3.2.58-rc1 review

---
 net/sctp/sm_make_chunk.c | 4 ++--
 net/sctp/sm_statefuns.c  | 5 -----
 2 files changed, 2 insertions(+), 7 deletions(-)

net/sctp/sm_make_chunk.c +2 -2

@@ -1366,8 +1366,8 @@ static void sctp_chunk_destroy(struct sc
 	BUG_ON(!list_empty(&chunk->list));
 	list_del_init(&chunk->transmitted_list);
 
-	/* Free the chunk skb data and the SCTP_chunk stub itself. */
-	dev_kfree_skb(chunk->skb);
+	consume_skb(chunk->skb);
+	consume_skb(chunk->auth_chunk);
 
 	SCTP_DBG_OBJCNT_DEC(chunk);
 	kmem_cache_free(sctp_chunk_cachep, chunk);

net/sctp/sm_statefuns.c +0 -5

@@ -749,7 +749,6 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(co
 
 		/* Make sure that we and the peer are AUTH capable */
 		if (!sctp_auth_enable || !new_asoc->peer.auth_capable) {
-			kfree_skb(chunk->auth_chunk);
 			sctp_association_free(new_asoc);
 			return sctp_sf_pdiscard(ep, asoc, type, arg, commands);
 		}

@@ -764,10 +763,6 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(co
 		auth.transport = chunk->transport;
 
 		ret = sctp_sf_authenticate(ep, new_asoc, type, &auth);
-
-		/* We can now safely free the auth_chunk clone */
-		kfree_skb(chunk->auth_chunk);
-
 		if (ret != SCTP_IERROR_NO_ERROR) {
 			sctp_association_free(new_asoc);
 			return sctp_sf_pdiscard(ep, asoc, type, arg, commands);

Ben Hutchings

author

2014-04-28 01:11 UTC #2 lore raw

PATCH 2/94 bridge: multicast: add sanity check for query source addresses

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Linus Lüssing <[email protected]>

[ Upstream commit 6565b9eeef194afbb3beec80d6dd2447f4091f8c ]

MLD queries are supposed to have an IPv6 link-local source address according to RFC2710, section 4 and RFC3810, section 5.1.14. This patch adds a sanity check to ignore such broken MLD queries.

Without this check, such malformed MLD queries can result in a denial of service: The queries are ignored by any MLD listener therefore they will not respond with an MLD report. However, without this patch these malformed MLD queries would enable the snooping part in the bridge code, potentially shutting down the according ports towards these hosts for multicast traffic as the bridge did not learn about these listeners.

Reported-by Jan Stancek <[email protected]>

Signed-off-by Linus Lüssing <[email protected]>

Reviewed-by Hannes Frederic Sowa <[email protected]>

---
 net/bridge/br_multicast.c | 6 ++++++
 1 file changed, 6 insertions(+)

net/bridge/br_multicast.c +6 -0

@@ -1138,6 +1138,12 @@ static int br_ip6_multicast_query(struct
 
 	br_multicast_query_received(br, port, !ipv6_addr_any(&ip6h->saddr));
 
+	/* RFC2710+RFC3810 (MLDv1+MLDv2) require link-local source addresses */
+	if (!(ipv6_addr_type(&ip6h->saddr) & IPV6_ADDR_LINKLOCAL)) {
+		err = -EINVAL;
+		goto out;
+	}
+
 	if (skb->len == sizeof(*mld)) {
 		if (!pskb_may_pull(skb, sizeof(*mld))) {
 			err = -EINVAL;

Ben Hutchings

author

2014-04-28 01:11 UTC #3 lore raw

PATCH 3/94 net: unix: non blocking recvmsg() should not return -EINTR

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <[email protected]>

[ Upstream commit de1443916791d75fdd26becb116898277bb0273f ]

Some applications didn't expect recvmsg() on a non blocking socket could return -EINTR. This possibility was added as a side effect of commit b3ca9b02b00704 ("net: fix multithreaded signal handling in unix recv routines").

To hit this bug, you need to be a bit unlucky, as the u->readlock mutex is usually held for very small periods.

Fixes b3ca9b02b00704 ("net: fix multithreaded signal handling in unix recv routines")

Signed-off-by Eric Dumazet <[email protected]>

Cc Rainer Weikusat <[email protected]>

---
 net/unix/af_unix.c | 17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

net/unix/af_unix.c +12 -5

@@ -1771,8 +1771,11 @@ static int unix_dgram_recvmsg(struct kio
 		goto out;
 
 	err = mutex_lock_interruptible(&u->readlock);
-	if (err) {
-		err = sock_intr_errno(sock_rcvtimeo(sk, noblock));
+	if (unlikely(err)) {
+		/* recvmsg() in non blocking mode is supposed to return -EAGAIN
+		 * sk_rcvtimeo is not honored by mutex_lock_interruptible()
+		 */
+		err = noblock ? -EAGAIN : -ERESTARTSYS;
 		goto out;
 	}

@@ -1887,6 +1890,7 @@ static int unix_stream_recvmsg(struct ki
 	struct unix_sock *u = unix_sk(sk);
 	struct sockaddr_un *sunaddr = msg->msg_name;
 	int copied = 0;
+	int noblock = flags & MSG_DONTWAIT;
 	int check_creds = 0;
 	int target;
 	int err = 0;

@@ -1901,7 +1905,7 @@ static int unix_stream_recvmsg(struct ki
 		goto out;
 
 	target = sock_rcvlowat(sk, flags&MSG_WAITALL, size);
-	timeo = sock_rcvtimeo(sk, flags&MSG_DONTWAIT);
+	timeo = sock_rcvtimeo(sk, noblock);
 
 	/* Lock the socket to prevent queue disordering
 	 * while sleeps in memcpy_tomsg

@@ -1913,8 +1917,11 @@ static int unix_stream_recvmsg(struct ki
 	}
 
 	err = mutex_lock_interruptible(&u->readlock);
-	if (err) {
-		err = sock_intr_errno(timeo);
+	if (unlikely(err)) {
+		/* recvmsg() in non blocking mode is supposed to return -EAGAIN
+		 * sk_rcvtimeo is not honored by mutex_lock_interruptible()
+		 */
+		err = noblock ? -EAGAIN : -ERESTARTSYS;
 		goto out;
 	}

Ben Hutchings

author

2014-04-28 01:11 UTC #4 lore raw

PATCH 4/94 vlan: Set correct source MAC address with TX VLAN offload enabled

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Peter Boström <[email protected]>

[ Upstream commit dd38743b4cc2f86be250eaf156cf113ba3dd531a ]

With TX VLAN offload enabled the source MAC address for frames sent using the VLAN interface is currently set to the address of the real interface. This is wrong since the VLAN interface may be configured with a different address.

The bug was introduced in commit 2205369a314e12fcec4781cc73ac9c08fc2b47de ("vlan: Fix header ops passthru when doing TX VLAN offload.").

This patch sets the source address before calling the create function of the real interface.

Signed-off-by Peter Boström <[email protected]>

---
 net/8021q/vlan_dev.c | 3 +++
 1 file changed, 3 insertions(+)

net/8021q/vlan_dev.c +3 -0

@@ -529,6 +529,9 @@ static int vlan_passthru_hard_header(str
 {
 	struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
 
+	if (saddr == NULL)
+		saddr = dev->dev_addr;
+
 	return dev_hard_header(skb, real_dev, type, daddr, saddr, len);
 }

Ben Hutchings

author

2014-04-28 01:11 UTC #5 lore raw

PATCH 5/94 net: socket: error on a negative msg_namelen

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Matthew Leach <[email protected]>

[ Upstream commit dbb490b96584d4e958533fb637f08b557f505657 ]

When copying in a struct msghdr from the user, if the user has set the msg_namelen parameter to a negative value it gets clamped to a valid size due to a comparison between signed and unsigned values.

Ensure the syscall errors when the user passes in a negative value.

Signed-off-by Matthew Leach <[email protected]>

---
 net/socket.c | 4 ++++
 1 file changed, 4 insertions(+)

net/socket.c +4 -0

@@ -1884,6 +1884,10 @@ static int copy_msghdr_from_user(struct
 {
 	if (copy_from_user(kmsg, umsg, sizeof(struct msghdr)))
 		return -EFAULT;
+
+	if (kmsg->msg_namelen < 0)
+		return -EINVAL;
+
 	if (kmsg->msg_namelen > sizeof(struct sockaddr_storage))
 		kmsg->msg_namelen = sizeof(struct sockaddr_storage);
 	return 0;

Ben Hutchings

author

2014-04-28 01:11 UTC #6 lore raw

PATCH 6/94 ipv6: Avoid unnecessary temporary addresses being generated

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Heiner Kallweit <[email protected]>

[ Upstream commit ecab67015ef6e3f3635551dcc9971cf363cc1cd5 ]

tmp_prefered_lft is an offset to ifp->tstamp, not now. Therefore age needs to be added to the condition.

Age calculation in ipv6_create_tempaddr is different from the one in addrconf_verify and doesn't consider ADDRCONF_TIMER_FUZZ_MINUS. This can cause age in ipv6_create_tempaddr to be less than the one in addrconf_verify and therefore unnecessary temporary address to be generated.
Use age calculation as in addrconf_modify to avoid this.

Signed-off-by Heiner Kallweit <[email protected]>

---
 net/ipv6/addrconf.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

net/ipv6/addrconf.c +4 -1

@@ -900,8 +900,11 @@ retry:
 	 * Lifetime is greater than REGEN_ADVANCE time units.  In particular,
 	 * an implementation must not create a temporary address with a zero
 	 * Preferred Lifetime.
+	 * Use age calculation as in addrconf_verify to avoid unnecessary
+	 * temporary addresses being generated.
 	 */
-	if (tmp_prefered_lft <= regen_advance) {
+	age = (now - tmp_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ;
+	if (tmp_prefered_lft <= regen_advance + age) {
 		in6_ifa_put(ifp);
 		in6_dev_put(idev);
 		ret = -1;

Ben Hutchings

author

2014-04-28 01:11 UTC #7 lore raw

PATCH 7/94 ipv6: ip6_append_data_mtu do not handle the mtu of the second fragment properly

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: lucien <[email protected]>

[ Upstream commit e367c2d03dba4c9bcafad24688fadb79dd95b218 ]

In ip6_append_data_mtu(), when the xfrm mode is not tunnel(such as transport),the ipsec header need to be added in the first fragment, so the mtu will decrease to reserve space for it, then the second fragment come, the mtu should be turn back, as the commit 0c1833797a5a6ec23ea9261d979aa18078720b74 said. however, in the commit a493e60ac4bbe2e977e7129d6d8cbb0dd236be, it use *mtu = min(*mtu, ...) to change the mtu, which lead to the new mtu is alway equal with the first fragment's. and cannot turn back.

when I test through ping6 -c1 -s5000 $ip (mtu=1280):
...frag (0|1232) ESP(spi=0x00002000,seq=0xb), length 1232

...frag (1232|1216)
...frag (2448|1216)
...frag (3664|1216)
...frag (4880|164)

which should be:
...frag (0|1232) ESP(spi=0x00001000,seq=0x1), length 1232

...frag (1232|1232)
...frag (2464|1232)
...frag (3696|1232)
...frag (4928|116)

so delete the min() when change back the mtu.

Signed-off-by Xin Long <[email protected]>

Fixes 75a493e60ac4bb ("ipv6: ip6_append_data_mtu did not care about pmtudisc and frag_size")

Acked-by Hannes Frederic Sowa <[email protected]>

---
 net/ipv6/ip6_output.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

net/ipv6/ip6_output.c +6 -8

@@ -1191,21 +1191,19 @@ static void ip6_append_data_mtu(unsigned
 				unsigned int fragheaderlen,
 				struct sk_buff *skb,
 				struct rt6_info *rt,
-				bool pmtuprobe)
+				unsigned int orig_mtu)
 {
 	if (!(rt->dst.flags & DST_XFRM_TUNNEL)) {
 		if (skb == NULL) {
 			/* first fragment, reserve header_len */
-			*mtu = *mtu - rt->dst.header_len;
+			*mtu = orig_mtu - rt->dst.header_len;
 
 		} else {
 			/*
 			 * this fragment is not first, the headers
 			 * space is regarded as data space.
 			 */
-			*mtu = min(*mtu, pmtuprobe ?
-				   rt->dst.dev->mtu :
-				   dst_mtu(rt->dst.path));
+			*mtu = orig_mtu;
 		}
 		*maxfraglen = ((*mtu - fragheaderlen) & ~7)
 			      + fragheaderlen - sizeof(struct frag_hdr);

@@ -1222,7 +1220,7 @@ int ip6_append_data(struct sock *sk, int
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct inet_cork *cork;
 	struct sk_buff *skb, *skb_prev = NULL;
-	unsigned int maxfraglen, fragheaderlen, mtu;
+	unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu;
 	int exthdrlen;
 	int dst_exthdrlen;
 	int hh_len;

@@ -1307,6 +1305,7 @@ int ip6_append_data(struct sock *sk, int
 		dst_exthdrlen = 0;
 		mtu = cork->fragsize;
 	}
+	orig_mtu = mtu;
 
 	hh_len = LL_RESERVED_SPACE(rt->dst.dev);

@@ -1389,8 +1388,7 @@ alloc_new_skb:
 			if (skb == NULL || skb_prev == NULL)
 				ip6_append_data_mtu(&mtu, &maxfraglen,
 						    fragheaderlen, skb, rt,
-						    np->pmtudisc ==
-						    IPV6_PMTUDISC_PROBE);
+						    orig_mtu);
 
 			skb_prev = skb;

Ben Hutchings

author

2014-04-28 01:11 UTC #8 lore raw

PATCH 8/94 vhost: fix total length when packets are too short

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: "Michael S. Tsirkin" <[email protected]>

[ Upstream commit d8316f3991d207fe32881a9ac20241be8fa2bad0 ]

When mergeable buffers are disabled, and the incoming packet is too large for the rx buffer, get_rx_bufs returns success.

This was intentional in order for make recvmsg truncate the packet and then handle_rx would detect err != sock_len and drop it.

Unfortunately we pass the original sock_len to recvmsg - which means we use parts of iov not fully validated.

Fix this up by detecting this overrun and doing packet drop immediately.

CVE-2014-0077

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 drivers/vhost/net.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

drivers/vhost/net.c +14 -0

@@ -346,6 +346,12 @@ static int get_rx_bufs(struct vhost_virt
 	*iovcount = seg;
 	if (unlikely(log))
 		*log_num = nlogs;
+
+	/* Detect overrun */
+	if (unlikely(datalen > 0)) {
+		r = UIO_MAXIOV + 1;
+		goto err;
+	}
 	return headcount;
 err:
 	vhost_discard_vq_desc(vq, headcount);

@@ -400,6 +406,14 @@ static void handle_rx(struct vhost_net *
 		/* On error, stop handling until the next kick. */
 		if (unlikely(headcount < 0))
 			break;
+		/* On overrun, truncate and discard */
+		if (unlikely(headcount > UIO_MAXIOV)) {
+			msg.msg_iovlen = 1;
+			err = sock->ops->recvmsg(NULL, sock, &msg,
+						 1, MSG_DONTWAIT | MSG_TRUNC);
+			pr_debug("Discarded rx packet: len %zd\n", sock_len);
+			continue;
+		}
 		/* OK, now we need to know about added descriptors. */
 		if (!headcount) {
 			if (unlikely(vhost_enable_notify(&net->dev, vq))) {

Ben Hutchings

author

2014-04-28 01:11 UTC #9 lore raw

PATCH 9/94 vhost: validate vhost_get_vq_desc return value

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: "Michael S. Tsirkin" <[email protected]>

[ Upstream commit a39ee449f96a2cd44ce056d8a0a112211a9b1a1f ]

vhost fails to validate negative error code from vhost_get_vq_desc causing
a crash: we are using -EFAULT which is 0xfffffff2 as vector size, which exceeds the allocated size.

The code in question was introduced in commit 8dd014adfea6f173c1ef6378f7e5e7924866c923
vhost-net: mergeable buffers support

CVE-2014-0055

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 drivers/vhost/net.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

drivers/vhost/net.c +5 -1

@@ -319,9 +319,13 @@ static int get_rx_bufs(struct vhost_virt
 			r = -ENOBUFS;
 			goto err;
 		}
-		d = vhost_get_vq_desc(vq->dev, vq, vq->iov + seg,
+		r = vhost_get_vq_desc(vq->dev, vq, vq->iov + seg,
 				      ARRAY_SIZE(vq->iov) - seg, &out,
 				      &in, log, log_num);
+		if (unlikely(r < 0))
+			goto err;
+
+		d = r;
 		if (d == vq->num) {
 			r = 0;
 			goto err;

Ben Hutchings

author

2014-04-28 01:11 UTC #10 lore raw

PATCH 10/94 xen-netback: remove pointless clause from if statement

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Paul Durrant <[email protected]>

[ Upstream commit 0576eddf24df716d8570ef8ca11452a9f98eaab2 ]

This patch removes a test in start_new_rx_buffer() that checks whether a copy operation is less than MAX_BUFFER_OFFSET in length, since MAX_BUFFER_OFFSET is defined to be PAGE_SIZE and the only caller of start_new_rx_buffer() already limits copy operations to PAGE_SIZE or less.

Signed-off-by Paul Durrant <[email protected]>

Cc Ian Campbell <[email protected]>

Cc Wei Liu <[email protected]>

Cc Sander Eikelenboom <[email protected]>

Reported-By Sander Eikelenboom <[email protected]>

Tested-by Sander Eikelenboom <[email protected]>

---
 drivers/net/xen-netback/netback.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

drivers/net/xen-netback/netback.c +2 -2

@@ -346,8 +346,8 @@ static bool start_new_rx_buffer(int offs
 	 * into multiple copies tend to give large frags their
 	 * own buffers as before.
 	 */
-	if ((offset + size > MAX_BUFFER_OFFSET) &&
-	    (size <= MAX_BUFFER_OFFSET) && offset && !head)
+	BUG_ON(size > MAX_BUFFER_OFFSET);
+	if ((offset + size > MAX_BUFFER_OFFSET) && offset && !head)
 		return true;
 
 	return false;

Ben Hutchings

author

2014-04-28 01:11 UTC #11 lore raw

PATCH 11/94 ipv6: some ipv6 statistic counters failed to disable bh

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Hannes Frederic Sowa <[email protected]>

[ Upstream commit 43a43b6040165f7b40b5b489fe61a4cb7f8c4980 ]

After commit c15b1ccadb323ea ("ipv6: move DAD and addrconf_verify processing to workqueue") some counters are now updated in process context and thus need to disable bh before doing so, otherwise deadlocks can happen on 32-bit archs. Fabio Estevam noticed this while while mounting a NFS volume on an ARM board.

As a compensation for missing this I looked after the other *_STATS_BH and found three other calls which need updating:

1) icmp6_send: ip6_fragment -> icmpv6_send -> icmp6_send (error handling)
2) ip6_push_pending_frames: rawv6_sendmsg -> rawv6_push_pending_frames -> ... (only in case of icmp protocol with raw sockets in error handling)
3) ping6_v6_sendmsg (error handling)

Fixes c15b1ccadb323ea ("ipv6: move DAD and addrconf_verify processing to workqueue")

Reported-by Fabio Estevam <[email protected]>

Tested-by Fabio Estevam <[email protected]>

Cc Eric Dumazet <[email protected]>

Signed-off-by Hannes Frederic Sowa <[email protected]>

---
 net/ipv6/icmp.c       |  2 +-
 net/ipv6/ip6_output.c |  4 ++--
 net/ipv6/mcast.c      | 11 ++++++-----
 3 files changed, 9 insertions(+), 8 deletions(-)

net/ipv6/icmp.c +1 -1

@@ -499,7 +499,7 @@ void icmpv6_send(struct sk_buff *skb, u8
 			      np->tclass, NULL, &fl6, (struct rt6_info*)dst,
 			      MSG_DONTWAIT, np->dontfrag);
 	if (err) {
-		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTERRORS);
+		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS);
 		ip6_flush_pending_frames(sk);
 	} else {
 		err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr,

net/ipv6/ip6_output.c +2 -2

@@ -1658,8 +1658,8 @@ int ip6_push_pending_frames(struct sock
 	if (proto == IPPROTO_ICMPV6) {
 		struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
 
-		ICMP6MSGOUT_INC_STATS_BH(net, idev, icmp6_hdr(skb)->icmp6_type);
-		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS);
+		ICMP6MSGOUT_INC_STATS(net, idev, icmp6_hdr(skb)->icmp6_type);
+		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
 	}
 
 	err = ip6_local_out(skb);

net/ipv6/mcast.c +6 -5

@@ -1435,11 +1435,12 @@ static void mld_sendpack(struct sk_buff
 		      dst_output);
 out:
 	if (!err) {
-		ICMP6MSGOUT_INC_STATS_BH(net, idev, ICMPV6_MLD2_REPORT);
-		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS);
-		IP6_UPD_PO_STATS_BH(net, idev, IPSTATS_MIB_OUTMCAST, payload_len);
-	} else
-		IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_OUTDISCARDS);
+		ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT);
+		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
+		IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, payload_len);
+	} else {
+		IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
+	}
 
 	rcu_read_unlock();
 	return;

Ben Hutchings

author

2014-04-28 01:11 UTC #12 lore raw

PATCH 12/94 netlink: don't compare the nul-termination in nla_strcmp

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Pablo Neira <[email protected]>

[ Upstream commit 8b7b932434f5eee495b91a2804f5b64ebb2bc835 ]

nla_strcmp compares the string length plus one, so it's implicitly including the nul-termination in the comparison.

int nla_strcmp(const struct nlattr *nla, const char *str)

 {
        int len = strlen(str) + 1;
        ...
                d = memcmp(nla_data(nla), str, len);

However, if NLA_STRING is used, userspace can send us a string without the nul-termination. This is a problem since the string comparison will not match as the last byte may be not the nul-termination.

Fix this by skipping the comparison of the nul-termination if the attribute data is nul-terminated. Suggested by Thomas Graf.

Cc Florian Westphal <[email protected]>

Cc Thomas Graf <[email protected]>

Signed-off-by Pablo Neira Ayuso <[email protected]>

---
 lib/nlattr.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

lib/nlattr.c +8 -2

@@ -299,9 +299,15 @@ int nla_memcmp(const struct nlattr *nla,
  */
 int nla_strcmp(const struct nlattr *nla, const char *str)
 {
-	int len = strlen(str) + 1;
-	int d = nla_len(nla) - len;
+	int len = strlen(str);
+	char *buf = nla_data(nla);
+	int attrlen = nla_len(nla);
+	int d;
 
+	if (attrlen > 0 && buf[attrlen - 1] == '\0')
+		attrlen--;
+
+	d = attrlen - len;
 	if (d == 0)
 		d = memcmp(nla_data(nla), str, len);

Ben Hutchings

author

2014-04-28 01:11 UTC #13 lore raw

PATCH 13/94 isdnloop: Validate NUL-terminated strings from user.

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: YOSHIFUJI Hideaki / 吉藤英明 <[email protected]>

[ Upstream commit 77bc6bed7121936bb2e019a8c336075f4c8eef62 ]

Return -EINVAL unless all of user-given strings are correctly NUL-terminated.

Signed-off-by YOSHIFUJI Hideaki <[email protected]>

---
 drivers/isdn/isdnloop/isdnloop.c | 6 ++++++
 1 file changed, 6 insertions(+)

drivers/isdn/isdnloop/isdnloop.c +6 -0

@@ -1070,6 +1070,12 @@ isdnloop_start(isdnloop_card * card, isd
 		return -EBUSY;
 	if (copy_from_user((char *) &sdef, (char *) sdefp, sizeof(sdef)))
 		return -EFAULT;
+
+	for (i = 0; i < 3; i++) {
+		if (!memchr(sdef.num[i], 0, sizeof(sdef.num[i])))
+			return -EINVAL;
+	}
+
 	spin_lock_irqsave(&card->isdnloop_lock, flags);
 	switch (sdef.ptype) {
 		case ISDN_PTYPE_EURO:

Ben Hutchings

author

2014-04-28 01:11 UTC #14 lore raw

PATCH 14/94 isdnloop: several buffer overflows

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Dan Carpenter <[email protected]>

[ Upstream commit 7563487cbf865284dcd35e9ef5a95380da046737 ]

There are three buffer overflows addressed in this patch.

1) In isdnloop_fake_err() we add an 'E' to a 60 character string and then copy it into a 60 character buffer. I have made the destination buffer 64 characters and I'm changed the sprintf() to a snprintf().

2) In isdnloop_parse_cmd(), p points to a 6 characters into a 60 character buffer so we have 54 characters. The ->eazlist[] is 11 characters long. I have modified the code to return if the source buffer is too long.

3) In isdnloop_command() the cbuf[] array was 60 characters long but the max length of the string then can be up to 79 characters. I made the cbuf array 80 characters long and changed the sprintf() to snprintf(). I also removed the temporary "dial" buffer and changed it to use "p" directly.

Unfortunately, we pass the "cbuf" string from isdnloop_command() to isdnloop_writecmd() which truncates anything over 60 characters to make it fit in card->omsg[]. (It can accept values up to 255 characters so long as there is a '\n' character every 60 characters). For now I have just fixed the memory corruption bug and left the other problems in this driver alone.

Signed-off-by Dan Carpenter <[email protected]>

---
 drivers/isdn/isdnloop/isdnloop.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

drivers/isdn/isdnloop/isdnloop.c +9 -8

@@ -518,9 +518,9 @@ static isdnloop_stat isdnloop_cmd_table[
 static void
 isdnloop_fake_err(isdnloop_card * card)
 {
-	char buf[60];
+	char buf[64];
 
-	sprintf(buf, "E%s", card->omsg);
+	snprintf(buf, sizeof(buf), "E%s", card->omsg);
 	isdnloop_fake(card, buf, -1);
 	isdnloop_fake(card, "NAK", -1);
 }

@@ -903,6 +903,8 @@ isdnloop_parse_cmd(isdnloop_card * card)
 		case 7:
 			/* 0x;EAZ */
 			p += 3;
+			if (strlen(p) >= sizeof(card->eazlist[0]))
+				break;
 			strcpy(card->eazlist[ch - 1], p);
 			break;
 		case 8:

@@ -1133,7 +1135,7 @@ isdnloop_command(isdn_ctrl * c, isdnloop
 {
 	ulong a;
 	int i;
-	char cbuf[60];
+	char cbuf[80];
 	isdn_ctrl cmd;
 	isdnloop_cdef cdef;

@@ -1198,7 +1200,6 @@ isdnloop_command(isdn_ctrl * c, isdnloop
 				break;
 			if ((c->arg & 255) < ISDNLOOP_BCH) {
 				char *p;
-				char dial[50];
 				char dcode[4];
 
 				a = c->arg;

@@ -1210,10 +1211,10 @@ isdnloop_command(isdn_ctrl * c, isdnloop
 				} else
 					/* Normal Dial */
 					strcpy(dcode, "CAL");
-				strcpy(dial, p);
-				sprintf(cbuf, "%02d;D%s_R%s,%02d,%02d,%s\n", (int) (a + 1),
-					dcode, dial, c->parm.setup.si1,
-				c->parm.setup.si2, c->parm.setup.eazmsn);
+				snprintf(cbuf, sizeof(cbuf),
+					 "%02d;D%s_R%s,%02d,%02d,%s\n", (int) (a + 1),
+					 dcode, p, c->parm.setup.si1,
+					 c->parm.setup.si2, c->parm.setup.eazmsn);
 				i = isdnloop_writecmd(cbuf, strlen(cbuf), 0, card);
 			}
 			break;

Ben Hutchings

author

2014-04-28 01:11 UTC #15 lore raw

PATCH 15/94 rds: prevent dereference of a NULL device in rds_iw_laddr_check

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Sasha Levin <[email protected]>

[ Upstream commit bf39b4247b8799935ea91d90db250ab608a58e50 ]

Binding might result in a NULL device which is later dereferenced without checking.

Signed-off-by Sasha Levin <[email protected]>

---
 net/rds/iw.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

net/rds/iw.c +2 -1

@@ -239,7 +239,8 @@ static int rds_iw_laddr_check(__be32 add
 	ret = rdma_bind_addr(cm_id, (struct sockaddr *)&sin);
 	/* due to this, we will claim to support IB devices unless we
 	   check node_type. */
-	if (ret || cm_id->device->node_type != RDMA_NODE_RNIC)
+	if (ret || !cm_id->device ||
+	    cm_id->device->node_type != RDMA_NODE_RNIC)
 		ret = -EADDRNOTAVAIL;
 
 	rdsdebug("addr %pI4 ret %d node type %d\n",

Ben Hutchings

author

2014-04-28 01:11 UTC #16 lore raw

PATCH 16/94 sparc: PCI: Fix incorrect address calculation of PCI Bridge windows on Simba-bridges

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: oftedal <[email protected]>

[ Upstream commit 557fc5873ef178c4b3e1e36a42db547ecdc43f9b ]

The SIMBA APB Bridges lacks the 'ranges' of-property describing the PCI I/O and memory areas located beneath the bridge. Faking this information has been performed by reading range registers in the APB bridge, and calculating the corresponding areas.

In commit 01f94c4a6ced476ce69b895426fc29bfc48c69bd ("Fix sabre pci controllers with new probing scheme.") a bug was introduced into this calculation, causing the PCI memory areas to be calculated incorrectly: The shift size was set to be identical for I/O and MEM ranges, which is incorrect.

This patch set the shift size of the MEM range back to the value used before 01f94c4a6ced476ce69b895426fc29bfc48c69bd.

Signed-off-by Kjetil Oftedal <[email protected]>

---
 arch/sparc/kernel/pci.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

arch/sparc/kernel/pci.c +2 -2

index 31111e3..656b5b6 100644
@@ -487,8 +487,8 @@ static void __devinit apb_fake_ranges(struct pci_dev *dev,
 	pci_read_config_byte(dev, APB_MEM_ADDRESS_MAP, &map);
 	apb_calc_first_last(map, &first, &last);
 	res = bus->resource[1];
-	res->start = (first << 21);
-	res->end = (last << 21) + ((1 << 21) - 1);
+	res->start = (first << 29);
+	res->end = (last << 29) + ((1 << 29) - 1);
 	res->flags = IORESOURCE_MEM;
 	pci_resource_adjust(res, &pbm->mem_space);
 }

Ben Hutchings

author

2014-04-28 01:11 UTC #17 lore raw

PATCH 17/94 Revert "sparc64: Fix __copy_{to,from}_user_inatomic defines."

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Dave Kleikamp <[email protected]>

[ Upstream commit 16932237f2978a2265662f8de4af743b1f55a209 ]

This reverts commit 145e1c0023585e0e8f6df22316308ec61c5066b2.

This commit broke the behavior of __copy_from_user_inatomic when it is only partially successful. Instead of returning the number of bytes not copied, it now returns 1. This translates to the wrong value being returned by iov_iter_copy_from_user_atomic.

xfstests generic/246 and LTP writev01 both fail on btrfs and nfs because of this.

Signed-off-by Dave Kleikamp <[email protected]>

Cc Hugh Dickins <[email protected]>

Cc David S. Miller <[email protected]>

Cc [email protected]

---
 arch/sparc/include/asm/uaccess_64.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

arch/sparc/include/asm/uaccess_64.h +2 -2

index 3e1449f..6d6c731 100644
@@ -267,8 +267,8 @@ extern long __strnlen_user(const char __user *, long len);
 
 #define strlen_user __strlen_user
 #define strnlen_user __strnlen_user
-#define __copy_to_user_inatomic ___copy_to_user
-#define __copy_from_user_inatomic ___copy_from_user
+#define __copy_to_user_inatomic __copy_to_user
+#define __copy_from_user_inatomic __copy_from_user
 
 #endif  /* __ASSEMBLY__ */

Ben Hutchings

author

2014-04-28 01:11 UTC #18 lore raw

PATCH 18/94 sparc32: fix build failure for arch_jump_label_transform

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Paul Gortmaker <[email protected]>

[ Upstream commit 4f6500fff5f7644a03c46728fd7ef0f62fa6940b ]

In arch/sparc/Kernel/Makefile, we see:

   obj-$(CONFIG_SPARC64)   += jump_label.o

However, the Kconfig selects HAVE_ARCH_JUMP_LABEL unconditionally for all SPARC. This in turn leads to the following failure when doing allmodconfig coverage builds:

kernel/built-in.o: In function `__jump_label_update':
jump_label.c:(.text+0x8560c): undefined reference to arch_jump_label_transform' kernel/built-in.o: In function arch_jump_label_transform_static':
(.text+0x85cf4): undefined reference to `arch_jump_label_transform'
make: *** [vmlinux] Error 1

Change HAVE_ARCH_JUMP_LABEL to be conditional on SPARC64 so that it matches the Makefile.

Signed-off-by Paul Gortmaker <[email protected]>

---
 arch/sparc/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

arch/sparc/Kconfig +1 -1

index 87537e2..88d442d 100644
@@ -24,7 +24,7 @@ config SPARC
 	select HAVE_IRQ_WORK
 	select HAVE_DMA_ATTRS
 	select HAVE_DMA_API_DEBUG
-	select HAVE_ARCH_JUMP_LABEL
+	select HAVE_ARCH_JUMP_LABEL if SPARC64
 	select HAVE_GENERIC_HARDIRQS
 	select GENERIC_IRQ_SHOW
 	select USE_GENERIC_SMP_HELPERS if SMP

Ben Hutchings

author

2014-04-28 01:11 UTC #19 lore raw

PATCH 19/94 sparc64: don't treat 64-bit syscall return codes as 32-bit

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Dave Kleikamp <[email protected]>

[ Upstream commit 1535bd8adbdedd60a0ee62e28fd5225d66434371 ]

When checking a system call return code for an error, linux_sparc_syscall was sign-extending the lower 32-bit value and comparing it to -ERESTART_RESTARTBLOCK. lseek can return valid return codes whose lower 32-bits alone would indicate a failure (such as 4G-1). Use the whole 64-bit value to check for errors. Only the 32-bit path should sign extend the lower 32-bit value.

Signed-off-by Dave Kleikamp <[email protected]>

Acked-by Bob Picco <[email protected]>

Acked-by Allen Pais <[email protected]>

Cc David S. Miller <[email protected]>

Cc [email protected]

---
 arch/sparc/kernel/syscalls.S | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

arch/sparc/kernel/syscalls.S +2 -2

index 817187d..557212c 100644
@@ -184,7 +184,8 @@ linux_sparc_syscall32:
 	 mov	%i0, %l5				! IEU1
 5:	call	%l7					! CTI	Group brk forced
 	 srl	%i5, 0, %o5				! IEU1
-	ba,a,pt	%xcc, 3f
+	ba,pt	%xcc, 3f
+	 sra	%o0, 0, %o0
 
 	/* Linux native system calls enter here... */
 	.align	32

@@ -212,7 +213,6 @@ linux_sparc_syscall:
 3:	stx	%o0, [%sp + PTREGS_OFF + PT_V9_I0]
 ret_sys_call:
 	ldx	[%sp + PTREGS_OFF + PT_V9_TSTATE], %g3
-	sra	%o0, 0, %o0
 	mov	%ulo(TSTATE_XCARRY | TSTATE_ICARRY), %g2
 	sllx	%g2, 32, %g2

Ben Hutchings

author

2014-04-28 01:11 UTC #20 lore raw

PATCH 20/94 ipv6: don't set DST_NOCOUNT for remotely added routes

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Sabrina Dubroca <[email protected]>

commit c88507fbad8055297c1d1e21e599f46960cbee39 upstream.

DST_NOCOUNT should only be used if an authorized user adds routes locally. In case of routes which are added on behalf of router advertisments this flag must not get used as it allows an unlimited number of routes getting added remotely.

Signed-off-by Sabrina Dubroca <[email protected]>

Acked-by Hannes Frederic Sowa <[email protected]>

[bwh: Backported to 3.2: adjust context]

Acked-by David S. Miller <[email protected]>

---
 net/ipv6/route.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

net/ipv6/route.c +1 -1

@@ -1250,7 +1250,7 @@ int ip6_route_add(struct fib6_config *cf
 		goto out;
 	}
 
-	rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, NULL, DST_NOCOUNT);
+	rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, NULL, (cfg->fc_flags & RTF_ADDRCONF) ? 0 : DST_NOCOUNT);
 
 	if (rt == NULL) {
 		err = -ENOMEM;

Ben Hutchings

author

2014-04-28 01:11 UTC #21 lore raw

PATCH 21/94 drm/i915: inverted brightness quirk for Acer Aspire 4736Z

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Daniel Vetter <[email protected]>

commit ac4199e0f047546aa40172785e26c82b54bbe811 upstream.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=53881

Cc Jani Nikula <[email protected]>

Tested-by Jani Monoses <[email protected]>

Signed-off-by Daniel Vetter <[email protected]>

[bwh: Backported to 3.2: adjust context]

---
 drivers/gpu/drm/i915/intel_display.c | 3 +++
 1 file changed, 3 insertions(+)

drivers/gpu/drm/i915/intel_display.c +3 -0

@@ -8946,6 +8946,9 @@ struct intel_quirk intel_quirks[] = {
 	/* Acer/Packard Bell NCL20 */
 	{ 0x2a42, 0x1025, 0x034b, quirk_invert_brightness },
 
+	/* Acer Aspire 4736Z */
+	{ 0x2a42, 0x1025, 0x0260, quirk_invert_brightness },
+
 	/* Dell XPS13 HD Sandy Bridge */
 	{ 0x0116, 0x1028, 0x052e, quirk_no_pcm_pwm_enable },
 	/* Dell XPS13 HD and XPS13 FHD Ivy Bridge */

Ben Hutchings

author

2014-04-28 01:11 UTC #22 lore raw

PATCH 22/94 drm/i915: quirk invert brightness for Acer Aspire 5336

http://patchwork.freedesktop.org/patch/17837/

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Jani Nikula <[email protected]>

commit 0f540c3a7cfb91c9d7a19eb0c95c24c5de1197d5 upstream.

Since
commit ee1452d7458451a7508e0663553ce88d63958157

Author: Jani Nikula <[email protected]>
Date:   Fri Sep 20 15:05:30 2013 +0300

drm/i915: assume all GM45 Acer laptops use inverted backlight PWM

failed and was later reverted in
commit be505f643925e257087247b996cd8ece787c12af

Author: Alexander van Heukelum <[email protected]>
Date:   Sat Dec 28 21:00:39 2013 +0100

Revert "drm/i915: assume all GM45 Acer laptops use inverted backlight PWM"

fix the individual broken machine instead.

Note to backporters:

is the patch you want for 3.13 and older.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=54171
Reference: http://mid.gmane.org/[email protected]

Signed-off-by Jani Nikula <[email protected]>

Reviewed-by Ville Syrjälä <[email protected]>

[danvet: Patch mangling for 3.14 plus adding the link to the original for 3.13.]

Signed-off-by Daniel Vetter <[email protected]>

---
 drivers/gpu/drm/i915/intel_display.c | 3 +++
 1 file changed, 3 insertions(+)

drivers/gpu/drm/i915/intel_display.c +3 -0

@@ -8949,6 +8949,9 @@ struct intel_quirk intel_quirks[] = {
 	/* Acer Aspire 4736Z */
 	{ 0x2a42, 0x1025, 0x0260, quirk_invert_brightness },
 
+	/* Acer Aspire 5336 */
+	{ 0x2a42, 0x1025, 0x048a, quirk_invert_brightness },
+
 	/* Dell XPS13 HD Sandy Bridge */
 	{ 0x0116, 0x1028, 0x052e, quirk_no_pcm_pwm_enable },
 	/* Dell XPS13 HD and XPS13 FHD Ivy Bridge */

Ben Hutchings

author

2014-04-28 01:11 UTC #23 lore raw

PATCH 23/94 w1: fix w1_send_slave dropping a slave id

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: David Fries <[email protected]>

commit 6b355b33a64fd6d8ead2b838ec16fb9b551f71e8 upstream.

Previous logic,

if (avail > 8) {
	store slave;
	return;
}

send data; clear;

The logic error is, if there isn't space send the buffer and clear, but the slave wasn't added to the now empty buffer loosing that slave id. It also should have been "if (avail >= 8)" because when it is 8, there is space.

Instead, if there isn't space send and clear the buffer, then there is always space for the slave id.

Signed-off-by David Fries <[email protected]>

Acked-by Evgeniy Polyakov <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/w1/w1_netlink.c | 25 +++++++++++++------------
 1 file changed, 13 insertions(+), 12 deletions(-)

drivers/w1/w1_netlink.c +14 ~~-13~~

@@ -54,28 +54,29 @@ static void w1_send_slave(struct w1_mast
 	struct w1_netlink_msg *hdr = (struct w1_netlink_msg *)(msg + 1);
 	struct w1_netlink_cmd *cmd = (struct w1_netlink_cmd *)(hdr + 1);
 	int avail;
+	u64 *data;
 
 	/* update kernel slave list */
 	w1_slave_found(dev, rn);
 
 	avail = dev->priv_size - cmd->len;
 
-	if (avail > 8) {
-		u64 *data = (void *)(cmd + 1) + cmd->len;
-
-		*data = rn;
-		cmd->len += 8;
-		hdr->len += 8;
-		msg->len += 8;
-		return;
+	if (avail < 8) {
+		msg->ack++;
+		cn_netlink_send(msg, 0, GFP_KERNEL);
+
+		msg->len = sizeof(struct w1_netlink_msg) +
+			sizeof(struct w1_netlink_cmd);
+		hdr->len = sizeof(struct w1_netlink_cmd);
+		cmd->len = 0;
 	}
 
-	msg->ack++;
-	cn_netlink_send(msg, 0, GFP_KERNEL);
+	data = (void *)(cmd + 1) + cmd->len;
 
-	msg->len = sizeof(struct w1_netlink_msg) + sizeof(struct w1_netlink_cmd);
-	hdr->len = sizeof(struct w1_netlink_cmd);
-	cmd->len = 0;
+	*data = rn;
+	cmd->len += 8;
+	hdr->len += 8;
+	msg->len += 8;
 }
 
 static int w1_process_search_command(struct w1_master *dev, struct cn_msg *msg,

Ben Hutchings

author

2014-04-28 01:11 UTC #24 lore raw

PATCH 24/94 ARM: mm: introduce present, faulting entries for PAGE_NONE

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

commit 26ffd0d43b186b0d5186354da8714a1c2d360df0 upstream.

PROT_NONE mappings apply the page protection attributes defined by _P000 which translate to PAGE_NONE for ARM. These attributes specify an XN, RDONLY pte that is inaccessible to userspace. However, on kernels configured without support for domains, such a pte *is* accessible to the kernel and can be read via get_user, allowing tasks to read PROT_NONE pages via syscalls such as read/write over a pipe.

This patch introduces a new software pte flag, L_PTE_NONE, that is set to identify faulting, present entries.

