_83XX_MBX_RESPONSE_ARRIVED;
 	struct qlcnic_adapter *adapter = data;
 	struct qlcnic_mailbox *mbx;
-	u32 mask, resp, event;
 	unsigned long flags;
 
 	mbx = adapter->ahw->mailbox;
@@ -2350,10 +2350,14 @@ static irqreturn_t qlcnic_83xx_handle_aen(int irq, void *data)
 		goto out;
 
 	event = readl(QLCNIC_MBX_FW(adapter->ahw, 0));
-	if (event &  QLCNIC_MBX_ASYNC_EVENT)
+	if (event &  QLCNIC_MBX_ASYNC_EVENT) {
 		__qlcnic_83xx_process_aen(adapter);
-	else
-		qlcnic_83xx_notify_mbx_response(mbx);
+	} else {
+		if (mbx->rsp_status != rsp_status)
+			qlcnic_83xx_notify_mbx_response(mbx);
+		else
+			adapter->stats.mbx_spurious_intr++;
+	}
 
 out:
 	mask = QLCRDX(adapter->ahw, QLCNIC_DEF_INT_MASK);
@@ -4028,6 +4032,7 @@ static void qlcnic_83xx_mailbox_worker(struct work_struct *work)
 	struct list_head *head = &mbx->cmd_q;
 	struct qlcnic_hardware_context *ahw;
 	struct qlcnic_cmd_args *cmd = NULL;
+	unsigned long flags;
 
 	ahw = adapter->ahw;
 
@@ -4037,7 +4042,9 @@ static void qlcnic_83xx_mailbox_worker(struct work_struct *work)
 			return;
 		}
 
+		spin_lock_irqsave(&mbx->aen_lock, flags);
 		mbx->rsp_status = QLC_83XX_MBX_RESPONSE_WAIT;
+		spin_unlock_irqrestore(&mbx->aen_lock, flags);
 
 		spin_lock(&mbx->queue_lock);
 
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
index 494e810..0a2318c 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
@@ -59,7 +59,8 @@ static const struct qlcnic_stats qlcnic_gstrings_stats[] = {
 	 QLC_OFF(stats.mac_filter_limit_overrun)},
 	{"spurious intr", QLC_SIZEOF(stats.spurious_intr),
 	 QLC_OFF(stats.spurious_intr)},
-
+	{"mbx spurious intr", QLC_SIZEOF(stats.mbx_spurious_intr),
+	 QLC_OFF(stats.mbx_spurious_intr)},
 };
 
 static const char qlcnic_device_gstrings_stats[][ETH_GSTRING_LEN] = {
-- 
2.5.0

[added to the 4.1 stable tree] macvtap: always pass ethernet header in linear

[Sasha Levin]

From: Willem de Bruijn <willemb@google.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 8e2ad4113ce4671686740f808ff2795395c39eef ]

The stack expects link layer headers in the skb linear section.
Macvtap can create skbs with llheader in frags in edge cases:
when (IFF_VNET_HDR is off or vnet_hdr.hdr_len < ETH_HLEN) and
prepad + len > PAGE_SIZE and vnet_hdr.flags has no or bad csum.

Add checks to ensure linear is always at least ETH_HLEN.
At this point, len is already ensured to be >= ETH_HLEN.

For backwards compatiblity, rounds up short vnet_hdr.hdr_len.
This differs from tap and packet, which return an error.

Fixes b9fb9ee07e67 ("macvtap: add GSO/csum offload support")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/net/macvtap.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 4dba5fb..2b212f3 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -710,6 +710,8 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 			macvtap16_to_cpu(q, vnet_hdr.hdr_len) : GOODCOPY_LEN;
 		if (copylen > good_linear)
 			copylen = good_linear;
+		else if (copylen < ETH_HLEN)
+			copylen = ETH_HLEN;
 		linear = copylen;
 		i = *from;
 		iov_iter_advance(&i, copylen);
@@ -719,10 +721,11 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 
 	if (!zerocopy) {
 		copylen = len;
-		if (macvtap16_to_cpu(q, vnet_hdr.hdr_len) > good_linear)
+		linear = macvtap16_to_cpu(q, vnet_hdr.hdr_len);
+		if (linear > good_linear)
 			linear = good_linear;
-		else
-			linear = macvtap16_to_cpu(q, vnet_hdr.hdr_len);
+		else if (linear < ETH_HLEN)
+			linear = ETH_HLEN;
 	}
 
 	skb = macvtap_alloc_skb(&q->sk, MACVTAP_RESERVE, copylen,
-- 
2.5.0

[added to the 4.1 stable tree] ipv4: Don't do expensive useless work during inetdev destroy.

[Sasha Levin]

From: "David S. Miller" <davem@davemloft.net>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit fbd40ea0180a2d328c5adc61414dc8bab9335ce2 ]

When an inetdev is destroyed, every address assigned to the interface
is removed.  And in this scenerio we do two pointless things which can
be very expensive if the number of assigned interfaces is large:

1) Address promotion.  We are deleting all addresses, so there is no
   point in doing this.

2) A full nf conntrack table purge for every address.  We only need to
   do this once, as is already caught by the existing
   masq_dev_notifier so masq_inet_event() can skip this.

Reported-by: Solar Designer <solar@openwall.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Tested-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/ipv4/devinet.c                          |  4 ++++
 net/ipv4/fib_frontend.c                     |  4 ++++
 net/ipv4/netfilter/nf_nat_masquerade_ipv4.c | 12 ++++++++++--
 3 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 280d46f..a57056d 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -334,6 +334,9 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
 
 	ASSERT_RTNL();
 
+	if (in_dev->dead)
+		goto no_promotions;
+
 	/* 1. Deleting primary ifaddr forces deletion all secondaries
 	 * unless alias promotion is set
 	 **/
@@ -380,6 +383,7 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
 			fib_del_ifaddr(ifa, ifa1);
 	}
 
+no_promotions:
 	/* 2. Unlink it */
 
 	*ifap = ifa1->ifa_next;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 872494e..8776636 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -876,6 +876,9 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim)
 		subnet = 1;
 	}
 
+	if (in_dev->dead)
+		goto no_promotions;
+
 	/* Deletion is more complicated than add.
 	 * We should take care of not to delete too much :-)
 	 *
@@ -951,6 +954,7 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim)
 		}
 	}
 
+no_promotions:
 	if (!(ok & BRD_OK))
 		fib_magic(RTM_DELROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim);
 	if (subnet && ifa->ifa_prefixlen < 31) {
diff --git a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
index c6eb421..ea91058 100644
--- a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
@@ -108,10 +108,18 @@ static int masq_inet_event(struct notifier_block *this,
 			   unsigned long event,
 			   void *ptr)
 {
-	struct net_device *dev = ((struct in_ifaddr *)ptr)->ifa_dev->dev;
+	struct in_device *idev = ((struct in_ifaddr *)ptr)->ifa_dev;
 	struct netdev_notifier_info info;
 
-	netdev_notifier_info_init(&info, dev);
+	/* The masq_dev_notifier will catch the case of the device going
+	 * down.  So if the inetdev is dead and being destroyed we have
+	 * no work to do.  Otherwise this is an individual address removal
+	 * and we have to perform the flush.
+	 */
+	if (idev->dead)
+		return NOTIFY_DONE;
+
+	netdev_notifier_info_init(&info, idev->dev);
 	return masq_device_event(this, event, &info);
 }
 
-- 
2.5.0

[added to the 4.1 stable tree] net: Fix use after free in the recvmmsg exit path

[Sasha Levin]

From: Arnaldo Carvalho de Melo <acme@redhat.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 34b88a68f26a75e4fded796f1a49c40f82234b7d ]

The syzkaller fuzzer hit the following use-after-free:

  Call Trace:
   [<ffffffff8175ea0e>] __asan_report_load8_noabort+0x3e/0x40 mm/kasan/report.c:295
   [<ffffffff851cc31a>] __sys_recvmmsg+0x6fa/0x7f0 net/socket.c:2261
   [<     inline     >] SYSC_recvmmsg net/socket.c:2281
   [<ffffffff851cc57f>] SyS_recvmmsg+0x16f/0x180 net/socket.c:2270
   [<ffffffff86332bb6>] entry_SYSCALL_64_fastpath+0x16/0x7a
  arch/x86/entry/entry_64.S:185

And, as Dmitry rightly assessed, that is because we can drop the
reference and then touch it when the underlying recvmsg calls return
some packets and then hit an error, which will make recvmmsg to set
sock->sk->sk_err, oops, fix it.

Reported-and-Tested-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Kostya Serebryany <kcc@google.com>
Cc: Sasha Levin <sasha.levin@oracle.com>
Fixes: a2e2725541fa ("net: Introduce recvmmsg socket syscall")
http://lkml.kernel.org/r/20160122211644.GC2470@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/socket.c | 38 +++++++++++++++++++-------------------
 1 file changed, 19 insertions(+), 19 deletions(-)

diff --git a/net/socket.c b/net/socket.c
index dcbfa86..e66e4f3 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2247,31 +2247,31 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
 			break;
 	}
 
-out_put:
-	fput_light(sock->file, fput_needed);
-
 	if (err == 0)
-		return datagrams;
+		goto out_put;
 
-	if (datagrams != 0) {
+	if (datagrams == 0) {
+		datagrams = err;
+		goto out_put;
+	}
+
+	/*
+	 * We may return less entries than requested (vlen) if the
+	 * sock is non block and there aren't enough datagrams...
+	 */
+	if (err != -EAGAIN) {
 		/*
-		 * We may return less entries than requested (vlen) if the
-		 * sock is non block and there aren't enough datagrams...
+		 * ... or  if recvmsg returns an error after we
+		 * received some datagrams, where we record the
+		 * error to return on the next call or if the
+		 * app asks about it using getsockopt(SO_ERROR).
 		 */
-		if (err != -EAGAIN) {
-			/*
-			 * ... or  if recvmsg returns an error after we
-			 * received some datagrams, where we record the
-			 * error to return on the next call or if the
-			 * app asks about it using getsockopt(SO_ERROR).
-			 */
-			sock->sk->sk_err = -err;
-		}
-
-		return datagrams;
+		sock->sk->sk_err = -err;
 	}
+out_put:
+	fput_light(sock->file, fput_needed);
 
-	return err;
+	return datagrams;
 }
 
 SYSCALL_DEFINE5(recvmmsg, int, fd, struct mmsghdr __user *, mmsg,
-- 
2.5.0

[added to the 4.1 stable tree] mlx4: add missing braces in verify_qp_parameters

[Sasha Levin]

From: Arnd Bergmann <arnd@arndb.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit baefd7015cdb304ce6c94f9679d0486c71954766 ]

The implementation of QP paravirtualization back in linux-3.7 included
some code that looks very dubious, and gcc-6 has grown smart enough
to warn about it:

drivers/net/ethernet/mellanox/mlx4/resource_tracker.c: In function 'verify_qp_parameters':
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c:3154:5: error: statement is indented as if it were guarded by... [-Werror=misleading-indentation]
     if (optpar & MLX4_QP_OPTPAR_ALT_ADDR_PATH) {
     ^~
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c:3144:4: note: ...this 'if' clause, but it is not
    if (slave != mlx4_master_func_num(dev))

>>From looking at the context, I'm reasonably sure that the indentation
is correct but that it should have contained curly braces from the
start, as the update_gid() function in the same patch correctly does.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Fixes: 54679e148287 ("mlx4: Implement QP paravirtualization and maintain phys_pkey_cache for smp_snoop")
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/net/ethernet/mellanox/mlx4/resource_tracker.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index bafe218..e662ab3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -2960,7 +2960,7 @@ static int verify_qp_parameters(struct mlx4_dev *dev,
 		case QP_TRANS_RTS2RTS:
 		case QP_TRANS_SQD2SQD:
 		case QP_TRANS_SQD2RTS:
-			if (slave != mlx4_master_func_num(dev))
+			if (slave != mlx4_master_func_num(dev)) {
 				if (optpar & MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH) {
 					port = (qp_ctx->pri_path.sched_queue >> 6 & 1) + 1;
 					if (dev->caps.port_mask[port] != MLX4_PORT_TYPE_IB)
@@ -2979,6 +2979,7 @@ static int verify_qp_parameters(struct mlx4_dev *dev,
 					if (qp_ctx->alt_path.mgid_index >= num_gids)
 						return -EINVAL;
 				}
+			}
 			break;
 		default:
 			break;
-- 
2.5.0

[added to the 4.1 stable tree] farsync: fix off-by-one bug in fst_add_one

[Sasha Levin]

From: Arnd Bergmann <arnd@arndb.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit e725a66c0202b5f36c2f9d59d26a65c53bbf21f7 ]

gcc-6 finds an out of bounds access in the fst_add_one function
when calculating the end of the mmio area:

drivers/net/wan/farsync.c: In function 'fst_add_one':
drivers/net/wan/farsync.c:418:53: error: index 2 denotes an offset greater than size of 'u8[2][8192] {aka unsigned char[2][8192]}' [-Werror=array-bounds]
 #define BUF_OFFSET(X)   (BFM_BASE + offsetof(struct buf_window, X))
                                                     ^
include/linux/compiler-gcc.h:158:21: note: in definition of macro '__compiler_offsetof'
  __builtin_offsetof(a, b)
                     ^
drivers/net/wan/farsync.c:418:37: note: in expansion of macro 'offsetof'
 #define BUF_OFFSET(X)   (BFM_BASE + offsetof(struct buf_window, X))
                                     ^~~~~~~~
drivers/net/wan/farsync.c:2519:36: note: in expansion of macro 'BUF_OFFSET'
                                  + BUF_OFFSET ( txBuffer[i][NUM_TX_BUFFER][0]);
                                    ^~~~~~~~~~

The warning is correct, but not critical because this appears
to be a write-only variable that is set by each WAN driver but
never accessed afterwards.

I'm taking the minimal fix here, using the correct pointer by
pointing 'mem_end' to the last byte inside of the register area
as all other WAN drivers do, rather than the first byte outside of
it. An alternative would be to just remove the mem_end member
entirely.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/net/wan/farsync.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wan/farsync.c b/drivers/net/wan/farsync.c
index 44541dbc..69b994f 100644
--- a/drivers/net/wan/farsync.c
+++ b/drivers/net/wan/farsync.c
@@ -2516,7 +2516,7 @@ fst_add_one(struct pci_dev *pdev, const struct pci_device_id *ent)
                 dev->mem_start   = card->phys_mem
                                  + BUF_OFFSET ( txBuffer[i][0][0]);
                 dev->mem_end     = card->phys_mem
-                                 + BUF_OFFSET ( txBuffer[i][NUM_TX_BUFFER][0]);
+                                 + BUF_OFFSET ( txBuffer[i][NUM_TX_BUFFER - 1][LEN_RX_BUFFER - 1]);
                 dev->base_addr   = card->pci_conf;
                 dev->irq         = card->irq;
 
-- 
2.5.0

[added to the 4.1 stable tree] ath9k: fix buffer overrun for ar9287

[Sasha Levin]

From: Arnd Bergmann <arnd@arndb.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 83d6f1f15f8cce844b0a131cbc63e444620e48b5 ]

Code that was added back in 2.6.38 has an obvious overflow
when accessing a static array, and at the time it was added
only a code comment was put in front of it as a reminder
to have it reviewed properly.

This has not happened, but gcc-6 now points to the specific
overflow:

drivers/net/wireless/ath/ath9k/eeprom.c: In function 'ath9k_hw_get_gain_boundaries_pdadcs':
drivers/net/wireless/ath/ath9k/eeprom.c:483:44: error: array subscript is above array bounds [-Werror=array-bounds]
     maxPwrT4[i] = data_9287[idxL].pwrPdg[i][4];
                   ~~~~~~~~~~~~~~~~~~~~~~~~~^~~

It turns out that the correct array length exists in the local
'intercepts' variable of this function, so we can just use that
instead of hardcoding '4', so this patch changes all three
instances to use that variable. The other two instances were
already correct, but it's more consistent this way.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Fixes: 940cd2c12ebf ("ath9k_hw: merge the ar9287 version of ath9k_hw_get_gain_boundaries_pdadcs")
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/net/wireless/ath/ath9k/eeprom.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/eeprom.c b/drivers/net/wireless/ath/ath9k/eeprom.c
index cc81482..113a43f 100644
--- a/drivers/net/wireless/ath/ath9k/eeprom.c
+++ b/drivers/net/wireless/ath/ath9k/eeprom.c
@@ -403,10 +403,9 @@ void ath9k_hw_get_gain_boundaries_pdadcs(struct ath_hw *ah,
 
 	if (match) {
 		if (AR_SREV_9287(ah)) {
-			/* FIXME: array overrun? */
 			for (i = 0; i < numXpdGains; i++) {
 				minPwrT4[i] = data_9287[idxL].pwrPdg[i][0];
-				maxPwrT4[i] = data_9287[idxL].pwrPdg[i][4];
+				maxPwrT4[i] = data_9287[idxL].pwrPdg[i][intercepts - 1];
 				ath9k_hw_fill_vpd_table(minPwrT4[i], maxPwrT4[i],
 						data_9287[idxL].pwrPdg[i],
 						data_9287[idxL].vpdPdg[i],
@@ -416,7 +415,7 @@ void ath9k_hw_get_gain_boundaries_pdadcs(struct ath_hw *ah,
 		} else if (eeprom_4k) {
 			for (i = 0; i < numXpdGains; i++) {
 				minPwrT4[i] = data_4k[idxL].pwrPdg[i][0];
-				maxPwrT4[i] = data_4k[idxL].pwrPdg[i][4];
+				maxPwrT4[i] = data_4k[idxL].pwrPdg[i][intercepts - 1];
 				ath9k_hw_fill_vpd_table(minPwrT4[i], maxPwrT4[i],
 						data_4k[idxL].pwrPdg[i],
 						data_4k[idxL].vpdPdg[i],
@@ -426,7 +425,7 @@ void ath9k_hw_get_gain_boundaries_pdadcs(struct ath_hw *ah,
 		} else {
 			for (i = 0; i < numXpdGains; i++) {
 				minPwrT4[i] = data_def[idxL].pwrPdg[i][0];
-				maxPwrT4[i] = data_def[idxL].pwrPdg[i][4];
+				maxPwrT4[i] = data_def[idxL].pwrPdg[i][intercepts - 1];
 				ath9k_hw_fill_vpd_table(minPwrT4[i], maxPwrT4[i],
 						data_def[idxL].pwrPdg[i],
 						data_def[idxL].vpdPdg[i],
-- 
2.5.0

[added to the 4.1 stable tree] ppp: ensure file->private_data can't be overridden

[Sasha Levin]

From: Guillaume Nault <g.nault@alphalink.fr>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit e8e56ffd9d2973398b60ece1f1bebb8d67b4d032 ]

Locking ppp_mutex must be done before dereferencing file->private_data,
otherwise it could be modified before ppp_unattached_ioctl() takes the
lock. This could lead ppp_unattached_ioctl() to override ->private_data,
thus leaking reference to the ppp_file previously pointed to.

v2: lock all ppp_ioctl() instead of just checking private_data in
    ppp_unattached_ioctl(), to avoid ambiguous behaviour.

Fixes: f3ff8a4d80e8 ("ppp: push BKL down into the driver")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/net/ppp/ppp_generic.c | 31 +++++++++++++++++--------------
 1 file changed, 17 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index cfe49a0..221334a 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -563,7 +563,7 @@ static int get_filter(void __user *arg, struct sock_filter **p)
 
 static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
-	struct ppp_file *pf = file->private_data;
+	struct ppp_file *pf;
 	struct ppp *ppp;
 	int err = -EFAULT, val, val2, i;
 	struct ppp_idle idle;
@@ -573,9 +573,14 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	void __user *argp = (void __user *)arg;
 	int __user *p = argp;
 
-	if (!pf)
-		return ppp_unattached_ioctl(current->nsproxy->net_ns,
-					pf, file, cmd, arg);
+	mutex_lock(&ppp_mutex);
+
+	pf = file->private_data;
+	if (!pf) {
+		err = ppp_unattached_ioctl(current->nsproxy->net_ns,
+					   pf, file, cmd, arg);
+		goto out;
+	}
 
 	if (cmd == PPPIOCDETACH) {
 		/*
@@ -590,7 +595,6 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		 * this fd and reopening /dev/ppp.
 		 */
 		err = -EINVAL;
-		mutex_lock(&ppp_mutex);
 		if (pf->kind == INTERFACE) {
 			ppp = PF_TO_PPP(pf);
 			if (file == ppp->owner)
@@ -602,15 +606,13 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		} else
 			pr_warn("PPPIOCDETACH file->f_count=%ld\n",
 				atomic_long_read(&file->f_count));
-		mutex_unlock(&ppp_mutex);
-		return err;
+		goto out;
 	}
 
 	if (pf->kind == CHANNEL) {
 		struct channel *pch;
 		struct ppp_channel *chan;
 
-		mutex_lock(&ppp_mutex);
 		pch = PF_TO_CHANNEL(pf);
 
 		switch (cmd) {
@@ -632,17 +634,16 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 				err = chan->ops->ioctl(chan, cmd, arg);
 			up_read(&pch->chan_sem);
 		}
-		mutex_unlock(&ppp_mutex);
-		return err;
+		goto out;
 	}
 
 	if (pf->kind != INTERFACE) {
 		/* can't happen */
 		pr_err("PPP: not interface or channel??\n");
-		return -EINVAL;
+		err = -EINVAL;
+		goto out;
 	}
 
-	mutex_lock(&ppp_mutex);
 	ppp = PF_TO_PPP(pf);
 	switch (cmd) {
 	case PPPIOCSMRU:
@@ -817,7 +818,10 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	default:
 		err = -ENOTTY;
 	}
+
+out:
 	mutex_unlock(&ppp_mutex);
+
 	return err;
 }
 
@@ -830,7 +834,6 @@ static int ppp_unattached_ioctl(struct net *net, struct ppp_file *pf,
 	struct ppp_net *pn;
 	int __user *p = (int __user *)arg;
 
-	mutex_lock(&ppp_mutex);
 	switch (cmd) {
 	case PPPIOCNEWUNIT:
 		/* Create a new ppp unit */
@@ -881,7 +884,7 @@ static int ppp_unattached_ioctl(struct net *net, struct ppp_file *pf,
 	default:
 		err = -ENOTTY;
 	}
-	mutex_unlock(&ppp_mutex);
+
 	return err;
 }
 
-- 
2.5.0

[added to the 4.1 stable tree] qlge: Fix receive packets drop.

[Sasha Levin]

From: Manish Chopra <manish.chopra@qlogic.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 2c9a266afefe137bff06bbe0fc48b4d3b3cb348c ]

When running small packets [length < 256 bytes] traffic, packets were
being dropped due to invalid data in those packets which were
delivered by the driver upto the stack. Using pci_dma_sync_single_for_cpu
ensures copying latest and updated data into skb from the receive buffer.

Signed-off-by: Sony Chacko <sony.chacko@qlogic.com>
Signed-off-by: Manish Chopra <manish.chopra@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/net/ethernet/qlogic/qlge/qlge_main.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
index 25800a1..b915de0 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
@@ -1648,7 +1648,18 @@ static void ql_process_mac_rx_skb(struct ql_adapter *qdev,
 		return;
 	}
 	skb_reserve(new_skb, NET_IP_ALIGN);
+
+	pci_dma_sync_single_for_cpu(qdev->pdev,
+				    dma_unmap_addr(sbq_desc, mapaddr),
+				    dma_unmap_len(sbq_desc, maplen),
+				    PCI_DMA_FROMDEVICE);
+
 	memcpy(skb_put(new_skb, length), skb->data, length);
+
+	pci_dma_sync_single_for_device(qdev->pdev,
+				       dma_unmap_addr(sbq_desc, mapaddr),
+				       dma_unmap_len(sbq_desc, maplen),
+				       PCI_DMA_FROMDEVICE);
 	skb = new_skb;
 
 	/* Frame error, so drop the packet. */
-- 
2.5.0

[added to the 4.1 stable tree] net: bcmgenet: fix dma api length mismatch

[Sasha Levin]

From: Eric Dumazet <edumazet@google.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit eee577232203842b4dcadb7ab477a298479633ed ]

When un-mapping skb->data in __bcmgenet_tx_reclaim(),
we must use the length that was used in original dma_map_single(),
instead of skb->len that might be bigger (includes the frags)

We simply can store skb_len into tx_cb_ptr->dma_len and use it
at unmap time.

Fixes: 1c1008c793fa ("net: bcmgenet: add main driver file")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 6043734..a9fcac0 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1048,7 +1048,7 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 			dev->stats.tx_bytes += tx_cb_ptr->skb->len;
 			dma_unmap_single(&dev->dev,
 					 dma_unmap_addr(tx_cb_ptr, dma_addr),
-					 tx_cb_ptr->skb->len,
+					 dma_unmap_len(tx_cb_ptr, dma_len),
 					 DMA_TO_DEVICE);
 			bcmgenet_free_cb(tx_cb_ptr);
 		} else if (dma_unmap_addr(tx_cb_ptr, dma_addr)) {
@@ -1159,7 +1159,7 @@ static int bcmgenet_xmit_single(struct net_device *dev,
 	}
 
 	dma_unmap_addr_set(tx_cb_ptr, dma_addr, mapping);
-	dma_unmap_len_set(tx_cb_ptr, dma_len, skb->len);
+	dma_unmap_len_set(tx_cb_ptr, dma_len, skb_len);
 	length_status = (skb_len << DMA_BUFLENGTH_SHIFT) | dma_desc_flags |
 			(priv->hw_params->qtag_mask << DMA_TX_QTAG_SHIFT) |
 			DMA_TX_APPEND_CRC;
-- 
2.5.0

[added to the 4.1 stable tree] bonding: fix bond_get_stats()

[Sasha Levin]

From: Eric Dumazet <edumazet@google.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit fe30937b65354c7fec244caebbdaae68e28ca797 ]

bond_get_stats() can be called from rtnetlink (with RTNL held)
or from /proc/net/dev seq handler (with RCU held)

The logic added in commit 5f0c5f73e5ef ("bonding: make global bonding
stats more reliable") kind of assumed only one cpu could run there.

If multiple threads are reading /proc/net/dev, stats can be really
messed up after a while.

A second problem is that some fields are 32bit, so we need to properly
handle the wrap around problem.

Given that RTNL is not always held, we need to use
bond_for_each_slave_rcu().

Fixes: 5f0c5f73e5ef ("bonding: make global bonding stats more reliable")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Andy Gospodarek <gospo@cumulusnetworks.com>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Cc: Veaceslav Falico <vfalico@gmail.com>
Reviewed-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/net/bonding/bond_main.c | 65 ++++++++++++++++++++++-------------------
 include/net/bonding.h           |  1 +
 2 files changed, 36 insertions(+), 30 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index bd744e3..9ba92e2 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3246,6 +3246,30 @@ static int bond_close(struct net_device *bond_dev)
 	return 0;
 }
 
+/* fold stats, assuming all rtnl_link_stats64 fields are u64, but
+ * that some drivers can provide 32bit values only.
+ */
+static void bond_fold_stats(struct rtnl_link_stats64 *_res,
+			    const struct rtnl_link_stats64 *_new,
+			    const struct rtnl_link_stats64 *_old)
+{
+	const u64 *new = (const u64 *)_new;
+	const u64 *old = (const u64 *)_old;
+	u64 *res = (u64 *)_res;
+	int i;
+
+	for (i = 0; i < sizeof(*_res) / sizeof(u64); i++) {
+		u64 nv = new[i];
+		u64 ov = old[i];
+
+		/* detects if this particular field is 32bit only */
+		if (((nv | ov) >> 32) == 0)
+			res[i] += (u32)nv - (u32)ov;
+		else
+			res[i] += nv - ov;
+	}
+}
+
 static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev,
 						struct rtnl_link_stats64 *stats)
 {
@@ -3254,43 +3278,23 @@ static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev,
 	struct list_head *iter;
 	struct slave *slave;
 
+	spin_lock(&bond->stats_lock);
 	memcpy(stats, &bond->bond_stats, sizeof(*stats));
 
-	bond_for_each_slave(bond, slave, iter) {
-		const struct rtnl_link_stats64 *sstats =
+	rcu_read_lock();
+	bond_for_each_slave_rcu(bond, slave, iter) {
+		const struct rtnl_link_stats64 *new =
 			dev_get_stats(slave->dev, &temp);
-		struct rtnl_link_stats64 *pstats = &slave->slave_stats;
-
-		stats->rx_packets +=  sstats->rx_packets - pstats->rx_packets;
-		stats->rx_bytes += sstats->rx_bytes - pstats->rx_bytes;
-		stats->rx_errors += sstats->rx_errors - pstats->rx_errors;
-		stats->rx_dropped += sstats->rx_dropped - pstats->rx_dropped;
-
-		stats->tx_packets += sstats->tx_packets - pstats->tx_packets;;
-		stats->tx_bytes += sstats->tx_bytes - pstats->tx_bytes;
-		stats->tx_errors += sstats->tx_errors - pstats->tx_errors;
-		stats->tx_dropped += sstats->tx_dropped - pstats->tx_dropped;
-
-		stats->multicast += sstats->multicast - pstats->multicast;
-		stats->collisions += sstats->collisions - pstats->collisions;
-
-		stats->rx_length_errors += sstats->rx_length_errors - pstats->rx_length_errors;
-		stats->rx_over_errors += sstats->rx_over_errors - pstats->rx_over_errors;
-		stats->rx_crc_errors += sstats->rx_crc_errors - pstats->rx_crc_errors;
-		stats->rx_frame_errors += sstats->rx_frame_errors - pstats->rx_frame_errors;
-		stats->rx_fifo_errors += sstats->rx_fifo_errors - pstats->rx_fifo_errors;
-		stats->rx_missed_errors += sstats->rx_missed_errors - pstats->rx_missed_errors;
-
-		stats->tx_aborted_errors += sstats->tx_aborted_errors - pstats->tx_aborted_errors;
-		stats->tx_carrier_errors += sstats->tx_carrier_errors - pstats->tx_carrier_errors;
-		stats->tx_fifo_errors += sstats->tx_fifo_errors - pstats->tx_fifo_errors;
-		stats->tx_heartbeat_errors += sstats->tx_heartbeat_errors - pstats->tx_heartbeat_errors;
-		stats->tx_window_errors += sstats->tx_window_errors - pstats->tx_window_errors;
+
+		bond_fold_stats(stats, new, &slave->slave_stats);
 
 		/* save off the slave stats for the next run */
-		memcpy(pstats, sstats, sizeof(*sstats));
+		memcpy(&slave->slave_stats, new, sizeof(*new));
 	}
+	rcu_read_unlock();
+
 	memcpy(&bond->bond_stats, stats, sizeof(*stats));
+	spin_unlock(&bond->stats_lock);
 
 	return stats;
 }
@@ -4102,6 +4106,7 @@ void bond_setup(struct net_device *bond_dev)
 	struct bonding *bond = netdev_priv(bond_dev);
 
 	spin_lock_init(&bond->mode_lock);
+	spin_lock_init(&bond->stats_lock);
 	bond->params = bonding_defaults;
 
 	/* Initialize pointers */
diff --git a/include/net/bonding.h b/include/net/bonding.h
index 78ed135..5cba8f3 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -211,6 +211,7 @@ struct bonding {
 	 * ALB mode (6) - to sync the use and modifications of its hash table
 	 */
 	spinlock_t mode_lock;
+	spinlock_t stats_lock;
 	u8	 send_peer_notif;
 	u8       igmp_retrans;
 #ifdef CONFIG_PROC_FS
-- 
2.5.0

[added to the 4.1 stable tree] ipv4: fix broadcast packets reception

[Sasha Levin]

From: Paolo Abeni <pabeni@redhat.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit ad0ea1989cc4d5905941d0a9e62c63ad6d859cef ]

Currently, ingress ipv4 broadcast datagrams are dropped since,
in udp_v4_early_demux(), ip_check_mc_rcu() is invoked even on
bcast packets.

This patch addresses the issue, invoking ip_check_mc_rcu()
only for mcast packets.

Fixes: 6e5403093261 ("ipv4/udp: Verify multicast group is ours in upd_v4_early_demux()")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/ipv4/udp.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index a390174..031752e 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1979,10 +1979,14 @@ void udp_v4_early_demux(struct sk_buff *skb)
 		if (!in_dev)
 			return;
 
-		ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr,
-				       iph->protocol);
-		if (!ours)
-			return;
+		/* we are supposed to accept bcast packets */
+		if (skb->pkt_type == PACKET_MULTICAST) {
+			ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr,
+					       iph->protocol);
+			if (!ours)
+				return;
+		}
+
 		sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr,
 						   uh->source, iph->saddr, dif);
 	} else if (skb->pkt_type == PACKET_HOST) {
-- 
2.5.0

[added to the 4.1 stable tree] ppp: take reference on channels netns

[Sasha Levin]

From: Guillaume Nault <g.nault@alphalink.fr>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 1f461dcdd296eecedaffffc6bae2bfa90bd7eb89 ]

Let channels hold a reference on their network namespace.
Some channel types, like ppp_async and ppp_synctty, can have their
userspace controller running in a different namespace. Therefore they
can't rely on them to preclude their netns from being removed from
under them.

==================================================================
BUG: KASAN: use-after-free in ppp_unregister_channel+0x372/0x3a0 at
addr ffff880064e217e0
Read of size 8 by task syz-executor/11581
=============================================================================
BUG net_namespace (Not tainted): kasan: bad access detected
-----------------------------------------------------------------------------

Disabling lock debugging due to kernel taint
INFO: Allocated in copy_net_ns+0x6b/0x1a0 age=92569 cpu=3 pid=6906
[<      none      >] ___slab_alloc+0x4c7/0x500 kernel/mm/slub.c:2440
[<      none      >] __slab_alloc+0x4c/0x90 kernel/mm/slub.c:2469
[<     inline     >] slab_alloc_node kernel/mm/slub.c:2532
[<     inline     >] slab_alloc kernel/mm/slub.c:2574
[<      none      >] kmem_cache_alloc+0x23a/0x2b0 kernel/mm/slub.c:2579
[<     inline     >] kmem_cache_zalloc kernel/include/linux/slab.h:597
[<     inline     >] net_alloc kernel/net/core/net_namespace.c:325
[<      none      >] copy_net_ns+0x6b/0x1a0 kernel/net/core/net_namespace.c:360
[<      none      >] create_new_namespaces+0x2f6/0x610 kernel/kernel/nsproxy.c:95
[<      none      >] copy_namespaces+0x297/0x320 kernel/kernel/nsproxy.c:150
[<      none      >] copy_process.part.35+0x1bf4/0x5760 kernel/kernel/fork.c:1451
[<     inline     >] copy_process kernel/kernel/fork.c:1274
[<      none      >] _do_fork+0x1bc/0xcb0 kernel/kernel/fork.c:1723
[<     inline     >] SYSC_clone kernel/kernel/fork.c:1832
[<      none      >] SyS_clone+0x37/0x50 kernel/kernel/fork.c:1826
[<      none      >] entry_SYSCALL_64_fastpath+0x16/0x7a kernel/arch/x86/entry/entry_64.S:185

INFO: Freed in net_drop_ns+0x67/0x80 age=575 cpu=2 pid=2631
[<      none      >] __slab_free+0x1fc/0x320 kernel/mm/slub.c:2650
[<     inline     >] slab_free kernel/mm/slub.c:2805
[<      none      >] kmem_cache_free+0x2a0/0x330 kernel/mm/slub.c:2814
[<     inline     >] net_free kernel/net/core/net_namespace.c:341
[<      none      >] net_drop_ns+0x67/0x80 kernel/net/core/net_namespace.c:348
[<      none      >] cleanup_net+0x4e5/0x600 kernel/net/core/net_namespace.c:448
[<      none      >] process_one_work+0x794/0x1440 kernel/kernel/workqueue.c:2036
[<      none      >] worker_thread+0xdb/0xfc0 kernel/kernel/workqueue.c:2170
[<      none      >] kthread+0x23f/0x2d0 kernel/drivers/block/aoe/aoecmd.c:1303
[<      none      >] ret_from_fork+0x3f/0x70 kernel/arch/x86/entry/entry_64.S:468
INFO: Slab 0xffffea0001938800 objects=3 used=0 fp=0xffff880064e20000
flags=0x5fffc0000004080
INFO: Object 0xffff880064e20000 @offset=0 fp=0xffff880064e24200

CPU: 1 PID: 11581 Comm: syz-executor Tainted: G    B           4.4.0+
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS
rel-1.8.2-0-g33fbe13 by qemu-project.org 04/01/2014
 00000000ffffffff ffff8800662c7790 ffffffff8292049d ffff88003e36a300
 ffff880064e20000 ffff880064e20000 ffff8800662c77c0 ffffffff816f2054
 ffff88003e36a300 ffffea0001938800 ffff880064e20000 0000000000000000
Call Trace:
 [<     inline     >] __dump_stack kernel/lib/dump_stack.c:15
 [<ffffffff8292049d>] dump_stack+0x6f/0xa2 kernel/lib/dump_stack.c:50
 [<ffffffff816f2054>] print_trailer+0xf4/0x150 kernel/mm/slub.c:654
 [<ffffffff816f875f>] object_err+0x2f/0x40 kernel/mm/slub.c:661
 [<     inline     >] print_address_description kernel/mm/kasan/report.c:138
 [<ffffffff816fb0c5>] kasan_report_error+0x215/0x530 kernel/mm/kasan/report.c:236
 [<     inline     >] kasan_report kernel/mm/kasan/report.c:259
 [<ffffffff816fb4de>] __asan_report_load8_noabort+0x3e/0x40 kernel/mm/kasan/report.c:280
 [<     inline     >] ? ppp_pernet kernel/include/linux/compiler.h:218
 [<ffffffff83ad71b2>] ? ppp_unregister_channel+0x372/0x3a0 kernel/drivers/net/ppp/ppp_generic.c:2392
 [<     inline     >] ppp_pernet kernel/include/linux/compiler.h:218
 [<ffffffff83ad71b2>] ppp_unregister_channel+0x372/0x3a0 kernel/drivers/net/ppp/ppp_generic.c:2392
 [<     inline     >] ? ppp_pernet kernel/drivers/net/ppp/ppp_generic.c:293
 [<ffffffff83ad6f26>] ? ppp_unregister_channel+0xe6/0x3a0 kernel/drivers/net/ppp/ppp_generic.c:2392
 [<ffffffff83ae18f3>] ppp_asynctty_close+0xa3/0x130 kernel/drivers/net/ppp/ppp_async.c:241
 [<ffffffff83ae1850>] ? async_lcp_peek+0x5b0/0x5b0 kernel/drivers/net/ppp/ppp_async.c:1000
 [<ffffffff82c33239>] tty_ldisc_close.isra.1+0x99/0xe0 kernel/drivers/tty/tty_ldisc.c:478
 [<ffffffff82c332c0>] tty_ldisc_kill+0x40/0x170 kernel/drivers/tty/tty_ldisc.c:744
 [<ffffffff82c34943>] tty_ldisc_release+0x1b3/0x260 kernel/drivers/tty/tty_ldisc.c:772
 [<ffffffff82c1ef21>] tty_release+0xac1/0x13e0 kernel/drivers/tty/tty_io.c:1901
 [<ffffffff82c1e460>] ? release_tty+0x320/0x320 kernel/drivers/tty/tty_io.c:1688
 [<ffffffff8174de36>] __fput+0x236/0x780 kernel/fs/file_table.c:208
 [<ffffffff8174e405>] ____fput+0x15/0x20 kernel/fs/file_table.c:244
 [<ffffffff813595ab>] task_work_run+0x16b/0x200 kernel/kernel/task_work.c:115
 [<     inline     >] exit_task_work kernel/include/linux/task_work.h:21
 [<ffffffff81307105>] do_exit+0x8b5/0x2c60 kernel/kernel/exit.c:750
 [<ffffffff813fdd20>] ? debug_check_no_locks_freed+0x290/0x290 kernel/kernel/locking/lockdep.c:4123
 [<ffffffff81306850>] ? mm_update_next_owner+0x6f0/0x6f0 kernel/kernel/exit.c:357
 [<ffffffff813215e6>] ? __dequeue_signal+0x136/0x470 kernel/kernel/signal.c:550
 [<ffffffff8132067b>] ? recalc_sigpending_tsk+0x13b/0x180 kernel/kernel/signal.c:145
 [<ffffffff81309628>] do_group_exit+0x108/0x330 kernel/kernel/exit.c:880
 [<ffffffff8132b9d4>] get_signal+0x5e4/0x14f0 kernel/kernel/signal.c:2307
 [<     inline     >] ? kretprobe_table_lock kernel/kernel/kprobes.c:1113
 [<ffffffff8151d355>] ? kprobe_flush_task+0xb5/0x450 kernel/kernel/kprobes.c:1158
 [<ffffffff8115f7d3>] do_signal+0x83/0x1c90 kernel/arch/x86/kernel/signal.c:712
 [<ffffffff8151d2a0>] ? recycle_rp_inst+0x310/0x310 kernel/include/linux/list.h:655
 [<ffffffff8115f750>] ? setup_sigcontext+0x780/0x780 kernel/arch/x86/kernel/signal.c:165
 [<ffffffff81380864>] ? finish_task_switch+0x424/0x5f0 kernel/kernel/sched/core.c:2692
 [<     inline     >] ? finish_lock_switch kernel/kernel/sched/sched.h:1099
 [<ffffffff81380560>] ? finish_task_switch+0x120/0x5f0 kernel/kernel/sched/core.c:2678
 [<     inline     >] ? context_switch kernel/kernel/sched/core.c:2807
 [<ffffffff85d794e9>] ? __schedule+0x919/0x1bd0 kernel/kernel/sched/core.c:3283
 [<ffffffff81003901>] exit_to_usermode_loop+0xf1/0x1a0 kernel/arch/x86/entry/common.c:247
 [<     inline     >] prepare_exit_to_usermode kernel/arch/x86/entry/common.c:282
 [<ffffffff810062ef>] syscall_return_slowpath+0x19f/0x210 kernel/arch/x86/entry/common.c:344
 [<ffffffff85d88022>] int_ret_from_sys_call+0x25/0x9f kernel/arch/x86/entry/entry_64.S:281
Memory state around the buggy address:
 ffff880064e21680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff880064e21700: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff880064e21780: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                                                       ^
 ffff880064e21800: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff880064e21880: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
==================================================================

Fixes: 273ec51dd7ce ("net: ppp_generic - introduce net-namespace functionality v2")
Reported-by: Baozeng Ding <sploving1@gmail.com>
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Reviewed-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/net/ppp/ppp_generic.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 221334a..51ba895 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -2247,7 +2247,7 @@ int ppp_register_net_channel(struct net *net, struct ppp_channel *chan)
 
 	pch->ppp = NULL;
 	pch->chan = chan;
-	pch->chan_net = net;
+	pch->chan_net = get_net(net);
 	chan->ppp = pch;
 	init_ppp_file(&pch->file, CHANNEL);
 	pch->file.hdrlen = chan->hdrlen;
@@ -2344,6 +2344,8 @@ ppp_unregister_channel(struct ppp_channel *chan)
 	spin_lock_bh(&pn->all_channels_lock);
 	list_del(&pch->list);
 	spin_unlock_bh(&pn->all_channels_lock);
+	put_net(pch->chan_net);
+	pch->chan_net = NULL;
 
 	pch->file.dead = 1;
 	wake_up_interruptible(&pch->file.rwait);
-- 
2.5.0

[added to the 4.1 stable tree] xfrm: Fix crash observed during device unregistration and decryption

[Sasha Levin]

From: "subashab@codeaurora.org" <subashab@codeaurora.org>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 071d36bf21bcc837be00cea55bcef8d129e7f609 ]

A crash is observed when a decrypted packet is processed in receive
path. get_rps_cpus() tries to dereference the skb->dev fields but it
appears that the device is freed from the poison pattern.

[<ffffffc000af58ec>] get_rps_cpu+0x94/0x2f0
[<ffffffc000af5f94>] netif_rx_internal+0x140/0x1cc
[<ffffffc000af6094>] netif_rx+0x74/0x94
[<ffffffc000bc0b6c>] xfrm_input+0x754/0x7d0
[<ffffffc000bc0bf8>] xfrm_input_resume+0x10/0x1c
[<ffffffc000ba6eb8>] esp_input_done+0x20/0x30
[<ffffffc0000b64c8>] process_one_work+0x244/0x3fc
[<ffffffc0000b7324>] worker_thread+0x2f8/0x418
[<ffffffc0000bb40c>] kthread+0xe0/0xec

-013|get_rps_cpu(
     |    dev = 0xFFFFFFC08B688000,
     |    skb = 0xFFFFFFC0C76AAC00 -> (
     |      dev = 0xFFFFFFC08B688000 -> (
     |        name =
"......................................................
     |        name_hlist = (next = 0xAAAAAAAAAAAAAAAA, pprev =
0xAAAAAAAAAAA

Following are the sequence of events observed -

- Encrypted packet in receive path from netdevice is queued
- Encrypted packet queued for decryption (asynchronous)
- Netdevice brought down and freed
- Packet is decrypted and returned through callback in esp_input_done
- Packet is queued again for process in network stack using netif_rx

Since the device appears to have been freed, the dereference of
skb->dev in get_rps_cpus() leads to an unhandled page fault
exception.

Fix this by holding on to device reference when queueing packets
asynchronously and releasing the reference on call back return.

v2: Make the change generic to xfrm as mentioned by Steffen and
update the title to xfrm

Suggested-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Jerome Stanislaus <jeromes@codeaurora.org>
Signed-off-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/xfrm/xfrm_input.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index b58286e..cbaf52c 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -292,12 +292,15 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 		XFRM_SKB_CB(skb)->seq.input.hi = seq_hi;
 
 		skb_dst_force(skb);
+		dev_hold(skb->dev);
 
 		nexthdr = x->type->input(x, skb);
 
 		if (nexthdr == -EINPROGRESS)
 			return 0;
 resume:
+		dev_put(skb->dev);
+
 		spin_lock(&x->lock);
 		if (nexthdr <= 0) {
 			if (nexthdr == -EBADMSG) {
-- 
2.5.0

[added to the 4.1 stable tree] qmi_wwan: add "D-Link DWM-221 B1" device id

[Sasha Levin]

From: Bjørn Mork <bjorn@mork.no>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit e84810c7b85a2d7897797b3ad3e879168a8e032a ]

Thomas reports:
"Windows:

00 diagnostics
01 modem
02 at-port
03 nmea
04 nic

Linux:

T:  Bus=02 Lev=01 Prnt=01 Port=03 Cnt=01 Dev#=  4 Spd=480 MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=2001 ProdID=7e19 Rev=02.32
S:  Manufacturer=Mobile Connect
S:  Product=Mobile Connect
S:  SerialNumber=0123456789ABCDEF
C:  #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
I:  If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:  If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:  If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
I:  If#= 5 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=usb-storage"

Reported-by: Thomas Schäfer <tschaefer@t-online.de>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 8677c6a..8153e97 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -749,6 +749,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x19d2, 0x1426, 2)},	/* ZTE MF91 */
 	{QMI_FIXED_INTF(0x19d2, 0x1428, 2)},	/* Telewell TW-LTE 4G v2 */
 	{QMI_FIXED_INTF(0x19d2, 0x2002, 4)},	/* ZTE (Vodafone) K3765-Z */
+	{QMI_FIXED_INTF(0x2001, 0x7e19, 4)},	/* D-Link DWM-221 B1 */
 	{QMI_FIXED_INTF(0x0f3d, 0x68a2, 8)},    /* Sierra Wireless MC7700 */
 	{QMI_FIXED_INTF(0x114f, 0x68a2, 8)},    /* Sierra Wireless MC7750 */
 	{QMI_FIXED_INTF(0x1199, 0x68a2, 8)},	/* Sierra Wireless MC7710 in QMI mode */
-- 
2.5.0

[added to the 4.1 stable tree] ipv6: udp: fix UDP_MIB_IGNOREDMULTI updates

[Sasha Levin]

From: Eric Dumazet <edumazet@google.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 2d4212261fdf13e29728ddb5ea9d60c342cc92b5 ]

IPv6 counters updates use a different macro than IPv4.

Fixes: 36cbb2452cbaf ("udp: Increment UDP_MIB_IGNOREDMULTI for arriving unmatched multicasts")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Rick Jones <rick.jones2@hp.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/ipv6/udp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index d28b2a1..1173557 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -834,8 +834,8 @@ start_lookup:
 		flush_stack(stack, count, skb, count - 1);
 	} else {
 		if (!inner_flushed)
-			UDP_INC_STATS_BH(net, UDP_MIB_IGNOREDMULTI,
-					 proto == IPPROTO_UDPLITE);
+			UDP6_INC_STATS_BH(net, UDP_MIB_IGNOREDMULTI,
+					  proto == IPPROTO_UDPLITE);
 		consume_skb(skb);
 	}
 	return 0;
-- 
2.5.0

[added to the 4.1 stable tree] rtnl: fix msg size calculation in if_nlmsg_size()

[Sasha Levin]

From: Nicolas Dichtel <nicolas.dichtel@6wind.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit c57c7a95da842807b475b823ed2e5435c42cb3b0 ]

Size of the attribute IFLA_PHYS_PORT_NAME was missing.

Fixes: db24a9044ee1 ("net: add support for phys_port_name")
CC: David Ahern <dsahern@gmail.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/core/rtnetlink.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index fe95cb7..31a46a7 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -884,7 +884,9 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + rtnl_link_get_size(dev) /* IFLA_LINKINFO */
 	       + rtnl_link_get_af_size(dev) /* IFLA_AF_SPEC */
 	       + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_PORT_ID */
-	       + nla_total_size(MAX_PHYS_ITEM_ID_LEN); /* IFLA_PHYS_SWITCH_ID */
+	       + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_SWITCH_ID */
+	       + nla_total_size(IFNAMSIZ); /* IFLA_PHYS_PORT_NAME */
+
 }
 
 static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev)
-- 
2.5.0

[added to the 4.1 stable tree] ipv4: l2tp: fix a potential issue in l2tp_ip_recv

[Sasha Levin]

From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 5745b8232e942abd5e16e85fa9b27cc21324acf0 ]

pskb_may_pull() can change skb->data, so we have to load ptr/optr at the
right place.

Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/l2tp/l2tp_ip.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 7964993..44ee068 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -123,12 +123,11 @@ static int l2tp_ip_recv(struct sk_buff *skb)
 	struct l2tp_tunnel *tunnel = NULL;
 	int length;
 
-	/* Point to L2TP header */
-	optr = ptr = skb->data;
-
 	if (!pskb_may_pull(skb, 4))
 		goto discard;
 
+	/* Point to L2TP header */
+	optr = ptr = skb->data;
 	session_id = ntohl(*((__be32 *) ptr));
 	ptr += 4;
 
@@ -156,6 +155,9 @@ static int l2tp_ip_recv(struct sk_buff *skb)
 		if (!pskb_may_pull(skb, length))
 			goto discard;
 
+		/* Point to L2TP header */
+		optr = ptr = skb->data;
+		ptr += 4;
 		pr_debug("%s: ip recv\n", tunnel->name);
 		print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length);
 	}
-- 
2.5.0

[added to the 4.1 stable tree] ipv6: l2tp: fix a potential issue in l2tp_ip6_recv

[Sasha Levin]

From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit be447f305494e019dfc37ea4cdf3b0e4200b4eba ]

pskb_may_pull() can change skb->data, so we have to load ptr/optr at the
right place.

Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/l2tp/l2tp_ip6.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 0ce9da9..36f8fa2 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -135,12 +135,11 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
 	struct l2tp_tunnel *tunnel = NULL;
 	int length;
 
-	/* Point to L2TP header */
-	optr = ptr = skb->data;
-
 	if (!pskb_may_pull(skb, 4))
 		goto discard;
 
+	/* Point to L2TP header */
+	optr = ptr = skb->data;
 	session_id = ntohl(*((__be32 *) ptr));
 	ptr += 4;
 
@@ -168,6 +167,9 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
 		if (!pskb_may_pull(skb, length))
 			goto discard;
 
+		/* Point to L2TP header */
+		optr = ptr = skb->data;
+		ptr += 4;
 		pr_debug("%s: ip recv\n", tunnel->name);
 		print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length);
 	}
-- 
2.5.0

[added to the 4.1 stable tree] ip6_tunnel: set rtnl_link_ops before calling register_netdevice

[Sasha Levin]

From: Thadeu Lima de Souza Cascardo <cascardo@redhat.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit b6ee376cb0b7fb4e7e07d6cd248bd40436fb9ba6 ]

When creating an ip6tnl tunnel with ip tunnel, rtnl_link_ops is not set
before ip6_tnl_create2 is called. When register_netdevice is called, there
is no linkinfo attribute in the NEWLINK message because of that.

Setting rtnl_link_ops before calling register_netdevice fixes that.

Fixes: 0b112457229d ("ip6tnl: add support of link creation via rtnl")
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@redhat.com>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/ipv6/ip6_tunnel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 6fd0f96..c7c2c33 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -284,12 +284,12 @@ static int ip6_tnl_create2(struct net_device *dev)
 
 	t = netdev_priv(dev);
 
+	dev->rtnl_link_ops = &ip6_link_ops;
 	err = register_netdevice(dev);
 	if (err < 0)
 		goto out;
 
 	strcpy(t->parms.name, dev->name);
-	dev->rtnl_link_ops = &ip6_link_ops;
 
 	dev_hold(dev);
 	ip6_tnl_link(ip6n, t);
-- 
2.5.0

[added to the 4.1 stable tree] pinctrl: nomadik: fix pull debug print inversion

[Sasha Levin]

From: Linus Walleij <linus.walleij@linaro.org>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 6ee334559324a55725e22463de633b99ad99fcad ]

Pull up was reported as pull down and vice versa. Fix this.

Fixes: 8f1774a2a971 "pinctrl: nomadik: improve GPIO debug prints"
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/pinctrl/nomadik/pinctrl-nomadik.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/nomadik/pinctrl-nomadik.c b/drivers/pinctrl/nomadik/pinctrl-nomadik.c
index a6a2205..f4b1dac 100644
--- a/drivers/pinctrl/nomadik/pinctrl-nomadik.c
+++ b/drivers/pinctrl/nomadik/pinctrl-nomadik.c
@@ -1025,7 +1025,7 @@ static void nmk_gpio_dbg_show_one(struct seq_file *s,
 		int pullidx = 0;
 
 		if (pull)
-			pullidx = data_out ? 1 : 2;
+			pullidx = data_out ? 2 : 1;
 
 		seq_printf(s, " gpio-%-3d (%-20.20s) in  %s %s",
 			   gpio,
-- 
2.5.0

[added to the 4.1 stable tree] [media] coda: fix error path in case of missing pdata on non-DT platform

[Sasha Levin]

From: Philipp Zabel <p.zabel@pengutronix.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit bc717d5e92c8c079280eb4acbe335c6f25041aa2 ]

If we bail out this early, v4l2_device_register() has not been called
yet, so no need to call v4l2_device_unregister().

Fixes: b7bd660a51f0 ("[media] coda: Call v4l2_device_unregister() from a single location")

Reported-by: Michael Olbrich <m.olbrich@pengutronix.de>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Reviewed-by: Fabio Estevam <fabio.estevam@nxp.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/media/platform/coda/coda-common.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/media/platform/coda/coda-common.c b/drivers/media/platform/coda/coda-common.c
index 8e6fe02..e14b1a1 100644
--- a/drivers/media/platform/coda/coda-common.c
+++ b/drivers/media/platform/coda/coda-common.c
@@ -2100,14 +2100,12 @@ static int coda_probe(struct platform_device *pdev)
 
 	pdev_id = of_id ? of_id->data : platform_get_device_id(pdev);
 
-	if (of_id) {
+	if (of_id)
 		dev->devtype = of_id->data;
-	} else if (pdev_id) {
+	else if (pdev_id)
 		dev->devtype = &coda_devdata[pdev_id->driver_data];
-	} else {
-		ret = -EINVAL;
-		goto err_v4l2_register;
-	}
+	else
+		return -EINVAL;
 
 	spin_lock_init(&dev->irqlock);
 	INIT_LIST_HEAD(&dev->instances);
-- 
2.5.0

[added to the 4.1 stable tree] [media] v4l: vsp1: Set the SRU CTRL0 register when starting the stream

[Sasha Levin]

From: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit f6acfcdc5b8cdc9ddd53a459361820b9efe958c4 ]

Commit 58f896d859ce ("[media] v4l: vsp1: sru: Make the intensity
controllable during streaming") refactored the stream start code and
removed the SRU CTRL0 register write by mistake. Add it back.

Fixes: 58f896d859ce ("[media] v4l: vsp1: sru: Make the intensity controllable during streaming")

Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/media/platform/vsp1/vsp1_sru.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/media/platform/vsp1/vsp1_sru.c b/drivers/media/platform/vsp1/vsp1_sru.c
index 6310aca..d41ae95 100644
--- a/drivers/media/platform/vsp1/vsp1_sru.c
+++ b/drivers/media/platform/vsp1/vsp1_sru.c
@@ -154,6 +154,7 @@ static int sru_s_stream(struct v4l2_subdev *subdev, int enable)
 	mutex_lock(sru->ctrls.lock);
 	ctrl0 |= vsp1_sru_read(sru, VI6_SRU_CTRL0)
 	       & (VI6_SRU_CTRL0_PARAM0_MASK | VI6_SRU_CTRL0_PARAM1_MASK);
+	vsp1_sru_write(sru, VI6_SRU_CTRL0, ctrl0);
 	mutex_unlock(sru->ctrls.lock);
 
 	vsp1_sru_write(sru, VI6_SRU_CTRL1, VI6_SRU_CTRL1_PARAM5);
-- 
2.5.0

[added to the 4.1 stable tree] mac80211: avoid excessive stack usage in sta_info

[Sasha Levin]

From: Arnd Bergmann <arnd@arndb.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 0ef049dc1167fe834d0ad5d63f89eddc5c70f6e4 ]

When CONFIG_OPTIMIZE_INLINING is set, the sta_info_insert_finish
function consumes more stack than normally, exceeding the
1024 byte limit on ARM:

net/mac80211/sta_info.c: In function 'sta_info_insert_finish':
net/mac80211/sta_info.c:561:1: error: the frame size of 1080 bytes is larger than 1024 bytes [-Werror=frame-larger-than=]

It turns out that there are two functions that put a 'struct station_info'
on the stack: __sta_info_destroy_part2 and sta_info_insert_finish, and
this structure alone requires up to 792 bytes.

Hoping that both are called rarely enough, this replaces the
on-stack structure with a dynamic allocation, which unfortunately
requires some suboptimal error handling for out-of-memory.

The __sta_info_destroy_part2 function is actually affected by the
stack usage twice because it calls cfg80211_del_sta_sinfo(), which
has another instance of struct station_info on its stack.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Fixes: 98b6218388e3 ("mac80211/cfg80211: add station events")
Fixes: 6f7a8d26e266 ("mac80211: send statistics with delete station event")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/mac80211/sta_info.c | 24 ++++++++++++++++--------
 1 file changed, 16 insertions(+), 8 deletions(-)

diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index a702719..bcdbda2 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -472,11 +472,17 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU)
 {
 	struct ieee80211_local *local = sta->local;
 	struct ieee80211_sub_if_data *sdata = sta->sdata;
-	struct station_info sinfo;
+	struct station_info *sinfo;
 	int err = 0;
 
 	lockdep_assert_held(&local->sta_mtx);
 
+	sinfo = kzalloc(sizeof(struct station_info), GFP_KERNEL);
+	if (!sinfo) {
+		err = -ENOMEM;
+		goto out_err;
+	}
+
 	/* check if STA exists already */
 	if (sta_info_get_bss(sdata, sta->sta.addr)) {
 		err = -EEXIST;
@@ -510,10 +516,9 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU)
 	ieee80211_sta_debugfs_add(sta);
 	rate_control_add_sta_debugfs(sta);
 
-	memset(&sinfo, 0, sizeof(sinfo));
-	sinfo.filled = 0;
-	sinfo.generation = local->sta_generation;
-	cfg80211_new_sta(sdata->dev, sta->sta.addr, &sinfo, GFP_KERNEL);
+	sinfo->generation = local->sta_generation;
+	cfg80211_new_sta(sdata->dev, sta->sta.addr, sinfo, GFP_KERNEL);
+	kfree(sinfo);
 
 	sta_dbg(sdata, "Inserted STA %pM\n", sta->sta.addr);
 
@@ -876,7 +881,7 @@ static void __sta_info_destroy_part2(struct sta_info *sta)
 {
 	struct ieee80211_local *local = sta->local;
 	struct ieee80211_sub_if_data *sdata = sta->sdata;
-	struct station_info sinfo = {};
+	struct station_info *sinfo;
 	int ret;
 
 	/*
@@ -914,8 +919,11 @@ static void __sta_info_destroy_part2(struct sta_info *sta)
 
 	sta_dbg(sdata, "Removed STA %pM\n", sta->sta.addr);
 
-	sta_set_sinfo(sta, &sinfo);
-	cfg80211_del_sta_sinfo(sdata->dev, sta->sta.addr, &sinfo, GFP_KERNEL);
+	sinfo = kzalloc(sizeof(*sinfo), GFP_KERNEL);
+	if (sinfo)
+		sta_set_sinfo(sta, sinfo);
+	cfg80211_del_sta_sinfo(sdata->dev, sta->sta.addr, sinfo, GFP_KERNEL);
+	kfree(sinfo);
 
 	rate_control_remove_sta_debugfs(sta);
 	ieee80211_sta_debugfs_remove(sta);
-- 
2.5.0

[added to the 4.1 stable tree] mac80211: fix ibss scan parameters

[Sasha Levin]

From: Sara Sharon <sara.sharon@intel.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit d321cd014e51baab475efbdec468255b9e0ec822 ]

When joining IBSS a full scan should be initiated in order to search
for existing cell, unless the fixed_channel parameter was set.
A default channel to create the IBSS on if no cell was found is
provided as well.
However - a scan is initiated only on the default channel provided
regardless of whether ifibss->fixed_channel is set or not, with the
obvious result of the cell not joining existing IBSS cell that is
on another channel.

