4.4.76-stable review

Cc Ben Hutchings <[email protected]>

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

---
 net/ipv6/ip6_output.c |    6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

net/ipv6/ip6_output.c +4 -2

@@ -1005,8 +1005,10 @@ static int ip6_dst_lookup_tail(struct ne
 	}
 #endif
 	if (ipv6_addr_v4mapped(&fl6->saddr) &&
-	    !(ipv6_addr_v4mapped(&fl6->daddr) || ipv6_addr_any(&fl6->daddr)))
-		return -EAFNOSUPPORT;
+	    !(ipv6_addr_v4mapped(&fl6->daddr) || ipv6_addr_any(&fl6->daddr))) {
+		err = -EAFNOSUPPORT;
+		goto out_err_release;
+	}
 
 	return 0;

Greg Kroah-Hartman

author maintainer

2017-07-03 13:34 UTC #2 lore raw

PATCH 2/101 net: dont call strlen on non-terminated string in dev_set_alias()

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Alexander Potapenko <[email protected]>

[ Upstream commit c28294b941232931fbd714099798eb7aa7e865d7 ]

KMSAN reported a use of uninitialized memory in dev_set_alias(), which was caused by calling strlcpy() (which in turn called strlen()) on the user-supplied non-terminated string.

Signed-off-by Alexander Potapenko <[email protected]>

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

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

net/core/dev.c +2 -1

@@ -1246,8 +1246,9 @@ int dev_set_alias(struct net_device *dev
 	if (!new_ifalias)
 		return -ENOMEM;
 	dev->ifalias = new_ifalias;
+	memcpy(dev->ifalias, alias, len);
+	dev->ifalias[len] = 0;
 
-	strlcpy(dev->ifalias, alias, len+1);
 	return len;
 }

Greg Kroah-Hartman

author maintainer

2017-07-03 13:37 UTC #3 lore raw

PATCH 3/101 decnet: dn_rtmsg: Improve input length sanitization in dnrmg_receive_user_skb

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Mateusz Jurczyk <[email protected]>

[ Upstream commit dd0da17b209ed91f39872766634ca967c170ada1 ]

Verify that the length of the socket buffer is sufficient to cover the nlmsghdr structure before accessing the nlh->nlmsg_len field for further input sanitization. If the client only supplies 1-3 bytes of data in sk_buff, then nlh->nlmsg_len remains partially uninitialized and contains leftover memory from the corresponding kernel allocation. Operating on such data may result in indeterminate evaluation of the nlmsg_len < sizeof(*nlh) expression.

The bug was discovered by a runtime instrumentation designed to detect use of uninitialized memory in the kernel. The patch prevents this and other similar tools (e.g. KMSAN) from flagging this behavior in the future.

Signed-off-by Mateusz Jurczyk <[email protected]>

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

---
 net/decnet/netfilter/dn_rtmsg.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

net/decnet/netfilter/dn_rtmsg.c +3 -1

@@ -102,7 +102,9 @@ static inline void dnrmg_receive_user_sk
 {
 	struct nlmsghdr *nlh = nlmsg_hdr(skb);
 
-	if (nlh->nlmsg_len < sizeof(*nlh) || skb->len < nlh->nlmsg_len)
+	if (skb->len < sizeof(*nlh) ||
+	    nlh->nlmsg_len < sizeof(*nlh) ||
+	    skb->len < nlh->nlmsg_len)
 		return;
 
 	if (!netlink_capable(skb, CAP_NET_ADMIN))

Greg Kroah-Hartman

author maintainer

2017-07-03 13:37 UTC #4 lore raw

PATCH 4/101 net: Zero ifla_vf_info in rtnl_fill_vfinfo()

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: "Mintz, Yuval" <[email protected]>

[ Upstream commit 0eed9cf58446b28b233388b7f224cbca268b6986 ]

Some of the structure's fields are not initialized by the rtnetlink. If driver doesn't set those in ndo_get_vf_config(), they'd leak memory to user.

Signed-off-by Yuval Mintz <[email protected]>

CC Michal Schmidt <[email protected]>

Reviewed-by Greg Rose <[email protected]>

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

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

net/core/rtnetlink.c +2 -1

@@ -1089,6 +1089,8 @@ static noinline_for_stack int rtnl_fill_
 	struct ifla_vf_mac vf_mac;
 	struct ifla_vf_info ivi;
 
+	memset(&ivi, 0, sizeof(ivi));
+
 	/* Not all SR-IOV capable drivers support the
 	 * spoofcheck and "RSS query enable" query.  Preset to
 	 * -1 so the user space tool can detect that the driver

@@ -1097,7 +1099,6 @@ static noinline_for_stack int rtnl_fill_
 	ivi.spoofchk = -1;
 	ivi.rss_query_en = -1;
 	ivi.trusted = -1;
-	memset(ivi.mac, 0, sizeof(ivi.mac));
 	/* The default value for VF link state is "auto"
 	 * IFLA_VF_LINK_STATE_AUTO which equals zero
 	 */