Signed-off-by Will Deacon <[email protected]>

[bwh: Backported to 3.2 as dependency of commit b6ccb9803e90
('ARM: 7954/1: mm: remove remaining domain support from ARMv6'):
- Drop 3-level changes
- Adjust filename, context]

---

arch/arm/include/asm/pgtable-2level.h +1 -0

@@ -123,6 +123,7 @@
 #define L_PTE_USER		(_AT(pteval_t, 1) << 8)
 #define L_PTE_XN		(_AT(pteval_t, 1) << 9)
 #define L_PTE_SHARED		(_AT(pteval_t, 1) << 10)	/* shared(v6), coherent(xsc3) */
+#define L_PTE_NONE		(_AT(pteval_t, 1) << 11)
 
 /*
  * These are the memory types, defined to be compatible with

arch/arm/include/asm/pgtable.h +3 -3

@@ -74,7 +74,7 @@ extern pgprot_t		pgprot_kernel;
 
 #define _MOD_PROT(p, b)	__pgprot(pgprot_val(p) | (b))
 
-#define PAGE_NONE		_MOD_PROT(pgprot_user, L_PTE_XN | L_PTE_RDONLY)
+#define PAGE_NONE		_MOD_PROT(pgprot_user, L_PTE_XN | L_PTE_RDONLY | L_PTE_NONE)
 #define PAGE_SHARED		_MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_XN)
 #define PAGE_SHARED_EXEC	_MOD_PROT(pgprot_user, L_PTE_USER)
 #define PAGE_COPY		_MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_RDONLY | L_PTE_XN)

@@ -84,7 +84,7 @@ extern pgprot_t		pgprot_kernel;
 #define PAGE_KERNEL		_MOD_PROT(pgprot_kernel, L_PTE_XN)
 #define PAGE_KERNEL_EXEC	pgprot_kernel
 
-#define __PAGE_NONE		__pgprot(_L_PTE_DEFAULT | L_PTE_RDONLY | L_PTE_XN)
+#define __PAGE_NONE		__pgprot(_L_PTE_DEFAULT | L_PTE_RDONLY | L_PTE_XN | L_PTE_NONE)
 #define __PAGE_SHARED		__pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_XN)
 #define __PAGE_SHARED_EXEC	__pgprot(_L_PTE_DEFAULT | L_PTE_USER)
 #define __PAGE_COPY		__pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_RDONLY | L_PTE_XN)

@@ -279,7 +279,7 @@ static inline pte_t pte_mkspecial(pte_t
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
-	const pteval_t mask = L_PTE_XN | L_PTE_RDONLY | L_PTE_USER;
+	const pteval_t mask = L_PTE_XN | L_PTE_RDONLY | L_PTE_USER | L_PTE_NONE;
 	pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask);
 	return pte;
 }

arch/arm/mm/proc-macros.S +4 -0

@@ -166,6 +166,10 @@
 	tst	r1, #L_PTE_YOUNG
 	tstne	r1, #L_PTE_PRESENT
 	moveq	r3, #0
+#ifndef CONFIG_CPU_USE_DOMAINS
+	tstne	r1, #L_PTE_NONE
+	movne	r3, #0
+#endif
 
 	str	r3, [r0]
 	mcr	p15, 0, r0, c7, c10, 1		@ flush_pte

arch/arm/mm/proc-v7.S +4 -0

@@ -171,6 +171,10 @@ ENTRY(cpu_v7_set_pte_ext)
 
 	tst	r1, #L_PTE_YOUNG
 	tstne	r1, #L_PTE_PRESENT
+#ifndef CONFIG_CPU_USE_DOMAINS
+	eorne	r1, r1, #L_PTE_NONE
+	tstne	r1, #L_PTE_NONE
+#endif
 	moveq	r3, #0
 
  ARM(	str	r3, [r0, #2048]! )

Ben Hutchings

author

2014-04-28 01:11 UTC #25 lore raw

PATCH 25/94 ARM: 7954/1: mm: remove remaining domain support from ARMv6

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

commit b6ccb9803e90c16b212cf4ed62913a7591e79a39 upstream.

CPU_32v6 currently selects CPU_USE_DOMAINS if CPU_V6 and MMU. This is because ARM 1136 r0pX CPUs lack the v6k extensions, and therefore do not have hardware thread registers. The lack of these registers requires the kernel to update the vectors page at each context switch in order to write a new TLS pointer. This write must be done via the userspace mapping, since aliasing caches can lead to expensive flushing when using kmap. Finally, this requires the vectors page to be mapped r/w for kernel and r/o for user, which has implications for things like put_user which must trigger CoW appropriately when targetting user pages.

The upshot of all this is that a v6/v7 kernel makes use of domains to segregate kernel and user memory accesses. This has the nasty side-effect of making device mappings executable, which has been observed to cause subtle bugs on recent cores (e.g. Cortex-A15 performing a speculative instruction fetch from the GIC and acking an interrupt in the process).

This patch solves this problem by removing the remaining domain support from ARMv6. A new memory type is added specifically for the vectors page which allows that page (and only that page) to be mapped as user r/o, kernel r/w. All other user r/o pages are mapped also as kernel r/o. Patch co-developed with Russell King.

Signed-off-by Will Deacon <[email protected]>

Signed-off-by Russell King <[email protected]>

[bwh: Backported to 3.2:
- Adjust filename, context
- Drop condition on CONFIG_ARM_LPAE]

---

arch/arm/include/asm/futex.h +0 -6

@@ -3,11 +3,6 @@
 
 #ifdef __KERNEL__
 
-#if defined(CONFIG_CPU_USE_DOMAINS) && defined(CONFIG_SMP)
-/* ARM doesn't provide unprivileged exclusive memory accessors */
-#include <asm-generic/futex.h>
-#else
-
 #include <linux/futex.h>
 #include <linux/uaccess.h>
 #include <asm/errno.h>

@@ -163,6 +158,5 @@ futex_atomic_op_inuser (int encoded_op,
 	return ret;
 }
 
-#endif /* !(CPU_USE_DOMAINS && SMP) */
 #endif /* __KERNEL__ */
 #endif /* _ASM_ARM_FUTEX_H */

arch/arm/include/asm/pgtable-2level.h +1 -0

@@ -139,6 +139,7 @@
 #define L_PTE_MT_DEV_NONSHARED	(_AT(pteval_t, 0x0c) << 2)	/* 1100 */
 #define L_PTE_MT_DEV_WC		(_AT(pteval_t, 0x09) << 2)	/* 1001 */
 #define L_PTE_MT_DEV_CACHED	(_AT(pteval_t, 0x0b) << 2)	/* 1011 */
+#define L_PTE_MT_VECTORS	(_AT(pteval_t, 0x0f) << 2)	/* 1111 */
 #define L_PTE_MT_MASK		(_AT(pteval_t, 0x0f) << 2)
 
 #endif /* _ASM_PGTABLE_2LEVEL_H */

arch/arm/mm/Kconfig +1 -2

@@ -458,7 +458,6 @@ config CPU_32v5
 config CPU_32v6
 	bool
 	select TLS_REG_EMUL if !CPU_32v6K && !MMU
-	select CPU_USE_DOMAINS if CPU_V6 && MMU
 
 config CPU_32v6K
 	bool

@@ -652,7 +651,7 @@ config ARM_THUMBEE
 
 config SWP_EMULATE
 	bool "Emulate SWP/SWPB instructions"
-	depends on !CPU_USE_DOMAINS && CPU_V7
+	depends on CPU_V7
 	select HAVE_PROC_CPU if PROC_FS
 	default y if SMP
 	help

arch/arm/mm/mmu.c +8 -0

@@ -426,6 +426,14 @@ static void __init build_mem_type_table(
 		mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED;
 	}
 	/*
+	 * We don't use domains on ARMv6 (since this causes problems with
+	 * v6/v7 kernels), so we must use a separate memory type for user
+	 * r/o, kernel r/w to map the vectors page.
+	 */
+	if (cpu_arch == CPU_ARCH_ARMv6)
+		vecs_pgprot |= L_PTE_MT_VECTORS;
+
+	/*
 	 * ARMv6 and above have extended page tables.
 	 */
 	if (cpu_arch >= CPU_ARCH_ARMv6 && (cr & CR_XP)) {

arch/arm/mm/proc-macros.S +6 ~~-13~~

@@ -106,13 +106,9 @@
  *  100x   1   0   1	r/o	no acc
  *  10x0   1   0   1	r/o	no acc
  *  1011   0   0   1	r/w	no acc
- *  110x   0   1   0	r/w	r/o
- *  11x0   0   1   0	r/w	r/o
- *  1111   0   1   1	r/w	r/w
- *
- * If !CONFIG_CPU_USE_DOMAINS, the following permissions are changed:
  *  110x   1   1   1	r/o	r/o
  *  11x0   1   1   1	r/o	r/o
+ *  1111   0   1   1	r/w	r/w
  */
 	.macro	armv6_mt_table pfx
 \pfx\()_mt_table:

@@ -131,7 +127,7 @@
 	.long	PTE_EXT_TEX(2)					@ L_PTE_MT_DEV_NONSHARED
 	.long	0x00						@ unused
 	.long	0x00						@ unused
-	.long	0x00						@ unused
+	.long	PTE_CACHEABLE | PTE_BUFFERABLE | PTE_EXT_APX	@ L_PTE_MT_VECTORS
 	.endm
 
 	.macro	armv6_set_pte_ext pfx

@@ -152,24 +148,21 @@
 
 	tst	r1, #L_PTE_USER
 	orrne	r3, r3, #PTE_EXT_AP1
-#ifdef CONFIG_CPU_USE_DOMAINS
-	@ allow kernel read/write access to read-only user pages
 	tstne	r3, #PTE_EXT_APX
-	bicne	r3, r3, #PTE_EXT_APX | PTE_EXT_AP0
-#endif
+
+	@ user read-only -> kernel read-only
+	bicne	r3, r3, #PTE_EXT_AP0
 
 	tst	r1, #L_PTE_XN
 	orrne	r3, r3, #PTE_EXT_XN
 
-	orr	r3, r3, r2
+	eor	r3, r3, r2
 
 	tst	r1, #L_PTE_YOUNG
 	tstne	r1, #L_PTE_PRESENT
 	moveq	r3, #0
-#ifndef CONFIG_CPU_USE_DOMAINS
 	tstne	r1, #L_PTE_NONE
 	movne	r3, #0
-#endif
 
 	str	r3, [r0]
 	mcr	p15, 0, r0, c7, c10, 1		@ flush_pte

arch/arm/mm/proc-v7.S +0 -7

@@ -160,21 +160,14 @@ ENTRY(cpu_v7_set_pte_ext)
 
 	tst	r1, #L_PTE_USER
 	orrne	r3, r3, #PTE_EXT_AP1
-#ifdef CONFIG_CPU_USE_DOMAINS
-	@ allow kernel read/write access to read-only user pages
-	tstne	r3, #PTE_EXT_APX
-	bicne	r3, r3, #PTE_EXT_APX | PTE_EXT_AP0
-#endif
 
 	tst	r1, #L_PTE_XN
 	orrne	r3, r3, #PTE_EXT_XN
 
 	tst	r1, #L_PTE_YOUNG
 	tstne	r1, #L_PTE_PRESENT
-#ifndef CONFIG_CPU_USE_DOMAINS
 	eorne	r1, r1, #L_PTE_NONE
 	tstne	r1, #L_PTE_NONE
-#endif
 	moveq	r3, #0
 
  ARM(	str	r3, [r0, #2048]! )

Ben Hutchings

author

2014-04-28 01:11 UTC #26 lore raw

PATCH 26/94 matroxfb: restore the registers M_ACCESS and M_PITCH

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Mikulas Patocka <[email protected]>

commit a772d4736641ec1b421ad965e13457c17379fc86 upstream.

When X11 is running and the user switches back to console, the card modifies the content of registers M_MACCESS and M_PITCH in periodic intervals.

This patch fixes it by restoring the content of these registers before issuing any accelerator command.

---
 drivers/video/matrox/matroxfb_accel.c | 38 ++++++++++++++++++++++++++---------
 drivers/video/matrox/matroxfb_base.h  |  2 ++
 2 files changed, 30 insertions(+), 10 deletions(-)

drivers/video/matrox/matroxfb_accel.c +28 ~~-10~~

@@ -192,10 +192,18 @@ void matrox_cfbX_init(struct matrox_fb_i
 	minfo->accel.m_dwg_rect = M_DWG_TRAP | M_DWG_SOLID | M_DWG_ARZERO | M_DWG_SGNZERO | M_DWG_SHIFTZERO;
 	if (isMilleniumII(minfo)) minfo->accel.m_dwg_rect |= M_DWG_TRANSC;
 	minfo->accel.m_opmode = mopmode;
+	minfo->accel.m_access = maccess;
+	minfo->accel.m_pitch = mpitch;
 }
 
 EXPORT_SYMBOL(matrox_cfbX_init);
 
+static void matrox_accel_restore_maccess(struct matrox_fb_info *minfo)
+{
+	mga_outl(M_MACCESS, minfo->accel.m_access);
+	mga_outl(M_PITCH, minfo->accel.m_pitch);
+}
+
 static void matrox_accel_bmove(struct matrox_fb_info *minfo, int vxres, int sy,
 			       int sx, int dy, int dx, int height, int width)
 {

@@ -207,7 +215,8 @@ static void matrox_accel_bmove(struct ma
 	CRITBEGIN
 
 	if ((dy < sy) || ((dy == sy) && (dx <= sx))) {
-		mga_fifo(2);
+		mga_fifo(4);
+		matrox_accel_restore_maccess(minfo);
 		mga_outl(M_DWGCTL, M_DWG_BITBLT | M_DWG_SHIFTZERO | M_DWG_SGNZERO |
 			 M_DWG_BFCOL | M_DWG_REPLACE);
 		mga_outl(M_AR5, vxres);

@@ -215,7 +224,8 @@ static void matrox_accel_bmove(struct ma
 		start = sy*vxres+sx+curr_ydstorg(minfo);
 		end = start+width;
 	} else {
-		mga_fifo(3);
+		mga_fifo(5);
+		matrox_accel_restore_maccess(minfo);
 		mga_outl(M_DWGCTL, M_DWG_BITBLT | M_DWG_SHIFTZERO | M_DWG_BFCOL | M_DWG_REPLACE);
 		mga_outl(M_SGN, 5);
 		mga_outl(M_AR5, -vxres);

@@ -224,7 +234,8 @@ static void matrox_accel_bmove(struct ma
 		start = end+width;
 		dy += height-1;
 	}
-	mga_fifo(4);
+	mga_fifo(6);
+	matrox_accel_restore_maccess(minfo);
 	mga_outl(M_AR0, end);
 	mga_outl(M_AR3, start);
 	mga_outl(M_FXBNDRY, ((dx+width)<<16) | dx);

@@ -246,7 +257,8 @@ static void matrox_accel_bmove_lin(struc
 	CRITBEGIN
 
 	if ((dy < sy) || ((dy == sy) && (dx <= sx))) {
-		mga_fifo(2);
+		mga_fifo(4);
+		matrox_accel_restore_maccess(minfo);
 		mga_outl(M_DWGCTL, M_DWG_BITBLT | M_DWG_SHIFTZERO | M_DWG_SGNZERO |
 			M_DWG_BFCOL | M_DWG_REPLACE);
 		mga_outl(M_AR5, vxres);

@@ -254,7 +266,8 @@ static void matrox_accel_bmove_lin(struc
 		start = sy*vxres+sx+curr_ydstorg(minfo);
 		end = start+width;
 	} else {
-		mga_fifo(3);
+		mga_fifo(5);
+		matrox_accel_restore_maccess(minfo);
 		mga_outl(M_DWGCTL, M_DWG_BITBLT | M_DWG_SHIFTZERO | M_DWG_BFCOL | M_DWG_REPLACE);
 		mga_outl(M_SGN, 5);
 		mga_outl(M_AR5, -vxres);

@@ -263,7 +276,8 @@ static void matrox_accel_bmove_lin(struc
 		start = end+width;
 		dy += height-1;
 	}
-	mga_fifo(5);
+	mga_fifo(7);
+	matrox_accel_restore_maccess(minfo);
 	mga_outl(M_AR0, end);
 	mga_outl(M_AR3, start);
 	mga_outl(M_FXBNDRY, ((dx+width)<<16) | dx);

@@ -298,7 +312,8 @@ static void matroxfb_accel_clear(struct
 
 	CRITBEGIN
 
-	mga_fifo(5);
+	mga_fifo(7);
+	matrox_accel_restore_maccess(minfo);
 	mga_outl(M_DWGCTL, minfo->accel.m_dwg_rect | M_DWG_REPLACE);
 	mga_outl(M_FCOL, color);
 	mga_outl(M_FXBNDRY, ((sx + width) << 16) | sx);

@@ -341,7 +356,8 @@ static void matroxfb_cfb4_clear(struct m
 	width >>= 1;
 	sx >>= 1;
 	if (width) {
-		mga_fifo(5);
+		mga_fifo(7);
+		matrox_accel_restore_maccess(minfo);
 		mga_outl(M_DWGCTL, minfo->accel.m_dwg_rect | M_DWG_REPLACE2);
 		mga_outl(M_FCOL, bgx);
 		mga_outl(M_FXBNDRY, ((sx + width) << 16) | sx);

@@ -415,7 +431,8 @@ static void matroxfb_1bpp_imageblit(stru
 
 	CRITBEGIN
 
-	mga_fifo(3);
+	mga_fifo(5);
+	matrox_accel_restore_maccess(minfo);
 	if (easy)
 		mga_outl(M_DWGCTL, M_DWG_ILOAD | M_DWG_SGNZERO | M_DWG_SHIFTZERO | M_DWG_BMONOWF | M_DWG_LINEAR | M_DWG_REPLACE);
 	else

@@ -425,7 +442,8 @@ static void matroxfb_1bpp_imageblit(stru
 	fxbndry = ((xx + width - 1) << 16) | xx;
 	mmio = minfo->mmio.vbase;
 
-	mga_fifo(6);
+	mga_fifo(8);
+	matrox_accel_restore_maccess(minfo);
 	mga_writel(mmio, M_FXBNDRY, fxbndry);
 	mga_writel(mmio, M_AR0, ar0);
 	mga_writel(mmio, M_AR3, 0);

drivers/video/matrox/matroxfb_base.h +2 -0

@@ -307,6 +307,8 @@ struct matrox_accel_data {
 #endif
 	u_int32_t	m_dwg_rect;
 	u_int32_t	m_opmode;
+	u_int32_t	m_access;
+	u_int32_t	m_pitch;
 };
 
 struct v4l2_queryctrl;

Ben Hutchings

author

2014-04-28 01:11 UTC #27 lore raw

PATCH 27/94 framebuffer: fix cfb_copyarea

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Mikulas Patocka <[email protected]>

commit 00a9d699bc85052d2d3ed56251cd928024ce06a3 upstream.

The function cfb_copyarea is buggy when the copy operation is not aligned on long boundary (4 bytes on 32-bit machines, 8 bytes on 64-bit machines).

How to reproduce:
- use x86-64 machine
- use a framebuffer driver without acceleration (for example uvesafb)
- set the framebuffer to 8-bit depth

	(for example fbset -a 1024x768-60 -depth 8)

- load a font with character width that is not a multiple of 8 pixels
note: the console-tools package cannot load a font that has width different from 8 pixels. You need to install the packages "kbd" and "console-terminus" and use the program "setfont" to set font width (for example: setfont Uni2-Terminus20x10)
- move some text left and right on the bash command line and you get a screen corruption

To expose more bugs, put this line to the end of uvesafb_init_info:
info->flags |= FBINFO_HWACCEL_COPYAREA | FBINFO_READS_FAST;
- Now framebuffer console will use cfb_copyarea for console scrolling. You get a screen corruption when console is scrolled.

This patch is a rewrite of cfb_copyarea. It fixes the bugs, with this patch, console scrolling in 8-bit depth with a font width that is not a multiple of 8 pixels works fine.

The cfb_copyarea code was very buggy and it looks like it was written and never tried with non-8-pixel font.

---
 drivers/video/cfbcopyarea.c | 153 ++++++++++++++++++++++----------------------
 1 file changed, 78 insertions(+), 75 deletions(-)

drivers/video/cfbcopyarea.c +78 ~~-75~~

@@ -43,13 +43,22 @@
      */
 
 static void
-bitcpy(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
-		const unsigned long __iomem *src, int src_idx, int bits,
+bitcpy(struct fb_info *p, unsigned long __iomem *dst, unsigned dst_idx,
+		const unsigned long __iomem *src, unsigned src_idx, int bits,
 		unsigned n, u32 bswapmask)
 {
 	unsigned long first, last;
 	int const shift = dst_idx-src_idx;
-	int left, right;
+
+#if 0
+	/*
+	 * If you suspect bug in this function, compare it with this simple
+	 * memmove implementation.
+	 */
+	fb_memmove((char *)dst + ((dst_idx & (bits - 1))) / 8,
+		   (char *)src + ((src_idx & (bits - 1))) / 8, n / 8);
+	return;
+#endif
 
 	first = fb_shifted_pixels_mask_long(p, dst_idx, bswapmask);
 	last = ~fb_shifted_pixels_mask_long(p, (dst_idx+n) % bits, bswapmask);

@@ -98,9 +107,8 @@ bitcpy(struct fb_info *p, unsigned long
 		unsigned long d0, d1;
 		int m;
 
-		right = shift & (bits - 1);
-		left = -shift & (bits - 1);
-		bswapmask &= shift;
+		int const left = shift & (bits - 1);
+		int const right = -shift & (bits - 1);
 
 		if (dst_idx+n <= bits) {
 			// Single destination word

@@ -110,15 +118,15 @@ bitcpy(struct fb_info *p, unsigned long
 			d0 = fb_rev_pixels_in_long(d0, bswapmask);
 			if (shift > 0) {
 				// Single source word
-				d0 >>= right;
+				d0 <<= left;
 			} else if (src_idx+n <= bits) {
 				// Single source word
-				d0 <<= left;
+				d0 >>= right;
 			} else {
 				// 2 source words
 				d1 = FB_READL(src + 1);
 				d1 = fb_rev_pixels_in_long(d1, bswapmask);
-				d0 = d0<<left | d1>>right;
+				d0 = d0 >> right | d1 << left;
 			}
 			d0 = fb_rev_pixels_in_long(d0, bswapmask);
 			FB_WRITEL(comp(d0, FB_READL(dst), first), dst);

@@ -135,60 +143,59 @@ bitcpy(struct fb_info *p, unsigned long
 			if (shift > 0) {
 				// Single source word
 				d1 = d0;
-				d0 >>= right;
-				dst++;
+				d0 <<= left;
 				n -= bits - dst_idx;
 			} else {
 				// 2 source words
 				d1 = FB_READL(src++);
 				d1 = fb_rev_pixels_in_long(d1, bswapmask);
 
-				d0 = d0<<left | d1>>right;
-				dst++;
+				d0 = d0 >> right | d1 << left;
 				n -= bits - dst_idx;
 			}
 			d0 = fb_rev_pixels_in_long(d0, bswapmask);
 			FB_WRITEL(comp(d0, FB_READL(dst), first), dst);
 			d0 = d1;
+			dst++;
 
 			// Main chunk
 			m = n % bits;
 			n /= bits;
 			while ((n >= 4) && !bswapmask) {
 				d1 = FB_READL(src++);
-				FB_WRITEL(d0 << left | d1 >> right, dst++);
+				FB_WRITEL(d0 >> right | d1 << left, dst++);
 				d0 = d1;
 				d1 = FB_READL(src++);
-				FB_WRITEL(d0 << left | d1 >> right, dst++);
+				FB_WRITEL(d0 >> right | d1 << left, dst++);
 				d0 = d1;
 				d1 = FB_READL(src++);
-				FB_WRITEL(d0 << left | d1 >> right, dst++);
+				FB_WRITEL(d0 >> right | d1 << left, dst++);
 				d0 = d1;
 				d1 = FB_READL(src++);
-				FB_WRITEL(d0 << left | d1 >> right, dst++);
+				FB_WRITEL(d0 >> right | d1 << left, dst++);
 				d0 = d1;
 				n -= 4;
 			}
 			while (n--) {
 				d1 = FB_READL(src++);
 				d1 = fb_rev_pixels_in_long(d1, bswapmask);
-				d0 = d0 << left | d1 >> right;
+				d0 = d0 >> right | d1 << left;
 				d0 = fb_rev_pixels_in_long(d0, bswapmask);
 				FB_WRITEL(d0, dst++);
 				d0 = d1;
 			}
 
 			// Trailing bits
-			if (last) {
-				if (m <= right) {
+			if (m) {
+				if (m <= bits - right) {
 					// Single source word
-					d0 <<= left;
+					d0 >>= right;
 				} else {
 					// 2 source words
 					d1 = FB_READL(src);
 					d1 = fb_rev_pixels_in_long(d1,
 								bswapmask);
-					d0 = d0<<left | d1>>right;
+					d0 = d0 >> right | d1 << left;
 				}
 				d0 = fb_rev_pixels_in_long(d0, bswapmask);
 				FB_WRITEL(comp(d0, FB_READL(dst), last), dst);

@@ -202,43 +209,46 @@ bitcpy(struct fb_info *p, unsigned long
      */
 
 static void
-bitcpy_rev(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
-		const unsigned long __iomem *src, int src_idx, int bits,
+bitcpy_rev(struct fb_info *p, unsigned long __iomem *dst, unsigned dst_idx,
+		const unsigned long __iomem *src, unsigned src_idx, int bits,
 		unsigned n, u32 bswapmask)
 {
 	unsigned long first, last;
 	int shift;
 
-	dst += (n-1)/bits;
-	src += (n-1)/bits;
-	if ((n-1) % bits) {
-		dst_idx += (n-1) % bits;
-		dst += dst_idx >> (ffs(bits) - 1);
-		dst_idx &= bits - 1;
-		src_idx += (n-1) % bits;
-		src += src_idx >> (ffs(bits) - 1);
-		src_idx &= bits - 1;
-	}
+#if 0
+	/*
+	 * If you suspect bug in this function, compare it with this simple
+	 * memmove implementation.
+	 */
+	fb_memmove((char *)dst + ((dst_idx & (bits - 1))) / 8,
+		   (char *)src + ((src_idx & (bits - 1))) / 8, n / 8);
+	return;
+#endif
+
+	dst += (dst_idx + n - 1) / bits;
+	src += (src_idx + n - 1) / bits;
+	dst_idx = (dst_idx + n - 1) % bits;
+	src_idx = (src_idx + n - 1) % bits;
 
 	shift = dst_idx-src_idx;
 
-	first = fb_shifted_pixels_mask_long(p, bits - 1 - dst_idx, bswapmask);
-	last = ~fb_shifted_pixels_mask_long(p, bits - 1 - ((dst_idx-n) % bits),
-					    bswapmask);
+	first = ~fb_shifted_pixels_mask_long(p, (dst_idx + 1) % bits, bswapmask);
+	last = fb_shifted_pixels_mask_long(p, (bits + dst_idx + 1 - n) % bits, bswapmask);
 
 	if (!shift) {
 		// Same alignment for source and dest
 
 		if ((unsigned long)dst_idx+1 >= n) {
 			// Single word
-			if (last)
-				first &= last;
-			FB_WRITEL( comp( FB_READL(src), FB_READL(dst), first), dst);
+			if (first)
+				last &= first;
+			FB_WRITEL( comp( FB_READL(src), FB_READL(dst), last), dst);
 		} else {
 			// Multiple destination words
 
 			// Leading bits
-			if (first != ~0UL) {
+			if (first) {
 				FB_WRITEL( comp( FB_READL(src), FB_READL(dst), first), dst);
 				dst--;
 				src--;

@@ -262,7 +272,7 @@ bitcpy_rev(struct fb_info *p, unsigned l
 				FB_WRITEL(FB_READL(src--), dst--);
 
 			// Trailing bits
-			if (last)
+			if (last != -1UL)
 				FB_WRITEL( comp( FB_READL(src), FB_READL(dst), last), dst);
 		}
 	} else {

@@ -270,29 +280,28 @@ bitcpy_rev(struct fb_info *p, unsigned l
 		unsigned long d0, d1;
 		int m;
 
-		int const left = -shift & (bits-1);
-		int const right = shift & (bits-1);
-		bswapmask &= shift;
+		int const left = shift & (bits-1);
+		int const right = -shift & (bits-1);
 
 		if ((unsigned long)dst_idx+1 >= n) {
 			// Single destination word
-			if (last)
-				first &= last;
+			if (first)
+				last &= first;
 			d0 = FB_READL(src);
 			if (shift < 0) {
 				// Single source word
-				d0 <<= left;
+				d0 >>= right;
 			} else if (1+(unsigned long)src_idx >= n) {
 				// Single source word
-				d0 >>= right;
+				d0 <<= left;
 			} else {
 				// 2 source words
 				d1 = FB_READL(src - 1);
 				d1 = fb_rev_pixels_in_long(d1, bswapmask);
-				d0 = d0>>right | d1<<left;
+				d0 = d0 << left | d1 >> right;
 			}
 			d0 = fb_rev_pixels_in_long(d0, bswapmask);
-			FB_WRITEL(comp(d0, FB_READL(dst), first), dst);
+			FB_WRITEL(comp(d0, FB_READL(dst), last), dst);
 		} else {
 			// Multiple destination words
 			/** We must always remember the last value read, because in case

@@ -307,12 +316,12 @@ bitcpy_rev(struct fb_info *p, unsigned l
 			if (shift < 0) {
 				// Single source word
 				d1 = d0;
-				d0 <<= left;
+				d0 >>= right;
 			} else {
 				// 2 source words
 				d1 = FB_READL(src--);
 				d1 = fb_rev_pixels_in_long(d1, bswapmask);
-				d0 = d0>>right | d1<<left;
+				d0 = d0 << left | d1 >> right;
 			}
 			d0 = fb_rev_pixels_in_long(d0, bswapmask);
 			FB_WRITEL(comp(d0, FB_READL(dst), first), dst);

@@ -325,39 +334,39 @@ bitcpy_rev(struct fb_info *p, unsigned l
 			n /= bits;
 			while ((n >= 4) && !bswapmask) {
 				d1 = FB_READL(src--);
-				FB_WRITEL(d0 >> right | d1 << left, dst--);
+				FB_WRITEL(d0 << left | d1 >> right, dst--);
 				d0 = d1;
 				d1 = FB_READL(src--);
-				FB_WRITEL(d0 >> right | d1 << left, dst--);
+				FB_WRITEL(d0 << left | d1 >> right, dst--);
 				d0 = d1;
 				d1 = FB_READL(src--);
-				FB_WRITEL(d0 >> right | d1 << left, dst--);
+				FB_WRITEL(d0 << left | d1 >> right, dst--);
 				d0 = d1;
 				d1 = FB_READL(src--);
-				FB_WRITEL(d0 >> right | d1 << left, dst--);
+				FB_WRITEL(d0 << left | d1 >> right, dst--);
 				d0 = d1;
 				n -= 4;
 			}
 			while (n--) {
 				d1 = FB_READL(src--);
 				d1 = fb_rev_pixels_in_long(d1, bswapmask);
-				d0 = d0 >> right | d1 << left;
+				d0 = d0 << left | d1 >> right;
 				d0 = fb_rev_pixels_in_long(d0, bswapmask);
 				FB_WRITEL(d0, dst--);
 				d0 = d1;
 			}
 
 			// Trailing bits
-			if (last) {
-				if (m <= left) {
+			if (m) {
+				if (m <= bits - left) {
 					// Single source word
-					d0 >>= right;
+					d0 <<= left;
 				} else {
 					// 2 source words
 					d1 = FB_READL(src);
 					d1 = fb_rev_pixels_in_long(d1,
 								bswapmask);
-					d0 = d0>>right | d1<<left;
+					d0 = d0 << left | d1 >> right;
 				}
 				d0 = fb_rev_pixels_in_long(d0, bswapmask);
 				FB_WRITEL(comp(d0, FB_READL(dst), last), dst);

@@ -371,9 +380,9 @@ void cfb_copyarea(struct fb_info *p, con
 	u32 dx = area->dx, dy = area->dy, sx = area->sx, sy = area->sy;
 	u32 height = area->height, width = area->width;
 	unsigned long const bits_per_line = p->fix.line_length*8u;
-	unsigned long __iomem *dst = NULL, *src = NULL;
+	unsigned long __iomem *base = NULL;
 	int bits = BITS_PER_LONG, bytes = bits >> 3;
-	int dst_idx = 0, src_idx = 0, rev_copy = 0;
+	unsigned dst_idx = 0, src_idx = 0, rev_copy = 0;
 	u32 bswapmask = fb_compute_bswapmask(p);
 
 	if (p->state != FBINFO_STATE_RUNNING)

@@ -389,7 +398,7 @@ void cfb_copyarea(struct fb_info *p, con
 
 	// split the base of the framebuffer into a long-aligned address and the
 	// index of the first bit
-	dst = src = (unsigned long __iomem *)((unsigned long)p->screen_base & ~(bytes-1));
+	base = (unsigned long __iomem *)((unsigned long)p->screen_base & ~(bytes-1));
 	dst_idx = src_idx = 8*((unsigned long)p->screen_base & (bytes-1));
 	// add offset of source and target area
 	dst_idx += dy*bits_per_line + dx*p->var.bits_per_pixel;

@@ -402,20 +411,14 @@ void cfb_copyarea(struct fb_info *p, con
 		while (height--) {
 			dst_idx -= bits_per_line;
 			src_idx -= bits_per_line;
-			dst += dst_idx >> (ffs(bits) - 1);
-			dst_idx &= (bytes - 1);
-			src += src_idx >> (ffs(bits) - 1);
-			src_idx &= (bytes - 1);
-			bitcpy_rev(p, dst, dst_idx, src, src_idx, bits,
+			bitcpy_rev(p, base + (dst_idx / bits), dst_idx % bits,
+				base + (src_idx / bits), src_idx % bits, bits,
 				width*p->var.bits_per_pixel, bswapmask);
 		}
 	} else {
 		while (height--) {
-			dst += dst_idx >> (ffs(bits) - 1);
-			dst_idx &= (bytes - 1);
-			src += src_idx >> (ffs(bits) - 1);
-			src_idx &= (bytes - 1);
-			bitcpy(p, dst, dst_idx, src, src_idx, bits,
+			bitcpy(p, base + (dst_idx / bits), dst_idx % bits,
+				base + (src_idx / bits), src_idx % bits, bits,
 				width*p->var.bits_per_pixel, bswapmask);
 			dst_idx += bits_per_line;
 			src_idx += bits_per_line;

Ben Hutchings

author

2014-04-28 01:11 UTC #28 lore raw

PATCH 28/94 mach64: use unaligned access

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Mikulas Patocka <[email protected]>

commit c29dd8696dc5dbd50b3ac441b8a26751277ba520 upstream.

This patch fixes mach64 to use unaligned access to the font bitmap.

This fixes unaligned access warning on sparc64 when 14x8 font is loaded.

On x86(64), unaligned access is handled in hardware, so both functions le32_to_cpup and get_unaligned_le32 perform the same operation.

On RISC machines, unaligned access is not handled in hardware, so we better use get_unaligned_le32 to avoid the unaligned trap and warning.

---
 drivers/video/aty/mach64_accel.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

drivers/video/aty/mach64_accel.c +2 -1

@@ -4,6 +4,7 @@
  */
 
 #include <linux/delay.h>
+#include <asm/unaligned.h>
 #include <linux/fb.h>
 #include <video/mach64.h>
 #include "atyfb.h"

@@ -419,7 +420,7 @@ void atyfb_imageblit(struct fb_info *inf
 		u32 *pbitmap, dwords = (src_bytes + 3) / 4;
 		for (pbitmap = (u32*)(image->data); dwords; dwords--, pbitmap++) {
 			wait_for_fifo(1, par);
-			aty_st_le32(HOST_DATA0, le32_to_cpup(pbitmap), par);
+			aty_st_le32(HOST_DATA0, get_unaligned_le32(pbitmap), par);
 		}
 	}

Ben Hutchings

author

2014-04-28 01:11 UTC #29 lore raw

PATCH 29/94 mach64: fix cursor when character width is not a multiple of 8 pixels

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Mikulas Patocka <[email protected]>

commit 43751a1b8ee2e70ce392bf31ef3133da324e68b3 upstream.

This patch fixes the hardware cursor on mach64 when font width is not a multiple of 8 pixels.

If you load such a font, the cursor is expanded to the next 8-byte boundary and a part of the next character after the cursor is not visible.
For example, when you load a font with 12-pixel width, the cursor width is 16 pixels and when the cursor is displayed, 4 pixels of the next character are not visible.

The reason is this: atyfb_cursor is called with proper parameters to load an image that is 12-pixel wide. However, the number is aligned on the next 8-pixel boundary on the line
"unsigned int width = (cursor->image.width + 7) >> 3;" and the whole function acts as it is was loading a 16-pixel image.

This patch fixes it so that the value written to the framebuffer is padded with 0xaaaa (the transparent pattern) when the image size it not a multiple of 8 pixels. The transparent pattern causes that the cursor will not interfere with the next character.

---
 drivers/video/aty/mach64_cursor.c | 22 ++++++++++++++++------
 1 file changed, 16 insertions(+), 6 deletions(-)

drivers/video/aty/mach64_cursor.c +16 -6

@@ -5,6 +5,7 @@
 #include <linux/fb.h>
 #include <linux/init.h>
 #include <linux/string.h>
+#include "../fb_draw.h"
 
 #include <asm/io.h>

@@ -157,24 +158,33 @@ static int atyfb_cursor(struct fb_info *
 
 	    for (i = 0; i < height; i++) {
 		for (j = 0; j < width; j++) {
+			u16 l = 0xaaaa;
 			b = *src++;
 			m = *msk++;
 			switch (cursor->rop) {
 			case ROP_XOR:
 			    // Upper 4 bits of mask data
-			    fb_writeb(cursor_bits_lookup[(b ^ m) >> 4], dst++);
+			    l = cursor_bits_lookup[(b ^ m) >> 4] |
 			    // Lower 4 bits of mask
-			    fb_writeb(cursor_bits_lookup[(b ^ m) & 0x0f],
-				      dst++);
+				    (cursor_bits_lookup[(b ^ m) & 0x0f] << 8);
 			    break;
 			case ROP_COPY:
 			    // Upper 4 bits of mask data
-			    fb_writeb(cursor_bits_lookup[(b & m) >> 4], dst++);
+			    l = cursor_bits_lookup[(b & m) >> 4] |
 			    // Lower 4 bits of mask
-			    fb_writeb(cursor_bits_lookup[(b & m) & 0x0f],
-				      dst++);
+				    (cursor_bits_lookup[(b & m) & 0x0f] << 8);
 			    break;
 			}
+			/*
+			 * If cursor size is not a multiple of 8 characters
+			 * we must pad it with transparent pattern (0xaaaa).
+			 */
+			if ((j + 1) * 8 > cursor->image.width) {
+				l = comp(l, 0xaaaa,
+				    (1 << ((cursor->image.width & 7) * 2)) - 1);
+			}
+			fb_writeb(l & 0xff, dst++);
+			fb_writeb(l >> 8, dst++);
 		}
 		dst += offset;
 	    }

Ben Hutchings

author

2014-04-28 01:11 UTC #30 lore raw

PATCH 30/94 tgafb: fix data copying

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Mikulas Patocka <[email protected]>

commit 6b0df6827bb6fcacb158dff29ad0a62d6418b534 upstream.

The functions for data copying copyarea_foreward_8bpp and copyarea_backward_8bpp are buggy, they produce screen corruption.

This patch fixes the functions and moves the logic to one function "copyarea_8bpp". For simplicity, the function only handles copying that is aligned on 8 pixes. If we copy an unaligned area, generic function cfb_copyarea is used.