Fixes: 76bed0f43b27 ("mac80211: IBSS fix scan request")
Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/mac80211/ibss.c | 22 +++++++++++++++-------
 1 file changed, 15 insertions(+), 7 deletions(-)

diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index 41adfc8..6f1f3bd 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -7,6 +7,7 @@
  * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
  * Copyright 2009, Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
+ * Copyright(c) 2016 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -1479,14 +1480,21 @@ static void ieee80211_sta_find_ibss(struct ieee80211_sub_if_data *sdata)
 
 		sdata_info(sdata, "Trigger new scan to find an IBSS to join\n");
 
-		num = ieee80211_ibss_setup_scan_channels(local->hw.wiphy,
-							 &ifibss->chandef,
-							 channels,
-							 ARRAY_SIZE(channels));
 		scan_width = cfg80211_chandef_to_scan_width(&ifibss->chandef);
-		ieee80211_request_ibss_scan(sdata, ifibss->ssid,
-					    ifibss->ssid_len, channels, num,
-					    scan_width);
+
+		if (ifibss->fixed_channel) {
+			num = ieee80211_ibss_setup_scan_channels(local->hw.wiphy,
+								 &ifibss->chandef,
+								 channels,
+								 ARRAY_SIZE(channels));
+			ieee80211_request_ibss_scan(sdata, ifibss->ssid,
+						    ifibss->ssid_len, channels,
+						    num, scan_width);
+		} else {
+			ieee80211_request_ibss_scan(sdata, ifibss->ssid,
+						    ifibss->ssid_len, NULL,
+						    0, scan_width);
+		}
 	} else {
 		int interval = IEEE80211_SCAN_INTERVAL;
 
-- 
2.5.0

[added to the 4.1 stable tree] mac80211: fix unnecessary frame drops in mesh fwding

[Sasha Levin]

From: Michal Kazior <michal.kazior@tieto.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit cf44012810ccdd8fd947518e965cb04b7b8498be ]

The ieee80211_queue_stopped() expects hw queue
number but it was given raw WMM AC number instead.

This could cause frame drops and problems with
traffic in some cases - most notably if driver
doesn't map AC numbers to queue numbers 1:1 and
uses ieee80211_stop_queues() and
ieee80211_wake_queue() only without ever calling
ieee80211_wake_queues().

On ath10k it was possible to hit this problem in
the following case:

  1. wlan0 uses queue 0
     (ath10k maps queues per vif)
  2. offchannel uses queue 15
  3. queues 1-14 are unused
  4. ieee80211_stop_queues()
  5. ieee80211_wake_queue(q=0)
  6. ieee80211_wake_queue(q=15)
     (other queues are not woken up because both
      driver and mac80211 know other queues are
      unused)
  7. ieee80211_rx_h_mesh_fwding()
  8. ieee80211_select_queue_80211() returns 2
  9. ieee80211_queue_stopped(q=2) returns true
 10. frame is dropped (oops!)

Fixes: d3c1597b8d1b ("mac80211: fix forwarded mesh frame queue mapping")
Signed-off-by: Michal Kazior <michal.kazior@tieto.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/mac80211/rx.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index d4b08d8..3073164 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -2227,7 +2227,7 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx)
 	struct ieee80211_sub_if_data *sdata = rx->sdata;
 	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
 	struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
-	u16 q, hdrlen;
+	u16 ac, q, hdrlen;
 
 	hdr = (struct ieee80211_hdr *) skb->data;
 	hdrlen = ieee80211_hdrlen(hdr->frame_control);
@@ -2297,7 +2297,8 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx)
 	    ether_addr_equal(sdata->vif.addr, hdr->addr3))
 		return RX_CONTINUE;
 
-	q = ieee80211_select_queue_80211(sdata, skb, hdr);
+	ac = ieee80211_select_queue_80211(sdata, skb, hdr);
+	q = sdata->vif.hw_queue[ac];
 	if (ieee80211_queue_stopped(&local->hw, q)) {
 		IEEE80211_IFSTA_MESH_CTR_INC(ifmsh, dropped_frames_congestion);
 		return RX_DROP_MONITOR;
-- 
2.5.0

[added to the 4.1 stable tree] mac80211: fix txq queue related crashes

[Sasha Levin]

From: Michal Kazior <michal.kazior@tieto.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 2a58d42c1e018ad514d4e23fd33fb2ded95d3ee6 ]

The driver can access the queue simultanously
while mac80211 tears down the interface. Without
spinlock protection this could lead to corrupting
sk_buff_head and subsequently to an invalid
pointer dereference.

Fixes: ba8c3d6f16a1 ("mac80211: add an intermediate software queue implementation")
Signed-off-by: Michal Kazior <michal.kazior@tieto.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/mac80211/iface.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 84cef60..6e89ab8 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -980,7 +980,10 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
 	if (sdata->vif.txq) {
 		struct txq_info *txqi = to_txq_info(sdata->vif.txq);
 
+		spin_lock_bh(&txqi->queue.lock);
 		ieee80211_purge_tx_queue(&local->hw, &txqi->queue);
+		spin_unlock_bh(&txqi->queue.lock);
+
 		atomic_set(&sdata->txqs_len[txqi->txq.ac], 0);
 	}
 
-- 
2.5.0

[added to the 4.1 stable tree] futex: Acknowledge a new waiter in counter before plist

[Sasha Levin]

From: Davidlohr Bueso <dave@stgolabs.net>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit fe1bce9e2107ba3a8faffe572483b6974201a0e6 ]

Otherwise an incoming waker on the dest hash bucket can miss
the waiter adding itself to the plist during the lockless
check optimization (small window but still the correct way
of doing this); similarly to the decrement counterpart.

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: bigeasy@linutronix.de
Cc: dvhart@infradead.org
Cc: stable@kernel.org
Link: http://lkml.kernel.org/r/1461208164-29150-1-git-send-email-dave@stgolabs.net
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 kernel/futex.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/futex.c b/kernel/futex.c
index 46b168e..2214b70 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1381,8 +1381,8 @@ void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1,
 	if (likely(&hb1->chain != &hb2->chain)) {
 		plist_del(&q->list, &hb1->chain);
 		hb_waiters_dec(hb1);
-		plist_add(&q->list, &hb2->chain);
 		hb_waiters_inc(hb2);
+		plist_add(&q->list, &hb2->chain);
 		q->lock_ptr = &hb2->lock;
 	}
 	get_futex_key_refs(key2);
-- 
2.5.0

[added to the 4.1 stable tree] powerpc: Update TM user feature bits in scan_features()

[Sasha Levin]

From: Anton Blanchard <anton@samba.org>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 4705e02498d6d5a7ab98dfee9595cd5e91db2017 ]

We need to update the user TM feature bits (PPC_FEATURE2_HTM and
PPC_FEATURE2_HTM) to mirror what we do with the kernel TM feature
bit.

At the moment, if firmware reports TM is not available we turn off
the kernel TM feature bit but leave the userspace ones on. Userspace
thinks it can execute TM instructions and it dies trying.

This (together with a QEMU patch) fixes PR KVM, which doesn't currently
support TM.

Signed-off-by: Anton Blanchard <anton@samba.org>
Cc: stable@vger.kernel.org
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 arch/powerpc/kernel/prom.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index abe9cdc..28dbbb0 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -162,11 +162,12 @@ static struct ibm_pa_feature {
 	{0, MMU_FTR_CI_LARGE_PAGE, 0, 0,		1, 2, 0},
 	{CPU_FTR_REAL_LE, 0, PPC_FEATURE_TRUE_LE, 0, 5, 0, 0},
 	/*
-	 * If the kernel doesn't support TM (ie. CONFIG_PPC_TRANSACTIONAL_MEM=n),
-	 * we don't want to turn on CPU_FTR_TM here, so we use CPU_FTR_TM_COMP
-	 * which is 0 if the kernel doesn't support TM.
+	 * If the kernel doesn't support TM (ie CONFIG_PPC_TRANSACTIONAL_MEM=n),
+	 * we don't want to turn on TM here, so we use the *_COMP versions
+	 * which are 0 if the kernel doesn't support TM.
 	 */
-	{CPU_FTR_TM_COMP, 0, 0, 0,		22, 0, 0},
+	{CPU_FTR_TM_COMP, 0, 0,
+	 PPC_FEATURE2_HTM_COMP|PPC_FEATURE2_HTM_NOSC_COMP, 22, 0, 0},
 };
 
 static void __init scan_features(unsigned long node, const unsigned char *ftrs,
-- 
2.5.0

[added to the 4.1 stable tree] Input: pmic8xxx-pwrkey - fix algorithm for converting trigger delay

[Sasha Levin]

From: Stephen Boyd <sboyd@codeaurora.org>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit eda5ecc0a6b865561997e177c393f0b0136fe3b7 ]

The trigger delay algorithm that converts from microseconds to
the register value looks incorrect. According to most of the PMIC
documentation, the equation is

	delay (Seconds) = (1 / 1024) * 2 ^ (x + 4)

except for one case where the documentation looks to have a
formatting issue and the equation looks like

	delay (Seconds) = (1 / 1024) * 2 x + 4

Most likely this driver was written with the improper
documentation to begin with. According to the downstream sources
the valid delays are from 2 seconds to 1/64 second, and the
latter equation just doesn't make sense for that. Let's fix the
algorithm and the range check to match the documentation and the
downstream sources.

Reported-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Fixes: 92d57a73e410 ("input: Add support for Qualcomm PMIC8XXX power key")
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Tested-by: John Stultz <john.stultz@linaro.org>
Acked-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/input/misc/pmic8xxx-pwrkey.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/input/misc/pmic8xxx-pwrkey.c b/drivers/input/misc/pmic8xxx-pwrkey.c
index c4ca20e..b6d14bb 100644
--- a/drivers/input/misc/pmic8xxx-pwrkey.c
+++ b/drivers/input/misc/pmic8xxx-pwrkey.c
@@ -92,7 +92,8 @@ static int pmic8xxx_pwrkey_probe(struct platform_device *pdev)
 	if (of_property_read_u32(pdev->dev.of_node, "debounce", &kpd_delay))
 		kpd_delay = 15625;
 
-	if (kpd_delay > 62500 || kpd_delay == 0) {
+	/* Valid range of pwr key trigger delay is 1/64 sec to 2 seconds. */
+	if (kpd_delay > USEC_PER_SEC * 2 || kpd_delay < USEC_PER_SEC / 64) {
 		dev_err(&pdev->dev, "invalid power key trigger delay\n");
 		return -EINVAL;
 	}
@@ -122,8 +123,8 @@ static int pmic8xxx_pwrkey_probe(struct platform_device *pdev)
 	pwr->name = "pmic8xxx_pwrkey";
 	pwr->phys = "pmic8xxx_pwrkey/input0";
 
-	delay = (kpd_delay << 10) / USEC_PER_SEC;
-	delay = 1 + ilog2(delay);
+	delay = (kpd_delay << 6) / USEC_PER_SEC;
+	delay = ilog2(delay);
 
 	err = regmap_read(regmap, PON_CNTL_1, &pon_cntl);
 	if (err < 0) {
-- 
2.5.0

[added to the 4.1 stable tree] xen kconfig: don't "select INPUT_XEN_KBDDEV_FRONTEND"

[Sasha Levin]

From: Arnd Bergmann <arnd@arndb.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 13aa38e291bdd4e4018f40dd2f75e464814dcbf3 ]

The Xen framebuffer driver selects the xen keyboard driver, so the latter
will be built-in if XEN_FBDEV_FRONTEND=y. However, when CONFIG_INPUT
is a loadable module, this configuration cannot work. On mainline kernels,
the symbol will be enabled but not used, while in combination with
a patch I have to detect such useless configurations, we get the
expected link failure:

drivers/input/built-in.o: In function `xenkbd_remove':
xen-kbdfront.c:(.text+0x2f0): undefined reference to `input_unregister_device'
xen-kbdfront.c:(.text+0x30e): undefined reference to `input_unregister_device'

This removes the extra "select", as it just causes more trouble than
it helps. In theory, some defconfig file might break if it has
XEN_FBDEV_FRONTEND in it but not INPUT_XEN_KBDDEV_FRONTEND. The Kconfig
fragment we ship in the kernel (kernel/configs/xen.config) however
already enables both, and anyone using an old .config file would
keep having both enabled.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Suggested-by: David Vrabel <david.vrabel@citrix.com>
Fixes: 36c1132e34bd ("xen kconfig: fix select INPUT_XEN_KBDDEV_FRONTEND")
Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/video/fbdev/Kconfig | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig
index d1e1e17..44eb7c7 100644
--- a/drivers/video/fbdev/Kconfig
+++ b/drivers/video/fbdev/Kconfig
@@ -2246,7 +2246,6 @@ config XEN_FBDEV_FRONTEND
 	select FB_SYS_IMAGEBLIT
 	select FB_SYS_FOPS
 	select FB_DEFERRED_IO
-	select INPUT_XEN_KBDDEV_FRONTEND if INPUT_MISC
 	select XEN_XENBUS_FRONTEND
 	default y
 	help
-- 
2.5.0

[added to the 4.1 stable tree] pinctrl: single: Fix pcs_parse_bits_in_pinctrl_entry to use __ffs than ffs

[Sasha Levin]

From: Keerthy <j-keerthy@ti.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 56b367c0cd67d4c3006738e7dc9dda9273fd2bfe ]

pcs_parse_bits_in_pinctrl_entry uses ffs which gives bit indices
ranging from 1 to MAX. This leads to a corner case where we try to request
the pin number = MAX and fails.

bit_pos value is being calculted using ffs. pin_num_from_lsb uses
bit_pos value. pins array is populated with:

pin + pin_num_from_lsb.

The above is 1 more than usual bit indices as bit_pos uses ffs to compute
first set bit. Hence the last of the pins array is populated with the MAX
value and not MAX - 1 which causes error when we call pin_request.

mask_pos is rightly calculated as ((pcs->fmask) << (bit_pos - 1))
Consequently val_pos and submask are correct.

Hence use __ffs which gives (ffs(x) - 1) as the first bit set.

fixes: 4e7e8017a8 ("pinctrl: pinctrl-single: enhance to configure multiple pins of different modules")
Signed-off-by: Keerthy <j-keerthy@ti.com>
Acked-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/pinctrl/pinctrl-single.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c
index 11bf750..f2e4232 100644
--- a/drivers/pinctrl/pinctrl-single.c
+++ b/drivers/pinctrl/pinctrl-single.c
@@ -1273,9 +1273,9 @@ static int pcs_parse_bits_in_pinctrl_entry(struct pcs_device *pcs,
 
 		/* Parse pins in each row from LSB */
 		while (mask) {
-			bit_pos = ffs(mask);
+			bit_pos = __ffs(mask);
 			pin_num_from_lsb = bit_pos / pcs->bits_per_pin;
-			mask_pos = ((pcs->fmask) << (bit_pos - 1));
+			mask_pos = ((pcs->fmask) << bit_pos);
 			val_pos = val & mask_pos;
 			submask = mask & mask_pos;
 
@@ -1854,7 +1854,7 @@ static int pcs_probe(struct platform_device *pdev)
 	ret = of_property_read_u32(np, "pinctrl-single,function-mask",
 				   &pcs->fmask);
 	if (!ret) {
-		pcs->fshift = ffs(pcs->fmask) - 1;
+		pcs->fshift = __ffs(pcs->fmask);
 		pcs->fmax = pcs->fmask >> pcs->fshift;
 	} else {
 		/* If mask property doesn't exist, function mux is invalid. */
-- 
2.5.0

[added to the 4.1 stable tree] drm/i915: Cleanup phys status page too

[Sasha Levin]

From: Ville Syrjälä <ville.syrjala@linux.intel.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 7d3fdfff23852fe458a0d0979a3555fe60f1e563 ]

Restore the lost phys status page cleanup.

Fixes the following splat with DMA_API_DEBUG=y:

WARNING: CPU: 0 PID: 21615 at ../lib/dma-debug.c:974 dma_debug_device_change+0x190/0x1f0()
pci 0000:00:02.0: DMA-API: device driver has pending DMA allocations while released from device [count=1]
               One of leaked entries details: [device address=0x0000000023163000] [size=4096 bytes] [mapped with DMA_BIDIRECTIONAL] [mapped as coherent]
Modules linked in: i915(-) i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops drm sha256_generic hmac drbg ctr ccm sch_fq_codel binfmt_misc joydev mousedev arc4 ath5k iTCO_wdt mac80211 smsc_ircc2 ath snd_intel8x0m snd_intel8x0 snd_ac97_codec ac97_bus psmouse snd_pcm input_leds i2c_i801 pcspkr snd_timer cfg80211 snd soundcore i2c_core ehci_pci firewire_ohci ehci_hcd firewire_core lpc_ich 8139too rfkill crc_itu_t mfd_core mii usbcore rng_core intel_agp intel_gtt usb_common agpgart irda crc_ccitt fujitsu_laptop led_class parport_pc video parport evdev backlight
CPU: 0 PID: 21615 Comm: rmmod Tainted: G     U          4.4.0-rc4-mgm-ovl+ #4
Hardware name: FUJITSU SIEMENS LIFEBOOK S6120/FJNB16C, BIOS Version 1.26  05/10/2004
 e31a3de0 e31a3de0 e31a3d9c c128d4bd e31a3dd0 c1045a0c c15e00c4 e31a3dfc
 0000546f c15dfad2 000003ce c12b3740 000003ce c12b3740 00000000 00000001
 f61fb8a0 e31a3de8 c1045a83 00000009 e31a3de0 c15e00c4 e31a3dfc e31a3e4c
Call Trace:
 [<c128d4bd>] dump_stack+0x16/0x19
 [<c1045a0c>] warn_slowpath_common+0x8c/0xd0
 [<c12b3740>] ? dma_debug_device_change+0x190/0x1f0
 [<c12b3740>] ? dma_debug_device_change+0x190/0x1f0
 [<c1045a83>] warn_slowpath_fmt+0x33/0x40
 [<c12b3740>] dma_debug_device_change+0x190/0x1f0
 [<c1065499>] notifier_call_chain+0x59/0x70
 [<c10655af>] __blocking_notifier_call_chain+0x3f/0x80
 [<c106560f>] blocking_notifier_call_chain+0x1f/0x30
 [<c134cfb3>] __device_release_driver+0xc3/0xf0
 [<c134d0d7>] driver_detach+0x97/0xa0
 [<c134c440>] bus_remove_driver+0x40/0x90
 [<c134db18>] driver_unregister+0x28/0x60
 [<c1079e8c>] ? trace_hardirqs_on_caller+0x12c/0x1d0
 [<c12c0618>] pci_unregister_driver+0x18/0x80
 [<f83e96e7>] drm_pci_exit+0x87/0xb0 [drm]
 [<f8b3be2d>] i915_exit+0x1b/0x1ee [i915]
 [<c10b999c>] SyS_delete_module+0x14c/0x210
 [<c1079e8c>] ? trace_hardirqs_on_caller+0x12c/0x1d0
 [<c115a9bd>] ? ____fput+0xd/0x10
 [<c1002014>] do_fast_syscall_32+0xa4/0x450
 [<c149f6fa>] sysenter_past_esp+0x3b/0x5d
---[ end trace c2ecbc77760f10a0 ]---
Mapped at:
 [<c12b3183>] debug_dma_alloc_coherent+0x33/0x90
 [<f83e989c>] drm_pci_alloc+0x18c/0x1e0 [drm]
 [<f8acd59f>] intel_init_ring_buffer+0x2af/0x490 [i915]
 [<f8acd8b0>] intel_init_render_ring_buffer+0x130/0x750 [i915]
 [<f8aaea4e>] i915_gem_init_rings+0x1e/0x110 [i915]

v2: s/BUG_ON/WARN_ON/ since dim doens't like the former anymore

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Fixes: 5c6c600 ("drm/i915: Remove DRI1 ring accessors and API")
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> (v1)
Link: http://patchwork.freedesktop.org/patch/msgid/1452538112-5331-1-git-send-email-ville.syrjala@linux.intel.com
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 24 ++++++++++++++++++++----
 1 file changed, 20 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index b7e20de..09844b5 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1814,6 +1814,17 @@ i915_dispatch_execbuffer(struct intel_engine_cs *ring,
 	return 0;
 }
 
+static void cleanup_phys_status_page(struct intel_engine_cs *ring)
+{
+	struct drm_i915_private *dev_priv = to_i915(ring->dev);
+
+	if (!dev_priv->status_page_dmah)
+		return;
+
+	drm_pci_free(ring->dev, dev_priv->status_page_dmah);
+	ring->status_page.page_addr = NULL;
+}
+
 static void cleanup_status_page(struct intel_engine_cs *ring)
 {
 	struct drm_i915_gem_object *obj;
@@ -1830,9 +1841,9 @@ static void cleanup_status_page(struct intel_engine_cs *ring)
 
 static int init_status_page(struct intel_engine_cs *ring)
 {
-	struct drm_i915_gem_object *obj;
+	struct drm_i915_gem_object *obj = ring->status_page.obj;
 
-	if ((obj = ring->status_page.obj) == NULL) {
+	if (obj == NULL) {
 		unsigned flags;
 		int ret;
 
@@ -1985,7 +1996,7 @@ static int intel_init_ring_buffer(struct drm_device *dev,
 		if (ret)
 			goto error;
 	} else {
-		BUG_ON(ring->id != RCS);
+		WARN_ON(ring->id != RCS);
 		ret = init_phys_status_page(ring);
 		if (ret)
 			goto error;
@@ -2049,7 +2060,12 @@ void intel_cleanup_ring_buffer(struct intel_engine_cs *ring)
 	if (ring->cleanup)
 		ring->cleanup(ring);
 
-	cleanup_status_page(ring);
+	if (I915_NEED_GFX_HWS(ring->dev)) {
+		cleanup_status_page(ring);
+	} else {
+		WARN_ON(ring->id != RCS);
+		cleanup_phys_status_page(ring);
+	}
 
 	i915_cmd_parser_fini_ring(ring);
 
-- 
2.5.0

[added to the 4.1 stable tree] i2c: exynos5: Fix possible ABBA deadlock by keeping I2C clock prepared

[Sasha Levin]

From: Javier Martinez Canillas <javier@osg.samsung.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 10ff4c5239a137abfc896ec73ef3d15a0f86a16a ]

The exynos5 I2C controller driver always prepares and enables a clock
before using it and then disables unprepares it when the clock is not
used anymore.

But this can cause a possible ABBA deadlock in some scenarios since a
driver that uses regmap to access its I2C registers, will first grab
the regmap lock and then the I2C xfer function will grab the prepare
lock when preparing the I2C clock. But since the clock driver also
uses regmap for I2C accesses, preparing a clock will first grab the
prepare lock and then the regmap lock when using the regmap API.

An example of this happens on the Exynos5422 Odroid XU4 board where a
s2mps11 PMIC is used and both the s2mps11 regulators and clk drivers
share the same I2C regmap.

The possible deadlock is reported by the kernel lockdep:

  Possible unsafe locking scenario:

        CPU0                    CPU1
        ----                    ----
   lock(sec_core:428:(regmap)->lock);
                                lock(prepare_lock);
                                lock(sec_core:428:(regmap)->lock);
   lock(prepare_lock);

  *** DEADLOCK ***

Fix it by leaving the code prepared on probe and use {en,dis}able in
the I2C transfer function.

This patch is similar to commit 34e81ad5f0b6 ("i2c: s3c2410: fix ABBA
deadlock by keeping clock prepared") that fixes the same bug in other
driver for an I2C controller found in Samsung SoCs.

Reported-by: Anand Moon <linux.amoon@gmail.com>
Signed-off-by: Javier Martinez Canillas <javier@osg.samsung.com>
Reviewed-by: Anand Moon <linux.amoon@gmail.com>
Reviewed-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
Cc: stable@kernel.org
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/i2c/busses/i2c-exynos5.c | 24 +++++++++++++++++++-----
 1 file changed, 19 insertions(+), 5 deletions(-)

diff --git a/drivers/i2c/busses/i2c-exynos5.c b/drivers/i2c/busses/i2c-exynos5.c
index b29c750..f54ece8 100644
--- a/drivers/i2c/busses/i2c-exynos5.c
+++ b/drivers/i2c/busses/i2c-exynos5.c
@@ -671,7 +671,9 @@ static int exynos5_i2c_xfer(struct i2c_adapter *adap,
 		return -EIO;
 	}
 
-	clk_prepare_enable(i2c->clk);
+	ret = clk_enable(i2c->clk);
+	if (ret)
+		return ret;
 
 	for (i = 0; i < num; i++, msgs++) {
 		stop = (i == num - 1);
@@ -695,7 +697,7 @@ static int exynos5_i2c_xfer(struct i2c_adapter *adap,
 	}
 
  out:
-	clk_disable_unprepare(i2c->clk);
+	clk_disable(i2c->clk);
 	return ret;
 }
 
@@ -747,7 +749,9 @@ static int exynos5_i2c_probe(struct platform_device *pdev)
 		return -ENOENT;
 	}
 
-	clk_prepare_enable(i2c->clk);
+	ret = clk_prepare_enable(i2c->clk);
+	if (ret)
+		return ret;
 
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	i2c->regs = devm_ioremap_resource(&pdev->dev, mem);
@@ -799,6 +803,10 @@ static int exynos5_i2c_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, i2c);
 
+	clk_disable(i2c->clk);
+
+	return 0;
+
  err_clk:
 	clk_disable_unprepare(i2c->clk);
 	return ret;
@@ -810,6 +818,8 @@ static int exynos5_i2c_remove(struct platform_device *pdev)
 
 	i2c_del_adapter(&i2c->adap);
 
+	clk_unprepare(i2c->clk);
+
 	return 0;
 }
 
@@ -821,6 +831,8 @@ static int exynos5_i2c_suspend_noirq(struct device *dev)
 
 	i2c->suspended = 1;
 
+	clk_unprepare(i2c->clk);
+
 	return 0;
 }
 
@@ -830,7 +842,9 @@ static int exynos5_i2c_resume_noirq(struct device *dev)
 	struct exynos5_i2c *i2c = platform_get_drvdata(pdev);
 	int ret = 0;
 
-	clk_prepare_enable(i2c->clk);
+	ret = clk_prepare_enable(i2c->clk);
+	if (ret)
+		return ret;
 
 	ret = exynos5_hsi2c_clock_setup(i2c);
 	if (ret) {
@@ -839,7 +853,7 @@ static int exynos5_i2c_resume_noirq(struct device *dev)
 	}
 
 	exynos5_i2c_init(i2c);
-	clk_disable_unprepare(i2c->clk);
+	clk_disable(i2c->clk);
 	i2c->suspended = 0;
 
 	return 0;
-- 
2.5.0

[added to the 4.1 stable tree] ASoC: s3c24xx: use const snd_soc_component_driver pointer

[Sasha Levin]

From: Arnd Bergmann <arnd@arndb.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit ba4bc32eaa39ba7687f0958ae90eec94da613b46 ]

An older patch to convert the API in the s3c i2s driver
ended up passing a const pointer into a function that takes
a non-const pointer, so we now get a warning:

sound/soc/samsung/s3c2412-i2s.c: In function 's3c2412_iis_dev_probe':
sound/soc/samsung/s3c2412-i2s.c:172:9: error: passing argument 3 of 's3c_i2sv2_register_component' discards 'const' qualifier from pointer target type [-Werror=discarded-qualifiers]

However, the s3c_i2sv2_register_component() function again
passes the pointer into another function taking a const, so
we just need to change its prototype.

Fixes: eca3b01d0885 ("ASoC: switch over to use snd_soc_register_component() on s3c i2s")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 sound/soc/samsung/s3c-i2s-v2.c | 2 +-
 sound/soc/samsung/s3c-i2s-v2.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/soc/samsung/s3c-i2s-v2.c b/sound/soc/samsung/s3c-i2s-v2.c
index df65c5b..b6ab3fc 100644
--- a/sound/soc/samsung/s3c-i2s-v2.c
+++ b/sound/soc/samsung/s3c-i2s-v2.c
@@ -709,7 +709,7 @@ static int s3c2412_i2s_resume(struct snd_soc_dai *dai)
 #endif
 
 int s3c_i2sv2_register_component(struct device *dev, int id,
-			   struct snd_soc_component_driver *cmp_drv,
+			   const struct snd_soc_component_driver *cmp_drv,
 			   struct snd_soc_dai_driver *dai_drv)
 {
 	struct snd_soc_dai_ops *ops = (struct snd_soc_dai_ops *)dai_drv->ops;
diff --git a/sound/soc/samsung/s3c-i2s-v2.h b/sound/soc/samsung/s3c-i2s-v2.h
index 90abab3..d068414 100644
--- a/sound/soc/samsung/s3c-i2s-v2.h
+++ b/sound/soc/samsung/s3c-i2s-v2.h
@@ -101,7 +101,7 @@ extern int s3c_i2sv2_probe(struct snd_soc_dai *dai,
  * soc core.
  */
 extern int s3c_i2sv2_register_component(struct device *dev, int id,
-					struct snd_soc_component_driver *cmp_drv,
+					const struct snd_soc_component_driver *cmp_drv,
 					struct snd_soc_dai_driver *dai_drv);
 
 #endif /* __SND_SOC_S3C24XX_S3C_I2SV2_I2S_H */
-- 
2.5.0

[added to the 4.1 stable tree] ASoC: ssm4567: Reset device before regcache_sync()

[Sasha Levin]

From: Lars-Peter Clausen <lars@metafoo.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 712a8038cc24dba668afe82f0413714ca87184e0 ]

When the ssm4567 is powered up the driver calles regcache_sync() to restore
the register map content. regcache_sync() assumes that the device is in its
power-on reset state. Make sure that this is the case by explicitly
resetting the ssm4567 register map before calling regcache_sync() otherwise
we might end up with a incorrect register map which leads to undefined
behaviour.

One such undefined behaviour was observed when returning from system
suspend while a playback stream is active, in that case the ssm4567 was
kept muted after resume.

Fixes: 1ee44ce03011 ("ASoC: ssm4567: Add driver for Analog Devices SSM4567 amplifier")
Reported-by: Harsha Priya <harshapriya.n@intel.com>
Tested-by: Fang, Yang A <yang.a.fang@intel.com>
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 sound/soc/codecs/ssm4567.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/sound/soc/codecs/ssm4567.c b/sound/soc/codecs/ssm4567.c
index f7549cc..d1f53ab 100644
--- a/sound/soc/codecs/ssm4567.c
+++ b/sound/soc/codecs/ssm4567.c
@@ -338,6 +338,11 @@ static int ssm4567_set_power(struct ssm4567 *ssm4567, bool enable)
 	regcache_cache_only(ssm4567->regmap, !enable);
 
 	if (enable) {
+		ret = regmap_write(ssm4567->regmap, SSM4567_REG_SOFT_RESET,
+			0x00);
+		if (ret)
+			return ret;
+
 		ret = regmap_update_bits(ssm4567->regmap,
 			SSM4567_REG_POWER_CTRL,
 			SSM4567_POWER_SPWDN, 0x00);
-- 
2.5.0

[added to the 4.1 stable tree] efi: Expose non-blocking set_variable() wrapper to efivars

[Sasha Levin]

From: Ard Biesheuvel <ard.biesheuvel@linaro.org>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 9c6672ac9c91f7eb1ec436be1442b8c26d098e55 ]

Commit 6d80dba1c9fe ("efi: Provide a non-blocking SetVariable()
operation") implemented a non-blocking alternative for the UEFI
SetVariable() invocation performed by efivars, since it may
occur in atomic context. However, this version of the function
was never exposed via the efivars struct, so the non-blocking
versions was not actually callable. Fix that.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-efi@vger.kernel.org
Fixes: 6d80dba1c9fe ("efi: Provide a non-blocking SetVariable() operation")
Link: http://lkml.kernel.org/r/1454364428-494-2-git-send-email-matt@codeblueprint.co.uk
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/firmware/efi/efi.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 63226e9..1f2c86d 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -170,6 +170,7 @@ static int generic_ops_register(void)
 {
 	generic_ops.get_variable = efi.get_variable;
 	generic_ops.set_variable = efi.set_variable;
+	generic_ops.set_variable_nonblocking = efi.set_variable_nonblocking;
 	generic_ops.get_next_variable = efi.get_next_variable;
 	generic_ops.query_variable_store = efi_query_variable_store;
 
-- 
2.5.0

[added to the 4.1 stable tree] cgroup: make sure a parent css isn't freed before its children

[Sasha Levin]

From: Tejun Heo <tj@kernel.org>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 8bb5ef79bc0f4016ecf79e8dce6096a3c63603e4 ]

There are three subsystem callbacks in css shutdown path -
css_offline(), css_released() and css_free().  Except for
css_released(), cgroup core didn't guarantee the order of invocation.
css_offline() or css_free() could be called on a parent css before its
children.  This behavior is unexpected and led to bugs in cpu and
memory controller.

The previous patch updated ordering for css_offline() which fixes the
cpu controller issue.  While there currently isn't a known bug caused
by misordering of css_free() invocations, let's fix it too for
consistency.

css_free() ordering can be trivially fixed by moving putting of the
parent css below css_free() invocation.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 kernel/cgroup.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index d01c604..3abce1e 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4378,14 +4378,15 @@ static void css_free_work_fn(struct work_struct *work)
 
 	if (ss) {
 		/* css free path */
+		struct cgroup_subsys_state *parent = css->parent;
 		int id = css->id;
 
-		if (css->parent)
-			css_put(css->parent);
-
 		ss->css_free(css);
 		cgroup_idr_remove(&ss->css_idr, id);
 		cgroup_put(cgrp);
+
+		if (parent)
+			css_put(parent);
 	} else {
 		/* cgroup free path */
 		atomic_dec(&cgrp->root->nr_cgrps);
-- 
2.5.0

[added to the 4.1 stable tree] USB: usbip: fix potential out-of-bounds write

[Sasha Levin]

From: Ignat Korchagin <ignat.korchagin@gmail.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit b348d7dddb6c4fbfc810b7a0626e8ec9e29f7cbb ]

Fix potential out-of-bounds write to urb->transfer_buffer
usbip handles network communication directly in the kernel. When receiving a
packet from its peer, usbip code parses headers according to protocol. As
part of this parsing urb->actual_length is filled. Since the input for
urb->actual_length comes from the network, it should be treated as untrusted.
Any entity controlling the network may put any value in the input and the
preallocated urb->transfer_buffer may not be large enough to hold the data.
Thus, the malicious entity is able to write arbitrary data to kernel memory.

Signed-off-by: Ignat Korchagin <ignat.korchagin@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/usb/usbip/usbip_common.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/usb/usbip/usbip_common.c b/drivers/usb/usbip/usbip_common.c
index facaaf0..e40da77 100644
--- a/drivers/usb/usbip/usbip_common.c
+++ b/drivers/usb/usbip/usbip_common.c
@@ -741,6 +741,17 @@ int usbip_recv_xbuff(struct usbip_device *ud, struct urb *urb)
 	if (!(size > 0))
 		return 0;
 
+	if (size > urb->transfer_buffer_length) {
+		/* should not happen, probably malicious packet */
+		if (ud->side == USBIP_STUB) {
+			usbip_event_add(ud, SDEV_EVENT_ERROR_TCP);
+			return 0;
+		} else {
+			usbip_event_add(ud, VDEV_EVENT_ERROR_TCP);
+			return -EPIPE;
+		}
+	}
+
 	ret = usbip_recv(ud->tcp_socket, urb->transfer_buffer, size);
 	if (ret != size) {
 		dev_err(&urb->dev->dev, "recv xbuf, %d\n", ret);
-- 
2.5.0

[added to the 4.1 stable tree] spi/rockchip: Make sure spi clk is on in rockchip_spi_set_cs

[Sasha Levin]

From: Huibin Hong <huibin.hong@rock-chips.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit b920cc3191d7612f26f36ee494e05b5ffd9044c0 ]

Rockchip_spi_set_cs could be called by spi_setup, but
spi_setup may be called by device driver after runtime suspend.
Then the spi clock is closed, rockchip_spi_set_cs may access the
spi registers, which causes cpu block in some socs.

Fixes: 64e36824b32 ("spi/rockchip: add driver for Rockchip RK3xxx")
Signed-off-by: Huibin Hong <huibin.hong@rock-chips.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/spi/spi-rockchip.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c
index 68e7efe..1d308cb 100644
--- a/drivers/spi/spi-rockchip.c
+++ b/drivers/spi/spi-rockchip.c
@@ -265,7 +265,10 @@ static inline u32 rx_max(struct rockchip_spi *rs)
 static void rockchip_spi_set_cs(struct spi_device *spi, bool enable)
 {
 	u32 ser;
-	struct rockchip_spi *rs = spi_master_get_devdata(spi->master);
+	struct spi_master *master = spi->master;
+	struct rockchip_spi *rs = spi_master_get_devdata(master);
+
+	pm_runtime_get_sync(rs->dev);
 
 	ser = readl_relaxed(rs->regs + ROCKCHIP_SPI_SER) & SER_MASK;
 
@@ -290,6 +293,8 @@ static void rockchip_spi_set_cs(struct spi_device *spi, bool enable)
 		ser &= ~(1 << spi->chip_select);
 
 	writel_relaxed(ser, rs->regs + ROCKCHIP_SPI_SER);
+
+	pm_runtime_put_sync(rs->dev);
 }
 
 static int rockchip_spi_prepare_message(struct spi_master *master,
-- 
2.5.0

[added to the 4.1 stable tree] regulator: s5m8767: fix get_register() error handling

[Sasha Levin]

From: Arnd Bergmann <arnd@arndb.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit e07ff9434167981c993a26d2edbbcb8e13801dbb ]

The s5m8767_pmic_probe() function calls s5m8767_get_register() to
read data without checking the return code, which produces a compile-time
warning when that data is accessed:

drivers/regulator/s5m8767.c: In function 's5m8767_pmic_probe':
drivers/regulator/s5m8767.c:924:7: error: 'enable_reg' may be used uninitialized in this function [-Werror=maybe-uninitialized]
drivers/regulator/s5m8767.c:944:30: error: 'enable_val' may be used uninitialized in this function [-Werror=maybe-uninitialized]

This changes the s5m8767_get_register() function to return a -EINVAL
not just for an invalid register number but also for an invalid
regulator number, as both would result in returning uninitialized
data. The s5m8767_pmic_probe() function is then changed accordingly
to fail on a read error, as all the other callers of s5m8767_get_register()
already do.

In practice this probably cannot happen, as we don't call
s5m8767_get_register() with invalid arguments, but the gcc
warning seems valid in principle, in terms writing safe
error checking.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Fixes: 9c4c60554acf ("regulator: s5m8767: Convert to use regulator_[enable|disable|is_enabled]_regmap")
Signed-off-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/regulator/s5m8767.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/regulator/s5m8767.c b/drivers/regulator/s5m8767.c
index 58f5d3b..27343e1 100644
--- a/drivers/regulator/s5m8767.c
+++ b/drivers/regulator/s5m8767.c
@@ -202,9 +202,10 @@ static int s5m8767_get_register(struct s5m8767_info *s5m8767, int reg_id,
 		}
 	}
 
-	if (i < s5m8767->num_regulators)
-		*enable_ctrl =
-		s5m8767_opmode_reg[reg_id][mode] << S5M8767_ENCTRL_SHIFT;
+	if (i >= s5m8767->num_regulators)
+		return -EINVAL;
+
+	*enable_ctrl = s5m8767_opmode_reg[reg_id][mode] << S5M8767_ENCTRL_SHIFT;
 
 	return 0;
 }
@@ -937,8 +938,12 @@ static int s5m8767_pmic_probe(struct platform_device *pdev)
 			else
 				regulators[id].vsel_mask = 0xff;
 
-			s5m8767_get_register(s5m8767, id, &enable_reg,
+			ret = s5m8767_get_register(s5m8767, id, &enable_reg,
 					     &enable_val);
+			if (ret) {
+				dev_err(s5m8767->dev, "error reading registers\n");
+				return ret;
+			}
 			regulators[id].enable_reg = enable_reg;
 			regulators[id].enable_mask = S5M8767_ENCTRL_MASK;
 			regulators[id].enable_val = enable_val;
-- 
2.5.0

[added to the 4.1 stable tree] paride: make 'verbose' parameter an 'int' again

[Sasha Levin]

From: Arnd Bergmann <arnd@arndb.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit dec63a4dec2d6d01346fd5d96062e67c0636852b ]

gcc-6.0 found an ancient bug in the paride driver, which had a
"module_param(verbose, bool, 0);" since before 2.6.12, but actually uses
it to accept '0', '1' or '2' as arguments:

  drivers/block/paride/pd.c: In function 'pd_init_dev_parms':
  drivers/block/paride/pd.c:298:29: warning: comparison of constant '1' with boolean expression is always false [-Wbool-compare]
   #define DBMSG(msg) ((verbose>1)?(msg):NULL)

In 2012, Rusty did a cleanup patch that also changed the type of the
variable to 'bool', which introduced what is now a gcc warning.

This changes the type back to 'int' and adapts the module_param() line
instead, so it should work as documented in case anyone ever cares about
running the ancient driver with debugging.

Fixes: 90ab5ee94171 ("module_param: make bool parameters really bool (drivers & misc)")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Rusty Russell <rusty@rustcorp.com.au>
Cc: Tim Waugh <tim@cyberelk.net>
Cc: Sudip Mukherjee <sudipm.mukherjee@gmail.com>
Cc: Jens Axboe <axboe@fb.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/block/paride/pd.c | 4 ++--
 drivers/block/paride/pt.c | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index d48715b..b041470 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -126,7 +126,7 @@
 */
 #include <linux/types.h>
 
-static bool verbose = 0;
+static int verbose = 0;
 static int major = PD_MAJOR;
 static char *name = PD_NAME;
 static int cluster = 64;
@@ -161,7 +161,7 @@ enum {D_PRT, D_PRO, D_UNI, D_MOD, D_GEO, D_SBY, D_DLY, D_SLV};
 static DEFINE_MUTEX(pd_mutex);
 static DEFINE_SPINLOCK(pd_lock);
 
-module_param(verbose, bool, 0);
+module_param(verbose, int, 0);
 module_param(major, int, 0);
 module_param(name, charp, 0);
 module_param(cluster, int, 0);
diff --git a/drivers/block/paride/pt.c b/drivers/block/paride/pt.c
index 2596042..ada4505 100644
--- a/drivers/block/paride/pt.c
+++ b/drivers/block/paride/pt.c
@@ -117,7 +117,7 @@
 
 */
 
-static bool verbose = 0;
+static int verbose = 0;
 static int major = PT_MAJOR;
 static char *name = PT_NAME;
 static int disable = 0;
@@ -152,7 +152,7 @@ static int (*drives[4])[6] = {&drive0, &drive1, &drive2, &drive3};
 
 #include <asm/uaccess.h>
 
-module_param(verbose, bool, 0);
+module_param(verbose, int, 0);
 module_param(major, int, 0);
 module_param(name, charp, 0);
 module_param_array(drive0, int, NULL, 0);
-- 
2.5.0

[added to the 4.1 stable tree] fbdev: da8xx-fb: fix videomodes of lcd panels

[Sasha Levin]

From: Sushaanth Srirangapathi <sushaanth.s@ti.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 713fced8d10fa1c759c8fb6bf9aaa681bae68cad ]

Commit 028cd86b794f4a ("video: da8xx-fb: fix the polarities of the
hsync/vsync pulse") fixes polarities of HSYNC/VSYNC pulse but
forgot to update known_lcd_panels[] which had sync values
according to old logic. This breaks LCD at least on DA850 EVM.

This patch fixes this issue and I have tested this for panel
"Sharp_LK043T1DG01" using DA850 EVM board.

Fixes: 028cd86b794f4a ("video: da8xx-fb: fix the polarities of the hsync/vsync pulse")
Signed-off-by: Sushaanth Srirangapathi <sushaanth.s@ti.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/video/fbdev/da8xx-fb.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/video/fbdev/da8xx-fb.c b/drivers/video/fbdev/da8xx-fb.c
index 0081725..d005100 100644
--- a/drivers/video/fbdev/da8xx-fb.c
+++ b/drivers/video/fbdev/da8xx-fb.c
@@ -209,8 +209,7 @@ static struct fb_videomode known_lcd_panels[] = {
 		.lower_margin   = 2,
 		.hsync_len      = 0,
 		.vsync_len      = 0,
-		.sync           = FB_SYNC_CLK_INVERT |
-			FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+		.sync           = FB_SYNC_CLK_INVERT,
 	},
 	/* Sharp LK043T1DG01 */
 	[1] = {
@@ -224,7 +223,7 @@ static struct fb_videomode known_lcd_panels[] = {
 		.lower_margin   = 2,
 		.hsync_len      = 41,
 		.vsync_len      = 10,
-		.sync           = FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+		.sync           = 0,
 		.flag           = 0,
 	},
 	[2] = {
@@ -239,7 +238,7 @@ static struct fb_videomode known_lcd_panels[] = {
 		.lower_margin   = 10,
 		.hsync_len      = 10,
 		.vsync_len      = 10,
-		.sync           = FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+		.sync           = 0,
 		.flag           = 0,
 	},
 	[3] = {
-- 
2.5.0

[added to the 4.1 stable tree] misc/bmp085: Enable building as a module

[Sasha Levin]

From: Ben Hutchings <ben@decadent.org.uk>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 50e6315dba721cbc24ccd6d7b299f1782f210a98 ]

Commit 985087dbcb02 'misc: add support for bmp18x chips to the bmp085
driver' changed the BMP085 config symbol to a boolean.  I see no
reason why the shared code cannot be built as a module, so change it
back to tristate.

Fixes: 985087dbcb02 ("misc: add support for bmp18x chips to the bmp085 driver")
Cc: Eric Andersson <eric.andersson@unixphere.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/misc/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index 006242c..b3c10b7 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -429,7 +429,7 @@ config ARM_CHARLCD
 	  still useful.
 
 config BMP085
-	bool
+	tristate
 	depends on SYSFS
 
 config BMP085_I2C
-- 
2.5.0

[added to the 4.1 stable tree] rtc: hym8563: fix invalid year calculation

[Sasha Levin]

From: Alexander Kochetkov <al.kochet@gmail.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit d5861262210067fc01b2fb4f7af2fd85a3453f15 ]

Year field must be in BCD format, according to
hym8563 datasheet.

Due to the bug year 2016 became 2010.

Fixes: dcaf03849352 ("rtc: add hym8563 rtc-driver")
Signed-off-by: Alexander Kochetkov <al.kochet@gmail.com>
Signed-off-by: Alexandre Belloni <alexandre.belloni@free-electrons.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/rtc/rtc-hym8563.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/rtc/rtc-hym8563.c b/drivers/rtc/rtc-hym8563.c
index 0f710e9..3db1557 100644
--- a/drivers/rtc/rtc-hym8563.c
+++ b/drivers/rtc/rtc-hym8563.c
@@ -144,7 +144,7 @@ static int hym8563_rtc_set_time(struct device *dev, struct rtc_time *tm)
 	 * it does not seem to carry it over a subsequent write/read.
 	 * So we'll limit ourself to 100 years, starting at 2000 for now.
 	 */
-	buf[6] = tm->tm_year - 100;
+	buf[6] = bin2bcd(tm->tm_year - 100);
 
 	/*
 	 * CTL1 only contains TEST-mode bits apart from stop,
-- 
2.5.0

[added to the 4.1 stable tree] rtc: vr41xx: Wire up alarm_irq_enable

[Sasha Levin]

From: Geert Uytterhoeven <geert@linux-m68k.org>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit a25f4a95ec3cded34c1250364eba704c5e4fdac4 ]

drivers/rtc/rtc-vr41xx.c:229: warning: ‘vr41xx_rtc_alarm_irq_enable’ defined but not used

Apparently the conversion to alarm_irq_enable forgot to wire up the
callback.

Fixes: 16380c153a69c378 ("RTC: Convert rtc drivers to use the alarm_irq_enable method")
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Alexandre Belloni <alexandre.belloni@free-electrons.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/rtc/rtc-vr41xx.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/rtc/rtc-vr41xx.c b/drivers/rtc/rtc-vr41xx.c
index f64c282..e1b86bb 100644
--- a/drivers/rtc/rtc-vr41xx.c
+++ b/drivers/rtc/rtc-vr41xx.c
@@ -272,12 +272,13 @@ static irqreturn_t rtclong1_interrupt(int irq, void *dev_id)
 }
 
 static const struct rtc_class_ops vr41xx_rtc_ops = {
-	.release	= vr41xx_rtc_release,
-	.ioctl		= vr41xx_rtc_ioctl,
-	.read_time	= vr41xx_rtc_read_time,
-	.set_time	= vr41xx_rtc_set_time,
-	.read_alarm	= vr41xx_rtc_read_alarm,
-	.set_alarm	= vr41xx_rtc_set_alarm,
+	.release		= vr41xx_rtc_release,
+	.ioctl			= vr41xx_rtc_ioctl,
+	.read_time		= vr41xx_rtc_read_time,
+	.set_time		= vr41xx_rtc_set_time,
+	.read_alarm		= vr41xx_rtc_read_alarm,
+	.set_alarm		= vr41xx_rtc_set_alarm,
+	.alarm_irq_enable	= vr41xx_rtc_alarm_irq_enable,
 };
 
 static int rtc_probe(struct platform_device *pdev)
-- 
2.5.0

[added to the 4.1 stable tree] rtc: ds1685: passing bogus values to irq_restore

[Sasha Levin]

From: Dan Carpenter <dan.carpenter@oracle.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 8c09b9fdecab1f4a289f07b46e2ad174b6641928 ]

We call spin_lock_irqrestore with "flags" set to zero instead of to the
value from spin_lock_irqsave().

Fixes: aaaf5fbf56f1 ('rtc: add driver for DS1685 family of real time clocks')
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Alexandre Belloni <alexandre.belloni@free-electrons.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/rtc/rtc-ds1685.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/rtc/rtc-ds1685.c b/drivers/rtc/rtc-ds1685.c
index 818a363..8686588 100644
--- a/drivers/rtc/rtc-ds1685.c
+++ b/drivers/rtc/rtc-ds1685.c
@@ -187,9 +187,9 @@ ds1685_rtc_end_data_access(struct ds1685_priv *rtc)
  * Only use this where you are certain another lock will not be held.
  */
 static inline void
-ds1685_rtc_begin_ctrl_access(struct ds1685_priv *rtc, unsigned long flags)
+ds1685_rtc_begin_ctrl_access(struct ds1685_priv *rtc, unsigned long *flags)
 {
-	spin_lock_irqsave(&rtc->lock, flags);
+	spin_lock_irqsave(&rtc->lock, *flags);
 	ds1685_rtc_switch_to_bank1(rtc);
 }
 
@@ -1304,7 +1304,7 @@ ds1685_rtc_sysfs_ctrl_regs_store(struct device *dev,
 {
 	struct ds1685_priv *rtc = dev_get_drvdata(dev);
 	u8 reg = 0, bit = 0, tmp;
-	unsigned long flags = 0;
+	unsigned long flags;
 	long int val = 0;
 	const struct ds1685_rtc_ctrl_regs *reg_info =
 		ds1685_rtc_sysfs_ctrl_regs_lookup(attr->attr.name);
@@ -1325,7 +1325,7 @@ ds1685_rtc_sysfs_ctrl_regs_store(struct device *dev,
 	bit = reg_info->bit;
 
 	/* Safe to spinlock during a write. */
-	ds1685_rtc_begin_ctrl_access(rtc, flags);
+	ds1685_rtc_begin_ctrl_access(rtc, &flags);
 	tmp = rtc->read(rtc, reg);
 	rtc->write(rtc, reg, (val ? (tmp | bit) : (tmp & ~(bit))));
 	ds1685_rtc_end_ctrl_access(rtc, flags);
-- 
2.5.0

[added to the 4.1 stable tree] rtc: max77686: Properly handle regmap_irq_get_virq() error code

[Sasha Levin]

From: Krzysztof Kozlowski <k.kozlowski@samsung.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit fb166ba1d7f0a662f7332f4ff660a0d6f4d76915 ]

The regmap_irq_get_virq() can return 0 or -EINVAL in error conditions
but driver checked only for value of 0.

This could lead to a cast of -EINVAL to an unsigned int used as a
interrupt number for devm_request_threaded_irq(). Although this is not
yet fatal (devm_request_threaded_irq() will just fail with -EINVAL) but
might be a misleading when diagnosing errors.

Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Fixes: 6f1c1e71d933 ("mfd: max77686: Convert to use regmap_irq")
Reviewed-by: Javier Martinez Canillas <javier@osg.samsung.com>
Signed-off-by: Alexandre Belloni <alexandre.belloni@free-electrons.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/rtc/rtc-max77686.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/rtc/rtc-max77686.c b/drivers/rtc/rtc-max77686.c
index 7632a87..d42cef0 100644
--- a/drivers/rtc/rtc-max77686.c
+++ b/drivers/rtc/rtc-max77686.c
@@ -465,7 +465,7 @@ static int max77686_rtc_probe(struct platform_device *pdev)
 
 	info->virq = regmap_irq_get_virq(max77686->rtc_irq_data,
 					 MAX77686_RTCIRQ_RTCA1);
-	if (!info->virq) {
+	if (info->virq <= 0) {
 		ret = -ENXIO;
 		goto err_rtc;
 	}
-- 
2.5.0

[added to the 4.1 stable tree] drivers/misc/ad525x_dpot: AD5274 fix RDAC read back errors

[Sasha Levin]

From: Michael Hennerich <michael.hennerich@analog.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit f3df53e4d70b5736368a8fe8aa1bb70c1cb1f577 ]

Fix RDAC read back errors caused by a typo. Value must shift by 2.

Fixes: a4bd394956f2 ("drivers/misc/ad525x_dpot.c: new features")
Signed-off-by: Michael Hennerich <michael.hennerich@analog.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/misc/ad525x_dpot.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/misc/ad525x_dpot.c b/drivers/misc/ad525x_dpot.c
index 15e8807..f1a0b99 100644
--- a/drivers/misc/ad525x_dpot.c
+++ b/drivers/misc/ad525x_dpot.c
@@ -216,7 +216,7 @@ static s32 dpot_read_i2c(struct dpot_data *dpot, u8 reg)
 			 */
 			value = swab16(value);
 
-			if (dpot->uid == DPOT_UID(AD5271_ID))
+			if (dpot->uid == DPOT_UID(AD5274_ID))
 				value = value >> 2;
 		return value;
 	default:
-- 
2.5.0

[added to the 4.1 stable tree] x86/mm/kmmio: Fix mmiotrace for hugepages

[Sasha Levin]

From: Karol Herbst <nouveau@karolherbst.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit cfa52c0cfa4d727aa3e457bf29aeff296c528a08 ]

Because Linux might use bigger pages than the 4K pages to handle those mmio
ioremaps, the kmmio code shouldn't rely on the pade id as it currently does.

Using the memory address instead of the page id lets us look up how big the
page is and what its base address is, so that we won't get a page fault
within the same page twice anymore.

Tested-by: Pierre Moreau <pierre.morrow@free.fr>
Signed-off-by: Karol Herbst <nouveau@karolherbst.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luis R. Rodriguez <mcgrof@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Toshi Kani <toshi.kani@hp.com>
Cc: linux-mm@kvack.org
Cc: linux-x86_64@vger.kernel.org
Cc: nouveau@lists.freedesktop.org
Cc: pq@iki.fi
Cc: rostedt@goodmis.org
Link: http://lkml.kernel.org/r/1456966991-6861-1-git-send-email-nouveau@karolherbst.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 arch/x86/mm/kmmio.c | 88 +++++++++++++++++++++++++++++++++++------------------
 1 file changed, 59 insertions(+), 29 deletions(-)

diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index 637ab34..ddb2244 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -33,7 +33,7 @@
 struct kmmio_fault_page {
 	struct list_head list;
 	struct kmmio_fault_page *release_next;
-	unsigned long page; /* location of the fault page */
+	unsigned long addr; /* the requested address */
 	pteval_t old_presence; /* page presence prior to arming */
 	bool armed;
 
@@ -70,9 +70,16 @@ unsigned int kmmio_count;
 static struct list_head kmmio_page_table[KMMIO_PAGE_TABLE_SIZE];
 static LIST_HEAD(kmmio_probes);
 
-static struct list_head *kmmio_page_list(unsigned long page)
+static struct list_head *kmmio_page_list(unsigned long addr)
 {
-	return &kmmio_page_table[hash_long(page, KMMIO_PAGE_HASH_BITS)];
+	unsigned int l;
+	pte_t *pte = lookup_address(addr, &l);
+
+	if (!pte)
+		return NULL;
+	addr &= page_level_mask(l);
+
+	return &kmmio_page_table[hash_long(addr, KMMIO_PAGE_HASH_BITS)];
 }
 
 /* Accessed per-cpu */
@@ -98,15 +105,19 @@ static struct kmmio_probe *get_kmmio_probe(unsigned long addr)
 }
 
 /* You must be holding RCU read lock. */
-static struct kmmio_fault_page *get_kmmio_fault_page(unsigned long page)
+static struct kmmio_fault_page *get_kmmio_fault_page(unsigned long addr)
 {
 	struct list_head *head;
 	struct kmmio_fault_page *f;
+	unsigned int l;
+	pte_t *pte = lookup_address(addr, &l);
 
-	page &= PAGE_MASK;
-	head = kmmio_page_list(page);
+	if (!pte)
+		return NULL;
+	addr &= page_level_mask(l);
+	head = kmmio_page_list(addr);
 	list_for_each_entry_rcu(f, head, list) {
-		if (f->page == page)
+		if (f->addr == addr)
 			return f;
 	}
 	return NULL;
@@ -137,10 +148,10 @@ static void clear_pte_presence(pte_t *pte, bool clear, pteval_t *old)
 static int clear_page_presence(struct kmmio_fault_page *f, bool clear)
 {
 	unsigned int level;
-	pte_t *pte = lookup_address(f->page, &level);
+	pte_t *pte = lookup_address(f->addr, &level);
 
 	if (!pte) {
-		pr_err("no pte for page 0x%08lx\n", f->page);
+		pr_err("no pte for addr 0x%08lx\n", f->addr);
 		return -1;
 	}
 
@@ -156,7 +167,7 @@ static int clear_page_presence(struct kmmio_fault_page *f, bool clear)
 		return -1;
 	}
 
-	__flush_tlb_one(f->page);
+	__flush_tlb_one(f->addr);
 	return 0;
 }
 
@@ -176,12 +187,12 @@ static int arm_kmmio_fault_page(struct kmmio_fault_page *f)
 	int ret;
 	WARN_ONCE(f->armed, KERN_ERR pr_fmt("kmmio page already armed.\n"));
 	if (f->armed) {
-		pr_warning("double-arm: page 0x%08lx, ref %d, old %d\n",
-			   f->page, f->count, !!f->old_presence);
+		pr_warning("double-arm: addr 0x%08lx, ref %d, old %d\n",
+			   f->addr, f->count, !!f->old_presence);
 	}
 	ret = clear_page_presence(f, true);
-	WARN_ONCE(ret < 0, KERN_ERR pr_fmt("arming 0x%08lx failed.\n"),
-		  f->page);
+	WARN_ONCE(ret < 0, KERN_ERR pr_fmt("arming at 0x%08lx failed.\n"),
+		  f->addr);
 	f->armed = true;
 	return ret;
 }
@@ -191,7 +202,7 @@ static void disarm_kmmio_fault_page(struct kmmio_fault_page *f)
 {
 	int ret = clear_page_presence(f, false);
 	WARN_ONCE(ret < 0,
-			KERN_ERR "kmmio disarming 0x%08lx failed.\n", f->page);
+			KERN_ERR "kmmio disarming at 0x%08lx failed.\n", f->addr);
 	f->armed = false;
 }
 
@@ -215,6 +226,12 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr)
 	struct kmmio_context *ctx;
 	struct kmmio_fault_page *faultpage;
 	int ret = 0; /* default to fault not handled */
+	unsigned long page_base = addr;
+	unsigned int l;
+	pte_t *pte = lookup_address(addr, &l);
+	if (!pte)
+		return -EINVAL;
+	page_base &= page_level_mask(l);
 
 	/*
 	 * Preemption is now disabled to prevent process switch during
@@ -227,7 +244,7 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr)
 	preempt_disable();
 	rcu_read_lock();
 
-	faultpage = get_kmmio_fault_page(addr);
+	faultpage = get_kmmio_fault_page(page_base);
 	if (!faultpage) {
 		/*
 		 * Either this page fault is not caused by kmmio, or
@@ -239,7 +256,7 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr)
 
 	ctx = &get_cpu_var(kmmio_ctx);
 	if (ctx->active) {
-		if (addr == ctx->addr) {
+		if (page_base == ctx->addr) {
 			/*
 			 * A second fault on the same page means some other
 			 * condition needs handling by do_page_fault(), the
@@ -267,9 +284,9 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr)
 	ctx->active++;
 
 	ctx->fpage = faultpage;
-	ctx->probe = get_kmmio_probe(addr);
+	ctx->probe = get_kmmio_probe(page_base);
 	ctx->saved_flags = (regs->flags & (X86_EFLAGS_TF | X86_EFLAGS_IF));
-	ctx->addr = addr;
+	ctx->addr = page_base;
 
 	if (ctx->probe && ctx->probe->pre_handler)
 		ctx->probe->pre_handler(ctx->probe, regs, addr);
@@ -354,12 +371,11 @@ out:
 }
 
 /* You must be holding kmmio_lock. */
-static int add_kmmio_fault_page(unsigned long page)
+static int add_kmmio_fault_page(unsigned long addr)
 {
 	struct kmmio_fault_page *f;
 
-	page &= PAGE_MASK;
-	f = get_kmmio_fault_page(page);
+	f = get_kmmio_fault_page(addr);
 	if (f) {
 		if (!f->count)
 			arm_kmmio_fault_page(f);
@@ -372,26 +388,25 @@ static int add_kmmio_fault_page(unsigned long page)
 		return -1;
 
 	f->count = 1;
-	f->page = page;
+	f->addr = addr;
 
 	if (arm_kmmio_fault_page(f)) {
 		kfree(f);
 		return -1;
 	}
 
-	list_add_rcu(&f->list, kmmio_page_list(f->page));
+	list_add_rcu(&f->list, kmmio_page_list(f->addr));
 
 	return 0;
 }
 
 /* You must be holding kmmio_lock. */
-static void release_kmmio_fault_page(unsigned long page,
+static void release_kmmio_fault_page(unsigned long addr,
 				struct kmmio_fault_page **release_list)
 {
 	struct kmmio_fault_page *f;
 
-	page &= PAGE_MASK;
-	f = get_kmmio_fault_page(page);
+	f = get_kmmio_fault_page(addr);
 	if (!f)
 		return;
 
@@ -420,18 +435,27 @@ int register_kmmio_probe(struct kmmio_probe *p)
 	int ret = 0;
 	unsigned long size = 0;
 	const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK);
+	unsigned int l;
+	pte_t *pte;
 
 	spin_lock_irqsave(&kmmio_lock, flags);
 	if (get_kmmio_probe(p->addr)) {
 		ret = -EEXIST;
 		goto out;
 	}
+
+	pte = lookup_address(p->addr, &l);
+	if (!pte) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	kmmio_count++;
 	list_add_rcu(&p->list, &kmmio_probes);
 	while (size < size_lim) {
 		if (add_kmmio_fault_page(p->addr + size))
 			pr_err("Unable to set page fault.\n");
-		size += PAGE_SIZE;
+		size += page_level_size(l);
 	}
 out:
 	spin_unlock_irqrestore(&kmmio_lock, flags);
@@ -506,11 +530,17 @@ void unregister_kmmio_probe(struct kmmio_probe *p)
 	const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK);
 	struct kmmio_fault_page *release_list = NULL;
 	struct kmmio_delayed_release *drelease;
+	unsigned int l;
+	pte_t *pte;
+
+	pte = lookup_address(p->addr, &l);
+	if (!pte)
+		return;
 
 	spin_lock_irqsave(&kmmio_lock, flags);
 	while (size < size_lim) {
 		release_kmmio_fault_page(p->addr + size, &release_list);
-		size += PAGE_SIZE;
+		size += page_level_size(l);
 	}
 	list_del_rcu(&p->list);
 	kmmio_count--;
-- 
2.5.0

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[added to the 4.1 stable tree] ext4: fix NULL pointer dereference in ext4_mark_inode_dirty()

[Sasha Levin]

From: Eryu Guan <guaneryu@gmail.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 5e1021f2b6dff1a86a468a1424d59faae2bc63c1 ]

ext4_reserve_inode_write() in ext4_mark_inode_dirty() could fail on
error (e.g. EIO) and iloc.bh can be NULL in this case. But the error is
ignored in the following "if" condition and ext4_expand_extra_isize()
might be called with NULL iloc.bh set, which triggers NULL pointer
dereference.