Greg Kroah-Hartman

author maintainer

2017-07-03 13:37 UTC #5 lore raw

PATCH 5/101 af_unix: Add sockaddr length checks before accessing sa_family in bind and connect handlers

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Mateusz Jurczyk <[email protected]>

[ Upstream commit defbcf2decc903a28d8398aa477b6881e711e3ea ]

Verify that the caller-provided sockaddr structure is large enough to contain the sa_family field, before accessing it in bind() and connect() handlers of the AF_UNIX socket. Since neither syscall enforces a minimum size of the corresponding memory region, very short sockaddrs (zero or one byte long) result in operating on uninitialized memory while referencing .sa_family.

Signed-off-by Mateusz Jurczyk <[email protected]>

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

---
 net/unix/af_unix.c |    7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

net/unix/af_unix.c +6 -1

@@ -997,7 +997,8 @@ static int unix_bind(struct socket *sock
 	struct path path = { NULL, NULL };
 
 	err = -EINVAL;
-	if (sunaddr->sun_family != AF_UNIX)
+	if (addr_len < offsetofend(struct sockaddr_un, sun_family) ||
+	    sunaddr->sun_family != AF_UNIX)
 		goto out;
 
 	if (addr_len == sizeof(short)) {

@@ -1108,6 +1109,10 @@ static int unix_dgram_connect(struct soc
 	unsigned int hash;
 	int err;
 
+	err = -EINVAL;
+	if (alen < offsetofend(struct sockaddr, sa_family))
+		goto out;
+
 	if (addr->sa_family != AF_UNSPEC) {
 		err = unix_mkname(sunaddr, alen, &hash);
 		if (err < 0)

Greg Kroah-Hartman

author maintainer

2017-07-03 13:37 UTC #6 lore raw

PATCH 6/101 Fix an intermittent pr_emerg warning about lo becoming free.

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Krister Johansen <[email protected]>

[ Upstream commit f186ce61bb8235d80068c390dc2aad7ca427a4c2 ]

It looks like this:

Message from syslogd@flamingo at Apr 26 00:45:00 ...
kernel:unregister_netdevice: waiting for lo to become free. Usage count = 4

They seem to coincide with net namespace teardown.

The message is emitted by netdev_wait_allrefs().

Forced a kdump in netdev_run_todo, but found that the refcount on the lo device was already 0 at the time we got to the panic.

Used bcc to check the blocking in netdev_run_todo. The only places where we're off cpu there are in the rcu_barrier() and msleep() calls. That behavior is expected. The msleep time coincides with the amount of time we spend waiting for the refcount to reach zero; the rcu_barrier() wait times are not excessive.

After looking through the list of callbacks that the netdevice notifiers invoke in this path, it appears that the dst_dev_event is the most interesting. The dst_ifdown path places a hold on the loopback_dev as part of releasing the dev associated with the original dst cache entry. Most of our notifier callbacks are straight-forward, but this one a) looks complex, and b) places a hold on the network interface in question.

I constructed a new bcc script that watches various events in the liftime of a dst cache entry. Note that dst_ifdown will take a hold on the loopback device until the invalidated dst entry gets freed.

[ __dst_free] on DST: ffff883ccabb7900 IF tap1008300eth0 invoked at 1282115677036183

    __dst_free
    rcu_nocb_kthread
    kthread
    ret_from_fork

Acked-by Eric Dumazet <[email protected]>

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

---
 net/core/dst.c |   14 ++++++++++++++
 1 file changed, 14 insertions(+)

net/core/dst.c +14 -0

@@ -462,6 +462,20 @@ static int dst_dev_event(struct notifier
 		spin_lock_bh(&dst_garbage.lock);
 		dst = dst_garbage.list;
 		dst_garbage.list = NULL;
+		/* The code in dst_ifdown places a hold on the loopback device.
+		 * If the gc entry processing is set to expire after a lengthy
+		 * interval, this hold can cause netdev_wait_allrefs() to hang
+		 * out and wait for a long time -- until the the loopback
+		 * interface is released.  If we're really unlucky, it'll emit
+		 * pr_emerg messages to console too.  Reset the interval here,
+		 * so dst cleanups occur in a more timely fashion.
+		 */
+		if (dst_garbage.timer_inc > DST_GC_INC) {
+			dst_garbage.timer_inc = DST_GC_INC;
+			dst_garbage.timer_expires = DST_GC_MIN;
+			mod_delayed_work(system_wq, &dst_gc_work,
+					 dst_garbage.timer_expires);
+		}
 		spin_unlock_bh(&dst_garbage.lock);
 
 		if (last)