---
 drivers/video/tgafb.c | 264 ++++++++++----------------------------------------
 1 file changed, 51 insertions(+), 213 deletions(-)

drivers/video/tgafb.c +51 ~~-213~~

@@ -1146,222 +1146,57 @@ copyarea_line_32bpp(struct fb_info *info
 	__raw_writel(TGA_MODE_SBM_24BPP|TGA_MODE_SIMPLE, tga_regs+TGA_MODE_REG);
 }
 
-/* The general case of forward copy in 8bpp mode.  */
+/* The (almost) general case of backward copy in 8bpp mode.  */
 static inline void
-copyarea_foreward_8bpp(struct fb_info *info, u32 dx, u32 dy, u32 sx, u32 sy,
-		       u32 height, u32 width, u32 line_length)
+copyarea_8bpp(struct fb_info *info, u32 dx, u32 dy, u32 sx, u32 sy,
+	      u32 height, u32 width, u32 line_length,
+	      const struct fb_copyarea *area)
 {
 	struct tga_par *par = (struct tga_par *) info->par;
-	unsigned long i, copied, left;
-	unsigned long dpos, spos, dalign, salign, yincr;
-	u32 smask_first, dmask_first, dmask_last;
-	int pixel_shift, need_prime, need_second;
-	unsigned long n64, n32, xincr_first;
+	unsigned i, yincr;
+	int depos, sepos, backward, last_step, step;
+	u32 mask_last;
+	unsigned n32;
 	void __iomem *tga_regs;
 	void __iomem *tga_fb;
 
-	yincr = line_length;
-	if (dy > sy) {
-		dy += height - 1;
-		sy += height - 1;
-		yincr = -yincr;
-	}
-
-	/* Compute the offsets and alignments in the frame buffer.
-	   More than anything else, these control how we do copies.  */
-	dpos = dy * line_length + dx;
-	spos = sy * line_length + sx;
-	dalign = dpos & 7;
-	salign = spos & 7;
-	dpos &= -8;
-	spos &= -8;
-
-	/* Compute the value for the PIXELSHIFT register.  This controls
-	   both non-co-aligned source and destination and copy direction.  */
-	if (dalign >= salign)
-		pixel_shift = dalign - salign;
-	else
-		pixel_shift = 8 - (salign - dalign);
-
-	/* Figure out if we need an additional priming step for the
-	   residue register.  */
-	need_prime = (salign > dalign);
-	if (need_prime)
-		dpos -= 8;
-
-	/* Begin by copying the leading unaligned destination.  Copy enough
-	   to make the next destination address 32-byte aligned.  */
-	copied = 32 - (dalign + (dpos & 31));
-	if (copied == 32)
-		copied = 0;
-	xincr_first = (copied + 7) & -8;
-	smask_first = dmask_first = (1ul << copied) - 1;
-	smask_first <<= salign;
-	dmask_first <<= dalign + need_prime*8;
-	if (need_prime && copied > 24)
-		copied -= 8;
-	left = width - copied;
-
-	/* Care for small copies.  */
-	if (copied > width) {
-		u32 t;
-		t = (1ul << width) - 1;
-		t <<= dalign + need_prime*8;
-		dmask_first &= t;
-		left = 0;
-	}
-
-	/* Attempt to use 64-byte copies.  This is only possible if the
-	   source and destination are co-aligned at 64 bytes.  */
-	n64 = need_second = 0;
-	if ((dpos & 63) == (spos & 63)
-	    && (height == 1 || line_length % 64 == 0)) {
-		/* We may need a 32-byte copy to ensure 64 byte alignment.  */
-		need_second = (dpos + xincr_first) & 63;
-		if ((need_second & 32) != need_second)
-			printk(KERN_ERR "tgafb: need_second wrong\n");
-		if (left >= need_second + 64) {
-			left -= need_second;
-			n64 = left / 64;
-			left %= 64;
-		} else
-			need_second = 0;
-	}
-
-	/* Copy trailing full 32-byte sections.  This will be the main
-	   loop if the 64 byte loop can't be used.  */
-	n32 = left / 32;
-	left %= 32;
-
-	/* Copy the trailing unaligned destination.  */
-	dmask_last = (1ul << left) - 1;
-
-	tga_regs = par->tga_regs_base;
-	tga_fb = par->tga_fb_base;
-
-	/* Set up the MODE and PIXELSHIFT registers.  */
-	__raw_writel(TGA_MODE_SBM_8BPP|TGA_MODE_COPY, tga_regs+TGA_MODE_REG);
-	__raw_writel(pixel_shift, tga_regs+TGA_PIXELSHIFT_REG);
-	wmb();
-
-	for (i = 0; i < height; ++i) {
-		unsigned long j;
-		void __iomem *sfb;
-		void __iomem *dfb;
-
-		sfb = tga_fb + spos;
-		dfb = tga_fb + dpos;
-		if (dmask_first) {
-			__raw_writel(smask_first, sfb);
-			wmb();
-			__raw_writel(dmask_first, dfb);
-			wmb();
-			sfb += xincr_first;
-			dfb += xincr_first;
-		}
-
-		if (need_second) {
-			__raw_writel(0xffffffff, sfb);
-			wmb();
-			__raw_writel(0xffffffff, dfb);
-			wmb();
-			sfb += 32;
-			dfb += 32;
-		}
-
-		if (n64 && (((unsigned long)sfb | (unsigned long)dfb) & 63))
-			printk(KERN_ERR
-			       "tgafb: misaligned copy64 (s:%p, d:%p)\n",
-			       sfb, dfb);
-
-		for (j = 0; j < n64; ++j) {
-			__raw_writel(sfb - tga_fb, tga_regs+TGA_COPY64_SRC);
-			wmb();
-			__raw_writel(dfb - tga_fb, tga_regs+TGA_COPY64_DST);
-			wmb();
-			sfb += 64;
-			dfb += 64;
-		}
-
-		for (j = 0; j < n32; ++j) {
-			__raw_writel(0xffffffff, sfb);
-			wmb();
-			__raw_writel(0xffffffff, dfb);
-			wmb();
-			sfb += 32;
-			dfb += 32;
-		}
-
-		if (dmask_last) {
-			__raw_writel(0xffffffff, sfb);
-			wmb();
-			__raw_writel(dmask_last, dfb);
-			wmb();
-		}
-
-		spos += yincr;
-		dpos += yincr;
+	/* Do acceleration only if we are aligned on 8 pixels */
+	if ((dx | sx | width) & 7) {
+		cfb_copyarea(info, area);
+		return;
 	}
 
-	/* Reset the MODE register to normal.  */
-	__raw_writel(TGA_MODE_SBM_8BPP|TGA_MODE_SIMPLE, tga_regs+TGA_MODE_REG);
-}
-
-/* The (almost) general case of backward copy in 8bpp mode.  */
-static inline void
-copyarea_backward_8bpp(struct fb_info *info, u32 dx, u32 dy, u32 sx, u32 sy,
-		       u32 height, u32 width, u32 line_length,
-		       const struct fb_copyarea *area)
-{
-	struct tga_par *par = (struct tga_par *) info->par;
-	unsigned long i, left, yincr;
-	unsigned long depos, sepos, dealign, sealign;
-	u32 mask_first, mask_last;
-	unsigned long n32;
-	void __iomem *tga_regs;
-	void __iomem *tga_fb;
-
 	yincr = line_length;
 	if (dy > sy) {
 		dy += height - 1;
 		sy += height - 1;
 		yincr = -yincr;
 	}
+	backward = dy == sy && dx > sx && dx < sx + width;
 
 	/* Compute the offsets and alignments in the frame buffer.
 	   More than anything else, these control how we do copies.  */
-	depos = dy * line_length + dx + width;
-	sepos = sy * line_length + sx + width;
-	dealign = depos & 7;
-	sealign = sepos & 7;
-
-	/* ??? The documentation appears to be incorrect (or very
-	   misleading) wrt how pixel shifting works in backward copy
-	   mode, i.e. when PIXELSHIFT is negative.  I give up for now.
-	   Do handle the common case of co-aligned backward copies,
-	   but frob everything else back on generic code.  */
-	if (dealign != sealign) {
-		cfb_copyarea(info, area);
-		return;
-	}
-
-	/* We begin the copy with the trailing pixels of the
-	   unaligned destination.  */
-	mask_first = (1ul << dealign) - 1;
-	left = width - dealign;
-
-	/* Care for small copies.  */
-	if (dealign > width) {
-		mask_first ^= (1ul << (dealign - width)) - 1;
-		left = 0;
-	}
+	depos = dy * line_length + dx;
+	sepos = sy * line_length + sx;
+	if (backward)
+		depos += width, sepos += width;
 
 	/* Next copy full words at a time.  */
-	n32 = left / 32;
-	left %= 32;
+	n32 = width / 32;
+	last_step = width % 32;
 
 	/* Finally copy the unaligned head of the span.  */
-	mask_last = -1 << (32 - left);
+	mask_last = (1ul << last_step) - 1;
+
+	if (!backward) {
+		step = 32;
+		last_step = 32;
+	} else {
+		step = -32;
+		last_step = -last_step;
+		sepos -= 32;
+		depos -= 32;
+	}
 
 	tga_regs = par->tga_regs_base;
 	tga_fb = par->tga_fb_base;

@@ -1378,25 +1213,33 @@ copyarea_backward_8bpp(struct fb_info *i
 
 		sfb = tga_fb + sepos;
 		dfb = tga_fb + depos;
-		if (mask_first) {
-			__raw_writel(mask_first, sfb);
-			wmb();
-			__raw_writel(mask_first, dfb);
-			wmb();
-		}
 
-		for (j = 0; j < n32; ++j) {
-			sfb -= 32;
-			dfb -= 32;
+		for (j = 0; j < n32; j++) {
+			if (j < 2 && j + 1 < n32 && !backward &&
+			    !(((unsigned long)sfb | (unsigned long)dfb) & 63)) {
+				do {
+					__raw_writel(sfb - tga_fb, tga_regs+TGA_COPY64_SRC);
+					wmb();
+					__raw_writel(dfb - tga_fb, tga_regs+TGA_COPY64_DST);
+					wmb();
+					sfb += 64;
+					dfb += 64;
+					j += 2;
+				} while (j + 1 < n32);
+				j--;
+				continue;
+			}
 			__raw_writel(0xffffffff, sfb);
 			wmb();
 			__raw_writel(0xffffffff, dfb);
 			wmb();
+			sfb += step;
+			dfb += step;
 		}
 
 		if (mask_last) {
-			sfb -= 32;
-			dfb -= 32;
+			sfb += last_step - step;
+			dfb += last_step - step;
 			__raw_writel(mask_last, sfb);
 			wmb();
 			__raw_writel(mask_last, dfb);

@@ -1457,14 +1300,9 @@ tgafb_copyarea(struct fb_info *info, con
 	else if (bpp == 32)
 		cfb_copyarea(info, area);
 
-	/* Detect overlapping source and destination that requires
-	   a backward copy.  */
-	else if (dy == sy && dx > sx && dx < sx + width)
-		copyarea_backward_8bpp(info, dx, dy, sx, sy, height,
-				       width, line_length, area);
 	else
-		copyarea_foreward_8bpp(info, dx, dy, sx, sy, height,
-				       width, line_length);
+		copyarea_8bpp(info, dx, dy, sx, sy, height,
+			      width, line_length, area);
 }

Ben Hutchings

author

2014-04-28 01:11 UTC #31 lore raw

PATCH 31/94 hvc: ensure hvc_init is only ever called once in hvc_console.c

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Paul Gortmaker <[email protected]>

commit f76a1cbed18c86e2d192455f0daebb48458965f3 upstream.

Commit 3e6c6f630a5282df8f3393a59f10eb9c56536d23 ("Delay creation of khcvd thread") moved the call of hvc_init from being a device_initcall into hvc_alloc, and used a non-null hvc_driver as indication of whether hvc_init had already been called.

The problem with this is that hvc_driver is only assigned a value at the bottom of hvc_init, and so there is a window where multiple hvc_alloc calls can be in progress at the same time and hence try and call hvc_init multiple times. Previously the use of device_init guaranteed that hvc_init was only called once.

This manifests itself as sporadic instances of two hvc_init calls racing each other, and with the loser of the race getting -EBUSY from tty_register_driver() and hence that virtual console fails:

Couldn't register hvc console driver virtio-ports vport0p1: error -16 allocating hvc for port

Here we add an atomic_t to guarantee we'll never run hvc_init twice.

Cc Rusty Russell <[email protected]>

Cc Greg Kroah-Hartman <[email protected]>

Fixes 3e6c6f630a52 ("Delay creation of khcvd thread")

Reported-by Jim Somerville <[email protected]>

Tested-by Jim Somerville <[email protected]>

Signed-off-by Paul Gortmaker <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/tty/hvc/hvc_console.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

drivers/tty/hvc/hvc_console.c +5 -1

@@ -31,6 +31,7 @@
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/major.h>
+#include <linux/atomic.h>
 #include <linux/sysrq.h>
 #include <linux/tty.h>
 #include <linux/tty_flip.h>

@@ -70,6 +71,9 @@ static struct task_struct *hvc_task;
 /* Picks up late kicks after list walk but before schedule() */
 static int hvc_kicked;
 
+/* hvc_init is triggered from hvc_alloc, i.e. only when actually used */
+static atomic_t hvc_needs_init __read_mostly = ATOMIC_INIT(-1);
+
 static int hvc_init(void);
 
 #ifdef CONFIG_MAGIC_SYSRQ

@@ -825,7 +829,7 @@ struct hvc_struct *hvc_alloc(uint32_t vt
 	int i;
 
 	/* We wait until a driver actually comes along */
-	if (!hvc_driver) {
+	if (atomic_inc_not_zero(&hvc_needs_init)) {
 		int err = hvc_init();
 		if (err)
 			return ERR_PTR(err);

Ben Hutchings

author

2014-04-28 01:11 UTC #32 lore raw

PATCH 32/94 usb: dwc3: fix wrong bit mask in dwc3_event_devt

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Huang Rui <[email protected]>

commit 06f9b6e59661cee510b04513b13ea7927727d758 upstream.

Around DWC USB3 2.30a release another bit has been added to the Device-Specific Event (DEVT) Event Information (EvtInfo) bitfield.

Because of that, what used to be 8 bits long, has become 9 bits long.

Per dwc3 2.30a+ spec in the Device-Specific Event (DEVT), the field of Event Information Bits(EvtInfo) uses [24:16] bits, and it has 9 bits not 8 bits. And the following reserved field uses [31:25] bits not [31:24] bits, and it has 7 bits.

So in dwc3_event_devt, the bit mask should be:
event_info [24:16] 9 bits
reserved31_25 [31:25] 7 bits

This patch makes sure that newer core releases will work fine with Linux and that we will decode the event information properly on new core releases.

[ [email protected] : improve commit log a bit ]

Signed-off-by Huang Rui <[email protected]>

Signed-off-by Felipe Balbi <[email protected]>

---
 drivers/usb/dwc3/core.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

drivers/usb/dwc3/core.h +3 -3

@@ -716,15 +716,15 @@ struct dwc3_event_depevt {
  *	12	- VndrDevTstRcved
  * @reserved15_12: Reserved, not used
  * @event_info: Information about this event
- * @reserved31_24: Reserved, not used
+ * @reserved31_25: Reserved, not used
  */
 struct dwc3_event_devt {
 	u32	one_bit:1;
 	u32	device_event:7;
 	u32	type:4;
 	u32	reserved15_12:4;
-	u32	event_info:8;
-	u32	reserved31_24:8;
+	u32	event_info:9;
+	u32	reserved31_25:7;
 } __packed;
 
 /**

Ben Hutchings

author

2014-04-28 01:11 UTC #33 lore raw

PATCH 33/94 media: gspca: sn9c20x: add ID for Genius Look 1320 V2

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Wolfram Sang <[email protected]>

commit 61f0319193c44adbbada920162d880b1fdb3aeb3 upstream.

Signed-off-by Wolfram Sang <[email protected]>

Signed-off-by Hans de Goede <[email protected]>

Signed-off-by Mauro Carvalho Chehab <[email protected]>

[bwh: Backported to 3.2: adjust filename]

---
 Documentation/video4linux/gspca.txt | 1 +
 drivers/media/video/gspca/sn9c20x.c | 1 +
 2 files changed, 2 insertions(+)

Documentation/video4linux/gspca.txt +1 -0

@@ -55,6 +55,7 @@ zc3xx		0458:700f	Genius VideoCam Web V2
 sonixj		0458:7025	Genius Eye 311Q
 sn9c20x		0458:7029	Genius Look 320s
 sonixj		0458:702e	Genius Slim 310 NB
+sn9c20x		0458:7045	Genius Look 1320 V2
 sn9c20x		0458:704a	Genius Slim 1320
 sn9c20x		0458:704c	Genius i-Look 1321
 sn9c20x		045e:00f4	LifeCam VX-6000 (SN9C20x + OV9650)

drivers/media/video/gspca/sn9c20x.c +1 -0

@@ -2521,6 +2521,7 @@ static const struct usb_device_id device
 	{USB_DEVICE(0x045e, 0x00f4), SN9C20X(OV9650, 0x30, 0)},
 	{USB_DEVICE(0x145f, 0x013d), SN9C20X(OV7660, 0x21, 0)},
 	{USB_DEVICE(0x0458, 0x7029), SN9C20X(HV7131R, 0x11, 0)},
+	{USB_DEVICE(0x0458, 0x7045), SN9C20X(MT9M112, 0x5d, LED_REVERSE)},
 	{USB_DEVICE(0x0458, 0x704a), SN9C20X(MT9M112, 0x5d, 0)},
 	{USB_DEVICE(0x0458, 0x704c), SN9C20X(MT9M112, 0x5d, 0)},
 	{USB_DEVICE(0xa168, 0x0610), SN9C20X(HV7131R, 0x11, 0)},

Ben Hutchings

author

2014-04-28 01:11 UTC #34 lore raw

PATCH 34/94 tty: Set correct tty name in 'active' sysfs attribute

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Hannes Reinecke <[email protected]>

commit 723abd87f6e536f1353c8f64f621520bc29523a3 upstream.

The 'active' sysfs attribute should refer to the currently active tty devices the console is running on, not the currently active console. The console structure doesn't refer to any device in sysfs, only the tty the console is running on has. So we need to print out the tty names in 'active', not the console names.

There is one special-case, which is tty0. If the console is directed to it, we want 'tty0' to show up in the file, so user-space knows that the messages get forwarded to the active VT. The ->device() callback would resolve tty0, though. Hence, treat it special and don't call into the VT layer to resolve it (plymouth is known to depend on it).

Cc Lennart Poettering <[email protected]>

Cc Kay Sievers <[email protected]>

Cc Greg Kroah-Hartman <[email protected]>

Cc Jiri Slaby <[email protected]>

Signed-off-by Werner Fink <[email protected]>

Signed-off-by Hannes Reinecke <[email protected]>

Signed-off-by David Herrmann <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

[bwh: Backported to 3.2: no TTY_DRIVER_UNNUMBERED_NODE case in tty_line_name()]

---
 drivers/tty/tty_io.c | 23 +++++++++++++++++------
 1 file changed, 17 insertions(+), 6 deletions(-)

drivers/tty/tty_io.c +15 -5

@@ -1222,9 +1222,9 @@ static void pty_line_name(struct tty_dri
  *
  *	Locking: None
  */
-static void tty_line_name(struct tty_driver *driver, int index, char *p)
+static ssize_t tty_line_name(struct tty_driver *driver, int index, char *p)
 {
-	sprintf(p, "%s%d", driver->name, index + driver->name_base);
+	return sprintf(p, "%s%d", driver->name, index + driver->name_base);
 }
 
 /**

@@ -3321,9 +3321,19 @@ static ssize_t show_cons_active(struct d
 		if (i >= ARRAY_SIZE(cs))
 			break;
 	}
-	while (i--)
-		count += sprintf(buf + count, "%s%d%c",
-				 cs[i]->name, cs[i]->index, i ? ' ':'\n');
+	while (i--) {
+		int index = cs[i]->index;
+		struct tty_driver *drv = cs[i]->device(cs[i], &index);
+
+		/* don't resolve tty0 as some programs depend on it */
+		if (drv && (cs[i]->index > 0 || drv->major != TTY_MAJOR))
+			count += tty_line_name(drv, index, buf + count);
+		else
+			count += sprintf(buf + count, "%s%d",
+					 cs[i]->name, cs[i]->index);
+
+		count += sprintf(buf + count, "%c", i ? ' ':'\n');
+	}
 	console_unlock();
 
 	return count;

Ben Hutchings

author

2014-04-28 01:11 UTC #35 lore raw

PATCH 35/94 uvcvideo: Do not use usb_set_interface on bulk EP

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Oleksij Rempel <[email protected]>

commit b1e43f232698274871e1358c276d7b0242a7d607 upstream.

The UVC specification uses alternate setting selection to notify devices of stream start/stop. This breaks when using bulk-based devices, as the video streaming interface has a single alternate setting in that case, making video stream start and video stream stop events to appear identical to the device. Bulk-based devices are thus not well supported by UVC.

The webcam built in the Asus Zenbook UX302LA ignores the set interface request and will keep the video stream enabled when the driver tries to stop it. If USB autosuspend is enabled the device will then be suspended and will crash, requiring a cold reboot.

USB trace capture showed that Windows sends a CLEAR_FEATURE(HALT) request to the bulk endpoint when stopping the stream instead of selecting alternate setting 0. The camera then behaves correctly, and thus seems to require that behaviour.

Replace selection of alternate setting 0 with clearing of the endpoint halt feature at video stream stop for bulk-based devices. Let's refrain from blaming Microsoft this time, as it's not clear whether this Windows-specific but USB-compliant behaviour was specifically developed to handle bulkd-based UVC devices, or if the camera just took advantage of it.

Signed-off-by Oleksij Rempel <[email protected]>

Signed-off-by Laurent Pinchart <[email protected]>

Signed-off-by Mauro Carvalho Chehab <[email protected]>

[bwh: Backported to 3.2: adjust filename]

---
 drivers/media/video/uvc/uvc_video.c | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

drivers/media/video/uvc/uvc_video.c +19 -1

@@ -1267,7 +1267,25 @@ int uvc_video_enable(struct uvc_streamin
 
 	if (!enable) {
 		uvc_uninit_video(stream, 1);
-		usb_set_interface(stream->dev->udev, stream->intfnum, 0);
+		if (stream->intf->num_altsetting > 1) {
+			usb_set_interface(stream->dev->udev,
+					  stream->intfnum, 0);
+		} else {
+			/* UVC doesn't specify how to inform a bulk-based device
+			 * when the video stream is stopped. Windows sends a
+			 * CLEAR_FEATURE(HALT) request to the video streaming
+			 * bulk endpoint, mimic the same behaviour.
+			 */
+			unsigned int epnum = stream->header.bEndpointAddress
+					   & USB_ENDPOINT_NUMBER_MASK;
+			unsigned int dir = stream->header.bEndpointAddress
+					 & USB_ENDPOINT_DIR_MASK;
+			unsigned int pipe;
+
+			pipe = usb_sndbulkpipe(stream->dev->udev, epnum) | dir;
+			usb_clear_halt(stream->dev->udev, pipe);
+		}
+
 		uvc_queue_enable(&stream->queue, 0);
 		return 0;
 	}

Ben Hutchings

author

2014-04-28 01:11 UTC #36 lore raw

PATCH 36/94 usb: gadget: atmel_usba: fix crashed during stopping when DEBUG is enabled

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Gregory CLEMENT <[email protected]>

commit d8eb6c653ef6b323d630de3c5685478469e248bc upstream.

commit 511f3c5 (usb: gadget: udc-core: fix a regression during gadget driver unbinding) introduced a crash when DEBUG is enabled.

The debug trace in the atmel_usba_stop function made the assumption that the driver pointer passed in parameter was not NULL, but since the commit above, such assumption was no longer always true.

This commit now uses the driver pointer stored in udc which fixes this issue.

[ [email protected] : improved commit log a bit ]

Acked-by Alexandre Belloni <[email protected]>

Signed-off-by Gregory CLEMENT <[email protected]>

Signed-off-by Felipe Balbi <[email protected]>

[bwh: Backported to 3.2: adjust context]

---

drivers/usb/gadget/atmel_usba_udc.c +3 -2

@@ -1875,12 +1875,13 @@ static int atmel_usba_stop(struct usb_ga
 
 	driver->unbind(&udc->gadget);
 	udc->gadget.dev.driver = NULL;
-	udc->driver = NULL;
 
 	clk_disable(udc->hclk);
 	clk_disable(udc->pclk);
 
-	DBG(DBG_GADGET, "unregistered driver `%s'\n", driver->driver.name);
+	DBG(DBG_GADGET, "unregistered driver `%s'\n", udc->driver->driver.name);
+
+	udc->driver = NULL;
 
 	return 0;
 }

Ben Hutchings

author

2014-04-28 01:11 UTC #37 lore raw

PATCH 37/94 blktrace: fix accounting of partially completed requests

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Roman Pen <[email protected]>

commit af5040da01ef980670b3741b3e10733ee3e33566 upstream.

trace_block_rq_complete does not take into account that request can be partially completed, so we can get the following incorrect output of blkparser:

  C   R 232 + 240 [0]
  C   R 240 + 232 [0]
  C   R 248 + 224 [0]
  C   R 256 + 216 [0]

but should be:

  C   R 232 + 8 [0]
  C   R 240 + 8 [0]
  C   R 248 + 8 [0]
  C   R 256 + 8 [0]

Also, the whole output summary statistics of completed requests and final throughput will be incorrect.

This patch takes into account real completion size of the request and fixes wrong completion accounting.

Signed-off-by Roman Pen <[email protected]>

CC Steven Rostedt <[email protected]>

CC Frederic Weisbecker <[email protected]>

CC Ingo Molnar <[email protected]>

CC [email protected]

Signed-off-by Jens Axboe <[email protected]>

[bwh: Backported to 3.2: drop change in blk-mq.c]

---

block/blk-core.c +1 -1

@@ -2077,7 +2077,7 @@ bool blk_update_request(struct request *
 	if (!req->bio)
 		return false;
 
-	trace_block_rq_complete(req->q, req);
+	trace_block_rq_complete(req->q, req, nr_bytes);
 
 	/*
 	 * For fs requests, rq is just carrier of independent bio's

include/trace/events/block.h +30 -3

@@ -81,6 +81,7 @@ DEFINE_EVENT(block_rq_with_error, block_
  * block_rq_complete - block IO operation completed by device driver
  * @q: queue containing the block operation request
  * @rq: block operations request
+ * @nr_bytes: number of completed bytes
  *
  * The block_rq_complete tracepoint event indicates that some portion
  * of operation request has been completed by the device driver.  If

@@ -88,11 +89,37 @@ DEFINE_EVENT(block_rq_with_error, block_
  * do for the request. If @rq->bio is non-NULL then there is
  * additional work required to complete the request.
  */
-DEFINE_EVENT(block_rq_with_error, block_rq_complete,
+TRACE_EVENT(block_rq_complete,
 
-	TP_PROTO(struct request_queue *q, struct request *rq),
+	TP_PROTO(struct request_queue *q, struct request *rq,
+		 unsigned int nr_bytes),
 
-	TP_ARGS(q, rq)
+	TP_ARGS(q, rq, nr_bytes),
+
+	TP_STRUCT__entry(
+		__field(  dev_t,	dev			)
+		__field(  sector_t,	sector			)
+		__field(  unsigned int,	nr_sector		)
+		__field(  int,		errors			)
+		__array(  char,		rwbs,	RWBS_LEN	)
+		__dynamic_array( char,	cmd,	blk_cmd_buf_len(rq)	)
+	),
+
+	TP_fast_assign(
+		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+		__entry->sector    = blk_rq_pos(rq);
+		__entry->nr_sector = nr_bytes >> 9;
+		__entry->errors    = rq->errors;
+
+		blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, nr_bytes);
+		blk_dump_cmd(__get_str(cmd), rq);
+	),
+
+	TP_printk("%d,%d %s (%s) %llu + %u [%d]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rwbs, __get_str(cmd),
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->errors)
 );
 
 DECLARE_EVENT_CLASS(block_rq,

kernel/trace/blktrace.c +11 -9

@@ -699,6 +699,7 @@ void blk_trace_shutdown(struct request_q
  * blk_add_trace_rq - Add a trace for a request oriented action
  * @q:		queue the io is for
  * @rq:		the source request
+ * @nr_bytes:	number of completed bytes
  * @what:	the action
  *
  * Description:

@@ -706,7 +707,7 @@ void blk_trace_shutdown(struct request_q
  *
  **/
 static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
-			     u32 what)
+			     unsigned int nr_bytes, u32 what)
 {
 	struct blk_trace *bt = q->blk_trace;

@@ -715,11 +716,11 @@ static void blk_add_trace_rq(struct requ
 
 	if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
 		what |= BLK_TC_ACT(BLK_TC_PC);
-		__blk_add_trace(bt, 0, blk_rq_bytes(rq), rq->cmd_flags,
+		__blk_add_trace(bt, 0, nr_bytes, rq->cmd_flags,
 				what, rq->errors, rq->cmd_len, rq->cmd);
 	} else  {
 		what |= BLK_TC_ACT(BLK_TC_FS);
-		__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
+		__blk_add_trace(bt, blk_rq_pos(rq), nr_bytes,
 				rq->cmd_flags, what, rq->errors, 0, NULL);
 	}
 }

@@ -727,33 +728,34 @@ static void blk_add_trace_rq(struct requ
 static void blk_add_trace_rq_abort(void *ignore,
 				   struct request_queue *q, struct request *rq)
 {
-	blk_add_trace_rq(q, rq, BLK_TA_ABORT);
+	blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_ABORT);
 }
 
 static void blk_add_trace_rq_insert(void *ignore,
 				    struct request_queue *q, struct request *rq)
 {
-	blk_add_trace_rq(q, rq, BLK_TA_INSERT);
+	blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_INSERT);
 }
 
 static void blk_add_trace_rq_issue(void *ignore,
 				   struct request_queue *q, struct request *rq)
 {
-	blk_add_trace_rq(q, rq, BLK_TA_ISSUE);
+	blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_ISSUE);
 }
 
 static void blk_add_trace_rq_requeue(void *ignore,
 				     struct request_queue *q,
 				     struct request *rq)
 {
-	blk_add_trace_rq(q, rq, BLK_TA_REQUEUE);
+	blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_REQUEUE);
 }
 
 static void blk_add_trace_rq_complete(void *ignore,
 				      struct request_queue *q,
-				      struct request *rq)
+				      struct request *rq,
+				      unsigned int nr_bytes)
 {
-	blk_add_trace_rq(q, rq, BLK_TA_COMPLETE);
+	blk_add_trace_rq(q, rq, nr_bytes, BLK_TA_COMPLETE);
 }
 
 /**

Ben Hutchings

author

2014-04-28 01:11 UTC #38 lore raw

PATCH 38/94 rtlwifi: rtl8192se: Fix too long disable of IRQs

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Larry Finger <[email protected]>

commit 2610decdd0b3808ba20471a999835cfee5275f98 upstream.

In commit f78bccd79ba3cd9d9664981b501d57bdb81ab8a4 entitled "rtlwifi:
rtl8192ce: Fix too long disable of IRQs", Olivier Langlois <[email protected]> fixed a problem caused by an extra long disabling of interrupts. This patch makes the same fix for rtl8192se.

Signed-off-by Larry Finger <[email protected]>

Signed-off-by John W. Linville <[email protected]>

[bwh: Backported to 3.2:
- Adjust context
- Drop change to an error path that we don't have]

---

drivers/net/wireless/rtlwifi/rtl8192se/hw.c +19 -5

@@ -924,7 +924,7 @@ int rtl92se_hw_init(struct ieee80211_hw
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 	struct rtl_efuse *rtlefuse = rtl_efuse(rtl_priv(hw));
 	u8 tmp_byte = 0;
-
+	unsigned long flags;
 	bool rtstatus = true;
 	u8 tmp_u1b;
 	int err = false;

@@ -936,6 +936,16 @@ int rtl92se_hw_init(struct ieee80211_hw
 
 	rtlpci->being_init_adapter = true;
 
+	/* As this function can take a very long time (up to 350 ms)
+	 * and can be called with irqs disabled, reenable the irqs
+	 * to let the other devices continue being serviced.
+	 *
+	 * It is safe doing so since our own interrupts will only be enabled
+	 * in a subsequent step.
+	 */
+	local_save_flags(flags);
+	local_irq_enable();
+
 	rtlpriv->intf_ops->disable_aspm(hw);
 
 	/* 1. MAC Initialize */

@@ -969,7 +979,8 @@ int rtl92se_hw_init(struct ieee80211_hw
 	/* 3. Initialize MAC/PHY Config by MACPHY_reg.txt */
 	if (rtl92s_phy_mac_config(hw) != true) {
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG, ("MAC Config failed\n"));
-		return rtstatus;
+		err = rtstatus;
+		goto exit;
 	}
 
 	/* Make sure BB/RF write OK. We should prevent enter IPS. radio off. */

@@ -979,7 +990,8 @@ int rtl92se_hw_init(struct ieee80211_hw
 	/* 4. Initialize BB After MAC Config PHY_reg.txt, AGC_Tab.txt */
 	if (rtl92s_phy_bb_config(hw) != true) {
 		RT_TRACE(rtlpriv, COMP_INIT, DBG_EMERG, ("BB Config failed\n"));
-		return rtstatus;
+		err = rtstatus;
+		goto exit;
 	}
 
 	/* 5. Initiailze RF RAIO_A.txt RF RAIO_B.txt */

@@ -1015,7 +1027,8 @@ int rtl92se_hw_init(struct ieee80211_hw
 
 	if (rtl92s_phy_rf_config(hw) != true) {
 		RT_TRACE(rtlpriv, COMP_INIT, DBG_DMESG, ("RF Config failed\n"));
-		return rtstatus;
+		err = rtstatus;
+		goto exit;
 	}
 
 	/* After read predefined TXT, we must set BB/MAC/RF

@@ -1089,8 +1102,9 @@ int rtl92se_hw_init(struct ieee80211_hw
 
 	rtlpriv->cfg->ops->led_control(hw, LED_CTL_POWER_ON);
 	rtl92s_dm_init(hw);
+exit:
+	local_irq_restore(flags);
 	rtlpci->being_init_adapter = false;
-
 	return err;
 }

Ben Hutchings

author

2014-04-28 01:11 UTC #39 lore raw

PATCH 39/94 staging:serqt_usb2: Fix sparse warning restricted __le16 degrades to integer

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Himangi Saraogi <[email protected]>

commit abe5d64d1a74195a44cd14624f8178b9f48b7cc7 upstream.

This patch fixes the following sparse warning :
drivers/staging/serqt_usb2/serqt_usb2.c:727:40: warning: restricted __le16 degrades to integer

Signed-off-by Himangi Saraogi <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/staging/serqt_usb2/serqt_usb2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

drivers/staging/serqt_usb2/serqt_usb2.c +1 -1

@@ -772,7 +772,7 @@ static int qt_startup(struct usb_serial
 		goto startup_error;
 	}
 
-	switch (serial->dev->descriptor.idProduct) {
+	switch (le16_to_cpu(serial->dev->descriptor.idProduct)) {
 	case QUATECH_DSU100:
 	case QUATECH_QSU100:
 	case QUATECH_ESU100A:

Ben Hutchings

author

2014-04-28 01:11 UTC #40 lore raw

PATCH 40/94 Btrfs: skip submitting barrier for missing device

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Hidetoshi Seto <[email protected]>

commit f88ba6a2a44ee98e8d59654463dc157bb6d13c43 upstream.

I got an error on v3.13:
BTRFS error (device sdf1) in write_all_supers:3378: errno=-5 IO failure (errors while submitting device barriers.)

how to reproduce:

Quoted 4 lines

mkfs.btrfs -f -d raid1 /dev/sdf1 /dev/sdf2
wipefs -a /dev/sdf2
mount -o degraded /dev/sdf1 /mnt
btrfs balance start -f -sconvert=single -mconvert=single -dconvert=single /mnt

The reason of the error is that barrier_all_devices() failed to submit barrier to the missing device. However it is clear that we cannot do anything on missing device, and also it is not necessary to care chunks on the missing device.

This patch stops sending/waiting barrier if device is missing.

Signed-off-by Hidetoshi Seto <[email protected]>

Signed-off-by Josef Bacik <[email protected]>

---
 fs/btrfs/disk-io.c | 4 ++++
 1 file changed, 4 insertions(+)

fs/btrfs/disk-io.c +4 -0

@@ -2731,6 +2731,8 @@ static int barrier_all_devices(struct bt
 	/* send down all the barriers */
 	head = &info->fs_devices->devices;
 	list_for_each_entry_rcu(dev, head, dev_list) {
+		if (dev->missing)
+			continue;
 		if (!dev->bdev) {
 			errors++;
 			continue;

@@ -2745,6 +2747,8 @@ static int barrier_all_devices(struct bt
 
 	/* wait for all the barriers */
 	list_for_each_entry_rcu(dev, head, dev_list) {
+		if (dev->missing)
+			continue;
 		if (!dev->bdev) {
 			errors++;
 			continue;

Ben Hutchings

author

2014-04-28 01:11 UTC #41 lore raw

PATCH 41/94 jffs2: remove from wait queue after schedule()

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Li Zefan <[email protected]>

commit 3ead9578443b66ddb3d50ed4f53af8a0c0298ec5 upstream.

@wait is a local variable, so if we don't remove it from the wait queue list, later wake_up() may end up accessing invalid memory.

This was spotted by eyes.

Signed-off-by Li Zefan <[email protected]>

Cc David Woodhouse <[email protected]>

Cc Artem Bityutskiy <[email protected]>

---
 fs/jffs2/nodemgmt.c | 1 +
 1 file changed, 1 insertion(+)

fs/jffs2/nodemgmt.c +1 -0

@@ -128,6 +128,7 @@ int jffs2_reserve_space(struct jffs2_sb_
 					spin_unlock(&c->erase_completion_lock);
 
 					schedule();
+					remove_wait_queue(&c->erase_wait, &wait);
 				} else
 					spin_unlock(&c->erase_completion_lock);
 			} else if (ret)

Ben Hutchings

author

2014-04-28 01:11 UTC #42 lore raw

PATCH 42/94 jffs2: avoid soft-lockup in jffs2_reserve_space_gc()

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Li Zefan <[email protected]>

commit 13b546d96207c131eeae15dc7b26c6e7d0f1cad7 upstream.

We triggered soft-lockup under stress test on 2.6.34 kernel.

BUG: soft lockup - CPU#1 stuck for 60009ms! [lockf2.test:14488]

...
[<bf09a4d4>] (jffs2_do_reserve_space+0x420/0x440 [jffs2]) [<bf09a528>] (jffs2_reserve_space_gc+0x34/0x78 [jffs2]) [<bf0a1350>] (jffs2_garbage_collect_dnode.isra.3+0x264/0x478 [jffs2]) [<bf0a2078>] (jffs2_garbage_collect_pass+0x9c0/0xe4c [jffs2]) [<bf09a670>] (jffs2_reserve_space+0x104/0x2a8 [jffs2]) [<bf09dc48>] (jffs2_write_inode_range+0x5c/0x4d4 [jffs2]) [<bf097d8c>] (jffs2_write_end+0x198/0x2c0 [jffs2]) [<c00e00a4>] (generic_file_buffered_write+0x158/0x200) [<c00e14f4>] (__generic_file_aio_write+0x3a4/0x414) [<c00e15c0>] (generic_file_aio_write+0x5c/0xbc) [<c012334c>] (do_sync_write+0x98/0xd4)
[<c0123a84>] (vfs_write+0xa8/0x150)
[<c0123d74>] (sys_write+0x3c/0xc0)]

Fix this by adding a cond_resched() in the while loop.

[[email protected]: don't initialize `ret']

Signed-off-by Li Zefan <[email protected]>

Cc David Woodhouse <[email protected]>

Cc Artem Bityutskiy <[email protected]>

[bwh: Backported to 3.2: adjust context]

---
 fs/jffs2/nodemgmt.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

fs/jffs2/nodemgmt.c +9 -4

@@ -159,19 +159,24 @@ int jffs2_reserve_space(struct jffs2_sb_
 int jffs2_reserve_space_gc(struct jffs2_sb_info *c, uint32_t minsize,
 			   uint32_t *len, uint32_t sumsize)
 {
-	int ret = -EAGAIN;
+	int ret;
 	minsize = PAD(minsize);
 
 	D1(printk(KERN_DEBUG "jffs2_reserve_space_gc(): Requested 0x%x bytes\n", minsize));
 
-	spin_lock(&c->erase_completion_lock);
-	while(ret == -EAGAIN) {
+	while (true) {
+		spin_lock(&c->erase_completion_lock);
 		ret = jffs2_do_reserve_space(c, minsize, len, sumsize);
 		if (ret) {
 			D1(printk(KERN_DEBUG "jffs2_reserve_space_gc: looping, ret is %d\n", ret));
 		}
+		spin_unlock(&c->erase_completion_lock);
+
+		if (ret == -EAGAIN)
+			cond_resched();
+		else
+			break;
 	}
-	spin_unlock(&c->erase_completion_lock);
 	if (!ret)
 		ret = jffs2_prealloc_raw_node_refs(c, c->nextblock, 1);

Ben Hutchings

author

2014-04-28 01:11 UTC #43 lore raw

PATCH 43/94 jffs2: Fix segmentation fault found in stress test

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Kamlakant Patel <[email protected]>

commit 3367da5610c50e6b83f86d366d72b41b350b06a2 upstream.

Creating a large file on a JFFS2 partition sometimes crashes with this call trace:

[  306.476000] CPU 13 Unable to handle kernel paging request at virtual address c0000000dfff8002, epc == ffffffffc03a80a8, ra == ffffffffc03a8044
[  306.488000] Oops[#1]:
[  306.488000] Cpu 13
[  306.492000] $ 0   : 0000000000000000 0000000000000000 0000000000008008 0000000000008007
[  306.500000] $ 4   : c0000000dfff8002 000000000000009f c0000000e0007cde c0000000ee95fa58
[  306.508000] $ 8   : 0000000000000001 0000000000008008 0000000000010000 ffffffffffff8002
[  306.516000] $12   : 0000000000007fa9 000000000000ff0e 000000000000ff0f 80e55930aebb92bb
[  306.524000] $16   : c0000000e0000000 c0000000ee95fa5c c0000000efc80000 ffffffffc09edd70
[  306.532000] $20   : ffffffffc2b60000 c0000000ee95fa58 0000000000000000 c0000000efc80000
[  306.540000] $24   : 0000000000000000 0000000000000004
[  306.548000] $28   : c0000000ee950000 c0000000ee95f738 0000000000000000 ffffffffc03a8044
[  306.556000] Hi    : 00000000000574a5
[  306.560000] Lo    : 6193b7a7e903d8c9
[  306.564000] epc   : ffffffffc03a80a8 jffs2_rtime_compress+0x98/0x198
[  306.568000]     Tainted: G        W
[  306.572000] ra    : ffffffffc03a8044 jffs2_rtime_compress+0x34/0x198
[  306.580000] Status: 5000f8e3    KX SX UX KERNEL EXL IE
[  306.584000] Cause : 00800008
[  306.588000] BadVA : c0000000dfff8002
[  306.592000] PrId  : 000c1100 (Netlogic XLP)
[  306.596000] Modules linked in:
[  306.596000] Process dd (pid: 170, threadinfo=c0000000ee950000, task=c0000000ee6e0858, tls=0000000000c47490)
[  306.608000] Stack : 7c547f377ddc7ee4 7ffc7f967f5d7fae 7f617f507fc37ff4 7e7d7f817f487f5f
        7d8e7fec7ee87eb3 7e977ff27eec7f9e 7d677ec67f917f67 7f3d7e457f017ed7
        7fd37f517f867eb2 7fed7fd17ca57e1d 7e5f7fe87f257f77 7fd77f0d7ede7fdb
        7fba7fef7e197f99 7fde7fe07ee37eb5 7f5c7f8c7fc67f65 7f457fb87f847e93
        7f737f3e7d137cd9 7f8e7e9c7fc47d25 7dbb7fac7fb67e52 7ff17f627da97f64
        7f6b7df77ffa7ec5 80057ef17f357fb3 7f767fa27dfc7fd5 7fe37e8e7fd07e53
        7e227fcf7efb7fa1 7f547e787fa87fcc 7fcb7fc57f5a7ffb 7fc07f6c7ea97e80
        7e2d7ed17e587ee0 7fb17f9d7feb7f31 7f607e797e887faa 7f757fdd7c607ff3
        7e877e657ef37fbd 7ec17fd67fe67ff7 7ff67f797ff87dc4 7eef7f3a7c337fa6
        7fe57fc97ed87f4b 7ebe7f097f0b8003 7fe97e2a7d997cba 7f587f987f3c7fa9
        ...
[  306.676000] Call Trace:
[  306.680000] [<ffffffffc03a80a8>] jffs2_rtime_compress+0x98/0x198
[  306.684000] [<ffffffffc0394f10>] jffs2_selected_compress+0x110/0x230
[  306.692000] [<ffffffffc039508c>] jffs2_compress+0x5c/0x388
[  306.696000] [<ffffffffc039dc58>] jffs2_write_inode_range+0xd8/0x388
[  306.704000] [<ffffffffc03971bc>] jffs2_write_end+0x16c/0x2d0
[  306.708000] [<ffffffffc01d3d90>] generic_file_buffered_write+0xf8/0x2b8
[  306.716000] [<ffffffffc01d4e7c>] __generic_file_aio_write+0x1ac/0x350
[  306.720000] [<ffffffffc01d50a0>] generic_file_aio_write+0x80/0x168
[  306.728000] [<ffffffffc021f7dc>] do_sync_write+0x94/0xf8
[  306.732000] [<ffffffffc021ff6c>] vfs_write+0xa4/0x1a0
[  306.736000] [<ffffffffc02202e8>] SyS_write+0x50/0x90
[  306.744000] [<ffffffffc0116cc0>] handle_sys+0x180/0x1a0
[  306.748000]
[  306.748000]
Code: 020b202d  0205282d  90a50000 <90840000> 14a40038  00000000  0060602d  0000282d  016c5823
[  306.760000] ---[ end trace 79dd088435be02d0 ]---

Segmentation fault

This crash is caused because the 'positions' is declared as an array of signed short. The value of position is in the range 0..65535, and will be converted to a negative number when the position is greater than 32767 and causes a corruption and crash. Changing the definition to 'unsigned short' fixes this issue

Signed-off-by Jayachandran C <[email protected]>

Signed-off-by Kamlakant Patel <[email protected]>

---
 fs/jffs2/compr_rtime.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

fs/jffs2/compr_rtime.c +2 -2

@@ -33,7 +33,7 @@ static int jffs2_rtime_compress(unsigned
 				unsigned char *cpage_out,
 				uint32_t *sourcelen, uint32_t *dstlen)
 {
-	short positions[256];
+	unsigned short positions[256];
 	int outpos = 0;
 	int pos=0;

@@ -74,7 +74,7 @@ static int jffs2_rtime_decompress(unsign
 				  unsigned char *cpage_out,
 				  uint32_t srclen, uint32_t destlen)
 {
-	short positions[256];
+	unsigned short positions[256];
 	int outpos = 0;
 	int pos=0;

Ben Hutchings

author

2014-04-28 01:11 UTC #44 lore raw

PATCH 44/94 jffs2: Fix crash due to truncation of csize

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Ajesh Kunhipurayil Vijayan <[email protected]>

commit 41bf1a24c1001f4d0d41a78e1ac575d2f14789d7 upstream.

mounting JFFS2 partition sometimes crashes with this call trace:

[ 1322.240000] Kernel bug detected[#1]:
[ 1322.244000] Cpu 2
[ 1322.244000] $ 0   : 0000000000000000 0000000000000018 000000003ff00070 0000000000000001
[ 1322.252000] $ 4   : 0000000000000000 c0000000f3980150 0000000000000000 0000000000010000
[ 1322.260000] $ 8   : ffffffffc09cd5f8 0000000000000001 0000000000000088 c0000000ed300de8
[ 1322.268000] $12   : e5e19d9c5f613a45 ffffffffc046d464 0000000000000000 66227ba5ea67b74e
[ 1322.276000] $16   : c0000000f1769c00 c0000000ed1e0200 c0000000f3980150 0000000000000000
[ 1322.284000] $20   : c0000000f3a80000 00000000fffffffc c0000000ed2cfbd8 c0000000f39818f0
[ 1322.292000] $24   : 0000000000000004 0000000000000000
[ 1322.300000] $28   : c0000000ed2c0000 c0000000ed2cfab8 0000000000010000 ffffffffc039c0b0
[ 1322.308000] Hi    : 000000000000023c
[ 1322.312000] Lo    : 000000000003f802
[ 1322.316000] epc   : ffffffffc039a9f8 check_tn_node+0x88/0x3b0
[ 1322.320000]     Not tainted
[ 1322.324000] ra    : ffffffffc039c0b0 jffs2_do_read_inode_internal+0x1250/0x1e48
[ 1322.332000] Status: 5400f8e3    KX SX UX KERNEL EXL IE
[ 1322.336000] Cause : 00800034
[ 1322.340000] PrId  : 000c1004 (Netlogic XLP)
[ 1322.344000] Modules linked in:
[ 1322.348000] Process jffs2_gcd_mtd7 (pid: 264, threadinfo=c0000000ed2c0000, task=c0000000f0e68dd8, tls=0000000000000000)
[ 1322.356000] Stack : c0000000f1769e30 c0000000ed010780 c0000000ed010780 c0000000ed300000
        c0000000f1769c00 c0000000f3980150 c0000000f3a80000 00000000fffffffc
        c0000000ed2cfbd8 ffffffffc039c0b0 ffffffffc09c6340 0000000000001000
        0000000000000dec ffffffffc016c9d8 c0000000f39805a0 c0000000f3980180
        0000008600000000 0000000000000000 0000000000000000 0000000000000000
        0001000000000dec c0000000f1769d98 c0000000ed2cfb18 0000000000010000
        0000000000010000 0000000000000044 c0000000f3a80000 c0000000f1769c00
        c0000000f3d207a8 c0000000f1769d98 c0000000f1769de0 ffffffffc076f9c0
        0000000000000009 0000000000000000 0000000000000000 ffffffffc039cf90
        0000000000000017 ffffffffc013fbdc 0000000000000001 000000010003e61c
        ...
[ 1322.424000] Call Trace:
[ 1322.428000] [<ffffffffc039a9f8>] check_tn_node+0x88/0x3b0
[ 1322.432000] [<ffffffffc039c0b0>] jffs2_do_read_inode_internal+0x1250/0x1e48
[ 1322.440000] [<ffffffffc039cf90>] jffs2_do_crccheck_inode+0x70/0xd0
[ 1322.448000] [<ffffffffc03a1b80>] jffs2_garbage_collect_pass+0x160/0x870
[ 1322.452000] [<ffffffffc03a392c>] jffs2_garbage_collect_thread+0xdc/0x1f0
[ 1322.460000] [<ffffffffc01541c8>] kthread+0xb8/0xc0
[ 1322.464000] [<ffffffffc0106d18>] kernel_thread_helper+0x10/0x18
[ 1322.472000]
[ 1322.472000]
Code: 67bd0050  94a4002c  2c830001 <00038036> de050218  2403fffc  0080a82d  00431824  24630044
[ 1322.480000] ---[ end trace b052bb90e97dfbf5 ]---

The variable csize in structure jffs2_tmp_dnode_info is of type uint16_t, but it is used to hold the compressed data length(csize) which is declared as uint32_t. So, when the value of csize exceeds 16bits, it gets truncated when assigned to tn->csize. This is causing a kernel BUG.
Changing the definition of csize in jffs2_tmp_dnode_info to uint32_t fixes the issue.