This is uncovered by commit 8b4953e13f4c ("ext4: reserve code points for
the project quota feature"), which enlarges the ext4_inode size, and
run the following script on new kernel but with old mke2fs:

  #/bin/bash
  mnt=/mnt/ext4
  devname=ext4-error
  dev=/dev/mapper/$devname
  fsimg=/home/fs.img

  trap cleanup 0 1 2 3 9 15

  cleanup()
  {
          umount $mnt >/dev/null 2>&1
          dmsetup remove $devname
          losetup -d $backend_dev
          rm -f $fsimg
          exit 0
  }

  rm -f $fsimg
  fallocate -l 1g $fsimg
  backend_dev=`losetup -f --show $fsimg`
  devsize=`blockdev --getsz $backend_dev`

  good_tab="0 $devsize linear $backend_dev 0"
  error_tab="0 $devsize error $backend_dev 0"

  dmsetup create $devname --table "$good_tab"

  mkfs -t ext4 $dev
  mount -t ext4 -o errors=continue,strictatime $dev $mnt

  dmsetup load $devname --table "$error_tab" && dmsetup resume $devname
  echo 3 > /proc/sys/vm/drop_caches
  ls -l $mnt
  exit 0

[ Patch changed to simplify the function a tiny bit. -- Ted ]

Signed-off-by: Eryu Guan <guaneryu@gmail.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 fs/ext4/inode.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index f439968..ba12e29 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5094,6 +5094,8 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
 	might_sleep();
 	trace_ext4_mark_inode_dirty(inode, _RET_IP_);
 	err = ext4_reserve_inode_write(handle, inode, &iloc);
+	if (err)
+		return err;
 	if (ext4_handle_valid(handle) &&
 	    EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize &&
 	    !ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND)) {
@@ -5124,9 +5126,7 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
 			}
 		}
 	}
-	if (!err)
-		err = ext4_mark_iloc_dirty(handle, inode, &iloc);
-	return err;
+	return ext4_mark_iloc_dirty(handle, inode, &iloc);
 }
 
 /*
-- 
2.5.0

[added to the 4.1 stable tree] perf tools: handle spaces in file names obtained from /proc/pid/maps

[Sasha Levin]

From: Marcin Ślusarz <marcin.slusarz@gmail.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 89fee59b504f86925894fcc9ba79d5c933842f93 ]

Steam frequently puts game binaries in folders with spaces.

Note: "(deleted)" markers are now treated as part of the file name.

Signed-off-by: Marcin Ślusarz <marcin.slusarz@gmail.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Fixes: 6064803313ba ("perf tools: Use sscanf for parsing /proc/pid/maps")
Link: http://lkml.kernel.org/r/20160119190303.GA17579@marcin-Inspiron-7720
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 tools/perf/util/event.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index ff866c4..d18a59a 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -251,7 +251,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		strcpy(execname, "");
 
 		/* 00400000-0040c000 r-xp 00000000 fd:01 41038  /bin/cat */
-		n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %s\n",
+		n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %[^\n]\n",
 		       &event->mmap2.start, &event->mmap2.len, prot,
 		       &event->mmap2.pgoff, &event->mmap2.maj,
 		       &event->mmap2.min,
-- 
2.5.0

[added to the 4.1 stable tree] perf stat: Document --detailed option

[Sasha Levin]

From: Borislav Petkov <bp@suse.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit f594bae08183fb6b57db55387794ece3e1edf6f6 ]

I'm surprised this remained undocumented since at least 2011. And it is
actually a very useful switch, as Steve and I came to realize recently.

Add the text from

  2cba3ffb9a9d ("perf stat: Add -d -d and -d -d -d options to show more CPU events")

which added the incrementing aspect to -d.

Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Davidlohr Bueso <dbueso@suse.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mel Gorman <mgorman@suse.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 2cba3ffb9a9d ("perf stat: Add -d -d and -d -d -d options to show more CPU events")
Link: http://lkml.kernel.org/r/1457347294-32546-1-git-send-email-bp@alien8.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 tools/perf/Documentation/perf-stat.txt | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 04e150d..756ed9f 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -62,6 +62,14 @@ OPTIONS
 --scale::
 	scale/normalize counter values
 
+-d::
+--detailed::
+	print more detailed statistics, can be specified up to 3 times
+
+	   -d:          detailed events, L1 and LLC data cache
+        -d -d:     more detailed events, dTLB and iTLB events
+     -d -d -d:     very detailed events, adding prefetch events
+
 -r::
 --repeat=<n>::
 	repeat command and print average + stddev (max: 100). 0 means forever.
-- 
2.5.0

[added to the 4.1 stable tree] ARM: OMAP3: Add cpuidle parameters table for omap3430

[Sasha Levin]

From: Pali Rohár <pali.rohar@gmail.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 98f42221501353067251fbf11e732707dbb68ce3 ]

Based on CPU type choose generic omap3 or omap3430 specific cpuidle
parameters. Parameters for omap3430 were measured on Nokia N900 device and
added by commit 5a1b1d3a9efa ("OMAP3: RX-51: Pass cpu idle parameters")
which were later removed by commit 231900afba52 ("ARM: OMAP3: cpuidle -
remove rx51 cpuidle parameters table") due to huge code complexity.

This patch brings cpuidle parameters for omap3430 devices again, but uses
simple condition based on CPU type.

Fixes: 231900afba52 ("ARM: OMAP3: cpuidle - remove rx51 cpuidle
parameters table")
Signed-off-by: Pali Rohár <pali.rohar@gmail.com>
Acked-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: Tony Lindgren <tony@atomide.com>

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 arch/arm/mach-omap2/cpuidle34xx.c | 69 ++++++++++++++++++++++++++++++++++++++-
 1 file changed, 68 insertions(+), 1 deletion(-)

diff --git a/arch/arm/mach-omap2/cpuidle34xx.c b/arch/arm/mach-omap2/cpuidle34xx.c
index aa7b379..2a3db0b 100644
--- a/arch/arm/mach-omap2/cpuidle34xx.c
+++ b/arch/arm/mach-omap2/cpuidle34xx.c
@@ -34,6 +34,7 @@
 #include "pm.h"
 #include "control.h"
 #include "common.h"
+#include "soc.h"
 
 /* Mach specific information to be recorded in the C-state driver_data */
 struct omap3_idle_statedata {
@@ -315,6 +316,69 @@ static struct cpuidle_driver omap3_idle_driver = {
 	.safe_state_index = 0,
 };
 
+/*
+ * Numbers based on measurements made in October 2009 for PM optimized kernel
+ * with CPU freq enabled on device Nokia N900. Assumes OPP2 (main idle OPP,
+ * and worst case latencies).
+ */
+static struct cpuidle_driver omap3430_idle_driver = {
+	.name             = "omap3430_idle",
+	.owner            = THIS_MODULE,
+	.states = {
+		{
+			.enter		  = omap3_enter_idle_bm,
+			.exit_latency	  = 110 + 162,
+			.target_residency = 5,
+			.name		  = "C1",
+			.desc		  = "MPU ON + CORE ON",
+		},
+		{
+			.enter		  = omap3_enter_idle_bm,
+			.exit_latency	  = 106 + 180,
+			.target_residency = 309,
+			.name		  = "C2",
+			.desc		  = "MPU ON + CORE ON",
+		},
+		{
+			.enter		  = omap3_enter_idle_bm,
+			.exit_latency	  = 107 + 410,
+			.target_residency = 46057,
+			.name		  = "C3",
+			.desc		  = "MPU RET + CORE ON",
+		},
+		{
+			.enter		  = omap3_enter_idle_bm,
+			.exit_latency	  = 121 + 3374,
+			.target_residency = 46057,
+			.name		  = "C4",
+			.desc		  = "MPU OFF + CORE ON",
+		},
+		{
+			.enter		  = omap3_enter_idle_bm,
+			.exit_latency	  = 855 + 1146,
+			.target_residency = 46057,
+			.name		  = "C5",
+			.desc		  = "MPU RET + CORE RET",
+		},
+		{
+			.enter		  = omap3_enter_idle_bm,
+			.exit_latency	  = 7580 + 4134,
+			.target_residency = 484329,
+			.name		  = "C6",
+			.desc		  = "MPU OFF + CORE RET",
+		},
+		{
+			.enter		  = omap3_enter_idle_bm,
+			.exit_latency	  = 7505 + 15274,
+			.target_residency = 484329,
+			.name		  = "C7",
+			.desc		  = "MPU OFF + CORE OFF",
+		},
+	},
+	.state_count = ARRAY_SIZE(omap3_idle_data),
+	.safe_state_index = 0,
+};
+
 /* Public functions */
 
 /**
@@ -333,5 +397,8 @@ int __init omap3_idle_init(void)
 	if (!mpu_pd || !core_pd || !per_pd || !cam_pd)
 		return -ENODEV;
 
-	return cpuidle_register(&omap3_idle_driver, NULL);
+	if (cpu_is_omap3430())
+		return cpuidle_register(&omap3430_idle_driver, NULL);
+	else
+		return cpuidle_register(&omap3_idle_driver, NULL);
 }
-- 
2.5.0

[added to the 4.1 stable tree] jme: Do not enable NIC WoL functions on S0

[Sasha Levin]

From: Guo-Fu Tseng <cooldavid@cooldavid.org>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 0772a99b818079e628a1da122ac7ee023faed83e ]

Otherwise it might be back on resume right after going to suspend in
some hardware.

Reported-by: Diego Viola <diego.viola@gmail.com>
Signed-off-by: Guo-Fu Tseng <cooldavid@cooldavid.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/net/ethernet/jme.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c
index 32d240b..73351d2 100644
--- a/drivers/net/ethernet/jme.c
+++ b/drivers/net/ethernet/jme.c
@@ -270,11 +270,17 @@ jme_reset_mac_processor(struct jme_adapter *jme)
 }
 
 static inline void
-jme_clear_pm(struct jme_adapter *jme)
+jme_clear_pm_enable_wol(struct jme_adapter *jme)
 {
 	jwrite32(jme, JME_PMCS, PMCS_STMASK | jme->reg_pmcs);
 }
 
+static inline void
+jme_clear_pm_disable_wol(struct jme_adapter *jme)
+{
+	jwrite32(jme, JME_PMCS, PMCS_STMASK);
+}
+
 static int
 jme_reload_eeprom(struct jme_adapter *jme)
 {
@@ -1857,7 +1863,7 @@ jme_open(struct net_device *netdev)
 	struct jme_adapter *jme = netdev_priv(netdev);
 	int rc;
 
-	jme_clear_pm(jme);
+	jme_clear_pm_disable_wol(jme);
 	JME_NAPI_ENABLE(jme);
 
 	tasklet_init(&jme->linkch_task, jme_link_change_tasklet,
@@ -1933,7 +1939,7 @@ jme_powersave_phy(struct jme_adapter *jme)
 		jme_set_100m_half(jme);
 		if (jme->reg_pmcs & (PMCS_LFEN | PMCS_LREN))
 			jme_wait_link(jme);
-		jme_clear_pm(jme);
+		jme_clear_pm_enable_wol(jme);
 	} else {
 		jme_phy_off(jme);
 	}
@@ -2650,7 +2656,6 @@ jme_set_wol(struct net_device *netdev,
 	if (wol->wolopts & WAKE_MAGIC)
 		jme->reg_pmcs |= PMCS_MFEN;
 
-	jwrite32(jme, JME_PMCS, jme->reg_pmcs);
 	device_set_wakeup_enable(&jme->pdev->dev, !!(jme->reg_pmcs));
 
 	return 0;
@@ -3176,7 +3181,7 @@ jme_init_one(struct pci_dev *pdev,
 	jme->mii_if.mdio_read = jme_mdio_read;
 	jme->mii_if.mdio_write = jme_mdio_write;
 
-	jme_clear_pm(jme);
+	jme_clear_pm_disable_wol(jme);
 	device_set_wakeup_enable(&pdev->dev, true);
 
 	jme_set_phyfifo_5level(jme);
@@ -3308,7 +3313,7 @@ jme_resume(struct device *dev)
 	if (!netif_running(netdev))
 		return 0;
 
-	jme_clear_pm(jme);
+	jme_clear_pm_disable_wol(jme);
 	jme_phy_on(jme);
 	if (test_bit(JME_FLAG_SSET, &jme->flags))
 		jme_set_settings(netdev, &jme->old_ecmd);
-- 
2.5.0

[added to the 4.1 stable tree] jme: Fix device PM wakeup API usage

[Sasha Levin]

From: Guo-Fu Tseng <cooldavid@cooldavid.org>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 81422e672f8181d7ad1ee6c60c723aac649f538f ]

According to Documentation/power/devices.txt

The driver should not use device_set_wakeup_enable() which is the policy
for user to decide.

Using device_init_wakeup() to initialize dev->power.should_wakeup and
dev->power.can_wakeup on driver initialization.

And use device_may_wakeup() on suspend to decide if WoL function should
be enabled on NIC.

Reported-by: Diego Viola <diego.viola@gmail.com>
Signed-off-by: Guo-Fu Tseng <cooldavid@cooldavid.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/net/ethernet/jme.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c
index 73351d2..46e8d5b 100644
--- a/drivers/net/ethernet/jme.c
+++ b/drivers/net/ethernet/jme.c
@@ -1935,7 +1935,7 @@ jme_wait_link(struct jme_adapter *jme)
 static void
 jme_powersave_phy(struct jme_adapter *jme)
 {
-	if (jme->reg_pmcs) {
+	if (jme->reg_pmcs && device_may_wakeup(&jme->pdev->dev)) {
 		jme_set_100m_half(jme);
 		if (jme->reg_pmcs & (PMCS_LFEN | PMCS_LREN))
 			jme_wait_link(jme);
@@ -2656,8 +2656,6 @@ jme_set_wol(struct net_device *netdev,
 	if (wol->wolopts & WAKE_MAGIC)
 		jme->reg_pmcs |= PMCS_MFEN;
 
-	device_set_wakeup_enable(&jme->pdev->dev, !!(jme->reg_pmcs));
-
 	return 0;
 }
 
@@ -3182,7 +3180,7 @@ jme_init_one(struct pci_dev *pdev,
 	jme->mii_if.mdio_write = jme_mdio_write;
 
 	jme_clear_pm_disable_wol(jme);
-	device_set_wakeup_enable(&pdev->dev, true);
+	device_init_wakeup(&pdev->dev, true);
 
 	jme_set_phyfifo_5level(jme);
 	jme->pcirev = pdev->revision;
-- 
2.5.0

[added to the 4.1 stable tree] sunrpc/cache: drop reference when sunrpc_cache_pipe_upcall() detects a race

[Sasha Levin]

From: NeilBrown <neilb@suse.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit a6ab1e8126d205238defbb55d23661a3a5c6a0d8 ]

sunrpc_cache_pipe_upcall() can detect a race if CACHE_PENDING is no longer
set.  In this case it aborts the queuing of the upcall.
However it has already taken a new counted reference on "h" and
doesn't "put" it, even though it frees the data structure holding the reference.

So let's delay the "cache_get" until we know we need it.

Fixes: f9e1aedc6c79 ("sunrpc/cache: remove races with queuing an upcall.")
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/sunrpc/cache.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 8d79e70..9ec709b 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -1175,14 +1175,14 @@ int sunrpc_cache_pipe_upcall(struct cache_detail *detail, struct cache_head *h)
 	}
 
 	crq->q.reader = 0;
-	crq->item = cache_get(h);
 	crq->buf = buf;
 	crq->len = 0;
 	crq->readers = 0;
 	spin_lock(&queue_lock);
-	if (test_bit(CACHE_PENDING, &h->flags))
+	if (test_bit(CACHE_PENDING, &h->flags)) {
+		crq->item = cache_get(h);
 		list_add_tail(&crq->q.list, &detail->queue);
-	else
+	} else
 		/* Lost a race, no longer PENDING, so don't enqueue */
 		ret = -EAGAIN;
 	spin_unlock(&queue_lock);
-- 
2.5.0

[added to the 4.1 stable tree] megaraid_sas: add missing curly braces in ioctl handler

[Sasha Levin]

From: Arnd Bergmann <arnd@arndb.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 3deb9438d34a09f6796639b652a01d110aca9f75 ]

gcc-6 found a dubious indentation in the megasas_mgmt_fw_ioctl
function:

drivers/scsi/megaraid/megaraid_sas_base.c: In function 'megasas_mgmt_fw_ioctl':
drivers/scsi/megaraid/megaraid_sas_base.c:6658:4: warning: statement is indented as if it were guarded by... [-Wmisleading-indentation]
    kbuff_arr[i] = NULL;
    ^~~~~~~~~
drivers/scsi/megaraid/megaraid_sas_base.c:6653:3: note: ...this 'if' clause, but it is not
   if (kbuff_arr[i])
   ^~

The code is actually correct, as there is no downside in clearing a NULL
pointer again.

This clarifies the code and avoids the warning by adding extra curly
braces.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Fixes: 90dc9d98f01b ("megaraid_sas : MFI MPT linked list corruption fix")
Reviewed-by: Hannes Reinecke <hare@suse.com>
Acked-by: Sumit Saxena <sumit.saxena@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/scsi/megaraid/megaraid_sas_base.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 890637f..7a1c4b4 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -6203,12 +6203,13 @@ megasas_mgmt_fw_ioctl(struct megasas_instance *instance,
 	}
 
 	for (i = 0; i < ioc->sge_count; i++) {
-		if (kbuff_arr[i])
+		if (kbuff_arr[i]) {
 			dma_free_coherent(&instance->pdev->dev,
 					  le32_to_cpu(kern_sge32[i].length),
 					  kbuff_arr[i],
 					  le32_to_cpu(kern_sge32[i].phys_addr));
 			kbuff_arr[i] = NULL;
+		}
 	}
 
 	if (instance->ctrl_context && cmd->mpt_pthr_cmd_blocked)
-- 
2.5.0

[added to the 4.1 stable tree] ipvs: correct initial offset of Call-ID header search in SIP persistence engine

[Sasha Levin]

From: Marco Angaroni <marcoangaroni@gmail.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 7617a24f83b5d67f4dab1844956be1cebc44aec8 ]

The IPVS SIP persistence engine is not able to parse the SIP header
"Call-ID" when such header is inserted in the first positions of
the SIP message.

When IPVS is configured with "--pe sip" option, like for example:
ipvsadm -A -u 1.2.3.4:5060 -s rr --pe sip -p 120 -o
some particular messages (see below for details) do not create entries
in the connection template table, which can be listed with:
ipvsadm -Lcn --persistent-conn

Problematic SIP messages are SIP responses having "Call-ID" header
positioned just after message first line:
SIP/2.0 200 OK
[Call-ID header here]
[rest of the headers]

When "Call-ID" header is positioned down (after a few other headers)
it is correctly recognized.

This is due to the data offset used in get_callid function call inside
ip_vs_pe_sip.c file: since dptr already points to the start of the
SIP message, the value of dataoff should be initially 0.
Otherwise the header is searched starting from some bytes after the
first character of the SIP message.

Fixes: 758ff0338722 ("IPVS: sip persistence engine")
Signed-off-by: Marco Angaroni <marcoangaroni@gmail.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/netfilter/ipvs/ip_vs_pe_sip.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/ipvs/ip_vs_pe_sip.c b/net/netfilter/ipvs/ip_vs_pe_sip.c
index bed5f70..bb318e4 100644
--- a/net/netfilter/ipvs/ip_vs_pe_sip.c
+++ b/net/netfilter/ipvs/ip_vs_pe_sip.c
@@ -88,7 +88,7 @@ ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb)
 	dptr = skb->data + dataoff;
 	datalen = skb->len - dataoff;
 
-	if (get_callid(dptr, dataoff, datalen, &matchoff, &matchlen))
+	if (get_callid(dptr, 0, datalen, &matchoff, &matchlen))
 		return -EINVAL;
 
 	/* N.B: pe_data is only set on success,
-- 
2.5.0

[added to the 4.1 stable tree] ipvs: drop first packet to redirect conntrack

[Sasha Levin]

From: Julian Anastasov <ja@ssi.bg>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit f719e3754ee2f7275437e61a6afd520181fdd43b ]

Jiri Bohac is reporting for a problem where the attempt
to reschedule existing connection to another real server
needs proper redirect for the conntrack used by the IPVS
connection. For example, when IPVS connection is created
to NAT-ed real server we alter the reply direction of
conntrack. If we later decide to select different real
server we can not alter again the conntrack. And if we
expire the old connection, the new connection is left
without conntrack.

So, the only way to redirect both the IPVS connection and
the Netfilter's conntrack is to drop the SYN packet that
hits existing connection, to wait for the next jiffie
to expire the old connection and its conntrack and to rely
on client's retransmission to create new connection as
usually.

Jiri Bohac provided a fix that drops all SYNs on rescheduling,
I extended his patch to do such drops only for connections
that use conntrack. Here is the original report from Jiri Bohac:

Since commit dc7b3eb900aa ("ipvs: Fix reuse connection if real server
is dead"), new connections to dead servers are redistributed
immediately to new servers.  The old connection is expired using
ip_vs_conn_expire_now() which sets the connection timer to expire
immediately.

However, before the timer callback, ip_vs_conn_expire(), is run
to clean the connection's conntrack entry, the new redistributed
connection may already be established and its conntrack removed
instead.

Fix this by dropping the first packet of the new connection
instead, like we do when the destination server is not available.
The timer will have deleted the old conntrack entry long before
the first packet of the new connection is retransmitted.

Fixes: dc7b3eb900aa ("ipvs: Fix reuse connection if real server is dead")
Signed-off-by: Jiri Bohac <jbohac@suse.cz>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 include/net/ip_vs.h             | 17 +++++++++++++++++
 net/netfilter/ipvs/ip_vs_core.c | 37 ++++++++++++++++++++++++++++---------
 2 files changed, 45 insertions(+), 9 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 4e3731e..cd85945 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1584,6 +1584,23 @@ static inline void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp)
 }
 #endif /* CONFIG_IP_VS_NFCT */
 
+/* Really using conntrack? */
+static inline bool ip_vs_conn_uses_conntrack(struct ip_vs_conn *cp,
+					     struct sk_buff *skb)
+{
+#ifdef CONFIG_IP_VS_NFCT
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn *ct;
+
+	if (!(cp->flags & IP_VS_CONN_F_NFCT))
+		return false;
+	ct = nf_ct_get(skb, &ctinfo);
+	if (ct && !nf_ct_is_untracked(ct))
+		return true;
+#endif
+	return false;
+}
+
 static inline int
 ip_vs_dest_conn_overhead(struct ip_vs_dest *dest)
 {
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 38fbc19..a26bd65 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1689,15 +1689,34 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	cp = pp->conn_in_get(af, skb, &iph, 0);
 
 	conn_reuse_mode = sysctl_conn_reuse_mode(ipvs);
-	if (conn_reuse_mode && !iph.fragoffs &&
-	    is_new_conn(skb, &iph) && cp &&
-	    ((unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest &&
-	      unlikely(!atomic_read(&cp->dest->weight))) ||
-	     unlikely(is_new_conn_expected(cp, conn_reuse_mode)))) {
-		if (!atomic_read(&cp->n_control))
-			ip_vs_conn_expire_now(cp);
-		__ip_vs_conn_put(cp);
-		cp = NULL;
+	if (conn_reuse_mode && !iph.fragoffs && is_new_conn(skb, &iph) && cp) {
+		bool uses_ct = false, resched = false;
+
+		if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest &&
+		    unlikely(!atomic_read(&cp->dest->weight))) {
+			resched = true;
+			uses_ct = ip_vs_conn_uses_conntrack(cp, skb);
+		} else if (is_new_conn_expected(cp, conn_reuse_mode)) {
+			uses_ct = ip_vs_conn_uses_conntrack(cp, skb);
+			if (!atomic_read(&cp->n_control)) {
+				resched = true;
+			} else {
+				/* Do not reschedule controlling connection
+				 * that uses conntrack while it is still
+				 * referenced by controlled connection(s).
+				 */
+				resched = !uses_ct;
+			}
+		}
+
+		if (resched) {
+			if (!atomic_read(&cp->n_control))
+				ip_vs_conn_expire_now(cp);
+			__ip_vs_conn_put(cp);
+			if (uses_ct)
+				return NF_DROP;
+			cp = NULL;
+		}
 	}
 
 	if (unlikely(!cp) && !iph.fragoffs) {
-- 
2.5.0

[added to the 4.1 stable tree] nbd: ratelimit error msgs after socket close

[Sasha Levin]

From: Dan Streetman <dan.streetman@canonical.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit da6ccaaa79caca4f38b540b651238f87215217a2 ]

Make the "Attempted send on closed socket" error messages generated in
nbd_request_handler() ratelimited.

When the nbd socket is shutdown, the nbd_request_handler() function emits
an error message for every request remaining in its queue.  If the queue
is large, this will spam a large amount of messages to the log.  There's
no need for a separate error message for each request, so this patch
ratelimits it.

In the specific case this was found, the system was virtual and the error
messages were logged to the serial port, which overwhelmed it.

Fixes: 4d48a542b427 ("nbd: fix I/O hang on disconnected nbds")
Signed-off-by: Dan Streetman <dan.streetman@canonical.com>
Signed-off-by: Markus Pargmann <mpa@pengutronix.de>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/block/nbd.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 39e5f7f..9911b20 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -557,8 +557,8 @@ static void do_nbd_request(struct request_queue *q)
 			req, req->cmd_type);
 
 		if (unlikely(!nbd->sock)) {
-			dev_err(disk_to_dev(nbd->disk),
-				"Attempted send on closed socket\n");
+			dev_err_ratelimited(disk_to_dev(nbd->disk),
+					    "Attempted send on closed socket\n");
 			req->errors++;
 			nbd_end_request(nbd, req);
 			spin_lock_irq(q->queue_lock);
-- 
2.5.0

[added to the 4.1 stable tree] clk: rockchip: free memory in error cases when registering clock branches

[Sasha Levin]

From: Shawn Lin <shawn.lin@rock-chips.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 2467b6745e0ae9c6cdccff24c4cceeb14b1cce3f ]

Add free memeory if rockchip_clk_register_branch fails.

Fixes: a245fecbb806 ("clk: rockchip: add basic infrastructure...")
Signed-off-by: Shawn Lin <shawn.lin@rock-chips.com>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/clk/rockchip/clk.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/clk/rockchip/clk.c b/drivers/clk/rockchip/clk.c
index edb5d48..3b9de32 100644
--- a/drivers/clk/rockchip/clk.c
+++ b/drivers/clk/rockchip/clk.c
@@ -70,7 +70,7 @@ static struct clk *rockchip_clk_register_branch(const char *name,
 	if (gate_offset >= 0) {
 		gate = kzalloc(sizeof(*gate), GFP_KERNEL);
 		if (!gate)
-			return ERR_PTR(-ENOMEM);
+			goto err_gate;
 
 		gate->flags = gate_flags;
 		gate->reg = base + gate_offset;
@@ -82,7 +82,7 @@ static struct clk *rockchip_clk_register_branch(const char *name,
 	if (div_width > 0) {
 		div = kzalloc(sizeof(*div), GFP_KERNEL);
 		if (!div)
-			return ERR_PTR(-ENOMEM);
+			goto err_div;
 
 		div->flags = div_flags;
 		div->reg = base + muxdiv_offset;
@@ -100,6 +100,11 @@ static struct clk *rockchip_clk_register_branch(const char *name,
 				     flags);
 
 	return clk;
+err_div:
+	kfree(gate);
+err_gate:
+	kfree(mux);
+	return ERR_PTR(-ENOMEM);
 }
 
 static struct clk *rockchip_clk_register_frac_branch(const char *name,
-- 
2.5.0

[added to the 4.1 stable tree] clk: qcom: msm8960: fix ce3_core clk enable register

[Sasha Levin]

From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 732d6913691848db9fabaa6a25b4d6fad10ddccf ]

This patch corrects the enable register offset which is actually 0x36cc
instead of 0x36c4

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Fixes: 5f775498bdc4 ("clk: qcom: Fully support apq8064 global clock control")
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/clk/qcom/gcc-msm8960.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/clk/qcom/gcc-msm8960.c b/drivers/clk/qcom/gcc-msm8960.c
index eb6a4f9..9ce658a 100644
--- a/drivers/clk/qcom/gcc-msm8960.c
+++ b/drivers/clk/qcom/gcc-msm8960.c
@@ -2769,7 +2769,7 @@ static struct clk_branch ce3_core_clk = {
 	.halt_reg = 0x2fdc,
 	.halt_bit = 5,
 	.clkr = {
-		.enable_reg = 0x36c4,
+		.enable_reg = 0x36cc,
 		.enable_mask = BIT(4),
 		.hw.init = &(struct clk_init_data){
 			.name = "ce3_core_clk",
-- 
2.5.0

[added to the 4.1 stable tree] clk: versatile: sp810: support reentrance

[Sasha Levin]

From: Linus Walleij <linus.walleij@linaro.org>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit ec7957a6aa0aaf981fb8356dc47a2cdd01cde03c ]

Despite care take to allocate clocks state containers the
SP810 driver actually just supports creating one instance:
all clocks registered for every instance will end up with the
exact same name and __clk_init() will fail.

Rename the timclken<0> .. timclken<n> to sp810_<instance>_<n>
so every clock on every instance gets a unique name.

This is necessary for the RealView PBA8 which has two SP810
blocks: the second block will not register its clocks unless
every clock on every instance is unique and results in boot
logs like this:

------------[ cut here ]------------
WARNING: CPU: 0 PID: 0 at ../drivers/clk/versatile/clk-sp810.c:137
  clk_sp810_of_setup+0x110/0x154()
Modules linked in:
CPU: 0 PID: 0 Comm: swapper/0 Not tainted
4.5.0-rc2-00030-g352718fc39f6-dirty #225
Hardware name: ARM RealView Machine (Device Tree Support)
[<c00167f8>] (unwind_backtrace) from [<c0013204>]
             (show_stack+0x10/0x14)
[<c0013204>] (show_stack) from [<c01a049c>]
             (dump_stack+0x84/0x9c)
[<c01a049c>] (dump_stack) from [<c0024990>]
             (warn_slowpath_common+0x74/0xb0)
[<c0024990>] (warn_slowpath_common) from [<c0024a68>]
             (warn_slowpath_null+0x1c/0x24)
[<c0024a68>] (warn_slowpath_null) from [<c051eb44>]
             (clk_sp810_of_setup+0x110/0x154)
[<c051eb44>] (clk_sp810_of_setup) from [<c051e3a4>]
             (of_clk_init+0x12c/0x1c8)
[<c051e3a4>] (of_clk_init) from [<c0504714>]
             (time_init+0x20/0x2c)
[<c0504714>] (time_init) from [<c0501b18>]
             (start_kernel+0x244/0x3c4)
[<c0501b18>] (start_kernel) from [<7000807c>] (0x7000807c)
---[ end trace cb88537fdc8fa200 ]---

Cc: Michael Turquette <mturquette@baylibre.com>
Cc: Pawel Moll <pawel.moll@arm.com>
Fixes: 6e973d2c4385 "clk: vexpress: Add separate SP810 driver"
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/clk/versatile/clk-sp810.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/clk/versatile/clk-sp810.c b/drivers/clk/versatile/clk-sp810.c
index 5122ef2..e63c3ef 100644
--- a/drivers/clk/versatile/clk-sp810.c
+++ b/drivers/clk/versatile/clk-sp810.c
@@ -141,6 +141,7 @@ void __init clk_sp810_of_setup(struct device_node *node)
 	const char *parent_names[2];
 	char name[12];
 	struct clk_init_data init;
+	static int instance;
 	int i;
 
 	if (!sp810) {
@@ -172,7 +173,7 @@ void __init clk_sp810_of_setup(struct device_node *node)
 	init.num_parents = ARRAY_SIZE(parent_names);
 
 	for (i = 0; i < ARRAY_SIZE(sp810->timerclken); i++) {
-		snprintf(name, ARRAY_SIZE(name), "timerclken%d", i);
+		snprintf(name, sizeof(name), "sp810_%d_%d", instance, i);
 
 		sp810->timerclken[i].sp810 = sp810;
 		sp810->timerclken[i].channel = i;
@@ -184,5 +185,6 @@ void __init clk_sp810_of_setup(struct device_node *node)
 	}
 
 	of_clk_add_provider(node, clk_sp810_timerclken_of_get, sp810);
+	instance++;
 }
 CLK_OF_DECLARE(sp810, "arm,sp810", clk_sp810_of_setup);
-- 
2.5.0

[added to the 4.1 stable tree] clk: qcom: msm8960: Fix ce3_src register offset

[Sasha Levin]

From: Stephen Boyd <sboyd@codeaurora.org>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 0f75e1a370fd843c9e508fc1ccf0662833034827 ]

The offset seems to have been copied from the sata clk. Fix it so
that enabling the crypto engine source clk works.

Tested-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Tested-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Fixes: 5f775498bdc4 ("clk: qcom: Fully support apq8064 global clock control")
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/clk/qcom/gcc-msm8960.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/clk/qcom/gcc-msm8960.c b/drivers/clk/qcom/gcc-msm8960.c
index 9ce658a..476d209 100644
--- a/drivers/clk/qcom/gcc-msm8960.c
+++ b/drivers/clk/qcom/gcc-msm8960.c
@@ -2753,7 +2753,7 @@ static struct clk_rcg ce3_src = {
 	},
 	.freq_tbl = clk_tbl_ce3,
 	.clkr = {
-		.enable_reg = 0x2c08,
+		.enable_reg = 0x36c0,
 		.enable_mask = BIT(7),
 		.hw.init = &(struct clk_init_data){
 			.name = "ce3_src",
-- 
2.5.0

[added to the 4.1 stable tree] lpfc: fix misleading indentation

[Sasha Levin]

From: Arnd Bergmann <arnd@arndb.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit aeb6641f8ebdd61939f462a8255b316f9bfab707 ]

gcc-6 complains about the indentation of the lpfc_destroy_vport_work_array()
call in lpfc_online(), which clearly doesn't look right:

drivers/scsi/lpfc/lpfc_init.c: In function 'lpfc_online':
drivers/scsi/lpfc/lpfc_init.c:2880:3: warning: statement is indented as if it were guarded by... [-Wmisleading-indentation]
   lpfc_destroy_vport_work_array(phba, vports);
   ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/scsi/lpfc/lpfc_init.c:2863:2: note: ...this 'if' clause, but it is not
  if (vports != NULL)
  ^~

Looking at the patch that introduced this code, it's clear that the
behavior is correct and the indentation is wrong.

This fixes the indentation and adds curly braces around the previous
if() block for clarity, as that is most likely what caused the code
to be misindented in the first place.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Fixes: 549e55cd2a1b ("[SCSI] lpfc 8.2.2 : Fix locking around HBA's port_list")
Reviewed-by: Sebastian Herbszt <herbszt@gmx.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Ewan D. Milne <emilne@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/scsi/lpfc/lpfc_init.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index e8c8c1e..bf8fd38 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -2848,7 +2848,7 @@ lpfc_online(struct lpfc_hba *phba)
 	}
 
 	vports = lpfc_create_vport_work_array(phba);
-	if (vports != NULL)
+	if (vports != NULL) {
 		for (i = 0; i <= phba->max_vports && vports[i] != NULL; i++) {
 			struct Scsi_Host *shost;
 			shost = lpfc_shost_from_vport(vports[i]);
@@ -2865,7 +2865,8 @@ lpfc_online(struct lpfc_hba *phba)
 			}
 			spin_unlock_irq(shost->host_lock);
 		}
-		lpfc_destroy_vport_work_array(phba, vports);
+	}
+	lpfc_destroy_vport_work_array(phba, vports);
 
 	lpfc_unblock_mgmt_io(phba);
 	return 0;
-- 
2.5.0

[added to the 4.1 stable tree] Input: zforce_ts - fix dual touch recognition

[Sasha Levin]

From: Knut Wohlrab <Knut.Wohlrab@de.bosch.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 6984ab1ab35f422292b7781c65284038bcc0f6a6 ]

A wrong decoding of the touch coordinate message causes a wrong touch
ID. Touch ID for dual touch must be 0 or 1.

According to the actual Neonode nine byte touch coordinate coding,
the state is transported in the lower nibble and the touch ID in
the higher nibble of payload byte five.

Signed-off-by: Knut Wohlrab <Knut.Wohlrab@de.bosch.com>
Signed-off-by: Oleksij Rempel <linux@rempel-privat.de>
Signed-off-by: Dirk Behme <dirk.behme@de.bosch.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/input/touchscreen/zforce_ts.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/input/touchscreen/zforce_ts.c b/drivers/input/touchscreen/zforce_ts.c
index 19880c7..d618f67 100644
--- a/drivers/input/touchscreen/zforce_ts.c
+++ b/drivers/input/touchscreen/zforce_ts.c
@@ -359,8 +359,8 @@ static int zforce_touch_event(struct zforce_ts *ts, u8 *payload)
 			point.coord_x = point.coord_y = 0;
 		}
 
-		point.state = payload[9 * i + 5] & 0x03;
-		point.id = (payload[9 * i + 5] & 0xfc) >> 2;
+		point.state = payload[9 * i + 5] & 0x0f;
+		point.id = (payload[9 * i + 5] & 0xf0) >> 4;
 
 		/* determine touch major, minor and orientation */
 		point.area_major = max(payload[9 * i + 6],
-- 
2.5.0

[added to the 4.1 stable tree] proc: prevent accessing /proc/<PID>/environ until it's ready

[Sasha Levin]

From: Mathias Krause <minipli@googlemail.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 8148a73c9901a8794a50f950083c00ccf97d43b3 ]

If /proc/<PID>/environ gets read before the envp[] array is fully set up
in create_{aout,elf,elf_fdpic,flat}_tables(), we might end up trying to
read more bytes than are actually written, as env_start will already be
set but env_end will still be zero, making the range calculation
underflow, allowing to read beyond the end of what has been written.

Fix this as it is done for /proc/<PID>/cmdline by testing env_end for
zero.  It is, apparently, intentionally set last in create_*_tables().

This bug was found by the PaX size_overflow plugin that detected the
arithmetic underflow of 'this_len = env_end - (env_start + src)' when
env_end is still zero.

The expected consequence is that userland trying to access
/proc/<PID>/environ of a not yet fully set up process may get
inconsistent data as we're in the middle of copying in the environment
variables.

Fixes: https://forums.grsecurity.net/viewtopic.php?f=3&t=4363
Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=116461
Signed-off-by: Mathias Krause <minipli@googlemail.com>
Cc: Emese Revfy <re.emese@gmail.com>
Cc: Pax Team <pageexec@freemail.hu>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Mateusz Guzik <mguzik@redhat.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Jarod Wilson <jarod@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 fs/proc/base.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 68d51ed..239dca3 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -759,7 +759,8 @@ static ssize_t environ_read(struct file *file, char __user *buf,
 	int ret = 0;
 	struct mm_struct *mm = file->private_data;
 
-	if (!mm)
+	/* Ensure the process spawned far enough to have an environment. */
+	if (!mm || !mm->env_end)
 		return 0;
 
 	page = (char *)__get_free_page(GFP_TEMPORARY);
-- 
2.5.0

[added to the 4.1 stable tree] mm: update min_free_kbytes from khugepaged after core initialization

[Sasha Levin]

From: Jason Baron <jbaron@akamai.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit bc22af74f271ef76b2e6f72f3941f91f0da3f5f8 ]

Khugepaged attempts to raise min_free_kbytes if its set too low.
However, on boot khugepaged sets min_free_kbytes first from
subsys_initcall(), and then the mm 'core' over-rides min_free_kbytes
after from init_per_zone_wmark_min(), via a module_init() call.

Khugepaged used to use a late_initcall() to set min_free_kbytes (such
that it occurred after the core initialization), however this was
removed when the initialization of min_free_kbytes was integrated into
the starting of the khugepaged thread.

The fix here is simply to invoke the core initialization using a
core_initcall() instead of module_init(), such that the previous
initialization ordering is restored.  I didn't restore the
late_initcall() since start_stop_khugepaged() already sets
min_free_kbytes via set_recommended_min_free_kbytes().

This was noticed when we had a number of page allocation failures when
moving a workload to a kernel with this new initialization ordering.  On
an 8GB system this restores min_free_kbytes back to 67584 from 11365
when CONFIG_TRANSPARENT_HUGEPAGE=y is set and either
CONFIG_TRANSPARENT_HUGEPAGE_ALWAYS=y or
CONFIG_TRANSPARENT_HUGEPAGE_MADVISE=y.

Fixes: 79553da293d3 ("thp: cleanup khugepaged startup")
Signed-off-by: Jason Baron <jbaron@akamai.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 mm/page_alloc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 5519230..f6f6831 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5926,7 +5926,7 @@ int __meminit init_per_zone_wmark_min(void)
 	setup_per_zone_inactive_ratio();
 	return 0;
 }
-module_init(init_per_zone_wmark_min)
+core_initcall(init_per_zone_wmark_min)
 
 /*
  * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so
-- 
2.5.0

[added to the 4.1 stable tree] batman-adv: Check skb size before using encapsulated ETH+VLAN header

[Sasha Levin]

From: Sven Eckelmann <sven@narfation.org>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit c78296665c3d81f040117432ab9e1cb125521b0c ]

The encapsulated ethernet and VLAN header may be outside the received
ethernet frame. Thus the skb buffer size has to be checked before it can be
parsed to find out if it encapsulates another batman-adv packet.

Fixes: 420193573f11 ("batman-adv: softif bridge loop avoidance")
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>
Signed-off-by: Antonio Quartulli <a@unstable.cc>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/batman-adv/soft-interface.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index a0b1b86..b38a8aa 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -377,11 +377,17 @@ void batadv_interface_rx(struct net_device *soft_iface,
 	 */
 	nf_reset(skb);
 
+	if (unlikely(!pskb_may_pull(skb, ETH_HLEN)))
+		goto dropped;
+
 	vid = batadv_get_vid(skb, 0);
 	ethhdr = eth_hdr(skb);
 
 	switch (ntohs(ethhdr->h_proto)) {
 	case ETH_P_8021Q:
+		if (!pskb_may_pull(skb, VLAN_ETH_HLEN))
+			goto dropped;
+
 		vhdr = (struct vlan_ethhdr *)skb->data;
 
 		if (vhdr->h_vlan_encapsulated_proto != ethertype)
@@ -393,8 +399,6 @@ void batadv_interface_rx(struct net_device *soft_iface,
 	}
 
 	/* skb->dev & skb->pkt_type are set here */
-	if (unlikely(!pskb_may_pull(skb, ETH_HLEN)))
-		goto dropped;
 	skb->protocol = eth_type_trans(skb, soft_iface);
 
 	/* should not be necessary anymore as we use skb_pull_rcsum()
-- 
2.5.0

[added to the 4.1 stable tree] batman-adv: Fix broadcast/ogm queue limit on a removed interface

[Sasha Levin]

From: Linus Lüssing <linus.luessing@c0d3.blue>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit c4fdb6cff2aa0ae740c5f19b6f745cbbe786d42f ]

When removing a single interface while a broadcast or ogm packet is
still pending then we will free the forward packet without releasing the
queue slots again.

This patch is supposed to fix this issue.

Fixes: 6d5808d4ae1b ("batman-adv: Add missing hardif_free_ref in forw_packet_free")
Signed-off-by: Linus Lüssing <linus.luessing@c0d3.blue>
[sven@narfation.org: fix conflicts with current version]
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>
Signed-off-by: Antonio Quartulli <a@unstable.cc>

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/batman-adv/send.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c
index 3d64ed2..6004c2d 100644
--- a/net/batman-adv/send.c
+++ b/net/batman-adv/send.c
@@ -611,6 +611,9 @@ batadv_purge_outstanding_packets(struct batadv_priv *bat_priv,
 
 		if (pending) {
 			hlist_del(&forw_packet->list);
+			if (!forw_packet->own)
+				atomic_inc(&bat_priv->bcast_queue_left);
+
 			batadv_forw_packet_free(forw_packet);
 		}
 	}
@@ -638,6 +641,9 @@ batadv_purge_outstanding_packets(struct batadv_priv *bat_priv,
 
 		if (pending) {
 			hlist_del(&forw_packet->list);
+			if (!forw_packet->own)
+				atomic_inc(&bat_priv->batman_queue_left);
+
 			batadv_forw_packet_free(forw_packet);
 		}
 	}
-- 
2.5.0

[added to the 4.1 stable tree] batman-adv: Reduce refcnt of removed router when updating route

[Sasha Levin]

From: Sven Eckelmann <sven@narfation.org>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit d1a65f1741bfd9c69f9e4e2ad447a89b6810427d ]

_batadv_update_route rcu_derefences orig_ifinfo->router outside of a
spinlock protected region to print some information messages to the debug
log. But this pointer is not checked again when the new pointer is assigned
in the spinlock protected region. Thus is can happen that the value of
orig_ifinfo->router changed in the meantime and thus the reference counter
of the wrong router gets reduced after the spinlock protected region.

Just rcu_dereferencing the value of orig_ifinfo->router inside the spinlock
protected region (which also set the new pointer) is enough to get the
correct old router object.

Fixes: e1a5382f978b ("batman-adv: Make orig_node->router an rcu protected pointer")
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>
Signed-off-by: Antonio Quartulli <a@unstable.cc>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/batman-adv/routing.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index da83982..f77dafc 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -88,6 +88,15 @@ static void _batadv_update_route(struct batadv_priv *bat_priv,
 		neigh_node = NULL;
 
 	spin_lock_bh(&orig_node->neigh_list_lock);
+	/* curr_router used earlier may not be the current orig_ifinfo->router
+	 * anymore because it was dereferenced outside of the neigh_list_lock
+	 * protected region. After the new best neighbor has replace the current
+	 * best neighbor the reference counter needs to decrease. Consequently,
+	 * the code needs to ensure the curr_router variable contains a pointer
+	 * to the replaced best neighbor.
+	 */
+	curr_router = rcu_dereference_protected(orig_ifinfo->router, true);
+
 	rcu_assign_pointer(orig_ifinfo->router, neigh_node);
 	spin_unlock_bh(&orig_node->neigh_list_lock);
 	batadv_orig_ifinfo_free_ref(orig_ifinfo);
-- 
2.5.0

[added to the 4.1 stable tree] iio: ak8975: fix maybe-uninitialized warning

[Sasha Levin]

From: Richard Leitner <dev@g0hl1n.net>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 05be8d4101d960bad271d32b4f6096af1ccb1534 ]

If i2c_device_id *id is NULL and acpi_match_device returns NULL too,
then chipset may be unitialized when accessing &ak_def_array[chipset] in
ak8975_probe. Therefore initialize chipset to AK_MAX_TYPE, which will
return an error when not changed.

This patch fixes the following maybe-uninitialized warning:

drivers/iio/magnetometer/ak8975.c: In function ‘ak8975_probe’:
drivers/iio/magnetometer/ak8975.c:788:14: warning: ‘chipset’ may be used
uninitialized in this function [-Wmaybe-uninitialized]
  data->def = &ak_def_array[chipset];

Signed-off-by: Richard Leitner <dev@g0hl1n.net>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/iio/magnetometer/ak8975.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/magnetometer/ak8975.c b/drivers/iio/magnetometer/ak8975.c
index fd780bb..f2a7f72 100644
--- a/drivers/iio/magnetometer/ak8975.c
+++ b/drivers/iio/magnetometer/ak8975.c
@@ -732,7 +732,7 @@ static int ak8975_probe(struct i2c_client *client,
 	int eoc_gpio;
 	int err;
 	const char *name = NULL;
-	enum asahi_compass_chipset chipset;
+	enum asahi_compass_chipset chipset = AK_MAX_TYPE;
 
 	/* Grab and set up the supplied GPIO. */
 	if (client->dev.platform_data)
-- 
2.5.0

[added to the 4.1 stable tree] ACPI / processor: Request native thermal interrupt handling via _OSC

[Sasha Levin]

From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit a21211672c9a1d730a39aa65d4a5b3414700adfb ]

There are several reports of freeze on enabling HWP (Hardware PStates)
feature on Skylake-based systems by the Intel P-states driver. The root
cause is identified as the HWP interrupts causing BIOS code to freeze.

HWP interrupts use the thermal LVT which can be handled by Linux
natively, but on the affected Skylake-based systems SMM will respond
to it by default.  This is a problem for several reasons:
 - On the affected systems the SMM thermal LVT handler is broken (it
   will crash when invoked) and a BIOS update is necessary to fix it.
 - With thermal interrupt handled in SMM we lose all of the reporting
   features of the arch/x86/kernel/cpu/mcheck/therm_throt driver.
 - Some thermal drivers like x86-package-temp depend on the thermal
   threshold interrupts signaled via the thermal LVT.
 - The HWP interrupts are useful for debugging and tuning
   performance (if the kernel can handle them).
The native handling of thermal interrupts needs to be enabled
because of that.

This requires some way to tell SMM that the OS can handle thermal
interrupts.  That can be done by using _OSC/_PDC in processor
scope very early during ACPI initialization.

The meaning of _OSC/_PDC bit 12 in processor scope is whether or
not the OS supports native handling of interrupts for Collaborative
Processor Performance Control (CPPC) notifications.  Since on
HWP-capable systems CPPC is a firmware interface to HWP, setting
this bit effectively tells the firmware that the OS will handle
thermal interrupts natively going forward.

For details on _OSC/_PDC refer to:
http://www.intel.com/content/www/us/en/standards/processor-vendor-specific-acpi-specification.html

To implement the _OSC/_PDC handshake as described, introduce a new
function, acpi_early_processor_osc(), that walks the ACPI
namespace looking for ACPI processor objects and invokes _OSC for
them with bit 12 in the capabilities buffer set and terminates the
namespace walk on the first success.

Also modify intel_thermal_interrupt() to clear HWP status bits in
the HWP_STATUS MSR to acknowledge HWP interrupts (which prevents
them from firing continuously).

Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
[ rjw: Subject & changelog, function rename ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 arch/x86/kernel/cpu/mcheck/therm_throt.c |  3 ++
 drivers/acpi/acpi_processor.c            | 52 ++++++++++++++++++++++++++++++++
 drivers/acpi/bus.c                       |  3 ++
 drivers/acpi/internal.h                  |  6 ++++
 4 files changed, 64 insertions(+)

diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 1af51b1..56270f0 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -385,6 +385,9 @@ static void intel_thermal_interrupt(void)
 {
 	__u64 msr_val;
 
+	if (static_cpu_has(X86_FEATURE_HWP))
+		wrmsrl_safe(MSR_HWP_STATUS, 0);
+
 	rdmsrl(MSR_IA32_THERM_STATUS, msr_val);
 
 	/* Check for violation of core thermal thresholds*/
diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
index 58f335c..568f2b9 100644
--- a/drivers/acpi/acpi_processor.c
+++ b/drivers/acpi/acpi_processor.c
@@ -475,6 +475,58 @@ static void acpi_processor_remove(struct acpi_device *device)
 }
 #endif /* CONFIG_ACPI_HOTPLUG_CPU */
 
+#ifdef CONFIG_X86
+static bool acpi_hwp_native_thermal_lvt_set;
+static acpi_status __init acpi_hwp_native_thermal_lvt_osc(acpi_handle handle,
+							  u32 lvl,
+							  void *context,
+							  void **rv)
+{
+	u8 sb_uuid_str[] = "4077A616-290C-47BE-9EBD-D87058713953";
+	u32 capbuf[2];
+	struct acpi_osc_context osc_context = {
+		.uuid_str = sb_uuid_str,
+		.rev = 1,
+		.cap.length = 8,
+		.cap.pointer = capbuf,
+	};
+
+	if (acpi_hwp_native_thermal_lvt_set)
+		return AE_CTRL_TERMINATE;
+
+	capbuf[0] = 0x0000;
+	capbuf[1] = 0x1000; /* set bit 12 */
+
+	if (ACPI_SUCCESS(acpi_run_osc(handle, &osc_context))) {
+		if (osc_context.ret.pointer && osc_context.ret.length > 1) {
+			u32 *capbuf_ret = osc_context.ret.pointer;
+
+			if (capbuf_ret[1] & 0x1000) {
+				acpi_handle_info(handle,
+					"_OSC native thermal LVT Acked\n");
+				acpi_hwp_native_thermal_lvt_set = true;
+			}
+		}
+		kfree(osc_context.ret.pointer);
+	}
+
+	return AE_OK;
+}
+
+void __init acpi_early_processor_osc(void)
+{
+	if (boot_cpu_has(X86_FEATURE_HWP)) {
+		acpi_walk_namespace(ACPI_TYPE_PROCESSOR, ACPI_ROOT_OBJECT,
+				    ACPI_UINT32_MAX,
+				    acpi_hwp_native_thermal_lvt_osc,
+				    NULL, NULL, NULL);
+		acpi_get_devices(ACPI_PROCESSOR_DEVICE_HID,
+				 acpi_hwp_native_thermal_lvt_osc,
+				 NULL, NULL);
+	}
+}
+#endif
+
 /*
  * The following ACPI IDs are known to be suitable for representing as
  * processor devices.
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 513e7230e..fd60539 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -612,6 +612,9 @@ static int __init acpi_bus_init(void)
 		goto error1;
 	}
 
+	/* Set capability bits for _OSC under processor scope */
+	acpi_early_processor_osc();
+
 	/*
 	 * _OSC method may exist in module level code,
 	 * so it must be run after ACPI_FULL_INITIALIZATION
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index ba4a61e..7db7f9d 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -121,6 +121,12 @@ void acpi_early_processor_set_pdc(void);
 static inline void acpi_early_processor_set_pdc(void) {}
 #endif
 
+#ifdef CONFIG_X86
+void acpi_early_processor_osc(void);
+#else
+static inline void acpi_early_processor_osc(void) {}
+#endif
+
 /* --------------------------------------------------------------------------
                                   Embedded Controller
    -------------------------------------------------------------------------- */
-- 
2.5.0

[added to the 4.1 stable tree] decnet: Do not build routes to devices without decnet private data.

[Sasha Levin]

From: "David S. Miller" <davem@davemloft.net>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit a36a0d4008488fa545c74445d69eaf56377d5d4e ]

In particular, make sure we check for decnet private presence
for loopback devices.

Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/decnet/dn_route.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index 03227ff..76d3bf70 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -1036,10 +1036,13 @@ source_ok:
 	if (!fld.daddr) {
 		fld.daddr = fld.saddr;
 
-		err = -EADDRNOTAVAIL;
 		if (dev_out)
 			dev_put(dev_out);
+		err = -EINVAL;
 		dev_out = init_net.loopback_dev;
+		if (!dev_out->dn_ptr)
+			goto out;
+		err = -EADDRNOTAVAIL;
 		dev_hold(dev_out);
 		if (!fld.daddr) {
 			fld.daddr =
@@ -1112,6 +1115,8 @@ source_ok:
 		if (dev_out == NULL)
 			goto out;
 		dn_db = rcu_dereference_raw(dev_out->dn_ptr);
+		if (!dn_db)
+			goto e_inval;
 		/* Possible improvement - check all devices for local addr */
 		if (dn_dev_islocal(dev_out, fld.daddr)) {
 			dev_put(dev_out);
@@ -1153,6 +1158,8 @@ select_source:
 			dev_put(dev_out);
 		dev_out = init_net.loopback_dev;
 		dev_hold(dev_out);
+		if (!dev_out->dn_ptr)
+			goto e_inval;
 		fld.flowidn_oif = dev_out->ifindex;
 		if (res.fi)
 			dn_fib_info_put(res.fi);
-- 
2.5.0

[added to the 4.1 stable tree] route: do not cache fib route info on local routes with oif

[Sasha Levin]

From: Chris Friesen <chris.friesen@windriver.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit d6d5e999e5df67f8ec20b6be45e2229455ee3699 ]

For local routes that require a particular output interface we do not want
to cache the result.  Caching the result causes incorrect behaviour when
there are multiple source addresses on the interface.  The end result
being that if the intended recipient is waiting on that interface for the
packet he won't receive it because it will be delivered on the loopback
interface and the IP_PKTINFO ipi_ifindex will be set to the loopback
interface as well.

This can be tested by running a program such as "dhcp_release" which
attempts to inject a packet on a particular interface so that it is
received by another program on the same board.  The receiving process
should see an IP_PKTINFO ipi_ifndex value of the source interface
(e.g., eth1) instead of the loopback interface (e.g., lo).  The packet
will still appear on the loopback interface in tcpdump but the important
aspect is that the CMSG info is correct.

Sample dhcp_release command line:

   dhcp_release eth1 192.168.204.222 02:11:33:22:44:66

Signed-off-by: Allain Legacy <allain.legacy@windriver.com>
Signed off-by: Chris Friesen <chris.friesen@windriver.com>
Reviewed-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/ipv4/route.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 1d3cdb4d..eb1d983 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1976,6 +1976,18 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 		 */
 		if (fi && res->prefixlen < 4)
 			fi = NULL;
+	} else if ((type == RTN_LOCAL) && (orig_oif != 0) &&
+		   (orig_oif != dev_out->ifindex)) {
+		/* For local routes that require a particular output interface
+		 * we do not want to cache the result.  Caching the result
+		 * causes incorrect behaviour when there are multiple source
+		 * addresses on the interface, the end result being that if the
+		 * intended recipient is waiting on that interface for the
+		 * packet he won't receive it because it will be delivered on
+		 * the loopback interface and the IP_PKTINFO ipi_ifindex will
+		 * be set to the loopback interface as well.
+		 */
+		fi = NULL;
 	}
 
 	fnhe = NULL;
-- 
2.5.0

[added to the 4.1 stable tree] packet: fix heap info leak in PACKET_DIAG_MCLIST sock_diag interface

[Sasha Levin]

From: Mathias Krause <minipli@googlemail.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 309cf37fe2a781279b7675d4bb7173198e532867 ]

Because we miss to wipe the remainder of i->addr[] in packet_mc_add(),
pdiag_put_mclist() leaks uninitialized heap bytes via the
PACKET_DIAG_MCLIST netlink attribute.

Fix this by explicitly memset(0)ing the remaining bytes in i->addr[].