Signed-off-by Ajesh Kunhipurayil Vijayan <[email protected]>

Signed-off-by Kamlakant Patel <[email protected]>

---
 fs/jffs2/nodelist.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

fs/jffs2/nodelist.h +1 -1

@@ -231,7 +231,7 @@ struct jffs2_tmp_dnode_info
 	uint32_t version;
 	uint32_t data_crc;
 	uint32_t partial_crc;
-	uint16_t csize;
+	uint32_t csize;
 	uint16_t overlapped;
 };

Ben Hutchings

author

2014-04-28 01:11 UTC #45 lore raw

PATCH 45/94 iwlwifi: dvm: take mutex when sending SYNC BT config command

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Emmanuel Grumbach <[email protected]>

commit 82e5a649453a3cf23516277abb84273768a1592b upstream.

There is a flow in which we send the host command in SYNC mode, but we don't take priv->mutex.

Fixes https://bugzilla.redhat.com/show_bug.cgi?id=1046495

Reviewed-by Johannes Berg <[email protected]>

Signed-off-by Emmanuel Grumbach <[email protected]>

[bwh: Backported to 3.2:
- Adjust filename, context
- mutex is priv->shrd->mutex]

---
 drivers/net/wireless/iwlwifi/iwl-agn.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

drivers/net/wireless/iwlwifi/iwl-agn.c +6 -2

@@ -246,13 +246,17 @@ static void iwl_bg_bt_runtime_config(str
 	struct iwl_priv *priv =
 		container_of(work, struct iwl_priv, bt_runtime_config);
 
+	mutex_lock(&priv->shrd->mutex);
 	if (test_bit(STATUS_EXIT_PENDING, &priv->shrd->status))
-		return;
+		goto out;
 
 	/* dont send host command if rf-kill is on */
 	if (!iwl_is_ready_rf(priv->shrd))
-		return;
+		goto out;
+
 	iwlagn_send_advance_bt_config(priv);
+out:
+	mutex_unlock(&priv->shrd->mutex);
 }
 
 static void iwl_bg_bt_full_concurrency(struct work_struct *work)

Ben Hutchings

author

2014-04-28 01:11 UTC #46 lore raw

PATCH 46/94 virtio_balloon: don't softlockup on huge balloon changes.

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Rusty Russell <[email protected]>

commit 1f74ef0f2d7d692fcd615621e0e734c3e7771413 upstream.

When adding or removing 100G from a balloon:

    BUG: soft lockup - CPU#0 stuck for 22s! [vballoon:367]

We have a wait_event_interruptible(), but the condition is always true (more ballooning to do) so we don't ever sleep. We also have a wait_event() for the host to ack, but that is also always true as QEMU is synchronous for balloon operations.

Reported-by Gopesh Kumar Chaudhary <[email protected]>

Signed-off-by Rusty Russell <[email protected]>

---
 drivers/virtio/virtio_balloon.c | 6 ++++++
 1 file changed, 6 insertions(+)

drivers/virtio/virtio_balloon.c +6 -0

@@ -271,6 +271,12 @@ static int balloon(void *_vballoon)
 		else if (diff < 0)
 			leak_balloon(vb, -diff);
 		update_balloon_size(vb);
+
+		/*
+		 * For large balloon changes, we could spend a lot of time
+		 * and always have work to do.  Be nice if preempt disabled.
+		 */
+		cond_resched();
 	}
 	return 0;
 }

Ben Hutchings

author

2014-04-28 01:11 UTC #47 lore raw

PATCH 47/94 ext4: fix partial cluster handling for bigalloc file systems

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Eric Whitney <[email protected]>

commit c06344939422bbd032ac967223a7863de57496b5 upstream.

Commit 9cb00419fa, which enables hole punching for bigalloc file systems, exposed a bug introduced by commit 6ae06ff51e in an earlier release. When run on a bigalloc file system, xfstests generic/013, 068, 075, 083, 091, 100, 112, 127, 263, 269, and 270 fail with e2fsck errors or cause kernel error messages indicating that previously freed blocks are being freed again.

The latter commit optimizes the selection of the starting extent in ext4_ext_rm_leaf() when hole punching by beginning with the extent supplied in the path argument rather than with the last extent in the leaf node (as is still done when truncating). However, the code in rm_leaf that initially sets partial_cluster to track cluster sharing on extent boundaries is only guaranteed to run if rm_leaf starts with the last node in the leaf. Consequently, partial_cluster is not correctly initialized when hole punching, and a cluster on the boundary of a punched region that should be retained may instead be deallocated.

Signed-off-by Eric Whitney <[email protected]>

Signed-off-by "Theodore Ts'o" <[email protected]>

---
 fs/ext4/extents.c | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

fs/ext4/extents.c +21 -0

@@ -2372,6 +2372,27 @@ ext4_ext_rm_leaf(handle_t *handle, struc
 	ex_ee_block = le32_to_cpu(ex->ee_block);
 	ex_ee_len = ext4_ext_get_actual_len(ex);
 
+	/*
+	 * If we're starting with an extent other than the last one in the
+	 * node, we need to see if it shares a cluster with the extent to
+	 * the right (towards the end of the file). If its leftmost cluster
+	 * is this extent's rightmost cluster and it is not cluster aligned,
+	 * we'll mark it as a partial that is not to be deallocated.
+	 */
+
+	if (ex != EXT_LAST_EXTENT(eh)) {
+		ext4_fsblk_t current_pblk, right_pblk;
+		long long current_cluster, right_cluster;
+
+		current_pblk = ext4_ext_pblock(ex) + ex_ee_len - 1;
+		current_cluster = (long long)EXT4_B2C(sbi, current_pblk);
+		right_pblk = ext4_ext_pblock(ex + 1);
+		right_cluster = (long long)EXT4_B2C(sbi, right_pblk);
+		if (current_cluster == right_cluster &&
+			EXT4_PBLK_COFF(sbi, right_pblk))
+			*partial_cluster = -right_cluster;
+	}
+
 	trace_ext4_ext_rm_leaf(inode, start, ex, *partial_cluster);
 
 	while (ex >= EXT_FIRST_EXTENT(eh) &&

Ben Hutchings

author

2014-04-28 01:11 UTC #48 lore raw

PATCH 48/94 ath9k: fix ready time of the multicast buffer queue

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Felix Fietkau <[email protected]>

commit 3b3e0efb5c72c4fc940af50b33626b8a78a907dc upstream.

qi->tqi_readyTime is written directly to registers that expect microseconds as unit instead of TU.
When setting the CABQ ready time, cur_conf->beacon_interval is in TU, so convert it to microseconds before passing it to ath9k_hw.

This should hopefully fix some Tx DMA issues with buffered multicast frames in AP mode.

Signed-off-by Felix Fietkau <[email protected]>

Signed-off-by John W. Linville <[email protected]>

[bwh: Backported to 3.2: adjust context]

---
 drivers/net/wireless/ath/ath9k/xmit.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

drivers/net/wireless/ath/ath9k/xmit.c +1 -1

@@ -1390,7 +1390,7 @@ int ath_cabq_update(struct ath_softc *sc
 	else if (sc->config.cabqReadytime > ATH9K_READY_TIME_HI_BOUND)
 		sc->config.cabqReadytime = ATH9K_READY_TIME_HI_BOUND;
 
-	qi.tqi_readyTime = (cur_conf->beacon_interval *
+	qi.tqi_readyTime = (TU_TO_USEC(cur_conf->beacon_interval) *
 			    sc->config.cabqReadytime) / 100;
 	ath_txq_update(sc, qnum, &qi);

Ben Hutchings

author

2014-04-28 01:11 UTC #49 lore raw

PATCH 49/94 IB/ipath: Fix potential buffer overrun in sending diag packet routine

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Dennis Dalessandro <[email protected]>

commit a2cb0eb8a64adb29a99fd864013de957028f36ae upstream.

Guard against a potential buffer overrun. The size to read from the user is passed in, and due to the padding that needs to be taken into account, as well as the place holder for the ICRC it is possible to overflow the 32bit value which would cause more data to be copied from user space than is allocated in the buffer.

Reported-by Nico Golde <[email protected]>

Reported-by Fabian Yamaguchi <[email protected]>

Reviewed-by Mike Marciniszyn <[email protected]>

Signed-off-by Dennis Dalessandro <[email protected]>

---
 drivers/infiniband/hw/ipath/ipath_diag.c | 66 ++++++++++++--------------------
 1 file changed, 25 insertions(+), 41 deletions(-)

drivers/infiniband/hw/ipath/ipath_diag.c +25 ~~-41~~

@@ -326,7 +326,7 @@ static ssize_t ipath_diagpkt_write(struc
 				   size_t count, loff_t *off)
 {
 	u32 __iomem *piobuf;
-	u32 plen, clen, pbufn;
+	u32 plen, pbufn, maxlen_reserve;
 	struct ipath_diag_pkt odp;
 	struct ipath_diag_xpkt dp;
 	u32 *tmpbuf = NULL;

@@ -335,51 +335,29 @@ static ssize_t ipath_diagpkt_write(struc
 	u64 val;
 	u32 l_state, lt_state; /* LinkState, LinkTrainingState */
 
-	if (count < sizeof(odp)) {
-		ret = -EINVAL;
-		goto bail;
-	}
 
 	if (count == sizeof(dp)) {
 		if (copy_from_user(&dp, data, sizeof(dp))) {
 			ret = -EFAULT;
 			goto bail;
 		}
-	} else if (copy_from_user(&odp, data, sizeof(odp))) {
-		ret = -EFAULT;
+	} else if (count == sizeof(odp)) {
+		if (copy_from_user(&odp, data, sizeof(odp))) {
+			ret = -EFAULT;
+			goto bail;
+		}
+	} else {
+		ret = -EINVAL;
 		goto bail;
 	}
 
-	/*
-	 * Due to padding/alignment issues (lessened with new struct)
-	 * the old and new structs are the same length. We need to
-	 * disambiguate them, which we can do because odp.len has never
-	 * been less than the total of LRH+BTH+DETH so far, while
-	 * dp.unit (same offset) unit is unlikely to get that high.
-	 * Similarly, dp.data, the pointer to user at the same offset
-	 * as odp.unit, is almost certainly at least one (512byte)page
-	 * "above" NULL. The if-block below can be omitted if compatibility
-	 * between a new driver and older diagnostic code is unimportant.
-	 * compatibility the other direction (new diags, old driver) is
-	 * handled in the diagnostic code, with a warning.
-	 */
-	if (dp.unit >= 20 && dp.data < 512) {
-		/* very probable version mismatch. Fix it up */
-		memcpy(&odp, &dp, sizeof(odp));
-		/* We got a legacy dp, copy elements to dp */
-		dp.unit = odp.unit;
-		dp.data = odp.data;
-		dp.len = odp.len;
-		dp.pbc_wd = 0; /* Indicate we need to compute PBC wd */
-	}
-
 	/* send count must be an exact number of dwords */
 	if (dp.len & 3) {
 		ret = -EINVAL;
 		goto bail;
 	}
 
-	clen = dp.len >> 2;
+	plen = dp.len >> 2;
 
 	dd = ipath_lookup(dp.unit);
 	if (!dd || !(dd->ipath_flags & IPATH_PRESENT) ||

@@ -422,16 +400,22 @@ static ssize_t ipath_diagpkt_write(struc
 		goto bail;
 	}
 
-	/* need total length before first word written */
-	/* +1 word is for the qword padding */
-	plen = sizeof(u32) + dp.len;
-
-	if ((plen + 4) > dd->ipath_ibmaxlen) {
+	/*
+	 * need total length before first word written, plus 2 Dwords. One Dword
+	 * is for padding so we get the full user data when not aligned on
+	 * a word boundary. The other Dword is to make sure we have room for the
+	 * ICRC which gets tacked on later.
+	 */
+	maxlen_reserve = 2 * sizeof(u32);
+	if (dp.len > dd->ipath_ibmaxlen - maxlen_reserve) {
 		ipath_dbg("Pkt len 0x%x > ibmaxlen %x\n",
-			  plen - 4, dd->ipath_ibmaxlen);
+			  dp.len, dd->ipath_ibmaxlen);
 		ret = -EINVAL;
-		goto bail;	/* before writing pbc */
+		goto bail;
 	}
+
+	plen = sizeof(u32) + dp.len;
+
 	tmpbuf = vmalloc(plen);
 	if (!tmpbuf) {
 		dev_info(&dd->pcidev->dev, "Unable to allocate tmp buffer, "

@@ -473,11 +457,11 @@ static ssize_t ipath_diagpkt_write(struc
 	 */
 	if (dd->ipath_flags & IPATH_PIO_FLUSH_WC) {
 		ipath_flush_wc();
-		__iowrite32_copy(piobuf + 2, tmpbuf, clen - 1);
+		__iowrite32_copy(piobuf + 2, tmpbuf, plen - 1);
 		ipath_flush_wc();
-		__raw_writel(tmpbuf[clen - 1], piobuf + clen + 1);
+		__raw_writel(tmpbuf[plen - 1], piobuf + plen + 1);
 	} else
-		__iowrite32_copy(piobuf + 2, tmpbuf, clen);
+		__iowrite32_copy(piobuf + 2, tmpbuf, plen);
 
 	ipath_flush_wc();

Ben Hutchings

author

2014-04-28 01:11 UTC #50 lore raw

PATCH 50/94 IB/nes: Return an error on ib_copy_from_udata() failure instead of NULL

Link https://www.gitorious.org/opteya/ib-hw-nes-create-qp-null

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Yann Droneaud <[email protected]>

commit 9d194d1025f463392feafa26ff8c2d8247f71be1 upstream.

In case of error while accessing to userspace memory, function nes_create_qp() returns NULL instead of an error code wrapped through ERR_PTR(). But NULL is not expected by ib_uverbs_create_qp(), as it check for error with IS_ERR().

As page 0 is likely not mapped, it is going to trigger an Oops when the kernel will try to dereference NULL pointer to access to struct ib_qp's fields.

In some rare cases, page 0 could be mapped by userspace, which could turn this bug to a vulnerability that could be exploited: the function pointers in struct ib_device will be under userspace total control.

This was caught when using spatch (aka. coccinelle) to rewrite calls to ib_copy_{from,to}_udata().

Link https://www.gitorious.org/opteya/coccib/source/75ebf2c1033c64c1d81df13e4ae44ee99c989eba:ib_copy_udata.cocci

Link http://marc.info/[email protected]

Signed-off-by Yann Droneaud <[email protected]>

---
 drivers/infiniband/hw/nes/nes_verbs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

drivers/infiniband/hw/nes/nes_verbs.c +1 -1

@@ -1183,7 +1183,7 @@ static struct ib_qp *nes_create_qp(struc
 					nes_free_resource(nesadapter, nesadapter->allocated_qps, qp_num);
 					kfree(nesqp->allocated_buffer);
 					nes_debug(NES_DBG_QP, "ib_copy_from_udata() Failed \n");
-					return NULL;
+					return ERR_PTR(-EFAULT);
 				}
 				if (req.user_wqe_buffers) {
 					virt_wqs = 1;

Ben Hutchings

author

2014-04-28 01:11 UTC #51 lore raw

PATCH 51/94 mfd: Include all drivers in subsystem menu

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Linus Walleij <[email protected]>

commit a6e6e660baa5c583022e3e48c85316bace027825 upstream.

It is currently not possible to select the SA1100 or Vexpress drivers in the MFD subsystem, because the menu for the entire subsystem ends before these options are presented.

Move the main menu closing and the endif for HAS_IOMEM to the end of the file so these are selectable again.

Signed-off-by Linus Walleij <[email protected]>

Signed-off-by Lee Jones <[email protected]>

[bwh: Backported to 3.2: adjust context]

---
 drivers/mfd/Kconfig | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

drivers/mfd/Kconfig +3 -3

@@ -772,9 +772,6 @@ config MFD_INTEL_MSIC
 	  Passage) chip. This chip embeds audio, battery, GPIO, etc.
 	  devices used in Intel Medfield platforms.
 
-endmenu
-endif
-
 menu "Multimedia Capabilities Port drivers"
 	depends on ARCH_SA1100

@@ -797,3 +794,6 @@ config MCP_UCB1200_TS
 	depends on MCP_UCB1200 && INPUT
 
 endmenu
+
+endmenu
+endif

Ben Hutchings

author

2014-04-28 01:11 UTC #52 lore raw

PATCH 52/94 mfd: max8997: Fix possible NULL pointer dereference on i2c_new_dummy error

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Krzysztof Kozlowski <[email protected]>

commit 97dc4ed3fa377ec91bb60ba98b70d645c2099384 upstream.

During probe the driver allocates dummy I2C devices for RTC, haptic and MUIC with i2c_new_dummy() but it does not check the return value of this calls.

In case of error (i2c_new_device(): memory allocation failure or I2C address cannot be used) this function returns NULL which is later used by i2c_unregister_device().

If i2c_new_dummy() fails for RTC, haptic or MUIC devices, fail also the probe for main MFD driver.

Signed-off-by Krzysztof Kozlowski <[email protected]>

Signed-off-by Lee Jones <[email protected]>

---
 drivers/mfd/max8997.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

drivers/mfd/max8997.c +18 -0

@@ -148,10 +148,26 @@ static int max8997_i2c_probe(struct i2c_
 	mutex_init(&max8997->iolock);
 
 	max8997->rtc = i2c_new_dummy(i2c->adapter, I2C_ADDR_RTC);
+	if (!max8997->rtc) {
+		dev_err(max8997->dev, "Failed to allocate I2C device for RTC\n");
+		return -ENODEV;
+	}
 	i2c_set_clientdata(max8997->rtc, max8997);
+
 	max8997->haptic = i2c_new_dummy(i2c->adapter, I2C_ADDR_HAPTIC);
+	if (!max8997->haptic) {
+		dev_err(max8997->dev, "Failed to allocate I2C device for Haptic\n");
+		ret = -ENODEV;
+		goto err_i2c_haptic;
+	}
 	i2c_set_clientdata(max8997->haptic, max8997);
+
 	max8997->muic = i2c_new_dummy(i2c->adapter, I2C_ADDR_MUIC);
+	if (!max8997->muic) {
+		dev_err(max8997->dev, "Failed to allocate I2C device for MUIC\n");
+		ret = -ENODEV;
+		goto err_i2c_muic;
+	}
 	i2c_set_clientdata(max8997->muic, max8997);
 
 	pm_runtime_set_active(max8997->dev);

@@ -178,7 +194,9 @@ static int max8997_i2c_probe(struct i2c_
 err_mfd:
 	mfd_remove_devices(max8997->dev);
 	i2c_unregister_device(max8997->muic);
+err_i2c_muic:
 	i2c_unregister_device(max8997->haptic);
+err_i2c_haptic:
 	i2c_unregister_device(max8997->rtc);
 err:
 	kfree(max8997);

Ben Hutchings

author

2014-04-28 01:11 UTC #53 lore raw

PATCH 53/94 mfd: max8998: Fix possible NULL pointer dereference on i2c_new_dummy error

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Krzysztof Kozlowski <[email protected]>

commit ed26f87b9f71693a1d1ee85f5e6209601505080f upstream.

During probe the driver allocates dummy I2C device for RTC with i2c_new_dummy() but it does not check the return value of this call.

In case of error (i2c_new_device(): memory allocation failure or I2C address cannot be used) this function returns NULL which is later used by i2c_unregister_device().

If i2c_new_dummy() fails for RTC device, fail also the probe for main MFD driver.

Signed-off-by Krzysztof Kozlowski <[email protected]>

Signed-off-by Lee Jones <[email protected]>

---
 drivers/mfd/max8998.c | 4 ++++
 1 file changed, 4 insertions(+)

drivers/mfd/max8998.c +4 -0

@@ -152,6 +152,10 @@ static int max8998_i2c_probe(struct i2c_
 	mutex_init(&max8998->iolock);
 
 	max8998->rtc = i2c_new_dummy(i2c->adapter, RTC_I2C_ADDR);
+	if (!max8998->rtc) {
+		dev_err(&i2c->dev, "Failed to allocate I2C device for RTC\n");
+		return -ENODEV;
+	}
 	i2c_set_clientdata(max8998->rtc, max8998);
 
 	max8998_irq_init(max8998);

Ben Hutchings

author

2014-04-28 01:11 UTC #54 lore raw

PATCH 54/94 mfd: max8925: Fix possible NULL pointer dereference on i2c_new_dummy error

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Krzysztof Kozlowski <[email protected]>

commit 96cf3dedc491d2f1f66cc26217f2b06b0c7b6797 upstream.

During probe the driver allocates dummy I2C devices for RTC and ADC with i2c_new_dummy() but it does not check the return value of this calls.

In case of error (i2c_new_device(): memory allocation failure or I2C address cannot be used) this function returns NULL which is later used by i2c_unregister_device().

If i2c_new_dummy() fails for RTC or ADC devices, fail also the probe for main MFD driver.

Signed-off-by Krzysztof Kozlowski <[email protected]>

Signed-off-by Lee Jones <[email protected]>

---
 drivers/mfd/max8925-i2c.c | 9 +++++++++
 1 file changed, 9 insertions(+)

drivers/mfd/max8925-i2c.c +9 -0

@@ -156,9 +156,18 @@ static int __devinit max8925_probe(struc
 	mutex_init(&chip->io_lock);
 
 	chip->rtc = i2c_new_dummy(chip->i2c->adapter, RTC_I2C_ADDR);
+	if (!chip->rtc) {
+		dev_err(chip->dev, "Failed to allocate I2C device for RTC\n");
+		return -ENODEV;
+	}
 	i2c_set_clientdata(chip->rtc, chip);
 
 	chip->adc = i2c_new_dummy(chip->i2c->adapter, ADC_I2C_ADDR);
+	if (!chip->adc) {
+		dev_err(chip->dev, "Failed to allocate I2C device for ADC\n");
+		i2c_unregister_device(chip->rtc);
+		return -ENODEV;
+	}
 	i2c_set_clientdata(chip->adc, chip);
 
 	max8925_device_init(chip, pdata);

Ben Hutchings

author

2014-04-28 01:11 UTC #55 lore raw

PATCH 55/94 mfd: 88pm860x: Fix possible NULL pointer dereference on i2c_new_dummy error

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Krzysztof Kozlowski <[email protected]>

commit 159ce52a6b777fc82fa0b51c7440e25f9e4c6feb upstream.

During probe the driver allocates dummy I2C device for companion chip with i2c_new_dummy() but it does not check the return value of this call.

In case of error (i2c_new_device(): memory allocation failure or I2C address cannot be used) this function returns NULL which is later used by regmap_init_i2c().

If i2c_new_dummy() fails for companion device, fail also the probe for main MFD driver.

Signed-off-by Krzysztof Kozlowski <[email protected]>

Signed-off-by Lee Jones <[email protected]>

[bwh: Backported to 3.2:
- Adjust filename, context
- Add kfree() before return, as driver is not using managed allocations]

---
 drivers/mfd/88pm860x-i2c.c | 5 +++++
 1 file changed, 5 insertions(+)

drivers/mfd/88pm860x-i2c.c +6 -0

@@ -290,6 +290,12 @@ static int __devinit pm860x_probe(struct
 		chip->companion_addr = pdata->companion_addr;
 		chip->companion = i2c_new_dummy(chip->client->adapter,
 						chip->companion_addr);
+		if (!chip->companion) {
+			dev_err(&client->dev,
+				"Failed to allocate I2C companion device\n");
+			kfree(chip);
+			return -ENODEV;
+		}
 		i2c_set_clientdata(chip->companion, chip);
 	}

Ben Hutchings

author

2014-04-28 01:11 UTC #56 lore raw

PATCH 56/94 pid: get pid_t ppid of task in init_pid_ns

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Richard Guy Briggs <[email protected]>

commit ad36d28293936b03d6b7996e9d6aadfd73c0eb08 upstream.

Added the functions task_ppid_nr_ns() and task_ppid_nr() to abstract the lookup of the PPID (real_parent's pid_t) of a process, including rcu locking, in the arbitrary and init_pid_ns.
This provides an alternative to sys_getppid(), which is relative to the child process' pid namespace.

(informed by ebiederman's 6c621b7e)

Cc Eric W. Biederman <[email protected]>

Signed-off-by Richard Guy Briggs <[email protected]>

---
 include/linux/sched.h | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

include/linux/sched.h +19 -1

@@ -1690,6 +1690,24 @@ static inline pid_t task_tgid_vnr(struct
 }
 
 
+static int pid_alive(const struct task_struct *p);
+static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns)
+{
+	pid_t pid = 0;
+
+	rcu_read_lock();
+	if (pid_alive(tsk))
+		pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns);
+	rcu_read_unlock();
+
+	return pid;
+}
+
+static inline pid_t task_ppid_nr(const struct task_struct *tsk)
+{
+	return task_ppid_nr_ns(tsk, &init_pid_ns);
+}
+
 static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk,
 					struct pid_namespace *ns)
 {

@@ -1727,7 +1745,7 @@ static inline pid_t task_pgrp_nr(struct
  * If pid_alive fails, then pointers within the task structure
  * can be stale and must not be dereferenced.
  */
-static inline int pid_alive(struct task_struct *p)
+static inline int pid_alive(const struct task_struct *p)
 {
 	return p->pids[PIDTYPE_PID].pid != NULL;
 }

Ben Hutchings

author

2014-04-28 01:11 UTC #57 lore raw

PATCH 57/94 audit: convert PPIDs to the inital PID namespace.

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Richard Guy Briggs <[email protected]>

commit c92cdeb45eea38515e82187f48c2e4f435fb4e25 upstream.

sys_getppid() returns the parent pid of the current process in its own pid namespace. Since audit filters are based in the init pid namespace, a process could avoid a filter or trigger an unintended one by being in an alternate pid namespace or log meaningless information.

Switch to task_ppid_nr() for PPIDs to anchor all audit filters in the init_pid_ns.

(informed by ebiederman's 6c621b7e)

Cc Eric W. Biederman <[email protected]>

Signed-off-by Richard Guy Briggs <[email protected]>

[bwh: Backported to 3.2: sys_getppid() is used by audit_exit() but not
audit_log_task_info()]

---

kernel/auditsc.c +2 -2

@@ -473,7 +473,7 @@ static int audit_filter_rules(struct tas
 		case AUDIT_PPID:
 			if (ctx) {
 				if (!ctx->ppid)
-					ctx->ppid = sys_getppid();
+					ctx->ppid = task_ppid_nr(tsk);
 				result = audit_comparator(ctx->ppid, f->op, f->val);
 			}
 			break;

@@ -1335,7 +1335,7 @@ static void audit_log_exit(struct audit_
 	/* tsk == current */
 	context->pid = tsk->pid;
 	if (!context->ppid)
-		context->ppid = sys_getppid();
+		context->ppid = task_ppid_nr(tsk);
 	cred = current_cred();
 	context->uid   = cred->uid;
 	context->gid   = cred->gid;

Ben Hutchings

author

2014-04-28 01:11 UTC #58 lore raw

PATCH 58/94 Btrfs: fix deadlock with nested trans handles

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Josef Bacik <[email protected]>

commit 3bbb24b20a8800158c33eca8564f432dd14d0bf3 upstream.

Zach found this deadlock that would happen like this

btrfs_end_transaction <- reduce trans->use_count to 0
btrfs_run_delayed_refs

    btrfs_cow_block
      find_free_extent
	btrfs_start_transaction <- increase trans->use_count to 1
          allocate chunk
	btrfs_end_transaction <- decrease trans->use_count to 0
	  btrfs_run_delayed_refs
	    lock tree block we are cowing above ^^

We need to only decrease trans->use_count if it is above 1, otherwise leave it alone. This will make nested trans be the only ones who decrease their added ref, and will let us get rid of the trans->use_count++ hack if we have to commit the transaction. Thanks,

Reported-by Zach Brown <[email protected]>

Signed-off-by Josef Bacik <[email protected]>

Tested-by Zach Brown <[email protected]>

Signed-off-by Chris Mason <[email protected]>

[bwh: Backported to 3.2: adjust context]

---
 fs/btrfs/transaction.c | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

fs/btrfs/transaction.c +4 ~~-10~~

@@ -460,7 +460,8 @@ static int __btrfs_end_transaction(struc
 	struct btrfs_fs_info *info = root->fs_info;
 	int count = 0;
 
-	if (--trans->use_count) {
+	if (trans->use_count > 1) {
+		trans->use_count--;
 		trans->block_rsv = trans->orig_rsv;
 		return 0;
 	}

@@ -494,17 +495,10 @@ static int __btrfs_end_transaction(struc
 	}
 
 	if (lock && cur_trans->blocked && !cur_trans->in_commit) {
-		if (throttle) {
-			/*
-			 * We may race with somebody else here so end up having
-			 * to call end_transaction on ourselves again, so inc
-			 * our use_count.
-			 */
-			trans->use_count++;
+		if (throttle)
 			return btrfs_commit_transaction(trans, root);
-		} else {
+		else
 			wake_up_process(info->transaction_kthread);
-		}
 	}
 
 	WARN_ON(cur_trans != info->running_transaction);

Ben Hutchings

author

2014-04-28 01:11 UTC #59 lore raw

PATCH 59/94 gpio: mxs: Allow for recursive enable_irq_wake() call

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Marek Vasut <[email protected]>

commit a585f87c863e4e1d496459d382b802bf5ebe3717 upstream.

The scenario here is that someone calls enable_irq_wake() from somewhere in the code. This will result in the lockdep producing a backtrace as can be seen below. In my case, this problem is triggered when using the wl1271 (TI WlCore) driver found in drivers/net/wireless/ti/ .

The problem cause is rather obvious from the backtrace, but let's outline the dependency. enable_irq_wake() grabs the IRQ buslock in irq_set_irq_wake(), which in turns calls mxs_gpio_set_wake_irq() . But mxs_gpio_set_wake_irq() calls enable_irq_wake() again on the one-level-higher IRQ , thus it tries to grab the IRQ buslock again in irq_set_irq_wake() . Because the spinlock in irq_set_irq_wake()->irq_get_desc_buslock()->__irq_get_desc_lock() is not marked as recursive, lockdep will spew the stuff below.

We know we can safely re-enter the lock, so use IRQ_GC_INIT_NESTED_LOCK to fix the spew.

=============================================
[ INFO: possible recursive locking detected ] 3.10.33-00012-gf06b763-dirty #61 Not tainted
---------------------------------------------
kworker/0:1/18 is trying to acquire lock:
(&irq_desc_lock_class){-.-...}, at: [<c00685f0>] __irq_get_desc_lock+0x48/0x88

but task is already holding lock:
(&irq_desc_lock_class){-.-...}, at: [<c00685f0>] __irq_get_desc_lock+0x48/0x88

other info that might help us debug this:

  Possible unsafe locking scenario:

        CPU0
        ----

lock(&irq_desc_lock_class);
lock(&irq_desc_lock_class);

*** DEADLOCK ***

May be due to missing lock nesting notation

3 locks held by kworker/0:1/18:

  #0:  (events){.+.+.+}, at: [<c0036308>] process_one_work+0x134/0x4a4
  #1:  ((&fw_work->work)){+.+.+.}, at: [<c0036308>] process_one_work+0x134/0x4a4
  #2:  (&irq_desc_lock_class){-.-...}, at: [<c00685f0>] __irq_get_desc_lock+0x48/0x88

 stack backtrace:
 CPU: 0 PID: 18 Comm: kworker/0:1 Not tainted 3.10.33-00012-gf06b763-dirty #61
 Workqueue: events request_firmware_work_func
 [<c0013eb4>] (unwind_backtrace+0x0/0xf0) from [<c0011c74>] (show_stack+0x10/0x14)
 [<c0011c74>] (show_stack+0x10/0x14) from [<c005bb08>] (__lock_acquire+0x140c/0x1a64)
 [<c005bb08>] (__lock_acquire+0x140c/0x1a64) from [<c005c6a8>] (lock_acquire+0x9c/0x104)
 [<c005c6a8>] (lock_acquire+0x9c/0x104) from [<c051d5a4>] (_raw_spin_lock_irqsave+0x44/0x58)
 [<c051d5a4>] (_raw_spin_lock_irqsave+0x44/0x58) from [<c00685f0>] (__irq_get_desc_lock+0x48/0x88)
 [<c00685f0>] (__irq_get_desc_lock+0x48/0x88) from [<c0068e78>] (irq_set_irq_wake+0x20/0xf4)
 [<c0068e78>] (irq_set_irq_wake+0x20/0xf4) from [<c027260c>] (mxs_gpio_set_wake_irq+0x1c/0x24)
 [<c027260c>] (mxs_gpio_set_wake_irq+0x1c/0x24) from [<c0068cf4>] (set_irq_wake_real+0x30/0x44)
 [<c0068cf4>] (set_irq_wake_real+0x30/0x44) from [<c0068ee4>] (irq_set_irq_wake+0x8c/0xf4)
 [<c0068ee4>] (irq_set_irq_wake+0x8c/0xf4) from [<c0310748>] (wlcore_nvs_cb+0x10c/0x97c)
 [<c0310748>] (wlcore_nvs_cb+0x10c/0x97c) from [<c02be5e8>] (request_firmware_work_func+0x38/0x58)
 [<c02be5e8>] (request_firmware_work_func+0x38/0x58) from [<c0036394>] (process_one_work+0x1c0/0x4a4)
 [<c0036394>] (process_one_work+0x1c0/0x4a4) from [<c0036a4c>] (worker_thread+0x138/0x394)
 [<c0036a4c>] (worker_thread+0x138/0x394) from [<c003cb74>] (kthread+0xa4/0xb0)
 [<c003cb74>] (kthread+0xa4/0xb0) from [<c000ee00>] (ret_from_fork+0x14/0x34)
 wlcore: loaded

Signed-off-by Marek Vasut <[email protected]>

Acked-by Shawn Guo <[email protected]>

Signed-off-by Linus Walleij <[email protected]>

---
 drivers/gpio/gpio-mxs.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

drivers/gpio/gpio-mxs.c +2 -1

@@ -167,7 +167,8 @@ static void __init mxs_gpio_init_gc(stru
 	ct->regs.ack = PINCTRL_IRQSTAT(port->id) + MXS_CLR;
 	ct->regs.mask = PINCTRL_IRQEN(port->id);
 
-	irq_setup_generic_chip(gc, IRQ_MSK(32), 0, IRQ_NOREQUEST, 0);
+	irq_setup_generic_chip(gc, IRQ_MSK(32), IRQ_GC_INIT_NESTED_LOCK,
+			       IRQ_NOREQUEST, 0);
 }
 
 static int mxs_gpio_to_irq(struct gpio_chip *gc, unsigned offset)

Ben Hutchings

author

2014-04-28 01:11 UTC #60 lore raw

PATCH 60/94 x86, hyperv: Bypass the timer_irq_works() check

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Jason Wang <[email protected]>

commit ca3ba2a2f4a49a308e7d78c784d51b2332064f15 upstream.

This patch bypass the timer_irq_works() check for hyperv guest since:

- It was guaranteed to work.
- timer_irq_works() may fail sometime due to the lpj calibration were inaccurate in a hyperv guest or a buggy host.

In the future, we should get the tsc frequency from hypervisor and use preset lpj instead.

[ hpa: I would prefer to not defer things to "the future" in the future... ]

Cc K. Y. Srinivasan <[email protected]>

Cc Haiyang Zhang <[email protected]>

Acked-by K. Y. Srinivasan <[email protected]>

Signed-off-by Jason Wang <[email protected]>

Link http://lkml.kernel.org/r/[email protected] open here

Signed-off-by H. Peter Anvin <[email protected]>

[bwh: Backported to 3.2: adjust context]

---
 arch/x86/kernel/cpu/mshyperv.c | 6 ++++++
 1 file changed, 6 insertions(+)

arch/x86/kernel/cpu/mshyperv.c +6 -0

@@ -18,6 +18,7 @@
 #include <asm/hypervisor.h>
 #include <asm/hyperv.h>
 #include <asm/mshyperv.h>
+#include <asm/timer.h>
 
 struct ms_hyperv_info ms_hyperv;
 EXPORT_SYMBOL_GPL(ms_hyperv);

@@ -70,6 +71,11 @@ static void __init ms_hyperv_init_platfo
 
 	if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE)
 		clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100);
+
+#ifdef CONFIG_X86_IO_APIC
+	no_timer_check = 1;
+#endif
+
 }
 
 const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {

Ben Hutchings

author

2014-04-28 01:11 UTC #61 lore raw

PATCH 61/94 nfsd4: buffer-length check for SUPPATTR_EXCLCREAT

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: "J. Bruce Fields" <[email protected]>

commit de3997a7eeb9ea286b15879fdf8a95aae065b4f7 upstream.

This was an omission from 8c18f2052e756e7d5dea712fc6e7ed70c00e8a39 "nfsd41: SUPPATTR_EXCLCREAT attribute".

Cc Benny Halevy <[email protected]>

---
 fs/nfsd/nfs4xdr.c | 2 ++
 1 file changed, 2 insertions(+)

fs/nfsd/nfs4xdr.c +2 -0

@@ -2413,6 +2413,8 @@ out_acl:
 		WRITE64(stat.ino);
 	}
 	if (bmval2 & FATTR4_WORD2_SUPPATTR_EXCLCREAT) {
+		if ((buflen -= 16) < 0)
+			goto out_resource;
 		WRITE32(3);
 		WRITE32(NFSD_SUPPATTR_EXCLCREAT_WORD0);
 		WRITE32(NFSD_SUPPATTR_EXCLCREAT_WORD1);

Ben Hutchings

author

2014-04-28 01:11 UTC #62 lore raw

PATCH 62/94 nfsd4: session needs room for following op to error out

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: "J. Bruce Fields" <[email protected]>

commit 4c69d5855a16f7378648c5733632628fa10431db upstream.