Fixes: eea68e2f1a00 ("packet: Report socket mclist info via diag module")
Signed-off-by: Mathias Krause <minipli@googlemail.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Acked-by: Pavel Emelyanov <xemul@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/packet/af_packet.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 68a04847..a3654d9 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3207,6 +3207,7 @@ static int packet_mc_add(struct sock *sk, struct packet_mreq_max *mreq)
 	i->ifindex = mreq->mr_ifindex;
 	i->alen = mreq->mr_alen;
 	memcpy(i->addr, mreq->mr_address, i->alen);
+	memset(i->addr + i->alen, 0, sizeof(i->addr) - i->alen);
 	i->count = 1;
 	i->next = po->mclist;
 	po->mclist = i;
-- 
2.5.0

[added to the 4.1 stable tree] net: sched: do not requeue a NULL skb

[Sasha Levin]

From: Lars Persson <lars.persson@axis.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 3dcd493fbebfd631913df6e2773cc295d3bf7d22 ]

A failure in validate_xmit_skb_list() triggered an unconditional call
to dev_requeue_skb with skb=NULL. This slowly grows the queue
discipline's qlen count until all traffic through the queue stops.

We take the optimistic approach and continue running the queue after a
failure since it is unknown if later packets also will fail in the
validate path.

Fixes: 55a93b3ea780 ("qdisc: validate skb without holding lock")
Signed-off-by: Lars Persson <larper@axis.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/sched/sch_generic.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 3c6f6b77..9821e6d 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -159,12 +159,15 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
 	if (validate)
 		skb = validate_xmit_skb_list(skb, dev);
 
-	if (skb) {
+	if (likely(skb)) {
 		HARD_TX_LOCK(dev, txq, smp_processor_id());
 		if (!netif_xmit_frozen_or_stopped(txq))
 			skb = dev_hard_start_xmit(skb, dev, txq, &ret);
 
 		HARD_TX_UNLOCK(dev, txq);
+	} else {
+		spin_lock(root_lock);
+		return qdisc_qlen(q);
 	}
 	spin_lock(root_lock);
 
-- 
2.5.0

[added to the 4.1 stable tree] bpf/verifier: reject invalid LD_ABS | BPF_DW instruction

[Sasha Levin]

From: Alexei Starovoitov <ast@fb.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit d82bccc69041a51f7b7b9b4a36db0772f4cdba21 ]

verifier must check for reserved size bits in instruction opcode and
reject BPF_LD | BPF_ABS | BPF_DW and BPF_LD | BPF_IND | BPF_DW instructions,
otherwise interpreter will WARN_RATELIMIT on them during execution.

Fixes: ddd872bc3098 ("bpf: verifier: add checks for BPF_ABS | BPF_IND instructions")
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 kernel/bpf/verifier.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 6582410..dd16d19 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1227,6 +1227,7 @@ static int check_ld_abs(struct verifier_env *env, struct bpf_insn *insn)
 	}
 
 	if (insn->dst_reg != BPF_REG_0 || insn->off != 0 ||
+	    BPF_SIZE(insn->code) == BPF_DW ||
 	    (mode == BPF_ABS && insn->src_reg != BPF_REG_0)) {
 		verbose("BPF_LD_ABS uses reserved fields\n");
 		return -EINVAL;
-- 
2.5.0

[added to the 4.1 stable tree] atl2: Disable unimplemented scatter/gather feature

[Sasha Levin]

From: Ben Hutchings <ben@decadent.org.uk>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit f43bfaeddc79effbf3d0fcb53ca477cca66f3db8 ]

atl2 includes NETIF_F_SG in hw_features even though it has no support
for non-linear skbs.  This bug was originally harmless since the
driver does not claim to implement checksum offload and that used to
be a requirement for SG.

Now that SG and checksum offload are independent features, if you
explicitly enable SG *and* use one of the rare protocols that can use
SG without checkusm offload, this potentially leaks sensitive
information (before you notice that it just isn't working).  Therefore
this obscure bug has been designated CVE-2016-2117.

Reported-by: Justin Yackoski <jyackoski@crypto-nite.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Fixes: ec5f06156423 ("net: Kill link between CSUM and SG features.")
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/net/ethernet/atheros/atlx/atl2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c
index 46a5353..972ee64 100644
--- a/drivers/net/ethernet/atheros/atlx/atl2.c
+++ b/drivers/net/ethernet/atheros/atlx/atl2.c
@@ -1412,7 +1412,7 @@ static int atl2_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	err = -EIO;
 
-	netdev->hw_features = NETIF_F_SG | NETIF_F_HW_VLAN_CTAG_RX;
+	netdev->hw_features = NETIF_F_HW_VLAN_CTAG_RX;
 	netdev->features |= (NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX);
 
 	/* Init PHY as early as possible due to power saving issue  */
-- 
2.5.0

[added to the 4.1 stable tree] openvswitch: use flow protocol when recalculating ipv6 checksums

[Sasha Levin]

From: Simon Horman <simon.horman@netronome.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit b4f70527f052b0c00be4d7cac562baa75b212df5 ]

When using masked actions the ipv6_proto field of an action
to set IPv6 fields may be zero rather than the prevailing protocol
which will result in skipping checksum recalculation.

This patch resolves the problem by relying on the protocol
in the flow key rather than that in the set field action.

Fixes: 83d2b9ba1abc ("net: openvswitch: Support masked set actions.")
Cc: Jarno Rajahalme <jrajahalme@nicira.com>
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/openvswitch/actions.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index b491c1c..9920f75 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -441,7 +441,7 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key,
 		mask_ipv6_addr(saddr, key->ipv6_src, mask->ipv6_src, masked);
 
 		if (unlikely(memcmp(saddr, masked, sizeof(masked)))) {
-			set_ipv6_addr(skb, key->ipv6_proto, saddr, masked,
+			set_ipv6_addr(skb, flow_key->ip.proto, saddr, masked,
 				      true);
 			memcpy(&flow_key->ipv6.addr.src, masked,
 			       sizeof(flow_key->ipv6.addr.src));
@@ -463,7 +463,7 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key,
 							     NULL, &flags)
 					       != NEXTHDR_ROUTING);
 
-			set_ipv6_addr(skb, key->ipv6_proto, daddr, masked,
+			set_ipv6_addr(skb, flow_key->ip.proto, daddr, masked,
 				      recalc_csum);
 			memcpy(&flow_key->ipv6.addr.dst, masked,
 			       sizeof(flow_key->ipv6.addr.dst));
-- 
2.5.0

[added to the 4.1 stable tree] ipv4/fib: don't warn when primary address is missing if in_dev is dead

[Sasha Levin]

From: Paolo Abeni <pabeni@redhat.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 391a20333b8393ef2e13014e6e59d192c5594471 ]

After commit fbd40ea0180a ("ipv4: Don't do expensive useless work
during inetdev destroy.") when deleting an interface,
fib_del_ifaddr() can be executed without any primary address
present on the dead interface.

The above is safe, but triggers some "bug: prim == NULL" warnings.

This commit avoids warning if the in_dev is dead

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/ipv4/fib_frontend.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 8776636..513b6aa 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -861,7 +861,11 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim)
 	if (ifa->ifa_flags & IFA_F_SECONDARY) {
 		prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask);
 		if (!prim) {
-			pr_warn("%s: bug: prim == NULL\n", __func__);
+			/* if the device has been deleted, we don't perform
+			 * address promotion
+			 */
+			if (!in_dev->dead)
+				pr_warn("%s: bug: prim == NULL\n", __func__);
 			return;
 		}
 		if (iprim && iprim != prim) {
-- 
2.5.0

[added to the 4.1 stable tree] net/mlx4_en: fix spurious timestamping callbacks

[Sasha Levin]

From: Eric Dumazet <edumazet@google.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit fc96256c906362e845d848d0f6a6354450059e81 ]

When multiple skb are TX-completed in a row, we might incorrectly keep
a timestamp of a prior skb and cause extra work.

Fixes: ec693d47010e8 ("net/mlx4_en: Add HW timestamping (TS) support")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/net/ethernet/mellanox/mlx4/en_tx.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index c10d98f..a1b4301 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -400,7 +400,6 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev,
 	u32 packets = 0;
 	u32 bytes = 0;
 	int factor = priv->cqe_factor;
-	u64 timestamp = 0;
 	int done = 0;
 	int budget = priv->tx_work_limit;
 	u32 last_nr_txbb;
@@ -440,9 +439,12 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev,
 		new_index = be16_to_cpu(cqe->wqe_index) & size_mask;
 
 		do {
+			u64 timestamp = 0;
+
 			txbbs_skipped += last_nr_txbb;
 			ring_index = (ring_index + last_nr_txbb) & size_mask;
-			if (ring->tx_info[ring_index].ts_requested)
+
+			if (unlikely(ring->tx_info[ring_index].ts_requested))
 				timestamp = mlx4_en_get_cqe_ts(cqe);
 
 			/* free next descriptor */
-- 
2.5.0

[added to the 4.1 stable tree] bpf: fix double-fdput in replace_map_fd_with_map_ptr()

[Sasha Levin]

From: Jann Horn <jannh@google.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 8358b02bf67d3a5d8a825070e1aa73f25fb2e4c7 ]

When bpf(BPF_PROG_LOAD, ...) was invoked with a BPF program whose bytecode
references a non-map file descriptor as a map file descriptor, the error
handling code called fdput() twice instead of once (in __bpf_map_get() and
in replace_map_fd_with_map_ptr()). If the file descriptor table of the
current task is shared, this causes f_count to be decremented too much,
allowing the struct file to be freed while it is still in use
(use-after-free). This can be exploited to gain root privileges by an
unprivileged user.

This bug was introduced in
commit 0246e64d9a5f ("bpf: handle pseudo BPF_LD_IMM64 insn"), but is only
exploitable since
commit 1be7f75d1668 ("bpf: enable non-root eBPF programs") because
previously, CAP_SYS_ADMIN was required to reach the vulnerable code.

(posted publicly according to request by maintainer)

Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 kernel/bpf/verifier.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index dd16d19..efd143d 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1865,7 +1865,6 @@ static int replace_map_fd_with_map_ptr(struct verifier_env *env)
 			if (IS_ERR(map)) {
 				verbose("fd %d is not pointing to valid bpf_map\n",
 					insn->imm);
-				fdput(f);
 				return PTR_ERR(map);
 			}
 
-- 
2.5.0

[added to the 4.1 stable tree] net_sched: introduce qdisc_replace() helper

[Sasha Levin]

From: WANG Cong <xiyou.wangcong@gmail.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 86a7996cc8a078793670d82ed97d5a99bb4e8496 ]

Remove nearly duplicated code and prepare for the following patch.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 include/net/sch_generic.h | 17 +++++++++++++++++
 net/sched/sch_cbq.c       |  7 +------
 net/sched/sch_drr.c       |  6 +-----
 net/sched/sch_dsmark.c    |  8 +-------
 net/sched/sch_hfsc.c      |  6 +-----
 net/sched/sch_htb.c       |  9 +--------
 net/sched/sch_multiq.c    |  8 +-------
 net/sched/sch_netem.c     | 10 +---------
 net/sched/sch_prio.c      |  8 +-------
 net/sched/sch_qfq.c       |  6 +-----
 net/sched/sch_red.c       |  7 +------
 net/sched/sch_sfb.c       |  7 +------
 net/sched/sch_tbf.c       |  8 +-------
 13 files changed, 29 insertions(+), 78 deletions(-)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 080b657..1fb8a5b 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -691,6 +691,23 @@ static inline void qdisc_reset_queue(struct Qdisc *sch)
 	sch->qstats.backlog = 0;
 }
 
+static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new,
+					  struct Qdisc **pold)
+{
+	struct Qdisc *old;
+
+	sch_tree_lock(sch);
+	old = *pold;
+	*pold = new;
+	if (old != NULL) {
+		qdisc_tree_decrease_qlen(old, old->q.qlen);
+		qdisc_reset(old);
+	}
+	sch_tree_unlock(sch);
+
+	return old;
+}
+
 static inline unsigned int __qdisc_queue_drop(struct Qdisc *sch,
 					      struct sk_buff_head *list)
 {
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index beeb75f..17ad79e 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1624,13 +1624,8 @@ static int cbq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 			new->reshape_fail = cbq_reshape_fail;
 #endif
 	}
-	sch_tree_lock(sch);
-	*old = cl->q;
-	cl->q = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
 
+	*old = qdisc_replace(sch, new, &cl->q);
 	return 0;
 }
 
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index 3387060..d4b3f82 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -226,11 +226,7 @@ static int drr_graft_class(struct Qdisc *sch, unsigned long arg,
 			new = &noop_qdisc;
 	}
 
-	sch_tree_lock(sch);
-	drr_purge_queue(cl);
-	*old = cl->qdisc;
-	cl->qdisc = new;
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &cl->qdisc);
 	return 0;
 }
 
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index 66700a6..d2084e7 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -67,13 +67,7 @@ static int dsmark_graft(struct Qdisc *sch, unsigned long arg,
 			new = &noop_qdisc;
 	}
 
-	sch_tree_lock(sch);
-	*old = p->q;
-	p->q = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
-
+	*old = qdisc_replace(sch, new, &p->q);
 	return 0;
 }
 
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index e6c7416..134f7d2 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1215,11 +1215,7 @@ hfsc_graft_class(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 			new = &noop_qdisc;
 	}
 
-	sch_tree_lock(sch);
-	hfsc_purge_queue(sch, cl);
-	*old = cl->qdisc;
-	cl->qdisc = new;
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &cl->qdisc);
 	return 0;
 }
 
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index f1acb0f..520ffe9 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1165,14 +1165,7 @@ static int htb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 				     cl->common.classid)) == NULL)
 		return -ENOBUFS;
 
-	sch_tree_lock(sch);
-	*old = cl->un.leaf.q;
-	cl->un.leaf.q = new;
-	if (*old != NULL) {
-		qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-		qdisc_reset(*old);
-	}
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &cl->un.leaf.q);
 	return 0;
 }
 
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index 42dd218..f36ff83 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -303,13 +303,7 @@ static int multiq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 	if (new == NULL)
 		new = &noop_qdisc;
 
-	sch_tree_lock(sch);
-	*old = q->queues[band];
-	q->queues[band] = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
-
+	*old = qdisc_replace(sch, new, &q->queues[band]);
 	return 0;
 }
 
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 956ead2..8d56016 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -1037,15 +1037,7 @@ static int netem_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 {
 	struct netem_sched_data *q = qdisc_priv(sch);
 
-	sch_tree_lock(sch);
-	*old = q->qdisc;
-	q->qdisc = new;
-	if (*old) {
-		qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-		qdisc_reset(*old);
-	}
-	sch_tree_unlock(sch);
-
+	*old = qdisc_replace(sch, new, &q->qdisc);
 	return 0;
 }
 
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index 8e5cd34..a677f543a 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -268,13 +268,7 @@ static int prio_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 	if (new == NULL)
 		new = &noop_qdisc;
 
-	sch_tree_lock(sch);
-	*old = q->queues[band];
-	q->queues[band] = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
-
+	*old = qdisc_replace(sch, new, &q->queues[band]);
 	return 0;
 }
 
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 3ec7e88..6fea320 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -619,11 +619,7 @@ static int qfq_graft_class(struct Qdisc *sch, unsigned long arg,
 			new = &noop_qdisc;
 	}
 
-	sch_tree_lock(sch);
-	qfq_purge_queue(cl);
-	*old = cl->qdisc;
-	cl->qdisc = new;
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &cl->qdisc);
 	return 0;
 }
 
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 6c0534c..d5abcee 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -313,12 +313,7 @@ static int red_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 	if (new == NULL)
 		new = &noop_qdisc;
 
-	sch_tree_lock(sch);
-	*old = q->qdisc;
-	q->qdisc = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &q->qdisc);
 	return 0;
 }
 
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index 5819dd8..fa7f0a3 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -614,12 +614,7 @@ static int sfb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 	if (new == NULL)
 		new = &noop_qdisc;
 
-	sch_tree_lock(sch);
-	*old = q->qdisc;
-	q->qdisc = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &q->qdisc);
 	return 0;
 }
 
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index a4afde1..56a1aef 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -502,13 +502,7 @@ static int tbf_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 	if (new == NULL)
 		new = &noop_qdisc;
 
-	sch_tree_lock(sch);
-	*old = q->qdisc;
-	q->qdisc = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
-
+	*old = qdisc_replace(sch, new, &q->qdisc);
 	return 0;
 }
 
-- 
2.5.0

[added to the 4.1 stable tree] net_sched: update hierarchical backlog too

[Sasha Levin]

From: WANG Cong <xiyou.wangcong@gmail.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 2ccccf5fb43ff62b2b96cc58d95fc0b3596516e4 ]

When the bottom qdisc decides to, for example, drop some packet,
it calls qdisc_tree_decrease_qlen() to update the queue length
for all its ancestors, we need to update the backlog too to
keep the stats on root qdisc accurate.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 include/net/codel.h       |  4 ++++
 include/net/sch_generic.h |  5 +++--
 net/sched/sch_api.c       |  8 +++++---
 net/sched/sch_cbq.c       |  5 +++--
 net/sched/sch_choke.c     |  6 ++++--
 net/sched/sch_codel.c     | 10 ++++++----
 net/sched/sch_drr.c       |  3 ++-
 net/sched/sch_fq.c        |  4 +++-
 net/sched/sch_fq_codel.c  | 17 ++++++++++++-----
 net/sched/sch_hfsc.c      |  3 ++-
 net/sched/sch_hhf.c       | 10 +++++++---
 net/sched/sch_htb.c       | 10 ++++++----
 net/sched/sch_multiq.c    |  8 +++++---
 net/sched/sch_netem.c     |  3 ++-
 net/sched/sch_pie.c       |  5 +++--
 net/sched/sch_prio.c      |  7 ++++---
 net/sched/sch_qfq.c       |  3 ++-
 net/sched/sch_red.c       |  3 ++-
 net/sched/sch_sfb.c       |  3 ++-
 net/sched/sch_sfq.c       | 16 +++++++++-------
 net/sched/sch_tbf.c       |  7 +++++--
 21 files changed, 91 insertions(+), 49 deletions(-)

diff --git a/include/net/codel.h b/include/net/codel.h
index 1e18005..0ee7610 100644
--- a/include/net/codel.h
+++ b/include/net/codel.h
@@ -160,11 +160,13 @@ struct codel_vars {
  * struct codel_stats - contains codel shared variables and stats
  * @maxpacket:	largest packet we've seen so far
  * @drop_count:	temp count of dropped packets in dequeue()
+ * @drop_len:	bytes of dropped packets in dequeue()
  * ecn_mark:	number of packets we ECN marked instead of dropping
  */
 struct codel_stats {
 	u32		maxpacket;
 	u32		drop_count;
+	u32		drop_len;
 	u32		ecn_mark;
 };
 
@@ -301,6 +303,7 @@ static struct sk_buff *codel_dequeue(struct Qdisc *sch,
 								  vars->rec_inv_sqrt);
 					goto end;
 				}
+				stats->drop_len += qdisc_pkt_len(skb);
 				qdisc_drop(skb, sch);
 				stats->drop_count++;
 				skb = dequeue_func(vars, sch);
@@ -323,6 +326,7 @@ static struct sk_buff *codel_dequeue(struct Qdisc *sch,
 		if (params->ecn && INET_ECN_set_ce(skb)) {
 			stats->ecn_mark++;
 		} else {
+			stats->drop_len += qdisc_pkt_len(skb);
 			qdisc_drop(skb, sch);
 			stats->drop_count++;
 
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 1fb8a5b..530bdca 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -395,7 +395,8 @@ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue,
 			      struct Qdisc *qdisc);
 void qdisc_reset(struct Qdisc *qdisc);
 void qdisc_destroy(struct Qdisc *qdisc);
-void qdisc_tree_decrease_qlen(struct Qdisc *qdisc, unsigned int n);
+void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, unsigned int n,
+			       unsigned int len);
 struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 			  const struct Qdisc_ops *ops);
 struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue,
@@ -700,7 +701,7 @@ static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new,
 	old = *pold;
 	*pold = new;
 	if (old != NULL) {
-		qdisc_tree_decrease_qlen(old, old->q.qlen);
+		qdisc_tree_reduce_backlog(old, old->q.qlen, old->qstats.backlog);
 		qdisc_reset(old);
 	}
 	sch_tree_unlock(sch);
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 68c599a..c244a49 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -744,14 +744,15 @@ static u32 qdisc_alloc_handle(struct net_device *dev)
 	return 0;
 }
 
-void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
+void qdisc_tree_reduce_backlog(struct Qdisc *sch, unsigned int n,
+			       unsigned int len)
 {
 	const struct Qdisc_class_ops *cops;
 	unsigned long cl;
 	u32 parentid;
 	int drops;
 
-	if (n == 0)
+	if (n == 0 && len == 0)
 		return;
 	drops = max_t(int, n, 0);
 	rcu_read_lock();
@@ -774,11 +775,12 @@ void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
 			cops->put(sch, cl);
 		}
 		sch->q.qlen -= n;
+		sch->qstats.backlog -= len;
 		__qdisc_qstats_drop(sch, drops);
 	}
 	rcu_read_unlock();
 }
-EXPORT_SYMBOL(qdisc_tree_decrease_qlen);
+EXPORT_SYMBOL(qdisc_tree_reduce_backlog);
 
 static void notify_and_destroy(struct net *net, struct sk_buff *skb,
 			       struct nlmsghdr *n, u32 clid,
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 17ad79e..f6e7a60 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1909,7 +1909,7 @@ static int cbq_delete(struct Qdisc *sch, unsigned long arg)
 {
 	struct cbq_sched_data *q = qdisc_priv(sch);
 	struct cbq_class *cl = (struct cbq_class *)arg;
-	unsigned int qlen;
+	unsigned int qlen, backlog;
 
 	if (cl->filters || cl->children || cl == &q->link)
 		return -EBUSY;
@@ -1917,8 +1917,9 @@ static int cbq_delete(struct Qdisc *sch, unsigned long arg)
 	sch_tree_lock(sch);
 
 	qlen = cl->q->q.qlen;
+	backlog = cl->q->qstats.backlog;
 	qdisc_reset(cl->q);
-	qdisc_tree_decrease_qlen(cl->q, qlen);
+	qdisc_tree_reduce_backlog(cl->q, qlen, backlog);
 
 	if (cl->next_alive)
 		cbq_deactivate_class(cl);
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index c009eb9..3f6437d 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -128,8 +128,8 @@ static void choke_drop_by_idx(struct Qdisc *sch, unsigned int idx)
 		choke_zap_tail_holes(q);
 
 	qdisc_qstats_backlog_dec(sch, skb);
+	qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb));
 	qdisc_drop(skb, sch);
-	qdisc_tree_decrease_qlen(sch, 1);
 	--sch->q.qlen;
 }
 
@@ -449,6 +449,7 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt)
 		old = q->tab;
 		if (old) {
 			unsigned int oqlen = sch->q.qlen, tail = 0;
+			unsigned dropped = 0;
 
 			while (q->head != q->tail) {
 				struct sk_buff *skb = q->tab[q->head];
@@ -460,11 +461,12 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt)
 					ntab[tail++] = skb;
 					continue;
 				}
+				dropped += qdisc_pkt_len(skb);
 				qdisc_qstats_backlog_dec(sch, skb);
 				--sch->q.qlen;
 				qdisc_drop(skb, sch);
 			}
-			qdisc_tree_decrease_qlen(sch, oqlen - sch->q.qlen);
+			qdisc_tree_reduce_backlog(sch, oqlen - sch->q.qlen, dropped);
 			q->head = 0;
 			q->tail = tail;
 		}
diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c
index 7a0bdb1..9a9068d 100644
--- a/net/sched/sch_codel.c
+++ b/net/sched/sch_codel.c
@@ -79,12 +79,13 @@ static struct sk_buff *codel_qdisc_dequeue(struct Qdisc *sch)
 
 	skb = codel_dequeue(sch, &q->params, &q->vars, &q->stats, dequeue);
 
-	/* We cant call qdisc_tree_decrease_qlen() if our qlen is 0,
+	/* We cant call qdisc_tree_reduce_backlog() if our qlen is 0,
 	 * or HTB crashes. Defer it for next round.
 	 */
 	if (q->stats.drop_count && sch->q.qlen) {
-		qdisc_tree_decrease_qlen(sch, q->stats.drop_count);
+		qdisc_tree_reduce_backlog(sch, q->stats.drop_count, q->stats.drop_len);
 		q->stats.drop_count = 0;
+		q->stats.drop_len = 0;
 	}
 	if (skb)
 		qdisc_bstats_update(sch, skb);
@@ -115,7 +116,7 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct codel_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_CODEL_MAX + 1];
-	unsigned int qlen;
+	unsigned int qlen, dropped = 0;
 	int err;
 
 	if (!opt)
@@ -149,10 +150,11 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt)
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = __skb_dequeue(&sch->q);
 
+		dropped += qdisc_pkt_len(skb);
 		qdisc_qstats_backlog_dec(sch, skb);
 		qdisc_drop(skb, sch);
 	}
-	qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen);
+	qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped);
 
 	sch_tree_unlock(sch);
 	return 0;
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index d4b3f82..e599803 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -53,9 +53,10 @@ static struct drr_class *drr_find_class(struct Qdisc *sch, u32 classid)
 static void drr_purge_queue(struct drr_class *cl)
 {
 	unsigned int len = cl->qdisc->q.qlen;
+	unsigned int backlog = cl->qdisc->qstats.backlog;
 
 	qdisc_reset(cl->qdisc);
-	qdisc_tree_decrease_qlen(cl->qdisc, len);
+	qdisc_tree_reduce_backlog(cl->qdisc, len, backlog);
 }
 
 static const struct nla_policy drr_policy[TCA_DRR_MAX + 1] = {
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index f377702..4816778 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -659,6 +659,7 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt)
 	struct fq_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_FQ_MAX + 1];
 	int err, drop_count = 0;
+	unsigned drop_len = 0;
 	u32 fq_log;
 
 	if (!opt)
@@ -733,10 +734,11 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt)
 
 		if (!skb)
 			break;
+		drop_len += qdisc_pkt_len(skb);
 		kfree_skb(skb);
 		drop_count++;
 	}
-	qdisc_tree_decrease_qlen(sch, drop_count);
+	qdisc_tree_reduce_backlog(sch, drop_count, drop_len);
 
 	sch_tree_unlock(sch);
 	return err;
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 9291598..96971c7 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -173,7 +173,7 @@ static unsigned int fq_codel_drop(struct Qdisc *sch)
 static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 {
 	struct fq_codel_sched_data *q = qdisc_priv(sch);
-	unsigned int idx;
+	unsigned int idx, prev_backlog;
 	struct fq_codel_flow *flow;
 	int uninitialized_var(ret);
 
@@ -201,6 +201,7 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	if (++sch->q.qlen <= sch->limit)
 		return NET_XMIT_SUCCESS;
 
+	prev_backlog = sch->qstats.backlog;
 	q->drop_overlimit++;
 	/* Return Congestion Notification only if we dropped a packet
 	 * from this flow.
@@ -209,7 +210,7 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		return NET_XMIT_CN;
 
 	/* As we dropped a packet, better let upper stack know this */
-	qdisc_tree_decrease_qlen(sch, 1);
+	qdisc_tree_reduce_backlog(sch, 1, prev_backlog - sch->qstats.backlog);
 	return NET_XMIT_SUCCESS;
 }
 
@@ -239,6 +240,7 @@ static struct sk_buff *fq_codel_dequeue(struct Qdisc *sch)
 	struct fq_codel_flow *flow;
 	struct list_head *head;
 	u32 prev_drop_count, prev_ecn_mark;
+	unsigned int prev_backlog;
 
 begin:
 	head = &q->new_flows;
@@ -257,6 +259,7 @@ begin:
 
 	prev_drop_count = q->cstats.drop_count;
 	prev_ecn_mark = q->cstats.ecn_mark;
+	prev_backlog = sch->qstats.backlog;
 
 	skb = codel_dequeue(sch, &q->cparams, &flow->cvars, &q->cstats,
 			    dequeue);
@@ -274,12 +277,14 @@ begin:
 	}
 	qdisc_bstats_update(sch, skb);
 	flow->deficit -= qdisc_pkt_len(skb);
-	/* We cant call qdisc_tree_decrease_qlen() if our qlen is 0,
+	/* We cant call qdisc_tree_reduce_backlog() if our qlen is 0,
 	 * or HTB crashes. Defer it for next round.
 	 */
 	if (q->cstats.drop_count && sch->q.qlen) {
-		qdisc_tree_decrease_qlen(sch, q->cstats.drop_count);
+		qdisc_tree_reduce_backlog(sch, q->cstats.drop_count,
+					  q->cstats.drop_len);
 		q->cstats.drop_count = 0;
+		q->cstats.drop_len = 0;
 	}
 	return skb;
 }
@@ -347,11 +352,13 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt)
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = fq_codel_dequeue(sch);
 
+		q->cstats.drop_len += qdisc_pkt_len(skb);
 		kfree_skb(skb);
 		q->cstats.drop_count++;
 	}
-	qdisc_tree_decrease_qlen(sch, q->cstats.drop_count);
+	qdisc_tree_reduce_backlog(sch, q->cstats.drop_count, q->cstats.drop_len);
 	q->cstats.drop_count = 0;
+	q->cstats.drop_len = 0;
 
 	sch_tree_unlock(sch);
 	return 0;
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 134f7d2..d3e21da 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -895,9 +895,10 @@ static void
 hfsc_purge_queue(struct Qdisc *sch, struct hfsc_class *cl)
 {
 	unsigned int len = cl->qdisc->q.qlen;
+	unsigned int backlog = cl->qdisc->qstats.backlog;
 
 	qdisc_reset(cl->qdisc);
-	qdisc_tree_decrease_qlen(cl->qdisc, len);
+	qdisc_tree_reduce_backlog(cl->qdisc, len, backlog);
 }
 
 static void
diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c
index 15d3aab..792c6f3 100644
--- a/net/sched/sch_hhf.c
+++ b/net/sched/sch_hhf.c
@@ -390,6 +390,7 @@ static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	struct hhf_sched_data *q = qdisc_priv(sch);
 	enum wdrr_bucket_idx idx;
 	struct wdrr_bucket *bucket;
+	unsigned int prev_backlog;
 
 	idx = hhf_classify(skb, sch);
 
@@ -417,6 +418,7 @@ static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	if (++sch->q.qlen <= sch->limit)
 		return NET_XMIT_SUCCESS;
 
+	prev_backlog = sch->qstats.backlog;
 	q->drop_overlimit++;
 	/* Return Congestion Notification only if we dropped a packet from this
 	 * bucket.
@@ -425,7 +427,7 @@ static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		return NET_XMIT_CN;
 
 	/* As we dropped a packet, better let upper stack know this. */
-	qdisc_tree_decrease_qlen(sch, 1);
+	qdisc_tree_reduce_backlog(sch, 1, prev_backlog - sch->qstats.backlog);
 	return NET_XMIT_SUCCESS;
 }
 
@@ -535,7 +537,7 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct hhf_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_HHF_MAX + 1];
-	unsigned int qlen;
+	unsigned int qlen, prev_backlog;
 	int err;
 	u64 non_hh_quantum;
 	u32 new_quantum = q->quantum;
@@ -585,12 +587,14 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt)
 	}
 
 	qlen = sch->q.qlen;
+	prev_backlog = sch->qstats.backlog;
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = hhf_dequeue(sch);
 
 		kfree_skb(skb);
 	}
-	qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen);
+	qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen,
+				  prev_backlog - sch->qstats.backlog);
 
 	sch_tree_unlock(sch);
 	return 0;
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 520ffe9..6b118b1 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1267,7 +1267,6 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg)
 {
 	struct htb_sched *q = qdisc_priv(sch);
 	struct htb_class *cl = (struct htb_class *)arg;
-	unsigned int qlen;
 	struct Qdisc *new_q = NULL;
 	int last_child = 0;
 
@@ -1287,9 +1286,11 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg)
 	sch_tree_lock(sch);
 
 	if (!cl->level) {
-		qlen = cl->un.leaf.q->q.qlen;
+		unsigned int qlen = cl->un.leaf.q->q.qlen;
+		unsigned int backlog = cl->un.leaf.q->qstats.backlog;
+
 		qdisc_reset(cl->un.leaf.q);
-		qdisc_tree_decrease_qlen(cl->un.leaf.q, qlen);
+		qdisc_tree_reduce_backlog(cl->un.leaf.q, qlen, backlog);
 	}
 
 	/* delete from hash and active; remainder in destroy_class */
@@ -1423,10 +1424,11 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 		sch_tree_lock(sch);
 		if (parent && !parent->level) {
 			unsigned int qlen = parent->un.leaf.q->q.qlen;
+			unsigned int backlog = parent->un.leaf.q->qstats.backlog;
 
 			/* turn parent into inner node */
 			qdisc_reset(parent->un.leaf.q);
-			qdisc_tree_decrease_qlen(parent->un.leaf.q, qlen);
+			qdisc_tree_reduce_backlog(parent->un.leaf.q, qlen, backlog);
 			qdisc_destroy(parent->un.leaf.q);
 			if (parent->prio_activity)
 				htb_deactivate(q, parent);
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index f36ff83..23437d6 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -218,7 +218,8 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt)
 		if (q->queues[i] != &noop_qdisc) {
 			struct Qdisc *child = q->queues[i];
 			q->queues[i] = &noop_qdisc;
-			qdisc_tree_decrease_qlen(child, child->q.qlen);
+			qdisc_tree_reduce_backlog(child, child->q.qlen,
+						  child->qstats.backlog);
 			qdisc_destroy(child);
 		}
 	}
@@ -238,8 +239,9 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt)
 				q->queues[i] = child;
 
 				if (old != &noop_qdisc) {
-					qdisc_tree_decrease_qlen(old,
-								 old->q.qlen);
+					qdisc_tree_reduce_backlog(old,
+								  old->q.qlen,
+								  old->qstats.backlog);
 					qdisc_destroy(old);
 				}
 				sch_tree_unlock(sch);
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 8d56016..cc00329 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -598,7 +598,8 @@ deliver:
 				if (unlikely(err != NET_XMIT_SUCCESS)) {
 					if (net_xmit_drop_count(err)) {
 						qdisc_qstats_drop(sch);
-						qdisc_tree_decrease_qlen(sch, 1);
+						qdisc_tree_reduce_backlog(sch, 1,
+									  qdisc_pkt_len(skb));
 					}
 				}
 				goto tfifo_dequeue;
diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c
index b783a44..71ae3b9 100644
--- a/net/sched/sch_pie.c
+++ b/net/sched/sch_pie.c
@@ -183,7 +183,7 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct pie_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_PIE_MAX + 1];
-	unsigned int qlen;
+	unsigned int qlen, dropped = 0;
 	int err;
 
 	if (!opt)
@@ -232,10 +232,11 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt)
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = __skb_dequeue(&sch->q);
 
+		dropped += qdisc_pkt_len(skb);
 		qdisc_qstats_backlog_dec(sch, skb);
 		qdisc_drop(skb, sch);
 	}
-	qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen);
+	qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped);
 
 	sch_tree_unlock(sch);
 	return 0;
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index a677f543a..e671b1a 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -191,7 +191,7 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt)
 		struct Qdisc *child = q->queues[i];
 		q->queues[i] = &noop_qdisc;
 		if (child != &noop_qdisc) {
-			qdisc_tree_decrease_qlen(child, child->q.qlen);
+			qdisc_tree_reduce_backlog(child, child->q.qlen, child->qstats.backlog);
 			qdisc_destroy(child);
 		}
 	}
@@ -210,8 +210,9 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt)
 				q->queues[i] = child;
 
 				if (old != &noop_qdisc) {
-					qdisc_tree_decrease_qlen(old,
-								 old->q.qlen);
+					qdisc_tree_reduce_backlog(old,
+								  old->q.qlen,
+								  old->qstats.backlog);
 					qdisc_destroy(old);
 				}
 				sch_tree_unlock(sch);
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 6fea320..e2b8fd4 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -221,9 +221,10 @@ static struct qfq_class *qfq_find_class(struct Qdisc *sch, u32 classid)
 static void qfq_purge_queue(struct qfq_class *cl)
 {
 	unsigned int len = cl->qdisc->q.qlen;
+	unsigned int backlog = cl->qdisc->qstats.backlog;
 
 	qdisc_reset(cl->qdisc);
-	qdisc_tree_decrease_qlen(cl->qdisc, len);
+	qdisc_tree_reduce_backlog(cl->qdisc, len, backlog);
 }
 
 static const struct nla_policy qfq_policy[TCA_QFQ_MAX + 1] = {
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index d5abcee..8c0508c 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -210,7 +210,8 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt)
 	q->flags = ctl->flags;
 	q->limit = ctl->limit;
 	if (child) {
-		qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen);
+		qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen,
+					  q->qdisc->qstats.backlog);
 		qdisc_destroy(q->qdisc);
 		q->qdisc = child;
 	}
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index fa7f0a3..e1d634e 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -518,7 +518,8 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt)
 
 	sch_tree_lock(sch);
 
-	qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen);
+	qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen,
+				  q->qdisc->qstats.backlog);
 	qdisc_destroy(q->qdisc);
 	q->qdisc = child;
 
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index b877140..4417fb2 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -369,7 +369,7 @@ static int
 sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 {
 	struct sfq_sched_data *q = qdisc_priv(sch);
-	unsigned int hash;
+	unsigned int hash, dropped;
 	sfq_index x, qlen;
 	struct sfq_slot *slot;
 	int uninitialized_var(ret);
@@ -484,7 +484,7 @@ enqueue:
 		return NET_XMIT_SUCCESS;
 
 	qlen = slot->qlen;
-	sfq_drop(sch);
+	dropped = sfq_drop(sch);
 	/* Return Congestion Notification only if we dropped a packet
 	 * from this flow.
 	 */
@@ -492,7 +492,7 @@ enqueue:
 		return NET_XMIT_CN;
 
 	/* As we dropped a packet, better let upper stack know this */
-	qdisc_tree_decrease_qlen(sch, 1);
+	qdisc_tree_reduce_backlog(sch, 1, dropped);
 	return NET_XMIT_SUCCESS;
 }
 
@@ -560,6 +560,7 @@ static void sfq_rehash(struct Qdisc *sch)
 	struct sfq_slot *slot;
 	struct sk_buff_head list;
 	int dropped = 0;
+	unsigned int drop_len = 0;
 
 	__skb_queue_head_init(&list);
 
@@ -588,6 +589,7 @@ static void sfq_rehash(struct Qdisc *sch)
 			if (x >= SFQ_MAX_FLOWS) {
 drop:
 				qdisc_qstats_backlog_dec(sch, skb);
+				drop_len += qdisc_pkt_len(skb);
 				kfree_skb(skb);
 				dropped++;
 				continue;
@@ -617,7 +619,7 @@ drop:
 		}
 	}
 	sch->q.qlen -= dropped;
-	qdisc_tree_decrease_qlen(sch, dropped);
+	qdisc_tree_reduce_backlog(sch, dropped, drop_len);
 }
 
 static void sfq_perturbation(unsigned long arg)
@@ -641,7 +643,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt)
 	struct sfq_sched_data *q = qdisc_priv(sch);
 	struct tc_sfq_qopt *ctl = nla_data(opt);
 	struct tc_sfq_qopt_v1 *ctl_v1 = NULL;
-	unsigned int qlen;
+	unsigned int qlen, dropped = 0;
 	struct red_parms *p = NULL;
 
 	if (opt->nla_len < nla_attr_size(sizeof(*ctl)))
@@ -690,8 +692,8 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt)
 
 	qlen = sch->q.qlen;
 	while (sch->q.qlen > q->limit)
-		sfq_drop(sch);
-	qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen);
+		dropped += sfq_drop(sch);
+	qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped);
 
 	del_timer(&q->perturb_timer);
 	if (q->perturb_period) {
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 56a1aef..c2fbde7 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -160,6 +160,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch)
 	struct tbf_sched_data *q = qdisc_priv(sch);
 	struct sk_buff *segs, *nskb;
 	netdev_features_t features = netif_skb_features(skb);
+	unsigned int len = 0, prev_len = qdisc_pkt_len(skb);
 	int ret, nb;
 
 	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
@@ -172,6 +173,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch)
 		nskb = segs->next;
 		segs->next = NULL;
 		qdisc_skb_cb(segs)->pkt_len = segs->len;
+		len += segs->len;
 		ret = qdisc_enqueue(segs, q->qdisc);
 		if (ret != NET_XMIT_SUCCESS) {
 			if (net_xmit_drop_count(ret))
@@ -183,7 +185,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch)
 	}
 	sch->q.qlen += nb;
 	if (nb > 1)
-		qdisc_tree_decrease_qlen(sch, 1 - nb);
+		qdisc_tree_reduce_backlog(sch, 1 - nb, prev_len - len);
 	consume_skb(skb);
 	return nb > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP;
 }
@@ -399,7 +401,8 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
 
 	sch_tree_lock(sch);
 	if (child) {
-		qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen);
+		qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen,
+					  q->qdisc->qstats.backlog);
 		qdisc_destroy(q->qdisc);
 		q->qdisc = child;
 	}
-- 
2.5.0

[added to the 4.1 stable tree] sch_htb: update backlog as well

[Sasha Levin]

From: WANG Cong <xiyou.wangcong@gmail.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 431e3a8e36a05a37126f34b41aa3a5a6456af04e ]

We saw qlen!=0 but backlog==0 on our production machine:

qdisc htb 1: dev eth0 root refcnt 2 r2q 10 default 1 direct_packets_stat 0 ver 3.17
 Sent 172680457356 bytes 222469449 pkt (dropped 0, overlimits 123575834 requeues 0)
 backlog 0b 72p requeues 0

The problem is we only count qlen for HTB qdisc but not backlog.
We need to update backlog too when we update qlen, so that we
can at least know the average packet length.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/sched/sch_htb.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 6b118b1..ccff006 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -600,6 +600,7 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		htb_activate(q, cl);
 	}
 
+	qdisc_qstats_backlog_inc(sch, skb);
 	sch->q.qlen++;
 	return NET_XMIT_SUCCESS;
 }
@@ -889,6 +890,7 @@ static struct sk_buff *htb_dequeue(struct Qdisc *sch)
 ok:
 		qdisc_bstats_update(sch, skb);
 		qdisc_unthrottled(sch);
+		qdisc_qstats_backlog_dec(sch, skb);
 		sch->q.qlen--;
 		return skb;
 	}
@@ -955,6 +957,7 @@ static unsigned int htb_drop(struct Qdisc *sch)
 			unsigned int len;
 			if (cl->un.leaf.q->ops->drop &&
 			    (len = cl->un.leaf.q->ops->drop(cl->un.leaf.q))) {
+				sch->qstats.backlog -= len;
 				sch->q.qlen--;
 				if (!cl->un.leaf.q->q.qlen)
 					htb_deactivate(q, cl);
@@ -984,12 +987,12 @@ static void htb_reset(struct Qdisc *sch)
 			}
 			cl->prio_activity = 0;
 			cl->cmode = HTB_CAN_SEND;
-
 		}
 	}
 	qdisc_watchdog_cancel(&q->watchdog);
 	__skb_queue_purge(&q->direct_queue);
 	sch->q.qlen = 0;
+	sch->qstats.backlog = 0;
 	memset(q->hlevel, 0, sizeof(q->hlevel));
 	memset(q->row_mask, 0, sizeof(q->row_mask));
 	for (i = 0; i < TC_HTB_NUMPRIO; i++)
-- 
2.5.0

[added to the 4.1 stable tree] sch_dsmark: update backlog as well

[Sasha Levin]

From: WANG Cong <xiyou.wangcong@gmail.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit bdf17661f63a79c3cb4209b970b1cc39e34f7543 ]

Similarly, we need to update backlog too when we update qlen.

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>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/sched/sch_dsmark.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index d2084e7..7288dda 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -256,6 +256,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		return err;
 	}
 
+	qdisc_qstats_backlog_inc(sch, skb);
 	sch->q.qlen++;
 
 	return NET_XMIT_SUCCESS;
@@ -278,6 +279,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch)
 		return NULL;
 
 	qdisc_bstats_update(sch, skb);
+	qdisc_qstats_backlog_dec(sch, skb);
 	sch->q.qlen--;
 
 	index = skb->tc_index & (p->indices - 1);
@@ -393,6 +395,7 @@ static void dsmark_reset(struct Qdisc *sch)
 
 	pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p);
 	qdisc_reset(p->q);
+	sch->qstats.backlog = 0;
 	sch->q.qlen = 0;
 }
 
-- 
2.5.0

[added to the 4.1 stable tree] netem: Segment GSO packets on enqueue

[Sasha Levin]

From: Neil Horman <nhorman@tuxdriver.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 6071bd1aa13ed9e41824bafad845b7b7f4df5cfd ]

This was recently reported to me, and reproduced on the latest net kernel,
when attempting to run netperf from a host that had a netem qdisc attached
to the egress interface:

[  788.073771] ---------------------[ cut here ]---------------------------
[  788.096716] WARNING: at net/core/dev.c:2253 skb_warn_bad_offload+0xcd/0xda()
[  788.129521] bnx2: caps=(0x00000001801949b3, 0x0000000000000000) len=2962
data_len=0 gso_size=1448 gso_type=1 ip_summed=3
[  788.182150] Modules linked in: sch_netem kvm_amd kvm crc32_pclmul ipmi_ssif
ghash_clmulni_intel sp5100_tco amd64_edac_mod aesni_intel lrw gf128mul
glue_helper ablk_helper edac_mce_amd cryptd pcspkr sg edac_core hpilo ipmi_si
i2c_piix4 k10temp fam15h_power hpwdt ipmi_msghandler shpchp acpi_power_meter
pcc_cpufreq nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c
sd_mod crc_t10dif crct10dif_generic mgag200 syscopyarea sysfillrect sysimgblt
i2c_algo_bit drm_kms_helper ahci ata_generic pata_acpi ttm libahci
crct10dif_pclmul pata_atiixp tg3 libata crct10dif_common drm crc32c_intel ptp
serio_raw bnx2 r8169 hpsa pps_core i2c_core mii dm_mirror dm_region_hash dm_log
dm_mod
[  788.465294] CPU: 16 PID: 0 Comm: swapper/16 Tainted: G        W
------------   3.10.0-327.el7.x86_64 #1
[  788.511521] Hardware name: HP ProLiant DL385p Gen8, BIOS A28 12/17/2012
[  788.542260]  ffff880437c036b8 f7afc56532a53db9 ffff880437c03670
ffffffff816351f1
[  788.576332]  ffff880437c036a8 ffffffff8107b200 ffff880633e74200
ffff880231674000
[  788.611943]  0000000000000001 0000000000000003 0000000000000000
ffff880437c03710
[  788.647241] Call Trace:
[  788.658817]  <IRQ>  [<ffffffff816351f1>] dump_stack+0x19/0x1b
[  788.686193]  [<ffffffff8107b200>] warn_slowpath_common+0x70/0xb0
[  788.713803]  [<ffffffff8107b29c>] warn_slowpath_fmt+0x5c/0x80
[  788.741314]  [<ffffffff812f92f3>] ? ___ratelimit+0x93/0x100
[  788.767018]  [<ffffffff81637f49>] skb_warn_bad_offload+0xcd/0xda
[  788.796117]  [<ffffffff8152950c>] skb_checksum_help+0x17c/0x190
[  788.823392]  [<ffffffffa01463a1>] netem_enqueue+0x741/0x7c0 [sch_netem]
[  788.854487]  [<ffffffff8152cb58>] dev_queue_xmit+0x2a8/0x570
[  788.880870]  [<ffffffff8156ae1d>] ip_finish_output+0x53d/0x7d0
...

The problem occurs because netem is not prepared to handle GSO packets (as it
uses skb_checksum_help in its enqueue path, which cannot manipulate these
frames).

The solution I think is to simply segment the skb in a simmilar fashion to the
way we do in __dev_queue_xmit (via validate_xmit_skb), with some minor changes.
When we decide to corrupt an skb, if the frame is GSO, we segment it, corrupt
the first segment, and enqueue the remaining ones.

tested successfully by myself on the latest net kernel, to which this applies

Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
CC: Jamal Hadi Salim <jhs@mojatatu.com>
CC: "David S. Miller" <davem@davemloft.net>
CC: netem@lists.linux-foundation.org
CC: eric.dumazet@gmail.com
CC: stephen@networkplumber.org
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/sched/sch_netem.c | 61 +++++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 59 insertions(+), 2 deletions(-)

diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index cc00329..80124c1 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -395,6 +395,25 @@ static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch)
 	sch->q.qlen++;
 }
 
+/* netem can't properly corrupt a megapacket (like we get from GSO), so instead
+ * when we statistically choose to corrupt one, we instead segment it, returning
+ * the first packet to be corrupted, and re-enqueue the remaining frames
+ */
+static struct sk_buff *netem_segment(struct sk_buff *skb, struct Qdisc *sch)
+{
+	struct sk_buff *segs;
+	netdev_features_t features = netif_skb_features(skb);
+
+	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+
+	if (IS_ERR_OR_NULL(segs)) {
+		qdisc_reshape_fail(skb, sch);
+		return NULL;
+	}
+	consume_skb(skb);
+	return segs;
+}
+
 /*
  * Insert one skb into qdisc.
  * Note: parent depends on return value to account for queue length.
@@ -407,7 +426,11 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	/* We don't fill cb now as skb_unshare() may invalidate it */
 	struct netem_skb_cb *cb;
 	struct sk_buff *skb2;
+	struct sk_buff *segs = NULL;
+	unsigned int len = 0, last_len, prev_len = qdisc_pkt_len(skb);
+	int nb = 0;
 	int count = 1;
+	int rc = NET_XMIT_SUCCESS;
 
 	/* Random duplication */
 	if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor))
@@ -453,10 +476,23 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	 * do it now in software before we mangle it.
 	 */
 	if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor)) {
+		if (skb_is_gso(skb)) {
+			segs = netem_segment(skb, sch);
+			if (!segs)
+				return NET_XMIT_DROP;
+		} else {
+			segs = skb;
+		}
+
+		skb = segs;
+		segs = segs->next;
+
 		if (!(skb = skb_unshare(skb, GFP_ATOMIC)) ||
 		    (skb->ip_summed == CHECKSUM_PARTIAL &&
-		     skb_checksum_help(skb)))
-			return qdisc_drop(skb, sch);
+		     skb_checksum_help(skb))) {
+			rc = qdisc_drop(skb, sch);
+			goto finish_segs;
+		}
 
 		skb->data[prandom_u32() % skb_headlen(skb)] ^=
 			1<<(prandom_u32() % 8);
@@ -516,6 +552,27 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		sch->qstats.requeues++;
 	}
 
+finish_segs:
+	if (segs) {
+		while (segs) {
+			skb2 = segs->next;
+			segs->next = NULL;
+			qdisc_skb_cb(segs)->pkt_len = segs->len;
+			last_len = segs->len;
+			rc = qdisc_enqueue(segs, sch);
+			if (rc != NET_XMIT_SUCCESS) {
+				if (net_xmit_drop_count(rc))
+					qdisc_qstats_drop(sch);
+			} else {
+				nb++;
+				len += last_len;
+			}
+			segs = skb2;
+		}
+		sch->q.qlen += nb;
+		if (nb > 1)
+			qdisc_tree_reduce_backlog(sch, 1 - nb, prev_len - len);
+	}
 	return NET_XMIT_SUCCESS;
 }
 
-- 
2.5.0

[added to the 4.1 stable tree] net: fec: only clear a queue's work bit if the queue was emptied

[Sasha Levin]

From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 1c021bb717a70aaeaa4b25c91f43c2aeddd922de ]

In the receive path a queue's work bit was cleared unconditionally even
if fec_enet_rx_queue only read out a part of the available packets from
the hardware. This resulted in not reading any packets in the next napi
turn and so packets were delayed or lost.

The obvious fix is to only clear a queue's bit when the queue was
emptied.

Fixes: 4d494cdc92b3 ("net: fec: change data structure to support multiqueue")
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Lucas Stach <l.stach@pengutronix.de>
Tested-by: Fugang Duan <fugang.duan@nxp.com>
Acked-by: Fugang Duan <fugang.duan@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/net/ethernet/freescale/fec_main.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 570390b..67aec18 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1546,9 +1546,15 @@ fec_enet_rx(struct net_device *ndev, int budget)
 	struct fec_enet_private *fep = netdev_priv(ndev);
 
 	for_each_set_bit(queue_id, &fep->work_rx, FEC_ENET_MAX_RX_QS) {
-		clear_bit(queue_id, &fep->work_rx);
-		pkt_received += fec_enet_rx_queue(ndev,
+		int ret;
+
+		ret = fec_enet_rx_queue(ndev,
 					budget - pkt_received, queue_id);
+
+		if (ret < budget - pkt_received)
+			clear_bit(queue_id, &fep->work_rx);
+
+		pkt_received += ret;
 	}
 	return pkt_received;
 }
-- 
2.5.0

[added to the 4.1 stable tree] net: fix infoleak in llc

[Sasha Levin]

From: Kangjie Lu <kangjielu@gmail.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit b8670c09f37bdf2847cc44f36511a53afc6161fd ]

The stack object “info” has a total size of 12 bytes. Its last byte
is padding which is not initialized and leaked via “put_cmsg”.

Signed-off-by: Kangjie Lu <kjlu@gatech.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/llc/af_llc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 17a8dff..c58f242 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -626,6 +626,7 @@ static void llc_cmsg_rcv(struct msghdr *msg, struct sk_buff *skb)
 	if (llc->cmsg_flags & LLC_CMSG_PKTINFO) {
 		struct llc_pktinfo info;
 
+		memset(&info, 0, sizeof(info));
 		info.lpi_ifindex = llc_sk(skb->sk)->dev->ifindex;
 		llc_pdu_decode_dsap(skb, &info.lpi_sap);
 		llc_pdu_decode_da(skb, info.lpi_mac);
-- 
2.5.0

[added to the 4.1 stable tree] net: fix infoleak in rtnetlink

[Sasha Levin]

From: Kangjie Lu <kangjielu@gmail.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 5f8e44741f9f216e33736ea4ec65ca9ac03036e6 ]

The stack object “map” has a total size of 32 bytes. Its last 4
bytes are padding generated by compiler. These padding bytes are
not initialized and sent out via “nla_put”.

Signed-off-by: Kangjie Lu <kjlu@gatech.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/core/rtnetlink.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 31a46a7..e9c4b51 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1072,14 +1072,16 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 		goto nla_put_failure;
 
 	if (1) {
-		struct rtnl_link_ifmap map = {
-			.mem_start   = dev->mem_start,
-			.mem_end     = dev->mem_end,
-			.base_addr   = dev->base_addr,
-			.irq         = dev->irq,
-			.dma         = dev->dma,
-			.port        = dev->if_port,
-		};
+		struct rtnl_link_ifmap map;
+
+		memset(&map, 0, sizeof(map));
+		map.mem_start   = dev->mem_start;
+		map.mem_end     = dev->mem_end;
+		map.base_addr   = dev->base_addr;
+		map.irq         = dev->irq;
+		map.dma         = dev->dma;
+		map.port        = dev->if_port;
+
 		if (nla_put(skb, IFLA_MAP, sizeof(map), &map))
 			goto nla_put_failure;
 	}
-- 
2.5.0

[added to the 4.1 stable tree] net/mlx4_en: Fix endianness bug in IPV6 csum calculation

[Sasha Levin]

From: Daniel Jurgens <danielj@mellanox.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 82d69203df634b4dfa765c94f60ce9482bcc44d6 ]

Use htons instead of unconditionally byte swapping nexthdr.  On a little
endian systems shifting the byte is correct behavior, but it results in
incorrect csums on big endian architectures.

Fixes: f8c6455bb04b ('net/mlx4_en: Extend checksum offloading by CHECKSUM COMPLETE')
Signed-off-by: Daniel Jurgens <danielj@mellanox.com>
Reviewed-by: Carol Soto <clsoto@us.ibm.com>
Tested-by: Carol Soto <clsoto@us.ibm.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/net/ethernet/mellanox/mlx4/en_rx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 80aac20..f6095d2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -710,7 +710,7 @@ static int get_fixed_ipv6_csum(__wsum hw_checksum, struct sk_buff *skb,
 
 	if (ipv6h->nexthdr == IPPROTO_FRAGMENT || ipv6h->nexthdr == IPPROTO_HOPOPTS)
 		return -1;
-	hw_checksum = csum_add(hw_checksum, (__force __wsum)(ipv6h->nexthdr << 8));
+	hw_checksum = csum_add(hw_checksum, (__force __wsum)htons(ipv6h->nexthdr));
 
 	csum_pseudo_hdr = csum_partial(&ipv6h->saddr,
 				       sizeof(ipv6h->saddr) + sizeof(ipv6h->daddr), 0);
-- 
2.5.0

[added to the 4.1 stable tree] VSOCK: do not disconnect socket when peer has shutdown SEND only

[Sasha Levin]

From: Ian Campbell <ian.campbell@docker.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit dedc58e067d8c379a15a8a183c5db318201295bb ]

The peer may be expecting a reply having sent a request and then done a
shutdown(SHUT_WR), so tearing down the whole socket at this point seems
wrong and breaks for me with a client which does a SHUT_WR.

Looking at other socket family's stream_recvmsg callbacks doing a shutdown
here does not seem to be the norm and removing it does not seem to have
had any adverse effects that I can see.

I'm using Stefan's RFC virtio transport patches, I'm unsure of the impact
on the vmci transport.

Signed-off-by: Ian Campbell <ian.campbell@docker.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Stefan Hajnoczi <stefanha@redhat.com>
Cc: Claudio Imbrenda <imbrenda@linux.vnet.ibm.com>
Cc: Andy King <acking@vmware.com>
Cc: Dmitry Torokhov <dtor@vmware.com>
Cc: Jorgen Hansen <jhansen@vmware.com>
Cc: Adit Ranadive <aditr@vmware.com>
Cc: netdev@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/vmw_vsock/af_vsock.c | 21 +--------------------
 1 file changed, 1 insertion(+), 20 deletions(-)

diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 2ec86e6..e1c69b2 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1794,27 +1794,8 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	else if (sk->sk_shutdown & RCV_SHUTDOWN)
 		err = 0;
 
-	if (copied > 0) {
-		/* We only do these additional bookkeeping/notification steps
-		 * if we actually copied something out of the queue pair
-		 * instead of just peeking ahead.
-		 */
-
-		if (!(flags & MSG_PEEK)) {
-			/* If the other side has shutdown for sending and there
-			 * is nothing more to read, then modify the socket
-			 * state.
-			 */
-			if (vsk->peer_shutdown & SEND_SHUTDOWN) {
-				if (vsock_stream_has_data(vsk) <= 0) {
-					sk->sk_state = SS_UNCONNECTED;
-					sock_set_flag(sk, SOCK_DONE);
-					sk->sk_state_change(sk);
-				}
-			}
-		}
+	if (copied > 0)
 		err = copied;
-	}
 
 out_wait:
 	finish_wait(sk_sleep(sk), &wait);
-- 
2.5.0

[added to the 4.1 stable tree] net: bridge: fix old ioctl unlocked net device walk

[Sasha Levin]

From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 31ca0458a61a502adb7ed192bf9716c6d05791a5 ]

get_bridge_ifindices() is used from the old "deviceless" bridge ioctl
calls which aren't called with rtnl held. The comment above says that it is
called with rtnl but that is not really the case.
Here's a sample output from a test ASSERT_RTNL() which I put in
get_bridge_ifindices and executed "brctl show":
[  957.422726] RTNL: assertion failed at net/bridge//br_ioctl.c (30)
[  957.422925] CPU: 0 PID: 1862 Comm: brctl Tainted: G        W  O
4.6.0-rc4+ #157
[  957.423009] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996),
BIOS 1.8.1-20150318_183358- 04/01/2014
[  957.423009]  0000000000000000 ffff880058adfdf0 ffffffff8138dec5
0000000000000400
[  957.423009]  ffffffff81ce8380 ffff880058adfe58 ffffffffa05ead32
0000000000000001
[  957.423009]  00007ffec1a444b0 0000000000000400 ffff880053c19130
0000000000008940
[  957.423009] Call Trace:
[  957.423009]  [<ffffffff8138dec5>] dump_stack+0x85/0xc0
[  957.423009]  [<ffffffffa05ead32>]
br_ioctl_deviceless_stub+0x212/0x2e0 [bridge]
[  957.423009]  [<ffffffff81515beb>] sock_ioctl+0x22b/0x290
[  957.423009]  [<ffffffff8126ba75>] do_vfs_ioctl+0x95/0x700
[  957.423009]  [<ffffffff8126c159>] SyS_ioctl+0x79/0x90
[  957.423009]  [<ffffffff8163a4c0>] entry_SYSCALL_64_fastpath+0x23/0xc1

Since it only reads bridge ifindices, we can use rcu to safely walk the net
device list. Also remove the wrong rtnl comment above.

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/bridge/br_ioctl.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c
index 8d423bc..f876f70 100644
--- a/net/bridge/br_ioctl.c
+++ b/net/bridge/br_ioctl.c
@@ -21,18 +21,19 @@
 #include <asm/uaccess.h>
 #include "br_private.h"
 
-/* called with RTNL */
 static int get_bridge_ifindices(struct net *net, int *indices, int num)
 {
 	struct net_device *dev;
 	int i = 0;
 
-	for_each_netdev(net, dev) {
+	rcu_read_lock();
+	for_each_netdev_rcu(net, dev) {
 		if (i >= num)
 			break;
 		if (dev->priv_flags & IFF_EBRIDGE)
 			indices[i++] = dev->ifindex;
 	}
+	rcu_read_unlock();
 
 	return i;
 }
-- 
2.5.0

[added to the 4.1 stable tree] net: fix a kernel infoleak in x25 module

[Sasha Levin]

From: Kangjie Lu <kangjielu@gmail.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 79e48650320e6fba48369fccf13fd045315b19b8 ]

Stack object "dte_facilities" is allocated in x25_rx_call_request(),
which is supposed to be initialized in x25_negotiate_facilities.
However, 5 fields (8 bytes in total) are not initialized. This
object is then copied to userland via copy_to_user, thus infoleak
occurs.

Signed-off-by: Kangjie Lu <kjlu@gatech.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/x25/x25_facilities.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/x25/x25_facilities.c b/net/x25/x25_facilities.c
index 7ecd04c..997ff7b 100644
--- a/net/x25/x25_facilities.c
+++ b/net/x25/x25_facilities.c
@@ -277,6 +277,7 @@ int x25_negotiate_facilities(struct sk_buff *skb, struct sock *sk,
 
 	memset(&theirs, 0, sizeof(theirs));
 	memcpy(new, ours, sizeof(*new));
+	memset(dte, 0, sizeof(*dte));
 
 	len = x25_parse_facilities(skb, &theirs, dte, &x25->vc_facil_mask);
 	if (len < 0)
-- 
2.5.0

[added to the 4.1 stable tree] tcp: refresh skb timestamp at retransmit time

[Sasha Levin]

From: Eric Dumazet <edumazet@google.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 10a81980fc47e64ffac26a073139813d3f697b64 ]

In the very unlikely case __tcp_retransmit_skb() can not use the cloning
done in tcp_transmit_skb(), we need to refresh skb_mstamp before doing
the copy and transmit, otherwise TCP TS val will be an exact copy of
original transmit.

Fixes: 7faee5c0d514 ("tcp: remove TCP_SKB_CB(skb)->when")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/ipv4/tcp_output.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 1ea4322..ae66c84 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2627,8 +2627,10 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 	 */
 	if (unlikely((NET_IP_ALIGN && ((unsigned long)skb->data & 3)) ||
 		     skb_headroom(skb) >= 0xFFFF)) {
-		struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER,
-						   GFP_ATOMIC);
+		struct sk_buff *nskb;
+
+		skb_mstamp_get(&skb->skb_mstamp);
+		nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC);
 		err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
 			     -ENOBUFS;
 	} else {
-- 
2.5.0

[added to the 4.1 stable tree] s390/mm: fix asce_bits handling with dynamic pagetable levels

[Sasha Levin]

From: Gerald Schaefer <gerald.schaefer@de.ibm.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 723cacbd9dc79582e562c123a0bacf8bfc69e72a ]

There is a race with multi-threaded applications between context switch and
pagetable upgrade. In switch_mm() a new user_asce is built from mm->pgd and
mm->context.asce_bits, w/o holding any locks. A concurrent mmap with a
pagetable upgrade on another thread in crst_table_upgrade() could already
have set new asce_bits, but not yet the new mm->pgd. This would result in a
corrupt user_asce in switch_mm(), and eventually in a kernel panic from a
translation exception.

Fix this by storing the complete asce instead of just the asce_bits, which
can then be read atomically from switch_mm(), so that it either sees the
old value or the new value, but no mixture. Both cases are OK. Having the
old value would result in a page fault on access to the higher level memory,
but the fault handler would see the new mm->pgd, if it was a valid access
after the mmap on the other thread has completed. So as worst-case scenario
we would have a page fault loop for the racing thread until the next time
slice.

Also remove dead code and simplify the upgrade/downgrade path, there are no
upgrades from 2 levels, and only downgrades from 3 levels for compat tasks.
There are also no concurrent upgrades, because the mmap_sem is held with
down_write() in do_mmap, so the flush and table checks during upgrade can
be removed.

Reported-by: Michael Munday <munday@ca.ibm.com>
Reviewed-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 arch/s390/include/asm/mmu.h         |  2 +-
 arch/s390/include/asm/mmu_context.h | 28 +++++++++---
 arch/s390/include/asm/pgalloc.h     |  4 +-
 arch/s390/include/asm/processor.h   |  2 +-
 arch/s390/include/asm/tlbflush.h    |  9 ++--
 arch/s390/mm/init.c                 |  3 +-
 arch/s390/mm/mmap.c                 |  6 +--
 arch/s390/mm/pgtable.c              | 85 ++++++++++++-------------------------
 8 files changed, 62 insertions(+), 77 deletions(-)

diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h
index d29ad95..081b2ad 100644
--- a/arch/s390/include/asm/mmu.h
+++ b/arch/s390/include/asm/mmu.h
@@ -11,7 +11,7 @@ typedef struct {
 	spinlock_t list_lock;
 	struct list_head pgtable_list;
 	struct list_head gmap_list;
-	unsigned long asce_bits;
+	unsigned long asce;
 	unsigned long asce_limit;
 	unsigned long vdso_base;
 	/* The mmu context allocates 4K page tables. */
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index e485817..22877c9 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -26,12 +26,28 @@ static inline int init_new_context(struct task_struct *tsk,
 	mm->context.has_pgste = 0;
 	mm->context.use_skey = 0;
 #endif
-	if (mm->context.asce_limit == 0) {
+	switch (mm->context.asce_limit) {
+	case 1UL << 42:
+		/*
+		 * forked 3-level task, fall through to set new asce with new
+		 * mm->pgd
+		 */
+	case 0:
 		/* context created by exec, set asce limit to 4TB */
-		mm->context.asce_bits = _ASCE_TABLE_LENGTH |
-			_ASCE_USER_BITS | _ASCE_TYPE_REGION3;
 		mm->context.asce_limit = STACK_TOP_MAX;
-	} else if (mm->context.asce_limit == (1UL << 31)) {
+		mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
+				   _ASCE_USER_BITS | _ASCE_TYPE_REGION3;
+		break;
+	case 1UL << 53:
+		/* forked 4-level task, set new asce with new mm->pgd */
+		mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
+				   _ASCE_USER_BITS | _ASCE_TYPE_REGION2;
+		break;
+	case 1UL << 31:
+		/* forked 2-level compat task, set new asce with new mm->pgd */
+		mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
+				   _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT;
+		/* pgd_alloc() did not increase mm->nr_pmds */
 		mm_inc_nr_pmds(mm);
 	}
 	crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm));
@@ -42,7 +58,7 @@ static inline int init_new_context(struct task_struct *tsk,
 
 static inline void set_user_asce(struct mm_struct *mm)
 {
-	S390_lowcore.user_asce = mm->context.asce_bits | __pa(mm->pgd);
+	S390_lowcore.user_asce = mm->context.asce;
 	if (current->thread.mm_segment.ar4)
 		__ctl_load(S390_lowcore.user_asce, 7, 7);
 	set_cpu_flag(CIF_ASCE);
@@ -71,7 +87,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 {
 	int cpu = smp_processor_id();
 
-	S390_lowcore.user_asce = next->context.asce_bits | __pa(next->pgd);
+	S390_lowcore.user_asce = next->context.asce;
 	if (prev == next)
 		return;
 	if (MACHINE_HAS_TLB_LC)
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index d7cc79f..5991cdcb5 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -56,8 +56,8 @@ static inline unsigned long pgd_entry_type(struct mm_struct *mm)
 	return _REGION2_ENTRY_EMPTY;
 }
 
-int crst_table_upgrade(struct mm_struct *, unsigned long limit);
-void crst_table_downgrade(struct mm_struct *, unsigned long limit);
+int crst_table_upgrade(struct mm_struct *);
+void crst_table_downgrade(struct mm_struct *);
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
 {
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index dedb621..7ce53f6 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -155,7 +155,7 @@ struct stack_frame {
 	regs->psw.mask	= PSW_USER_BITS | PSW_MASK_BA;			\
 	regs->psw.addr	= new_psw | PSW_ADDR_AMODE;			\
 	regs->gprs[15]	= new_stackp;					\
-	crst_table_downgrade(current->mm, 1UL << 31);			\
+	crst_table_downgrade(current->mm);				\
 	execve_tail();							\
 } while (0)
 
diff --git a/arch/s390/include/asm/tlbflush.h b/arch/s390/include/asm/tlbflush.h
index ca148f7..a2e6ef3 100644
--- a/arch/s390/include/asm/tlbflush.h
+++ b/arch/s390/include/asm/tlbflush.h
@@ -110,8 +110,7 @@ static inline void __tlb_flush_asce(struct mm_struct *mm, unsigned long asce)
 static inline void __tlb_flush_kernel(void)
 {
 	if (MACHINE_HAS_IDTE)
-		__tlb_flush_idte((unsigned long) init_mm.pgd |
-				 init_mm.context.asce_bits);
+		__tlb_flush_idte(init_mm.context.asce);
 	else
 		__tlb_flush_global();
 }
@@ -133,8 +132,7 @@ static inline void __tlb_flush_asce(struct mm_struct *mm, unsigned long asce)
 static inline void __tlb_flush_kernel(void)
 {
 	if (MACHINE_HAS_TLB_LC)
-		__tlb_flush_idte_local((unsigned long) init_mm.pgd |
-				       init_mm.context.asce_bits);
+		__tlb_flush_idte_local(init_mm.context.asce);
 	else
 		__tlb_flush_local();
 }
@@ -148,8 +146,7 @@ static inline void __tlb_flush_mm(struct mm_struct * mm)
 	 * only ran on the local cpu.
 	 */
 	if (MACHINE_HAS_IDTE && list_empty(&mm->context.gmap_list))
-		__tlb_flush_asce(mm, (unsigned long) mm->pgd |
-				 mm->context.asce_bits);
+		__tlb_flush_asce(mm, mm->context.asce);
 	else
 		__tlb_flush_full(mm);
 }
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 80875c4..7287449 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -112,7 +112,8 @@ void __init paging_init(void)
 		asce_bits = _ASCE_TYPE_REGION3 | _ASCE_TABLE_LENGTH;
 		pgd_type = _REGION3_ENTRY_EMPTY;
 	}
-	S390_lowcore.kernel_asce = (__pa(init_mm.pgd) & PAGE_MASK) | asce_bits;
+	init_mm.context.asce = (__pa(init_mm.pgd) & PAGE_MASK) | asce_bits;
+	S390_lowcore.kernel_asce = init_mm.context.asce;
 	clear_table((unsigned long *) init_mm.pgd, pgd_type,
 		    sizeof(unsigned long)*2048);
 	vmem_map_init();
diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c
index 6e552af..e2f8685 100644
--- a/arch/s390/mm/mmap.c
+++ b/arch/s390/mm/mmap.c
@@ -184,7 +184,7 @@ int s390_mmap_check(unsigned long addr, unsigned long len, unsigned long flags)
 	if (!(flags & MAP_FIXED))
 		addr = 0;
 	if ((addr + len) >= TASK_SIZE)
-		return crst_table_upgrade(current->mm, 1UL << 53);
+		return crst_table_upgrade(current->mm);
 	return 0;
 }
 
@@ -201,7 +201,7 @@ s390_get_unmapped_area(struct file *filp, unsigned long addr,
 		return area;
 	if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < (1UL << 53)) {
 		/* Upgrade the page table to 4 levels and retry. */
-		rc = crst_table_upgrade(mm, 1UL << 53);
+		rc = crst_table_upgrade(mm);
 		if (rc)
 			return (unsigned long) rc;
 		area = arch_get_unmapped_area(filp, addr, len, pgoff, flags);
@@ -223,7 +223,7 @@ s390_get_unmapped_area_topdown(struct file *filp, const unsigned long addr,
 		return area;
 	if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < (1UL << 53)) {
 		/* Upgrade the page table to 4 levels and retry. */
-		rc = crst_table_upgrade(mm, 1UL << 53);
+		rc = crst_table_upgrade(mm);
 		if (rc)
 			return (unsigned long) rc;
 		area = arch_get_unmapped_area_topdown(filp, addr, len,
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index b33f661..ebf82a9 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -56,81 +56,52 @@ static void __crst_table_upgrade(void *arg)
 	__tlb_flush_local();
 }
 
-int crst_table_upgrade(struct mm_struct *mm, unsigned long limit)
+int crst_table_upgrade(struct mm_struct *mm)
 {
 	unsigned long *table, *pgd;
-	unsigned long entry;
-	int flush;
 
-	BUG_ON(limit > (1UL << 53));
-	flush = 0;
-repeat:
+	/* upgrade should only happen from 3 to 4 levels */
+	BUG_ON(mm->context.asce_limit != (1UL << 42));
+
 	table = crst_table_alloc(mm);
 	if (!table)
 		return -ENOMEM;
+
 	spin_lock_bh(&mm->page_table_lock);
-	if (mm->context.asce_limit < limit) {
-		pgd = (unsigned long *) mm->pgd;
-		if (mm->context.asce_limit <= (1UL << 31)) {
-			entry = _REGION3_ENTRY_EMPTY;
-			mm->context.asce_limit = 1UL << 42;
-			mm->context.asce_bits = _ASCE_TABLE_LENGTH |
-						_ASCE_USER_BITS |
-						_ASCE_TYPE_REGION3;
-		} else {
-			entry = _REGION2_ENTRY_EMPTY;
-			mm->context.asce_limit = 1UL << 53;
-			mm->context.asce_bits = _ASCE_TABLE_LENGTH |
-						_ASCE_USER_BITS |
-						_ASCE_TYPE_REGION2;
-		}
-		crst_table_init(table, entry);
-		pgd_populate(mm, (pgd_t *) table, (pud_t *) pgd);
-		mm->pgd = (pgd_t *) table;
-		mm->task_size = mm->context.asce_limit;
-		table = NULL;
-		flush = 1;
-	}
+	pgd = (unsigned long *) mm->pgd;
+	crst_table_init(table, _REGION2_ENTRY_EMPTY);
+	pgd_populate(mm, (pgd_t *) table, (pud_t *) pgd);
+	mm->pgd = (pgd_t *) table;
+	mm->context.asce_limit = 1UL << 53;
+	mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
+			   _ASCE_USER_BITS | _ASCE_TYPE_REGION2;
+	mm->task_size = mm->context.asce_limit;
 	spin_unlock_bh(&mm->page_table_lock);
-	if (table)
-		crst_table_free(mm, table);
-	if (mm->context.asce_limit < limit)
-		goto repeat;
-	if (flush)
-		on_each_cpu(__crst_table_upgrade, mm, 0);
+
+	on_each_cpu(__crst_table_upgrade, mm, 0);
 	return 0;
 }
 
-void crst_table_downgrade(struct mm_struct *mm, unsigned long limit)
+void crst_table_downgrade(struct mm_struct *mm)
 {
 	pgd_t *pgd;
 
+	/* downgrade should only happen from 3 to 2 levels (compat only) */
+	BUG_ON(mm->context.asce_limit != (1UL << 42));
+
 	if (current->active_mm == mm) {
 		clear_user_asce();
 		__tlb_flush_mm(mm);
 	}
-	while (mm->context.asce_limit > limit) {
-		pgd = mm->pgd;
-		switch (pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) {
-		case _REGION_ENTRY_TYPE_R2:
-			mm->context.asce_limit = 1UL << 42;
-			mm->context.asce_bits = _ASCE_TABLE_LENGTH |
-						_ASCE_USER_BITS |
-						_ASCE_TYPE_REGION3;
-			break;
-		case _REGION_ENTRY_TYPE_R3:
-			mm->context.asce_limit = 1UL << 31;
-			mm->context.asce_bits = _ASCE_TABLE_LENGTH |
-						_ASCE_USER_BITS |
-						_ASCE_TYPE_SEGMENT;
-			break;
-		default:
-			BUG();
-		}
-		mm->pgd = (pgd_t *) (pgd_val(*pgd) & _REGION_ENTRY_ORIGIN);
-		mm->task_size = mm->context.asce_limit;
-		crst_table_free(mm, (unsigned long *) pgd);
-	}
+
+	pgd = mm->pgd;
+	mm->pgd = (pgd_t *) (pgd_val(*pgd) & _REGION_ENTRY_ORIGIN);
+	mm->context.asce_limit = 1UL << 31;
+	mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
+			   _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT;
+	mm->task_size = mm->context.asce_limit;
+	crst_table_free(mm, (unsigned long *) pgd);
+
 	if (current->active_mm == mm)
 		set_user_asce(mm);
 }
-- 
2.5.0

[added to the 4.1 stable tree] drm/radeon: fix PLL sharing on DCE6.1 (v2)

[Sasha Levin]

From: Lucas Stach <dev@lynxeye.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit e3c00d87845ab375f90fa6e10a5e72a3a5778cd3 ]

On DCE6.1 PPLL2 is exclusively available to UNIPHYA, so it should not
be taken into consideration when looking for an already enabled PLL
to be shared with other outputs.

This fixes the broken VGA port (TRAVIS DP->VGA bridge) on my Richland
based laptop, where the internal display is connected to UNIPHYA through
a TRAVIS DP->LVDS bridge.

Bug:
https://bugs.freedesktop.org/show_bug.cgi?id=78987

v2: agd: add check in radeon_get_shared_nondp_ppll as well, drop
    extra parameter.

Signed-off-by: Lucas Stach <dev@lynxeye.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/gpu/drm/radeon/atombios_crtc.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index dac78ad..79bab6f 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -1739,6 +1739,7 @@ static u32 radeon_get_pll_use_mask(struct drm_crtc *crtc)
 static int radeon_get_shared_dp_ppll(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
+	struct radeon_device *rdev = dev->dev_private;
 	struct drm_crtc *test_crtc;
 	struct radeon_crtc *test_radeon_crtc;
 
@@ -1748,6 +1749,10 @@ static int radeon_get_shared_dp_ppll(struct drm_crtc *crtc)
 		test_radeon_crtc = to_radeon_crtc(test_crtc);
 		if (test_radeon_crtc->encoder &&
 		    ENCODER_MODE_IS_DP(atombios_get_encoder_mode(test_radeon_crtc->encoder))) {
+			/* PPLL2 is exclusive to UNIPHYA on DCE61 */
+			if (ASIC_IS_DCE61(rdev) && !ASIC_IS_DCE8(rdev) &&
+			    test_radeon_crtc->pll_id == ATOM_PPLL2)
+				continue;
 			/* for DP use the same PLL for all */
 			if (test_radeon_crtc->pll_id != ATOM_PPLL_INVALID)
 				return test_radeon_crtc->pll_id;
@@ -1769,6 +1774,7 @@ static int radeon_get_shared_nondp_ppll(struct drm_crtc *crtc)
 {
 	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
+	struct radeon_device *rdev = dev->dev_private;
 	struct drm_crtc *test_crtc;
 	struct radeon_crtc *test_radeon_crtc;
 	u32 adjusted_clock, test_adjusted_clock;
@@ -1784,6 +1790,10 @@ static int radeon_get_shared_nondp_ppll(struct drm_crtc *crtc)
 		test_radeon_crtc = to_radeon_crtc(test_crtc);
 		if (test_radeon_crtc->encoder &&
 		    !ENCODER_MODE_IS_DP(atombios_get_encoder_mode(test_radeon_crtc->encoder))) {
+			/* PPLL2 is exclusive to UNIPHYA on DCE61 */
+			if (ASIC_IS_DCE61(rdev) && !ASIC_IS_DCE8(rdev) &&
+			    test_radeon_crtc->pll_id == ATOM_PPLL2)
+				continue;
 			/* check if we are already driving this connector with another crtc */
 			if (test_radeon_crtc->connector == radeon_crtc->connector) {
 				/* if we are, return that pll */
-- 
2.5.0

[added to the 4.1 stable tree] Btrfs: don't use src fd for printk

[Sasha Levin]

From: Josef Bacik <jbacik@fb.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit c79b4713304f812d3d6c95826fc3e5fc2c0b0c14 ]

The fd we pass in may not be on a btrfs file system, so don't try to do
BTRFS_I() on it.  Thanks,

Signed-off-by: Josef Bacik <jbacik@fb.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 fs/btrfs/ioctl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 4350224..2eca30a 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1639,7 +1639,7 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file,
 
 		src_inode = file_inode(src.file);
 		if (src_inode->i_sb != file_inode(file)->i_sb) {
-			btrfs_info(BTRFS_I(src_inode)->root->fs_info,
+			btrfs_info(BTRFS_I(file_inode(file))->root->fs_info,
 				   "Snapshot src from another FS");
 			ret = -EXDEV;
 		} else if (!inode_owner_or_capable(src_inode)) {
-- 
2.5.0

[added to the 4.1 stable tree] clk: qcom: msm8916: Fix crypto clock flags

[Sasha Levin]

From: Andy Gross <andy.gross@linaro.org>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 2a0974aa1a0b40a92387ea03dbfeacfbc9ba182c ]

This patch adds the CLK_SET_RATE_PARENT flag for the crypto core and
ahb blocks.  Without this flag, clk_set_rate can fail for certain
frequency requests.

Signed-off-by: Andy Gross <andy.gross@linaro.org>
Fixes: 3966fab8b6ab ("clk: qcom: Add MSM8916 Global Clock Controller support")
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/clk/qcom/gcc-msm8916.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/clk/qcom/gcc-msm8916.c b/drivers/clk/qcom/gcc-msm8916.c
index 5d75bff..0f72199 100644
--- a/drivers/clk/qcom/gcc-msm8916.c
+++ b/drivers/clk/qcom/gcc-msm8916.c
@@ -1961,6 +1961,7 @@ static struct clk_branch gcc_crypto_ahb_clk = {
 				"pcnoc_bfdcd_clk_src",
 			},
 			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
 			.ops = &clk_branch2_ops,
 		},
 	},
@@ -1996,6 +1997,7 @@ static struct clk_branch gcc_crypto_clk = {
 				"crypto_clk_src",
 			},
 			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
 			.ops = &clk_branch2_ops,
 		},
 	},
-- 
2.5.0

[added to the 4.1 stable tree] usb: gadget: f_fs: Fix EFAULT generation for async read operations

[Sasha Levin]

From: Lars-Peter Clausen <lars@metafoo.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 332a5b446b7916d272c2a659a3b20909ce34d2c1 ]

In the current implementation functionfs generates a EFAULT for async read
operations if the read buffer size is larger than the URB data size. Since
a application does not necessarily know how much data the host side is
going to send it typically supplies a buffer larger than the actual data,
which will then result in a EFAULT error.

This behaviour was introduced while refactoring the code to use iov_iter
interface in commit c993c39b8639 ("gadget/function/f_fs.c: use put iov_iter
into io_data"). The original code took the minimum over the URB size and
the user buffer size and then attempted to copy that many bytes using
copy_to_user(). If copy_to_user() could not copy all data a EFAULT error
was generated. Restore the original behaviour by only generating a EFAULT
error when the number of bytes copied is not the size of the URB and the
target buffer has not been fully filled.

Commit 342f39a6c8d3 ("usb: gadget: f_fs: fix check in read operation")
already fixed the same problem for the synchronous read path.

Fixes: c993c39b8639 ("gadget/function/f_fs.c: use put iov_iter into io_data")
Acked-by: Michal Nazarewicz <mina86@mina86.com>
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Felipe Balbi <felipe.balbi@linux.intel.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/usb/gadget/function/f_fs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index 82240db..db9433e 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -651,7 +651,7 @@ static void ffs_user_copy_worker(struct work_struct *work)
 	if (io_data->read && ret > 0) {
 		use_mm(io_data->mm);
 		ret = copy_to_iter(io_data->buf, ret, &io_data->data);
-		if (iov_iter_count(&io_data->data))
+		if (ret != io_data->req->actual && iov_iter_count(&io_data->data))
 			ret = -EFAULT;
 		unuse_mm(io_data->mm);
 	}
-- 
2.5.0

[added to the 4.1 stable tree] KVM: x86: mask CPUID(0xD,0x1).EAX against host value

[Sasha Levin]

From: Paolo Bonzini <pbonzini@redhat.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 316314cae15fb0e3869b76b468f59a0c83ac3d4e ]

This ensures that the guest doesn't see XSAVE extensions
(e.g. xgetbv1 or xsavec) that the host lacks.

Cc: stable@vger.kernel.org
Reviewed-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 arch/x86/kvm/cpuid.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 1d08ad3..090aa5c 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -501,6 +501,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 			do_cpuid_1_ent(&entry[i], function, idx);
 			if (idx == 1) {
 				entry[i].eax &= kvm_supported_word10_x86_features;
+				cpuid_mask(&entry[i].eax, 10);
 				entry[i].ebx = 0;
 				if (entry[i].eax & (F(XSAVES)|F(XSAVEC)))
 					entry[i].ebx =
-- 
2.5.0

[added to the 4.1 stable tree] tty: vt, return error when con_startup fails

[Sasha Levin]

From: Jiri Slaby <jslaby@suse.cz>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 6798df4c5fe0a7e6d2065cf79649a794e5ba7114 ]

When csw->con_startup() fails in do_register_con_driver, we return no
error (i.e. 0). This was changed back in 2006 by commit 3e795de763.
Before that we used to return -ENODEV.

So fix the return value to be -ENODEV in that case again.

Fixes: 3e795de763 ("VT binding: Add binding/unbinding support for the VT console")
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Reported-by: "Dan Carpenter" <dan.carpenter@oracle.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/tty/vt/vt.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 4a24eb2..ba86956 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -3587,9 +3587,10 @@ static int do_register_con_driver(const struct consw *csw, int first, int last)
 		goto err;
 
 	desc = csw->con_startup();
-
-	if (!desc)
+	if (!desc) {
+		retval = -ENODEV;
 		goto err;
+	}
 
 	retval = -EINVAL;
 
-- 
2.5.0

[added to the 4.1 stable tree] serial: samsung: Reorder the sequence of clock control when call s3c24xx_serial_set_termios()

[Sasha Levin]

From: Chanwoo Choi <cw00.choi@samsung.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit b8995f527aac143e83d3900ff39357651ea4e0f6 ]

This patch fixes the broken serial log when changing the clock source
of uart device. Before disabling the original clock source, this patch
enables the new clock source to protect the clock off state for a split second.

Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
Reviewed-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/tty/serial/samsung.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/tty/serial/samsung.c b/drivers/tty/serial/samsung.c
index 1e0d9b8..e42cb6b 100644
--- a/drivers/tty/serial/samsung.c
+++ b/drivers/tty/serial/samsung.c
@@ -1288,6 +1288,8 @@ static void s3c24xx_serial_set_termios(struct uart_port *port,
 	/* check to see if we need  to change clock source */
 
 	if (ourport->baudclk != clk) {
+		clk_prepare_enable(clk);
+
 		s3c24xx_serial_setsource(port, clk_sel);
 
 		if (!IS_ERR(ourport->baudclk)) {
@@ -1295,8 +1297,6 @@ static void s3c24xx_serial_set_termios(struct uart_port *port,
 			ourport->baudclk = ERR_PTR(-EINVAL);
 		}
 
-		clk_prepare_enable(clk);
-
 		ourport->baudclk = clk;
 		ourport->baudclk_rate = clk ? clk_get_rate(clk) : 0;
 	}
-- 
2.5.0

[added to the 4.1 stable tree] MIPS: Reserve nosave data for hibernation

[Sasha Levin]

From: Huacai Chen <chenhc@lemote.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit a95d069204e178f18476f5499abab0d0d9cbc32c ]

After commit 92923ca3aacef63c92d ("mm: meminit: only set page reserved
in the memblock region"), the MIPS hibernation is broken. Because pages
in nosave data section should be "reserved", but currently they aren't
set to "reserved" at initialization. This patch makes hibernation work
again.

Signed-off-by: Huacai Chen <chenhc@lemote.com>
Cc: Aurelien Jarno <aurelien@aurel32.net>
Cc: Steven J . Hill <sjhill@realitydiluted.com>
Cc: Fuxin Zhang <zhangfx@lemote.com>
Cc: Zhangjin Wu <wuzhangjin@gmail.com>
Cc: linux-mips@linux-mips.org
Cc: stable@vger.kernel.org
Patchwork: https://patchwork.linux-mips.org/patch/12888/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 arch/mips/kernel/setup.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index be73c49..49b5203 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -686,6 +686,9 @@ static void __init arch_mem_init(char **cmdline_p)
 	for_each_memblock(reserved, reg)
 		if (reg->size != 0)
 			reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
+
+	reserve_bootmem_region(__pa_symbol(&__nosave_begin),
+			__pa_symbol(&__nosave_end)); /* Reserve for hibernation */
 }
 
 static void __init resource_init(void)
-- 
2.5.0

Re: [added to the 4.1 stable tree] MIPS: Reserve nosave data for hibernation

[Huacai Chen]

Hi, Sasha,

This patch should only be added to 4.2+.

Huacai

On Tue, Jul 12, 2016 at 10:55 AM, Sasha Levin <sasha.levin@oracle.com> wrote:
> From: Huacai Chen <chenhc@lemote.com>
>
> This patch has been added to the 4.1 stable tree. If you have any
> objections, please let us know.
>
> ===============
>
> [ Upstream commit a95d069204e178f18476f5499abab0d0d9cbc32c ]
>
> After commit 92923ca3aacef63c92d ("mm: meminit: only set page reserved
> in the memblock region"), the MIPS hibernation is broken. Because pages
> in nosave data section should be "reserved", but currently they aren't
> set to "reserved" at initialization. This patch makes hibernation work
> again.
>
> Signed-off-by: Huacai Chen <chenhc@lemote.com>
> Cc: Aurelien Jarno <aurelien@aurel32.net>
> Cc: Steven J . Hill <sjhill@realitydiluted.com>
> Cc: Fuxin Zhang <zhangfx@lemote.com>
> Cc: Zhangjin Wu <wuzhangjin@gmail.com>
> Cc: linux-mips@linux-mips.org
> Cc: stable@vger.kernel.org
> Patchwork: https://patchwork.linux-mips.org/patch/12888/
> Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
> Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
> ---
>  arch/mips/kernel/setup.c | 3 +++
>  1 file changed, 3 insertions(+)
>
> diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
> index be73c49..49b5203 100644
> --- a/arch/mips/kernel/setup.c
> +++ b/arch/mips/kernel/setup.c
> @@ -686,6 +686,9 @@ static void __init arch_mem_init(char **cmdline_p)
>         for_each_memblock(reserved, reg)
>                 if (reg->size != 0)
>                         reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
> +
> +       reserve_bootmem_region(__pa_symbol(&__nosave_begin),
> +                       __pa_symbol(&__nosave_end)); /* Reserve for hibernation */
>  }
>
>  static void __init resource_init(void)
> --
> 2.5.0
>
>

[added to the 4.1 stable tree] pipe: limit the per-user amount of pages allocated in pipes

[Sasha Levin]

From: Willy Tarreau <w@1wt.eu>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 759c01142a5d0f364a462346168a56de28a80f52 ]

On no-so-small systems, it is possible for a single process to cause an
OOM condition by filling large pipes with data that are never read. A
typical process filling 4000 pipes with 1 MB of data will use 4 GB of
memory. On small systems it may be tricky to set the pipe max size to
prevent this from happening.

This patch makes it possible to enforce a per-user soft limit above
which new pipes will be limited to a single page, effectively limiting
them to 4 kB each, as well as a hard limit above which no new pipes may
be created for this user. This has the effect of protecting the system
against memory abuse without hurting other users, and still allowing
pipes to work correctly though with less data at once.

The limit are controlled by two new sysctls : pipe-user-pages-soft, and
pipe-user-pages-hard. Both may be disabled by setting them to zero. The
default soft limit allows the default number of FDs per process (1024)
to create pipes of the default size (64kB), thus reaching a limit of 64MB
before starting to create only smaller pipes. With 256 processes limited
to 1024 FDs each, this results in 1024*64kB + (256*1024 - 1024) * 4kB =
1084 MB of memory allocated for a user. The hard limit is disabled by
default to avoid breaking existing applications that make intensive use
of pipes (eg: for splicing).

Reported-by: socketpair@gmail.com
Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Mitigates: CVE-2013-4312 (Linux 2.0+)
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 Documentation/sysctl/fs.txt | 23 ++++++++++++++++++++++
 fs/pipe.c                   | 47 +++++++++++++++++++++++++++++++++++++++++++--
 include/linux/pipe_fs_i.h   |  4 ++++
 include/linux/sched.h       |  1 +
 kernel/sysctl.c             | 14 ++++++++++++++
 5 files changed, 87 insertions(+), 2 deletions(-)

diff --git a/Documentation/sysctl/fs.txt b/Documentation/sysctl/fs.txt
index 88152f2..302b5ed 100644
--- a/Documentation/sysctl/fs.txt
+++ b/Documentation/sysctl/fs.txt
@@ -32,6 +32,8 @@ Currently, these files are in /proc/sys/fs:
 - nr_open
 - overflowuid
 - overflowgid
+- pipe-user-pages-hard
+- pipe-user-pages-soft
 - protected_hardlinks
 - protected_symlinks
 - suid_dumpable
@@ -159,6 +161,27 @@ The default is 65534.
 
 ==============================================================
 
+pipe-user-pages-hard:
+
+Maximum total number of pages a non-privileged user may allocate for pipes.
+Once this limit is reached, no new pipes may be allocated until usage goes
+below the limit again. When set to 0, no limit is applied, which is the default
+setting.
+
+==============================================================
+
+pipe-user-pages-soft:
+
+Maximum total number of pages a non-privileged user may allocate for pipes
+before the pipe size gets limited to a single page. Once this limit is reached,
+new pipes will be limited to a single page in size for this user in order to
+limit total memory usage, and trying to increase them using fcntl() will be
+denied until usage goes below the limit again. The default value allows to
+allocate up to 1024 pipes at their default size. When set to 0, no limit is
+applied.
+
+==============================================================
+
 protected_hardlinks:
 
 A long-standing class of security issues is the hardlink-based
diff --git a/fs/pipe.c b/fs/pipe.c
index 8865f79..5916c19 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -38,6 +38,12 @@ unsigned int pipe_max_size = 1048576;
  */
 unsigned int pipe_min_size = PAGE_SIZE;
 
+/* Maximum allocatable pages per user. Hard limit is unset by default, soft
+ * matches default values.
+ */
+unsigned long pipe_user_pages_hard;
+unsigned long pipe_user_pages_soft = PIPE_DEF_BUFFERS * INR_OPEN_CUR;
+
 /*
  * We use a start+len construction, which provides full use of the 
  * allocated memory.
@@ -584,20 +590,49 @@ pipe_fasync(int fd, struct file *filp, int on)
 	return retval;
 }
 
+static void account_pipe_buffers(struct pipe_inode_info *pipe,
+                                 unsigned long old, unsigned long new)
+{
+	atomic_long_add(new - old, &pipe->user->pipe_bufs);
+}
+
+static bool too_many_pipe_buffers_soft(struct user_struct *user)
+{
+	return pipe_user_pages_soft &&
+	       atomic_long_read(&user->pipe_bufs) >= pipe_user_pages_soft;
+}
+
+static bool too_many_pipe_buffers_hard(struct user_struct *user)
+{
+	return pipe_user_pages_hard &&
+	       atomic_long_read(&user->pipe_bufs) >= pipe_user_pages_hard;
+}
+
 struct pipe_inode_info *alloc_pipe_info(void)
 {
 	struct pipe_inode_info *pipe;
 
 	pipe = kzalloc(sizeof(struct pipe_inode_info), GFP_KERNEL);
 	if (pipe) {
-		pipe->bufs = kzalloc(sizeof(struct pipe_buffer) * PIPE_DEF_BUFFERS, GFP_KERNEL);
+		unsigned long pipe_bufs = PIPE_DEF_BUFFERS;
+		struct user_struct *user = get_current_user();
+
+		if (!too_many_pipe_buffers_hard(user)) {
+			if (too_many_pipe_buffers_soft(user))
+				pipe_bufs = 1;
+			pipe->bufs = kzalloc(sizeof(struct pipe_buffer) * pipe_bufs, GFP_KERNEL);
+		}
+
 		if (pipe->bufs) {
 			init_waitqueue_head(&pipe->wait);
 			pipe->r_counter = pipe->w_counter = 1;
-			pipe->buffers = PIPE_DEF_BUFFERS;
+			pipe->buffers = pipe_bufs;
+			pipe->user = user;
+			account_pipe_buffers(pipe, 0, pipe_bufs);
 			mutex_init(&pipe->mutex);
 			return pipe;
 		}
+		free_uid(user);
 		kfree(pipe);
 	}
 
@@ -608,6 +643,8 @@ void free_pipe_info(struct pipe_inode_info *pipe)
 {
 	int i;
 
+	account_pipe_buffers(pipe, pipe->buffers, 0);
+	free_uid(pipe->user);
 	for (i = 0; i < pipe->buffers; i++) {
 		struct pipe_buffer *buf = pipe->bufs + i;
 		if (buf->ops)
@@ -996,6 +1033,7 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long nr_pages)
 			memcpy(bufs + head, pipe->bufs, tail * sizeof(struct pipe_buffer));
 	}
 
+	account_pipe_buffers(pipe, pipe->buffers, nr_pages);
 	pipe->curbuf = 0;
 	kfree(pipe->bufs);
 	pipe->bufs = bufs;
@@ -1067,6 +1105,11 @@ long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
 		if (!capable(CAP_SYS_RESOURCE) && size > pipe_max_size) {
 			ret = -EPERM;
 			goto out;
+		} else if ((too_many_pipe_buffers_hard(pipe->user) ||
+			    too_many_pipe_buffers_soft(pipe->user)) &&
+		           !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) {
+			ret = -EPERM;
+			goto out;
 		}
 		ret = pipe_set_size(pipe, nr_pages);
 		break;
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index eb8b8ac..24f5470 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -42,6 +42,7 @@ struct pipe_buffer {
  *	@fasync_readers: reader side fasync
  *	@fasync_writers: writer side fasync
  *	@bufs: the circular array of pipe buffers
+ *	@user: the user who created this pipe
  **/
 struct pipe_inode_info {
 	struct mutex mutex;
@@ -57,6 +58,7 @@ struct pipe_inode_info {
 	struct fasync_struct *fasync_readers;
 	struct fasync_struct *fasync_writers;
 	struct pipe_buffer *bufs;
+	struct user_struct *user;
 };
 
 /*
@@ -123,6 +125,8 @@ void pipe_unlock(struct pipe_inode_info *);
 void pipe_double_lock(struct pipe_inode_info *, struct pipe_inode_info *);
 
 extern unsigned int pipe_max_size, pipe_min_size;
+extern unsigned long pipe_user_pages_hard;
+extern unsigned long pipe_user_pages_soft;
 int pipe_proc_fn(struct ctl_table *, int, void __user *, size_t *, loff_t *);
 
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9128b4e..9e39dea 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -803,6 +803,7 @@ struct user_struct {
 #endif
 	unsigned long locked_shm; /* How many pages of mlocked shm ? */
 	unsigned long unix_inflight;	/* How many files in flight in unix sockets */
+	atomic_long_t pipe_bufs;  /* how many pages are allocated in pipe buffers */
 
 #ifdef CONFIG_KEYS
 	struct key *uid_keyring;	/* UID specific keyring */
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index c3eee4c..7d49004 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1695,6 +1695,20 @@ static struct ctl_table fs_table[] = {
 		.proc_handler	= &pipe_proc_fn,
 		.extra1		= &pipe_min_size,
 	},
+	{
+		.procname	= "pipe-user-pages-hard",
+		.data		= &pipe_user_pages_hard,
+		.maxlen		= sizeof(pipe_user_pages_hard),
+		.mode		= 0644,
+		.proc_handler	= proc_doulongvec_minmax,
+	},
+	{
+		.procname	= "pipe-user-pages-soft",
+		.data		= &pipe_user_pages_soft,
+		.maxlen		= sizeof(pipe_user_pages_soft),
+		.mode		= 0644,
+		.proc_handler	= proc_doulongvec_minmax,
+	},
 	{ }
 };
 
-- 
2.5.0

[added to the 4.1 stable tree] xfs: print name of verifier if it fails

[Sasha Levin]

From: Eric Sandeen <sandeen@redhat.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 233135b763db7c64d07b728a9c66745fb0376275 ]

This adds a name to each buf_ops structure, so that if
a verifier fails we can print the type of verifier that
failed it.  Should be a slight debugging aid, I hope.

Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 fs/xfs/libxfs/xfs_alloc.c          | 2 ++
 fs/xfs/libxfs/xfs_alloc_btree.c    | 1 +
 fs/xfs/libxfs/xfs_attr_leaf.c      | 1 +
 fs/xfs/libxfs/xfs_attr_remote.c    | 1 +
 fs/xfs/libxfs/xfs_bmap_btree.c     | 1 +
 fs/xfs/libxfs/xfs_da_btree.c       | 1 +
 fs/xfs/libxfs/xfs_dir2_block.c     | 1 +
 fs/xfs/libxfs/xfs_dir2_data.c      | 2 ++
 fs/xfs/libxfs/xfs_dir2_leaf.c      | 2 ++
 fs/xfs/libxfs/xfs_dir2_node.c      | 1 +
 fs/xfs/libxfs/xfs_dquot_buf.c      | 1 +
 fs/xfs/libxfs/xfs_ialloc.c         | 1 +
 fs/xfs/libxfs/xfs_ialloc_btree.c   | 1 +
 fs/xfs/libxfs/xfs_inode_buf.c      | 2 ++
 fs/xfs/libxfs/xfs_sb.c             | 2 ++
 fs/xfs/libxfs/xfs_symlink_remote.c | 1 +
 fs/xfs/xfs_buf.h                   | 1 +
 fs/xfs/xfs_error.c                 | 4 ++--
 18 files changed, 24 insertions(+), 2 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 516162b..e1b1c82 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -519,6 +519,7 @@ xfs_agfl_write_verify(
 }
 
 const struct xfs_buf_ops xfs_agfl_buf_ops = {
+	.name = "xfs_agfl",
 	.verify_read = xfs_agfl_read_verify,
 	.verify_write = xfs_agfl_write_verify,
 };
@@ -2276,6 +2277,7 @@ xfs_agf_write_verify(
 }
 
 const struct xfs_buf_ops xfs_agf_buf_ops = {
+	.name = "xfs_agf",
 	.verify_read = xfs_agf_read_verify,
 	.verify_write = xfs_agf_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c
index 59d521c..13629ad 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.c
+++ b/fs/xfs/libxfs/xfs_alloc_btree.c
@@ -379,6 +379,7 @@ xfs_allocbt_write_verify(
 }
 
 const struct xfs_buf_ops xfs_allocbt_buf_ops = {
+	.name = "xfs_allocbt",
 	.verify_read = xfs_allocbt_read_verify,
 	.verify_write = xfs_allocbt_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index e9d401c..0532561 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -325,6 +325,7 @@ xfs_attr3_leaf_read_verify(
 }
 
 const struct xfs_buf_ops xfs_attr3_leaf_buf_ops = {
+	.name = "xfs_attr3_leaf",
 	.verify_read = xfs_attr3_leaf_read_verify,
 	.verify_write = xfs_attr3_leaf_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index dd71403..c3db53d 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -201,6 +201,7 @@ xfs_attr3_rmt_write_verify(
 }
 
 const struct xfs_buf_ops xfs_attr3_rmt_buf_ops = {
+	.name = "xfs_attr3_rmt",
 	.verify_read = xfs_attr3_rmt_read_verify,
 	.verify_write = xfs_attr3_rmt_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index 2c44c8e..225f2a8 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -719,6 +719,7 @@ xfs_bmbt_write_verify(
 }
 
 const struct xfs_buf_ops xfs_bmbt_buf_ops = {
+	.name = "xfs_bmbt",
 	.verify_read = xfs_bmbt_read_verify,
 	.verify_write = xfs_bmbt_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index 2385f8c..5d18270 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -241,6 +241,7 @@ xfs_da3_node_read_verify(
 }
 
 const struct xfs_buf_ops xfs_da3_node_buf_ops = {
+	.name = "xfs_da3_node",
 	.verify_read = xfs_da3_node_read_verify,
 	.verify_write = xfs_da3_node_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_dir2_block.c b/fs/xfs/libxfs/xfs_dir2_block.c
index 9354e19..a02ee01 100644
--- a/fs/xfs/libxfs/xfs_dir2_block.c
+++ b/fs/xfs/libxfs/xfs_dir2_block.c
@@ -120,6 +120,7 @@ xfs_dir3_block_write_verify(
 }
 
 const struct xfs_buf_ops xfs_dir3_block_buf_ops = {
+	.name = "xfs_dir3_block",
 	.verify_read = xfs_dir3_block_read_verify,
 	.verify_write = xfs_dir3_block_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_dir2_data.c b/fs/xfs/libxfs/xfs_dir2_data.c
index 534bbf2..e020a2c 100644
--- a/fs/xfs/libxfs/xfs_dir2_data.c
+++ b/fs/xfs/libxfs/xfs_dir2_data.c
@@ -302,11 +302,13 @@ xfs_dir3_data_write_verify(
 }
 
 const struct xfs_buf_ops xfs_dir3_data_buf_ops = {
+	.name = "xfs_dir3_data",
 	.verify_read = xfs_dir3_data_read_verify,
 	.verify_write = xfs_dir3_data_write_verify,
 };
 
 static const struct xfs_buf_ops xfs_dir3_data_reada_buf_ops = {
+	.name = "xfs_dir3_data_reada",
 	.verify_read = xfs_dir3_data_reada_verify,
 	.verify_write = xfs_dir3_data_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_dir2_leaf.c b/fs/xfs/libxfs/xfs_dir2_leaf.c
index 1061199..eb66ae0 100644
--- a/fs/xfs/libxfs/xfs_dir2_leaf.c
+++ b/fs/xfs/libxfs/xfs_dir2_leaf.c
@@ -242,11 +242,13 @@ xfs_dir3_leafn_write_verify(
 }
 
 const struct xfs_buf_ops xfs_dir3_leaf1_buf_ops = {
+	.name = "xfs_dir3_leaf1",
 	.verify_read = xfs_dir3_leaf1_read_verify,
 	.verify_write = xfs_dir3_leaf1_write_verify,
 };
 
 const struct xfs_buf_ops xfs_dir3_leafn_buf_ops = {
+	.name = "xfs_dir3_leafn",
 	.verify_read = xfs_dir3_leafn_read_verify,
 	.verify_write = xfs_dir3_leafn_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c
index 06bb421..f6e591e 100644
--- a/fs/xfs/libxfs/xfs_dir2_node.c
+++ b/fs/xfs/libxfs/xfs_dir2_node.c
@@ -147,6 +147,7 @@ xfs_dir3_free_write_verify(
 }
 
 const struct xfs_buf_ops xfs_dir3_free_buf_ops = {
+	.name = "xfs_dir3_free",
 	.verify_read = xfs_dir3_free_read_verify,
 	.verify_write = xfs_dir3_free_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_dquot_buf.c b/fs/xfs/libxfs/xfs_dquot_buf.c
index 48aff07..f48c304 100644
--- a/fs/xfs/libxfs/xfs_dquot_buf.c
+++ b/fs/xfs/libxfs/xfs_dquot_buf.c
@@ -301,6 +301,7 @@ xfs_dquot_buf_write_verify(
 }
 
 const struct xfs_buf_ops xfs_dquot_buf_ops = {
+	.name = "xfs_dquot",
 	.verify_read = xfs_dquot_buf_read_verify,
 	.verify_write = xfs_dquot_buf_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 1c9e755..fe20c26 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -2117,6 +2117,7 @@ xfs_agi_write_verify(
 }
 
 const struct xfs_buf_ops xfs_agi_buf_ops = {
+	.name = "xfs_agi",
 	.verify_read = xfs_agi_read_verify,
 	.verify_write = xfs_agi_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index 964c465..216a6f0 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -295,6 +295,7 @@ xfs_inobt_write_verify(
 }
 
 const struct xfs_buf_ops xfs_inobt_buf_ops = {
+	.name = "xfs_inobt",
 	.verify_read = xfs_inobt_read_verify,
 	.verify_write = xfs_inobt_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 7da6d0b..a217176 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -138,11 +138,13 @@ xfs_inode_buf_write_verify(
 }
 
 const struct xfs_buf_ops xfs_inode_buf_ops = {
+	.name = "xfs_inode",
 	.verify_read = xfs_inode_buf_read_verify,
 	.verify_write = xfs_inode_buf_write_verify,
 };
 
 const struct xfs_buf_ops xfs_inode_buf_ra_ops = {
+	.name = "xxfs_inode_ra",
 	.verify_read = xfs_inode_buf_readahead_verify,
 	.verify_write = xfs_inode_buf_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index dc4bfc5..535bd84 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -637,11 +637,13 @@ xfs_sb_write_verify(
 }
 
 const struct xfs_buf_ops xfs_sb_buf_ops = {
+	.name = "xfs_sb",
 	.verify_read = xfs_sb_read_verify,
 	.verify_write = xfs_sb_write_verify,
 };
 
 const struct xfs_buf_ops xfs_sb_quiet_buf_ops = {
+	.name = "xfs_sb_quiet",
 	.verify_read = xfs_sb_quiet_read_verify,
 	.verify_write = xfs_sb_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_symlink_remote.c b/fs/xfs/libxfs/xfs_symlink_remote.c
index e7e26bd..4caff91 100644
--- a/fs/xfs/libxfs/xfs_symlink_remote.c
+++ b/fs/xfs/libxfs/xfs_symlink_remote.c
@@ -164,6 +164,7 @@ xfs_symlink_write_verify(
 }
 
 const struct xfs_buf_ops xfs_symlink_buf_ops = {
+	.name = "xfs_symlink",
 	.verify_read = xfs_symlink_read_verify,
 	.verify_write = xfs_symlink_write_verify,
 };
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 75ff5d5..110cb85 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -131,6 +131,7 @@ struct xfs_buf_map {
 	struct xfs_buf_map (map) = { .bm_bn = (blkno), .bm_len = (numblk) };
 
 struct xfs_buf_ops {
+	char *name;
 	void (*verify_read)(struct xfs_buf *);
 	void (*verify_write)(struct xfs_buf *);
 };
diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c
index 338e50b..63db1cc 100644
--- a/fs/xfs/xfs_error.c
+++ b/fs/xfs/xfs_error.c
@@ -164,9 +164,9 @@ xfs_verifier_error(
 {
 	struct xfs_mount *mp = bp->b_target->bt_mount;
 
-	xfs_alert(mp, "Metadata %s detected at %pF, block 0x%llx",
+	xfs_alert(mp, "Metadata %s detected at %pF, %s block 0x%llx",
 		  bp->b_error == -EFSBADCRC ? "CRC error" : "corruption",
-		  __return_address, bp->b_bn);
+		  __return_address, bp->b_ops->name, bp->b_bn);
 
 	xfs_alert(mp, "Unmount and run xfs_repair");
 
-- 
2.5.0

[added to the 4.1 stable tree] tipc: check nl sock before parsing nested attributes

[Sasha Levin]

From: Richard Alpe <richard.alpe@ericsson.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 45e093ae2830cd1264677d47ff9a95a71f5d9f9c ]

Make sure the socket for which the user is listing publication exists
before parsing the socket netlink attributes.

Prior to this patch a call without any socket caused a NULL pointer
dereference in tipc_nl_publ_dump().

Tested-and-reported-by: Baozeng Ding <sploving1@gmail.com>
Signed-off-by: Richard Alpe <richard.alpe@ericsson.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.cm>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/tipc/socket.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 20cc6df..d41d424 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2804,6 +2804,9 @@ int tipc_nl_publ_dump(struct sk_buff *skb, struct netlink_callback *cb)
 		if (err)
 			return err;
 
+		if (!attrs[TIPC_NLA_SOCK])
+			return -EINVAL;
+
 		err = nla_parse_nested(sock, TIPC_NLA_SOCK_MAX,
 				       attrs[TIPC_NLA_SOCK],
 				       tipc_nl_sock_policy);
-- 
2.5.0

[added to the 4.1 stable tree] netlink: Fix dump skb leak/double free

[Sasha Levin]

From: Herbert Xu <herbert@gondor.apana.org.au>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 92964c79b357efd980812c4de5c1fd2ec8bb5520 ]

When we free cb->skb after a dump, we do it after releasing the
lock.  This means that a new dump could have started in the time
being and we'll end up freeing their skb instead of ours.

This patch saves the skb and module before we unlock so we free
the right memory.

Fixes: 16b304f3404f ("netlink: Eliminate kmalloc in netlink dump operation.")
Reported-by: Baozeng Ding <sploving1@gmail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/netlink/af_netlink.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 0c29986..dbc32b1 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2683,6 +2683,7 @@ static int netlink_dump(struct sock *sk)
 	struct netlink_callback *cb;
 	struct sk_buff *skb = NULL;
 	struct nlmsghdr *nlh;
+	struct module *module;
 	int len, err = -ENOBUFS;
 	int alloc_min_size;
 	int alloc_size;
@@ -2762,9 +2763,11 @@ static int netlink_dump(struct sock *sk)
 		cb->done(cb);
 
 	nlk->cb_running = false;
+	module = cb->module;
+	skb = cb->skb;
 	mutex_unlock(nlk->cb_mutex);
-	module_put(cb->module);
-	consume_skb(cb->skb);
+	module_put(module);
+	consume_skb(skb);
 	return 0;
 
 errout_skb:
-- 
2.5.0

[added to the 4.1 stable tree] tipc: fix nametable publication field in nl compat

[Sasha Levin]

From: Richard Alpe <richard.alpe@ericsson.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 03aaaa9b941e136757b55c4cf775aab6068dfd94 ]

The publication field of the old netlink API should contain the
publication key and not the publication reference.

Fixes: 44a8ae94fd55 (tipc: convert legacy nl name table dump to nl compat)
Signed-off-by: Richard Alpe <richard.alpe@ericsson.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/tipc/netlink_compat.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index ce9121e..e5ec86d 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -712,7 +712,7 @@ static int tipc_nl_compat_name_table_dump(struct tipc_nl_compat_msg *msg,
 		goto out;
 
 	tipc_tlv_sprintf(msg->rep, "%-10u %s",
-			 nla_get_u32(publ[TIPC_NLA_PUBL_REF]),
+			 nla_get_u32(publ[TIPC_NLA_PUBL_KEY]),
 			 scope_str[nla_get_u32(publ[TIPC_NLA_PUBL_SCOPE])]);
 out:
 	tipc_tlv_sprintf(msg->rep, "\n");
-- 
2.5.0

[added to the 4.1 stable tree] tuntap: correctly wake up process during uninit

[Sasha Levin]

From: Jason Wang <jasowang@redhat.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit addf8fc4acb1cf79492ac64966f07178793cb3d7 ]

We used to check dev->reg_state against NETREG_REGISTERED after each
time we are woke up. But after commit 9e641bdcfa4e ("net-tun:
restructure tun_do_read for better sleep/wakeup efficiency"), it uses
skb_recv_datagram() which does not check dev->reg_state. This will
result if we delete a tun/tap device after a process is blocked in the
reading. The device will wait for the reference count which was held
by that process for ever.

Fixes this by using RCV_SHUTDOWN which will be checked during
sk_recv_datagram() before trying to wake up the process during uninit.

Fixes: 9e641bdcfa4e ("net-tun: restructure tun_do_read for better
sleep/wakeup efficiency")
Cc: Eric Dumazet <edumazet@google.com>
Cc: Xi Wang <xii@google.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/net/tun.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index e470ae5..01f5ff8 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -516,11 +516,13 @@ static void tun_detach_all(struct net_device *dev)
 	for (i = 0; i < n; i++) {
 		tfile = rtnl_dereference(tun->tfiles[i]);
 		BUG_ON(!tfile);
+		tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN;
 		tfile->socket.sk->sk_data_ready(tfile->socket.sk);
 		RCU_INIT_POINTER(tfile->tun, NULL);
 		--tun->numqueues;
 	}
 	list_for_each_entry(tfile, &tun->disabled, next) {
+		tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN;
 		tfile->socket.sk->sk_data_ready(tfile->socket.sk);
 		RCU_INIT_POINTER(tfile->tun, NULL);
 	}
@@ -575,6 +577,7 @@ static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filte
 			goto out;
 	}
 	tfile->queue_index = tun->numqueues;
+	tfile->socket.sk->sk_shutdown &= ~RCV_SHUTDOWN;
 	rcu_assign_pointer(tfile->tun, tun);
 	rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile);
 	tun->numqueues++;
@@ -1357,9 +1360,6 @@ static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile,
 	if (!iov_iter_count(to))
 		return 0;
 
-	if (tun->dev->reg_state != NETREG_REGISTERED)
-		return -EIO;
-
 	/* Read frames from queue */
 	skb = __skb_recv_datagram(tfile->socket.sk, noblock ? MSG_DONTWAIT : 0,
 				  &peeked, &off, &err);
-- 
2.5.0

[added to the 4.1 stable tree] sfc: on MC reset, clear PIO buffer linkage in TXQs

[Sasha Levin]

From: Edward Cree <ecree@solarflare.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit c0795bf64cba4d1b796fdc5b74b33772841ed1bb ]

Otherwise, if we fail to allocate new PIO buffers, our TXQs will try to
use the old ones, which aren't there any more.

Fixes: 183233bec810 "sfc: Allocate and link PIO buffers; map them with write-combining"
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 drivers/net/ethernet/sfc/ef10.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index feca46e..c642e20 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -452,6 +452,17 @@ fail:
 	return rc;
 }
 
+static void efx_ef10_forget_old_piobufs(struct efx_nic *efx)
+{
+	struct efx_channel *channel;
+	struct efx_tx_queue *tx_queue;
+
+	/* All our existing PIO buffers went away */
+	efx_for_each_channel(channel, efx)
+		efx_for_each_channel_tx_queue(tx_queue, channel)
+			tx_queue->piobuf = NULL;
+}
+
 #else /* !EFX_USE_PIO */
 
 static int efx_ef10_alloc_piobufs(struct efx_nic *efx, unsigned int n)
@@ -468,6 +479,10 @@ static void efx_ef10_free_piobufs(struct efx_nic *efx)
 {
 }
 
+static void efx_ef10_forget_old_piobufs(struct efx_nic *efx)
+{
+}
+
 #endif /* EFX_USE_PIO */
 
 static void efx_ef10_remove(struct efx_nic *efx)
@@ -699,6 +714,7 @@ static void efx_ef10_reset_mc_allocations(struct efx_nic *efx)
 	nic_data->must_realloc_vis = true;
 	nic_data->must_restore_filters = true;
 	nic_data->must_restore_piobufs = true;
+	efx_ef10_forget_old_piobufs(efx);
 	nic_data->rx_rss_context = EFX_EF10_RSS_CONTEXT_INVALID;
 }
 
-- 
2.5.0

[added to the 4.1 stable tree] tcp: record TLP and ER timer stats in v6 stats

[Sasha Levin]

From: Yuchung Cheng <ycheng@google.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit ce3cf4ec0305919fc69a972f6c2b2efd35d36abc ]

The v6 tcp stats scan do not provide TLP and ER timer information
correctly like the v4 version . This patch fixes that.

Fixes: 6ba8a3b19e76 ("tcp: Tail loss probe (TLP)")
Fixes: eed530b6c676 ("tcp: early retransmit")
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/ipv6/tcp_ipv6.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index c1147ac..ac6c40d 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1691,7 +1691,9 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
 	destp = ntohs(inet->inet_dport);
 	srcp  = ntohs(inet->inet_sport);
 
-	if (icsk->icsk_pending == ICSK_TIME_RETRANS) {
+	if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
+	    icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
+	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
 		timer_active	= 1;
 		timer_expires	= icsk->icsk_timeout;
 	} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
-- 
2.5.0

[added to the 4.1 stable tree] sparc: Fix system call tracing register handling.

[Sasha Levin]

From: Mike Frysinger <vapier@gentoo.org>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 1a40b95374f680625318ab61d81958e949e0afe3 ]

A system call trace trigger on entry allows the tracing
process to inspect and potentially change the traced
process's registers.

Account for that by reloading the %g1 (syscall number)
and %i0-%i5 (syscall argument) values.  We need to be
careful to revalidate the range of %g1, and reload the
system call table entry it corresponds to into %l7.