---
 fs/nfsd/nfs4proc.c | 6 ++++++
 1 file changed, 6 insertions(+)

fs/nfsd/nfs4proc.c +6 -0

@@ -1224,6 +1224,12 @@ nfsd4_proc_compound(struct svc_rqst *rqs
 		/* If op is non-idempotent */
 		if (opdesc->op_flags & OP_MODIFIES_SOMETHING) {
 			plen = opdesc->op_rsize_bop(rqstp, op);
+			/*
+			 * If there's still another operation, make sure
+			 * we'll have space to at least encode an error:
+			 */
+			if (resp->opcnt < args->opcnt)
+				plen += COMPOUND_ERR_SLACK_SPACE;
 			op->status = nfsd4_check_resp_size(resp, plen);
 		}

Ben Hutchings

author

2014-04-28 01:11 UTC #63 lore raw

PATCH 63/94 nfsd: Add fh_{want,drop}_write()

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Ben Hutchings <[email protected]>

Part of commit bad0dcffc21d17a07dbb83a2bf764f35a57feba5 ('new helpers: fh_{want,drop}_write()') upstream.

---

fs/nfsd/vfs.h +10 -0

@@ -108,4 +108,14 @@ struct posix_acl *nfsd_get_posix_acl(str
 int nfsd_set_posix_acl(struct svc_fh *, int, struct posix_acl *);
 #endif
 
+static inline int fh_want_write(struct svc_fh *fh)
+{
+	return mnt_want_write(fh->fh_export->ex_path.mnt);
+}
+
+static inline void fh_drop_write(struct svc_fh *fh)
+{
+	mnt_drop_write(fh->fh_export->ex_path.mnt);
+}
+
 #endif /* LINUX_NFSD_VFS_H */

Ben Hutchings

author

2014-04-28 01:11 UTC #64 lore raw

PATCH 64/94 nfsd: notify_change needs elevated write count

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: "J. Bruce Fields" <[email protected]>

commit 9f67f189939eccaa54f3d2c9cf10788abaf2d584 upstream.

Looks like this bug has been here since these write counts were introduced, not sure why it was just noticed now.

Thanks also to Jan Kara for pointing out the problem.

Reported-by Matthew Rahtz <[email protected]>

---
 fs/nfsd/vfs.c | 9 +++++++++
 1 file changed, 9 insertions(+)

fs/nfsd/vfs.c +9 -0

@@ -406,6 +406,7 @@ nfsd_setattr(struct svc_rqst *rqstp, str
 	int		ftype = 0;
 	__be32		err;
 	int		host_err;
+	bool		get_write_count;
 	int		size_change = 0;
 
 	if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE))

@@ -413,10 +414,18 @@ nfsd_setattr(struct svc_rqst *rqstp, str
 	if (iap->ia_valid & ATTR_SIZE)
 		ftype = S_IFREG;
 
+	/* Callers that do fh_verify should do the fh_want_write: */
+	get_write_count = !fhp->fh_dentry;
+
 	/* Get inode */
 	err = fh_verify(rqstp, fhp, ftype, accmode);
 	if (err)
 		goto out;
+	if (get_write_count) {
+		host_err = fh_want_write(fhp);
+		if (host_err)
+			return nfserrno(host_err);
+	}
 
 	dentry = fhp->fh_dentry;
 	inode = dentry->d_inode;

Ben Hutchings

author

2014-04-28 01:11 UTC #65 lore raw

PATCH 65/94 drm/i915/tv: fix gen4 composite s-video tv-out

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Jani Nikula <[email protected]>

commit e1f23f3dd817f53f622e486913ac662add46eeed upstream.

This is *not* bisected, but the likely regression is

commit c35614380d5c956bfda20eab2755b2f5a7d6f1e7

Author: Zhao Yakui <[email protected]>
Date:   Tue Nov 24 09:48:48 2009 +0800

drm/i915: Don't set up the TV port if it isn't in the BIOS table.

The commit does not check for all TV device types that might be present in the VBT, disabling TV out for the missing ones. Add composite S-video.

Reported-and-tested-by Matthew Khouzam <[email protected]>

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=73362

Signed-off-by Jani Nikula <[email protected]>

Signed-off-by Daniel Vetter <[email protected]>

[bwh: Backported to 3.2: s/old\.device_type/device_type/]

---
 drivers/gpu/drm/i915/intel_tv.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

drivers/gpu/drm/i915/intel_tv.c +7 -2

@@ -1599,9 +1599,14 @@ static int tv_is_present_in_vbt(struct d
 		/*
 		 * If the device type is not TV, continue.
 		 */
-		if (p_child->device_type != DEVICE_TYPE_INT_TV &&
-			p_child->device_type != DEVICE_TYPE_TV)
+		switch (p_child->device_type) {
+		case DEVICE_TYPE_INT_TV:
+		case DEVICE_TYPE_TV:
+		case DEVICE_TYPE_TV_SVIDEO_COMPOSITE:
+			break;
+		default:
 			continue;
+		}
 		/* Only when the addin_offset is non-zero, it is regarded
 		 * as present.
 		 */

Ben Hutchings

author

2014-04-28 01:11 UTC #66 lore raw

PATCH 66/94 dm thin: fix dangling bio in process_deferred_bios error path

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Mike Snitzer <[email protected]>

commit fe76cd88e654124d1431bb662a0fc6e99ca811a5 upstream.

If unable to ensure_next_mapping() we must add the current bio, which was removed from the @bios list via bio_list_pop, back to the deferred_bios list before all the remaining @bios.

Signed-off-by Mike Snitzer <[email protected]>

Acked-by Joe Thornber <[email protected]>

---
 drivers/md/dm-thin.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

drivers/md/dm-thin.c +1 -1

@@ -1298,9 +1298,9 @@ static void process_deferred_bios(struct
 		 */
 		if (ensure_next_mapping(pool)) {
 			spin_lock_irqsave(&pool->lock, flags);
+			bio_list_add(&pool->deferred_bios, bio);
 			bio_list_merge(&pool->deferred_bios, &bios);
 			spin_unlock_irqrestore(&pool->lock, flags);
-
 			break;
 		}
 		process_bio(tc, bio);

Ben Hutchings

author

2014-04-28 01:11 UTC #67 lore raw

PATCH 67/94 nfsd4: fix setclientid encode size

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: "J. Bruce Fields" <[email protected]>

commit 480efaee085235bb848f1063f959bf144103c342 upstream.

---
 fs/nfsd/nfs4proc.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

fs/nfsd/nfs4proc.c +2 -1

@@ -1387,7 +1387,8 @@ static inline u32 nfsd4_setattr_rsize(st
 
 static inline u32 nfsd4_setclientid_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
 {
-	return (op_encode_hdr_size + 2 + 1024) * sizeof(__be32);
+	return (op_encode_hdr_size + 2 + XDR_QUADLEN(NFS4_VERIFIER_SIZE)) *
+								sizeof(__be32);
 }
 
 static inline u32 nfsd4_write_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)

Ben Hutchings

author

2014-04-28 01:11 UTC #68 lore raw

PATCH 68/94 MIPS: Hibernate: Flush TLB entries in swsusp_arch_resume()

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Huacai Chen <[email protected]>

commit c14af233fbe279d0e561ecf84f1208b1bae087ef upstream.

The original MIPS hibernate code flushes cache and TLB entries in swsusp_arch_resume(). But they are removed in Commit 44eeab67416711 (MIPS: Hibernation: Remove SMP TLB and cacheflushing code.). A cross- CPU flush is surely unnecessary because all but the local CPU have already been disabled. But a local flush (at least the TLB flush) is needed. When we do hibernation on Loongson-3 with an E1000E NIC, it is very easy to produce a kernel panic (kernel page fault, or unaligned access). The root cause is E1000E driver use vzalloc_node() to allocate pages, the stale TLB entries of the booting kernel will be misused by the resumed target kernel.

Signed-off-by Huacai Chen <[email protected]>

Cc John Crispin <[email protected]>

Cc Steven J. Hill <[email protected]>

Cc Aurelien Jarno <[email protected]>

Cc [email protected]

Cc Fuxin Zhang <[email protected]>

Cc Zhangjin Wu <[email protected]>

Patchwork: https://patchwork.linux-mips.org/patch/6643/

Signed-off-by Ralf Baechle <[email protected]>

---
 arch/mips/power/hibernate.S | 1 +
 1 file changed, 1 insertion(+)

arch/mips/power/hibernate.S +1 -0

@@ -44,6 +44,7 @@ LEAF(swsusp_arch_resume)
 	bne t1, t3, 1b
 	PTR_L t0, PBE_NEXT(t0)
 	bnez t0, 0b
+	jal local_flush_tlb_all /* Avoid TLB mismatch after kernel resume */
 	PTR_LA t0, saved_regs
 	PTR_L ra, PT_R31(t0)
 	PTR_L sp, PT_R29(t0)

Ben Hutchings

author

2014-04-28 01:11 UTC #69 lore raw

PATCH 69/94 ALSA: hda - Enable beep for ASUS 1015E

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: "W. Trevor King" <[email protected]>

commit a4b7f21d7b42b33609df3f86992a8deff80abfaf upstream.

The lspci -nnvv output contains (wrapped for line length):

00:1b.0 Audio device [0403]:
Intel Corporation 7 Series/C210 Series Chipset Family High Definition Audio Controller [8086:1e20] (rev 04)
Subsystem: ASUSTeK Computer Inc. Device [1043:115d]

Signed-off-by W. Trevor King <[email protected]>

Signed-off-by Takashi Iwai <[email protected]>

---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

sound/pci/hda/patch_realtek.c +1 -0

@@ -3855,6 +3855,7 @@ static void alc_auto_init_std(struct hda
 
 static const struct snd_pci_quirk beep_white_list[] = {
 	SND_PCI_QUIRK(0x1043, 0x103c, "ASUS", 1),
+	SND_PCI_QUIRK(0x1043, 0x115d, "ASUS", 1),
 	SND_PCI_QUIRK(0x1043, 0x829f, "ASUS", 1),
 	SND_PCI_QUIRK(0x1043, 0x83ce, "EeePC", 1),
 	SND_PCI_QUIRK(0x1043, 0x831a, "EeePC", 1),

Ben Hutchings

author

2014-04-28 01:11 UTC #70 lore raw

PATCH 70/94 IB/mthca: Return an error on ib_copy_to_udata() failure

Link https://www.gitorious.org/opteya/coccib/source/75ebf2c1033c64c1d81df13e4ae44ee99c989eba:ib_copy_udata.cocci

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Yann Droneaud <[email protected]>

commit 08e74c4b00c30c232d535ff368554959403d0432 upstream.

In case of error when writing to userspace, the function mthca_create_cq() does not set an error code before following its error path.

This patch sets the error code to -EFAULT when ib_copy_to_udata() fails.

This was caught when using spatch (aka. coccinelle) to rewrite call to ib_copy_{from,to}_udata().

Link http://marc.info/[email protected]

Signed-off-by Yann Droneaud <[email protected]>

---
 drivers/infiniband/hw/mthca/mthca_provider.c | 1 +
 1 file changed, 1 insertion(+)

drivers/infiniband/hw/mthca/mthca_provider.c +1 -0

@@ -695,6 +695,7 @@ static struct ib_cq *mthca_create_cq(str
 
 	if (context && ib_copy_to_udata(udata, &cq->cqn, sizeof (__u32))) {
 		mthca_free_cq(to_mdev(ibdev), cq);
+		err = -EFAULT;
 		goto err_free;
 	}

Ben Hutchings

author

2014-04-28 01:11 UTC #71 lore raw

PATCH 71/94 IB/ehca: Returns an error on ib_copy_to_udata() failure

Link https://www.gitorious.org/opteya/coccib/source/75ebf2c1033c64c1d81df13e4ae44ee99c989eba:ib_copy_udata.cocci

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Yann Droneaud <[email protected]>

commit 5bdb0f02add5994b0bc17494f4726925ca5d6ba1 upstream.

In case of error when writing to userspace, function ehca_create_cq() does not set an error code before following its error path.

This patch sets the error code to -EFAULT when ib_copy_to_udata() fails.

This was caught when using spatch (aka. coccinelle) to rewrite call to ib_copy_{from,to}_udata().

Link http://marc.info/[email protected]

Signed-off-by Yann Droneaud <[email protected]>

---
 drivers/infiniband/hw/ehca/ehca_cq.c | 1 +
 1 file changed, 1 insertion(+)

drivers/infiniband/hw/ehca/ehca_cq.c +1 -0

@@ -296,6 +296,7 @@ struct ib_cq *ehca_create_cq(struct ib_d
 			(my_cq->galpas.user.fw_handle & (PAGE_SIZE - 1));
 		if (ib_copy_to_udata(udata, &resp, sizeof(resp))) {
 			ehca_err(device, "Copy to udata failed.");
+			cq = ERR_PTR(-EFAULT);
 			goto create_cq_exit4;
 		}
 	}

Ben Hutchings

author

2014-04-28 01:11 UTC #72 lore raw

PATCH 72/94 reiserfs: fix race in readdir

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Jeff Mahoney <[email protected]>

commit 01d8885785a60ae8f4c37b0ed75bdc96d0fc6a44 upstream.

jdm-20004 reiserfs_delete_xattrs: Couldn't delete all xattrs (-2)

The -ENOENT is due to readdir calling dir_emit on the same entry twice.

If the dir_emit callback sleeps and the tree is changed underneath us, we won't be able to trust deh_offset(deh) anymore. We need to save next_pos before we might sleep so we can find the next entry.

Signed-off-by Jeff Mahoney <[email protected]>

Signed-off-by Jan Kara <[email protected]>

---
 fs/reiserfs/dir.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

fs/reiserfs/dir.c +4 -2

@@ -128,6 +128,7 @@ int reiserfs_readdir_dentry(struct dentr
 				char *d_name;
 				off_t d_off;
 				ino_t d_ino;
+				loff_t cur_pos = deh_offset(deh);
 
 				if (!de_visible(deh))
 					/* it is hidden entry */

@@ -200,8 +201,9 @@ int reiserfs_readdir_dentry(struct dentr
 				if (local_buf != small_buf) {
 					kfree(local_buf);
 				}
-				// next entry should be looked for with such offset
-				next_pos = deh_offset(deh) + 1;
+
+				/* deh_offset(deh) may be invalid now. */
+				next_pos = cur_pos + 1;
 
 				if (item_moved(&tmp_ih, &path_to_entry)) {
 					goto research;

Ben Hutchings

author

2014-04-28 01:11 UTC #73 lore raw

PATCH 73/94 drm/vmwgfx: correct fb_fix_screeninfo.line_length

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Christopher Friedt <[email protected]>

commit aa6de142c901cd2d90ef08db30ae87da214bedcc upstream.

Previously, the vmwgfx_fb driver would allow users to call FBIOSET_VINFO, but it would not adjust the FINFO properly, resulting in distorted screen rendering. The patch corrects that behaviour.

See https://bugs.gentoo.org/show_bug.cgi?id=494794 for examples.

Signed-off-by Christopher Friedt <[email protected]>

Reviewed-by Thomas Hellstrom <[email protected]>

---
 drivers/gpu/drm/vmwgfx/vmwgfx_fb.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

drivers/gpu/drm/vmwgfx/vmwgfx_fb.c +4 -1

@@ -147,7 +147,7 @@ static int vmw_fb_check_var(struct fb_va
 	}
 
 	if (!vmw_kms_validate_mode_vram(vmw_priv,
-					info->fix.line_length,
+					var->xres * var->bits_per_pixel/8,
 					var->yoffset + var->yres)) {
 		DRM_ERROR("Requested geom can not fit in framebuffer\n");
 		return -EINVAL;

@@ -162,6 +162,8 @@ static int vmw_fb_set_par(struct fb_info
 	struct vmw_private *vmw_priv = par->vmw_priv;
 	int ret;
 
+	info->fix.line_length = info->var.xres * info->var.bits_per_pixel/8;
+
 	ret = vmw_kms_write_svga(vmw_priv, info->var.xres, info->var.yres,
 				 info->fix.line_length,
 				 par->bpp, par->depth);

@@ -177,6 +179,7 @@ static int vmw_fb_set_par(struct fb_info
 		vmw_write(vmw_priv, SVGA_REG_DISPLAY_POSITION_Y, info->var.yoffset);
 		vmw_write(vmw_priv, SVGA_REG_DISPLAY_WIDTH, info->var.xres);
 		vmw_write(vmw_priv, SVGA_REG_DISPLAY_HEIGHT, info->var.yres);
+		vmw_write(vmw_priv, SVGA_REG_BYTES_PER_LINE, info->fix.line_length);
 		vmw_write(vmw_priv, SVGA_REG_DISPLAY_ID, SVGA_ID_INVALID);
 	}

Ben Hutchings

author

2014-04-28 01:11 UTC #74 lore raw

PATCH 74/94 drm/radeon: call drm_edid_to_eld when we update the edid

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Alex Deucher <[email protected]>

commit 16086279353cbfecbb3ead474072dced17b97ddc upstream.

This needs to be done to update some of the fields in the connector structure used by the audio code.

Noticed by several users on irc.

Signed-off-by Alex Deucher <[email protected]>

Signed-off-by Christian König <[email protected]>

---
 drivers/gpu/drm/radeon/radeon_display.c | 1 +
 1 file changed, 1 insertion(+)

drivers/gpu/drm/radeon/radeon_display.c +1 -0

@@ -738,6 +738,7 @@ int radeon_ddc_get_modes(struct radeon_c
 	if (radeon_connector->edid) {
 		drm_mode_connector_update_edid_property(&radeon_connector->base, radeon_connector->edid);
 		ret = drm_add_edid_modes(&radeon_connector->base, radeon_connector->edid);
+		drm_edid_to_eld(&radeon_connector->base, radeon_connector->edid);
 		return ret;
 	}
 	drm_mode_connector_update_edid_property(&radeon_connector->base, NULL);

Ben Hutchings

author

2014-04-28 01:11 UTC #75 lore raw

PATCH 75/94 sh: fix format string bug in stack tracer

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Matt Fleming <[email protected]>

commit a0c32761e73c9999cbf592b702f284221fea8040 upstream.

Kees reported the following error:

arch/sh/kernel/dumpstack.c: In function 'print_trace_address':
arch/sh/kernel/dumpstack.c:118:2: error: format not a string literal and no format arguments [-Werror=format-security]

Use the "%s" format so that it's impossible to interpret 'data' as a format string.

Signed-off-by Matt Fleming <[email protected]>

Reported-by Kees Cook <[email protected]>

Acked-by Kees Cook <[email protected]>

Cc Paul Mundt <[email protected]>

---
 arch/sh/kernel/dumpstack.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

arch/sh/kernel/dumpstack.c +1 -1

@@ -80,7 +80,7 @@ static int print_trace_stack(void *data,
  */
 static void print_trace_address(void *data, unsigned long addr, int reliable)
 {
-	printk(data);
+	printk("%s", (char *)data);
 	printk_address(addr, reliable);
 }

Ben Hutchings

author

2014-04-28 01:11 UTC #76 lore raw

PATCH 76/94 ocfs2: dlm: fix lock migration crash

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Junxiao Bi <[email protected]>

commit 34aa8dac482f1358d59110d5e3a12f4351f6acaa upstream.

This issue was introduced by commit 800deef3f6f8 ("ocfs2: use list_for_each_entry where benefical") in 2007 where it replaced list_for_each with list_for_each_entry. The variable "lock" will point to invalid data if "tmpq" list is empty and a panic will be triggered due to this. Sunil advised reverting it back, but the old version was also not right. At the end of the outer for loop, that list_for_each_entry will also set "lock" to an invalid data, then in the next loop, if the "tmpq" list is empty, "lock" will be an stale invalid data and cause the panic. So reverting the list_for_each back and reset "lock" to NULL to fix this issue.

Another concern is that this seemes can not happen because the "tmpq" list should not be empty. Let me describe how.

old lock resource owner(node 1): migratation target(node 2):
image there's lockres with a EX lock from node 2 in granted list, a NR lock from node x with convert_type EX in converting list.
dlm_empty_lockres() {
dlm_pick_migration_target() {
pick node 2 as target as its lock is the first one in granted list.
}
dlm_migrate_lockres() {

   dlm_mark_lockres_migrating() {
     res->state |= DLM_LOCK_RES_BLOCK_DIRTY;
     wait_event(dlm->ast_wq, !dlm_lockres_is_dirty(dlm, res));
	 //after the above code, we can not dirty lockres any more,
     // so dlm_thread shuffle list will not run
                                                                   downconvert lock from EX to NR
                                                                   upconvert lock from NR to EX

<<< migration may schedule out here, then
<<< node 2 send down convert request to convert type from EX to <<< NR, then send up convert request to convert type from NR to <<< EX, at this time, lockres granted list is empty, and two locks <<< in the converting list, node x up convert lock followed by <<< node 2 up convert lock.

	 // will set lockres RES_MIGRATING flag, the following
	 // lock/unlock can not run
     dlm_lockres_release_ast(dlm, res);

}

dlm_send_one_lockres()

                                                                 dlm_process_recovery_data()
                                                                   for (i=0; i<mres->num_locks; i++)
                                                                     if (ml->node == dlm->node_num)
                                                                       for (j = DLM_GRANTED_LIST; j <= DLM_BLOCKED_LIST; j++) {
                                                                        list_for_each_entry(lock, tmpq, list)
                                                                        if (lock) break; <<< lock is invalid as grant list is empty.
                                                                       }
                                                                       if (lock->ml.node != ml->node)
                                                                         BUG() >>> crash here

}

I see the above locks status from a vmcore of our internal bug.

Signed-off-by Junxiao Bi <[email protected]>

Reviewed-by Wengang Wang <[email protected]>

Cc Sunil Mushran <[email protected]>

Reviewed-by Srinivas Eeda <[email protected]>

Cc Joel Becker <[email protected]>

Cc Mark Fasheh <[email protected]>

---
 fs/ocfs2/dlm/dlmrecovery.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

fs/ocfs2/dlm/dlmrecovery.c +8 -6

@@ -1752,13 +1752,13 @@ static int dlm_process_recovery_data(str
 				     struct dlm_migratable_lockres *mres)
 {
 	struct dlm_migratable_lock *ml;
-	struct list_head *queue;
+	struct list_head *queue, *iter;
 	struct list_head *tmpq = NULL;
 	struct dlm_lock *newlock = NULL;
 	struct dlm_lockstatus *lksb = NULL;
 	int ret = 0;
 	int i, j, bad;
-	struct dlm_lock *lock = NULL;
+	struct dlm_lock *lock;
 	u8 from = O2NM_MAX_NODES;
 	unsigned int added = 0;
 	__be64 c;

@@ -1793,14 +1793,16 @@ static int dlm_process_recovery_data(str
 			/* MIGRATION ONLY! */
 			BUG_ON(!(mres->flags & DLM_MRES_MIGRATION));
 
+			lock = NULL;
 			spin_lock(&res->spinlock);
 			for (j = DLM_GRANTED_LIST; j <= DLM_BLOCKED_LIST; j++) {
 				tmpq = dlm_list_idx_to_ptr(res, j);
-				list_for_each_entry(lock, tmpq, list) {
-					if (lock->ml.cookie != ml->cookie)
-						lock = NULL;
-					else
+				list_for_each(iter, tmpq) {
+					lock = list_entry(iter,
+						  struct dlm_lock, list);
+					if (lock->ml.cookie == ml->cookie)
 						break;
+					lock = NULL;
 				}
 				if (lock)
 					break;

Ben Hutchings

author

2014-04-28 01:11 UTC #77 lore raw

PATCH 77/94 ocfs2: dlm: fix recovery hung

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Junxiao Bi <[email protected]>

commit ded2cf71419b9353060e633b59e446c42a6a2a09 upstream.

There is a race window in dlm_do_recovery() between dlm_remaster_locks() and dlm_reset_recovery() when the recovery master nearly finish the recovery process for a dead node. After the master sends FINALIZE_RECO message in dlm_remaster_locks(), another node may become the recovery master for another dead node, and then send the BEGIN_RECO message to all the nodes included the old master, in the handler of this message dlm_begin_reco_handler() of old master, dlm->reco.dead_node and dlm->reco.new_master will be set to the second dead node and the new master, then in dlm_reset_recovery(), these two variables will be reset to default value. This will cause new recovery master can not finish the recovery process and hung, at last the whole cluster will hung for recovery.

old recovery master: new recovery master:
dlm_remaster_locks()
become recovery master for another dead node. dlm_send_begin_reco_message()
dlm_begin_reco_handler()
{
if (dlm->reco.state & DLM_RECO_STATE_FINALIZE) {
return -EAGAIN;
}
dlm_set_reco_master(dlm, br->node_idx);
dlm_set_reco_dead_node(dlm, br->dead_node);
}
dlm_reset_recovery()
{
dlm_set_reco_dead_node(dlm, O2NM_INVALID_NODE_NUM); dlm_set_reco_master(dlm, O2NM_INVALID_NODE_NUM);
}
will hang in dlm_remaster_locks() for request dlm locks info

Before send FINALIZE_RECO message, recovery master should set DLM_RECO_STATE_FINALIZE for itself and clear it after the recovery done, this can break the race windows as the BEGIN_RECO messages will not be handled before DLM_RECO_STATE_FINALIZE flag is cleared.

A similar race may happen between new recovery master and normal node which is in dlm_finalize_reco_handler(), also fix it.

Signed-off-by Junxiao Bi <[email protected]>

Reviewed-by Srinivas Eeda <[email protected]>

Reviewed-by Wengang Wang <[email protected]>

Cc Joel Becker <[email protected]>

Cc Mark Fasheh <[email protected]>

---
 fs/ocfs2/dlm/dlmrecovery.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

fs/ocfs2/dlm/dlmrecovery.c +13 -2

@@ -540,7 +540,10 @@ master_here:
 		/* success!  see if any other nodes need recovery */
 		mlog(0, "DONE mastering recovery of %s:%u here(this=%u)!\n",
 		     dlm->name, dlm->reco.dead_node, dlm->node_num);
-		dlm_reset_recovery(dlm);
+		spin_lock(&dlm->spinlock);
+		__dlm_reset_recovery(dlm);
+		dlm->reco.state &= ~DLM_RECO_STATE_FINALIZE;
+		spin_unlock(&dlm->spinlock);
 	}
 	dlm_end_recovery(dlm);

@@ -698,6 +701,14 @@ static int dlm_remaster_locks(struct dlm
 		if (all_nodes_done) {
 			int ret;
 
+			/* Set this flag on recovery master to avoid
+			 * a new recovery for another dead node start
+			 * before the recovery is not done. That may
+			 * cause recovery hung.*/
+			spin_lock(&dlm->spinlock);
+			dlm->reco.state |= DLM_RECO_STATE_FINALIZE;
+			spin_unlock(&dlm->spinlock);
+
 			/* all nodes are now in DLM_RECO_NODE_DATA_DONE state
 	 		 * just send a finalize message to everyone and
 	 		 * clean up */

@@ -2872,8 +2883,8 @@ int dlm_finalize_reco_handler(struct o2n
 				BUG();
 			}
 			dlm->reco.state &= ~DLM_RECO_STATE_FINALIZE;
+			__dlm_reset_recovery(dlm);
 			spin_unlock(&dlm->spinlock);
-			dlm_reset_recovery(dlm);
 			dlm_kick_recovery_thread(dlm);
 			break;
 		default:

Ben Hutchings

author

2014-04-28 01:11 UTC #78 lore raw

PATCH 78/94 ocfs2: do not put bh when buffer_uptodate failed

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: alex chen <[email protected]>

commit f7cf4f5bfe073ad792ab49c04f247626b3e38db6 upstream.

Do not put bh when buffer_uptodate failed in ocfs2_write_block and ocfs2_write_super_or_backup, because it will put bh in b_end_io. Otherwise it will hit a warning "VFS: brelse: Trying to free free buffer".

Signed-off-by Alex Chen <[email protected]>

Reviewed-by Joseph Qi <[email protected]>

Reviewed-by Srinivas Eeda <[email protected]>

Cc Mark Fasheh <[email protected]>

Acked-by Joel Becker <[email protected]>

---
 fs/ocfs2/buffer_head_io.c | 2 --
 1 file changed, 2 deletions(-)

fs/ocfs2/buffer_head_io.c +0 -2

@@ -90,7 +90,6 @@ int ocfs2_write_block(struct ocfs2_super
 		 * information for this bh as it's not marked locally
 		 * uptodate. */
 		ret = -EIO;
-		put_bh(bh);
 		mlog_errno(ret);
 	}

@@ -420,7 +419,6 @@ int ocfs2_write_super_or_backup(struct o
 
 	if (!buffer_uptodate(bh)) {
 		ret = -EIO;
-		put_bh(bh);
 		mlog_errno(ret);
 	}

Ben Hutchings

author

2014-04-28 01:11 UTC #79 lore raw

PATCH 79/94 iscsi-target: Fix ERL=2 ASYNC_EVENT connection pointer bug

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Nicholas Bellinger <[email protected]>

commit d444edc679e7713412f243b792b1f964e5cff1e1 upstream.

This patch fixes a long-standing bug in iscsit_build_conn_drop_async_message() where during ERL=2 connection recovery, a bogus conn_p pointer could end up being used to send the ISCSI_OP_ASYNC_EVENT + DROPPING_CONNECTION notifying the initiator that cmd->logout_cid has failed.

The bug was manifesting itself as an OOPs in iscsit_allocate_cmd() with a bogus conn_p pointer in iscsit_build_conn_drop_async_message().

Reported-by Arshad Hussain <[email protected]>

Reported-by santosh kulkarni <[email protected]>

Signed-off-by Nicholas Bellinger <[email protected]>

---
 drivers/target/iscsi/iscsi_target.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

drivers/target/iscsi/iscsi_target.c +3 -1

@@ -2358,6 +2358,7 @@ static void iscsit_build_conn_drop_async
 {
 	struct iscsi_cmd *cmd;
 	struct iscsi_conn *conn_p;
+	bool found = false;
 
 	/*
 	 * Only send a Asynchronous Message on connections whos network

@@ -2366,11 +2367,12 @@ static void iscsit_build_conn_drop_async
 	list_for_each_entry(conn_p, &conn->sess->sess_conn_list, conn_list) {
 		if (conn_p->conn_state == TARG_CONN_STATE_LOGGED_IN) {
 			iscsit_inc_conn_usage_count(conn_p);
+			found = true;
 			break;
 		}
 	}
 
-	if (!conn_p)
+	if (!found)
 		return;
 
 	cmd = iscsit_allocate_cmd(conn_p, GFP_ATOMIC);

Ben Hutchings

author

2014-04-28 01:11 UTC #80 lore raw

PATCH 80/94 mm: try_to_unmap_cluster() should lock_page() before mlocking

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Vlastimil Babka <[email protected]>

commit 57e68e9cd65b4b8eb4045a1e0d0746458502554c upstream.

A BUG_ON(!PageLocked) was triggered in mlock_vma_page() by Sasha Levin fuzzing with trinity. The call site try_to_unmap_cluster() does not lock the pages other than its check_page parameter (which is already locked).

The BUG_ON in mlock_vma_page() is not documented and its purpose is somewhat unclear, but apparently it serializes against page migration, which could otherwise fail to transfer the PG_mlocked flag. This would not be fatal, as the page would be eventually encountered again, but NR_MLOCK accounting would become distorted nevertheless. This patch adds a comment to the BUG_ON in mlock_vma_page() and munlock_vma_page() to that effect.

The call site try_to_unmap_cluster() is fixed so that for page != check_page, trylock_page() is attempted (to avoid possible deadlocks as we already have check_page locked) and mlock_vma_page() is performed only upon success. If the page lock cannot be obtained, the page is left without PG_mlocked, which is again not a problem in the whole unevictable memory design.

Signed-off-by Vlastimil Babka <[email protected]>

Signed-off-by Bob Liu <[email protected]>

Reported-by Sasha Levin <[email protected]>

Cc Wanpeng Li <[email protected]>

Cc Michel Lespinasse <[email protected]>

Cc KOSAKI Motohiro <[email protected]>

Acked-by Rik van Riel <[email protected]>

Cc David Rientjes <[email protected]>

Cc Mel Gorman <[email protected]>

Cc Hugh Dickins <[email protected]>

Cc Joonsoo Kim <[email protected]>

[bwh: Backported to 3.2: adjust context]

---
 mm/mlock.c |  2 ++
 mm/rmap.c  | 14 ++++++++++++--
 2 files changed, 14 insertions(+), 2 deletions(-)

mm/mlock.c +2 -0

@@ -78,6 +78,7 @@ void __clear_page_mlock(struct page *pag
  */
 void mlock_vma_page(struct page *page)
 {
+	/* Serialize with page migration */
 	BUG_ON(!PageLocked(page));
 
 	if (!TestSetPageMlocked(page)) {

@@ -105,6 +106,7 @@ void mlock_vma_page(struct page *page)
  */
 void munlock_vma_page(struct page *page)
 {
+	/* For try_to_munlock() and to serialize with page migration */
 	BUG_ON(!PageLocked(page));
 
 	if (TestClearPageMlocked(page)) {

mm/rmap.c +12 -2

@@ -1385,9 +1385,19 @@ static int try_to_unmap_cluster(unsigned
 		BUG_ON(!page || PageAnon(page));
 
 		if (locked_vma) {
-			mlock_vma_page(page);   /* no-op if already mlocked */
-			if (page == check_page)
+			if (page == check_page) {
+				/* we know we have check_page locked */
+				mlock_vma_page(page);
 				ret = SWAP_MLOCK;
+			} else if (trylock_page(page)) {
+				/*
+				 * If we can lock the page, perform mlock.
+				 * Otherwise leave the page alone, it will be
+				 * eventually encountered again later.
+				 */
+				mlock_vma_page(page);
+				unlock_page(page);
+			}
 			continue;	/* don't unmap */
 		}

Ben Hutchings

author

2014-04-28 01:11 UTC #81 lore raw

PATCH 81/94 mm: hugetlb: fix softlockup when a large number of hugepages are freed.

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: "Mizuma, Masayoshi" <[email protected]>

commit 55f67141a8927b2be3e51840da37b8a2320143ed upstream.

When I decrease the value of nr_hugepage in procfs a lot, softlockup happens. It is because there is no chance of context switch during this process.

On the other hand, when I allocate a large number of hugepages, there is some chance of context switch. Hence softlockup doesn't happen during this process. So it's necessary to add the context switch in the freeing process as same as allocating process to avoid softlockup.

When I freed 12 TB hugapages with kernel-2.6.32-358.el6, the freeing process occupied a CPU over 150 seconds and following softlockup message appeared twice or more.

$ echo 6000000 > /proc/sys/vm/nr_hugepages
$ cat /proc/sys/vm/nr_hugepages
6000000
$ grep ^Huge /proc/meminfo
HugePages_Total:   6000000
HugePages_Free:    6000000
HugePages_Rsvd:        0
HugePages_Surp:        0
Hugepagesize:       2048 kB
$ echo 0 > /proc/sys/vm/nr_hugepages

BUG: soft lockup - CPU#16 stuck for 67s! [sh:12883] ...
Pid: 12883, comm: sh Not tainted 2.6.32-358.el6.x86_64 #1
Call Trace:
  free_pool_huge_page+0xb8/0xd0
  set_max_huge_pages+0x128/0x190
  hugetlb_sysctl_handler_common+0x113/0x140
  hugetlb_sysctl_handler+0x1e/0x20
  proc_sys_call_handler+0x97/0xd0
  proc_sys_write+0x14/0x20
  vfs_write+0xb8/0x1a0
  sys_write+0x51/0x90
  __audit_syscall_exit+0x265/0x290
  system_call_fastpath+0x16/0x1b

I have not confirmed this problem with upstream kernels because I am not able to prepare the machine equipped with 12TB memory now. However I confirmed that the amount of decreasing hugepages was directly proportional to the amount of required time.

I measured required times on a smaller machine. It showed 130-145 hugepages decreased in a millisecond.

Amount of decreasing Required time Decreasing rate
hugepages (msec) (pages/msec)
------------------------------------------------------------
10,000 pages == 20GB 70 - 74 135-142
30,000 pages == 60GB 208 - 229 131-144

It means decrement of 6TB hugepages will trigger softlockup with the default threshold 20sec, in this decreasing rate.

Signed-off-by Masayoshi Mizuma <[email protected]>

Cc Joonsoo Kim <[email protected]>

Cc Michal Hocko <[email protected]>

Cc Wanpeng Li <[email protected]>

Cc Aneesh Kumar <[email protected]>

Cc KOSAKI Motohiro <[email protected]>

Cc Naoya Horiguchi <[email protected]>

---
 mm/hugetlb.c | 1 +
 1 file changed, 1 insertion(+)

mm/hugetlb.c +1 -0

@@ -1447,6 +1447,7 @@ static unsigned long set_max_huge_pages(
 	while (min_count < persistent_huge_pages(h)) {
 		if (!free_pool_huge_page(h, nodes_allowed, 0))
 			break;
+		cond_resched_lock(&hugetlb_lock);
 	}
 	while (count < persistent_huge_pages(h)) {
 		if (!adjust_pool_surplus(h, nodes_allowed, 1))

Ben Hutchings

author

2014-04-28 01:11 UTC #82 lore raw

PATCH 82/94 wait: fix reparent_leader() vs EXIT_DEAD->EXIT_ZOMBIE race

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Oleg Nesterov <[email protected]>

commit dfccbb5e49a621c1b21a62527d61fc4305617aca upstream.

wait_task_zombie() first does EXIT_ZOMBIE->EXIT_DEAD transition and drops tasklist_lock. If this task is not the natural child and it is traced, we change its state back to EXIT_ZOMBIE for ->real_parent.

The last transition is racy, this is even documented in 50b8d257486a "ptrace: partially fix the do_wait(WEXITED) vs EXIT_DEAD->EXIT_ZOMBIE race". wait_consider_task() tries to detect this transition and clear ->notask_error but we can't rely on ptrace_reparented(), debugger can exit and do ptrace_unlink() before its sub-thread sets EXIT_ZOMBIE.

And there is another problem which were missed before: this transition can also race with reparent_leader() which doesn't reset >exit_signal if EXIT_DEAD, assuming that this task must be reaped by someone else. So the tracee can be re-parented with ->exit_signal != SIGCHLD, and if /sbin/init doesn't use __WALL it becomes unreapable.

Change reparent_leader() to update ->exit_signal even if EXIT_DEAD.
Note: this is the simple temporary hack for -stable, it doesn't try to solve all problems, it will be reverted by the next changes.

Signed-off-by Oleg Nesterov <[email protected]>

Reported-by Jan Kratochvil <[email protected]>

Reported-by Michal Schmidt <[email protected]>

Tested-by Michal Schmidt <[email protected]>

Cc Al Viro <[email protected]>

Cc Lennart Poettering <[email protected]>

Cc Roland McGrath <[email protected]>

Cc Tejun Heo <[email protected]>

---
 kernel/exit.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

kernel/exit.c +11 -4

@@ -734,9 +734,6 @@ static void reparent_leader(struct task_
 				struct list_head *dead)
 {
 	list_move_tail(&p->sibling, &p->real_parent->children);
-
-	if (p->exit_state == EXIT_DEAD)
-		return;
 	/*
 	 * If this is a threaded reparent there is no need to
 	 * notify anyone anything has happened.

@@ -744,9 +741,19 @@ static void reparent_leader(struct task_
 	if (same_thread_group(p->real_parent, father))
 		return;
 
-	/* We don't want people slaying init.  */
+	/*
+	 * We don't want people slaying init.
+	 *
+	 * Note: we do this even if it is EXIT_DEAD, wait_task_zombie()
+	 * can change ->exit_state to EXIT_ZOMBIE. If this is the final
+	 * state, do_notify_parent() was already called and ->exit_signal
+	 * doesn't matter.
+	 */
 	p->exit_signal = SIGCHLD;
 
+	if (p->exit_state == EXIT_DEAD)
+		return;
+
 	/* If it has exited notify the new parent about this child's death. */
 	if (!p->ptrace &&
 	    p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) {

Ben Hutchings

author

2014-04-28 01:11 UTC #83 lore raw

PATCH 83/94 ALSA: ice1712: Fix boundary checks in PCM pointer ops

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Takashi Iwai <[email protected]>

commit 4f8e940095536bc002a81666a4107a581c84e9b9 upstream.

PCM pointer callbacks in ice1712 driver check the buffer size boundary wrongly between bytes and frames. This leads to PCM core warnings
like:
snd_pcm_update_hw_ptr0: 105 callbacks suppressed
ALSA pcm_lib.c:352 BUG: pcmC3D0c:0, pos = 5461, buffer size = 5461, period size = 2730

This patch fixes these checks to be placed after the proper unit conversions.

Signed-off-by Takashi Iwai <[email protected]>

---
 sound/pci/ice1712/ice1712.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

sound/pci/ice1712/ice1712.c +10 -5

@@ -686,9 +686,10 @@ static snd_pcm_uframes_t snd_ice1712_pla
 	if (!(snd_ice1712_read(ice, ICE1712_IREG_PBK_CTRL) & 1))
 		return 0;
 	ptr = runtime->buffer_size - inw(ice->ddma_port + 4);
+	ptr = bytes_to_frames(substream->runtime, ptr);
 	if (ptr == runtime->buffer_size)
 		ptr = 0;
-	return bytes_to_frames(substream->runtime, ptr);
+	return ptr;
 }
 
 static snd_pcm_uframes_t snd_ice1712_playback_ds_pointer(struct snd_pcm_substream *substream)

@@ -705,9 +706,10 @@ static snd_pcm_uframes_t snd_ice1712_pla
 		addr = ICE1712_DSC_ADDR0;
 	ptr = snd_ice1712_ds_read(ice, substream->number * 2, addr) -
 		ice->playback_con_virt_addr[substream->number];
+	ptr = bytes_to_frames(substream->runtime, ptr);
 	if (ptr == substream->runtime->buffer_size)
 		ptr = 0;
-	return bytes_to_frames(substream->runtime, ptr);
+	return ptr;
 }
 
 static snd_pcm_uframes_t snd_ice1712_capture_pointer(struct snd_pcm_substream *substream)

@@ -718,9 +720,10 @@ static snd_pcm_uframes_t snd_ice1712_cap
 	if (!(snd_ice1712_read(ice, ICE1712_IREG_CAP_CTRL) & 1))
 		return 0;
 	ptr = inl(ICEREG(ice, CONCAP_ADDR)) - ice->capture_con_virt_addr;
+	ptr = bytes_to_frames(substream->runtime, ptr);
 	if (ptr == substream->runtime->buffer_size)
 		ptr = 0;
-	return bytes_to_frames(substream->runtime, ptr);
+	return ptr;
 }
 
 static const struct snd_pcm_hardware snd_ice1712_playback = {

@@ -1114,9 +1117,10 @@ static snd_pcm_uframes_t snd_ice1712_pla
 	if (!(inl(ICEMT(ice, PLAYBACK_CONTROL)) & ICE1712_PLAYBACK_START))
 		return 0;
 	ptr = ice->playback_pro_size - (inw(ICEMT(ice, PLAYBACK_SIZE)) << 2);
+	ptr = bytes_to_frames(substream->runtime, ptr);
 	if (ptr == substream->runtime->buffer_size)
 		ptr = 0;
-	return bytes_to_frames(substream->runtime, ptr);
+	return ptr;
 }
 
 static snd_pcm_uframes_t snd_ice1712_capture_pro_pointer(struct snd_pcm_substream *substream)

@@ -1127,9 +1131,10 @@ static snd_pcm_uframes_t snd_ice1712_cap
 	if (!(inl(ICEMT(ice, PLAYBACK_CONTROL)) & ICE1712_CAPTURE_START_SHADOW))
 		return 0;
 	ptr = ice->capture_pro_size - (inw(ICEMT(ice, CAPTURE_SIZE)) << 2);
+	ptr = bytes_to_frames(substream->runtime, ptr);
 	if (ptr == substream->runtime->buffer_size)
 		ptr = 0;
-	return bytes_to_frames(substream->runtime, ptr);
+	return ptr;
 }
 
 static const struct snd_pcm_hardware snd_ice1712_playback_pro = {

Ben Hutchings

author

2014-04-28 01:11 UTC #84 lore raw

PATCH 84/94 lib/percpu_counter.c: fix bad percpu counter state during suspend

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Jens Axboe <[email protected]>

commit e39435ce68bb4685288f78b1a7e24311f7ef939f upstream.