Reported-by: Mike Frysinger <vapier@gentoo.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Tested-by: Mike Frysinger <vapier@gentoo.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 arch/sparc/kernel/entry.S    | 17 +++++++++++++++++
 arch/sparc/kernel/syscalls.S | 36 ++++++++++++++++++++++++++++++++++++
 2 files changed, 53 insertions(+)

diff --git a/arch/sparc/kernel/entry.S b/arch/sparc/kernel/entry.S
index 33c02b1..a83707c 100644
--- a/arch/sparc/kernel/entry.S
+++ b/arch/sparc/kernel/entry.S
@@ -948,7 +948,24 @@ linux_syscall_trace:
 	cmp	%o0, 0
 	bne	3f
 	 mov	-ENOSYS, %o0
+
+	/* Syscall tracing can modify the registers.  */
+	ld	[%sp + STACKFRAME_SZ + PT_G1], %g1
+	sethi	%hi(sys_call_table), %l7
+	ld	[%sp + STACKFRAME_SZ + PT_I0], %i0
+	or	%l7, %lo(sys_call_table), %l7
+	ld	[%sp + STACKFRAME_SZ + PT_I1], %i1
+	ld	[%sp + STACKFRAME_SZ + PT_I2], %i2
+	ld	[%sp + STACKFRAME_SZ + PT_I3], %i3
+	ld	[%sp + STACKFRAME_SZ + PT_I4], %i4
+	ld	[%sp + STACKFRAME_SZ + PT_I5], %i5
+	cmp	%g1, NR_syscalls
+	bgeu	3f
+	 mov	-ENOSYS, %o0
+
+	sll	%g1, 2, %l4
 	mov	%i0, %o0
+	ld	[%l7 + %l4], %l7
 	mov	%i1, %o1
 	mov	%i2, %o2
 	mov	%i3, %o3
diff --git a/arch/sparc/kernel/syscalls.S b/arch/sparc/kernel/syscalls.S
index bb00089..c4a1b5c 100644
--- a/arch/sparc/kernel/syscalls.S
+++ b/arch/sparc/kernel/syscalls.S
@@ -158,7 +158,25 @@ linux_syscall_trace32:
 	 add	%sp, PTREGS_OFF, %o0
 	brnz,pn	%o0, 3f
 	 mov	-ENOSYS, %o0
+
+	/* Syscall tracing can modify the registers.  */
+	ldx	[%sp + PTREGS_OFF + PT_V9_G1], %g1
+	sethi	%hi(sys_call_table32), %l7
+	ldx	[%sp + PTREGS_OFF + PT_V9_I0], %i0
+	or	%l7, %lo(sys_call_table32), %l7
+	ldx	[%sp + PTREGS_OFF + PT_V9_I1], %i1
+	ldx	[%sp + PTREGS_OFF + PT_V9_I2], %i2
+	ldx	[%sp + PTREGS_OFF + PT_V9_I3], %i3
+	ldx	[%sp + PTREGS_OFF + PT_V9_I4], %i4
+	ldx	[%sp + PTREGS_OFF + PT_V9_I5], %i5
+
+	cmp	%g1, NR_syscalls
+	bgeu,pn	%xcc, 3f
+	 mov	-ENOSYS, %o0
+
+	sll	%g1, 2, %l4
 	srl	%i0, 0, %o0
+	lduw	[%l7 + %l4], %l7
 	srl	%i4, 0, %o4
 	srl	%i1, 0, %o1
 	srl	%i2, 0, %o2
@@ -170,7 +188,25 @@ linux_syscall_trace:
 	 add	%sp, PTREGS_OFF, %o0
 	brnz,pn	%o0, 3f
 	 mov	-ENOSYS, %o0
+
+	/* Syscall tracing can modify the registers.  */
+	ldx	[%sp + PTREGS_OFF + PT_V9_G1], %g1
+	sethi	%hi(sys_call_table64), %l7
+	ldx	[%sp + PTREGS_OFF + PT_V9_I0], %i0
+	or	%l7, %lo(sys_call_table64), %l7
+	ldx	[%sp + PTREGS_OFF + PT_V9_I1], %i1
+	ldx	[%sp + PTREGS_OFF + PT_V9_I2], %i2
+	ldx	[%sp + PTREGS_OFF + PT_V9_I3], %i3
+	ldx	[%sp + PTREGS_OFF + PT_V9_I4], %i4
+	ldx	[%sp + PTREGS_OFF + PT_V9_I5], %i5
+
+	cmp	%g1, NR_syscalls
+	bgeu,pn	%xcc, 3f
+	 mov	-ENOSYS, %o0
+
+	sll	%g1, 2, %l4
 	mov	%i0, %o0
+	lduw	[%l7 + %l4], %l7
 	mov	%i1, %o1
 	mov	%i2, %o2
 	mov	%i3, %o3
-- 
2.5.0

[added to the 4.1 stable tree] sparc64: Fix bootup regressions on some Kconfig combinations.

[Sasha Levin]

From: "David S. Miller" <davem@davemloft.net>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 49fa5230462f9f2c4e97c81356473a6bdf06c422 ]

The system call tracing bug fix mentioned in the Fixes tag
below increased the amount of assembler code in the sequence
of assembler files included by head_64.S

This caused to total set of code to exceed 0x4000 bytes in
size, which overflows the expression in head_64.S that works
to place swapper_tsb at address 0x408000.

When this is violated, the TSB is not properly aligned, and
also the trap table is not aligned properly either.  All of
this together results in failed boots.

So, do two things:

1) Simplify some code by using ba,a instead of ba/nop to get
   those bytes back.

2) Add a linker script assertion to make sure that if this
   happens again the build will fail.

Fixes: 1a40b95374f6 ("sparc: Fix system call tracing register handling.")
Reported-by: Meelis Roos <mroos@linux.ee>
Reported-by: Joerg Abraham <joerg.abraham@nokia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 arch/sparc/kernel/cherrs.S      | 14 +++++---------
 arch/sparc/kernel/fpu_traps.S   | 11 +++++------
 arch/sparc/kernel/head_64.S     | 24 ++++++++----------------
 arch/sparc/kernel/misctrap.S    | 12 ++++--------
 arch/sparc/kernel/spiterrs.S    | 18 ++++++------------
 arch/sparc/kernel/utrap.S       |  3 +--
 arch/sparc/kernel/vmlinux.lds.S |  4 ++++
 arch/sparc/kernel/winfixup.S    |  3 +--
 8 files changed, 34 insertions(+), 55 deletions(-)

diff --git a/arch/sparc/kernel/cherrs.S b/arch/sparc/kernel/cherrs.S
index 4ee1ad4..655628de 100644
--- a/arch/sparc/kernel/cherrs.S
+++ b/arch/sparc/kernel/cherrs.S
@@ -214,8 +214,7 @@ do_dcpe_tl1_nonfatal:	/* Ok we may use interrupt globals safely. */
 	subcc		%g1, %g2, %g1		! Next cacheline
 	bge,pt		%icc, 1b
 	 nop
-	ba,pt		%xcc, dcpe_icpe_tl1_common
-	 nop
+	ba,a,pt		%xcc, dcpe_icpe_tl1_common
 
 do_dcpe_tl1_fatal:
 	sethi		%hi(1f), %g7
@@ -224,8 +223,7 @@ do_dcpe_tl1_fatal:
 	mov		0x2, %o0
 	call		cheetah_plus_parity_error
 	 add		%sp, PTREGS_OFF, %o1
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		do_dcpe_tl1,.-do_dcpe_tl1
 
 	.globl		do_icpe_tl1
@@ -259,8 +257,7 @@ do_icpe_tl1_nonfatal:	/* Ok we may use interrupt globals safely. */
 	subcc		%g1, %g2, %g1
 	bge,pt		%icc, 1b
 	 nop
-	ba,pt		%xcc, dcpe_icpe_tl1_common
-	 nop
+	ba,a,pt		%xcc, dcpe_icpe_tl1_common
 
 do_icpe_tl1_fatal:
 	sethi		%hi(1f), %g7
@@ -269,8 +266,7 @@ do_icpe_tl1_fatal:
 	mov		0x3, %o0
 	call		cheetah_plus_parity_error
 	 add		%sp, PTREGS_OFF, %o1
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		do_icpe_tl1,.-do_icpe_tl1
 	
 	.type		dcpe_icpe_tl1_common,#function
@@ -456,7 +452,7 @@ __cheetah_log_error:
 	 cmp		%g2, 0x63
 	be		c_cee
 	 nop
-	ba,pt		%xcc, c_deferred
+	ba,a,pt		%xcc, c_deferred
 	.size		__cheetah_log_error,.-__cheetah_log_error
 
 	/* Cheetah FECC trap handling, we get here from tl{0,1}_fecc
diff --git a/arch/sparc/kernel/fpu_traps.S b/arch/sparc/kernel/fpu_traps.S
index a686482..336d275 100644
--- a/arch/sparc/kernel/fpu_traps.S
+++ b/arch/sparc/kernel/fpu_traps.S
@@ -100,8 +100,8 @@ do_fpdis:
 	fmuld		%f0, %f2, %f26
 	faddd		%f0, %f2, %f28
 	fmuld		%f0, %f2, %f30
-	b,pt		%xcc, fpdis_exit
-	 nop
+	ba,a,pt		%xcc, fpdis_exit
+
 2:	andcc		%g5, FPRS_DU, %g0
 	bne,pt		%icc, 3f
 	 fzero		%f32
@@ -144,8 +144,8 @@ do_fpdis:
 	fmuld		%f32, %f34, %f58
 	faddd		%f32, %f34, %f60
 	fmuld		%f32, %f34, %f62
-	ba,pt		%xcc, fpdis_exit
-	 nop
+	ba,a,pt		%xcc, fpdis_exit
+
 3:	mov		SECONDARY_CONTEXT, %g3
 	add		%g6, TI_FPREGS, %g1
 
@@ -197,8 +197,7 @@ fpdis_exit2:
 fp_other_bounce:
 	call		do_fpother
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		fp_other_bounce,.-fp_other_bounce
 
 	.align		32
diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S
index 3d61fca..8ff5763 100644
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -461,9 +461,8 @@ sun4v_chip_type:
 	subcc	%g3, 1, %g3
 	bne,pt	%xcc, 41b
 	add	%g1, 1, %g1
-	mov	SUN4V_CHIP_SPARC64X, %g4
 	ba,pt	%xcc, 5f
-	nop
+	 mov	SUN4V_CHIP_SPARC64X, %g4
 
 49:
 	mov	SUN4V_CHIP_UNKNOWN, %g4
@@ -548,8 +547,7 @@ sun4u_init:
 	stxa		%g0, [%g7] ASI_DMMU
 	membar	#Sync
 
-	ba,pt		%xcc, sun4u_continue
-	 nop
+	ba,a,pt		%xcc, sun4u_continue
 
 sun4v_init:
 	/* Set ctx 0 */
@@ -560,14 +558,12 @@ sun4v_init:
 	mov		SECONDARY_CONTEXT, %g7
 	stxa		%g0, [%g7] ASI_MMU
 	membar		#Sync
-	ba,pt		%xcc, niagara_tlb_fixup
-	 nop
+	ba,a,pt		%xcc, niagara_tlb_fixup
 
 sun4u_continue:
 	BRANCH_IF_ANY_CHEETAH(g1, g7, cheetah_tlb_fixup)
 
-	ba,pt	%xcc, spitfire_tlb_fixup
-	 nop
+	ba,a,pt	%xcc, spitfire_tlb_fixup
 
 niagara_tlb_fixup:
 	mov	3, %g2		/* Set TLB type to hypervisor. */
@@ -639,8 +635,7 @@ niagara_patch:
 	call	hypervisor_patch_cachetlbops
 	 nop
 
-	ba,pt	%xcc, tlb_fixup_done
-	 nop
+	ba,a,pt	%xcc, tlb_fixup_done
 
 cheetah_tlb_fixup:
 	mov	2, %g2		/* Set TLB type to cheetah+. */
@@ -659,8 +654,7 @@ cheetah_tlb_fixup:
 	call	cheetah_patch_cachetlbops
 	 nop
 
-	ba,pt	%xcc, tlb_fixup_done
-	 nop
+	ba,a,pt	%xcc, tlb_fixup_done
 
 spitfire_tlb_fixup:
 	/* Set TLB type to spitfire. */
@@ -782,8 +776,7 @@ setup_trap_table:
 	call	%o1
 	 add	%sp, (2047 + 128), %o0
 
-	ba,pt	%xcc, 2f
-	 nop
+	ba,a,pt	%xcc, 2f
 
 1:	sethi	%hi(sparc64_ttable_tl0), %o0
 	set	prom_set_trap_table_name, %g2
@@ -822,8 +815,7 @@ setup_trap_table:
 
 	BRANCH_IF_ANY_CHEETAH(o2, o3, 1f)
 
-	ba,pt	%xcc, 2f
-	 nop
+	ba,a,pt	%xcc, 2f
 
 	/* Disable STICK_INT interrupts. */
 1:
diff --git a/arch/sparc/kernel/misctrap.S b/arch/sparc/kernel/misctrap.S
index 753b4f0..34b4933 100644
--- a/arch/sparc/kernel/misctrap.S
+++ b/arch/sparc/kernel/misctrap.S
@@ -18,8 +18,7 @@ __do_privact:
 109:	or		%g7, %lo(109b), %g7
 	call		do_privact
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		__do_privact,.-__do_privact
 
 	.type		do_mna,#function
@@ -46,8 +45,7 @@ do_mna:
 	mov		%l5, %o2
 	call		mem_address_unaligned
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		do_mna,.-do_mna
 
 	.type		do_lddfmna,#function
@@ -65,8 +63,7 @@ do_lddfmna:
 	mov		%l5, %o2
 	call		handle_lddfmna
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		do_lddfmna,.-do_lddfmna
 
 	.type		do_stdfmna,#function
@@ -84,8 +81,7 @@ do_stdfmna:
 	mov		%l5, %o2
 	call		handle_stdfmna
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		do_stdfmna,.-do_stdfmna
 
 	.type		breakpoint_trap,#function
diff --git a/arch/sparc/kernel/spiterrs.S b/arch/sparc/kernel/spiterrs.S
index c357e40..4a73009 100644
--- a/arch/sparc/kernel/spiterrs.S
+++ b/arch/sparc/kernel/spiterrs.S
@@ -85,8 +85,7 @@ __spitfire_cee_trap_continue:
 	ba,pt		%xcc, etraptl1
 	 rd		%pc, %g7
 
-	ba,pt		%xcc, 2f
-	 nop
+	ba,a,pt		%xcc, 2f
 
 1:	ba,pt		%xcc, etrap_irq
 	 rd		%pc, %g7
@@ -100,8 +99,7 @@ __spitfire_cee_trap_continue:
 	mov		%l5, %o2
 	call		spitfire_access_error
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		__spitfire_access_error,.-__spitfire_access_error
 
 	/* This is the trap handler entry point for ECC correctable
@@ -179,8 +177,7 @@ __spitfire_data_access_exception_tl1:
 	mov		%l5, %o2
 	call		spitfire_data_access_exception_tl1
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		__spitfire_data_access_exception_tl1,.-__spitfire_data_access_exception_tl1
 
 	.type		__spitfire_data_access_exception,#function
@@ -200,8 +197,7 @@ __spitfire_data_access_exception:
 	mov		%l5, %o2
 	call		spitfire_data_access_exception
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		__spitfire_data_access_exception,.-__spitfire_data_access_exception
 
 	.type		__spitfire_insn_access_exception_tl1,#function
@@ -220,8 +216,7 @@ __spitfire_insn_access_exception_tl1:
 	mov		%l5, %o2
 	call		spitfire_insn_access_exception_tl1
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		__spitfire_insn_access_exception_tl1,.-__spitfire_insn_access_exception_tl1
 
 	.type		__spitfire_insn_access_exception,#function
@@ -240,6 +235,5 @@ __spitfire_insn_access_exception:
 	mov		%l5, %o2
 	call		spitfire_insn_access_exception
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		__spitfire_insn_access_exception,.-__spitfire_insn_access_exception
diff --git a/arch/sparc/kernel/utrap.S b/arch/sparc/kernel/utrap.S
index b7f0f3f..c731e80 100644
--- a/arch/sparc/kernel/utrap.S
+++ b/arch/sparc/kernel/utrap.S
@@ -11,8 +11,7 @@ utrap_trap:		/* %g3=handler,%g4=level */
 	mov		%l4, %o1
         call		bad_trap
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 
 invoke_utrap:
 	sllx		%g3, 3, %g3
diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S
index f1a2f68..4a41d41 100644
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -33,6 +33,10 @@ ENTRY(_start)
 jiffies = jiffies_64;
 #endif
 
+#ifdef CONFIG_SPARC64
+ASSERT((swapper_tsb == 0x0000000000408000), "Error: sparc64 early assembler too large")
+#endif
+
 SECTIONS
 {
 #ifdef CONFIG_SPARC64
diff --git a/arch/sparc/kernel/winfixup.S b/arch/sparc/kernel/winfixup.S
index 1e67ce9..855019a 100644
--- a/arch/sparc/kernel/winfixup.S
+++ b/arch/sparc/kernel/winfixup.S
@@ -32,8 +32,7 @@ fill_fixup:
 	 rd	%pc, %g7
 	call	do_sparc64_fault
 	 add	%sp, PTREGS_OFF, %o0
-	ba,pt	%xcc, rtrap
-	 nop
+	ba,a,pt	%xcc, rtrap
 
 	/* Be very careful about usage of the trap globals here.
 	 * You cannot touch %g5 as that has the fault information.
-- 
2.5.0

[added to the 4.1 stable tree] sparc64: Fix numa node distance initialization

[Sasha Levin]

From: Nitin Gupta <nitin.m.gupta@oracle.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 36beca6571c941b28b0798667608239731f9bc3a ]

Orabug: 22495713

Currently, NUMA node distance matrix is initialized only
when a machine descriptor (MD) exists. However, sun4u
machines (e.g. Sun Blade 2500) do not have an MD and thus
distance values were left uninitialized. The initialization
is now moved such that it happens on both sun4u and sun4v.

Signed-off-by: Nitin Gupta <nitin.m.gupta@oracle.com>
Tested-by: Mikael Pettersson <mikpelinux@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 arch/sparc/mm/init_64.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 559cb74..b2f1e75 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -1301,10 +1301,18 @@ static int __init numa_parse_sun4u(void)
 
 static int __init bootmem_init_numa(void)
 {
+	int i, j;
 	int err = -1;
 
 	numadbg("bootmem_init_numa()\n");
 
+	/* Some sane defaults for numa latency values */
+	for (i = 0; i < MAX_NUMNODES; i++) {
+		for (j = 0; j < MAX_NUMNODES; j++)
+			numa_latency[i][j] = (i == j) ?
+				LOCAL_DISTANCE : REMOTE_DISTANCE;
+	}
+
 	if (numa_enabled) {
 		if (tlb_type == hypervisor)
 			err = numa_parse_mdesc();
-- 
2.5.0

Re: [added to the 4.1 stable tree] sparc64: Fix numa node distance initialization

[Nitin Gupta]

On 7/11/16 7:55 PM, Sasha Levin wrote:
> From: Nitin Gupta <nitin.m.gupta@oracle.com>
> 
> This patch has been added to the 4.1 stable tree. If you have any
> objections, please let us know.
>


This port of upstream patch (36beca6) looks incorrect. This patch
must be applied after upstream patch 52708d69. So, the correct
order of porting upstream patches is:

  sparc64: Fix numa distance values
  52708d690b8be132ba9d294464625dbbdb9fa5df

and then:

  sparc64: Fix numa node distance initialization
  36beca6571c941b28b0798667608239731f9bc3a


Thanks,
Nitin


> ===============
> 
> [ Upstream commit 36beca6571c941b28b0798667608239731f9bc3a ]
> 
> Orabug: 22495713
> 
> Currently, NUMA node distance matrix is initialized only
> when a machine descriptor (MD) exists. However, sun4u
> machines (e.g. Sun Blade 2500) do not have an MD and thus
> distance values were left uninitialized. The initialization
> is now moved such that it happens on both sun4u and sun4v.
> 
> Signed-off-by: Nitin Gupta <nitin.m.gupta@oracle.com>
> Tested-by: Mikael Pettersson <mikpelinux@gmail.com>
> Signed-off-by: David S. Miller <davem@davemloft.net>
> Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
> ---
>  arch/sparc/mm/init_64.c | 8 ++++++++
>  1 file changed, 8 insertions(+)
> 
> diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
> index 559cb74..b2f1e75 100644
> --- a/arch/sparc/mm/init_64.c
> +++ b/arch/sparc/mm/init_64.c
> @@ -1301,10 +1301,18 @@ static int __init numa_parse_sun4u(void)
>  
>  static int __init bootmem_init_numa(void)
>  {
> +	int i, j;
>  	int err = -1;
>  
>  	numadbg("bootmem_init_numa()\n");
>  
> +	/* Some sane defaults for numa latency values */
> +	for (i = 0; i < MAX_NUMNODES; i++) {
> +		for (j = 0; j < MAX_NUMNODES; j++)
> +			numa_latency[i][j] = (i == j) ?
> +				LOCAL_DISTANCE : REMOTE_DISTANCE;
> +	}
> +
>  	if (numa_enabled) {
>  		if (tlb_type == hypervisor)
>  			err = numa_parse_mdesc();
> 

[added to the 4.1 stable tree] sparc64: Fix sparc64_set_context stack handling.

[Sasha Levin]

From: "David S. Miller" <davem@davemloft.net>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 397d1533b6cce0ccb5379542e2e6d079f6936c46 ]

Like a signal return, we should use synchronize_user_stack() rather
than flush_user_windows().

Reported-by: Ilya Malakhov <ilmalakhovthefirst@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 arch/sparc/kernel/signal_64.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c
index d88beff4..39aaec1 100644
--- a/arch/sparc/kernel/signal_64.c
+++ b/arch/sparc/kernel/signal_64.c
@@ -52,7 +52,7 @@ asmlinkage void sparc64_set_context(struct pt_regs *regs)
 	unsigned char fenab;
 	int err;
 
-	flush_user_windows();
+	synchronize_user_stack();
 	if (get_thread_wsaved()					||
 	    (((unsigned long)ucp) & (sizeof(unsigned long)-1))	||
 	    (!__access_ok(ucp, sizeof(*ucp))))
-- 
2.5.0

[added to the 4.1 stable tree] sparc/PCI: Fix for panic while enabling SR-IOV

[Sasha Levin]

From: Babu Moger <babu.moger@oracle.com>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit d0c31e02005764dae0aab130a57e9794d06b824d ]

We noticed this panic while enabling SR-IOV in sparc.

mlx4_core: Mellanox ConnectX core driver v2.2-1 (Jan  1 2015)
mlx4_core: Initializing 0007:01:00.0
mlx4_core 0007:01:00.0: Enabling SR-IOV with 5 VFs
mlx4_core: Initializing 0007:01:00.1
Unable to handle kernel NULL pointer dereference
insmod(10010): Oops [#1]
CPU: 391 PID: 10010 Comm: insmod Not tainted
		4.1.12-32.el6uek.kdump2.sparc64 #1
TPC: <dma_supported+0x20/0x80>
I7: <__mlx4_init_one+0x324/0x500 [mlx4_core]>
Call Trace:
 [00000000104c5ea4] __mlx4_init_one+0x324/0x500 [mlx4_core]
 [00000000104c613c] mlx4_init_one+0xbc/0x120 [mlx4_core]
 [0000000000725f14] local_pci_probe+0x34/0xa0
 [0000000000726028] pci_call_probe+0xa8/0xe0
 [0000000000726310] pci_device_probe+0x50/0x80
 [000000000079f700] really_probe+0x140/0x420
 [000000000079fa24] driver_probe_device+0x44/0xa0
 [000000000079fb5c] __device_attach+0x3c/0x60
 [000000000079d85c] bus_for_each_drv+0x5c/0xa0
 [000000000079f588] device_attach+0x88/0xc0
 [000000000071acd0] pci_bus_add_device+0x30/0x80
 [0000000000736090] virtfn_add.clone.1+0x210/0x360
 [00000000007364a4] sriov_enable+0x2c4/0x520
 [000000000073672c] pci_enable_sriov+0x2c/0x40
 [00000000104c2d58] mlx4_enable_sriov+0xf8/0x180 [mlx4_core]
 [00000000104c49ac] mlx4_load_one+0x42c/0xd40 [mlx4_core]
Disabling lock debugging due to kernel taint
Caller[00000000104c5ea4]: __mlx4_init_one+0x324/0x500 [mlx4_core]
Caller[00000000104c613c]: mlx4_init_one+0xbc/0x120 [mlx4_core]
Caller[0000000000725f14]: local_pci_probe+0x34/0xa0
Caller[0000000000726028]: pci_call_probe+0xa8/0xe0
Caller[0000000000726310]: pci_device_probe+0x50/0x80
Caller[000000000079f700]: really_probe+0x140/0x420
Caller[000000000079fa24]: driver_probe_device+0x44/0xa0
Caller[000000000079fb5c]: __device_attach+0x3c/0x60
Caller[000000000079d85c]: bus_for_each_drv+0x5c/0xa0
Caller[000000000079f588]: device_attach+0x88/0xc0
Caller[000000000071acd0]: pci_bus_add_device+0x30/0x80
Caller[0000000000736090]: virtfn_add.clone.1+0x210/0x360
Caller[00000000007364a4]: sriov_enable+0x2c4/0x520
Caller[000000000073672c]: pci_enable_sriov+0x2c/0x40
Caller[00000000104c2d58]: mlx4_enable_sriov+0xf8/0x180 [mlx4_core]
Caller[00000000104c49ac]: mlx4_load_one+0x42c/0xd40 [mlx4_core]
Caller[00000000104c5f90]: __mlx4_init_one+0x410/0x500 [mlx4_core]
Caller[00000000104c613c]: mlx4_init_one+0xbc/0x120 [mlx4_core]
Caller[0000000000725f14]: local_pci_probe+0x34/0xa0
Caller[0000000000726028]: pci_call_probe+0xa8/0xe0
Caller[0000000000726310]: pci_device_probe+0x50/0x80
Caller[000000000079f700]: really_probe+0x140/0x420
Caller[000000000079fa24]: driver_probe_device+0x44/0xa0
Caller[000000000079fb08]: __driver_attach+0x88/0xa0
Caller[000000000079d90c]: bus_for_each_dev+0x6c/0xa0
Caller[000000000079f29c]: driver_attach+0x1c/0x40
Caller[000000000079e35c]: bus_add_driver+0x17c/0x220
Caller[00000000007a02d4]: driver_register+0x74/0x120
Caller[00000000007263fc]: __pci_register_driver+0x3c/0x60
Caller[00000000104f62bc]: mlx4_init+0x60/0xcc [mlx4_core]
Kernel panic - not syncing: Fatal exception
Press Stop-A (L1-A) to return to the boot prom
---[ end Kernel panic - not syncing: Fatal exception

Details:
Here is the call sequence
virtfn_add->__mlx4_init_one->dma_set_mask->dma_supported

The panic happened at line 760(file arch/sparc/kernel/iommu.c)

758 int dma_supported(struct device *dev, u64 device_mask)
759 {
760         struct iommu *iommu = dev->archdata.iommu;
761         u64 dma_addr_mask = iommu->dma_addr_mask;
762
763         if (device_mask >= (1UL << 32UL))
764                 return 0;
765
766         if ((device_mask & dma_addr_mask) == dma_addr_mask)
767                 return 1;
768
769 #ifdef CONFIG_PCI
770         if (dev_is_pci(dev))
771		return pci64_dma_supported(to_pci_dev(dev), device_mask);
772 #endif
773
774         return 0;
775 }
776 EXPORT_SYMBOL(dma_supported);

Same panic happened with Intel ixgbe driver also.

SR-IOV code looks for arch specific data while enabling
VFs. When VF device is added, driver probe function makes set
of calls to initialize the pci device. Because the VF device is
added different way than the normal PF device(which happens via
of_create_pci_dev for sparc), some of the arch specific initialization
does not happen for VF device.  That causes panic when archdata is
accessed.

To fix this, I have used already defined weak function
pcibios_setup_device to copy archdata from PF to VF.
Also verified the fix.

Signed-off-by: Babu Moger <babu.moger@oracle.com>
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Reviewed-by: Ethan Zhao <ethan.zhao@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 arch/sparc/kernel/pci.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c
index c928bc6..991ba90 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -994,6 +994,23 @@ void pcibios_set_master(struct pci_dev *dev)
 	/* No special bus mastering setup handling */
 }
 
+#ifdef CONFIG_PCI_IOV
+int pcibios_add_device(struct pci_dev *dev)
+{
+	struct pci_dev *pdev;
+
+	/* Add sriov arch specific initialization here.
+	 * Copy dev_archdata from PF to VF
+	 */
+	if (dev->is_virtfn) {
+		pdev = dev->physfn;
+		memcpy(&dev->dev.archdata, &pdev->dev.archdata,
+		       sizeof(struct dev_archdata));
+	}
+	return 0;
+}
+#endif /* CONFIG_PCI_IOV */
+
 static int __init pcibios_init(void)
 {
 	pci_dfl_cache_line_size = 64 >> 2;
-- 
2.5.0

[added to the 4.1 stable tree] sparc64: Take ctx_alloc_lock properly in hugetlb_setup().

[Sasha Levin]

From: "David S. Miller" <davem@davemloft.net>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 9ea46abe22550e3366ff7cee2f8391b35b12f730 ]

On cheetahplus chips we take the ctx_alloc_lock in order to
modify the TLB lookup parameters for the indexed TLBs, which
are stored in the context register.

This is called with interrupts disabled, however ctx_alloc_lock
is an IRQ safe lock, therefore we must take acquire/release it
properly with spin_{lock,unlock}_irq().

Reported-by: Meelis Roos <mroos@linux.ee>
Tested-by: Meelis Roos <mroos@linux.ee>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 arch/sparc/mm/init_64.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index b2f1e75..71c7ace 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -2770,9 +2770,10 @@ void hugetlb_setup(struct pt_regs *regs)
 	 * the Data-TLB for huge pages.
 	 */
 	if (tlb_type == cheetah_plus) {
+		bool need_context_reload = false;
 		unsigned long ctx;
 
-		spin_lock(&ctx_alloc_lock);
+		spin_lock_irq(&ctx_alloc_lock);
 		ctx = mm->context.sparc64_ctx_val;
 		ctx &= ~CTX_PGSZ_MASK;
 		ctx |= CTX_PGSZ_BASE << CTX_PGSZ0_SHIFT;
@@ -2791,9 +2792,12 @@ void hugetlb_setup(struct pt_regs *regs)
 			 * also executing in this address space.
 			 */
 			mm->context.sparc64_ctx_val = ctx;
-			on_each_cpu(context_reload, mm, 0);
+			need_context_reload = true;
 		}
-		spin_unlock(&ctx_alloc_lock);
+		spin_unlock_irq(&ctx_alloc_lock);
+
+		if (need_context_reload)
+			on_each_cpu(context_reload, mm, 0);
 	}
 }
 #endif
-- 
2.5.0

[added to the 4.1 stable tree] sparc: Harden signal return frame checks.

[Sasha Levin]

From: "David S. Miller" <davem@davemloft.net>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit d11c2a0de2824395656cf8ed15811580c9dd38aa ]

All signal frames must be at least 16-byte aligned, because that is
the alignment we explicitly create when we build signal return stack
frames.

All stack pointers must be at least 8-byte aligned.

Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 arch/sparc/kernel/signal32.c   | 46 +++++++++++++++++++++++++++---------------
 arch/sparc/kernel/signal_32.c  | 41 +++++++++++++++++++++++--------------
 arch/sparc/kernel/signal_64.c  | 31 ++++++++++++++++++----------
 arch/sparc/kernel/sigutil_32.c |  9 ++++++++-
 arch/sparc/kernel/sigutil_64.c | 10 +++++++--
 5 files changed, 92 insertions(+), 45 deletions(-)

diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c
index 4eed773..77655f0 100644
--- a/arch/sparc/kernel/signal32.c
+++ b/arch/sparc/kernel/signal32.c
@@ -138,12 +138,24 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
 	return 0;
 }
 
+/* Checks if the fp is valid.  We always build signal frames which are
+ * 16-byte aligned, therefore we can always enforce that the restore
+ * frame has that property as well.
+ */
+static bool invalid_frame_pointer(void __user *fp, int fplen)
+{
+	if ((((unsigned long) fp) & 15) ||
+	    ((unsigned long)fp) > 0x100000000ULL - fplen)
+		return true;
+	return false;
+}
+
 void do_sigreturn32(struct pt_regs *regs)
 {
 	struct signal_frame32 __user *sf;
 	compat_uptr_t fpu_save;
 	compat_uptr_t rwin_save;
-	unsigned int psr;
+	unsigned int psr, ufp;
 	unsigned pc, npc;
 	sigset_t set;
 	compat_sigset_t seta;
@@ -158,11 +170,16 @@ void do_sigreturn32(struct pt_regs *regs)
 	sf = (struct signal_frame32 __user *) regs->u_regs[UREG_FP];
 
 	/* 1. Make sure we are not getting garbage from the user */
-	if (!access_ok(VERIFY_READ, sf, sizeof(*sf)) ||
-	    (((unsigned long) sf) & 3))
+	if (invalid_frame_pointer(sf, sizeof(*sf)))
+		goto segv;
+
+	if (get_user(ufp, &sf->info.si_regs.u_regs[UREG_FP]))
+		goto segv;
+
+	if (ufp & 0x7)
 		goto segv;
 
-	if (get_user(pc, &sf->info.si_regs.pc) ||
+	if (__get_user(pc, &sf->info.si_regs.pc) ||
 	    __get_user(npc, &sf->info.si_regs.npc))
 		goto segv;
 
@@ -227,7 +244,7 @@ segv:
 asmlinkage void do_rt_sigreturn32(struct pt_regs *regs)
 {
 	struct rt_signal_frame32 __user *sf;
-	unsigned int psr, pc, npc;
+	unsigned int psr, pc, npc, ufp;
 	compat_uptr_t fpu_save;
 	compat_uptr_t rwin_save;
 	sigset_t set;
@@ -242,11 +259,16 @@ asmlinkage void do_rt_sigreturn32(struct pt_regs *regs)
 	sf = (struct rt_signal_frame32 __user *) regs->u_regs[UREG_FP];
 
 	/* 1. Make sure we are not getting garbage from the user */
-	if (!access_ok(VERIFY_READ, sf, sizeof(*sf)) ||
-	    (((unsigned long) sf) & 3))
+	if (invalid_frame_pointer(sf, sizeof(*sf)))
 		goto segv;
 
-	if (get_user(pc, &sf->regs.pc) || 
+	if (get_user(ufp, &sf->regs.u_regs[UREG_FP]))
+		goto segv;
+
+	if (ufp & 0x7)
+		goto segv;
+
+	if (__get_user(pc, &sf->regs.pc) ||
 	    __get_user(npc, &sf->regs.npc))
 		goto segv;
 
@@ -307,14 +329,6 @@ segv:
 	force_sig(SIGSEGV, current);
 }
 
-/* Checks if the fp is valid */
-static int invalid_frame_pointer(void __user *fp, int fplen)
-{
-	if ((((unsigned long) fp) & 7) || ((unsigned long)fp) > 0x100000000ULL - fplen)
-		return 1;
-	return 0;
-}
-
 static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, unsigned long framesize)
 {
 	unsigned long sp;
diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c
index 52aa5e4..c3c12ef 100644
--- a/arch/sparc/kernel/signal_32.c
+++ b/arch/sparc/kernel/signal_32.c
@@ -60,10 +60,22 @@ struct rt_signal_frame {
 #define SF_ALIGNEDSZ  (((sizeof(struct signal_frame) + 7) & (~7)))
 #define RT_ALIGNEDSZ  (((sizeof(struct rt_signal_frame) + 7) & (~7)))
 
+/* Checks if the fp is valid.  We always build signal frames which are
+ * 16-byte aligned, therefore we can always enforce that the restore
+ * frame has that property as well.
+ */
+static inline bool invalid_frame_pointer(void __user *fp, int fplen)
+{
+	if ((((unsigned long) fp) & 15) || !__access_ok((unsigned long)fp, fplen))
+		return true;
+
+	return false;
+}
+
 asmlinkage void do_sigreturn(struct pt_regs *regs)
 {
+	unsigned long up_psr, pc, npc, ufp;
 	struct signal_frame __user *sf;
-	unsigned long up_psr, pc, npc;
 	sigset_t set;
 	__siginfo_fpu_t __user *fpu_save;
 	__siginfo_rwin_t __user *rwin_save;
@@ -77,10 +89,13 @@ asmlinkage void do_sigreturn(struct pt_regs *regs)
 	sf = (struct signal_frame __user *) regs->u_regs[UREG_FP];
 
 	/* 1. Make sure we are not getting garbage from the user */
-	if (!access_ok(VERIFY_READ, sf, sizeof(*sf)))
+	if (!invalid_frame_pointer(sf, sizeof(*sf)))
+		goto segv_and_exit;
+
+	if (get_user(ufp, &sf->info.si_regs.u_regs[UREG_FP]))
 		goto segv_and_exit;
 
-	if (((unsigned long) sf) & 3)
+	if (ufp & 0x7)
 		goto segv_and_exit;
 
 	err = __get_user(pc,  &sf->info.si_regs.pc);
@@ -127,7 +142,7 @@ segv_and_exit:
 asmlinkage void do_rt_sigreturn(struct pt_regs *regs)
 {
 	struct rt_signal_frame __user *sf;
-	unsigned int psr, pc, npc;
+	unsigned int psr, pc, npc, ufp;
 	__siginfo_fpu_t __user *fpu_save;
 	__siginfo_rwin_t __user *rwin_save;
 	sigset_t set;
@@ -135,8 +150,13 @@ asmlinkage void do_rt_sigreturn(struct pt_regs *regs)
 
 	synchronize_user_stack();
 	sf = (struct rt_signal_frame __user *) regs->u_regs[UREG_FP];
-	if (!access_ok(VERIFY_READ, sf, sizeof(*sf)) ||
-	    (((unsigned long) sf) & 0x03))
+	if (!invalid_frame_pointer(sf, sizeof(*sf)))
+		goto segv;
+
+	if (get_user(ufp, &sf->regs.u_regs[UREG_FP]))
+		goto segv;
+
+	if (ufp & 0x7)
 		goto segv;
 
 	err = __get_user(pc, &sf->regs.pc);
@@ -178,15 +198,6 @@ segv:
 	force_sig(SIGSEGV, current);
 }
 
-/* Checks if the fp is valid */
-static inline int invalid_frame_pointer(void __user *fp, int fplen)
-{
-	if ((((unsigned long) fp) & 7) || !__access_ok((unsigned long)fp, fplen))
-		return 1;
-
-	return 0;
-}
-
 static inline void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, unsigned long framesize)
 {
 	unsigned long sp = regs->u_regs[UREG_FP];
diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c
index 39aaec1..5ee930c 100644
--- a/arch/sparc/kernel/signal_64.c
+++ b/arch/sparc/kernel/signal_64.c
@@ -234,6 +234,17 @@ do_sigsegv:
 	goto out;
 }
 
+/* Checks if the fp is valid.  We always build rt signal frames which
+ * are 16-byte aligned, therefore we can always enforce that the
+ * restore frame has that property as well.
+ */
+static bool invalid_frame_pointer(void __user *fp)
+{
+	if (((unsigned long) fp) & 15)
+		return true;
+	return false;
+}
+
 struct rt_signal_frame {
 	struct sparc_stackf	ss;
 	siginfo_t		info;
@@ -246,8 +257,8 @@ struct rt_signal_frame {
 
 void do_rt_sigreturn(struct pt_regs *regs)
 {
+	unsigned long tpc, tnpc, tstate, ufp;
 	struct rt_signal_frame __user *sf;
-	unsigned long tpc, tnpc, tstate;
 	__siginfo_fpu_t __user *fpu_save;
 	__siginfo_rwin_t __user *rwin_save;
 	sigset_t set;
@@ -261,10 +272,16 @@ void do_rt_sigreturn(struct pt_regs *regs)
 		(regs->u_regs [UREG_FP] + STACK_BIAS);
 
 	/* 1. Make sure we are not getting garbage from the user */
-	if (((unsigned long) sf) & 3)
+	if (invalid_frame_pointer(sf))
+		goto segv;
+
+	if (get_user(ufp, &sf->regs.u_regs[UREG_FP]))
 		goto segv;
 
-	err = get_user(tpc, &sf->regs.tpc);
+	if ((ufp + STACK_BIAS) & 0x7)
+		goto segv;
+
+	err = __get_user(tpc, &sf->regs.tpc);
 	err |= __get_user(tnpc, &sf->regs.tnpc);
 	if (test_thread_flag(TIF_32BIT)) {
 		tpc &= 0xffffffff;
@@ -308,14 +325,6 @@ segv:
 	force_sig(SIGSEGV, current);
 }
 
-/* Checks if the fp is valid */
-static int invalid_frame_pointer(void __user *fp)
-{
-	if (((unsigned long) fp) & 15)
-		return 1;
-	return 0;
-}
-
 static inline void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, unsigned long framesize)
 {
 	unsigned long sp = regs->u_regs[UREG_FP] + STACK_BIAS;
diff --git a/arch/sparc/kernel/sigutil_32.c b/arch/sparc/kernel/sigutil_32.c
index 0f6eebe..e5fe8ce 100644
--- a/arch/sparc/kernel/sigutil_32.c
+++ b/arch/sparc/kernel/sigutil_32.c
@@ -48,6 +48,10 @@ int save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
 int restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
 {
 	int err;
+
+	if (((unsigned long) fpu) & 3)
+		return -EFAULT;
+
 #ifdef CONFIG_SMP
 	if (test_tsk_thread_flag(current, TIF_USEDFPU))
 		regs->psr &= ~PSR_EF;
@@ -97,7 +101,10 @@ int restore_rwin_state(__siginfo_rwin_t __user *rp)
 	struct thread_info *t = current_thread_info();
 	int i, wsaved, err;
 
-	__get_user(wsaved, &rp->wsaved);
+	if (((unsigned long) rp) & 3)
+		return -EFAULT;
+
+	get_user(wsaved, &rp->wsaved);
 	if (wsaved > NSWINS)
 		return -EFAULT;
 
diff --git a/arch/sparc/kernel/sigutil_64.c b/arch/sparc/kernel/sigutil_64.c
index 387834a..36aadcb 100644
--- a/arch/sparc/kernel/sigutil_64.c
+++ b/arch/sparc/kernel/sigutil_64.c
@@ -37,7 +37,10 @@ int restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
 	unsigned long fprs;
 	int err;
 
-	err = __get_user(fprs, &fpu->si_fprs);
+	if (((unsigned long) fpu) & 7)
+		return -EFAULT;
+
+	err = get_user(fprs, &fpu->si_fprs);
 	fprs_write(0);
 	regs->tstate &= ~TSTATE_PEF;
 	if (fprs & FPRS_DL)
@@ -72,7 +75,10 @@ int restore_rwin_state(__siginfo_rwin_t __user *rp)
 	struct thread_info *t = current_thread_info();
 	int i, wsaved, err;
 
-	__get_user(wsaved, &rp->wsaved);
+	if (((unsigned long) rp) & 7)
+		return -EFAULT;
+
+	get_user(wsaved, &rp->wsaved);
 	if (wsaved > NSWINS)
 		return -EFAULT;
 
-- 
2.5.0

[added to the 4.1 stable tree] sparc64: Fix return from trap window fill crashes.

[Sasha Levin]

From: "David S. Miller" <davem@davemloft.net>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 7cafc0b8bf130f038b0ec2dcdd6a9de6dc59b65a ]

We must handle data access exception as well as memory address unaligned
exceptions from return from trap window fill faults, not just normal
TLB misses.

Otherwise we can get an OOPS that looks like this:

ld-linux.so.2(36808): Kernel bad sw trap 5 [#1]
CPU: 1 PID: 36808 Comm: ld-linux.so.2 Not tainted 4.6.0 #34
task: fff8000303be5c60 ti: fff8000301344000 task.ti: fff8000301344000
TSTATE: 0000004410001601 TPC: 0000000000a1a784 TNPC: 0000000000a1a788 Y: 00000002    Not tainted
TPC: <do_sparc64_fault+0x5c4/0x700>
g0: fff8000024fc8248 g1: 0000000000db04dc g2: 0000000000000000 g3: 0000000000000001
g4: fff8000303be5c60 g5: fff800030e672000 g6: fff8000301344000 g7: 0000000000000001
o0: 0000000000b95ee8 o1: 000000000000012b o2: 0000000000000000 o3: 0000000200b9b358
o4: 0000000000000000 o5: fff8000301344040 sp: fff80003013475c1 ret_pc: 0000000000a1a77c
RPC: <do_sparc64_fault+0x5bc/0x700>
l0: 00000000000007ff l1: 0000000000000000 l2: 000000000000005f l3: 0000000000000000
l4: fff8000301347e98 l5: fff8000024ff3060 l6: 0000000000000000 l7: 0000000000000000
i0: fff8000301347f60 i1: 0000000000102400 i2: 0000000000000000 i3: 0000000000000000
i4: 0000000000000000 i5: 0000000000000000 i6: fff80003013476a1 i7: 0000000000404d4c
I7: <user_rtt_fill_fixup+0x6c/0x7c>
Call Trace:
 [0000000000404d4c] user_rtt_fill_fixup+0x6c/0x7c

The window trap handlers are slightly clever, the trap table entries for them are
composed of two pieces of code.  First comes the code that actually performs
the window fill or spill trap handling, and then there are three instructions at
the end which are for exception processing.

The userland register window fill handler is:

	add	%sp, STACK_BIAS + 0x00, %g1;		\
	ldxa	[%g1 + %g0] ASI, %l0;			\
	mov	0x08, %g2;				\
	mov	0x10, %g3;				\
	ldxa	[%g1 + %g2] ASI, %l1;			\
	mov	0x18, %g5;				\
	ldxa	[%g1 + %g3] ASI, %l2;			\
	ldxa	[%g1 + %g5] ASI, %l3;			\
	add	%g1, 0x20, %g1;				\
	ldxa	[%g1 + %g0] ASI, %l4;			\
	ldxa	[%g1 + %g2] ASI, %l5;			\
	ldxa	[%g1 + %g3] ASI, %l6;			\
	ldxa	[%g1 + %g5] ASI, %l7;			\
	add	%g1, 0x20, %g1;				\
	ldxa	[%g1 + %g0] ASI, %i0;			\
	ldxa	[%g1 + %g2] ASI, %i1;			\
	ldxa	[%g1 + %g3] ASI, %i2;			\
	ldxa	[%g1 + %g5] ASI, %i3;			\
	add	%g1, 0x20, %g1;				\
	ldxa	[%g1 + %g0] ASI, %i4;			\
	ldxa	[%g1 + %g2] ASI, %i5;			\
	ldxa	[%g1 + %g3] ASI, %i6;			\
	ldxa	[%g1 + %g5] ASI, %i7;			\
	restored;					\
	retry; nop; nop; nop; nop;			\
	b,a,pt	%xcc, fill_fixup_dax;			\
	b,a,pt	%xcc, fill_fixup_mna;			\
	b,a,pt	%xcc, fill_fixup;

And the way this works is that if any of those memory accesses
generate an exception, the exception handler can revector to one of
those final three branch instructions depending upon which kind of
exception the memory access took.  In this way, the fault handler
doesn't have to know if it was a spill or a fill that it's handling
the fault for.  It just always branches to the last instruction in
the parent trap's handler.

For example, for a regular fault, the code goes:

winfix_trampoline:
	rdpr	%tpc, %g3
	or	%g3, 0x7c, %g3
	wrpr	%g3, %tnpc
	done

All window trap handlers are 0x80 aligned, so if we "or" 0x7c into the
trap time program counter, we'll get that final instruction in the
trap handler.

On return from trap, we have to pull the register window in but we do
this by hand instead of just executing a "restore" instruction for
several reasons.  The largest being that from Niagara and onward we
simply don't have enough levels in the trap stack to fully resolve all
possible exception cases of a window fault when we are already at
trap level 1 (which we enter to get ready to return from the original
trap).

This is executed inline via the FILL_*_RTRAP handlers.  rtrap_64.S's
code branches directly to these to do the window fill by hand if
necessary.  Now if you look at them, we'll see at the end:

	    ba,a,pt    %xcc, user_rtt_fill_fixup;
	    ba,a,pt    %xcc, user_rtt_fill_fixup;
	    ba,a,pt    %xcc, user_rtt_fill_fixup;

And oops, all three cases are handled like a fault.

This doesn't work because each of these trap types (data access
exception, memory address unaligned, and faults) store their auxiliary
info in different registers to pass on to the C handler which does the
real work.

So in the case where the stack was unaligned, the unaligned trap
handler sets up the arg registers one way, and then we branched to
the fault handler which expects them setup another way.

So the FAULT_TYPE_* value ends up basically being garbage, and
randomly would generate the backtrace seen above.

Reported-by: Nick Alcock <nix@esperi.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 arch/sparc/include/asm/head_64.h |  4 ++
 arch/sparc/include/asm/ttable.h  |  8 ++--
 arch/sparc/kernel/Makefile       |  1 +
 arch/sparc/kernel/rtrap_64.S     | 57 ++++-------------------
 arch/sparc/kernel/urtt_fill.S    | 98 ++++++++++++++++++++++++++++++++++++++++
 5 files changed, 116 insertions(+), 52 deletions(-)
 create mode 100644 arch/sparc/kernel/urtt_fill.S

diff --git a/arch/sparc/include/asm/head_64.h b/arch/sparc/include/asm/head_64.h
index 10e9dab..f0700cf 100644
--- a/arch/sparc/include/asm/head_64.h
+++ b/arch/sparc/include/asm/head_64.h
@@ -15,6 +15,10 @@
 
 #define	PTREGS_OFF	(STACK_BIAS + STACKFRAME_SZ)
 
+#define	RTRAP_PSTATE		(PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_IE)
+#define	RTRAP_PSTATE_IRQOFF	(PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV)
+#define RTRAP_PSTATE_AG_IRQOFF	(PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_AG)
+
 #define __CHEETAH_ID	0x003e0014
 #define __JALAPENO_ID	0x003e0016
 #define __SERRANO_ID	0x003e0022
diff --git a/arch/sparc/include/asm/ttable.h b/arch/sparc/include/asm/ttable.h
index 71b5a67..781b9f1 100644
--- a/arch/sparc/include/asm/ttable.h
+++ b/arch/sparc/include/asm/ttable.h
@@ -589,8 +589,8 @@ user_rtt_fill_64bit:					\
 	 restored;					\
 	nop; nop; nop; nop; nop; nop;			\
 	nop; nop; nop; nop; nop;			\
-	ba,a,pt	%xcc, user_rtt_fill_fixup;		\
-	ba,a,pt	%xcc, user_rtt_fill_fixup;		\
+	ba,a,pt	%xcc, user_rtt_fill_fixup_dax;		\
+	ba,a,pt	%xcc, user_rtt_fill_fixup_mna;		\
 	ba,a,pt	%xcc, user_rtt_fill_fixup;
 
 
@@ -652,8 +652,8 @@ user_rtt_fill_32bit:					\
 	 restored;					\
 	nop; nop; nop; nop; nop;			\
 	nop; nop; nop;					\
-	ba,a,pt	%xcc, user_rtt_fill_fixup;		\
-	ba,a,pt	%xcc, user_rtt_fill_fixup;		\
+	ba,a,pt	%xcc, user_rtt_fill_fixup_dax;		\
+	ba,a,pt	%xcc, user_rtt_fill_fixup_mna;		\
 	ba,a,pt	%xcc, user_rtt_fill_fixup;
 
 
diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile
index 7cf9c6e..fdb1332 100644
--- a/arch/sparc/kernel/Makefile
+++ b/arch/sparc/kernel/Makefile
@@ -21,6 +21,7 @@ CFLAGS_REMOVE_perf_event.o := -pg
 CFLAGS_REMOVE_pcr.o := -pg
 endif
 
+obj-$(CONFIG_SPARC64)   += urtt_fill.o
 obj-$(CONFIG_SPARC32)   += entry.o wof.o wuf.o
 obj-$(CONFIG_SPARC32)   += etrap_32.o
 obj-$(CONFIG_SPARC32)   += rtrap_32.o
diff --git a/arch/sparc/kernel/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S
index 39f0c66..8de386d 100644
--- a/arch/sparc/kernel/rtrap_64.S
+++ b/arch/sparc/kernel/rtrap_64.S
@@ -14,10 +14,6 @@
 #include <asm/visasm.h>
 #include <asm/processor.h>
 
-#define		RTRAP_PSTATE		(PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_IE)
-#define		RTRAP_PSTATE_IRQOFF	(PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV)
-#define		RTRAP_PSTATE_AG_IRQOFF	(PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_AG)
-
 #ifdef CONFIG_CONTEXT_TRACKING
 # define SCHEDULE_USER schedule_user
 #else
@@ -236,52 +232,17 @@ rt_continue:	ldx			[%sp + PTREGS_OFF + PT_V9_G1], %g1
 		 wrpr			%g1, %cwp
 		ba,a,pt			%xcc, user_rtt_fill_64bit
 
-user_rtt_fill_fixup:
-		rdpr	%cwp, %g1
-		add	%g1, 1, %g1
-		wrpr	%g1, 0x0, %cwp
-
-		rdpr	%wstate, %g2
-		sll	%g2, 3, %g2
-		wrpr	%g2, 0x0, %wstate
-
-		/* We know %canrestore and %otherwin are both zero.  */
-
-		sethi	%hi(sparc64_kern_pri_context), %g2
-		ldx	[%g2 + %lo(sparc64_kern_pri_context)], %g2
-		mov	PRIMARY_CONTEXT, %g1
-
-661:		stxa	%g2, [%g1] ASI_DMMU
-		.section .sun4v_1insn_patch, "ax"
-		.word	661b
-		stxa	%g2, [%g1] ASI_MMU
-		.previous
-
-		sethi	%hi(KERNBASE), %g1
-		flush	%g1
+user_rtt_fill_fixup_dax:
+		ba,pt	%xcc, user_rtt_fill_fixup_common
+		 mov	1, %g3
 
-		or	%g4, FAULT_CODE_WINFIXUP, %g4
-		stb	%g4, [%g6 + TI_FAULT_CODE]
-		stx	%g5, [%g6 + TI_FAULT_ADDR]
+user_rtt_fill_fixup_mna:
+		ba,pt	%xcc, user_rtt_fill_fixup_common
+		 mov	2, %g3
 
-		mov	%g6, %l1
-		wrpr	%g0, 0x0, %tl
-
-661:		nop
-		.section		.sun4v_1insn_patch, "ax"
-		.word			661b
-		SET_GL(0)
-		.previous
-
-		wrpr	%g0, RTRAP_PSTATE, %pstate
-
-		mov	%l1, %g6
-		ldx	[%g6 + TI_TASK], %g4
-		LOAD_PER_CPU_BASE(%g5, %g6, %g1, %g2, %g3)
-		call	do_sparc64_fault
-		 add	%sp, PTREGS_OFF, %o0
-		ba,pt	%xcc, rtrap
-		 nop
+user_rtt_fill_fixup:
+		ba,pt	%xcc, user_rtt_fill_fixup_common
+		 clr	%g3
 
 user_rtt_pre_restore:
 		add			%g1, 1, %g1
diff --git a/arch/sparc/kernel/urtt_fill.S b/arch/sparc/kernel/urtt_fill.S
new file mode 100644
index 0000000..5604a2b
--- /dev/null
+++ b/arch/sparc/kernel/urtt_fill.S
@@ -0,0 +1,98 @@
+#include <asm/thread_info.h>
+#include <asm/trap_block.h>
+#include <asm/spitfire.h>
+#include <asm/ptrace.h>
+#include <asm/head.h>
+
+		.text
+		.align	8
+		.globl	user_rtt_fill_fixup_common
+user_rtt_fill_fixup_common:
+		rdpr	%cwp, %g1
+		add	%g1, 1, %g1
+		wrpr	%g1, 0x0, %cwp
+
+		rdpr	%wstate, %g2
+		sll	%g2, 3, %g2
+		wrpr	%g2, 0x0, %wstate
+
+		/* We know %canrestore and %otherwin are both zero.  */
+
+		sethi	%hi(sparc64_kern_pri_context), %g2
+		ldx	[%g2 + %lo(sparc64_kern_pri_context)], %g2
+		mov	PRIMARY_CONTEXT, %g1
+
+661:		stxa	%g2, [%g1] ASI_DMMU
+		.section .sun4v_1insn_patch, "ax"
+		.word	661b
+		stxa	%g2, [%g1] ASI_MMU
+		.previous
+
+		sethi	%hi(KERNBASE), %g1
+		flush	%g1
+
+		mov	%g4, %l4
+		mov	%g5, %l5
+		brnz,pn	%g3, 1f
+		 mov	%g3, %l3
+
+		or	%g4, FAULT_CODE_WINFIXUP, %g4
+		stb	%g4, [%g6 + TI_FAULT_CODE]
+		stx	%g5, [%g6 + TI_FAULT_ADDR]
+1:
+		mov	%g6, %l1
+		wrpr	%g0, 0x0, %tl
+
+661:		nop
+		.section		.sun4v_1insn_patch, "ax"
+		.word			661b
+		SET_GL(0)
+		.previous
+
+		wrpr	%g0, RTRAP_PSTATE, %pstate
+
+		mov	%l1, %g6
+		ldx	[%g6 + TI_TASK], %g4
+		LOAD_PER_CPU_BASE(%g5, %g6, %g1, %g2, %g3)
+
+		brnz,pn	%l3, 1f
+		 nop
+
+		call	do_sparc64_fault
+		 add	%sp, PTREGS_OFF, %o0
+		ba,pt	%xcc, rtrap
+		 nop
+
+1:		cmp	%g3, 2
+		bne,pn	%xcc, 2f
+		 nop
+
+		sethi	%hi(tlb_type), %g1
+		lduw	[%g1 + %lo(tlb_type)], %g1
+		cmp	%g1, 3
+		bne,pt	%icc, 1f
+		 add	%sp, PTREGS_OFF, %o0
+		mov	%l4, %o2
+		call	sun4v_do_mna
+		 mov	%l5, %o1
+		ba,a,pt	%xcc, rtrap
+1:		mov	%l4, %o1
+		mov	%l5, %o2
+		call	mem_address_unaligned
+		 nop
+		ba,a,pt	%xcc, rtrap
+
+2:		sethi	%hi(tlb_type), %g1
+		mov	%l4, %o1
+		lduw	[%g1 + %lo(tlb_type)], %g1
+		mov	%l5, %o2
+		cmp	%g1, 3
+		bne,pt	%icc, 1f
+		 add	%sp, PTREGS_OFF, %o0
+		call	sun4v_data_access_exception
+		 nop
+		ba,a,pt	%xcc, rtrap
+
+1:		call	spitfire_data_access_exception
+		 nop
+		ba,a,pt	%xcc, rtrap
-- 
2.5.0

[added to the 4.1 stable tree] MIPS: Fix 64k page support for 32 bit kernels.

[Sasha Levin]

From: Ralf Baechle <ralf@linux-mips.org>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit d7de413475f443957a0c1d256e405d19b3a2cb22 ]

TASK_SIZE was defined as 0x7fff8000UL which for 64k pages is not a
multiple of the page size.  Somewhere further down the math fails
such that executing an ELF binary fails.

Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Tested-by: Joshua Henderson <joshua.henderson@microchip.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 arch/mips/include/asm/processor.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h
index 9b3b48e..6ec90a1 100644
--- a/arch/mips/include/asm/processor.h
+++ b/arch/mips/include/asm/processor.h
@@ -51,7 +51,7 @@ extern unsigned int vced_count, vcei_count;
  * User space process size: 2GB. This is hardcoded into a few places,
  * so don't change it unless you know what you are doing.
  */
-#define TASK_SIZE	0x7fff8000UL
+#define TASK_SIZE	0x80000000UL
 #endif
 
 #define STACK_TOP_MAX	TASK_SIZE
-- 
2.5.0

[added to the 4.1 stable tree] netfilter: x_tables: validate e->target_offset early

[Sasha Levin]

From: Florian Westphal <fw@strlen.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit bdf533de6968e9686df777dc178486f600c6e617 ]

We should check that e->target_offset is sane before
mark_source_chains gets called since it will fetch the target entry
for loop detection.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/ipv4/netfilter/arp_tables.c | 17 ++++++++---------
 net/ipv4/netfilter/ip_tables.c  | 17 ++++++++---------
 net/ipv6/netfilter/ip6_tables.c | 17 ++++++++---------
 3 files changed, 24 insertions(+), 27 deletions(-)

diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index a612007..e500f4f 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -469,14 +469,12 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
 	return 1;
 }
 
-static inline int check_entry(const struct arpt_entry *e, const char *name)
+static inline int check_entry(const struct arpt_entry *e)
 {
 	const struct xt_entry_target *t;
 
-	if (!arp_checkentry(&e->arp)) {
-		duprintf("arp_tables: arp check failed %p %s.\n", e, name);
+	if (!arp_checkentry(&e->arp))
 		return -EINVAL;
-	}
 
 	if (e->target_offset + sizeof(struct xt_entry_target) > e->next_offset)
 		return -EINVAL;
@@ -517,10 +515,6 @@ find_check_entry(struct arpt_entry *e, const char *name, unsigned int size)
 	struct xt_target *target;
 	int ret;
 
-	ret = check_entry(e, name);
-	if (ret)
-		return ret;
-
 	t = arpt_get_target(e);
 	target = xt_request_find_target(NFPROTO_ARP, t->u.user.name,
 					t->u.user.revision);
@@ -565,6 +559,7 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e,
 					     unsigned int valid_hooks)
 {
 	unsigned int h;
+	int err;
 
 	if ((unsigned long)e % __alignof__(struct arpt_entry) != 0 ||
 	    (unsigned char *)e + sizeof(struct arpt_entry) >= limit) {
@@ -579,6 +574,10 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e,
 		return -EINVAL;
 	}
 
+	err = check_entry(e);
+	if (err)
+		return err;
+
 	/* Check hooks & underflows */
 	for (h = 0; h < NF_ARP_NUMHOOKS; h++) {
 		if (!(valid_hooks & (1 << h)))
@@ -1239,7 +1238,7 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e,
 	}
 
 	/* For purposes of check_entry casting the compat entry is fine */
-	ret = check_entry((struct arpt_entry *)e, name);
+	ret = check_entry((struct arpt_entry *)e);
 	if (ret)
 		return ret;
 
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 2d0e265..a75ff8a84 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -564,14 +564,12 @@ static void cleanup_match(struct xt_entry_match *m, struct net *net)
 }
 
 static int
-check_entry(const struct ipt_entry *e, const char *name)
+check_entry(const struct ipt_entry *e)
 {
 	const struct xt_entry_target *t;
 
-	if (!ip_checkentry(&e->ip)) {
-		duprintf("ip check failed %p %s.\n", e, name);
+	if (!ip_checkentry(&e->ip))
 		return -EINVAL;
-	}
 
 	if (e->target_offset + sizeof(struct xt_entry_target) >
 	    e->next_offset)
@@ -661,10 +659,6 @@ find_check_entry(struct ipt_entry *e, struct net *net, const char *name,
 	struct xt_mtchk_param mtpar;
 	struct xt_entry_match *ematch;
 
-	ret = check_entry(e, name);
-	if (ret)
-		return ret;
-
 	j = 0;
 	mtpar.net	= net;
 	mtpar.table     = name;
@@ -728,6 +722,7 @@ check_entry_size_and_hooks(struct ipt_entry *e,
 			   unsigned int valid_hooks)
 {
 	unsigned int h;
+	int err;
 
 	if ((unsigned long)e % __alignof__(struct ipt_entry) != 0 ||
 	    (unsigned char *)e + sizeof(struct ipt_entry) >= limit) {
@@ -742,6 +737,10 @@ check_entry_size_and_hooks(struct ipt_entry *e,
 		return -EINVAL;
 	}
 
+	err = check_entry(e);
+	if (err)
+		return err;
+
 	/* Check hooks & underflows */
 	for (h = 0; h < NF_INET_NUMHOOKS; h++) {
 		if (!(valid_hooks & (1 << h)))
@@ -1505,7 +1504,7 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e,
 	}
 
 	/* For purposes of check_entry casting the compat entry is fine */
-	ret = check_entry((struct ipt_entry *)e, name);
+	ret = check_entry((struct ipt_entry *)e);
 	if (ret)
 		return ret;
 
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 62f5b0d..ef764a6 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -577,14 +577,12 @@ static void cleanup_match(struct xt_entry_match *m, struct net *net)
 }
 
 static int
-check_entry(const struct ip6t_entry *e, const char *name)
+check_entry(const struct ip6t_entry *e)
 {
 	const struct xt_entry_target *t;
 
-	if (!ip6_checkentry(&e->ipv6)) {
-		duprintf("ip_tables: ip check failed %p %s.\n", e, name);
+	if (!ip6_checkentry(&e->ipv6))
 		return -EINVAL;
-	}
 
 	if (e->target_offset + sizeof(struct xt_entry_target) >
 	    e->next_offset)
@@ -675,10 +673,6 @@ find_check_entry(struct ip6t_entry *e, struct net *net, const char *name,
 	struct xt_mtchk_param mtpar;
 	struct xt_entry_match *ematch;
 
-	ret = check_entry(e, name);
-	if (ret)
-		return ret;
-
 	j = 0;
 	mtpar.net	= net;
 	mtpar.table     = name;
@@ -742,6 +736,7 @@ check_entry_size_and_hooks(struct ip6t_entry *e,
 			   unsigned int valid_hooks)
 {
 	unsigned int h;
+	int err;
 
 	if ((unsigned long)e % __alignof__(struct ip6t_entry) != 0 ||
 	    (unsigned char *)e + sizeof(struct ip6t_entry) >= limit) {
@@ -756,6 +751,10 @@ check_entry_size_and_hooks(struct ip6t_entry *e,
 		return -EINVAL;
 	}
 
+	err = check_entry(e);
+	if (err)
+		return err;
+
 	/* Check hooks & underflows */
 	for (h = 0; h < NF_INET_NUMHOOKS; h++) {
 		if (!(valid_hooks & (1 << h)))
@@ -1520,7 +1519,7 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e,
 	}
 
 	/* For purposes of check_entry casting the compat entry is fine */
-	ret = check_entry((struct ip6t_entry *)e, name);
+	ret = check_entry((struct ip6t_entry *)e);
 	if (ret)
 		return ret;
 
-- 
2.5.0

[added to the 4.1 stable tree] netfilter: x_tables: make sure e->next_offset covers remaining blob size

[Sasha Levin]

From: Florian Westphal <fw@strlen.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 6e94e0cfb0887e4013b3b930fa6ab1fe6bb6ba91 ]

Otherwise this function may read data beyond the ruleset blob.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/ipv4/netfilter/arp_tables.c | 6 ++++--
 net/ipv4/netfilter/ip_tables.c  | 6 ++++--
 net/ipv6/netfilter/ip6_tables.c | 6 ++++--
 3 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index e500f4f..835b768 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -562,7 +562,8 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e,
 	int err;
 
 	if ((unsigned long)e % __alignof__(struct arpt_entry) != 0 ||
-	    (unsigned char *)e + sizeof(struct arpt_entry) >= limit) {
+	    (unsigned char *)e + sizeof(struct arpt_entry) >= limit ||
+	    (unsigned char *)e + e->next_offset > limit) {
 		duprintf("Bad offset %p\n", e);
 		return -EINVAL;
 	}
@@ -1225,7 +1226,8 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e,
 
 	duprintf("check_compat_entry_size_and_hooks %p\n", e);
 	if ((unsigned long)e % __alignof__(struct compat_arpt_entry) != 0 ||
-	    (unsigned char *)e + sizeof(struct compat_arpt_entry) >= limit) {
+	    (unsigned char *)e + sizeof(struct compat_arpt_entry) >= limit ||
+	    (unsigned char *)e + e->next_offset > limit) {
 		duprintf("Bad offset %p, limit = %p\n", e, limit);
 		return -EINVAL;
 	}
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index a75ff8a84..4ad5576 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -725,7 +725,8 @@ check_entry_size_and_hooks(struct ipt_entry *e,
 	int err;
 
 	if ((unsigned long)e % __alignof__(struct ipt_entry) != 0 ||
-	    (unsigned char *)e + sizeof(struct ipt_entry) >= limit) {
+	    (unsigned char *)e + sizeof(struct ipt_entry) >= limit ||
+	    (unsigned char *)e + e->next_offset > limit) {
 		duprintf("Bad offset %p\n", e);
 		return -EINVAL;
 	}
@@ -1491,7 +1492,8 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e,
 
 	duprintf("check_compat_entry_size_and_hooks %p\n", e);
 	if ((unsigned long)e % __alignof__(struct compat_ipt_entry) != 0 ||
-	    (unsigned char *)e + sizeof(struct compat_ipt_entry) >= limit) {
+	    (unsigned char *)e + sizeof(struct compat_ipt_entry) >= limit ||
+	    (unsigned char *)e + e->next_offset > limit) {
 		duprintf("Bad offset %p, limit = %p\n", e, limit);
 		return -EINVAL;
 	}
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index ef764a6..9a4666b 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -739,7 +739,8 @@ check_entry_size_and_hooks(struct ip6t_entry *e,
 	int err;
 
 	if ((unsigned long)e % __alignof__(struct ip6t_entry) != 0 ||
-	    (unsigned char *)e + sizeof(struct ip6t_entry) >= limit) {
+	    (unsigned char *)e + sizeof(struct ip6t_entry) >= limit ||
+	    (unsigned char *)e + e->next_offset > limit) {
 		duprintf("Bad offset %p\n", e);
 		return -EINVAL;
 	}
@@ -1506,7 +1507,8 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e,
 
 	duprintf("check_compat_entry_size_and_hooks %p\n", e);
 	if ((unsigned long)e % __alignof__(struct compat_ip6t_entry) != 0 ||
-	    (unsigned char *)e + sizeof(struct compat_ip6t_entry) >= limit) {
+	    (unsigned char *)e + sizeof(struct compat_ip6t_entry) >= limit ||
+	    (unsigned char *)e + e->next_offset > limit) {
 		duprintf("Bad offset %p, limit = %p\n", e, limit);
 		return -EINVAL;
 	}
-- 
2.5.0

[added to the 4.1 stable tree] netfilter: x_tables: fix unconditional helper

[Sasha Levin]

From: Florian Westphal <fw@strlen.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 54d83fc74aa9ec72794373cb47432c5f7fb1a309 ]

Ben Hawkes says:

 In the mark_source_chains function (net/ipv4/netfilter/ip_tables.c) it
 is possible for a user-supplied ipt_entry structure to have a large
 next_offset field. This field is not bounds checked prior to writing a
 counter value at the supplied offset.

Problem is that mark_source_chains should not have been called --
the rule doesn't have a next entry, so its supposed to return
an absolute verdict of either ACCEPT or DROP.

However, the function conditional() doesn't work as the name implies.
It only checks that the rule is using wildcard address matching.

However, an unconditional rule must also not be using any matches
(no -m args).

The underflow validator only checked the addresses, therefore
passing the 'unconditional absolute verdict' test, while
mark_source_chains also tested for presence of matches, and thus
proceeeded to the next (not-existent) rule.

Unify this so that all the callers have same idea of 'unconditional rule'.

Reported-by: Ben Hawkes <hawkes@google.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/ipv4/netfilter/arp_tables.c | 18 +++++++++---------
 net/ipv4/netfilter/ip_tables.c  | 23 +++++++++++------------
 net/ipv6/netfilter/ip6_tables.c | 23 +++++++++++------------
 3 files changed, 31 insertions(+), 33 deletions(-)

diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 835b768..236dcd6 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -354,11 +354,12 @@ unsigned int arpt_do_table(struct sk_buff *skb,
 }
 
 /* All zeroes == unconditional rule. */
-static inline bool unconditional(const struct arpt_arp *arp)
+static inline bool unconditional(const struct arpt_entry *e)
 {
 	static const struct arpt_arp uncond;
 
-	return memcmp(arp, &uncond, sizeof(uncond)) == 0;
+	return e->target_offset == sizeof(struct arpt_entry) &&
+	       memcmp(&e->arp, &uncond, sizeof(uncond)) == 0;
 }
 
 /* Figures out from what hook each rule can be called: returns 0 if
@@ -397,11 +398,10 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
 				|= ((1 << hook) | (1 << NF_ARP_NUMHOOKS));
 
 			/* Unconditional return/END. */
-			if ((e->target_offset == sizeof(struct arpt_entry) &&
+			if ((unconditional(e) &&
 			     (strcmp(t->target.u.user.name,
 				     XT_STANDARD_TARGET) == 0) &&
-			     t->verdict < 0 && unconditional(&e->arp)) ||
-			    visited) {
+			     t->verdict < 0) || visited) {
 				unsigned int oldpos, size;
 
 				if ((strcmp(t->target.u.user.name,
@@ -540,7 +540,7 @@ static bool check_underflow(const struct arpt_entry *e)
 	const struct xt_entry_target *t;
 	unsigned int verdict;
 
-	if (!unconditional(&e->arp))
+	if (!unconditional(e))
 		return false;
 	t = arpt_get_target_c(e);
 	if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0)
@@ -587,9 +587,9 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e,
 			newinfo->hook_entry[h] = hook_entries[h];
 		if ((unsigned char *)e - base == underflows[h]) {
 			if (!check_underflow(e)) {
-				pr_err("Underflows must be unconditional and "
-				       "use the STANDARD target with "
-				       "ACCEPT/DROP\n");
+				pr_debug("Underflows must be unconditional and "
+					 "use the STANDARD target with "
+					 "ACCEPT/DROP\n");
 				return -EINVAL;
 			}
 			newinfo->underflow[h] = underflows[h];
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 4ad5576..b653b9d 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -168,11 +168,12 @@ get_entry(const void *base, unsigned int offset)
 
 /* All zeroes == unconditional rule. */
 /* Mildly perf critical (only if packet tracing is on) */
-static inline bool unconditional(const struct ipt_ip *ip)
+static inline bool unconditional(const struct ipt_entry *e)
 {
 	static const struct ipt_ip uncond;
 
-	return memcmp(ip, &uncond, sizeof(uncond)) == 0;
+	return e->target_offset == sizeof(struct ipt_entry) &&
+	       memcmp(&e->ip, &uncond, sizeof(uncond)) == 0;
 #undef FWINV
 }
 
@@ -229,11 +230,10 @@ get_chainname_rulenum(const struct ipt_entry *s, const struct ipt_entry *e,
 	} else if (s == e) {
 		(*rulenum)++;
 
-		if (s->target_offset == sizeof(struct ipt_entry) &&
+		if (unconditional(s) &&
 		    strcmp(t->target.u.kernel.target->name,
 			   XT_STANDARD_TARGET) == 0 &&
-		   t->verdict < 0 &&
-		   unconditional(&s->ip)) {
+		   t->verdict < 0) {
 			/* Tail of chains: STANDARD target (return/policy) */
 			*comment = *chainname == hookname
 				? comments[NF_IP_TRACE_COMMENT_POLICY]
@@ -471,11 +471,10 @@ mark_source_chains(const struct xt_table_info *newinfo,
 			e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS));
 
 			/* Unconditional return/END. */
-			if ((e->target_offset == sizeof(struct ipt_entry) &&
+			if ((unconditional(e) &&
 			     (strcmp(t->target.u.user.name,
 				     XT_STANDARD_TARGET) == 0) &&
-			     t->verdict < 0 && unconditional(&e->ip)) ||
-			    visited) {
+			     t->verdict < 0) || visited) {
 				unsigned int oldpos, size;
 
 				if ((strcmp(t->target.u.user.name,
@@ -702,7 +701,7 @@ static bool check_underflow(const struct ipt_entry *e)
 	const struct xt_entry_target *t;
 	unsigned int verdict;
 
-	if (!unconditional(&e->ip))
+	if (!unconditional(e))
 		return false;
 	t = ipt_get_target_c(e);
 	if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0)
@@ -750,9 +749,9 @@ check_entry_size_and_hooks(struct ipt_entry *e,
 			newinfo->hook_entry[h] = hook_entries[h];
 		if ((unsigned char *)e - base == underflows[h]) {
 			if (!check_underflow(e)) {
-				pr_err("Underflows must be unconditional and "
-				       "use the STANDARD target with "
-				       "ACCEPT/DROP\n");
+				pr_debug("Underflows must be unconditional and "
+					 "use the STANDARD target with "
+					 "ACCEPT/DROP\n");
 				return -EINVAL;
 			}
 			newinfo->underflow[h] = underflows[h];
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 9a4666b..077982a 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -198,11 +198,12 @@ get_entry(const void *base, unsigned int offset)
 
 /* All zeroes == unconditional rule. */
 /* Mildly perf critical (only if packet tracing is on) */
-static inline bool unconditional(const struct ip6t_ip6 *ipv6)
+static inline bool unconditional(const struct ip6t_entry *e)
 {
 	static const struct ip6t_ip6 uncond;
 
-	return memcmp(ipv6, &uncond, sizeof(uncond)) == 0;
+	return e->target_offset == sizeof(struct ip6t_entry) &&
+	       memcmp(&e->ipv6, &uncond, sizeof(uncond)) == 0;
 }
 
 static inline const struct xt_entry_target *
@@ -258,11 +259,10 @@ get_chainname_rulenum(const struct ip6t_entry *s, const struct ip6t_entry *e,
 	} else if (s == e) {
 		(*rulenum)++;
 
-		if (s->target_offset == sizeof(struct ip6t_entry) &&
+		if (unconditional(s) &&
 		    strcmp(t->target.u.kernel.target->name,
 			   XT_STANDARD_TARGET) == 0 &&
-		    t->verdict < 0 &&
-		    unconditional(&s->ipv6)) {
+		    t->verdict < 0) {
 			/* Tail of chains: STANDARD target (return/policy) */
 			*comment = *chainname == hookname
 				? comments[NF_IP6_TRACE_COMMENT_POLICY]
@@ -484,11 +484,10 @@ mark_source_chains(const struct xt_table_info *newinfo,
 			e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS));
 
 			/* Unconditional return/END. */
-			if ((e->target_offset == sizeof(struct ip6t_entry) &&
+			if ((unconditional(e) &&
 			     (strcmp(t->target.u.user.name,
 				     XT_STANDARD_TARGET) == 0) &&
-			     t->verdict < 0 &&
-			     unconditional(&e->ipv6)) || visited) {
+			     t->verdict < 0) || visited) {
 				unsigned int oldpos, size;
 
 				if ((strcmp(t->target.u.user.name,
@@ -716,7 +715,7 @@ static bool check_underflow(const struct ip6t_entry *e)
 	const struct xt_entry_target *t;
 	unsigned int verdict;
 
-	if (!unconditional(&e->ipv6))
+	if (!unconditional(e))
 		return false;
 	t = ip6t_get_target_c(e);
 	if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0)
@@ -764,9 +763,9 @@ check_entry_size_and_hooks(struct ip6t_entry *e,
 			newinfo->hook_entry[h] = hook_entries[h];
 		if ((unsigned char *)e - base == underflows[h]) {
 			if (!check_underflow(e)) {
-				pr_err("Underflows must be unconditional and "
-				       "use the STANDARD target with "
-				       "ACCEPT/DROP\n");
+				pr_debug("Underflows must be unconditional and "
+					 "use the STANDARD target with "
+					 "ACCEPT/DROP\n");
 				return -EINVAL;
 			}
 			newinfo->underflow[h] = underflows[h];
-- 
2.5.0

[added to the 4.1 stable tree] netfilter: x_tables: don't move to non-existent next rule

[Sasha Levin]

From: Florian Westphal <fw@strlen.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit f24e230d257af1ad7476c6e81a8dc3127a74204e ]

Ben Hawkes says:

 In the mark_source_chains function (net/ipv4/netfilter/ip_tables.c) it
 is possible for a user-supplied ipt_entry structure to have a large
 next_offset field. This field is not bounds checked prior to writing a
 counter value at the supplied offset.

Base chains enforce absolute verdict.

User defined chains are supposed to end with an unconditional return,
xtables userspace adds them automatically.

But if such return is missing we will move to non-existent next rule.

Reported-by: Ben Hawkes <hawkes@google.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/ipv4/netfilter/arp_tables.c | 8 +++++---
 net/ipv4/netfilter/ip_tables.c  | 4 ++++
 net/ipv6/netfilter/ip6_tables.c | 4 ++++
 3 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 236dcd6..d5305001 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -434,6 +434,8 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
 				size = e->next_offset;
 				e = (struct arpt_entry *)
 					(entry0 + pos + size);
+				if (pos + size >= newinfo->size)
+					return 0;
 				e->counters.pcnt = pos;
 				pos += size;
 			} else {
@@ -456,6 +458,8 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
 				} else {
 					/* ... this is a fallthru */
 					newpos = pos + e->next_offset;
+					if (newpos >= newinfo->size)
+						return 0;
 				}
 				e = (struct arpt_entry *)
 					(entry0 + newpos);
@@ -679,10 +683,8 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
 		}
 	}
 
-	if (!mark_source_chains(newinfo, repl->valid_hooks, entry0)) {
-		duprintf("Looping hook\n");
+	if (!mark_source_chains(newinfo, repl->valid_hooks, entry0))
 		return -ELOOP;
-	}
 
 	/* Finally, each sanity check must pass */
 	i = 0;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index b653b9d..aee8016 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -515,6 +515,8 @@ mark_source_chains(const struct xt_table_info *newinfo,
 				size = e->next_offset;
 				e = (struct ipt_entry *)
 					(entry0 + pos + size);
+				if (pos + size >= newinfo->size)
+					return 0;
 				e->counters.pcnt = pos;
 				pos += size;
 			} else {
@@ -536,6 +538,8 @@ mark_source_chains(const struct xt_table_info *newinfo,
 				} else {
 					/* ... this is a fallthru */
 					newpos = pos + e->next_offset;
+					if (newpos >= newinfo->size)
+						return 0;
 				}
 				e = (struct ipt_entry *)
 					(entry0 + newpos);
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 077982a..74d6ad0 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -528,6 +528,8 @@ mark_source_chains(const struct xt_table_info *newinfo,
 				size = e->next_offset;
 				e = (struct ip6t_entry *)
 					(entry0 + pos + size);
+				if (pos + size >= newinfo->size)
+					return 0;
 				e->counters.pcnt = pos;
 				pos += size;
 			} else {
@@ -549,6 +551,8 @@ mark_source_chains(const struct xt_table_info *newinfo,
 				} else {
 					/* ... this is a fallthru */
 					newpos = pos + e->next_offset;
+					if (newpos >= newinfo->size)
+						return 0;
 				}
 				e = (struct ip6t_entry *)
 					(entry0 + newpos);
-- 
2.5.0

[added to the 4.1 stable tree] netfilter: x_tables: validate targets of jumps

[Sasha Levin]

From: Florian Westphal <fw@strlen.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 36472341017529e2b12573093cc0f68719300997 ]

When we see a jump also check that the offset gets us to beginning of
a rule (an ipt_entry).

The extra overhead is negible, even with absurd cases.

300k custom rules, 300k jumps to 'next' user chain:
[ plus one jump from INPUT to first userchain ]:

Before:
real    0m24.874s
user    0m7.532s
sys     0m16.076s

After:
real    0m27.464s
user    0m7.436s
sys     0m18.840s

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/ipv4/netfilter/arp_tables.c | 16 ++++++++++++++++
 net/ipv4/netfilter/ip_tables.c  | 16 ++++++++++++++++
 net/ipv6/netfilter/ip6_tables.c | 16 ++++++++++++++++
 3 files changed, 48 insertions(+)

diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index d5305001..538839d 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -362,6 +362,18 @@ static inline bool unconditional(const struct arpt_entry *e)
 	       memcmp(&e->arp, &uncond, sizeof(uncond)) == 0;
 }
 
+static bool find_jump_target(const struct xt_table_info *t,
+			     const struct arpt_entry *target)
+{
+	struct arpt_entry *iter;
+
+	xt_entry_foreach(iter, t->entries, t->size) {
+		 if (iter == target)
+			return true;
+	}
+	return false;
+}
+
 /* Figures out from what hook each rule can be called: returns 0 if
  * there are loops.  Puts hook bitmask in comefrom.
  */
@@ -455,6 +467,10 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
 					/* This a jump; chase it. */
 					duprintf("Jump rule %u -> %u\n",
 						 pos, newpos);
+					e = (struct arpt_entry *)
+						(entry0 + newpos);
+					if (!find_jump_target(newinfo, e))
+						return 0;
 				} else {
 					/* ... this is a fallthru */
 					newpos = pos + e->next_offset;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index aee8016..ff7a5f3 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -438,6 +438,18 @@ ipt_do_table(struct sk_buff *skb,
 #endif
 }
 
+static bool find_jump_target(const struct xt_table_info *t,
+			     const struct ipt_entry *target)
+{
+	struct ipt_entry *iter;
+
+	xt_entry_foreach(iter, t->entries, t->size) {
+		 if (iter == target)
+			return true;
+	}
+	return false;
+}
+
 /* Figures out from what hook each rule can be called: returns 0 if
    there are loops.  Puts hook bitmask in comefrom. */
 static int
@@ -535,6 +547,10 @@ mark_source_chains(const struct xt_table_info *newinfo,
 					/* This a jump; chase it. */
 					duprintf("Jump rule %u -> %u\n",
 						 pos, newpos);
+					e = (struct ipt_entry *)
+						(entry0 + newpos);
+					if (!find_jump_target(newinfo, e))
+						return 0;
 				} else {
 					/* ... this is a fallthru */
 					newpos = pos + e->next_offset;
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 74d6ad0..18b455b 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -451,6 +451,18 @@ ip6t_do_table(struct sk_buff *skb,
 #endif
 }
 
+static bool find_jump_target(const struct xt_table_info *t,
+			     const struct ip6t_entry *target)
+{
+	struct ip6t_entry *iter;
+
+	xt_entry_foreach(iter, t->entries, t->size) {
+		 if (iter == target)
+			return true;
+	}
+	return false;
+}
+
 /* Figures out from what hook each rule can be called: returns 0 if
    there are loops.  Puts hook bitmask in comefrom. */
 static int
@@ -548,6 +560,10 @@ mark_source_chains(const struct xt_table_info *newinfo,
 					/* This a jump; chase it. */
 					duprintf("Jump rule %u -> %u\n",
 						 pos, newpos);
+					e = (struct ip6t_entry *)
+						(entry0 + newpos);
+					if (!find_jump_target(newinfo, e))
+						return 0;
 				} else {
 					/* ... this is a fallthru */
 					newpos = pos + e->next_offset;
-- 
2.5.0

[added to the 4.1 stable tree] netfilter: x_tables: add and use xt_check_entry_offsets

[Sasha Levin]

From: Florian Westphal <fw@strlen.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 7d35812c3214afa5b37a675113555259cfd67b98 ]

Currently arp/ip and ip6tables each implement a short helper to check that
the target offset is large enough to hold one xt_entry_target struct and
that t->u.target_size fits within the current rule.

Unfortunately these checks are not sufficient.

To avoid adding new tests to all of ip/ip6/arptables move the current
checks into a helper, then extend this helper in followup patches.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 include/linux/netfilter/x_tables.h |  4 ++++
 net/ipv4/netfilter/arp_tables.c    | 11 +----------
 net/ipv4/netfilter/ip_tables.c     | 12 +-----------
 net/ipv6/netfilter/ip6_tables.c    | 12 +-----------
 net/netfilter/x_tables.c           | 34 ++++++++++++++++++++++++++++++++++
 5 files changed, 41 insertions(+), 32 deletions(-)

diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index a3e215b..a2d1508 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -239,6 +239,10 @@ void xt_unregister_match(struct xt_match *target);
 int xt_register_matches(struct xt_match *match, unsigned int n);
 void xt_unregister_matches(struct xt_match *match, unsigned int n);
 
+int xt_check_entry_offsets(const void *base,
+			   unsigned int target_offset,
+			   unsigned int next_offset);
+
 int xt_check_match(struct xt_mtchk_param *, unsigned int size, u_int8_t proto,
 		   bool inv_proto);
 int xt_check_target(struct xt_tgchk_param *, unsigned int size, u_int8_t proto,
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 538839d..8c2d13c 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -491,19 +491,10 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
 
 static inline int check_entry(const struct arpt_entry *e)
 {
-	const struct xt_entry_target *t;
-
 	if (!arp_checkentry(&e->arp))
 		return -EINVAL;
 
-	if (e->target_offset + sizeof(struct xt_entry_target) > e->next_offset)
-		return -EINVAL;
-
-	t = arpt_get_target_c(e);
-	if (e->target_offset + t->u.target_size > e->next_offset)
-		return -EINVAL;
-
-	return 0;
+	return xt_check_entry_offsets(e, e->target_offset, e->next_offset);
 }
 
 static inline int check_target(struct arpt_entry *e, const char *name)
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index ff7a5f3..2a3f689 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -585,20 +585,10 @@ static void cleanup_match(struct xt_entry_match *m, struct net *net)
 static int
 check_entry(const struct ipt_entry *e)
 {
-	const struct xt_entry_target *t;
-
 	if (!ip_checkentry(&e->ip))
 		return -EINVAL;
 
-	if (e->target_offset + sizeof(struct xt_entry_target) >
-	    e->next_offset)
-		return -EINVAL;
-
-	t = ipt_get_target_c(e);
-	if (e->target_offset + t->u.target_size > e->next_offset)
-		return -EINVAL;
-
-	return 0;
+	return xt_check_entry_offsets(e, e->target_offset, e->next_offset);
 }
 
 static int
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 18b455b..a7de7c0 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -598,20 +598,10 @@ static void cleanup_match(struct xt_entry_match *m, struct net *net)
 static int
 check_entry(const struct ip6t_entry *e)
 {
-	const struct xt_entry_target *t;
-
 	if (!ip6_checkentry(&e->ipv6))
 		return -EINVAL;
 
-	if (e->target_offset + sizeof(struct xt_entry_target) >
-	    e->next_offset)
-		return -EINVAL;
-
-	t = ip6t_get_target_c(e);
-	if (e->target_offset + t->u.target_size > e->next_offset)
-		return -EINVAL;
-
-	return 0;
+	return xt_check_entry_offsets(e, e->target_offset, e->next_offset);
 }
 
 static int check_match(struct xt_entry_match *m, struct xt_mtchk_param *par)
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 51a459c..b631357 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -543,6 +543,40 @@ int xt_compat_match_to_user(const struct xt_entry_match *m,
 EXPORT_SYMBOL_GPL(xt_compat_match_to_user);
 #endif /* CONFIG_COMPAT */
 
+/**
+ * xt_check_entry_offsets - validate arp/ip/ip6t_entry
+ *
+ * @base: pointer to arp/ip/ip6t_entry
+ * @target_offset: the arp/ip/ip6_t->target_offset
+ * @next_offset: the arp/ip/ip6_t->next_offset
+ *
+ * validates that target_offset and next_offset are sane.
+ *
+ * The arp/ip/ip6t_entry structure @base must have passed following tests:
+ * - it must point to a valid memory location
+ * - base to base + next_offset must be accessible, i.e. not exceed allocated
+ *   length.
+ *
+ * Return: 0 on success, negative errno on failure.
+ */
+int xt_check_entry_offsets(const void *base,
+			   unsigned int target_offset,
+			   unsigned int next_offset)
+{
+	const struct xt_entry_target *t;
+	const char *e = base;
+
+	if (target_offset + sizeof(*t) > next_offset)
+		return -EINVAL;
+
+	t = (void *)(e + target_offset);
+	if (target_offset + t->u.target_size > next_offset)
+		return -EINVAL;
+
+	return 0;
+}
+EXPORT_SYMBOL(xt_check_entry_offsets);
+
 int xt_check_target(struct xt_tgchk_param *par,
 		    unsigned int size, u_int8_t proto, bool inv_proto)
 {
-- 
2.5.0

[added to the 4.1 stable tree] netfilter: x_tables: kill check_entry helper

[Sasha Levin]

From: Florian Westphal <fw@strlen.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit aa412ba225dd3bc36d404c28cdc3d674850d80d0 ]

Once we add more sanity testing to xt_check_entry_offsets it
becomes relvant if we're expecting a 32bit 'config_compat' blob
or a normal one.

Since we already have a lot of similar-named functions (check_entry,
compat_check_entry, find_and_check_entry, etc.) and the current
incarnation is short just fold its contents into the callers.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/ipv4/netfilter/arp_tables.c | 19 ++++++++-----------
 net/ipv4/netfilter/ip_tables.c  | 20 ++++++++------------
 net/ipv6/netfilter/ip6_tables.c | 20 ++++++++------------
 3 files changed, 24 insertions(+), 35 deletions(-)

diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 8c2d13c..a86aa8d 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -489,14 +489,6 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
 	return 1;
 }
 
-static inline int check_entry(const struct arpt_entry *e)
-{
-	if (!arp_checkentry(&e->arp))
-		return -EINVAL;
-
-	return xt_check_entry_offsets(e, e->target_offset, e->next_offset);
-}
-
 static inline int check_target(struct arpt_entry *e, const char *name)
 {
 	struct xt_entry_target *t = arpt_get_target(e);
@@ -586,7 +578,10 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e,
 		return -EINVAL;
 	}
 
-	err = check_entry(e);
+	if (!arp_checkentry(&e->arp))
+		return -EINVAL;
+
+	err = xt_check_entry_offsets(e, e->target_offset, e->next_offset);
 	if (err)
 		return err;
 
@@ -1248,8 +1243,10 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e,
 		return -EINVAL;
 	}
 
-	/* For purposes of check_entry casting the compat entry is fine */
-	ret = check_entry((struct arpt_entry *)e);
+	if (!arp_checkentry(&e->arp))
+		return -EINVAL;
+
+	ret = xt_check_entry_offsets(e, e->target_offset, e->next_offset);
 	if (ret)
 		return ret;
 
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 2a3f689..077d682 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -583,15 +583,6 @@ static void cleanup_match(struct xt_entry_match *m, struct net *net)
 }
 
 static int
-check_entry(const struct ipt_entry *e)
-{
-	if (!ip_checkentry(&e->ip))
-		return -EINVAL;
-
-	return xt_check_entry_offsets(e, e->target_offset, e->next_offset);
-}
-
-static int
 check_match(struct xt_entry_match *m, struct xt_mtchk_param *par)
 {
 	const struct ipt_ip *ip = par->entryinfo;
@@ -747,7 +738,10 @@ check_entry_size_and_hooks(struct ipt_entry *e,
 		return -EINVAL;
 	}
 
-	err = check_entry(e);
+	if (!ip_checkentry(&e->ip))
+		return -EINVAL;
+
+	err = xt_check_entry_offsets(e, e->target_offset, e->next_offset);
 	if (err)
 		return err;
 
@@ -1514,8 +1508,10 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e,
 		return -EINVAL;
 	}
 
-	/* For purposes of check_entry casting the compat entry is fine */
-	ret = check_entry((struct ipt_entry *)e);
+	if (!ip_checkentry(&e->ip))
+		return -EINVAL;
+
+	ret = xt_check_entry_offsets(e, e->target_offset, e->next_offset);
 	if (ret)
 		return ret;
 
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index a7de7c0..ca0c347 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -595,15 +595,6 @@ static void cleanup_match(struct xt_entry_match *m, struct net *net)
 	module_put(par.match->me);
 }
 
-static int
-check_entry(const struct ip6t_entry *e)
-{
-	if (!ip6_checkentry(&e->ipv6))
-		return -EINVAL;
-
-	return xt_check_entry_offsets(e, e->target_offset, e->next_offset);
-}
-
 static int check_match(struct xt_entry_match *m, struct xt_mtchk_param *par)
 {
 	const struct ip6t_ip6 *ipv6 = par->entryinfo;
@@ -761,7 +752,10 @@ check_entry_size_and_hooks(struct ip6t_entry *e,
 		return -EINVAL;
 	}
 
-	err = check_entry(e);
+	if (!ip6_checkentry(&e->ipv6))
+		return -EINVAL;
+
+	err = xt_check_entry_offsets(e, e->target_offset, e->next_offset);
 	if (err)
 		return err;
 
@@ -1529,8 +1523,10 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e,
 		return -EINVAL;
 	}
 
-	/* For purposes of check_entry casting the compat entry is fine */
-	ret = check_entry((struct ip6t_entry *)e);
+	if (!ip6_checkentry(&e->ipv6))
+		return -EINVAL;
+
+	ret = xt_check_entry_offsets(e, e->target_offset, e->next_offset);
 	if (ret)
 		return ret;
 
-- 
2.5.0

[added to the 4.1 stable tree] netfilter: x_tables: assert minimum target size

[Sasha Levin]

From: Florian Westphal <fw@strlen.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit a08e4e190b866579896c09af59b3bdca821da2cd ]

The target size includes the size of the xt_entry_target struct.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/netfilter/x_tables.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index b631357..ce9f7b3 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -570,6 +570,9 @@ int xt_check_entry_offsets(const void *base,
 		return -EINVAL;
 
 	t = (void *)(e + target_offset);
+	if (t->u.target_size < sizeof(*t))
+		return -EINVAL;
+
 	if (target_offset + t->u.target_size > next_offset)
 		return -EINVAL;
 
-- 
2.5.0

[added to the 4.1 stable tree] netfilter: x_tables: add compat version of xt_check_entry_offsets

[Sasha Levin]

From: Florian Westphal <fw@strlen.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit fc1221b3a163d1386d1052184202d5dc50d302d1 ]

32bit rulesets have different layout and alignment requirements, so once
more integrity checks get added to xt_check_entry_offsets it will reject
well-formed 32bit rulesets.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 include/linux/netfilter/x_tables.h |  3 +++
 net/ipv4/netfilter/arp_tables.c    |  3 ++-
 net/ipv4/netfilter/ip_tables.c     |  3 ++-
 net/ipv6/netfilter/ip6_tables.c    |  3 ++-
 net/netfilter/x_tables.c           | 22 ++++++++++++++++++++++
 5 files changed, 31 insertions(+), 3 deletions(-)

diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index a2d1508..81843aa 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -435,6 +435,9 @@ void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr,
 				unsigned int *size);
 int xt_compat_target_to_user(const struct xt_entry_target *t,
 			     void __user **dstptr, unsigned int *size);
+int xt_compat_check_entry_offsets(const void *base,
+				  unsigned int target_offset,
+				  unsigned int next_offset);
 
 #endif /* CONFIG_COMPAT */
 #endif /* _X_TABLES_H */
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index a86aa8d..d865edf 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -1246,7 +1246,8 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e,
 	if (!arp_checkentry(&e->arp))
 		return -EINVAL;
 
-	ret = xt_check_entry_offsets(e, e->target_offset, e->next_offset);
+	ret = xt_compat_check_entry_offsets(e, e->target_offset,
+					    e->next_offset);
 	if (ret)
 		return ret;
 
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 077d682..a355ebb 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1511,7 +1511,8 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e,
 	if (!ip_checkentry(&e->ip))
 		return -EINVAL;
 
-	ret = xt_check_entry_offsets(e, e->target_offset, e->next_offset);
+	ret = xt_compat_check_entry_offsets(e,
+					    e->target_offset, e->next_offset);
 	if (ret)
 		return ret;
 
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index ca0c347..7157bf5 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1526,7 +1526,8 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e,
 	if (!ip6_checkentry(&e->ipv6))
 		return -EINVAL;
 
-	ret = xt_check_entry_offsets(e, e->target_offset, e->next_offset);
+	ret = xt_compat_check_entry_offsets(e,
+					    e->target_offset, e->next_offset);
 	if (ret)
 		return ret;
 
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index ce9f7b3..a00ea2a 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -541,6 +541,27 @@ int xt_compat_match_to_user(const struct xt_entry_match *m,
 	return 0;
 }
 EXPORT_SYMBOL_GPL(xt_compat_match_to_user);
+
+int xt_compat_check_entry_offsets(const void *base,
+				  unsigned int target_offset,
+				  unsigned int next_offset)
+{
+	const struct compat_xt_entry_target *t;
+	const char *e = base;
+
+	if (target_offset + sizeof(*t) > next_offset)
+		return -EINVAL;
+
+	t = (void *)(e + target_offset);
+	if (t->u.target_size < sizeof(*t))
+		return -EINVAL;
+
+	if (target_offset + t->u.target_size > next_offset)
+		return -EINVAL;
+
+	return 0;
+}
+EXPORT_SYMBOL(xt_compat_check_entry_offsets);
 #endif /* CONFIG_COMPAT */
 
 /**
@@ -551,6 +572,7 @@ EXPORT_SYMBOL_GPL(xt_compat_match_to_user);
  * @next_offset: the arp/ip/ip6_t->next_offset
  *
  * validates that target_offset and next_offset are sane.
+ * Also see xt_compat_check_entry_offsets for CONFIG_COMPAT version.
  *
  * The arp/ip/ip6t_entry structure @base must have passed following tests:
  * - it must point to a valid memory location
-- 
2.5.0

[added to the 4.1 stable tree] netfilter: x_tables: check standard target size too

[Sasha Levin]

From: Florian Westphal <fw@strlen.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 7ed2abddd20cf8f6bd27f65bd218f26fa5bf7f44 ]

We have targets and standard targets -- the latter carries a verdict.

The ip/ip6tables validation functions will access t->verdict for the
standard targets to fetch the jump offset or verdict for chainloop
detection, but this happens before the targets get checked/validated.

Thus we also need to check for verdict presence here, else t->verdict
can point right after a blob.

Spotted with UBSAN while testing malformed blobs.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/netfilter/x_tables.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index a00ea2a..6b64441 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -542,6 +542,13 @@ int xt_compat_match_to_user(const struct xt_entry_match *m,
 }
 EXPORT_SYMBOL_GPL(xt_compat_match_to_user);
 
+/* non-compat version may have padding after verdict */
+struct compat_xt_standard_target {
+	struct compat_xt_entry_target t;
+	compat_uint_t verdict;
+};
+
+/* see xt_check_entry_offsets */
 int xt_compat_check_entry_offsets(const void *base,
 				  unsigned int target_offset,
 				  unsigned int next_offset)
@@ -559,6 +566,10 @@ int xt_compat_check_entry_offsets(const void *base,
 	if (target_offset + t->u.target_size > next_offset)
 		return -EINVAL;
 
+	if (strcmp(t->u.user.name, XT_STANDARD_TARGET) == 0 &&
+	    target_offset + sizeof(struct compat_xt_standard_target) != next_offset)
+		return -EINVAL;
+
 	return 0;
 }
 EXPORT_SYMBOL(xt_compat_check_entry_offsets);
@@ -598,6 +609,10 @@ int xt_check_entry_offsets(const void *base,
 	if (target_offset + t->u.target_size > next_offset)
 		return -EINVAL;
 
+	if (strcmp(t->u.user.name, XT_STANDARD_TARGET) == 0 &&
+	    target_offset + sizeof(struct xt_standard_target) != next_offset)
+		return -EINVAL;
+
 	return 0;
 }
 EXPORT_SYMBOL(xt_check_entry_offsets);
-- 
2.5.0

[added to the 4.1 stable tree] netfilter: x_tables: check for bogus target offset

[Sasha Levin]

From: Florian Westphal <fw@strlen.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit ce683e5f9d045e5d67d1312a42b359cb2ab2a13c ]

We're currently asserting that targetoff + targetsize <= nextoff.

Extend it to also check that targetoff is >= sizeof(xt_entry).
Since this is generic code, add an argument pointing to the start of the
match/target, we can then derive the base structure size from the delta.

We also need the e->elems pointer in a followup change to validate matches.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 include/linux/netfilter/x_tables.h |  4 ++--
 net/ipv4/netfilter/arp_tables.c    |  5 +++--
 net/ipv4/netfilter/ip_tables.c     |  5 +++--
 net/ipv6/netfilter/ip6_tables.c    |  5 +++--
 net/netfilter/x_tables.c           | 17 +++++++++++++++--
 5 files changed, 26 insertions(+), 10 deletions(-)

diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index 81843aa..726f4dd 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -239,7 +239,7 @@ void xt_unregister_match(struct xt_match *target);
 int xt_register_matches(struct xt_match *match, unsigned int n);
 void xt_unregister_matches(struct xt_match *match, unsigned int n);
 
-int xt_check_entry_offsets(const void *base,
+int xt_check_entry_offsets(const void *base, const char *elems,
 			   unsigned int target_offset,
 			   unsigned int next_offset);
 
@@ -435,7 +435,7 @@ void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr,
 				unsigned int *size);
 int xt_compat_target_to_user(const struct xt_entry_target *t,
 			     void __user **dstptr, unsigned int *size);
-int xt_compat_check_entry_offsets(const void *base,
+int xt_compat_check_entry_offsets(const void *base, const char *elems,
 				  unsigned int target_offset,
 				  unsigned int next_offset);
 
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index d865edf..53315ee 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -581,7 +581,8 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e,
 	if (!arp_checkentry(&e->arp))
 		return -EINVAL;
 
-	err = xt_check_entry_offsets(e, e->target_offset, e->next_offset);
+	err = xt_check_entry_offsets(e, e->elems, e->target_offset,
+				     e->next_offset);
 	if (err)
 		return err;
 
@@ -1246,7 +1247,7 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e,
 	if (!arp_checkentry(&e->arp))
 		return -EINVAL;
 
-	ret = xt_compat_check_entry_offsets(e, e->target_offset,
+	ret = xt_compat_check_entry_offsets(e, e->elems, e->target_offset,
 					    e->next_offset);
 	if (ret)
 		return ret;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index a355ebb..fb00670 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -741,7 +741,8 @@ check_entry_size_and_hooks(struct ipt_entry *e,
 	if (!ip_checkentry(&e->ip))
 		return -EINVAL;
 
-	err = xt_check_entry_offsets(e, e->target_offset, e->next_offset);
+	err = xt_check_entry_offsets(e, e->elems, e->target_offset,
+				     e->next_offset);
 	if (err)
 		return err;
 
@@ -1511,7 +1512,7 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e,
 	if (!ip_checkentry(&e->ip))
 		return -EINVAL;
 
-	ret = xt_compat_check_entry_offsets(e,
+	ret = xt_compat_check_entry_offsets(e, e->elems,
 					    e->target_offset, e->next_offset);
 	if (ret)
 		return ret;
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 7157bf5..c09dbcc 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -755,7 +755,8 @@ check_entry_size_and_hooks(struct ip6t_entry *e,
 	if (!ip6_checkentry(&e->ipv6))
 		return -EINVAL;
 
-	err = xt_check_entry_offsets(e, e->target_offset, e->next_offset);
+	err = xt_check_entry_offsets(e, e->elems, e->target_offset,
+				     e->next_offset);
 	if (err)
 		return err;
 
@@ -1526,7 +1527,7 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e,
 	if (!ip6_checkentry(&e->ipv6))
 		return -EINVAL;
 
-	ret = xt_compat_check_entry_offsets(e,
+	ret = xt_compat_check_entry_offsets(e, e->elems,
 					    e->target_offset, e->next_offset);
 	if (ret)
 		return ret;
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 6b64441..bd7fd79 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -548,14 +548,17 @@ struct compat_xt_standard_target {
 	compat_uint_t verdict;
 };
 
-/* see xt_check_entry_offsets */
-int xt_compat_check_entry_offsets(const void *base,
+int xt_compat_check_entry_offsets(const void *base, const char *elems,
 				  unsigned int target_offset,
 				  unsigned int next_offset)
 {
+	long size_of_base_struct = elems - (const char *)base;
 	const struct compat_xt_entry_target *t;
 	const char *e = base;
 
+	if (target_offset < size_of_base_struct)
+		return -EINVAL;
+
 	if (target_offset + sizeof(*t) > next_offset)
 		return -EINVAL;
 
@@ -579,12 +582,16 @@ EXPORT_SYMBOL(xt_compat_check_entry_offsets);
  * xt_check_entry_offsets - validate arp/ip/ip6t_entry
  *
  * @base: pointer to arp/ip/ip6t_entry
+ * @elems: pointer to first xt_entry_match, i.e. ip(6)t_entry->elems
  * @target_offset: the arp/ip/ip6_t->target_offset
  * @next_offset: the arp/ip/ip6_t->next_offset
  *
  * validates that target_offset and next_offset are sane.
  * Also see xt_compat_check_entry_offsets for CONFIG_COMPAT version.
  *
+ * This function does not validate the targets or matches themselves, it
+ * only tests that all the offsets and sizes are correct.
+ *
  * The arp/ip/ip6t_entry structure @base must have passed following tests:
  * - it must point to a valid memory location
  * - base to base + next_offset must be accessible, i.e. not exceed allocated
@@ -593,12 +600,18 @@ EXPORT_SYMBOL(xt_compat_check_entry_offsets);
  * Return: 0 on success, negative errno on failure.
  */
 int xt_check_entry_offsets(const void *base,
+			   const char *elems,
 			   unsigned int target_offset,
 			   unsigned int next_offset)
 {
+	long size_of_base_struct = elems - (const char *)base;
 	const struct xt_entry_target *t;
 	const char *e = base;
 
+	/* target start is within the ip/ip6/arpt_entry struct */
+	if (target_offset < size_of_base_struct)
+		return -EINVAL;
+
 	if (target_offset + sizeof(*t) > next_offset)
 		return -EINVAL;
 
-- 
2.5.0

[added to the 4.1 stable tree] netfilter: x_tables: validate all offsets and sizes in a rule

[Sasha Levin]

From: Florian Westphal <fw@strlen.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 13631bfc604161a9d69cd68991dff8603edd66f9 ]

Validate that all matches (if any) add up to the beginning of
the target and that each match covers at least the base structure size.

The compat path should be able to safely re-use the function
as the structures only differ in alignment; added a
BUILD_BUG_ON just in case we have an arch that adds padding as well.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/netfilter/x_tables.c | 81 +++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 76 insertions(+), 5 deletions(-)

diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index bd7fd79..467cead 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -418,6 +418,47 @@ int xt_check_match(struct xt_mtchk_param *par,
 }
 EXPORT_SYMBOL_GPL(xt_check_match);
 
+/** xt_check_entry_match - check that matches end before start of target
+ *
+ * @match: beginning of xt_entry_match
+ * @target: beginning of this rules target (alleged end of matches)
+ * @alignment: alignment requirement of match structures
+ *
+ * Validates that all matches add up to the beginning of the target,
+ * and that each match covers at least the base structure size.
+ *
+ * Return: 0 on success, negative errno on failure.
+ */
+static int xt_check_entry_match(const char *match, const char *target,
+				const size_t alignment)
+{
+	const struct xt_entry_match *pos;
+	int length = target - match;
+
+	if (length == 0) /* no matches */
+		return 0;
+
+	pos = (struct xt_entry_match *)match;
+	do {
+		if ((unsigned long)pos % alignment)
+			return -EINVAL;
+
+		if (length < (int)sizeof(struct xt_entry_match))
+			return -EINVAL;
+
+		if (pos->u.match_size < sizeof(struct xt_entry_match))
+			return -EINVAL;
+
+		if (pos->u.match_size > length)
+			return -EINVAL;
+
+		length -= pos->u.match_size;
+		pos = ((void *)((char *)(pos) + (pos)->u.match_size));
+	} while (length > 0);
+
+	return 0;
+}
+
 #ifdef CONFIG_COMPAT
 int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta)
 {
@@ -573,7 +614,14 @@ int xt_compat_check_entry_offsets(const void *base, const char *elems,
 	    target_offset + sizeof(struct compat_xt_standard_target) != next_offset)
 		return -EINVAL;
 
-	return 0;
+	/* compat_xt_entry match has less strict aligment requirements,
+	 * otherwise they are identical.  In case of padding differences
+	 * we need to add compat version of xt_check_entry_match.
+	 */
+	BUILD_BUG_ON(sizeof(struct compat_xt_entry_match) != sizeof(struct xt_entry_match));
+
+	return xt_check_entry_match(elems, base + target_offset,
+				    __alignof__(struct compat_xt_entry_match));
 }
 EXPORT_SYMBOL(xt_compat_check_entry_offsets);
 #endif /* CONFIG_COMPAT */
@@ -586,17 +634,39 @@ EXPORT_SYMBOL(xt_compat_check_entry_offsets);
  * @target_offset: the arp/ip/ip6_t->target_offset
  * @next_offset: the arp/ip/ip6_t->next_offset
  *
- * validates that target_offset and next_offset are sane.
- * Also see xt_compat_check_entry_offsets for CONFIG_COMPAT version.
+ * validates that target_offset and next_offset are sane and that all
+ * match sizes (if any) align with the target offset.
  *
  * This function does not validate the targets or matches themselves, it
- * only tests that all the offsets and sizes are correct.
+ * only tests that all the offsets and sizes are correct, that all
+ * match structures are aligned, and that the last structure ends where
+ * the target structure begins.
+ *
+ * Also see xt_compat_check_entry_offsets for CONFIG_COMPAT version.
  *
  * The arp/ip/ip6t_entry structure @base must have passed following tests:
  * - it must point to a valid memory location
  * - base to base + next_offset must be accessible, i.e. not exceed allocated
  *   length.
  *
+ * A well-formed entry looks like this:
+ *
+ * ip(6)t_entry   match [mtdata]  match [mtdata] target [tgdata] ip(6)t_entry
+ * e->elems[]-----'                              |               |
+ *                matchsize                      |               |
+ *                                matchsize      |               |
+ *                                               |               |
+ * target_offset---------------------------------'               |
+ * next_offset---------------------------------------------------'
+ *
+ * elems[]: flexible array member at end of ip(6)/arpt_entry struct.
+ *          This is where matches (if any) and the target reside.
+ * target_offset: beginning of target.
+ * next_offset: start of the next rule; also: size of this rule.
+ * Since targets have a minimum size, target_offset + minlen <= next_offset.
+ *
+ * Every match stores its size, sum of sizes must not exceed target_offset.
+ *
  * Return: 0 on success, negative errno on failure.
  */
 int xt_check_entry_offsets(const void *base,
@@ -626,7 +696,8 @@ int xt_check_entry_offsets(const void *base,
 	    target_offset + sizeof(struct xt_standard_target) != next_offset)
 		return -EINVAL;
 
-	return 0;
+	return xt_check_entry_match(elems, base + target_offset,
+				    __alignof__(struct xt_entry_match));
 }
 EXPORT_SYMBOL(xt_check_entry_offsets);
 
-- 
2.5.0

[added to the 4.1 stable tree] netfilter: x_tables: don't reject valid target size on some architectures

[Sasha Levin]

From: Florian Westphal <fw@strlen.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 7b7eba0f3515fca3296b8881d583f7c1042f5226 ]

Quoting John Stultz:
  In updating a 32bit arm device from 4.6 to Linus' current HEAD, I
  noticed I was having some trouble with networking, and realized that
  /proc/net/ip_tables_names was suddenly empty.
  Digging through the registration process, it seems we're catching on the:

   if (strcmp(t->u.user.name, XT_STANDARD_TARGET) == 0 &&
       target_offset + sizeof(struct xt_standard_target) != next_offset)
         return -EINVAL;

  Where next_offset seems to be 4 bytes larger then the
  offset + standard_target struct size.

next_offset needs to be aligned via XT_ALIGN (so we can access all members
of ip(6)t_entry struct).

This problem didn't show up on i686 as it only needs 4-byte alignment for
u64, but iptables userspace on other 32bit arches does insert extra padding.