I got a bug report yesterday from Laszlo Ersek in which he states that his kvm instance fails to suspend. Laszlo bisected it down to this commit 1cf7e9c68fe8 ("virtio_blk: blk-mq support") where virtio-blk is converted to use the blk-mq infrastructure.

After digging a bit, it became clear that the issue was with the queue drain. blk-mq tracks queue usage in a percpu counter, which is incremented on request alloc and decremented when the request is freed. The initial hunt was for an inconsistency in blk-mq, but everything seemed fine. In fact, the counter only returned crazy values when suspend was in progress.

When a CPU is unplugged, the percpu counters merges that CPU state with the general state. blk-mq takes care to register a hotcpu notifier with the appropriate priority, so we know it runs after the percpu counter notifier. However, the percpu counter notifier only merges the state when the CPU is fully gone. This leaves a state transition where the CPU going away is no longer in the online mask, yet it still holds private values. This means that in this state, percpu_counter_sum() returns invalid results, and the suspend then hangs waiting for abs(dead-cpu-value) requests to complete which of course will never happen.

Fix this by clearing the state earlier, so we never have a case where the CPU isn't in online mask but still holds private state. This bug has been there since forever, I guess we don't have a lot of users where percpu counters needs to be reliable during the suspend cycle.

Signed-off-by Jens Axboe <[email protected]>

Reported-by Laszlo Ersek <[email protected]>

Tested-by Laszlo Ersek <[email protected]>

---
 lib/percpu_counter.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

lib/percpu_counter.c +1 -1

@@ -166,7 +166,7 @@ static int __cpuinit percpu_counter_hotc
 	struct percpu_counter *fbc;
 
 	compute_batch_value();
-	if (action != CPU_DEAD)
+	if (action != CPU_DEAD && action != CPU_DEAD_FROZEN)
 		return NOTIFY_OK;
 
 	cpu = (unsigned long)hcpu;

Ben Hutchings

author

2014-04-28 01:11 UTC #85 lore raw

PATCH 85/94 b43: Fix machine check error due to improper access of B43_MMIO_PSM_PHY_HDR

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Rafał Miłecki <[email protected]>

commit 12cd43c6ed6da7bf7c5afbd74da6959cda6d056b upstream.

Register B43_MMIO_PSM_PHY_HDR is 16 bit one, so accessing it with 32b functions isn't safe. On my machine it causes delayed (!) CPU exception:

Disabling lock debugging due to kernel taint
mce: [Hardware Error]: CPU 0: Machine Check Exception: 4 Bank 4: b200000000070f0f
mce: [Hardware Error]: TSC 164083803dc
mce: [Hardware Error]: PROCESSOR 2:20fc2 TIME 1396650505 SOCKET 0 APIC 0 microcode 0
mce: [Hardware Error]: Run the above through 'mcelog --ascii'
mce: [Hardware Error]: Machine check: Processor context corrupt

Kernel panic - not syncing: Fatal machine check on current CPU

Kernel Offset: 0x0 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffff9fffffff)

Signed-off-by Rafał Miłecki <[email protected]>

Acked-by Larry Finger <[email protected]>

Signed-off-by John W. Linville <[email protected]>

---
 drivers/net/wireless/b43/phy_n.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

drivers/net/wireless/b43/phy_n.c +7 -7

@@ -3937,22 +3937,22 @@ static void b43_nphy_channel_setup(struc
 	struct b43_phy_n *nphy = dev->phy.n;
 
 	u16 old_band_5ghz;
-	u32 tmp32;
+	u16 tmp16;
 
 	old_band_5ghz =
 		b43_phy_read(dev, B43_NPHY_BANDCTL) & B43_NPHY_BANDCTL_5GHZ;
 	if (new_channel->band == IEEE80211_BAND_5GHZ && !old_band_5ghz) {
-		tmp32 = b43_read32(dev, B43_MMIO_PSM_PHY_HDR);
-		b43_write32(dev, B43_MMIO_PSM_PHY_HDR, tmp32 | 4);
+		tmp16 = b43_read16(dev, B43_MMIO_PSM_PHY_HDR);
+		b43_write16(dev, B43_MMIO_PSM_PHY_HDR, tmp16 | 4);
 		b43_phy_set(dev, B43_PHY_B_BBCFG, 0xC000);
-		b43_write32(dev, B43_MMIO_PSM_PHY_HDR, tmp32);
+		b43_write16(dev, B43_MMIO_PSM_PHY_HDR, tmp16);
 		b43_phy_set(dev, B43_NPHY_BANDCTL, B43_NPHY_BANDCTL_5GHZ);
 	} else if (new_channel->band == IEEE80211_BAND_2GHZ && old_band_5ghz) {
 		b43_phy_mask(dev, B43_NPHY_BANDCTL, ~B43_NPHY_BANDCTL_5GHZ);
-		tmp32 = b43_read32(dev, B43_MMIO_PSM_PHY_HDR);
-		b43_write32(dev, B43_MMIO_PSM_PHY_HDR, tmp32 | 4);
+		tmp16 = b43_read16(dev, B43_MMIO_PSM_PHY_HDR);
+		b43_write16(dev, B43_MMIO_PSM_PHY_HDR, tmp16 | 4);
 		b43_phy_mask(dev, B43_PHY_B_BBCFG, 0x3FFF);
-		b43_write32(dev, B43_MMIO_PSM_PHY_HDR, tmp32);
+		b43_write16(dev, B43_MMIO_PSM_PHY_HDR, tmp16);
 	}
 
 	b43_chantab_phy_upload(dev, e);

Ben Hutchings

author

2014-04-28 01:11 UTC #86 lore raw

PATCH 86/94 x86-64, modify_ldt: Ban 16-bit segments on 64-bit kernels

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: "H. Peter Anvin" <[email protected]>

commit b3b42ac2cbae1f3cecbb6229964a4d48af31d382 upstream.

The IRET instruction, when returning to a 16-bit segment, only restores the bottom 16 bits of the user space stack pointer. We have a software workaround for that ("espfix") for the 32-bit kernel, but it relies on a nonzero stack segment base which is not available in 32-bit mode.

Since 16-bit support is somewhat crippled anyway on a 64-bit kernel (no V86 mode), and most (if not quite all) 64-bit processors support virtualization for the users who really need it, simply reject attempts at creating a 16-bit segment when running on top of a 64-bit kernel.

Cc Linus Torvalds <[email protected]>

Signed-off-by H. Peter Anvin <[email protected]>

Link http://lkml.kernel.org/n/[email protected] open here

---
 arch/x86/kernel/ldt.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

arch/x86/kernel/ldt.c +11 -0

@@ -230,6 +230,17 @@ static int write_ldt(void __user *ptr, u
 		}
 	}
 
+	/*
+	 * On x86-64 we do not support 16-bit segments due to
+	 * IRET leaking the high bits of the kernel stack address.
+	 */
+#ifdef CONFIG_X86_64
+	if (!ldt_info.seg_32bit) {
+		error = -EINVAL;
+		goto out_unlock;
+	}
+#endif
+
 	fill_ldt(&ldt, &ldt_info);
 	if (oldmode)
 		ldt.avl = 0;

Ben Hutchings

author

2014-04-28 01:11 UTC #87 lore raw

PATCH 87/94 target/tcm_fc: Fix use-after-free of ft_tpg

see https://bugzilla.redhat.com/show_bug.cgi?id=1071340

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Andy Grover <[email protected]>

commit 2c42be2dd4f6586728dba5c4e197afd5cfaded78 upstream.

ft_del_tpg checks tpg->tport is set before unlinking the tpg from the tport when the tpg is being removed. Set this pointer in ft_tport_create, or the unlinking won't happen in ft_del_tpg and tport->tpg will reference a deleted object.

This patch sets tpg->tport in ft_tport_create, because that's what ft_del_tpg checks, and is the only way to get back to the tport to clear tport->tpg.

The bug was occuring when:

- lport created, tport (our per-lport, per-provider context) is allocated.
tport->tpg = NULL
- tpg created
- a PRLI is received. ft_tport_create is called, tpg is found and tport->tpg is set
- tpg removed. ft_tpg is freed in ft_del_tpg. Since tpg->tport was not set, tport->tpg is not cleared and points at freed memory
- Future calls to ft_tport_create return tport via first conditional, instead of searching for new tpg by calling ft_lport_find_tpg. tport->tpg is still invalid, and will access freed memory.

Signed-off-by Andy Grover <[email protected]>

Signed-off-by Nicholas Bellinger <[email protected]>

---
 drivers/target/tcm_fc/tfc_sess.c | 1 +
 1 file changed, 1 insertion(+)

drivers/target/tcm_fc/tfc_sess.c +1 -0

@@ -72,6 +72,7 @@ static struct ft_tport *ft_tport_create(
 
 	if (tport) {
 		tport->tpg = tpg;
+		tpg->tport = tport;
 		return tport;
 	}

Ben Hutchings

author

2014-04-28 01:11 UTC #88 lore raw

PATCH 88/94 drivers: hv: additional switch to use mb() instead of smp_mb()

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Qiang Huang <[email protected]>

commit e4af376d04b0(drivers: hv: switch to use mb() instead of smp_mb()), the adjustment mistakenly dropped the change in hv_ringbuffer_read, so add it.

Signed-off-by Qiang Huang <[email protected]>

---
 drivers/hv/ring_buffer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

drivers/hv/ring_buffer.c +1 -1

@@ -485,7 +485,7 @@ int hv_ringbuffer_read(struct hv_ring_bu
 	/* Make sure all reads are done before we update the read index since */
 	/* the writer may start writing to the read area once the read index */
 	/*is updated */
-	smp_mb();
+	mb();
 
 	/* Update the read index */
 	hv_set_next_read_location(inring_info, next_read_location);

Ben Hutchings

author

2014-04-28 01:11 UTC #89 lore raw

PATCH 89/94 Char: ipmi_bt_sm, fix infinite loop

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Jiri Slaby <[email protected]>

commit a94cdd1f4d30f12904ab528152731fb13a812a16 upstream.

In read_all_bytes, we do

  unsigned char i;
  ...
  bt->read_data[0] = BMC2HOST;
  bt->read_count = bt->read_data[0];
  ...
  for (i = 1; i <= bt->read_count; i++)
    bt->read_data[i] = BMC2HOST;

If bt->read_data[0] == bt->read_count == 255, we loop infinitely in the 'for' loop. Make 'i' an 'int' instead of 'char' to get rid of the overflow and finish the loop after 255 iterations every time.

Signed-off-by Jiri Slaby <[email protected]>

Reported-and-debugged-by Rui Hui Dian <[email protected]>

Cc Tomas Cech <[email protected]>

Cc Corey Minyard <[email protected]>

Cc <[email protected]>

Signed-off-by Corey Minyard <[email protected]>

---
 drivers/char/ipmi/ipmi_bt_sm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

drivers/char/ipmi/ipmi_bt_sm.c +1 -1

index f5e4cd7..61e7161 100644
@@ -352,7 +352,7 @@ static inline void write_all_bytes(struct si_sm_data *bt)
 
 static inline int read_all_bytes(struct si_sm_data *bt)
 {
-	unsigned char i;
+	unsigned int i;
 
 	/*
 	 * length is "framing info", minimum = 4: NetFn, Seq, Cmd, cCode.

Ben Hutchings

author

2014-04-28 01:11 UTC #90 lore raw

PATCH 90/94 selinux: correctly label /proc inodes in use before the policy is loaded

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Paul Moore <[email protected]>

commit f64410ec665479d7b4b77b7519e814253ed0f686 upstream.

This patch is based on an earlier patch by Eric Paris, he describes the problem below:

"If an inode is accessed before policy load it will get placed on a
list of inodes to be initialized after policy load. After policy load we call inode_doinit() which calls inode_doinit_with_dentry() on all inodes accessed before policy load. In the case of inodes in procfs that means we'll end up at the bottom where it does:

     /* Default to the fs superblock SID. */
     isec->sid = sbsec->sid;

     if ((sbsec->flags & SE_SBPROC) && !S_ISLNK(inode->i_mode)) {
             if (opt_dentry) {
                     isec->sclass = inode_mode_to_security_class(...)
                     rc = selinux_proc_get_sid(opt_dentry,
                                               isec->sclass,
                                               &sid);
                     if (rc)
                             goto out_unlock;
                     isec->sid = sid;
             }
     }

Since opt_dentry is null, we'll never call selinux_proc_get_sid() and will leave the inode labeled with the label on the superblock. I believe a fix would be to mimic the behavior of xattrs. Look for an alias of the inode. If it can't be found, just leave the inode uninitialized (and pick it up later) if it can be found, we should be able to call selinux_proc_get_sid() ..."

On a system exhibiting this problem, you will notice a lot of files in /proc with the generic "proc_t" type (at least the ones that were accessed early in the boot), for example:

   # ls -Z /proc/sys/kernel/shmmax | awk '{ print $4 " " $5 }'
   system_u:object_r:proc_t:s0 /proc/sys/kernel/shmmax

However, with this patch in place we see the expected result:

   # ls -Z /proc/sys/kernel/shmmax | awk '{ print $4 " " $5 }'
   system_u:object_r:sysctl_kernel_t:s0 /proc/sys/kernel/shmmax

Cc Eric Paris <[email protected]>

Signed-off-by Paul Moore <[email protected]>

Acked-by Eric Paris <[email protected]>

---
 security/selinux/hooks.c | 36 +++++++++++++++++++++++++++---------
 1 file changed, 27 insertions(+), 9 deletions(-)

security/selinux/hooks.c +27 -9

@@ -1328,15 +1328,33 @@ static int inode_doinit_with_dentry(stru
 		isec->sid = sbsec->sid;
 
 		if ((sbsec->flags & SE_SBPROC) && !S_ISLNK(inode->i_mode)) {
-			if (opt_dentry) {
-				isec->sclass = inode_mode_to_security_class(inode->i_mode);
-				rc = selinux_proc_get_sid(opt_dentry,
-							  isec->sclass,
-							  &sid);
-				if (rc)
-					goto out_unlock;
-				isec->sid = sid;
-			}
+			/* We must have a dentry to determine the label on
+			 * procfs inodes */
+			if (opt_dentry)
+				/* Called from d_instantiate or
+				 * d_splice_alias. */
+				dentry = dget(opt_dentry);
+			else
+				/* Called from selinux_complete_init, try to
+				 * find a dentry. */
+				dentry = d_find_alias(inode);
+			/*
+			 * This can be hit on boot when a file is accessed
+			 * before the policy is loaded.  When we load policy we
+			 * may find inodes that have no dentry on the
+			 * sbsec->isec_head list.  No reason to complain as
+			 * these will get fixed up the next time we go through
+			 * inode_doinit() with a dentry, before these inodes
+			 * could be used again by userspace.
+			 */
+			if (!dentry)
+				goto out_unlock;
+			isec->sclass = inode_mode_to_security_class(inode->i_mode);
+			rc = selinux_proc_get_sid(dentry, isec->sclass, &sid);
+			dput(dentry);
+			if (rc)
+				goto out_unlock;
+			isec->sid = sid;
 		}
 		break;
 	}

Ben Hutchings

author

2014-04-28 01:11 UTC #91 lore raw

PATCH 91/94 powernow-k6: disable cache when changing frequency

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Mikulas Patocka <[email protected]>

commit e20e1d0ac02308e2211306fc67abcd0b2668fb8b upstream.

I found out that a system with k6-3+ processor is unstable during network server load. The system locks up or the network card stops receiving. The reason for the instability is the CPU frequency scaling.

During frequency transition the processor is in "EPM Stop Grant" state. The documentation says that the processor doesn't respond to inquiry requests in this state. Consequently, coherency of processor caches and bus master devices is not maintained, causing the system instability.

This patch flushes the cache during frequency transition. It fixes the instability.

Other minor changes:
* u64 invalue changed to unsigned long because the variable is 32-bit
* move the logic to set the multiplier to a separate function powernow_k6_set_cpu_multiplier
* preserve lower 5 bits of the powernow port instead of 4 (the voltage field has 5 bits)
* mask interrupts when reading the multiplier, so that the port is not open during other activity (running other kernel code with the port open shouldn't cause any misbehavior, but we should better be safe and keep the port closed)

This patch should be backported to all stable kernels. If it doesn't apply cleanly, change it, or ask me to change it.

Signed-off-by Rafael J. Wysocki <[email protected]>

[bwh: Backported to 3.2: adjust context]

---
 drivers/cpufreq/powernow-k6.c | 56 ++++++++++++++++++++++++++++++-------------
 1 file changed, 39 insertions(+), 17 deletions(-)

drivers/cpufreq/powernow-k6.c +39 ~~-17~~

@@ -43,23 +43,58 @@ static struct cpufreq_frequency_table cl
 /**
  * powernow_k6_get_cpu_multiplier - returns the current FSB multiplier
  *
- *   Returns the current setting of the frequency multiplier. Core clock
+ * Returns the current setting of the frequency multiplier. Core clock
  * speed is frequency of the Front-Side Bus multiplied with this value.
  */
 static int powernow_k6_get_cpu_multiplier(void)
 {
-	u64 invalue = 0;
+	unsigned long invalue = 0;
 	u32 msrval;
 
+	local_irq_disable();
+
 	msrval = POWERNOW_IOPORT + 0x1;
 	wrmsr(MSR_K6_EPMR, msrval, 0); /* enable the PowerNow port */
 	invalue = inl(POWERNOW_IOPORT + 0x8);
 	msrval = POWERNOW_IOPORT + 0x0;
 	wrmsr(MSR_K6_EPMR, msrval, 0); /* disable it again */
 
+	local_irq_enable();
+
 	return clock_ratio[(invalue >> 5)&7].index;
 }
 
+static void powernow_k6_set_cpu_multiplier(unsigned int best_i)
+{
+	unsigned long outvalue, invalue;
+	unsigned long msrval;
+	unsigned long cr0;
+
+	/* we now need to transform best_i to the BVC format, see AMD#23446 */
+
+	/*
+	 * The processor doesn't respond to inquiry cycles while changing the
+	 * frequency, so we must disable cache.
+	 */
+	local_irq_disable();
+	cr0 = read_cr0();
+	write_cr0(cr0 | X86_CR0_CD);
+	wbinvd();
+
+	outvalue = (1<<12) | (1<<10) | (1<<9) | (best_i<<5);
+
+	msrval = POWERNOW_IOPORT + 0x1;
+	wrmsr(MSR_K6_EPMR, msrval, 0); /* enable the PowerNow port */
+	invalue = inl(POWERNOW_IOPORT + 0x8);
+	invalue = invalue & 0x1f;
+	outvalue = outvalue | invalue;
+	outl(outvalue, (POWERNOW_IOPORT + 0x8));
+	msrval = POWERNOW_IOPORT + 0x0;
+	wrmsr(MSR_K6_EPMR, msrval, 0); /* disable it again */
+
+	write_cr0(cr0);
+	local_irq_enable();
+}
 
 /**
  * powernow_k6_set_state - set the PowerNow! multiplier

@@ -69,8 +104,6 @@ static int powernow_k6_get_cpu_multiplie
  */
 static void powernow_k6_set_state(unsigned int best_i)
 {
-	unsigned long outvalue = 0, invalue = 0;
-	unsigned long msrval;
 	struct cpufreq_freqs freqs;
 
 	if (clock_ratio[best_i].index > max_multiplier) {

@@ -84,18 +117,7 @@ static void powernow_k6_set_state(unsign
 
 	cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
 
-	/* we now need to transform best_i to the BVC format, see AMD#23446 */
-
-	outvalue = (1<<12) | (1<<10) | (1<<9) | (best_i<<5);
-
-	msrval = POWERNOW_IOPORT + 0x1;
-	wrmsr(MSR_K6_EPMR, msrval, 0); /* enable the PowerNow port */
-	invalue = inl(POWERNOW_IOPORT + 0x8);
-	invalue = invalue & 0xf;
-	outvalue = outvalue | invalue;
-	outl(outvalue , (POWERNOW_IOPORT + 0x8));
-	msrval = POWERNOW_IOPORT + 0x0;
-	wrmsr(MSR_K6_EPMR, msrval, 0); /* disable it again */
+	powernow_k6_set_cpu_multiplier(best_i);
 
 	cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);

@@ -163,7 +185,7 @@ static int powernow_k6_cpu_init(struct c
 	}
 
 	/* cpuinfo and default policy values */
-	policy->cpuinfo.transition_latency = 200000;
+	policy->cpuinfo.transition_latency = 500000;
 	policy->cur = busfreq * max_multiplier;
 
 	result = cpufreq_frequency_table_cpuinfo(policy, clock_ratio);

Ben Hutchings

author

2014-04-28 01:11 UTC #92 lore raw

PATCH 92/94 powernow-k6: correctly initialize default parameters

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Mikulas Patocka <[email protected]>

commit d82b922a4acc1781d368aceac2f9da43b038cab2 upstream.

The powernow-k6 driver used to read the initial multiplier from the powernow register. However, there is a problem with this:

* If there was a frequency transition before, the multiplier read from the register corresponds to the current multiplier.
* If there was no frequency transition since reset, the field in the register always reads as zero, regardless of the current multiplier that is set using switches on the mainboard and that the CPU is running at.

The zero value corresponds to multiplier 4.5, so as a consequence, the powernow-k6 driver always assumes multiplier 4.5.

For example, if we have 550MHz CPU with bus frequency 100MHz and multiplier 5.5, the powernow-k6 driver thinks that the multiplier is 4.5 and bus frequency is 122MHz. The powernow-k6 driver then sets the multiplier to 4.5, underclocking the CPU to 450MHz, but reports the current frequency as 550MHz.

There is no reliable way how to read the initial multiplier. I modified the driver so that it contains a table of known frequencies (based on parameters of existing CPUs and some common overclocking schemes) and sets the multiplier according to the frequency. If the frequency is unknown (because of unusual overclocking or underclocking), the user must supply the bus speed and maximum multiplier as module parameters.

This patch should be backported to all stable kernels. If it doesn't apply cleanly, change it, or ask me to change it.

Signed-off-by Rafael J. Wysocki <[email protected]>

[bwh: Backported to 3.2: adjust context]

---
 drivers/cpufreq/powernow-k6.c | 76 ++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 72 insertions(+), 4 deletions(-)

drivers/cpufreq/powernow-k6.c +72 -4

@@ -25,6 +25,14 @@
 static unsigned int                     busfreq;   /* FSB, in 10 kHz */
 static unsigned int                     max_multiplier;
 
+static unsigned int			param_busfreq = 0;
+static unsigned int			param_max_multiplier = 0;
+
+module_param_named(max_multiplier, param_max_multiplier, uint, S_IRUGO);
+MODULE_PARM_DESC(max_multiplier, "Maximum multiplier (allowed values: 20 30 35 40 45 50 55 60)");
+
+module_param_named(bus_frequency, param_busfreq, uint, S_IRUGO);
+MODULE_PARM_DESC(bus_frequency, "Bus frequency in kHz");
 
 /* Clock ratio multiplied by 10 - see table 27 in AMD#23446 */
 static struct cpufreq_frequency_table clock_ratio[] = {

@@ -39,6 +47,27 @@ static struct cpufreq_frequency_table cl
 	{0, CPUFREQ_TABLE_END}
 };
 
+static const struct {
+	unsigned freq;
+	unsigned mult;
+} usual_frequency_table[] = {
+	{ 400000, 40 },	// 100   * 4
+	{ 450000, 45 }, // 100   * 4.5
+	{ 475000, 50 }, //  95   * 5
+	{ 500000, 50 }, // 100   * 5
+	{ 506250, 45 }, // 112.5 * 4.5
+	{ 533500, 55 }, //  97   * 5.5
+	{ 550000, 55 }, // 100   * 5.5
+	{ 562500, 50 }, // 112.5 * 5
+	{ 570000, 60 }, //  95   * 6
+	{ 600000, 60 }, // 100   * 6
+	{ 618750, 55 }, // 112.5 * 5.5
+	{ 660000, 55 }, // 120   * 5.5
+	{ 675000, 60 }, // 112.5 * 6
+	{ 720000, 60 }, // 120   * 6
+};
+
+#define FREQ_RANGE		3000
 
 /**
  * powernow_k6_get_cpu_multiplier - returns the current FSB multiplier

@@ -162,18 +191,57 @@ static int powernow_k6_target(struct cpu
 	return 0;
 }
 
-
 static int powernow_k6_cpu_init(struct cpufreq_policy *policy)
 {
 	unsigned int i, f;
 	int result;
+	unsigned khz;
 
 	if (policy->cpu != 0)
 		return -ENODEV;
 
-	/* get frequencies */
-	max_multiplier = powernow_k6_get_cpu_multiplier();
-	busfreq = cpu_khz / max_multiplier;
+	max_multiplier = 0;
+	khz = cpu_khz;
+	for (i = 0; i < ARRAY_SIZE(usual_frequency_table); i++) {
+		if (khz >= usual_frequency_table[i].freq - FREQ_RANGE &&
+		    khz <= usual_frequency_table[i].freq + FREQ_RANGE) {
+			khz = usual_frequency_table[i].freq;
+			max_multiplier = usual_frequency_table[i].mult;
+			break;
+		}
+	}
+	if (param_max_multiplier) {
+		for (i = 0; (clock_ratio[i].frequency != CPUFREQ_TABLE_END); i++) {
+			if (clock_ratio[i].driver_data == param_max_multiplier) {
+				max_multiplier = param_max_multiplier;
+				goto have_max_multiplier;
+			}
+		}
+		printk(KERN_ERR "powernow-k6: invalid max_multiplier parameter, valid parameters 20, 30, 35, 40, 45, 50, 55, 60\n");
+		return -EINVAL;
+	}
+
+	if (!max_multiplier) {
+		printk(KERN_WARNING "powernow-k6: unknown frequency %u, cannot determine current multiplier\n", khz);
+		printk(KERN_WARNING "powernow-k6: use module parameters max_multiplier and bus_frequency\n");
+		return -EOPNOTSUPP;
+	}
+
+have_max_multiplier:
+	param_max_multiplier = max_multiplier;
+
+	if (param_busfreq) {
+		if (param_busfreq >= 50000 && param_busfreq <= 150000) {
+			busfreq = param_busfreq / 10;
+			goto have_busfreq;
+		}
+		printk(KERN_ERR "powernow-k6: invalid bus_frequency parameter, allowed range 50000 - 150000 kHz\n");
+		return -EINVAL;
+	}
+
+	busfreq = khz / max_multiplier;
+have_busfreq:
+	param_busfreq = busfreq * 10;
 
 	/* table init */
 	for (i = 0; (clock_ratio[i].frequency != CPUFREQ_TABLE_END); i++) {

Ben Hutchings

author

2014-04-28 01:11 UTC #93 lore raw

PATCH 93/94 powernow-k6: reorder frequencies

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Mikulas Patocka <[email protected]>

commit 22c73795b101597051924556dce019385a1e2fa0 upstream.

This patch reorders reported frequencies from the highest to the lowest, just like in other frequency drivers.

Acked-by Viresh Kumar <[email protected]>

Signed-off-by Rafael J. Wysocki <[email protected]>

[bwh: Backported to 3.2: cpu_frequency_table::driver_data is called index]

---
 drivers/cpufreq/powernow-k6.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

drivers/cpufreq/powernow-k6.c +10 -7

@@ -36,17 +36,20 @@ MODULE_PARM_DESC(bus_frequency, "Bus fre
 
 /* Clock ratio multiplied by 10 - see table 27 in AMD#23446 */
 static struct cpufreq_frequency_table clock_ratio[] = {
-	{45,  /* 000 -> 4.5x */ 0},
+	{60,  /* 110 -> 6.0x */ 0},
+	{55,  /* 011 -> 5.5x */ 0},
 	{50,  /* 001 -> 5.0x */ 0},
+	{45,  /* 000 -> 4.5x */ 0},
 	{40,  /* 010 -> 4.0x */ 0},
-	{55,  /* 011 -> 5.5x */ 0},
-	{20,  /* 100 -> 2.0x */ 0},
-	{30,  /* 101 -> 3.0x */ 0},
-	{60,  /* 110 -> 6.0x */ 0},
 	{35,  /* 111 -> 3.5x */ 0},
+	{30,  /* 101 -> 3.0x */ 0},
+	{20,  /* 100 -> 2.0x */ 0},
 	{0, CPUFREQ_TABLE_END}
 };
 
+static const u8 index_to_register[8] = { 6, 3, 1, 0, 2, 7, 5, 4 };
+static const u8 register_to_index[8] = { 3, 2, 4, 1, 7, 6, 0, 5 };
+
 static const struct {
 	unsigned freq;
 	unsigned mult;

@@ -90,7 +93,7 @@ static int powernow_k6_get_cpu_multiplie
 
 	local_irq_enable();
 
-	return clock_ratio[(invalue >> 5)&7].index;
+	return clock_ratio[register_to_index[(invalue >> 5)&7]].index;
 }
 
 static void powernow_k6_set_cpu_multiplier(unsigned int best_i)

@@ -110,7 +113,7 @@ static void powernow_k6_set_cpu_multipli
 	write_cr0(cr0 | X86_CR0_CD);
 	wbinvd();
 
-	outvalue = (1<<12) | (1<<10) | (1<<9) | (best_i<<5);
+	outvalue = (1<<12) | (1<<10) | (1<<9) | (index_to_register[best_i]<<5);
 
 	msrval = POWERNOW_IOPORT + 0x1;
 	wrmsr(MSR_K6_EPMR, msrval, 0); /* enable the PowerNow port */

Ben Hutchings

author

2014-04-28 01:11 UTC #94 lore raw

PATCH 94/94 Revert "alpha: fix broken network checksum"

3.2.58-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: Ben Hutchings <[email protected]>

This reverts commit b93b90ff7c50288d602108ae1a09673df3f799a8, which was commit 0ef38d70d4118b2ce1a538d14357be5ff9dc2bbd upstream. It was intended to fix a regression which never occurred in 3.2.

arch/alpha/lib/csum_partial_copy.c +2 -7

@@ -373,11 +373,6 @@
 __wsum
 csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum)
 {
-	__wsum checksum;
-	mm_segment_t oldfs = get_fs();
-	set_fs(KERNEL_DS);
-	checksum = csum_partial_copy_from_user((__force const void __user *)src,
-						dst, len, sum, NULL);
-	set_fs(oldfs);
-	return checksum;
+	return csum_partial_copy_from_user((__force const void __user *)src,
+			dst, len, sum, NULL);
 }

Ben Hutchings

author

2014-04-28 15:05 UTC #95 lore raw

This is the combined patch for 3.2.58-rc1 relative to 3.2.57.

Ben.

Signature · 3 lines

Ben Hutchings
Q.  Which is the greater problem in the world today, ignorance or apathy?
A.  I don't know and I couldn't care less.

Documentation/video4linux/gspca.txt +1 -0

index b15e29f..90aae856 100644
@@ -55,6 +55,7 @@ zc3xx		0458:700f	Genius VideoCam Web V2
 sonixj		0458:7025	Genius Eye 311Q
 sn9c20x		0458:7029	Genius Look 320s
 sonixj		0458:702e	Genius Slim 310 NB
+sn9c20x		0458:7045	Genius Look 1320 V2
 sn9c20x		0458:704a	Genius Slim 1320
 sn9c20x		0458:704c	Genius i-Look 1321
 sn9c20x		045e:00f4	LifeCam VX-6000 (SN9C20x + OV9650)

Makefile +2 -2

index c92db9b..8d66ad3 100644
@@ -1,7 +1,7 @@
 VERSION = 3
 PATCHLEVEL = 2
-SUBLEVEL = 57
-EXTRAVERSION =
+SUBLEVEL = 58
+EXTRAVERSION = -rc1
 NAME = Saber-toothed Squirrel
 
 # *DOCUMENTATION*

arch/arm/include/asm/futex.h +0 -6

index 253cc86..aefd459 100644
@@ -3,11 +3,6 @@
 
 #ifdef __KERNEL__
 
-#if defined(CONFIG_CPU_USE_DOMAINS) && defined(CONFIG_SMP)
-/* ARM doesn't provide unprivileged exclusive memory accessors */
-#include <asm-generic/futex.h>
-#else
-
 #include <linux/futex.h>
 #include <linux/uaccess.h>
 #include <asm/errno.h>

@@ -163,6 +158,5 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 	return ret;
 }
 
-#endif /* !(CPU_USE_DOMAINS && SMP) */
 #endif /* __KERNEL__ */
 #endif /* _ASM_ARM_FUTEX_H */

arch/arm/include/asm/pgtable-2level.h +2 -0

index 470457e..1cb80c4 100644
@@ -123,6 +123,7 @@
 #define L_PTE_USER		(_AT(pteval_t, 1) << 8)
 #define L_PTE_XN		(_AT(pteval_t, 1) << 9)
 #define L_PTE_SHARED		(_AT(pteval_t, 1) << 10)	/* shared(v6), coherent(xsc3) */
+#define L_PTE_NONE		(_AT(pteval_t, 1) << 11)
 
 /*
  * These are the memory types, defined to be compatible with

@@ -138,6 +139,7 @@
 #define L_PTE_MT_DEV_NONSHARED	(_AT(pteval_t, 0x0c) << 2)	/* 1100 */
 #define L_PTE_MT_DEV_WC		(_AT(pteval_t, 0x09) << 2)	/* 1001 */
 #define L_PTE_MT_DEV_CACHED	(_AT(pteval_t, 0x0b) << 2)	/* 1011 */
+#define L_PTE_MT_VECTORS	(_AT(pteval_t, 0x0f) << 2)	/* 1111 */
 #define L_PTE_MT_MASK		(_AT(pteval_t, 0x0f) << 2)
 
 #endif /* _ASM_PGTABLE_2LEVEL_H */

arch/arm/include/asm/pgtable.h +3 -3

index 9b419ab..fcbac3c 100644
@@ -74,7 +74,7 @@ extern pgprot_t		pgprot_kernel;
 
 #define _MOD_PROT(p, b)	__pgprot(pgprot_val(p) | (b))
 
-#define PAGE_NONE		_MOD_PROT(pgprot_user, L_PTE_XN | L_PTE_RDONLY)
+#define PAGE_NONE		_MOD_PROT(pgprot_user, L_PTE_XN | L_PTE_RDONLY | L_PTE_NONE)
 #define PAGE_SHARED		_MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_XN)
 #define PAGE_SHARED_EXEC	_MOD_PROT(pgprot_user, L_PTE_USER)
 #define PAGE_COPY		_MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_RDONLY | L_PTE_XN)

@@ -84,7 +84,7 @@ extern pgprot_t		pgprot_kernel;
 #define PAGE_KERNEL		_MOD_PROT(pgprot_kernel, L_PTE_XN)
 #define PAGE_KERNEL_EXEC	pgprot_kernel
 
-#define __PAGE_NONE		__pgprot(_L_PTE_DEFAULT | L_PTE_RDONLY | L_PTE_XN)
+#define __PAGE_NONE		__pgprot(_L_PTE_DEFAULT | L_PTE_RDONLY | L_PTE_XN | L_PTE_NONE)
 #define __PAGE_SHARED		__pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_XN)
 #define __PAGE_SHARED_EXEC	__pgprot(_L_PTE_DEFAULT | L_PTE_USER)
 #define __PAGE_COPY		__pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_RDONLY | L_PTE_XN)

@@ -279,7 +279,7 @@ static inline pte_t pte_mkspecial(pte_t pte) { return pte; }
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
-	const pteval_t mask = L_PTE_XN | L_PTE_RDONLY | L_PTE_USER;
+	const pteval_t mask = L_PTE_XN | L_PTE_RDONLY | L_PTE_USER | L_PTE_NONE;
 	pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask);
 	return pte;
 }

arch/arm/mm/Kconfig +1 -2

index 67f75a0..4e1ef6e 100644
@@ -458,7 +458,6 @@ config CPU_32v5
 config CPU_32v6
 	bool
 	select TLS_REG_EMUL if !CPU_32v6K && !MMU
-	select CPU_USE_DOMAINS if CPU_V6 && MMU
 
 config CPU_32v6K
 	bool

@@ -652,7 +651,7 @@ config ARM_THUMBEE
 
 config SWP_EMULATE
 	bool "Emulate SWP/SWPB instructions"
-	depends on !CPU_USE_DOMAINS && CPU_V7
+	depends on CPU_V7
 	select HAVE_PROC_CPU if PROC_FS
 	default y if SMP
 	help

arch/arm/mm/mmu.c +8 -0

index 9e28fdb..082fa18 100644
@@ -426,6 +426,14 @@ static void __init build_mem_type_table(void)
 		mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED;
 	}
 	/*
+	 * We don't use domains on ARMv6 (since this causes problems with
+	 * v6/v7 kernels), so we must use a separate memory type for user
+	 * r/o, kernel r/w to map the vectors page.
+	 */
+	if (cpu_arch == CPU_ARCH_ARMv6)
+		vecs_pgprot |= L_PTE_MT_VECTORS;
+
+	/*
 	 * ARMv6 and above have extended page tables.
 	 */
 	if (cpu_arch >= CPU_ARCH_ARMv6 && (cr & CR_XP)) {

arch/arm/mm/proc-macros.S +8 ~~-11~~

index 307a4de..8a3edd4 100644
@@ -106,13 +106,9 @@
  *  100x   1   0   1	r/o	no acc
  *  10x0   1   0   1	r/o	no acc
  *  1011   0   0   1	r/w	no acc
- *  110x   0   1   0	r/w	r/o
- *  11x0   0   1   0	r/w	r/o
- *  1111   0   1   1	r/w	r/w
- *
- * If !CONFIG_CPU_USE_DOMAINS, the following permissions are changed:
  *  110x   1   1   1	r/o	r/o
  *  11x0   1   1   1	r/o	r/o
+ *  1111   0   1   1	r/w	r/w
  */
 	.macro	armv6_mt_table pfx
 \pfx\()_mt_table:

@@ -131,7 +127,7 @@
 	.long	PTE_EXT_TEX(2)					@ L_PTE_MT_DEV_NONSHARED
 	.long	0x00						@ unused
 	.long	0x00						@ unused
-	.long	0x00						@ unused
+	.long	PTE_CACHEABLE | PTE_BUFFERABLE | PTE_EXT_APX	@ L_PTE_MT_VECTORS
 	.endm
 
 	.macro	armv6_set_pte_ext pfx

@@ -152,20 +148,21 @@
 
 	tst	r1, #L_PTE_USER
 	orrne	r3, r3, #PTE_EXT_AP1
-#ifdef CONFIG_CPU_USE_DOMAINS
-	@ allow kernel read/write access to read-only user pages
 	tstne	r3, #PTE_EXT_APX
-	bicne	r3, r3, #PTE_EXT_APX | PTE_EXT_AP0
-#endif
+
+	@ user read-only -> kernel read-only
+	bicne	r3, r3, #PTE_EXT_AP0
 
 	tst	r1, #L_PTE_XN
 	orrne	r3, r3, #PTE_EXT_XN
 
-	orr	r3, r3, r2
+	eor	r3, r3, r2
 
 	tst	r1, #L_PTE_YOUNG
 	tstne	r1, #L_PTE_PRESENT
 	moveq	r3, #0
+	tstne	r1, #L_PTE_NONE
+	movne	r3, #0
 
 	str	r3, [r0]
 	mcr	p15, 0, r0, c7, c10, 1		@ flush_pte

arch/arm/mm/proc-v7.S +2 -5

index 19d21ff..43c6981 100644
@@ -160,17 +160,14 @@ ENTRY(cpu_v7_set_pte_ext)
 
 	tst	r1, #L_PTE_USER
 	orrne	r3, r3, #PTE_EXT_AP1
-#ifdef CONFIG_CPU_USE_DOMAINS
-	@ allow kernel read/write access to read-only user pages
-	tstne	r3, #PTE_EXT_APX
-	bicne	r3, r3, #PTE_EXT_APX | PTE_EXT_AP0
-#endif
 
 	tst	r1, #L_PTE_XN
 	orrne	r3, r3, #PTE_EXT_XN
 
 	tst	r1, #L_PTE_YOUNG
 	tstne	r1, #L_PTE_PRESENT
+	eorne	r1, r1, #L_PTE_NONE
+	tstne	r1, #L_PTE_NONE
 	moveq	r3, #0
 
  ARM(	str	r3, [r0, #2048]! )

arch/mips/power/hibernate.S +1 -0

index f8a751c..5bf34ec 100644
@@ -44,6 +44,7 @@ LEAF(swsusp_arch_resume)
 	bne t1, t3, 1b
 	PTR_L t0, PBE_NEXT(t0)
 	bnez t0, 0b
+	jal local_flush_tlb_all /* Avoid TLB mismatch after kernel resume */
 	PTR_LA t0, saved_regs
 	PTR_L ra, PT_R31(t0)
 	PTR_L sp, PT_R29(t0)

arch/sh/kernel/dumpstack.c +1 -1

index 694158b..3a6528c 100644
@@ -80,7 +80,7 @@ static int print_trace_stack(void *data, char *name)
  */
 static void print_trace_address(void *data, unsigned long addr, int reliable)
 {
-	printk(data);
+	printk("%s", (char *)data);
 	printk_address(addr, reliable);
 }

arch/sparc/Kconfig +1 -1

index 87537e2..88d442d 100644
@@ -24,7 +24,7 @@ config SPARC
 	select HAVE_IRQ_WORK
 	select HAVE_DMA_ATTRS
 	select HAVE_DMA_API_DEBUG
-	select HAVE_ARCH_JUMP_LABEL
+	select HAVE_ARCH_JUMP_LABEL if SPARC64
 	select HAVE_GENERIC_HARDIRQS
 	select GENERIC_IRQ_SHOW
 	select USE_GENERIC_SMP_HELPERS if SMP

arch/sparc/include/asm/uaccess_64.h +2 -2

index 3e1449f..6d6c731 100644
@@ -267,8 +267,8 @@ extern long __strnlen_user(const char __user *, long len);
 
 #define strlen_user __strlen_user
 #define strnlen_user __strnlen_user
-#define __copy_to_user_inatomic ___copy_to_user
-#define __copy_from_user_inatomic ___copy_from_user
+#define __copy_to_user_inatomic __copy_to_user
+#define __copy_from_user_inatomic __copy_from_user
 
 #endif  /* __ASSEMBLY__ */

arch/sparc/kernel/pci.c +2 -2

index 31111e3..656b5b6 100644
@@ -487,8 +487,8 @@ static void __devinit apb_fake_ranges(struct pci_dev *dev,
 	pci_read_config_byte(dev, APB_MEM_ADDRESS_MAP, &map);
 	apb_calc_first_last(map, &first, &last);
 	res = bus->resource[1];
-	res->start = (first << 21);
-	res->end = (last << 21) + ((1 << 21) - 1);
+	res->start = (first << 29);
+	res->end = (last << 29) + ((1 << 29) - 1);
 	res->flags = IORESOURCE_MEM;
 	pci_resource_adjust(res, &pbm->mem_space);
 }

arch/sparc/kernel/syscalls.S +2 -2

index 817187d..557212c 100644
@@ -184,7 +184,8 @@ linux_sparc_syscall32:
 	 mov	%i0, %l5				! IEU1
 5:	call	%l7					! CTI	Group brk forced
 	 srl	%i5, 0, %o5				! IEU1
-	ba,a,pt	%xcc, 3f
+	ba,pt	%xcc, 3f
+	 sra	%o0, 0, %o0
 
 	/* Linux native system calls enter here... */
 	.align	32

@@ -212,7 +213,6 @@ linux_sparc_syscall:
 3:	stx	%o0, [%sp + PTREGS_OFF + PT_V9_I0]
 ret_sys_call:
 	ldx	[%sp + PTREGS_OFF + PT_V9_TSTATE], %g3
-	sra	%o0, 0, %o0
 	mov	%ulo(TSTATE_XCARRY | TSTATE_ICARRY), %g2
 	sllx	%g2, 32, %g2

arch/x86/kernel/cpu/mshyperv.c +6 -0

index 646d192..1a3cf6e 100644
@@ -18,6 +18,7 @@
 #include <asm/hypervisor.h>
 #include <asm/hyperv.h>
 #include <asm/mshyperv.h>
+#include <asm/timer.h>
 
 struct ms_hyperv_info ms_hyperv;
 EXPORT_SYMBOL_GPL(ms_hyperv);

@@ -70,6 +71,11 @@ static void __init ms_hyperv_init_platform(void)
 
 	if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE)
 		clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100);
+
+#ifdef CONFIG_X86_IO_APIC
+	no_timer_check = 1;
+#endif
+
 }
 
 const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {

arch/x86/kernel/ldt.c +11 -0

index ea69726..4ac4531 100644
@@ -230,6 +230,17 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 		}
 	}
 
+	/*
+	 * On x86-64 we do not support 16-bit segments due to
+	 * IRET leaking the high bits of the kernel stack address.
+	 */
+#ifdef CONFIG_X86_64
+	if (!ldt_info.seg_32bit) {
+		error = -EINVAL;
+		goto out_unlock;
+	}
+#endif
+
 	fill_ldt(&ldt, &ldt_info);
 	if (oldmode)
 		ldt.avl = 0;

block/blk-core.c +1 -1

index a219c89..ec494ff 100644
@@ -2077,7 +2077,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 	if (!req->bio)
 		return false;
 
-	trace_block_rq_complete(req->q, req);
+	trace_block_rq_complete(req->q, req, nr_bytes);
 
 	/*
 	 * For fs requests, rq is just carrier of independent bio's

drivers/gpio/gpio-mxs.c +2 -1

index 385c58e..0f8114d 100644
@@ -167,7 +167,8 @@ static void __init mxs_gpio_init_gc(struct mxs_gpio_port *port)
 	ct->regs.ack = PINCTRL_IRQSTAT(port->id) + MXS_CLR;
 	ct->regs.mask = PINCTRL_IRQEN(port->id);
 
-	irq_setup_generic_chip(gc, IRQ_MSK(32), 0, IRQ_NOREQUEST, 0);
+	irq_setup_generic_chip(gc, IRQ_MSK(32), IRQ_GC_INIT_NESTED_LOCK,
+			       IRQ_NOREQUEST, 0);
 }
 
 static int mxs_gpio_to_irq(struct gpio_chip *gc, unsigned offset)

drivers/gpu/drm/i915/intel_display.c +6 -0

index 2ea8a96..27999d9 100644
@@ -8946,6 +8946,12 @@ struct intel_quirk intel_quirks[] = {
 	/* Acer/Packard Bell NCL20 */
 	{ 0x2a42, 0x1025, 0x034b, quirk_invert_brightness },
 
+	/* Acer Aspire 4736Z */
+	{ 0x2a42, 0x1025, 0x0260, quirk_invert_brightness },
+
+	/* Acer Aspire 5336 */
+	{ 0x2a42, 0x1025, 0x048a, quirk_invert_brightness },
+
 	/* Dell XPS13 HD Sandy Bridge */
 	{ 0x0116, 0x1028, 0x052e, quirk_no_pcm_pwm_enable },
 	/* Dell XPS13 HD and XPS13 FHD Ivy Bridge */

drivers/gpu/drm/i915/intel_tv.c +7 -2

index 12041fa..b221f2b 100644
@@ -1599,9 +1599,14 @@ static int tv_is_present_in_vbt(struct drm_device *dev)
 		/*
 		 * If the device type is not TV, continue.
 		 */
-		if (p_child->device_type != DEVICE_TYPE_INT_TV &&
-			p_child->device_type != DEVICE_TYPE_TV)
+		switch (p_child->device_type) {
+		case DEVICE_TYPE_INT_TV:
+		case DEVICE_TYPE_TV:
+		case DEVICE_TYPE_TV_SVIDEO_COMPOSITE:
+			break;
+		default:
 			continue;
+		}
 		/* Only when the addin_offset is non-zero, it is regarded
 		 * as present.
 		 */

drivers/gpu/drm/radeon/radeon_display.c +1 -0

index 63e7143..3291ab8 100644
@@ -738,6 +738,7 @@ int radeon_ddc_get_modes(struct radeon_connector *radeon_connector)
 	if (radeon_connector->edid) {
 		drm_mode_connector_update_edid_property(&radeon_connector->base, radeon_connector->edid);
 		ret = drm_add_edid_modes(&radeon_connector->base, radeon_connector->edid);
+		drm_edid_to_eld(&radeon_connector->base, radeon_connector->edid);
 		return ret;
 	}
 	drm_mode_connector_update_edid_property(&radeon_connector->base, NULL);

drivers/gpu/drm/vmwgfx/vmwgfx_fb.c +4 -1

index 34e51a1..907c26f 100644
@@ -147,7 +147,7 @@ static int vmw_fb_check_var(struct fb_var_screeninfo *var,
 	}
 
 	if (!vmw_kms_validate_mode_vram(vmw_priv,
-					info->fix.line_length,
+					var->xres * var->bits_per_pixel/8,
 					var->yoffset + var->yres)) {
 		DRM_ERROR("Requested geom can not fit in framebuffer\n");
 		return -EINVAL;

@@ -162,6 +162,8 @@ static int vmw_fb_set_par(struct fb_info *info)
 	struct vmw_private *vmw_priv = par->vmw_priv;
 	int ret;
 
+	info->fix.line_length = info->var.xres * info->var.bits_per_pixel/8;
+
 	ret = vmw_kms_write_svga(vmw_priv, info->var.xres, info->var.yres,
 				 info->fix.line_length,
 				 par->bpp, par->depth);

@@ -177,6 +179,7 @@ static int vmw_fb_set_par(struct fb_info *info)
 		vmw_write(vmw_priv, SVGA_REG_DISPLAY_POSITION_Y, info->var.yoffset);
 		vmw_write(vmw_priv, SVGA_REG_DISPLAY_WIDTH, info->var.xres);
 		vmw_write(vmw_priv, SVGA_REG_DISPLAY_HEIGHT, info->var.yres);
+		vmw_write(vmw_priv, SVGA_REG_BYTES_PER_LINE, info->fix.line_length);
 		vmw_write(vmw_priv, SVGA_REG_DISPLAY_ID, SVGA_ID_INVALID);
 	}

drivers/hv/ring_buffer.c +1 -1

index 810658e..d01edf3 100644
@@ -485,7 +485,7 @@ int hv_ringbuffer_read(struct hv_ring_buffer_info *inring_info, void *buffer,
 	/* Make sure all reads are done before we update the read index since */
 	/* the writer may start writing to the read area once the read index */
 	/*is updated */
-	smp_mb();
+	mb();
 
 	/* Update the read index */
 	hv_set_next_read_location(inring_info, next_read_location);

drivers/infiniband/hw/ehca/ehca_cq.c +1 -0

index d9b0ebc..6eeb84d 100644
@@ -296,6 +296,7 @@ struct ib_cq *ehca_create_cq(struct ib_device *device, int cqe, int comp_vector,
 			(my_cq->galpas.user.fw_handle & (PAGE_SIZE - 1));
 		if (ib_copy_to_udata(udata, &resp, sizeof(resp))) {
 			ehca_err(device, "Copy to udata failed.");
+			cq = ERR_PTR(-EFAULT);
 			goto create_cq_exit4;
 		}
 	}

drivers/infiniband/hw/ipath/ipath_diag.c +25 ~~-41~~

110 lines not on this page · raw message

drivers/infiniband/hw/mthca/mthca_provider.c +1 -0

index 5b71d43..42dde06 100644
@@ -695,6 +695,7 @@ static struct ib_cq *mthca_create_cq(struct ib_device *ibdev, int entries,
 
 	if (context && ib_copy_to_udata(udata, &cq->cqn, sizeof (__u32))) {
 		mthca_free_cq(to_mdev(ibdev), cq);
+		err = -EFAULT;
 		goto err_free;
 	}

drivers/infiniband/hw/nes/nes_verbs.c +1 -1

index b0471b4..330eb6e 100644
@@ -1183,7 +1183,7 @@ static struct ib_qp *nes_create_qp(struct ib_pd *ibpd,
 					nes_free_resource(nesadapter, nesadapter->allocated_qps, qp_num);
 					kfree(nesqp->allocated_buffer);
 					nes_debug(NES_DBG_QP, "ib_copy_from_udata() Failed \n");
-					return NULL;
+					return ERR_PTR(-EFAULT);
 				}
 				if (req.user_wqe_buffers) {
 					virt_wqs = 1;

drivers/isdn/isdnloop/isdnloop.c +15 -8

index 4df80fb..75ca5d2 100644
@@ -518,9 +518,9 @@ static isdnloop_stat isdnloop_cmd_table[] =
 static void
 isdnloop_fake_err(isdnloop_card * card)
 {
-	char buf[60];
+	char buf[64];
 
-	sprintf(buf, "E%s", card->omsg);
+	snprintf(buf, sizeof(buf), "E%s", card->omsg);
 	isdnloop_fake(card, buf, -1);
 	isdnloop_fake(card, "NAK", -1);
 }

@@ -903,6 +903,8 @@ isdnloop_parse_cmd(isdnloop_card * card)
 		case 7:
 			/* 0x;EAZ */
 			p += 3;
+			if (strlen(p) >= sizeof(card->eazlist[0]))
+				break;
 			strcpy(card->eazlist[ch - 1], p);
 			break;
 		case 8:

@@ -1070,6 +1072,12 @@ isdnloop_start(isdnloop_card * card, isdnloop_sdef * sdefp)
 		return -EBUSY;
 	if (copy_from_user((char *) &sdef, (char *) sdefp, sizeof(sdef)))
 		return -EFAULT;
+
+	for (i = 0; i < 3; i++) {
+		if (!memchr(sdef.num[i], 0, sizeof(sdef.num[i])))
+			return -EINVAL;
+	}
+
 	spin_lock_irqsave(&card->isdnloop_lock, flags);
 	switch (sdef.ptype) {
 		case ISDN_PTYPE_EURO:

@@ -1127,7 +1135,7 @@ isdnloop_command(isdn_ctrl * c, isdnloop_card * card)
 {
 	ulong a;
 	int i;
-	char cbuf[60];
+	char cbuf[80];
 	isdn_ctrl cmd;
 	isdnloop_cdef cdef;

@@ -1192,7 +1200,6 @@ isdnloop_command(isdn_ctrl * c, isdnloop_card * card)
 				break;
 			if ((c->arg & 255) < ISDNLOOP_BCH) {
 				char *p;
-				char dial[50];
 				char dcode[4];
 
 				a = c->arg;

@@ -1204,10 +1211,10 @@ isdnloop_command(isdn_ctrl * c, isdnloop_card * card)
 				} else
 					/* Normal Dial */
 					strcpy(dcode, "CAL");
-				strcpy(dial, p);
-				sprintf(cbuf, "%02d;D%s_R%s,%02d,%02d,%s\n", (int) (a + 1),
-					dcode, dial, c->parm.setup.si1,
-				c->parm.setup.si2, c->parm.setup.eazmsn);
+				snprintf(cbuf, sizeof(cbuf),
+					 "%02d;D%s_R%s,%02d,%02d,%s\n", (int) (a + 1),
+					 dcode, p, c->parm.setup.si1,
+					 c->parm.setup.si2, c->parm.setup.eazmsn);
 				i = isdnloop_writecmd(cbuf, strlen(cbuf), 0, card);
 			}
 			break;

drivers/md/dm-thin.c +1 -1

index 2c9dd2c..80f8bd5 100644
@@ -1298,9 +1298,9 @@ static void process_deferred_bios(struct pool *pool)
 		 */
 		if (ensure_next_mapping(pool)) {
 			spin_lock_irqsave(&pool->lock, flags);
+			bio_list_add(&pool->deferred_bios, bio);
 			bio_list_merge(&pool->deferred_bios, &bios);
 			spin_unlock_irqrestore(&pool->lock, flags);
-
 			break;
 		}
 		process_bio(tc, bio);

drivers/media/video/gspca/sn9c20x.c +1 -0

index 86e07a1..509e202 100644
@@ -2521,6 +2521,7 @@ static const struct usb_device_id device_table[] = {
 	{USB_DEVICE(0x045e, 0x00f4), SN9C20X(OV9650, 0x30, 0)},
 	{USB_DEVICE(0x145f, 0x013d), SN9C20X(OV7660, 0x21, 0)},
 	{USB_DEVICE(0x0458, 0x7029), SN9C20X(HV7131R, 0x11, 0)},
+	{USB_DEVICE(0x0458, 0x7045), SN9C20X(MT9M112, 0x5d, LED_REVERSE)},
 	{USB_DEVICE(0x0458, 0x704a), SN9C20X(MT9M112, 0x5d, 0)},
 	{USB_DEVICE(0x0458, 0x704c), SN9C20X(MT9M112, 0x5d, 0)},
 	{USB_DEVICE(0xa168, 0x0610), SN9C20X(HV7131R, 0x11, 0)},

drivers/media/video/uvc/uvc_video.c +19 -1

index b015e8e..af5c040 100644
@@ -1267,7 +1267,25 @@ int uvc_video_enable(struct uvc_streaming *stream, int enable)
 
 	if (!enable) {
 		uvc_uninit_video(stream, 1);
-		usb_set_interface(stream->dev->udev, stream->intfnum, 0);
+		if (stream->intf->num_altsetting > 1) {
+			usb_set_interface(stream->dev->udev,
+					  stream->intfnum, 0);
+		} else {
+			/* UVC doesn't specify how to inform a bulk-based device
+			 * when the video stream is stopped. Windows sends a
+			 * CLEAR_FEATURE(HALT) request to the video streaming
+			 * bulk endpoint, mimic the same behaviour.
+			 */
+			unsigned int epnum = stream->header.bEndpointAddress
+					   & USB_ENDPOINT_NUMBER_MASK;
+			unsigned int dir = stream->header.bEndpointAddress
+					 & USB_ENDPOINT_DIR_MASK;
+			unsigned int pipe;
+
+			pipe = usb_sndbulkpipe(stream->dev->udev, epnum) | dir;
+			usb_clear_halt(stream->dev->udev, pipe);
+		}
+
 		uvc_queue_enable(&stream->queue, 0);
 		return 0;
 	}

drivers/mfd/88pm860x-i2c.c +6 -0

index e017dc8..f035dd3 100644
@@ -290,6 +290,12 @@ static int __devinit pm860x_probe(struct i2c_client *client,
 		chip->companion_addr = pdata->companion_addr;
 		chip->companion = i2c_new_dummy(chip->client->adapter,
 						chip->companion_addr);
+		if (!chip->companion) {
+			dev_err(&client->dev,
+				"Failed to allocate I2C companion device\n");
+			kfree(chip);
+			return -ENODEV;
+		}
 		i2c_set_clientdata(chip->companion, chip);
 	}

drivers/mfd/Kconfig +3 -3

index f1391c2..b2b6916 100644
@@ -772,9 +772,6 @@ config MFD_INTEL_MSIC
 	  Passage) chip. This chip embeds audio, battery, GPIO, etc.
 	  devices used in Intel Medfield platforms.
 
-endmenu
-endif
-
 menu "Multimedia Capabilities Port drivers"
 	depends on ARCH_SA1100

@@ -797,3 +794,6 @@ config MCP_UCB1200_TS
 	depends on MCP_UCB1200 && INPUT
 
 endmenu
+
+endmenu
+endif

drivers/mfd/max8925-i2c.c +9 -0

index 0219115..90b450c 100644
@@ -156,9 +156,18 @@ static int __devinit max8925_probe(struct i2c_client *client,
 	mutex_init(&chip->io_lock);
 
 	chip->rtc = i2c_new_dummy(chip->i2c->adapter, RTC_I2C_ADDR);
+	if (!chip->rtc) {
+		dev_err(chip->dev, "Failed to allocate I2C device for RTC\n");
+		return -ENODEV;
+	}
 	i2c_set_clientdata(chip->rtc, chip);
 
 	chip->adc = i2c_new_dummy(chip->i2c->adapter, ADC_I2C_ADDR);
+	if (!chip->adc) {
+		dev_err(chip->dev, "Failed to allocate I2C device for ADC\n");
+		i2c_unregister_device(chip->rtc);
+		return -ENODEV;
+	}
 	i2c_set_clientdata(chip->adc, chip);
 
 	max8925_device_init(chip, pdata);

drivers/mfd/max8997.c +18 -0

index 5be53ae..1926a54 100644
@@ -148,10 +148,26 @@ static int max8997_i2c_probe(struct i2c_client *i2c,
 	mutex_init(&max8997->iolock);
 
 	max8997->rtc = i2c_new_dummy(i2c->adapter, I2C_ADDR_RTC);
+	if (!max8997->rtc) {
+		dev_err(max8997->dev, "Failed to allocate I2C device for RTC\n");
+		return -ENODEV;
+	}
 	i2c_set_clientdata(max8997->rtc, max8997);
+
 	max8997->haptic = i2c_new_dummy(i2c->adapter, I2C_ADDR_HAPTIC);
+	if (!max8997->haptic) {
+		dev_err(max8997->dev, "Failed to allocate I2C device for Haptic\n");
+		ret = -ENODEV;
+		goto err_i2c_haptic;
+	}
 	i2c_set_clientdata(max8997->haptic, max8997);
+
 	max8997->muic = i2c_new_dummy(i2c->adapter, I2C_ADDR_MUIC);
+	if (!max8997->muic) {
+		dev_err(max8997->dev, "Failed to allocate I2C device for MUIC\n");
+		ret = -ENODEV;
+		goto err_i2c_muic;
+	}
 	i2c_set_clientdata(max8997->muic, max8997);
 
 	pm_runtime_set_active(max8997->dev);

@@ -178,7 +194,9 @@ static int max8997_i2c_probe(struct i2c_client *i2c,
 err_mfd:
 	mfd_remove_devices(max8997->dev);
 	i2c_unregister_device(max8997->muic);
+err_i2c_muic:
 	i2c_unregister_device(max8997->haptic);
+err_i2c_haptic:
 	i2c_unregister_device(max8997->rtc);
 err:
 	kfree(max8997);

drivers/mfd/max8998.c +4 -0

index de4096a..2fa6a28 100644
@@ -152,6 +152,10 @@ static int max8998_i2c_probe(struct i2c_client *i2c,
 	mutex_init(&max8998->iolock);
 
 	max8998->rtc = i2c_new_dummy(i2c->adapter, RTC_I2C_ADDR);
+	if (!max8998->rtc) {
+		dev_err(&i2c->dev, "Failed to allocate I2C device for RTC\n");
+		return -ENODEV;
+	}
 	i2c_set_clientdata(max8998->rtc, max8998);
 
 	max8998_irq_init(max8998);

drivers/net/wireless/ath/ath9k/xmit.c +1 -1

index 2e88af1..a0ba5ac 100644
@@ -1390,7 +1390,7 @@ int ath_cabq_update(struct ath_softc *sc)
 	else if (sc->config.cabqReadytime > ATH9K_READY_TIME_HI_BOUND)
 		sc->config.cabqReadytime = ATH9K_READY_TIME_HI_BOUND;
 
-	qi.tqi_readyTime = (cur_conf->beacon_interval *
+	qi.tqi_readyTime = (TU_TO_USEC(cur_conf->beacon_interval) *
 			    sc->config.cabqReadytime) / 100;
 	ath_txq_update(sc, qnum, &qi);

drivers/net/wireless/b43/phy_n.c +7 -7

index b17d9b6..0490c7c 100644
@@ -3937,22 +3937,22 @@ static void b43_nphy_channel_setup(struct b43_wldev *dev,
 	struct b43_phy_n *nphy = dev->phy.n;
 
 	u16 old_band_5ghz;
-	u32 tmp32;
+	u16 tmp16;
 
 	old_band_5ghz =
 		b43_phy_read(dev, B43_NPHY_BANDCTL) & B43_NPHY_BANDCTL_5GHZ;
 	if (new_channel->band == IEEE80211_BAND_5GHZ && !old_band_5ghz) {
-		tmp32 = b43_read32(dev, B43_MMIO_PSM_PHY_HDR);
-		b43_write32(dev, B43_MMIO_PSM_PHY_HDR, tmp32 | 4);
+		tmp16 = b43_read16(dev, B43_MMIO_PSM_PHY_HDR);
+		b43_write16(dev, B43_MMIO_PSM_PHY_HDR, tmp16 | 4);
 		b43_phy_set(dev, B43_PHY_B_BBCFG, 0xC000);
-		b43_write32(dev, B43_MMIO_PSM_PHY_HDR, tmp32);
+		b43_write16(dev, B43_MMIO_PSM_PHY_HDR, tmp16);
 		b43_phy_set(dev, B43_NPHY_BANDCTL, B43_NPHY_BANDCTL_5GHZ);
 	} else if (new_channel->band == IEEE80211_BAND_2GHZ && old_band_5ghz) {
 		b43_phy_mask(dev, B43_NPHY_BANDCTL, ~B43_NPHY_BANDCTL_5GHZ);
-		tmp32 = b43_read32(dev, B43_MMIO_PSM_PHY_HDR);
-		b43_write32(dev, B43_MMIO_PSM_PHY_HDR, tmp32 | 4);
+		tmp16 = b43_read16(dev, B43_MMIO_PSM_PHY_HDR);
+		b43_write16(dev, B43_MMIO_PSM_PHY_HDR, tmp16 | 4);
 		b43_phy_mask(dev, B43_PHY_B_BBCFG, 0x3FFF);
-		b43_write32(dev, B43_MMIO_PSM_PHY_HDR, tmp32);
+		b43_write16(dev, B43_MMIO_PSM_PHY_HDR, tmp16);
 	}
 
 	b43_chantab_phy_upload(dev, e);

drivers/net/wireless/iwlwifi/iwl-agn.c +6 -2

index 94d35ad..4a36973 100644
@@ -246,13 +246,17 @@ static void iwl_bg_bt_runtime_config(struct work_struct *work)
 	struct iwl_priv *priv =
 		container_of(work, struct iwl_priv, bt_runtime_config);
 
+	mutex_lock(&priv->shrd->mutex);
 	if (test_bit(STATUS_EXIT_PENDING, &priv->shrd->status))
-		return;
+		goto out;
 
 	/* dont send host command if rf-kill is on */
 	if (!iwl_is_ready_rf(priv->shrd))
-		return;
+		goto out;
+
 	iwlagn_send_advance_bt_config(priv);
+out:
+	mutex_unlock(&priv->shrd->mutex);
 }
 
 static void iwl_bg_bt_full_concurrency(struct work_struct *work)

drivers/net/wireless/rtlwifi/rtl8192se/hw.c +19 -5

index c474486..503c160 100644
@@ -924,7 +924,7 @@ int rtl92se_hw_init(struct ieee80211_hw *hw)
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 	struct rtl_efuse *rtlefuse = rtl_efuse(rtl_priv(hw));
 	u8 tmp_byte = 0;
-
+	unsigned long flags;
 	bool rtstatus = true;
 	u8 tmp_u1b;
 	int err = false;

@@ -936,6 +936,16 @@ int rtl92se_hw_init(struct ieee80211_hw *hw)
 
 	rtlpci->being_init_adapter = true;
 
+	/* As this function can take a very long time (up to 350 ms)
+	 * and can be called with irqs disabled, reenable the irqs
+	 * to let the other devices continue being serviced.
+	 *
+	 * It is safe doing so since our own interrupts will only be enabled
+	 * in a subsequent step.
+	 */
+	local_save_flags(flags);
+	local_irq_enable();
+
 	rtlpriv->intf_ops->disable_aspm(hw);
 
 	/* 1. MAC Initialize */

@@ -969,7 +979,8 @@ int rtl92se_hw_init(struct ieee80211_hw *hw)
 	/* 3. Initialize MAC/PHY Config by MACPHY_reg.txt */
 	if (rtl92s_phy_mac_config(hw) != true) {
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG, ("MAC Config failed\n"));
-		return rtstatus;
+		err = rtstatus;
+		goto exit;
 	}
 
 	/* Make sure BB/RF write OK. We should prevent enter IPS. radio off. */

@@ -979,7 +990,8 @@ int rtl92se_hw_init(struct ieee80211_hw *hw)
 	/* 4. Initialize BB After MAC Config PHY_reg.txt, AGC_Tab.txt */
 	if (rtl92s_phy_bb_config(hw) != true) {
 		RT_TRACE(rtlpriv, COMP_INIT, DBG_EMERG, ("BB Config failed\n"));
-		return rtstatus;
+		err = rtstatus;
+		goto exit;
 	}
 
 	/* 5. Initiailze RF RAIO_A.txt RF RAIO_B.txt */

@@ -1015,7 +1027,8 @@ int rtl92se_hw_init(struct ieee80211_hw *hw)
 
 	if (rtl92s_phy_rf_config(hw) != true) {
 		RT_TRACE(rtlpriv, COMP_INIT, DBG_DMESG, ("RF Config failed\n"));
-		return rtstatus;
+		err = rtstatus;
+		goto exit;
 	}
 
 	/* After read predefined TXT, we must set BB/MAC/RF

@@ -1089,8 +1102,9 @@ int rtl92se_hw_init(struct ieee80211_hw *hw)
 
 	rtlpriv->cfg->ops->led_control(hw, LED_CTL_POWER_ON);
 	rtl92s_dm_init(hw);
+exit:
+	local_irq_restore(flags);
 	rtlpci->being_init_adapter = false;
-
 	return err;
 }

drivers/net/xen-netback/netback.c +2 -2

index 9a4626c..b2528f6 100644
@@ -346,8 +346,8 @@ static bool start_new_rx_buffer(int offset, unsigned long size, int head)
 	 * into multiple copies tend to give large frags their
 	 * own buffers as before.
 	 */
-	if ((offset + size > MAX_BUFFER_OFFSET) &&
-	    (size <= MAX_BUFFER_OFFSET) && offset && !head)
+	BUG_ON(size > MAX_BUFFER_OFFSET);
+	if ((offset + size > MAX_BUFFER_OFFSET) && offset && !head)
 		return true;
 
 	return false;

drivers/staging/serqt_usb2/serqt_usb2.c +1 -1

index c44e41a..c2731ca 100644
@@ -772,7 +772,7 @@ static int qt_startup(struct usb_serial *serial)
 		goto startup_error;
 	}
 
-	switch (serial->dev->descriptor.idProduct) {
+	switch (le16_to_cpu(serial->dev->descriptor.idProduct)) {
 	case QUATECH_DSU100:
 	case QUATECH_QSU100:
 	case QUATECH_ESU100A:

drivers/target/iscsi/iscsi_target.c +3 -1

index 4a88eea..ab5dd16 100644
@@ -2358,6 +2358,7 @@ static void iscsit_build_conn_drop_async_message(struct iscsi_conn *conn)
 {
 	struct iscsi_cmd *cmd;
 	struct iscsi_conn *conn_p;
+	bool found = false;
 
 	/*
 	 * Only send a Asynchronous Message on connections whos network

@@ -2366,11 +2367,12 @@ static void iscsit_build_conn_drop_async_message(struct iscsi_conn *conn)
 	list_for_each_entry(conn_p, &conn->sess->sess_conn_list, conn_list) {
 		if (conn_p->conn_state == TARG_CONN_STATE_LOGGED_IN) {
 			iscsit_inc_conn_usage_count(conn_p);
+			found = true;
 			break;
 		}
 	}
 
-	if (!conn_p)
+	if (!found)
 		return;
 
 	cmd = iscsit_allocate_cmd(conn_p, GFP_ATOMIC);

drivers/target/tcm_fc/tfc_sess.c +1 -0

index ab0a3fa..b328011 100644
@@ -72,6 +72,7 @@ static struct ft_tport *ft_tport_create(struct fc_lport *lport)
 
 	if (tport) {
 		tport->tpg = tpg;
+		tpg->tport = tport;
 		return tport;
 	}

drivers/tty/hvc/hvc_console.c +5 -1

index b6b2d18..7b97e7e 100644
@@ -31,6 +31,7 @@
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/major.h>
+#include <linux/atomic.h>
 #include <linux/sysrq.h>
 #include <linux/tty.h>
 #include <linux/tty_flip.h>

@@ -70,6 +71,9 @@ static struct task_struct *hvc_task;
 /* Picks up late kicks after list walk but before schedule() */
 static int hvc_kicked;
 
+/* hvc_init is triggered from hvc_alloc, i.e. only when actually used */
+static atomic_t hvc_needs_init __read_mostly = ATOMIC_INIT(-1);
+
 static int hvc_init(void);
 
 #ifdef CONFIG_MAGIC_SYSRQ

@@ -825,7 +829,7 @@ struct hvc_struct *hvc_alloc(uint32_t vtermno, int data,
 	int i;
 
 	/* We wait until a driver actually comes along */
-	if (!hvc_driver) {
+	if (atomic_inc_not_zero(&hvc_needs_init)) {
 		int err = hvc_init();
 		if (err)
 			return ERR_PTR(err);

drivers/tty/tty_io.c +15 -5

index 3f35e42..446df6b 100644
@@ -1222,9 +1222,9 @@ static void pty_line_name(struct tty_driver *driver, int index, char *p)
  *
  *	Locking: None
  */
-static void tty_line_name(struct tty_driver *driver, int index, char *p)
+static ssize_t tty_line_name(struct tty_driver *driver, int index, char *p)
 {
-	sprintf(p, "%s%d", driver->name, index + driver->name_base);
+	return sprintf(p, "%s%d", driver->name, index + driver->name_base);
 }
 
 /**

@@ -3321,9 +3321,19 @@ static ssize_t show_cons_active(struct device *dev,
 		if (i >= ARRAY_SIZE(cs))
 			break;
 	}
-	while (i--)
-		count += sprintf(buf + count, "%s%d%c",
-				 cs[i]->name, cs[i]->index, i ? ' ':'\n');
+	while (i--) {
+		int index = cs[i]->index;
+		struct tty_driver *drv = cs[i]->device(cs[i], &index);
+
+		/* don't resolve tty0 as some programs depend on it */
+		if (drv && (cs[i]->index > 0 || drv->major != TTY_MAJOR))
+			count += tty_line_name(drv, index, buf + count);
+		else
+			count += sprintf(buf + count, "%s%d",
+					 cs[i]->name, cs[i]->index);
+
+		count += sprintf(buf + count, "%c", i ? ' ':'\n');
+	}
 	console_unlock();
 
 	return count;

drivers/usb/dwc3/core.h +3 -3

index 4795c0c..ae2b763 100644
@@ -716,15 +716,15 @@ struct dwc3_event_depevt {
  *	12	- VndrDevTstRcved
  * @reserved15_12: Reserved, not used
  * @event_info: Information about this event
- * @reserved31_24: Reserved, not used
+ * @reserved31_25: Reserved, not used
  */
 struct dwc3_event_devt {
 	u32	one_bit:1;
 	u32	device_event:7;
 	u32	type:4;
 	u32	reserved15_12:4;
-	u32	event_info:8;
-	u32	reserved31_24:8;
+	u32	event_info:9;
+	u32	reserved31_25:7;
 } __packed;
 
 /**

drivers/usb/gadget/atmel_usba_udc.c +3 -2

index 271a9d8..b299c32 100644
@@ -1875,12 +1875,13 @@ static int atmel_usba_stop(struct usb_gadget_driver *driver)
 
 	driver->unbind(&udc->gadget);
 	udc->gadget.dev.driver = NULL;
-	udc->driver = NULL;
 
 	clk_disable(udc->hclk);
 	clk_disable(udc->pclk);
 
-	DBG(DBG_GADGET, "unregistered driver `%s'\n", driver->driver.name);
+	DBG(DBG_GADGET, "unregistered driver `%s'\n", udc->driver->driver.name);
+
+	udc->driver = NULL;
 
 	return 0;
 }

drivers/vhost/net.c +19 -1

index 5c58128..7ef84c1 100644
@@ -319,9 +319,13 @@ static int get_rx_bufs(struct vhost_virtqueue *vq,
 			r = -ENOBUFS;
 			goto err;
 		}
-		d = vhost_get_vq_desc(vq->dev, vq, vq->iov + seg,
+		r = vhost_get_vq_desc(vq->dev, vq, vq->iov + seg,
 				      ARRAY_SIZE(vq->iov) - seg, &out,
 				      &in, log, log_num);
+		if (unlikely(r < 0))
+			goto err;
+
+		d = r;
 		if (d == vq->num) {
 			r = 0;
 			goto err;

@@ -346,6 +350,12 @@ static int get_rx_bufs(struct vhost_virtqueue *vq,
 	*iovcount = seg;
 	if (unlikely(log))
 		*log_num = nlogs;
+
+	/* Detect overrun */
+	if (unlikely(datalen > 0)) {
+		r = UIO_MAXIOV + 1;
+		goto err;
+	}
 	return headcount;
 err:
 	vhost_discard_vq_desc(vq, headcount);

@@ -400,6 +410,14 @@ static void handle_rx(struct vhost_net *net)
 		/* On error, stop handling until the next kick. */
 		if (unlikely(headcount < 0))
 			break;
+		/* On overrun, truncate and discard */
+		if (unlikely(headcount > UIO_MAXIOV)) {
+			msg.msg_iovlen = 1;
+			err = sock->ops->recvmsg(NULL, sock, &msg,
+						 1, MSG_DONTWAIT | MSG_TRUNC);
+			pr_debug("Discarded rx packet: len %zd\n", sock_len);
+			continue;
+		}
 		/* OK, now we need to know about added descriptors. */
 		if (!headcount) {
 			if (unlikely(vhost_enable_notify(&net->dev, vq))) {

drivers/video/aty/mach64_accel.c +2 -1

index e45833c..182bd68 100644
@@ -4,6 +4,7 @@
  */
 
 #include <linux/delay.h>
+#include <asm/unaligned.h>
 #include <linux/fb.h>
 #include <video/mach64.h>
 #include "atyfb.h"

@@ -419,7 +420,7 @@ void atyfb_imageblit(struct fb_info *info, const struct fb_image *image)
 		u32 *pbitmap, dwords = (src_bytes + 3) / 4;
 		for (pbitmap = (u32*)(image->data); dwords; dwords--, pbitmap++) {
 			wait_for_fifo(1, par);
-			aty_st_le32(HOST_DATA0, le32_to_cpup(pbitmap), par);
+			aty_st_le32(HOST_DATA0, get_unaligned_le32(pbitmap), par);
 		}
 	}

drivers/video/aty/mach64_cursor.c +16 -6

index 46f72ed..4b87318 100644
@@ -5,6 +5,7 @@
 #include <linux/fb.h>
 #include <linux/init.h>
 #include <linux/string.h>
+#include "../fb_draw.h"
 
 #include <asm/io.h>

@@ -157,24 +158,33 @@ static int atyfb_cursor(struct fb_info *info, struct fb_cursor *cursor)
 
 	    for (i = 0; i < height; i++) {
 		for (j = 0; j < width; j++) {
+			u16 l = 0xaaaa;
 			b = *src++;
 			m = *msk++;
 			switch (cursor->rop) {
 			case ROP_XOR:
 			    // Upper 4 bits of mask data
-			    fb_writeb(cursor_bits_lookup[(b ^ m) >> 4], dst++);
+			    l = cursor_bits_lookup[(b ^ m) >> 4] |
 			    // Lower 4 bits of mask
-			    fb_writeb(cursor_bits_lookup[(b ^ m) & 0x0f],
-				      dst++);
+				    (cursor_bits_lookup[(b ^ m) & 0x0f] << 8);
 			    break;
 			case ROP_COPY:
 			    // Upper 4 bits of mask data
-			    fb_writeb(cursor_bits_lookup[(b & m) >> 4], dst++);
+			    l = cursor_bits_lookup[(b & m) >> 4] |
 			    // Lower 4 bits of mask
-			    fb_writeb(cursor_bits_lookup[(b & m) & 0x0f],
-				      dst++);
+				    (cursor_bits_lookup[(b & m) & 0x0f] << 8);
 			    break;
 			}
+			/*
+			 * If cursor size is not a multiple of 8 characters
+			 * we must pad it with transparent pattern (0xaaaa).
+			 */
+			if ((j + 1) * 8 > cursor->image.width) {
+				l = comp(l, 0xaaaa,
+				    (1 << ((cursor->image.width & 7) * 2)) - 1);
+			}
+			fb_writeb(l & 0xff, dst++);
+			fb_writeb(l >> 8, dst++);
 		}
 		dst += offset;
 	    }

drivers/video/cfbcopyarea.c +78 ~~-75~~

341 lines not on this page · raw message

drivers/video/matrox/matroxfb_accel.c +28 ~~-10~~

index 8335a6f..0d5cb85 100644
@@ -192,10 +192,18 @@ void matrox_cfbX_init(struct matrox_fb_info *minfo)
 	minfo->accel.m_dwg_rect = M_DWG_TRAP | M_DWG_SOLID | M_DWG_ARZERO | M_DWG_SGNZERO | M_DWG_SHIFTZERO;
 	if (isMilleniumII(minfo)) minfo->accel.m_dwg_rect |= M_DWG_TRANSC;
 	minfo->accel.m_opmode = mopmode;
+	minfo->accel.m_access = maccess;
+	minfo->accel.m_pitch = mpitch;
 }
 
 EXPORT_SYMBOL(matrox_cfbX_init);
 
+static void matrox_accel_restore_maccess(struct matrox_fb_info *minfo)
+{
+	mga_outl(M_MACCESS, minfo->accel.m_access);
+	mga_outl(M_PITCH, minfo->accel.m_pitch);
+}
+
 static void matrox_accel_bmove(struct matrox_fb_info *minfo, int vxres, int sy,
 			       int sx, int dy, int dx, int height, int width)
 {

@@ -207,7 +215,8 @@ static void matrox_accel_bmove(struct matrox_fb_info *minfo, int vxres, int sy,
 	CRITBEGIN
 
 	if ((dy < sy) || ((dy == sy) && (dx <= sx))) {
-		mga_fifo(2);
+		mga_fifo(4);
+		matrox_accel_restore_maccess(minfo);
 		mga_outl(M_DWGCTL, M_DWG_BITBLT | M_DWG_SHIFTZERO | M_DWG_SGNZERO |
 			 M_DWG_BFCOL | M_DWG_REPLACE);
 		mga_outl(M_AR5, vxres);

@@ -215,7 +224,8 @@ static void matrox_accel_bmove(struct matrox_fb_info *minfo, int vxres, int sy,
 		start = sy*vxres+sx+curr_ydstorg(minfo);
 		end = start+width;
 	} else {
-		mga_fifo(3);
+		mga_fifo(5);
+		matrox_accel_restore_maccess(minfo);
 		mga_outl(M_DWGCTL, M_DWG_BITBLT | M_DWG_SHIFTZERO | M_DWG_BFCOL | M_DWG_REPLACE);
 		mga_outl(M_SGN, 5);
 		mga_outl(M_AR5, -vxres);

@@ -224,7 +234,8 @@ static void matrox_accel_bmove(struct matrox_fb_info *minfo, int vxres, int sy,
 		start = end+width;
 		dy += height-1;
 	}
-	mga_fifo(4);
+	mga_fifo(6);
+	matrox_accel_restore_maccess(minfo);
 	mga_outl(M_AR0, end);
 	mga_outl(M_AR3, start);
 	mga_outl(M_FXBNDRY, ((dx+width)<<16) | dx);

@@ -246,7 +257,8 @@ static void matrox_accel_bmove_lin(struct matrox_fb_info *minfo, int vxres,
 	CRITBEGIN
 
 	if ((dy < sy) || ((dy == sy) && (dx <= sx))) {
-		mga_fifo(2);
+		mga_fifo(4);
+		matrox_accel_restore_maccess(minfo);
 		mga_outl(M_DWGCTL, M_DWG_BITBLT | M_DWG_SHIFTZERO | M_DWG_SGNZERO |
 			M_DWG_BFCOL | M_DWG_REPLACE);
 		mga_outl(M_AR5, vxres);

@@ -254,7 +266,8 @@ static void matrox_accel_bmove_lin(struct matrox_fb_info *minfo, int vxres,
 		start = sy*vxres+sx+curr_ydstorg(minfo);
 		end = start+width;
 	} else {
-		mga_fifo(3);
+		mga_fifo(5);
+		matrox_accel_restore_maccess(minfo);
 		mga_outl(M_DWGCTL, M_DWG_BITBLT | M_DWG_SHIFTZERO | M_DWG_BFCOL | M_DWG_REPLACE);
 		mga_outl(M_SGN, 5);
 		mga_outl(M_AR5, -vxres);

@@ -263,7 +276,8 @@ static void matrox_accel_bmove_lin(struct matrox_fb_info *minfo, int vxres,
 		start = end+width;
 		dy += height-1;
 	}
-	mga_fifo(5);
+	mga_fifo(7);
+	matrox_accel_restore_maccess(minfo);
 	mga_outl(M_AR0, end);
 	mga_outl(M_AR3, start);
 	mga_outl(M_FXBNDRY, ((dx+width)<<16) | dx);

@@ -298,7 +312,8 @@ static void matroxfb_accel_clear(struct matrox_fb_info *minfo, u_int32_t color,
 
 	CRITBEGIN
 
-	mga_fifo(5);
+	mga_fifo(7);
+	matrox_accel_restore_maccess(minfo);
 	mga_outl(M_DWGCTL, minfo->accel.m_dwg_rect | M_DWG_REPLACE);
 	mga_outl(M_FCOL, color);
 	mga_outl(M_FXBNDRY, ((sx + width) << 16) | sx);