Reported-by: John Stultz <john.stultz@linaro.org>
Tested-by: John Stultz <john.stultz@linaro.org>
Fixes: 7ed2abddd20cf ("netfilter: x_tables: check standard target size too")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/netfilter/x_tables.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 467cead..5e5cc45 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -611,7 +611,7 @@ int xt_compat_check_entry_offsets(const void *base, const char *elems,
 		return -EINVAL;
 
 	if (strcmp(t->u.user.name, XT_STANDARD_TARGET) == 0 &&
-	    target_offset + sizeof(struct compat_xt_standard_target) != next_offset)
+	    COMPAT_XT_ALIGN(target_offset + sizeof(struct compat_xt_standard_target)) != next_offset)
 		return -EINVAL;
 
 	/* compat_xt_entry match has less strict aligment requirements,
@@ -693,7 +693,7 @@ int xt_check_entry_offsets(const void *base,
 		return -EINVAL;
 
 	if (strcmp(t->u.user.name, XT_STANDARD_TARGET) == 0 &&
-	    target_offset + sizeof(struct xt_standard_target) != next_offset)
+	    XT_ALIGN(target_offset + sizeof(struct xt_standard_target)) != next_offset)
 		return -EINVAL;
 
 	return xt_check_entry_match(elems, base + target_offset,
-- 
2.5.0

[added to the 4.1 stable tree] netfilter: arp_tables: simplify translate_compat_table args

[Sasha Levin]

From: Florian Westphal <fw@strlen.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 8dddd32756f6fe8e4e82a63361119b7e2384e02f ]

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/ipv4/netfilter/arp_tables.c | 82 ++++++++++++++++++-----------------------
 1 file changed, 36 insertions(+), 46 deletions(-)

diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 53315ee..aca12b8 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -1206,6 +1206,18 @@ static int do_add_counters(struct net *net, const void __user *user,
 }
 
 #ifdef CONFIG_COMPAT
+struct compat_arpt_replace {
+	char				name[XT_TABLE_MAXNAMELEN];
+	u32				valid_hooks;
+	u32				num_entries;
+	u32				size;
+	u32				hook_entry[NF_ARP_NUMHOOKS];
+	u32				underflow[NF_ARP_NUMHOOKS];
+	u32				num_counters;
+	compat_uptr_t			counters;
+	struct compat_arpt_entry	entries[0];
+};
+
 static inline void compat_release_entry(struct compat_arpt_entry *e)
 {
 	struct xt_entry_target *t;
@@ -1221,8 +1233,7 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e,
 				  const unsigned char *base,
 				  const unsigned char *limit,
 				  const unsigned int *hook_entries,
-				  const unsigned int *underflows,
-				  const char *name)
+				  const unsigned int *underflows)
 {
 	struct xt_entry_target *t;
 	struct xt_target *target;
@@ -1293,7 +1304,7 @@ out:
 
 static int
 compat_copy_entry_from_user(struct compat_arpt_entry *e, void **dstptr,
-			    unsigned int *size, const char *name,
+			    unsigned int *size,
 			    struct xt_table_info *newinfo, unsigned char *base)
 {
 	struct xt_entry_target *t;
@@ -1326,14 +1337,9 @@ compat_copy_entry_from_user(struct compat_arpt_entry *e, void **dstptr,
 	return ret;
 }
 
-static int translate_compat_table(const char *name,
-				  unsigned int valid_hooks,
-				  struct xt_table_info **pinfo,
+static int translate_compat_table(struct xt_table_info **pinfo,
 				  void **pentry0,
-				  unsigned int total_size,
-				  unsigned int number,
-				  unsigned int *hook_entries,
-				  unsigned int *underflows)
+				  const struct compat_arpt_replace *compatr)
 {
 	unsigned int i, j;
 	struct xt_table_info *newinfo, *info;
@@ -1345,8 +1351,8 @@ static int translate_compat_table(const char *name,
 
 	info = *pinfo;
 	entry0 = *pentry0;
-	size = total_size;
-	info->number = number;
+	size = compatr->size;
+	info->number = compatr->num_entries;
 
 	/* Init all hooks to impossible value. */
 	for (i = 0; i < NF_ARP_NUMHOOKS; i++) {
@@ -1357,40 +1363,39 @@ static int translate_compat_table(const char *name,
 	duprintf("translate_compat_table: size %u\n", info->size);
 	j = 0;
 	xt_compat_lock(NFPROTO_ARP);
-	xt_compat_init_offsets(NFPROTO_ARP, number);
+	xt_compat_init_offsets(NFPROTO_ARP, compatr->num_entries);
 	/* Walk through entries, checking offsets. */
-	xt_entry_foreach(iter0, entry0, total_size) {
+	xt_entry_foreach(iter0, entry0, compatr->size) {
 		ret = check_compat_entry_size_and_hooks(iter0, info, &size,
 							entry0,
-							entry0 + total_size,
-							hook_entries,
-							underflows,
-							name);
+							entry0 + compatr->size,
+							compatr->hook_entry,
+							compatr->underflow);
 		if (ret != 0)
 			goto out_unlock;
 		++j;
 	}
 
 	ret = -EINVAL;
-	if (j != number) {
+	if (j != compatr->num_entries) {
 		duprintf("translate_compat_table: %u not %u entries\n",
-			 j, number);
+			 j, compatr->num_entries);
 		goto out_unlock;
 	}
 
 	/* Check hooks all assigned */
 	for (i = 0; i < NF_ARP_NUMHOOKS; i++) {
 		/* Only hooks which are valid */
-		if (!(valid_hooks & (1 << i)))
+		if (!(compatr->valid_hooks & (1 << i)))
 			continue;
 		if (info->hook_entry[i] == 0xFFFFFFFF) {
 			duprintf("Invalid hook entry %u %u\n",
-				 i, hook_entries[i]);
+				 i, info->hook_entry[i]);
 			goto out_unlock;
 		}
 		if (info->underflow[i] == 0xFFFFFFFF) {
 			duprintf("Invalid underflow %u %u\n",
-				 i, underflows[i]);
+				 i, info->underflow[i]);
 			goto out_unlock;
 		}
 	}
@@ -1400,17 +1405,17 @@ static int translate_compat_table(const char *name,
 	if (!newinfo)
 		goto out_unlock;
 
-	newinfo->number = number;
+	newinfo->number = compatr->num_entries;
 	for (i = 0; i < NF_ARP_NUMHOOKS; i++) {
 		newinfo->hook_entry[i] = info->hook_entry[i];
 		newinfo->underflow[i] = info->underflow[i];
 	}
 	entry1 = newinfo->entries[raw_smp_processor_id()];
 	pos = entry1;
-	size = total_size;
-	xt_entry_foreach(iter0, entry0, total_size) {
+	size = compatr->size;
+	xt_entry_foreach(iter0, entry0, compatr->size) {
 		ret = compat_copy_entry_from_user(iter0, &pos, &size,
-						  name, newinfo, entry1);
+						  newinfo, entry1);
 		if (ret != 0)
 			break;
 	}
@@ -1420,12 +1425,12 @@ static int translate_compat_table(const char *name,
 		goto free_newinfo;
 
 	ret = -ELOOP;
-	if (!mark_source_chains(newinfo, valid_hooks, entry1))
+	if (!mark_source_chains(newinfo, compatr->valid_hooks, entry1))
 		goto free_newinfo;
 
 	i = 0;
 	xt_entry_foreach(iter1, entry1, newinfo->size) {
-		ret = check_target(iter1, name);
+		ret = check_target(iter1, compatr->name);
 		if (ret != 0)
 			break;
 		++i;
@@ -1470,7 +1475,7 @@ static int translate_compat_table(const char *name,
 free_newinfo:
 	xt_free_table_info(newinfo);
 out:
-	xt_entry_foreach(iter0, entry0, total_size) {
+	xt_entry_foreach(iter0, entry0, compatr->size) {
 		if (j-- == 0)
 			break;
 		compat_release_entry(iter0);
@@ -1482,18 +1487,6 @@ out_unlock:
 	goto out;
 }
 
-struct compat_arpt_replace {
-	char				name[XT_TABLE_MAXNAMELEN];
-	u32				valid_hooks;
-	u32				num_entries;
-	u32				size;
-	u32				hook_entry[NF_ARP_NUMHOOKS];
-	u32				underflow[NF_ARP_NUMHOOKS];
-	u32				num_counters;
-	compat_uptr_t			counters;
-	struct compat_arpt_entry	entries[0];
-};
-
 static int compat_do_replace(struct net *net, void __user *user,
 			     unsigned int len)
 {
@@ -1527,10 +1520,7 @@ static int compat_do_replace(struct net *net, void __user *user,
 		goto free_newinfo;
 	}
 
-	ret = translate_compat_table(tmp.name, tmp.valid_hooks,
-				     &newinfo, &loc_cpu_entry, tmp.size,
-				     tmp.num_entries, tmp.hook_entry,
-				     tmp.underflow);
+	ret = translate_compat_table(&newinfo, &loc_cpu_entry, &tmp);
 	if (ret != 0)
 		goto free_newinfo;
 
-- 
2.5.0

[added to the 4.1 stable tree] netfilter: ip_tables: simplify translate_compat_table args

[Sasha Levin]

From: Florian Westphal <fw@strlen.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 7d3f843eed29222254c9feab481f55175a1afcc9 ]

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/ipv4/netfilter/ip_tables.c | 61 +++++++++++++++++-------------------------
 1 file changed, 25 insertions(+), 36 deletions(-)

diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index fb00670..e4c0a27 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1446,7 +1446,6 @@ compat_copy_entry_to_user(struct ipt_entry *e, void __user **dstptr,
 
 static int
 compat_find_calc_match(struct xt_entry_match *m,
-		       const char *name,
 		       const struct ipt_ip *ip,
 		       unsigned int hookmask,
 		       int *size)
@@ -1484,8 +1483,7 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e,
 				  const unsigned char *base,
 				  const unsigned char *limit,
 				  const unsigned int *hook_entries,
-				  const unsigned int *underflows,
-				  const char *name)
+				  const unsigned int *underflows)
 {
 	struct xt_entry_match *ematch;
 	struct xt_entry_target *t;
@@ -1521,8 +1519,8 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e,
 	entry_offset = (void *)e - (void *)base;
 	j = 0;
 	xt_ematch_foreach(ematch, e) {
-		ret = compat_find_calc_match(ematch, name,
-					     &e->ip, e->comefrom, &off);
+		ret = compat_find_calc_match(ematch, &e->ip, e->comefrom,
+					     &off);
 		if (ret != 0)
 			goto release_matches;
 		++j;
@@ -1571,7 +1569,7 @@ release_matches:
 
 static int
 compat_copy_entry_from_user(struct compat_ipt_entry *e, void **dstptr,
-			    unsigned int *size, const char *name,
+			    unsigned int *size,
 			    struct xt_table_info *newinfo, unsigned char *base)
 {
 	struct xt_entry_target *t;
@@ -1647,14 +1645,9 @@ compat_check_entry(struct ipt_entry *e, struct net *net, const char *name)
 
 static int
 translate_compat_table(struct net *net,
-		       const char *name,
-		       unsigned int valid_hooks,
 		       struct xt_table_info **pinfo,
 		       void **pentry0,
-		       unsigned int total_size,
-		       unsigned int number,
-		       unsigned int *hook_entries,
-		       unsigned int *underflows)
+		       const struct compat_ipt_replace *compatr)
 {
 	unsigned int i, j;
 	struct xt_table_info *newinfo, *info;
@@ -1666,8 +1659,8 @@ translate_compat_table(struct net *net,
 
 	info = *pinfo;
 	entry0 = *pentry0;
-	size = total_size;
-	info->number = number;
+	size = compatr->size;
+	info->number = compatr->num_entries;
 
 	/* Init all hooks to impossible value. */
 	for (i = 0; i < NF_INET_NUMHOOKS; i++) {
@@ -1678,40 +1671,39 @@ translate_compat_table(struct net *net,
 	duprintf("translate_compat_table: size %u\n", info->size);
 	j = 0;
 	xt_compat_lock(AF_INET);
-	xt_compat_init_offsets(AF_INET, number);
+	xt_compat_init_offsets(AF_INET, compatr->num_entries);
 	/* Walk through entries, checking offsets. */
-	xt_entry_foreach(iter0, entry0, total_size) {
+	xt_entry_foreach(iter0, entry0, compatr->size) {
 		ret = check_compat_entry_size_and_hooks(iter0, info, &size,
 							entry0,
-							entry0 + total_size,
-							hook_entries,
-							underflows,
-							name);
+							entry0 + compatr->size,
+							compatr->hook_entry,
+							compatr->underflow);
 		if (ret != 0)
 			goto out_unlock;
 		++j;
 	}
 
 	ret = -EINVAL;
-	if (j != number) {
+	if (j != compatr->num_entries) {
 		duprintf("translate_compat_table: %u not %u entries\n",
-			 j, number);
+			 j, compatr->num_entries);
 		goto out_unlock;
 	}
 
 	/* Check hooks all assigned */
 	for (i = 0; i < NF_INET_NUMHOOKS; i++) {
 		/* Only hooks which are valid */
-		if (!(valid_hooks & (1 << i)))
+		if (!(compatr->valid_hooks & (1 << i)))
 			continue;
 		if (info->hook_entry[i] == 0xFFFFFFFF) {
 			duprintf("Invalid hook entry %u %u\n",
-				 i, hook_entries[i]);
+				 i, info->hook_entry[i]);
 			goto out_unlock;
 		}
 		if (info->underflow[i] == 0xFFFFFFFF) {
 			duprintf("Invalid underflow %u %u\n",
-				 i, underflows[i]);
+				 i, info->underflow[i]);
 			goto out_unlock;
 		}
 	}
@@ -1721,17 +1713,17 @@ translate_compat_table(struct net *net,
 	if (!newinfo)
 		goto out_unlock;
 
-	newinfo->number = number;
+	newinfo->number = compatr->num_entries;
 	for (i = 0; i < NF_INET_NUMHOOKS; i++) {
 		newinfo->hook_entry[i] = info->hook_entry[i];
 		newinfo->underflow[i] = info->underflow[i];
 	}
 	entry1 = newinfo->entries[raw_smp_processor_id()];
 	pos = entry1;
-	size = total_size;
-	xt_entry_foreach(iter0, entry0, total_size) {
+	size = compatr->size;
+	xt_entry_foreach(iter0, entry0, compatr->size) {
 		ret = compat_copy_entry_from_user(iter0, &pos, &size,
-						  name, newinfo, entry1);
+						  newinfo, entry1);
 		if (ret != 0)
 			break;
 	}
@@ -1741,12 +1733,12 @@ translate_compat_table(struct net *net,
 		goto free_newinfo;
 
 	ret = -ELOOP;
-	if (!mark_source_chains(newinfo, valid_hooks, entry1))
+	if (!mark_source_chains(newinfo, compatr->valid_hooks, entry1))
 		goto free_newinfo;
 
 	i = 0;
 	xt_entry_foreach(iter1, entry1, newinfo->size) {
-		ret = compat_check_entry(iter1, net, name);
+		ret = compat_check_entry(iter1, net, compatr->name);
 		if (ret != 0)
 			break;
 		++i;
@@ -1791,7 +1783,7 @@ translate_compat_table(struct net *net,
 free_newinfo:
 	xt_free_table_info(newinfo);
 out:
-	xt_entry_foreach(iter0, entry0, total_size) {
+	xt_entry_foreach(iter0, entry0, compatr->size) {
 		if (j-- == 0)
 			break;
 		compat_release_entry(iter0);
@@ -1837,10 +1829,7 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len)
 		goto free_newinfo;
 	}
 
-	ret = translate_compat_table(net, tmp.name, tmp.valid_hooks,
-				     &newinfo, &loc_cpu_entry, tmp.size,
-				     tmp.num_entries, tmp.hook_entry,
-				     tmp.underflow);
+	ret = translate_compat_table(net, &newinfo, &loc_cpu_entry, &tmp);
 	if (ret != 0)
 		goto free_newinfo;
 
-- 
2.5.0

[added to the 4.1 stable tree] netfilter: ip6_tables: simplify translate_compat_table args

[Sasha Levin]

From: Florian Westphal <fw@strlen.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 329a0807124f12fe1c8032f95d8a8eb47047fb0e ]

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/ipv6/netfilter/ip6_tables.c | 61 +++++++++++++++++------------------------
 1 file changed, 25 insertions(+), 36 deletions(-)

diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index c09dbcc..0c34c08 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1461,7 +1461,6 @@ compat_copy_entry_to_user(struct ip6t_entry *e, void __user **dstptr,
 
 static int
 compat_find_calc_match(struct xt_entry_match *m,
-		       const char *name,
 		       const struct ip6t_ip6 *ipv6,
 		       unsigned int hookmask,
 		       int *size)
@@ -1499,8 +1498,7 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e,
 				  const unsigned char *base,
 				  const unsigned char *limit,
 				  const unsigned int *hook_entries,
-				  const unsigned int *underflows,
-				  const char *name)
+				  const unsigned int *underflows)
 {
 	struct xt_entry_match *ematch;
 	struct xt_entry_target *t;
@@ -1536,8 +1534,8 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e,
 	entry_offset = (void *)e - (void *)base;
 	j = 0;
 	xt_ematch_foreach(ematch, e) {
-		ret = compat_find_calc_match(ematch, name,
-					     &e->ipv6, e->comefrom, &off);
+		ret = compat_find_calc_match(ematch, &e->ipv6, e->comefrom,
+					     &off);
 		if (ret != 0)
 			goto release_matches;
 		++j;
@@ -1586,7 +1584,7 @@ release_matches:
 
 static int
 compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr,
-			    unsigned int *size, const char *name,
+			    unsigned int *size,
 			    struct xt_table_info *newinfo, unsigned char *base)
 {
 	struct xt_entry_target *t;
@@ -1660,14 +1658,9 @@ static int compat_check_entry(struct ip6t_entry *e, struct net *net,
 
 static int
 translate_compat_table(struct net *net,
-		       const char *name,
-		       unsigned int valid_hooks,
 		       struct xt_table_info **pinfo,
 		       void **pentry0,
-		       unsigned int total_size,
-		       unsigned int number,
-		       unsigned int *hook_entries,
-		       unsigned int *underflows)
+		       const struct compat_ip6t_replace *compatr)
 {
 	unsigned int i, j;
 	struct xt_table_info *newinfo, *info;
@@ -1679,8 +1672,8 @@ translate_compat_table(struct net *net,
 
 	info = *pinfo;
 	entry0 = *pentry0;
-	size = total_size;
-	info->number = number;
+	size = compatr->size;
+	info->number = compatr->num_entries;
 
 	/* Init all hooks to impossible value. */
 	for (i = 0; i < NF_INET_NUMHOOKS; i++) {
@@ -1691,40 +1684,39 @@ translate_compat_table(struct net *net,
 	duprintf("translate_compat_table: size %u\n", info->size);
 	j = 0;
 	xt_compat_lock(AF_INET6);
-	xt_compat_init_offsets(AF_INET6, number);
+	xt_compat_init_offsets(AF_INET6, compatr->num_entries);
 	/* Walk through entries, checking offsets. */
-	xt_entry_foreach(iter0, entry0, total_size) {
+	xt_entry_foreach(iter0, entry0, compatr->size) {
 		ret = check_compat_entry_size_and_hooks(iter0, info, &size,
 							entry0,
-							entry0 + total_size,
-							hook_entries,
-							underflows,
-							name);
+							entry0 + compatr->size,
+							compatr->hook_entry,
+							compatr->underflow);
 		if (ret != 0)
 			goto out_unlock;
 		++j;
 	}
 
 	ret = -EINVAL;
-	if (j != number) {
+	if (j != compatr->num_entries) {
 		duprintf("translate_compat_table: %u not %u entries\n",
-			 j, number);
+			 j, compatr->num_entries);
 		goto out_unlock;
 	}
 
 	/* Check hooks all assigned */
 	for (i = 0; i < NF_INET_NUMHOOKS; i++) {
 		/* Only hooks which are valid */
-		if (!(valid_hooks & (1 << i)))
+		if (!(compatr->valid_hooks & (1 << i)))
 			continue;
 		if (info->hook_entry[i] == 0xFFFFFFFF) {
 			duprintf("Invalid hook entry %u %u\n",
-				 i, hook_entries[i]);
+				 i, info->hook_entry[i]);
 			goto out_unlock;
 		}
 		if (info->underflow[i] == 0xFFFFFFFF) {
 			duprintf("Invalid underflow %u %u\n",
-				 i, underflows[i]);
+				 i, info->underflow[i]);
 			goto out_unlock;
 		}
 	}
@@ -1734,17 +1726,17 @@ translate_compat_table(struct net *net,
 	if (!newinfo)
 		goto out_unlock;
 
-	newinfo->number = number;
+	newinfo->number = compatr->num_entries;
 	for (i = 0; i < NF_INET_NUMHOOKS; i++) {
 		newinfo->hook_entry[i] = info->hook_entry[i];
 		newinfo->underflow[i] = info->underflow[i];
 	}
 	entry1 = newinfo->entries[raw_smp_processor_id()];
 	pos = entry1;
-	size = total_size;
-	xt_entry_foreach(iter0, entry0, total_size) {
+	size = compatr->size;
+	xt_entry_foreach(iter0, entry0, compatr->size) {
 		ret = compat_copy_entry_from_user(iter0, &pos, &size,
-						  name, newinfo, entry1);
+						  newinfo, entry1);
 		if (ret != 0)
 			break;
 	}
@@ -1754,12 +1746,12 @@ translate_compat_table(struct net *net,
 		goto free_newinfo;
 
 	ret = -ELOOP;
-	if (!mark_source_chains(newinfo, valid_hooks, entry1))
+	if (!mark_source_chains(newinfo, compatr->valid_hooks, entry1))
 		goto free_newinfo;
 
 	i = 0;
 	xt_entry_foreach(iter1, entry1, newinfo->size) {
-		ret = compat_check_entry(iter1, net, name);
+		ret = compat_check_entry(iter1, net, compatr->name);
 		if (ret != 0)
 			break;
 		++i;
@@ -1804,7 +1796,7 @@ translate_compat_table(struct net *net,
 free_newinfo:
 	xt_free_table_info(newinfo);
 out:
-	xt_entry_foreach(iter0, entry0, total_size) {
+	xt_entry_foreach(iter0, entry0, compatr->size) {
 		if (j-- == 0)
 			break;
 		compat_release_entry(iter0);
@@ -1850,10 +1842,7 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len)
 		goto free_newinfo;
 	}
 
-	ret = translate_compat_table(net, tmp.name, tmp.valid_hooks,
-				     &newinfo, &loc_cpu_entry, tmp.size,
-				     tmp.num_entries, tmp.hook_entry,
-				     tmp.underflow);
+	ret = translate_compat_table(net, &newinfo, &loc_cpu_entry, &tmp);
 	if (ret != 0)
 		goto free_newinfo;
 
-- 
2.5.0

[added to the 4.1 stable tree] netfilter: x_tables: xt_compat_match_from_user doesn't need a retval

[Sasha Levin]

From: Florian Westphal <fw@strlen.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 0188346f21e6546498c2a0f84888797ad4063fc5 ]

Always returned 0.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 include/linux/netfilter/x_tables.h |  2 +-
 net/ipv4/netfilter/arp_tables.c    | 17 +++++------------
 net/ipv4/netfilter/ip_tables.c     | 26 +++++++++-----------------
 net/ipv6/netfilter/ip6_tables.c    | 27 +++++++++------------------
 net/netfilter/x_tables.c           |  5 ++---
 5 files changed, 26 insertions(+), 51 deletions(-)

diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index 726f4dd..445a2d5 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -425,7 +425,7 @@ void xt_compat_init_offsets(u_int8_t af, unsigned int number);
 int xt_compat_calc_jump(u_int8_t af, unsigned int offset);
 
 int xt_compat_match_offset(const struct xt_match *match);
-int xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr,
+void xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr,
 			      unsigned int *size);
 int xt_compat_match_to_user(const struct xt_entry_match *m,
 			    void __user **dstptr, unsigned int *size);
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index aca12b8..8bdc267 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -1302,7 +1302,7 @@ out:
 	return ret;
 }
 
-static int
+static void
 compat_copy_entry_from_user(struct compat_arpt_entry *e, void **dstptr,
 			    unsigned int *size,
 			    struct xt_table_info *newinfo, unsigned char *base)
@@ -1311,9 +1311,8 @@ compat_copy_entry_from_user(struct compat_arpt_entry *e, void **dstptr,
 	struct xt_target *target;
 	struct arpt_entry *de;
 	unsigned int origsize;
-	int ret, h;
+	int h;
 
-	ret = 0;
 	origsize = *size;
 	de = (struct arpt_entry *)*dstptr;
 	memcpy(de, e, sizeof(struct arpt_entry));
@@ -1334,7 +1333,6 @@ compat_copy_entry_from_user(struct compat_arpt_entry *e, void **dstptr,
 		if ((unsigned char *)de - base < newinfo->underflow[h])
 			newinfo->underflow[h] -= origsize - *size;
 	}
-	return ret;
 }
 
 static int translate_compat_table(struct xt_table_info **pinfo,
@@ -1413,16 +1411,11 @@ static int translate_compat_table(struct xt_table_info **pinfo,
 	entry1 = newinfo->entries[raw_smp_processor_id()];
 	pos = entry1;
 	size = compatr->size;
-	xt_entry_foreach(iter0, entry0, compatr->size) {
-		ret = compat_copy_entry_from_user(iter0, &pos, &size,
-						  newinfo, entry1);
-		if (ret != 0)
-			break;
-	}
+	xt_entry_foreach(iter0, entry0, compatr->size)
+		compat_copy_entry_from_user(iter0, &pos, &size,
+					    newinfo, entry1);
 	xt_compat_flush_offsets(NFPROTO_ARP);
 	xt_compat_unlock(NFPROTO_ARP);
-	if (ret)
-		goto free_newinfo;
 
 	ret = -ELOOP;
 	if (!mark_source_chains(newinfo, compatr->valid_hooks, entry1))
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index e4c0a27..ac02824 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1567,7 +1567,7 @@ release_matches:
 	return ret;
 }
 
-static int
+static void
 compat_copy_entry_from_user(struct compat_ipt_entry *e, void **dstptr,
 			    unsigned int *size,
 			    struct xt_table_info *newinfo, unsigned char *base)
@@ -1576,10 +1576,9 @@ compat_copy_entry_from_user(struct compat_ipt_entry *e, void **dstptr,
 	struct xt_target *target;
 	struct ipt_entry *de;
 	unsigned int origsize;
-	int ret, h;
+	int h;
 	struct xt_entry_match *ematch;
 
-	ret = 0;
 	origsize = *size;
 	de = (struct ipt_entry *)*dstptr;
 	memcpy(de, e, sizeof(struct ipt_entry));
@@ -1588,11 +1587,9 @@ compat_copy_entry_from_user(struct compat_ipt_entry *e, void **dstptr,
 	*dstptr += sizeof(struct ipt_entry);
 	*size += sizeof(struct ipt_entry) - sizeof(struct compat_ipt_entry);
 
-	xt_ematch_foreach(ematch, e) {
-		ret = xt_compat_match_from_user(ematch, dstptr, size);
-		if (ret != 0)
-			return ret;
-	}
+	xt_ematch_foreach(ematch, e)
+		xt_compat_match_from_user(ematch, dstptr, size);
+
 	de->target_offset = e->target_offset - (origsize - *size);
 	t = compat_ipt_get_target(e);
 	target = t->u.kernel.target;
@@ -1605,7 +1602,6 @@ compat_copy_entry_from_user(struct compat_ipt_entry *e, void **dstptr,
 		if ((unsigned char *)de - base < newinfo->underflow[h])
 			newinfo->underflow[h] -= origsize - *size;
 	}
-	return ret;
 }
 
 static int
@@ -1721,16 +1717,12 @@ translate_compat_table(struct net *net,
 	entry1 = newinfo->entries[raw_smp_processor_id()];
 	pos = entry1;
 	size = compatr->size;
-	xt_entry_foreach(iter0, entry0, compatr->size) {
-		ret = compat_copy_entry_from_user(iter0, &pos, &size,
-						  newinfo, entry1);
-		if (ret != 0)
-			break;
-	}
+	xt_entry_foreach(iter0, entry0, compatr->size)
+		compat_copy_entry_from_user(iter0, &pos, &size,
+					    newinfo, entry1);
+
 	xt_compat_flush_offsets(AF_INET);
 	xt_compat_unlock(AF_INET);
-	if (ret)
-		goto free_newinfo;
 
 	ret = -ELOOP;
 	if (!mark_source_chains(newinfo, compatr->valid_hooks, entry1))
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 0c34c08..43cc379 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1582,7 +1582,7 @@ release_matches:
 	return ret;
 }
 
-static int
+static void
 compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr,
 			    unsigned int *size,
 			    struct xt_table_info *newinfo, unsigned char *base)
@@ -1590,10 +1590,9 @@ compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr,
 	struct xt_entry_target *t;
 	struct ip6t_entry *de;
 	unsigned int origsize;
-	int ret, h;
+	int h;
 	struct xt_entry_match *ematch;
 
-	ret = 0;
 	origsize = *size;
 	de = (struct ip6t_entry *)*dstptr;
 	memcpy(de, e, sizeof(struct ip6t_entry));
@@ -1602,11 +1601,9 @@ compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr,
 	*dstptr += sizeof(struct ip6t_entry);
 	*size += sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry);
 
-	xt_ematch_foreach(ematch, e) {
-		ret = xt_compat_match_from_user(ematch, dstptr, size);
-		if (ret != 0)
-			return ret;
-	}
+	xt_ematch_foreach(ematch, e)
+		xt_compat_match_from_user(ematch, dstptr, size);
+
 	de->target_offset = e->target_offset - (origsize - *size);
 	t = compat_ip6t_get_target(e);
 	xt_compat_target_from_user(t, dstptr, size);
@@ -1618,7 +1615,6 @@ compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr,
 		if ((unsigned char *)de - base < newinfo->underflow[h])
 			newinfo->underflow[h] -= origsize - *size;
 	}
-	return ret;
 }
 
 static int compat_check_entry(struct ip6t_entry *e, struct net *net,
@@ -1733,17 +1729,12 @@ translate_compat_table(struct net *net,
 	}
 	entry1 = newinfo->entries[raw_smp_processor_id()];
 	pos = entry1;
-	size = compatr->size;
-	xt_entry_foreach(iter0, entry0, compatr->size) {
-		ret = compat_copy_entry_from_user(iter0, &pos, &size,
-						  newinfo, entry1);
-		if (ret != 0)
-			break;
-	}
+	xt_entry_foreach(iter0, entry0, compatr->size)
+		compat_copy_entry_from_user(iter0, &pos, &size,
+					    newinfo, entry1);
+
 	xt_compat_flush_offsets(AF_INET6);
 	xt_compat_unlock(AF_INET6);
-	if (ret)
-		goto free_newinfo;
 
 	ret = -ELOOP;
 	if (!mark_source_chains(newinfo, compatr->valid_hooks, entry1))
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 5e5cc45..a914369 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -528,8 +528,8 @@ int xt_compat_match_offset(const struct xt_match *match)
 }
 EXPORT_SYMBOL_GPL(xt_compat_match_offset);
 
-int xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr,
-			      unsigned int *size)
+void xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr,
+			       unsigned int *size)
 {
 	const struct xt_match *match = m->u.kernel.match;
 	struct compat_xt_entry_match *cm = (struct compat_xt_entry_match *)m;
@@ -551,7 +551,6 @@ int xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr,
 
 	*size += off;
 	*dstptr += msize;
-	return 0;
 }
 EXPORT_SYMBOL_GPL(xt_compat_match_from_user);
 
-- 
2.5.0

[added to the 4.1 stable tree] netfilter: x_tables: do compat validation via translate_table

[Sasha Levin]

From: Florian Westphal <fw@strlen.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit 09d9686047dbbe1cf4faa558d3ecc4aae2046054 ]

This looks like refactoring, but its also a bug fix.

Problem is that the compat path (32bit iptables, 64bit kernel) lacks a few
sanity tests that are done in the normal path.

For example, we do not check for underflows and the base chain policies.

While its possible to also add such checks to the compat path, its more
copy&pastry, for instance we cannot reuse check_underflow() helper as
e->target_offset differs in the compat case.

Other problem is that it makes auditing for validation errors harder; two
places need to be checked and kept in sync.

At a high level 32 bit compat works like this:
1- initial pass over blob:
   validate match/entry offsets, bounds checking
   lookup all matches and targets
   do bookkeeping wrt. size delta of 32/64bit structures
   assign match/target.u.kernel pointer (points at kernel
   implementation, needed to access ->compatsize etc.)

2- allocate memory according to the total bookkeeping size to
   contain the translated ruleset

3- second pass over original blob:
   for each entry, copy the 32bit representation to the newly allocated
   memory.  This also does any special match translations (e.g.
   adjust 32bit to 64bit longs, etc).

4- check if ruleset is free of loops (chase all jumps)

5-first pass over translated blob:
   call the checkentry function of all matches and targets.

The alternative implemented by this patch is to drop steps 3&4 from the
compat process, the translation is changed into an intermediate step
rather than a full 1:1 translate_table replacement.

In the 2nd pass (step #3), change the 64bit ruleset back to a kernel
representation, i.e. put() the kernel pointer and restore ->u.user.name .

This gets us a 64bit ruleset that is in the format generated by a 64bit
iptables userspace -- we can then use translate_table() to get the
'native' sanity checks.

This has two drawbacks:

1. we re-validate all the match and target entry structure sizes even
though compat translation is supposed to never generate bogus offsets.
2. we put and then re-lookup each match and target.

THe upside is that we get all sanity tests and ruleset validations
provided by the normal path and can remove some duplicated compat code.

iptables-restore time of autogenerated ruleset with 300k chains of form
-A CHAIN0001 -m limit --limit 1/s -j CHAIN0002
-A CHAIN0002 -m limit --limit 1/s -j CHAIN0003

shows no noticeable differences in restore times:
old:   0m30.796s
new:   0m31.521s
64bit: 0m25.674s

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 net/ipv4/netfilter/arp_tables.c | 109 ++++++-----------------------
 net/ipv4/netfilter/ip_tables.c  | 151 ++++++++--------------------------------
 net/ipv6/netfilter/ip6_tables.c | 145 ++++++--------------------------------
 net/netfilter/x_tables.c        |   8 +++
 4 files changed, 80 insertions(+), 333 deletions(-)

diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 8bdc267..49620aa 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -1226,19 +1226,17 @@ static inline void compat_release_entry(struct compat_arpt_entry *e)
 	module_put(t->u.kernel.target->me);
 }
 
-static inline int
+static int
 check_compat_entry_size_and_hooks(struct compat_arpt_entry *e,
 				  struct xt_table_info *newinfo,
 				  unsigned int *size,
 				  const unsigned char *base,
-				  const unsigned char *limit,
-				  const unsigned int *hook_entries,
-				  const unsigned int *underflows)
+				  const unsigned char *limit)
 {
 	struct xt_entry_target *t;
 	struct xt_target *target;
 	unsigned int entry_offset;
-	int ret, off, h;
+	int ret, off;
 
 	duprintf("check_compat_entry_size_and_hooks %p\n", e);
 	if ((unsigned long)e % __alignof__(struct compat_arpt_entry) != 0 ||
@@ -1283,17 +1281,6 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e,
 	if (ret)
 		goto release_target;
 
-	/* Check hooks & underflows */
-	for (h = 0; h < NF_ARP_NUMHOOKS; h++) {
-		if ((unsigned char *)e - base == hook_entries[h])
-			newinfo->hook_entry[h] = hook_entries[h];
-		if ((unsigned char *)e - base == underflows[h])
-			newinfo->underflow[h] = underflows[h];
-	}
-
-	/* Clear counters and comefrom */
-	memset(&e->counters, 0, sizeof(e->counters));
-	e->comefrom = 0;
 	return 0;
 
 release_target:
@@ -1343,7 +1330,7 @@ static int translate_compat_table(struct xt_table_info **pinfo,
 	struct xt_table_info *newinfo, *info;
 	void *pos, *entry0, *entry1;
 	struct compat_arpt_entry *iter0;
-	struct arpt_entry *iter1;
+	struct arpt_replace repl;
 	unsigned int size;
 	int ret = 0;
 
@@ -1352,12 +1339,6 @@ static int translate_compat_table(struct xt_table_info **pinfo,
 	size = compatr->size;
 	info->number = compatr->num_entries;
 
-	/* Init all hooks to impossible value. */
-	for (i = 0; i < NF_ARP_NUMHOOKS; i++) {
-		info->hook_entry[i] = 0xFFFFFFFF;
-		info->underflow[i] = 0xFFFFFFFF;
-	}
-
 	duprintf("translate_compat_table: size %u\n", info->size);
 	j = 0;
 	xt_compat_lock(NFPROTO_ARP);
@@ -1366,9 +1347,7 @@ static int translate_compat_table(struct xt_table_info **pinfo,
 	xt_entry_foreach(iter0, entry0, compatr->size) {
 		ret = check_compat_entry_size_and_hooks(iter0, info, &size,
 							entry0,
-							entry0 + compatr->size,
-							compatr->hook_entry,
-							compatr->underflow);
+							entry0 + compatr->size);
 		if (ret != 0)
 			goto out_unlock;
 		++j;
@@ -1381,23 +1360,6 @@ static int translate_compat_table(struct xt_table_info **pinfo,
 		goto out_unlock;
 	}
 
-	/* Check hooks all assigned */
-	for (i = 0; i < NF_ARP_NUMHOOKS; i++) {
-		/* Only hooks which are valid */
-		if (!(compatr->valid_hooks & (1 << i)))
-			continue;
-		if (info->hook_entry[i] == 0xFFFFFFFF) {
-			duprintf("Invalid hook entry %u %u\n",
-				 i, info->hook_entry[i]);
-			goto out_unlock;
-		}
-		if (info->underflow[i] == 0xFFFFFFFF) {
-			duprintf("Invalid underflow %u %u\n",
-				 i, info->underflow[i]);
-			goto out_unlock;
-		}
-	}
-
 	ret = -ENOMEM;
 	newinfo = xt_alloc_table_info(size);
 	if (!newinfo)
@@ -1414,51 +1376,25 @@ static int translate_compat_table(struct xt_table_info **pinfo,
 	xt_entry_foreach(iter0, entry0, compatr->size)
 		compat_copy_entry_from_user(iter0, &pos, &size,
 					    newinfo, entry1);
+
+	/* all module references in entry0 are now gone */
+
 	xt_compat_flush_offsets(NFPROTO_ARP);
 	xt_compat_unlock(NFPROTO_ARP);
 
-	ret = -ELOOP;
-	if (!mark_source_chains(newinfo, compatr->valid_hooks, entry1))
-		goto free_newinfo;
+	memcpy(&repl, compatr, sizeof(*compatr));
 
-	i = 0;
-	xt_entry_foreach(iter1, entry1, newinfo->size) {
-		ret = check_target(iter1, compatr->name);
-		if (ret != 0)
-			break;
-		++i;
-		if (strcmp(arpt_get_target(iter1)->u.user.name,
-		    XT_ERROR_TARGET) == 0)
-			++newinfo->stacksize;
-	}
-	if (ret) {
-		/*
-		 * The first i matches need cleanup_entry (calls ->destroy)
-		 * because they had called ->check already. The other j-i
-		 * entries need only release.
-		 */
-		int skip = i;
-		j -= i;
-		xt_entry_foreach(iter0, entry0, newinfo->size) {
-			if (skip-- > 0)
-				continue;
-			if (j-- == 0)
-				break;
-			compat_release_entry(iter0);
-		}
-		xt_entry_foreach(iter1, entry1, newinfo->size) {
-			if (i-- == 0)
-				break;
-			cleanup_entry(iter1);
-		}
-		xt_free_table_info(newinfo);
-		return ret;
+	for (i = 0; i < NF_ARP_NUMHOOKS; i++) {
+		repl.hook_entry[i] = newinfo->hook_entry[i];
+		repl.underflow[i] = newinfo->underflow[i];
 	}
 
-	/* And one copy for every other CPU */
-	for_each_possible_cpu(i)
-		if (newinfo->entries[i] && newinfo->entries[i] != entry1)
-			memcpy(newinfo->entries[i], entry1, newinfo->size);
+	repl.num_counters = 0;
+	repl.counters = NULL;
+	repl.size = newinfo->size;
+	ret = translate_table(newinfo, entry1, &repl);
+	if (ret)
+		goto free_newinfo;
 
 	*pinfo = newinfo;
 	*pentry0 = entry1;
@@ -1467,17 +1403,16 @@ static int translate_compat_table(struct xt_table_info **pinfo,
 
 free_newinfo:
 	xt_free_table_info(newinfo);
-out:
+	return ret;
+out_unlock:
+	xt_compat_flush_offsets(NFPROTO_ARP);
+	xt_compat_unlock(NFPROTO_ARP);
 	xt_entry_foreach(iter0, entry0, compatr->size) {
 		if (j-- == 0)
 			break;
 		compat_release_entry(iter0);
 	}
 	return ret;
-out_unlock:
-	xt_compat_flush_offsets(NFPROTO_ARP);
-	xt_compat_unlock(NFPROTO_ARP);
-	goto out;
 }
 
 static int compat_do_replace(struct net *net, void __user *user,
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index ac02824..c2d3f0e 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1481,16 +1481,14 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e,
 				  struct xt_table_info *newinfo,
 				  unsigned int *size,
 				  const unsigned char *base,
-				  const unsigned char *limit,
-				  const unsigned int *hook_entries,
-				  const unsigned int *underflows)
+				  const unsigned char *limit)
 {
 	struct xt_entry_match *ematch;
 	struct xt_entry_target *t;
 	struct xt_target *target;
 	unsigned int entry_offset;
 	unsigned int j;
-	int ret, off, h;
+	int ret, off;
 
 	duprintf("check_compat_entry_size_and_hooks %p\n", e);
 	if ((unsigned long)e % __alignof__(struct compat_ipt_entry) != 0 ||
@@ -1543,17 +1541,6 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e,
 	if (ret)
 		goto out;
 
-	/* Check hooks & underflows */
-	for (h = 0; h < NF_INET_NUMHOOKS; h++) {
-		if ((unsigned char *)e - base == hook_entries[h])
-			newinfo->hook_entry[h] = hook_entries[h];
-		if ((unsigned char *)e - base == underflows[h])
-			newinfo->underflow[h] = underflows[h];
-	}
-
-	/* Clear counters and comefrom */
-	memset(&e->counters, 0, sizeof(e->counters));
-	e->comefrom = 0;
 	return 0;
 
 out:
@@ -1596,6 +1583,7 @@ compat_copy_entry_from_user(struct compat_ipt_entry *e, void **dstptr,
 	xt_compat_target_from_user(t, dstptr, size);
 
 	de->next_offset = e->next_offset - (origsize - *size);
+
 	for (h = 0; h < NF_INET_NUMHOOKS; h++) {
 		if ((unsigned char *)de - base < newinfo->hook_entry[h])
 			newinfo->hook_entry[h] -= origsize - *size;
@@ -1605,41 +1593,6 @@ compat_copy_entry_from_user(struct compat_ipt_entry *e, void **dstptr,
 }
 
 static int
-compat_check_entry(struct ipt_entry *e, struct net *net, const char *name)
-{
-	struct xt_entry_match *ematch;
-	struct xt_mtchk_param mtpar;
-	unsigned int j;
-	int ret = 0;
-
-	j = 0;
-	mtpar.net	= net;
-	mtpar.table     = name;
-	mtpar.entryinfo = &e->ip;
-	mtpar.hook_mask = e->comefrom;
-	mtpar.family    = NFPROTO_IPV4;
-	xt_ematch_foreach(ematch, e) {
-		ret = check_match(ematch, &mtpar);
-		if (ret != 0)
-			goto cleanup_matches;
-		++j;
-	}
-
-	ret = check_target(e, net, name);
-	if (ret)
-		goto cleanup_matches;
-	return 0;
-
- cleanup_matches:
-	xt_ematch_foreach(ematch, e) {
-		if (j-- == 0)
-			break;
-		cleanup_match(ematch, net);
-	}
-	return ret;
-}
-
-static int
 translate_compat_table(struct net *net,
 		       struct xt_table_info **pinfo,
 		       void **pentry0,
@@ -1649,7 +1602,7 @@ translate_compat_table(struct net *net,
 	struct xt_table_info *newinfo, *info;
 	void *pos, *entry0, *entry1;
 	struct compat_ipt_entry *iter0;
-	struct ipt_entry *iter1;
+	struct ipt_replace repl;
 	unsigned int size;
 	int ret;
 
@@ -1658,12 +1611,6 @@ translate_compat_table(struct net *net,
 	size = compatr->size;
 	info->number = compatr->num_entries;
 
-	/* Init all hooks to impossible value. */
-	for (i = 0; i < NF_INET_NUMHOOKS; i++) {
-		info->hook_entry[i] = 0xFFFFFFFF;
-		info->underflow[i] = 0xFFFFFFFF;
-	}
-
 	duprintf("translate_compat_table: size %u\n", info->size);
 	j = 0;
 	xt_compat_lock(AF_INET);
@@ -1672,9 +1619,7 @@ translate_compat_table(struct net *net,
 	xt_entry_foreach(iter0, entry0, compatr->size) {
 		ret = check_compat_entry_size_and_hooks(iter0, info, &size,
 							entry0,
-							entry0 + compatr->size,
-							compatr->hook_entry,
-							compatr->underflow);
+							entry0 + compatr->size);
 		if (ret != 0)
 			goto out_unlock;
 		++j;
@@ -1687,23 +1632,6 @@ translate_compat_table(struct net *net,
 		goto out_unlock;
 	}
 
-	/* Check hooks all assigned */
-	for (i = 0; i < NF_INET_NUMHOOKS; i++) {
-		/* Only hooks which are valid */
-		if (!(compatr->valid_hooks & (1 << i)))
-			continue;
-		if (info->hook_entry[i] == 0xFFFFFFFF) {
-			duprintf("Invalid hook entry %u %u\n",
-				 i, info->hook_entry[i]);
-			goto out_unlock;
-		}
-		if (info->underflow[i] == 0xFFFFFFFF) {
-			duprintf("Invalid underflow %u %u\n",
-				 i, info->underflow[i]);
-			goto out_unlock;
-		}
-	}
-
 	ret = -ENOMEM;
 	newinfo = xt_alloc_table_info(size);
 	if (!newinfo)
@@ -1711,8 +1639,8 @@ translate_compat_table(struct net *net,
 
 	newinfo->number = compatr->num_entries;
 	for (i = 0; i < NF_INET_NUMHOOKS; i++) {
-		newinfo->hook_entry[i] = info->hook_entry[i];
-		newinfo->underflow[i] = info->underflow[i];
+		newinfo->hook_entry[i] = compatr->hook_entry[i];
+		newinfo->underflow[i] = compatr->underflow[i];
 	}
 	entry1 = newinfo->entries[raw_smp_processor_id()];
 	pos = entry1;
@@ -1721,51 +1649,29 @@ translate_compat_table(struct net *net,
 		compat_copy_entry_from_user(iter0, &pos, &size,
 					    newinfo, entry1);
 
+	/* all module references in entry0 are now gone.
+	 * entry1/newinfo contains a 64bit ruleset that looks exactly as
+	 * generated by 64bit userspace.
+	 *
+	 * Call standard translate_table() to validate all hook_entrys,
+	 * underflows, check for loops, etc.
+	 */
 	xt_compat_flush_offsets(AF_INET);
 	xt_compat_unlock(AF_INET);
 
-	ret = -ELOOP;
-	if (!mark_source_chains(newinfo, compatr->valid_hooks, entry1))
-		goto free_newinfo;
+	memcpy(&repl, compatr, sizeof(*compatr));
 
-	i = 0;
-	xt_entry_foreach(iter1, entry1, newinfo->size) {
-		ret = compat_check_entry(iter1, net, compatr->name);
-		if (ret != 0)
-			break;
-		++i;
-		if (strcmp(ipt_get_target(iter1)->u.user.name,
-		    XT_ERROR_TARGET) == 0)
-			++newinfo->stacksize;
-	}
-	if (ret) {
-		/*
-		 * The first i matches need cleanup_entry (calls ->destroy)
-		 * because they had called ->check already. The other j-i
-		 * entries need only release.
-		 */
-		int skip = i;
-		j -= i;
-		xt_entry_foreach(iter0, entry0, newinfo->size) {
-			if (skip-- > 0)
-				continue;
-			if (j-- == 0)
-				break;
-			compat_release_entry(iter0);
-		}
-		xt_entry_foreach(iter1, entry1, newinfo->size) {
-			if (i-- == 0)
-				break;
-			cleanup_entry(iter1, net);
-		}
-		xt_free_table_info(newinfo);
-		return ret;
+	for (i = 0; i < NF_INET_NUMHOOKS; i++) {
+		repl.hook_entry[i] = newinfo->hook_entry[i];
+		repl.underflow[i] = newinfo->underflow[i];
 	}
 
-	/* And one copy for every other CPU */
-	for_each_possible_cpu(i)
-		if (newinfo->entries[i] && newinfo->entries[i] != entry1)
-			memcpy(newinfo->entries[i], entry1, newinfo->size);
+	repl.num_counters = 0;
+	repl.counters = NULL;
+	repl.size = newinfo->size;
+	ret = translate_table(net, newinfo, entry1, &repl);
+	if (ret)
+		goto free_newinfo;
 
 	*pinfo = newinfo;
 	*pentry0 = entry1;
@@ -1774,17 +1680,16 @@ translate_compat_table(struct net *net,
 
 free_newinfo:
 	xt_free_table_info(newinfo);
-out:
+	return ret;
+out_unlock:
+	xt_compat_flush_offsets(AF_INET);
+	xt_compat_unlock(AF_INET);
 	xt_entry_foreach(iter0, entry0, compatr->size) {
 		if (j-- == 0)
 			break;
 		compat_release_entry(iter0);
 	}
 	return ret;
-out_unlock:
-	xt_compat_flush_offsets(AF_INET);
-	xt_compat_unlock(AF_INET);
-	goto out;
 }
 
 static int
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 43cc379..faad607 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1496,16 +1496,14 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e,
 				  struct xt_table_info *newinfo,
 				  unsigned int *size,
 				  const unsigned char *base,
-				  const unsigned char *limit,
-				  const unsigned int *hook_entries,
-				  const unsigned int *underflows)
+				  const unsigned char *limit)
 {
 	struct xt_entry_match *ematch;
 	struct xt_entry_target *t;
 	struct xt_target *target;
 	unsigned int entry_offset;
 	unsigned int j;
-	int ret, off, h;
+	int ret, off;
 
 	duprintf("check_compat_entry_size_and_hooks %p\n", e);
 	if ((unsigned long)e % __alignof__(struct compat_ip6t_entry) != 0 ||
@@ -1558,17 +1556,6 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e,
 	if (ret)
 		goto out;
 
-	/* Check hooks & underflows */
-	for (h = 0; h < NF_INET_NUMHOOKS; h++) {
-		if ((unsigned char *)e - base == hook_entries[h])
-			newinfo->hook_entry[h] = hook_entries[h];
-		if ((unsigned char *)e - base == underflows[h])
-			newinfo->underflow[h] = underflows[h];
-	}
-
-	/* Clear counters and comefrom */
-	memset(&e->counters, 0, sizeof(e->counters));
-	e->comefrom = 0;
 	return 0;
 
 out:
@@ -1617,41 +1604,6 @@ compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr,
 	}
 }
 
-static int compat_check_entry(struct ip6t_entry *e, struct net *net,
-			      const char *name)
-{
-	unsigned int j;
-	int ret = 0;
-	struct xt_mtchk_param mtpar;
-	struct xt_entry_match *ematch;
-
-	j = 0;
-	mtpar.net	= net;
-	mtpar.table     = name;
-	mtpar.entryinfo = &e->ipv6;
-	mtpar.hook_mask = e->comefrom;
-	mtpar.family    = NFPROTO_IPV6;
-	xt_ematch_foreach(ematch, e) {
-		ret = check_match(ematch, &mtpar);
-		if (ret != 0)
-			goto cleanup_matches;
-		++j;
-	}
-
-	ret = check_target(e, net, name);
-	if (ret)
-		goto cleanup_matches;
-	return 0;
-
- cleanup_matches:
-	xt_ematch_foreach(ematch, e) {
-		if (j-- == 0)
-			break;
-		cleanup_match(ematch, net);
-	}
-	return ret;
-}
-
 static int
 translate_compat_table(struct net *net,
 		       struct xt_table_info **pinfo,
@@ -1662,7 +1614,7 @@ translate_compat_table(struct net *net,
 	struct xt_table_info *newinfo, *info;
 	void *pos, *entry0, *entry1;
 	struct compat_ip6t_entry *iter0;
-	struct ip6t_entry *iter1;
+	struct ip6t_replace repl;
 	unsigned int size;
 	int ret = 0;
 
@@ -1671,12 +1623,6 @@ translate_compat_table(struct net *net,
 	size = compatr->size;
 	info->number = compatr->num_entries;
 
-	/* Init all hooks to impossible value. */
-	for (i = 0; i < NF_INET_NUMHOOKS; i++) {
-		info->hook_entry[i] = 0xFFFFFFFF;
-		info->underflow[i] = 0xFFFFFFFF;
-	}
-
 	duprintf("translate_compat_table: size %u\n", info->size);
 	j = 0;
 	xt_compat_lock(AF_INET6);
@@ -1685,9 +1631,7 @@ translate_compat_table(struct net *net,
 	xt_entry_foreach(iter0, entry0, compatr->size) {
 		ret = check_compat_entry_size_and_hooks(iter0, info, &size,
 							entry0,
-							entry0 + compatr->size,
-							compatr->hook_entry,
-							compatr->underflow);
+							entry0 + compatr->size);
 		if (ret != 0)
 			goto out_unlock;
 		++j;
@@ -1700,23 +1644,6 @@ translate_compat_table(struct net *net,
 		goto out_unlock;
 	}
 
-	/* Check hooks all assigned */
-	for (i = 0; i < NF_INET_NUMHOOKS; i++) {
-		/* Only hooks which are valid */
-		if (!(compatr->valid_hooks & (1 << i)))
-			continue;
-		if (info->hook_entry[i] == 0xFFFFFFFF) {
-			duprintf("Invalid hook entry %u %u\n",
-				 i, info->hook_entry[i]);
-			goto out_unlock;
-		}
-		if (info->underflow[i] == 0xFFFFFFFF) {
-			duprintf("Invalid underflow %u %u\n",
-				 i, info->underflow[i]);
-			goto out_unlock;
-		}
-	}
-
 	ret = -ENOMEM;
 	newinfo = xt_alloc_table_info(size);
 	if (!newinfo)
@@ -1724,60 +1651,33 @@ translate_compat_table(struct net *net,
 
 	newinfo->number = compatr->num_entries;
 	for (i = 0; i < NF_INET_NUMHOOKS; i++) {
-		newinfo->hook_entry[i] = info->hook_entry[i];
-		newinfo->underflow[i] = info->underflow[i];
+		newinfo->hook_entry[i] = compatr->hook_entry[i];
+		newinfo->underflow[i] = compatr->underflow[i];
 	}
 	entry1 = newinfo->entries[raw_smp_processor_id()];
 	pos = entry1;
+	size = compatr->size;
 	xt_entry_foreach(iter0, entry0, compatr->size)
 		compat_copy_entry_from_user(iter0, &pos, &size,
 					    newinfo, entry1);
 
+	/* all module references in entry0 are now gone. */
 	xt_compat_flush_offsets(AF_INET6);
 	xt_compat_unlock(AF_INET6);
 
-	ret = -ELOOP;
-	if (!mark_source_chains(newinfo, compatr->valid_hooks, entry1))
-		goto free_newinfo;
+	memcpy(&repl, compatr, sizeof(*compatr));
 
-	i = 0;
-	xt_entry_foreach(iter1, entry1, newinfo->size) {
-		ret = compat_check_entry(iter1, net, compatr->name);
-		if (ret != 0)
-			break;
-		++i;
-		if (strcmp(ip6t_get_target(iter1)->u.user.name,
-		    XT_ERROR_TARGET) == 0)
-			++newinfo->stacksize;
-	}
-	if (ret) {
-		/*
-		 * The first i matches need cleanup_entry (calls ->destroy)
-		 * because they had called ->check already. The other j-i
-		 * entries need only release.
-		 */
-		int skip = i;
-		j -= i;
-		xt_entry_foreach(iter0, entry0, newinfo->size) {
-			if (skip-- > 0)
-				continue;
-			if (j-- == 0)
-				break;
-			compat_release_entry(iter0);
-		}
-		xt_entry_foreach(iter1, entry1, newinfo->size) {
-			if (i-- == 0)
-				break;
-			cleanup_entry(iter1, net);
-		}
-		xt_free_table_info(newinfo);
-		return ret;
+	for (i = 0; i < NF_INET_NUMHOOKS; i++) {
+		repl.hook_entry[i] = newinfo->hook_entry[i];
+		repl.underflow[i] = newinfo->underflow[i];
 	}
 
-	/* And one copy for every other CPU */
-	for_each_possible_cpu(i)
-		if (newinfo->entries[i] && newinfo->entries[i] != entry1)
-			memcpy(newinfo->entries[i], entry1, newinfo->size);
+	repl.num_counters = 0;
+	repl.counters = NULL;
+	repl.size = newinfo->size;
+	ret = translate_table(net, newinfo, entry1, &repl);
+	if (ret)
+		goto free_newinfo;
 
 	*pinfo = newinfo;
 	*pentry0 = entry1;
@@ -1786,17 +1686,16 @@ translate_compat_table(struct net *net,
 
 free_newinfo:
 	xt_free_table_info(newinfo);
-out:
+	return ret;
+out_unlock:
+	xt_compat_flush_offsets(AF_INET6);
+	xt_compat_unlock(AF_INET6);
 	xt_entry_foreach(iter0, entry0, compatr->size) {
 		if (j-- == 0)
 			break;
 		compat_release_entry(iter0);
 	}
 	return ret;
-out_unlock:
-	xt_compat_flush_offsets(AF_INET6);
-	xt_compat_unlock(AF_INET6);
-	goto out;
 }
 
 static int
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index a914369..141ae20 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -535,6 +535,7 @@ void xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr,
 	struct compat_xt_entry_match *cm = (struct compat_xt_entry_match *)m;
 	int pad, off = xt_compat_match_offset(match);
 	u_int16_t msize = cm->u.user.match_size;
+	char name[sizeof(m->u.user.name)];
 
 	m = *dstptr;
 	memcpy(m, cm, sizeof(*cm));
@@ -548,6 +549,9 @@ void xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr,
 
 	msize += off;
 	m->u.user.match_size = msize;
+	strlcpy(name, match->name, sizeof(name));
+	module_put(match->me);
+	strncpy(m->u.user.name, name, sizeof(m->u.user.name));
 
 	*size += off;
 	*dstptr += msize;
@@ -765,6 +769,7 @@ void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr,
 	struct compat_xt_entry_target *ct = (struct compat_xt_entry_target *)t;
 	int pad, off = xt_compat_target_offset(target);
 	u_int16_t tsize = ct->u.user.target_size;
+	char name[sizeof(t->u.user.name)];
 
 	t = *dstptr;
 	memcpy(t, ct, sizeof(*ct));
@@ -778,6 +783,9 @@ void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr,
 
 	tsize += off;
 	t->u.user.target_size = tsize;
+	strlcpy(name, target->name, sizeof(name));
+	module_put(target->me);
+	strncpy(t->u.user.name, name, sizeof(t->u.user.name));
 
 	*size += off;
 	*dstptr += tsize;
-- 
2.5.0

[added to the 4.1 stable tree] netfilter: x_tables: introduce and use xt_copy_counters_from_user

[Sasha Levin]

From: Florian Westphal <fw@strlen.de>

This patch has been added to the 4.1 stable tree. If you have any
objections, please let us know.

===============

[ Upstream commit d7591f0c41ce3e67600a982bab6989ef0f07b3ce ]

The three variants use same copy&pasted code, condense this into a
helper and use that.

Make sure info.name is 0-terminated.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
 include/linux/netfilter/x_tables.h |  3 ++
 net/ipv4/netfilter/arp_tables.c    | 48 +++----------------------
 net/ipv4/netfilter/ip_tables.c     | 48 +++----------------------
 net/ipv6/netfilter/ip6_tables.c    | 49 +++----------------------
 net/netfilter/x_tables.c           | 74 ++++++++++++++++++++++++++++++++++++++
 5 files changed, 92 insertions(+), 130 deletions(-)

diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index 445a2d5..7741efa 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -248,6 +248,9 @@ int xt_check_match(struct xt_mtchk_param *, unsigned int size, u_int8_t proto,
 int xt_check_target(struct xt_tgchk_param *, unsigned int size, u_int8_t proto,
 		    bool inv_proto);
 
+void *xt_copy_counters_from_user(const void __user *user, unsigned int len,
+				 struct xt_counters_info *info, bool compat);
+
 struct xt_table *xt_register_table(struct net *net,
 				   const struct xt_table *table,
 				   struct xt_table_info *bootstrap,
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 49620aa..2953ee9 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -1123,56 +1123,18 @@ static int do_add_counters(struct net *net, const void __user *user,
 	unsigned int i, curcpu;
 	struct xt_counters_info tmp;
 	struct xt_counters *paddc;
-	unsigned int num_counters;
-	const char *name;
-	int size;
-	void *ptmp;
 	struct xt_table *t;
 	const struct xt_table_info *private;
 	int ret = 0;
 	void *loc_cpu_entry;
 	struct arpt_entry *iter;
 	unsigned int addend;
-#ifdef CONFIG_COMPAT
-	struct compat_xt_counters_info compat_tmp;
-
-	if (compat) {
-		ptmp = &compat_tmp;
-		size = sizeof(struct compat_xt_counters_info);
-	} else
-#endif
-	{
-		ptmp = &tmp;
-		size = sizeof(struct xt_counters_info);
-	}
 
-	if (copy_from_user(ptmp, user, size) != 0)
-		return -EFAULT;
-
-#ifdef CONFIG_COMPAT
-	if (compat) {
-		num_counters = compat_tmp.num_counters;
-		name = compat_tmp.name;
-	} else
-#endif
-	{
-		num_counters = tmp.num_counters;
-		name = tmp.name;
-	}
-
-	if (len != size + num_counters * sizeof(struct xt_counters))
-		return -EINVAL;
-
-	paddc = vmalloc(len - size);
-	if (!paddc)
-		return -ENOMEM;
-
-	if (copy_from_user(paddc, user + size, len - size) != 0) {
-		ret = -EFAULT;
-		goto free;
-	}
+	paddc = xt_copy_counters_from_user(user, len, &tmp, compat);
+	if (IS_ERR(paddc))
+		return PTR_ERR(paddc);
 
-	t = xt_find_table_lock(net, NFPROTO_ARP, name);
+	t = xt_find_table_lock(net, NFPROTO_ARP, tmp.name);
 	if (IS_ERR_OR_NULL(t)) {
 		ret = t ? PTR_ERR(t) : -ENOENT;
 		goto free;
@@ -1180,7 +1142,7 @@ static int do_add_counters(struct net *net, const void __user *user,
 
 	local_bh_disable();
 	private = t->private;
-	if (private->number != num_counters) {
+	if (private->number != tmp.num_counters) {
 		ret = -EINVAL;
 		goto unlock_up_free;
 	}
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index c2d3f0e..3bcf28b 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1310,56 +1310,18 @@ do_add_counters(struct net *net, const void __user *user,
 	unsigned int i, curcpu;
 	struct xt_counters_info tmp;
 	struct xt_counters *paddc;
-	unsigned int num_counters;
-	const char *name;
-	int size;
-	void *ptmp;
 	struct xt_table *t;
 	const struct xt_table_info *private;
 	int ret = 0;
 	void *loc_cpu_entry;
 	struct ipt_entry *iter;
 	unsigned int addend;
-#ifdef CONFIG_COMPAT
-	struct compat_xt_counters_info compat_tmp;
-
-	if (compat) {
-		ptmp = &compat_tmp;
-		size = sizeof(struct compat_xt_counters_info);
-	} else
-#endif
-	{
-		ptmp = &tmp;
-		size = sizeof(struct xt_counters_info);
-	}
 
-	if (copy_from_user(ptmp, user, size) != 0)
-		return -EFAULT;
-
-#ifdef CONFIG_COMPAT
-	if (compat) {
-		num_counters = compat_tmp.num_counters;
-		name = compat_tmp.name;
-	} else
-#endif
-	{
-		num_counters = tmp.num_counters;
-		name = tmp.name;
-	}
-
-	if (len != size + num_counters * sizeof(struct xt_counters))
-		return -EINVAL;
-
-	paddc = vmalloc(len - size);
-	if (!paddc)
-		return -ENOMEM;
-
-	if (copy_from_user(paddc, user + size, len - size) != 0) {
-		ret = -EFAULT;
-		goto free;
-	}
+	paddc = xt_copy_counters_from_user(user, len, &tmp, compat);
+	if (IS_ERR(paddc))
+		return PTR_ERR(paddc);
 
-	t = xt_find_table_lock(net, AF_INET, name);
+	t = xt_find_table_lock(net, AF_INET, tmp.name);
 	if (IS_ERR_OR_NULL(t)) {
 		ret = t ? PTR_ERR(t) : -ENOENT;
 		goto free;
@@ -1367,7 +1329,7 @@ do_add_counters(struct net *net, const void __user *user,
 
 	local_bh_disable();
 	private = t->private;
-	if (private->number != num_counters) {
+	if (private->number != tmp.num_counters) {
 		ret = -EINVAL;
 		goto unlock_up_free;
 	}
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index faad607..5254d76 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1323,56 +1323,17 @@ do_add_counters(struct net *net, const void __user *user, unsigned int len,
 	unsigned int i, curcpu;
 	struct xt_counters_info tmp;
 	struct xt_counters *paddc;
-	unsigned int num_counters;
-	char *name;
-	int size;
-	void *ptmp;
 	struct xt_table *t;
 	const struct xt_table_info *private;
 	int ret = 0;
 	const void *loc_cpu_entry;
 	struct ip6t_entry *iter;
 	unsigned int addend;
-#ifdef CONFIG_COMPAT
-	struct compat_xt_counters_info compat_tmp;
-
-	if (compat) {
-		ptmp = &compat_tmp;
-		size = sizeof(struct compat_xt_counters_info);
-	} else
-#endif
-	{
-		ptmp = &tmp;
-		size = sizeof(struct xt_counters_info);
-	}
-
-	if (copy_from_user(ptmp, user, size) != 0)
-		return -EFAULT;
-
-#ifdef CONFIG_COMPAT
-	if (compat) {
-		num_counters = compat_tmp.num_counters;
-		name = compat_tmp.name;
-	} else
-#endif
-	{
-		num_counters = tmp.num_counters;
-		name = tmp.name;
-	}
-
-	if (len != size + num_counters * sizeof(struct xt_counters))
-		return -EINVAL;
-
-	paddc = vmalloc(len - size);
-	if (!paddc)
-		return -ENOMEM;
-
-	if (copy_from_user(paddc, user + size, len - size) != 0) {
-		ret = -EFAULT;
-		goto free;
-	}
 
-	t = xt_find_table_lock(net, AF_INET6, name);
+	paddc = xt_copy_counters_from_user(user, len, &tmp, compat);
+	if (IS_ERR(paddc))
+		return PTR_ERR(paddc);
+	t = xt_find_table_lock(net, AF_INET6, tmp.name);
 	if (IS_ERR_OR_NULL(t)) {
 		ret = t ? PTR_ERR(t) : -ENOENT;
 		goto free;
@@ -1381,7 +1342,7 @@ do_add_counters(struct net *net, const void __user *user, unsigned int len,
 
 	local_bh_disable();
 	private = t->private;
-	if (private->number != num_counters) {
+	if (private->number != tmp.num_counters) {
 		ret = -EINVAL;
 		goto unlock_up_free;
 	}
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 141ae20..4b850c6 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -754,6 +754,80 @@ int xt_check_target(struct xt_tgchk_param *par,
 }
 EXPORT_SYMBOL_GPL(xt_check_target);
 
+/**
+ * xt_copy_counters_from_user - copy counters and metadata from userspace
+ *
+ * @user: src pointer to userspace memory
+ * @len: alleged size of userspace memory
+ * @info: where to store the xt_counters_info metadata
+ * @compat: true if we setsockopt call is done by 32bit task on 64bit kernel
+ *
+ * Copies counter meta data from @user and stores it in @info.
+ *
+ * vmallocs memory to hold the counters, then copies the counter data
+ * from @user to the new memory and returns a pointer to it.
+ *
+ * If @compat is true, @info gets converted automatically to the 64bit
+ * representation.
+ *
+ * The metadata associated with the counters is stored in @info.
+ *
+ * Return: returns pointer that caller has to test via IS_ERR().
+ * If IS_ERR is false, caller has to vfree the pointer.
+ */
+void *xt_copy_counters_from_user(const void __user *user, unsigned int len,
+				 struct xt_counters_info *info, bool compat)
+{
+	void *mem;
+	u64 size;
+
+#ifdef CONFIG_COMPAT
+	if (compat) {
+		/* structures only differ in size due to alignment */
+		struct compat_xt_counters_info compat_tmp;
+
+		if (len <= sizeof(compat_tmp))
+			return ERR_PTR(-EINVAL);
+
+		len -= sizeof(compat_tmp);
+		if (copy_from_user(&compat_tmp, user, sizeof(compat_tmp)) != 0)
+			return ERR_PTR(-EFAULT);
+
+		strlcpy(info->name, compat_tmp.name, sizeof(info->name));
+		info->num_counters = compat_tmp.num_counters;
+		user += sizeof(compat_tmp);
+	} else
+#endif
+	{
+		if (len <= sizeof(*info))
+			return ERR_PTR(-EINVAL);
+
+		len -= sizeof(*info);
+		if (copy_from_user(info, user, sizeof(*info)) != 0)
+			return ERR_PTR(-EFAULT);
+
+		info->name[sizeof(info->name) - 1] = '\0';
+		user += sizeof(*info);
+	}
+
+	size = sizeof(struct xt_counters);
+	size *= info->num_counters;
+
+	if (size != (u64)len)
+		return ERR_PTR(-EINVAL);
+
+	mem = vmalloc(len);
+	if (!mem)
+		return ERR_PTR(-ENOMEM);
+
+	if (copy_from_user(mem, user, len) == 0)
+		return mem;
+
+	vfree(mem);
+	return ERR_PTR(-EFAULT);
+}
+EXPORT_SYMBOL_GPL(xt_copy_counters_from_user);
+
 #ifdef CONFIG_COMPAT
 int xt_compat_target_offset(const struct xt_target *target)
 {
-- 
2.5.0