@@ -341,7 +356,8 @@ static void matroxfb_cfb4_clear(struct matrox_fb_info *minfo, u_int32_t bgx,
 	width >>= 1;
 	sx >>= 1;
 	if (width) {
-		mga_fifo(5);
+		mga_fifo(7);
+		matrox_accel_restore_maccess(minfo);
 		mga_outl(M_DWGCTL, minfo->accel.m_dwg_rect | M_DWG_REPLACE2);
 		mga_outl(M_FCOL, bgx);
 		mga_outl(M_FXBNDRY, ((sx + width) << 16) | sx);

@@ -415,7 +431,8 @@ static void matroxfb_1bpp_imageblit(struct matrox_fb_info *minfo, u_int32_t fgx,
 
 	CRITBEGIN
 
-	mga_fifo(3);
+	mga_fifo(5);
+	matrox_accel_restore_maccess(minfo);
 	if (easy)
 		mga_outl(M_DWGCTL, M_DWG_ILOAD | M_DWG_SGNZERO | M_DWG_SHIFTZERO | M_DWG_BMONOWF | M_DWG_LINEAR | M_DWG_REPLACE);
 	else

@@ -425,7 +442,8 @@ static void matroxfb_1bpp_imageblit(struct matrox_fb_info *minfo, u_int32_t fgx,
 	fxbndry = ((xx + width - 1) << 16) | xx;
 	mmio = minfo->mmio.vbase;
 
-	mga_fifo(6);
+	mga_fifo(8);
+	matrox_accel_restore_maccess(minfo);
 	mga_writel(mmio, M_FXBNDRY, fxbndry);
 	mga_writel(mmio, M_AR0, ar0);
 	mga_writel(mmio, M_AR3, 0);

drivers/video/matrox/matroxfb_base.h +2 -0

index 11ed57b..556d96c 100644
@@ -307,6 +307,8 @@ struct matrox_accel_data {
 #endif
 	u_int32_t	m_dwg_rect;
 	u_int32_t	m_opmode;
+	u_int32_t	m_access;
+	u_int32_t	m_pitch;
 };
 
 struct v4l2_queryctrl;

drivers/video/tgafb.c +51 ~~-213~~

312 lines not on this page · raw message

drivers/virtio/virtio_balloon.c +6 -0

index 94fd738..28153fb 100644
@@ -271,6 +271,12 @@ static int balloon(void *_vballoon)
 		else if (diff < 0)
 			leak_balloon(vb, -diff);
 		update_balloon_size(vb);
+
+		/*
+		 * For large balloon changes, we could spend a lot of time
+		 * and always have work to do.  Be nice if preempt disabled.
+		 */
+		cond_resched();
 	}
 	return 0;
 }

drivers/w1/w1_netlink.c +13 ~~-12~~

index 40788c9..73705af 100644
@@ -54,28 +54,29 @@ static void w1_send_slave(struct w1_master *dev, u64 rn)
 	struct w1_netlink_msg *hdr = (struct w1_netlink_msg *)(msg + 1);
 	struct w1_netlink_cmd *cmd = (struct w1_netlink_cmd *)(hdr + 1);
 	int avail;
+	u64 *data;
 
 	/* update kernel slave list */
 	w1_slave_found(dev, rn);
 
 	avail = dev->priv_size - cmd->len;
 
-	if (avail > 8) {
-		u64 *data = (void *)(cmd + 1) + cmd->len;
+	if (avail < 8) {
+		msg->ack++;
+		cn_netlink_send(msg, 0, GFP_KERNEL);
 
-		*data = rn;
-		cmd->len += 8;
-		hdr->len += 8;
-		msg->len += 8;
-		return;
+		msg->len = sizeof(struct w1_netlink_msg) +
+			sizeof(struct w1_netlink_cmd);
+		hdr->len = sizeof(struct w1_netlink_cmd);
+		cmd->len = 0;
 	}
 
-	msg->ack++;
-	cn_netlink_send(msg, 0, GFP_KERNEL);
+	data = (void *)(cmd + 1) + cmd->len;
 
-	msg->len = sizeof(struct w1_netlink_msg) + sizeof(struct w1_netlink_cmd);
-	hdr->len = sizeof(struct w1_netlink_cmd);
-	cmd->len = 0;
+	*data = rn;
+	cmd->len += 8;
+	hdr->len += 8;
+	msg->len += 8;
 }
 
 static int w1_process_search_command(struct w1_master *dev, struct cn_msg *msg,

fs/btrfs/disk-io.c +4 -0

index 6b2a724..cfdf6fe 100644
@@ -2731,6 +2731,8 @@ static int barrier_all_devices(struct btrfs_fs_info *info)
 	/* send down all the barriers */
 	head = &info->fs_devices->devices;
 	list_for_each_entry_rcu(dev, head, dev_list) {
+		if (dev->missing)
+			continue;
 		if (!dev->bdev) {
 			errors++;
 			continue;

@@ -2745,6 +2747,8 @@ static int barrier_all_devices(struct btrfs_fs_info *info)
 
 	/* wait for all the barriers */
 	list_for_each_entry_rcu(dev, head, dev_list) {
+		if (dev->missing)
+			continue;
 		if (!dev->bdev) {
 			errors++;
 			continue;

fs/btrfs/transaction.c +4 ~~-10~~

index 81376d9..292e847 100644
@@ -460,7 +460,8 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 	struct btrfs_fs_info *info = root->fs_info;
 	int count = 0;
 
-	if (--trans->use_count) {
+	if (trans->use_count > 1) {
+		trans->use_count--;
 		trans->block_rsv = trans->orig_rsv;
 		return 0;
 	}

@@ -494,17 +495,10 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 	}
 
 	if (lock && cur_trans->blocked && !cur_trans->in_commit) {
-		if (throttle) {
-			/*
-			 * We may race with somebody else here so end up having
-			 * to call end_transaction on ourselves again, so inc
-			 * our use_count.
-			 */
-			trans->use_count++;
+		if (throttle)
 			return btrfs_commit_transaction(trans, root);
-		} else {
+		else
 			wake_up_process(info->transaction_kthread);
-		}
 	}
 
 	WARN_ON(cur_trans != info->running_transaction);

fs/ext4/extents.c +21 -0

index bf35fe0..834d9a1 100644
@@ -2372,6 +2372,27 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 	ex_ee_block = le32_to_cpu(ex->ee_block);
 	ex_ee_len = ext4_ext_get_actual_len(ex);
 
+	/*
+	 * If we're starting with an extent other than the last one in the
+	 * node, we need to see if it shares a cluster with the extent to
+	 * the right (towards the end of the file). If its leftmost cluster
+	 * is this extent's rightmost cluster and it is not cluster aligned,
+	 * we'll mark it as a partial that is not to be deallocated.
+	 */
+
+	if (ex != EXT_LAST_EXTENT(eh)) {
+		ext4_fsblk_t current_pblk, right_pblk;
+		long long current_cluster, right_cluster;
+
+		current_pblk = ext4_ext_pblock(ex) + ex_ee_len - 1;
+		current_cluster = (long long)EXT4_B2C(sbi, current_pblk);
+		right_pblk = ext4_ext_pblock(ex + 1);
+		right_cluster = (long long)EXT4_B2C(sbi, right_pblk);
+		if (current_cluster == right_cluster &&
+			EXT4_PBLK_COFF(sbi, right_pblk))
+			*partial_cluster = -right_cluster;
+	}
+
 	trace_ext4_ext_rm_leaf(inode, start, ex, *partial_cluster);
 
 	while (ex >= EXT_FIRST_EXTENT(eh) &&

fs/jffs2/compr_rtime.c +2 -2

index 16a5047..406d9cc 100644
@@ -33,7 +33,7 @@ static int jffs2_rtime_compress(unsigned char *data_in,
 				unsigned char *cpage_out,
 				uint32_t *sourcelen, uint32_t *dstlen)
 {
-	short positions[256];
+	unsigned short positions[256];
 	int outpos = 0;
 	int pos=0;

@@ -74,7 +74,7 @@ static int jffs2_rtime_decompress(unsigned char *data_in,
 				  unsigned char *cpage_out,
 				  uint32_t srclen, uint32_t destlen)
 {
-	short positions[256];
+	unsigned short positions[256];
 	int outpos = 0;
 	int pos=0;

fs/jffs2/nodelist.h +1 -1

index e4619b0..fa35ff7 100644
@@ -231,7 +231,7 @@ struct jffs2_tmp_dnode_info
 	uint32_t version;
 	uint32_t data_crc;
 	uint32_t partial_crc;
-	uint16_t csize;
+	uint32_t csize;
 	uint16_t overlapped;
 };

fs/jffs2/nodemgmt.c +10 -4

index 694aa5b..145ba39 100644
@@ -128,6 +128,7 @@ int jffs2_reserve_space(struct jffs2_sb_info *c, uint32_t minsize,
 					spin_unlock(&c->erase_completion_lock);
 
 					schedule();
+					remove_wait_queue(&c->erase_wait, &wait);
 				} else
 					spin_unlock(&c->erase_completion_lock);
 			} else if (ret)

@@ -158,19 +159,24 @@ int jffs2_reserve_space(struct jffs2_sb_info *c, uint32_t minsize,
 int jffs2_reserve_space_gc(struct jffs2_sb_info *c, uint32_t minsize,
 			   uint32_t *len, uint32_t sumsize)
 {
-	int ret = -EAGAIN;
+	int ret;
 	minsize = PAD(minsize);
 
 	D1(printk(KERN_DEBUG "jffs2_reserve_space_gc(): Requested 0x%x bytes\n", minsize));
 
-	spin_lock(&c->erase_completion_lock);
-	while(ret == -EAGAIN) {
+	while (true) {
+		spin_lock(&c->erase_completion_lock);
 		ret = jffs2_do_reserve_space(c, minsize, len, sumsize);
 		if (ret) {
 			D1(printk(KERN_DEBUG "jffs2_reserve_space_gc: looping, ret is %d\n", ret));
 		}
+		spin_unlock(&c->erase_completion_lock);
+
+		if (ret == -EAGAIN)
+			cond_resched();
+		else
+			break;
 	}
-	spin_unlock(&c->erase_completion_lock);
 	if (!ret)
 		ret = jffs2_prealloc_raw_node_refs(c, c->nextblock, 1);

fs/nfsd/nfs4proc.c +8 -1

index e065497..315a1ba 100644
@@ -1224,6 +1224,12 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
 		/* If op is non-idempotent */
 		if (opdesc->op_flags & OP_MODIFIES_SOMETHING) {
 			plen = opdesc->op_rsize_bop(rqstp, op);
+			/*
+			 * If there's still another operation, make sure
+			 * we'll have space to at least encode an error:
+			 */
+			if (resp->opcnt < args->opcnt)
+				plen += COMPOUND_ERR_SLACK_SPACE;
 			op->status = nfsd4_check_resp_size(resp, plen);
 		}

@@ -1381,7 +1387,8 @@ static inline u32 nfsd4_setattr_rsize(struct svc_rqst *rqstp, struct nfsd4_op *o
 
 static inline u32 nfsd4_setclientid_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
 {
-	return (op_encode_hdr_size + 2 + 1024) * sizeof(__be32);
+	return (op_encode_hdr_size + 2 + XDR_QUADLEN(NFS4_VERIFIER_SIZE)) *
+								sizeof(__be32);
 }
 
 static inline u32 nfsd4_write_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)

fs/nfsd/nfs4xdr.c +2 -0

index ade5316..4835b90 100644
@@ -2413,6 +2413,8 @@ out_acl:
 		WRITE64(stat.ino);
 	}
 	if (bmval2 & FATTR4_WORD2_SUPPATTR_EXCLCREAT) {
+		if ((buflen -= 16) < 0)
+			goto out_resource;
 		WRITE32(3);
 		WRITE32(NFSD_SUPPATTR_EXCLCREAT_WORD0);
 		WRITE32(NFSD_SUPPATTR_EXCLCREAT_WORD1);

fs/nfsd/vfs.c +9 -0

index 6a66fc0..11e1888 100644
@@ -406,6 +406,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 	int		ftype = 0;
 	__be32		err;
 	int		host_err;
+	bool		get_write_count;
 	int		size_change = 0;
 
 	if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE))

@@ -413,10 +414,18 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 	if (iap->ia_valid & ATTR_SIZE)
 		ftype = S_IFREG;
 
+	/* Callers that do fh_verify should do the fh_want_write: */
+	get_write_count = !fhp->fh_dentry;
+
 	/* Get inode */
 	err = fh_verify(rqstp, fhp, ftype, accmode);
 	if (err)
 		goto out;
+	if (get_write_count) {
+		host_err = fh_want_write(fhp);
+		if (host_err)
+			return nfserrno(host_err);
+	}
 
 	dentry = fhp->fh_dentry;
 	inode = dentry->d_inode;

fs/nfsd/vfs.h +10 -0

index 85d4d42..c7fe962 100644
@@ -108,4 +108,14 @@ struct posix_acl *nfsd_get_posix_acl(struct svc_fh *, int);
 int nfsd_set_posix_acl(struct svc_fh *, int, struct posix_acl *);
 #endif
 
+static inline int fh_want_write(struct svc_fh *fh)
+{
+	return mnt_want_write(fh->fh_export->ex_path.mnt);
+}
+
+static inline void fh_drop_write(struct svc_fh *fh)
+{
+	mnt_drop_write(fh->fh_export->ex_path.mnt);
+}
+
 #endif /* LINUX_NFSD_VFS_H */

fs/ocfs2/buffer_head_io.c +0 -2

index 5d18ad1..4f66e00 100644
@@ -90,7 +90,6 @@ int ocfs2_write_block(struct ocfs2_super *osb, struct buffer_head *bh,
 		 * information for this bh as it's not marked locally
 		 * uptodate. */
 		ret = -EIO;
-		put_bh(bh);
 		mlog_errno(ret);
 	}

@@ -420,7 +419,6 @@ int ocfs2_write_super_or_backup(struct ocfs2_super *osb,
 
 	if (!buffer_uptodate(bh)) {
 		ret = -EIO;
-		put_bh(bh);
 		mlog_errno(ret);
 	}

fs/ocfs2/dlm/dlmrecovery.c +21 -8

index 01ebfd0..d15b071 100644
@@ -540,7 +540,10 @@ master_here:
 		/* success!  see if any other nodes need recovery */
 		mlog(0, "DONE mastering recovery of %s:%u here(this=%u)!\n",
 		     dlm->name, dlm->reco.dead_node, dlm->node_num);
-		dlm_reset_recovery(dlm);
+		spin_lock(&dlm->spinlock);
+		__dlm_reset_recovery(dlm);
+		dlm->reco.state &= ~DLM_RECO_STATE_FINALIZE;
+		spin_unlock(&dlm->spinlock);
 	}
 	dlm_end_recovery(dlm);

@@ -698,6 +701,14 @@ static int dlm_remaster_locks(struct dlm_ctxt *dlm, u8 dead_node)
 		if (all_nodes_done) {
 			int ret;
 
+			/* Set this flag on recovery master to avoid
+			 * a new recovery for another dead node start
+			 * before the recovery is not done. That may
+			 * cause recovery hung.*/
+			spin_lock(&dlm->spinlock);
+			dlm->reco.state |= DLM_RECO_STATE_FINALIZE;
+			spin_unlock(&dlm->spinlock);
+
 			/* all nodes are now in DLM_RECO_NODE_DATA_DONE state
 	 		 * just send a finalize message to everyone and
 	 		 * clean up */

@@ -1752,13 +1763,13 @@ static int dlm_process_recovery_data(struct dlm_ctxt *dlm,
 				     struct dlm_migratable_lockres *mres)
 {
 	struct dlm_migratable_lock *ml;
-	struct list_head *queue;
+	struct list_head *queue, *iter;
 	struct list_head *tmpq = NULL;
 	struct dlm_lock *newlock = NULL;
 	struct dlm_lockstatus *lksb = NULL;
 	int ret = 0;
 	int i, j, bad;
-	struct dlm_lock *lock = NULL;
+	struct dlm_lock *lock;
 	u8 from = O2NM_MAX_NODES;
 	unsigned int added = 0;
 	__be64 c;

@@ -1793,14 +1804,16 @@ static int dlm_process_recovery_data(struct dlm_ctxt *dlm,
 			/* MIGRATION ONLY! */
 			BUG_ON(!(mres->flags & DLM_MRES_MIGRATION));
 
+			lock = NULL;
 			spin_lock(&res->spinlock);
 			for (j = DLM_GRANTED_LIST; j <= DLM_BLOCKED_LIST; j++) {
 				tmpq = dlm_list_idx_to_ptr(res, j);
-				list_for_each_entry(lock, tmpq, list) {
-					if (lock->ml.cookie != ml->cookie)
-						lock = NULL;
-					else
+				list_for_each(iter, tmpq) {
+					lock = list_entry(iter,
+						  struct dlm_lock, list);
+					if (lock->ml.cookie == ml->cookie)
 						break;
+					lock = NULL;
 				}
 				if (lock)
 					break;

@@ -2870,8 +2883,8 @@ int dlm_finalize_reco_handler(struct o2net_msg *msg, u32 len, void *data,
 				BUG();
 			}
 			dlm->reco.state &= ~DLM_RECO_STATE_FINALIZE;
+			__dlm_reset_recovery(dlm);
 			spin_unlock(&dlm->spinlock);
-			dlm_reset_recovery(dlm);
 			dlm_kick_recovery_thread(dlm);
 			break;
 		default:

fs/reiserfs/dir.c +4 -2

index 133e935..8048eea 100644
@@ -128,6 +128,7 @@ int reiserfs_readdir_dentry(struct dentry *dentry, void *dirent,
 				char *d_name;
 				off_t d_off;
 				ino_t d_ino;
+				loff_t cur_pos = deh_offset(deh);
 
 				if (!de_visible(deh))
 					/* it is hidden entry */

@@ -200,8 +201,9 @@ int reiserfs_readdir_dentry(struct dentry *dentry, void *dirent,
 				if (local_buf != small_buf) {
 					kfree(local_buf);
 				}
-				// next entry should be looked for with such offset
-				next_pos = deh_offset(deh) + 1;
+
+				/* deh_offset(deh) may be invalid now. */
+				next_pos = cur_pos + 1;
 
 				if (item_moved(&tmp_ih, &path_to_entry)) {
 					goto research;

include/linux/sched.h +19 -1

index c17fdfb..cb34ff4 100644
@@ -1690,6 +1690,24 @@ static inline pid_t task_tgid_vnr(struct task_struct *tsk)
 }
 
 
+static int pid_alive(const struct task_struct *p);
+static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns)
+{
+	pid_t pid = 0;
+
+	rcu_read_lock();
+	if (pid_alive(tsk))
+		pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns);
+	rcu_read_unlock();
+
+	return pid;
+}
+
+static inline pid_t task_ppid_nr(const struct task_struct *tsk)
+{
+	return task_ppid_nr_ns(tsk, &init_pid_ns);
+}
+
 static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk,
 					struct pid_namespace *ns)
 {

@@ -1727,7 +1745,7 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk)
  * If pid_alive fails, then pointers within the task structure
  * can be stale and must not be dereferenced.
  */
-static inline int pid_alive(struct task_struct *p)
+static inline int pid_alive(const struct task_struct *p)
 {
 	return p->pids[PIDTYPE_PID].pid != NULL;
 }

include/trace/events/block.h +30 -3

index 05c5e61..048e265 100644
@@ -81,6 +81,7 @@ DEFINE_EVENT(block_rq_with_error, block_rq_requeue,
  * block_rq_complete - block IO operation completed by device driver
  * @q: queue containing the block operation request
  * @rq: block operations request
+ * @nr_bytes: number of completed bytes
  *
  * The block_rq_complete tracepoint event indicates that some portion
  * of operation request has been completed by the device driver.  If

@@ -88,11 +89,37 @@ DEFINE_EVENT(block_rq_with_error, block_rq_requeue,
  * do for the request. If @rq->bio is non-NULL then there is
  * additional work required to complete the request.
  */
-DEFINE_EVENT(block_rq_with_error, block_rq_complete,
+TRACE_EVENT(block_rq_complete,
 
-	TP_PROTO(struct request_queue *q, struct request *rq),
+	TP_PROTO(struct request_queue *q, struct request *rq,
+		 unsigned int nr_bytes),
 
-	TP_ARGS(q, rq)
+	TP_ARGS(q, rq, nr_bytes),
+
+	TP_STRUCT__entry(
+		__field(  dev_t,	dev			)
+		__field(  sector_t,	sector			)
+		__field(  unsigned int,	nr_sector		)
+		__field(  int,		errors			)
+		__array(  char,		rwbs,	RWBS_LEN	)
+		__dynamic_array( char,	cmd,	blk_cmd_buf_len(rq)	)
+	),
+
+	TP_fast_assign(
+		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+		__entry->sector    = blk_rq_pos(rq);
+		__entry->nr_sector = nr_bytes >> 9;
+		__entry->errors    = rq->errors;
+
+		blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, nr_bytes);
+		blk_dump_cmd(__get_str(cmd), rq);
+	),
+
+	TP_printk("%d,%d %s (%s) %llu + %u [%d]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rwbs, __get_str(cmd),
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->errors)
 );
 
 DECLARE_EVENT_CLASS(block_rq,

kernel/auditsc.c +2 -2

index 47b7fc1..aeac7cc 100644
@@ -473,7 +473,7 @@ static int audit_filter_rules(struct task_struct *tsk,
 		case AUDIT_PPID:
 			if (ctx) {
 				if (!ctx->ppid)
-					ctx->ppid = sys_getppid();
+					ctx->ppid = task_ppid_nr(tsk);
 				result = audit_comparator(ctx->ppid, f->op, f->val);
 			}
 			break;

@@ -1335,7 +1335,7 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 	/* tsk == current */
 	context->pid = tsk->pid;
 	if (!context->ppid)
-		context->ppid = sys_getppid();
+		context->ppid = task_ppid_nr(tsk);
 	cred = current_cred();
 	context->uid   = cred->uid;
 	context->gid   = cred->gid;

kernel/exit.c +11 -4

index 234e152..fde15f9 100644
@@ -734,9 +734,6 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p,
 				struct list_head *dead)
 {
 	list_move_tail(&p->sibling, &p->real_parent->children);
-
-	if (p->exit_state == EXIT_DEAD)
-		return;
 	/*
 	 * If this is a threaded reparent there is no need to
 	 * notify anyone anything has happened.

@@ -744,9 +741,19 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p,
 	if (same_thread_group(p->real_parent, father))
 		return;
 
-	/* We don't want people slaying init.  */
+	/*
+	 * We don't want people slaying init.
+	 *
+	 * Note: we do this even if it is EXIT_DEAD, wait_task_zombie()
+	 * can change ->exit_state to EXIT_ZOMBIE. If this is the final
+	 * state, do_notify_parent() was already called and ->exit_signal
+	 * doesn't matter.
+	 */
 	p->exit_signal = SIGCHLD;
 
+	if (p->exit_state == EXIT_DEAD)
+		return;
+
 	/* If it has exited notify the new parent about this child's death. */
 	if (!p->ptrace &&
 	    p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) {

kernel/trace/blktrace.c +11 -9

index 16fc34a..92cac05 100644
@@ -699,6 +699,7 @@ void blk_trace_shutdown(struct request_queue *q)
  * blk_add_trace_rq - Add a trace for a request oriented action
  * @q:		queue the io is for
  * @rq:		the source request
+ * @nr_bytes:	number of completed bytes
  * @what:	the action
  *
  * Description:

@@ -706,7 +707,7 @@ void blk_trace_shutdown(struct request_queue *q)
  *
  **/
 static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
-			     u32 what)
+			     unsigned int nr_bytes, u32 what)
 {
 	struct blk_trace *bt = q->blk_trace;

@@ -715,11 +716,11 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
 
 	if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
 		what |= BLK_TC_ACT(BLK_TC_PC);
-		__blk_add_trace(bt, 0, blk_rq_bytes(rq), rq->cmd_flags,
+		__blk_add_trace(bt, 0, nr_bytes, rq->cmd_flags,
 				what, rq->errors, rq->cmd_len, rq->cmd);
 	} else  {
 		what |= BLK_TC_ACT(BLK_TC_FS);
-		__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
+		__blk_add_trace(bt, blk_rq_pos(rq), nr_bytes,
 				rq->cmd_flags, what, rq->errors, 0, NULL);
 	}
 }

@@ -727,33 +728,34 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
 static void blk_add_trace_rq_abort(void *ignore,
 				   struct request_queue *q, struct request *rq)
 {
-	blk_add_trace_rq(q, rq, BLK_TA_ABORT);
+	blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_ABORT);
 }
 
 static void blk_add_trace_rq_insert(void *ignore,
 				    struct request_queue *q, struct request *rq)
 {
-	blk_add_trace_rq(q, rq, BLK_TA_INSERT);
+	blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_INSERT);
 }
 
 static void blk_add_trace_rq_issue(void *ignore,
 				   struct request_queue *q, struct request *rq)
 {
-	blk_add_trace_rq(q, rq, BLK_TA_ISSUE);
+	blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_ISSUE);
 }
 
 static void blk_add_trace_rq_requeue(void *ignore,
 				     struct request_queue *q,
 				     struct request *rq)
 {
-	blk_add_trace_rq(q, rq, BLK_TA_REQUEUE);
+	blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_REQUEUE);
 }
 
 static void blk_add_trace_rq_complete(void *ignore,
 				      struct request_queue *q,
-				      struct request *rq)
+				      struct request *rq,
+				      unsigned int nr_bytes)
 {
-	blk_add_trace_rq(q, rq, BLK_TA_COMPLETE);
+	blk_add_trace_rq(q, rq, nr_bytes, BLK_TA_COMPLETE);
 }
 
 /**

lib/nlattr.c +8 -2

index a8408b6..190ae10 100644
@@ -299,9 +299,15 @@ int nla_memcmp(const struct nlattr *nla, const void *data,
  */
 int nla_strcmp(const struct nlattr *nla, const char *str)
 {
-	int len = strlen(str) + 1;
-	int d = nla_len(nla) - len;
+	int len = strlen(str);
+	char *buf = nla_data(nla);
+	int attrlen = nla_len(nla);
+	int d;
 
+	if (attrlen > 0 && buf[attrlen - 1] == '\0')
+		attrlen--;
+
+	d = attrlen - len;
 	if (d == 0)
 		d = memcmp(nla_data(nla), str, len);

lib/percpu_counter.c +1 -1

index f8a3f1a..33459e0 100644
@@ -166,7 +166,7 @@ static int __cpuinit percpu_counter_hotcpu_callback(struct notifier_block *nb,
 	struct percpu_counter *fbc;
 
 	compute_batch_value();
-	if (action != CPU_DEAD)
+	if (action != CPU_DEAD && action != CPU_DEAD_FROZEN)
 		return NOTIFY_OK;
 
 	cpu = (unsigned long)hcpu;

mm/hugetlb.c +1 -0

index 3a5aae2..d399f5f 100644
@@ -1447,6 +1447,7 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count,
 	while (min_count < persistent_huge_pages(h)) {
 		if (!free_pool_huge_page(h, nodes_allowed, 0))
 			break;
+		cond_resched_lock(&hugetlb_lock);
 	}
 	while (count < persistent_huge_pages(h)) {
 		if (!adjust_pool_surplus(h, nodes_allowed, 1))

mm/mlock.c +2 -0

index 4f4f53b..39b3a7d 100644
@@ -78,6 +78,7 @@ void __clear_page_mlock(struct page *page)
  */
 void mlock_vma_page(struct page *page)
 {
+	/* Serialize with page migration */
 	BUG_ON(!PageLocked(page));
 
 	if (!TestSetPageMlocked(page)) {

@@ -105,6 +106,7 @@ void mlock_vma_page(struct page *page)
  */
 void munlock_vma_page(struct page *page)
 {
+	/* For try_to_munlock() and to serialize with page migration */
 	BUG_ON(!PageLocked(page));
 
 	if (TestClearPageMlocked(page)) {

mm/rmap.c +12 -2

index 52a2f36..9ac405b 100644
@@ -1385,9 +1385,19 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount,
 		BUG_ON(!page || PageAnon(page));
 
 		if (locked_vma) {
-			mlock_vma_page(page);   /* no-op if already mlocked */
-			if (page == check_page)
+			if (page == check_page) {
+				/* we know we have check_page locked */
+				mlock_vma_page(page);
 				ret = SWAP_MLOCK;
+			} else if (trylock_page(page)) {
+				/*
+				 * If we can lock the page, perform mlock.
+				 * Otherwise leave the page alone, it will be
+				 * eventually encountered again later.
+				 */
+				mlock_vma_page(page);
+				unlock_page(page);
+			}
 			continue;	/* don't unmap */
 		}

net/8021q/vlan_dev.c +3 -0

index 48a62d8..c43a788 100644
@@ -529,6 +529,9 @@ static int vlan_passthru_hard_header(struct sk_buff *skb, struct net_device *dev
 {
 	struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
 
+	if (saddr == NULL)
+		saddr = dev->dev_addr;
+
 	return dev_hard_header(skb, real_dev, type, daddr, saddr, len);
 }

net/bridge/br_multicast.c +6 -0

index 2157984..398a297 100644
@@ -1138,6 +1138,12 @@ static int br_ip6_multicast_query(struct net_bridge *br,
 
 	br_multicast_query_received(br, port, !ipv6_addr_any(&ip6h->saddr));
 
+	/* RFC2710+RFC3810 (MLDv1+MLDv2) require link-local source addresses */
+	if (!(ipv6_addr_type(&ip6h->saddr) & IPV6_ADDR_LINKLOCAL)) {
+		err = -EINVAL;
+		goto out;
+	}
+
 	if (skb->len == sizeof(*mld)) {
 		if (!pskb_may_pull(skb, sizeof(*mld))) {
 			err = -EINVAL;

net/ipv6/addrconf.c +4 -1

index 5d41293..b9edff0 100644
@@ -900,8 +900,11 @@ retry:
 	 * Lifetime is greater than REGEN_ADVANCE time units.  In particular,
 	 * an implementation must not create a temporary address with a zero
 	 * Preferred Lifetime.
+	 * Use age calculation as in addrconf_verify to avoid unnecessary
+	 * temporary addresses being generated.
 	 */
-	if (tmp_prefered_lft <= regen_advance) {
+	age = (now - tmp_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ;
+	if (tmp_prefered_lft <= regen_advance + age) {
 		in6_ifa_put(ifp);
 		in6_dev_put(idev);
 		ret = -1;

net/ipv6/icmp.c +1 -1

index d505453..ceced67 100644
@@ -499,7 +499,7 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 			      np->tclass, NULL, &fl6, (struct rt6_info*)dst,
 			      MSG_DONTWAIT, np->dontfrag);
 	if (err) {
-		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTERRORS);
+		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS);
 		ip6_flush_pending_frames(sk);
 	} else {
 		err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr,

net/ipv6/ip6_output.c +8 ~~-10~~

index cd4b529..7871cc6 100644
@@ -1191,21 +1191,19 @@ static void ip6_append_data_mtu(unsigned int *mtu,
 				unsigned int fragheaderlen,
 				struct sk_buff *skb,
 				struct rt6_info *rt,
-				bool pmtuprobe)
+				unsigned int orig_mtu)
 {
 	if (!(rt->dst.flags & DST_XFRM_TUNNEL)) {
 		if (skb == NULL) {
 			/* first fragment, reserve header_len */
-			*mtu = *mtu - rt->dst.header_len;
+			*mtu = orig_mtu - rt->dst.header_len;
 
 		} else {
 			/*
 			 * this fragment is not first, the headers
 			 * space is regarded as data space.
 			 */
-			*mtu = min(*mtu, pmtuprobe ?
-				   rt->dst.dev->mtu :
-				   dst_mtu(rt->dst.path));
+			*mtu = orig_mtu;
 		}
 		*maxfraglen = ((*mtu - fragheaderlen) & ~7)
 			      + fragheaderlen - sizeof(struct frag_hdr);

@@ -1222,7 +1220,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct inet_cork *cork;
 	struct sk_buff *skb, *skb_prev = NULL;
-	unsigned int maxfraglen, fragheaderlen, mtu;
+	unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu;
 	int exthdrlen;
 	int dst_exthdrlen;
 	int hh_len;

@@ -1307,6 +1305,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 		dst_exthdrlen = 0;
 		mtu = cork->fragsize;
 	}
+	orig_mtu = mtu;
 
 	hh_len = LL_RESERVED_SPACE(rt->dst.dev);

@@ -1389,8 +1388,7 @@ alloc_new_skb:
 			if (skb == NULL || skb_prev == NULL)
 				ip6_append_data_mtu(&mtu, &maxfraglen,
 						    fragheaderlen, skb, rt,
-						    np->pmtudisc ==
-						    IPV6_PMTUDISC_PROBE);
+						    orig_mtu);
 
 			skb_prev = skb;

@@ -1660,8 +1658,8 @@ int ip6_push_pending_frames(struct sock *sk)
 	if (proto == IPPROTO_ICMPV6) {
 		struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
 
-		ICMP6MSGOUT_INC_STATS_BH(net, idev, icmp6_hdr(skb)->icmp6_type);
-		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS);
+		ICMP6MSGOUT_INC_STATS(net, idev, icmp6_hdr(skb)->icmp6_type);
+		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
 	}
 
 	err = ip6_local_out(skb);

net/ipv6/mcast.c +6 -5

index d20a9be..4f12b66 100644
@@ -1435,11 +1435,12 @@ static void mld_sendpack(struct sk_buff *skb)
 		      dst_output);
 out:
 	if (!err) {
-		ICMP6MSGOUT_INC_STATS_BH(net, idev, ICMPV6_MLD2_REPORT);
-		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS);
-		IP6_UPD_PO_STATS_BH(net, idev, IPSTATS_MIB_OUTMCAST, payload_len);
-	} else
-		IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_OUTDISCARDS);
+		ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT);
+		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
+		IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, payload_len);
+	} else {
+		IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
+	}
 
 	rcu_read_unlock();
 	return;

net/ipv6/route.c +1 -1

index 9a4f437..39e11f9 100644
@@ -1250,7 +1250,7 @@ int ip6_route_add(struct fib6_config *cfg)
 		goto out;
 	}
 
-	rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, NULL, DST_NOCOUNT);
+	rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, NULL, (cfg->fc_flags & RTF_ADDRCONF) ? 0 : DST_NOCOUNT);
 
 	if (rt == NULL) {
 		err = -ENOMEM;

net/rds/iw.c +2 -1

index 7826d46..5899356 100644
@@ -239,7 +239,8 @@ static int rds_iw_laddr_check(__be32 addr)
 	ret = rdma_bind_addr(cm_id, (struct sockaddr *)&sin);
 	/* due to this, we will claim to support IB devices unless we
 	   check node_type. */
-	if (ret || cm_id->device->node_type != RDMA_NODE_RNIC)
+	if (ret || !cm_id->device ||
+	    cm_id->device->node_type != RDMA_NODE_RNIC)
 		ret = -EADDRNOTAVAIL;
 
 	rdsdebug("addr %pI4 ret %d node type %d\n",

net/sctp/sm_make_chunk.c +2 -2

index 0121e0a..c95a3f2 100644
@@ -1366,8 +1366,8 @@ static void sctp_chunk_destroy(struct sctp_chunk *chunk)
 	BUG_ON(!list_empty(&chunk->list));
 	list_del_init(&chunk->transmitted_list);
 
-	/* Free the chunk skb data and the SCTP_chunk stub itself. */
-	dev_kfree_skb(chunk->skb);
+	consume_skb(chunk->skb);
+	consume_skb(chunk->auth_chunk);
 
 	SCTP_DBG_OBJCNT_DEC(chunk);
 	kmem_cache_free(sctp_chunk_cachep, chunk);

net/sctp/sm_statefuns.c +0 -5

index f131caf..5ac33b6 100644
@@ -749,7 +749,6 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(const struct sctp_endpoint *ep,
 
 		/* Make sure that we and the peer are AUTH capable */
 		if (!sctp_auth_enable || !new_asoc->peer.auth_capable) {
-			kfree_skb(chunk->auth_chunk);
 			sctp_association_free(new_asoc);
 			return sctp_sf_pdiscard(ep, asoc, type, arg, commands);
 		}

@@ -764,10 +763,6 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(const struct sctp_endpoint *ep,
 		auth.transport = chunk->transport;
 
 		ret = sctp_sf_authenticate(ep, new_asoc, type, &auth);
-
-		/* We can now safely free the auth_chunk clone */
-		kfree_skb(chunk->auth_chunk);
-
 		if (ret != SCTP_IERROR_NO_ERROR) {
 			sctp_association_free(new_asoc);
 			return sctp_sf_pdiscard(ep, asoc, type, arg, commands);

net/socket.c +4 -0

index d4faade..3faa358 100644
@@ -1884,6 +1884,10 @@ static int copy_msghdr_from_user(struct msghdr *kmsg,
 {
 	if (copy_from_user(kmsg, umsg, sizeof(struct msghdr)))
 		return -EFAULT;
+
+	if (kmsg->msg_namelen < 0)
+		return -EINVAL;
+
 	if (kmsg->msg_namelen > sizeof(struct sockaddr_storage))
 		kmsg->msg_namelen = sizeof(struct sockaddr_storage);
 	return 0;

net/unix/af_unix.c +12 -5

index 54fc90b..8705ee3 100644
@@ -1771,8 +1771,11 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock,
 		goto out;
 
 	err = mutex_lock_interruptible(&u->readlock);
-	if (err) {
-		err = sock_intr_errno(sock_rcvtimeo(sk, noblock));
+	if (unlikely(err)) {
+		/* recvmsg() in non blocking mode is supposed to return -EAGAIN
+		 * sk_rcvtimeo is not honored by mutex_lock_interruptible()
+		 */
+		err = noblock ? -EAGAIN : -ERESTARTSYS;
 		goto out;
 	}

@@ -1887,6 +1890,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 	struct unix_sock *u = unix_sk(sk);
 	struct sockaddr_un *sunaddr = msg->msg_name;
 	int copied = 0;
+	int noblock = flags & MSG_DONTWAIT;
 	int check_creds = 0;
 	int target;
 	int err = 0;

@@ -1901,7 +1905,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 		goto out;
 
 	target = sock_rcvlowat(sk, flags&MSG_WAITALL, size);
-	timeo = sock_rcvtimeo(sk, flags&MSG_DONTWAIT);
+	timeo = sock_rcvtimeo(sk, noblock);
 
 	/* Lock the socket to prevent queue disordering
 	 * while sleeps in memcpy_tomsg

@@ -1913,8 +1917,11 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 	}
 
 	err = mutex_lock_interruptible(&u->readlock);
-	if (err) {
-		err = sock_intr_errno(timeo);
+	if (unlikely(err)) {
+		/* recvmsg() in non blocking mode is supposed to return -EAGAIN
+		 * sk_rcvtimeo is not honored by mutex_lock_interruptible()
+		 */
+		err = noblock ? -EAGAIN : -ERESTARTSYS;
 		goto out;
 	}

sound/pci/hda/patch_realtek.c +1 -0

index 36bce68..d307adb 100644
@@ -3855,6 +3855,7 @@ static void alc_auto_init_std(struct hda_codec *codec)
 
 static const struct snd_pci_quirk beep_white_list[] = {
 	SND_PCI_QUIRK(0x1043, 0x103c, "ASUS", 1),
+	SND_PCI_QUIRK(0x1043, 0x115d, "ASUS", 1),
 	SND_PCI_QUIRK(0x1043, 0x829f, "ASUS", 1),
 	SND_PCI_QUIRK(0x1043, 0x83ce, "EeePC", 1),
 	SND_PCI_QUIRK(0x1043, 0x831a, "EeePC", 1),

sound/pci/ice1712/ice1712.c +10 -5

index 44446f2..7a4a196 100644
@@ -686,9 +686,10 @@ static snd_pcm_uframes_t snd_ice1712_playback_pointer(struct snd_pcm_substream *
 	if (!(snd_ice1712_read(ice, ICE1712_IREG_PBK_CTRL) & 1))
 		return 0;
 	ptr = runtime->buffer_size - inw(ice->ddma_port + 4);
+	ptr = bytes_to_frames(substream->runtime, ptr);
 	if (ptr == runtime->buffer_size)
 		ptr = 0;
-	return bytes_to_frames(substream->runtime, ptr);
+	return ptr;
 }
 
 static snd_pcm_uframes_t snd_ice1712_playback_ds_pointer(struct snd_pcm_substream *substream)

@@ -705,9 +706,10 @@ static snd_pcm_uframes_t snd_ice1712_playback_ds_pointer(struct snd_pcm_substrea
 		addr = ICE1712_DSC_ADDR0;
 	ptr = snd_ice1712_ds_read(ice, substream->number * 2, addr) -
 		ice->playback_con_virt_addr[substream->number];
+	ptr = bytes_to_frames(substream->runtime, ptr);
 	if (ptr == substream->runtime->buffer_size)
 		ptr = 0;
-	return bytes_to_frames(substream->runtime, ptr);
+	return ptr;
 }
 
 static snd_pcm_uframes_t snd_ice1712_capture_pointer(struct snd_pcm_substream *substream)

@@ -718,9 +720,10 @@ static snd_pcm_uframes_t snd_ice1712_capture_pointer(struct snd_pcm_substream *s
 	if (!(snd_ice1712_read(ice, ICE1712_IREG_CAP_CTRL) & 1))
 		return 0;
 	ptr = inl(ICEREG(ice, CONCAP_ADDR)) - ice->capture_con_virt_addr;
+	ptr = bytes_to_frames(substream->runtime, ptr);
 	if (ptr == substream->runtime->buffer_size)
 		ptr = 0;
-	return bytes_to_frames(substream->runtime, ptr);
+	return ptr;
 }
 
 static const struct snd_pcm_hardware snd_ice1712_playback = {

@@ -1114,9 +1117,10 @@ static snd_pcm_uframes_t snd_ice1712_playback_pro_pointer(struct snd_pcm_substre
 	if (!(inl(ICEMT(ice, PLAYBACK_CONTROL)) & ICE1712_PLAYBACK_START))
 		return 0;
 	ptr = ice->playback_pro_size - (inw(ICEMT(ice, PLAYBACK_SIZE)) << 2);
+	ptr = bytes_to_frames(substream->runtime, ptr);
 	if (ptr == substream->runtime->buffer_size)
 		ptr = 0;
-	return bytes_to_frames(substream->runtime, ptr);
+	return ptr;
 }
 
 static snd_pcm_uframes_t snd_ice1712_capture_pro_pointer(struct snd_pcm_substream *substream)

@@ -1127,9 +1131,10 @@ static snd_pcm_uframes_t snd_ice1712_capture_pro_pointer(struct snd_pcm_substrea
 	if (!(inl(ICEMT(ice, PLAYBACK_CONTROL)) & ICE1712_CAPTURE_START_SHADOW))
 		return 0;
 	ptr = ice->capture_pro_size - (inw(ICEMT(ice, CAPTURE_SIZE)) << 2);
+	ptr = bytes_to_frames(substream->runtime, ptr);
 	if (ptr == substream->runtime->buffer_size)
 		ptr = 0;
-	return bytes_to_frames(substream->runtime, ptr);
+	return ptr;
 }
 
 static const struct snd_pcm_hardware snd_ice1712_playback_pro = {

Guenter Roeck

2014-04-29 04:01 UTC #96 lore raw