Greg Kroah-Hartman

author maintainer

2017-07-03 13:37 UTC #7 lore raw

PATCH 7/101 net: caif: Fix a sleep-in-atomic bug in cfpkt_create_pfx

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Jia-Ju Bai <[email protected]>

[ Upstream commit f146e872eb12ebbe92d8e583b2637e0741440db3 ]

The kernel may sleep under a rcu read lock in cfpkt_create_pfx, and the function call path is:
cfcnfg_linkup_rsp (acquire the lock by rcu_read_lock)
cfctrl_linkdown_req

    cfpkt_create
      cfpkt_create_pfx
        alloc_skb(GFP_KERNEL) --> may sleep
cfserl_receive (acquire the lock by rcu_read_lock)
  cfpkt_split
    cfpkt_create_pfx
      alloc_skb(GFP_KERNEL) --> may sleep

There is "in_interrupt" in cfpkt_create_pfx to decide use "GFP_KERNEL" or "GFP_ATOMIC". In this situation, "GFP_KERNEL" is used because the function is called under a rcu read lock, instead in interrupt.

To fix it, only "GFP_ATOMIC" is used in cfpkt_create_pfx.

Signed-off-by Jia-Ju Bai <[email protected]>

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

---
 net/caif/cfpkt_skbuff.c |    6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

net/caif/cfpkt_skbuff.c +1 -5

@@ -81,11 +81,7 @@ static struct cfpkt *cfpkt_create_pfx(u1
 {
 	struct sk_buff *skb;
 
-	if (likely(in_interrupt()))
-		skb = alloc_skb(len + pfx, GFP_ATOMIC);
-	else
-		skb = alloc_skb(len + pfx, GFP_KERNEL);
-
+	skb = alloc_skb(len + pfx, GFP_ATOMIC);
 	if (unlikely(skb == NULL))
 		return NULL;

Greg Kroah-Hartman

author maintainer

2017-07-03 13:34 UTC #8 lore raw

PATCH 8/101 igmp: acquire pmc lock for ip_mc_clear_src()

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: WANG Cong <[email protected]>

[ Upstream commit c38b7d327aafd1e3ad7ff53eefac990673b65667 ]

Andrey reported a use-after-free in add_grec():

        for (psf = *psf_list; psf; psf = psf_next) {
		...
                psf_next = psf->sf_next;

where the struct ip_sf_list's were already freed by:

 kfree+0xe8/0x2b0 mm/slub.c:3882
 ip_mc_clear_src+0x69/0x1c0 net/ipv4/igmp.c:2078
 ip_mc_dec_group+0x19a/0x470 net/ipv4/igmp.c:1618
 ip_mc_drop_socket+0x145/0x230 net/ipv4/igmp.c:2609
 inet_release+0x4e/0x1c0 net/ipv4/af_inet.c:411
 sock_release+0x8d/0x1e0 net/socket.c:597
 sock_close+0x16/0x20 net/socket.c:1072

This happens because we don't hold pmc->lock in ip_mc_clear_src() and a parallel mr_ifc_timer timer could jump in and access them.

The RCU lock is there but it is merely for pmc itself, this spinlock could actually ensure we don't access them in parallel.

Thanks to Eric and Long for discussion on this bug.

Reported-by Andrey Konovalov <[email protected]>

Cc Eric Dumazet <[email protected]>

Cc Xin Long <[email protected]>

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

Reviewed-by Xin Long <[email protected]>

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

---
 net/ipv4/igmp.c |   21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

net/ipv4/igmp.c +13 -8

@@ -2026,21 +2026,26 @@ static int ip_mc_add_src(struct in_devic
 
 static void ip_mc_clear_src(struct ip_mc_list *pmc)
 {
-	struct ip_sf_list *psf, *nextpsf;
+	struct ip_sf_list *psf, *nextpsf, *tomb, *sources;
 
-	for (psf = pmc->tomb; psf; psf = nextpsf) {
+	spin_lock_bh(&pmc->lock);
+	tomb = pmc->tomb;
+	pmc->tomb = NULL;
+	sources = pmc->sources;
+	pmc->sources = NULL;
+	pmc->sfmode = MCAST_EXCLUDE;
+	pmc->sfcount[MCAST_INCLUDE] = 0;
+	pmc->sfcount[MCAST_EXCLUDE] = 1;
+	spin_unlock_bh(&pmc->lock);
+
+	for (psf = tomb; psf; psf = nextpsf) {
 		nextpsf = psf->sf_next;
 		kfree(psf);
 	}
-	pmc->tomb = NULL;
-	for (psf = pmc->sources; psf; psf = nextpsf) {
+	for (psf = sources; psf; psf = nextpsf) {
 		nextpsf = psf->sf_next;
 		kfree(psf);
 	}
-	pmc->sources = NULL;
-	pmc->sfmode = MCAST_EXCLUDE;
-	pmc->sfcount[MCAST_INCLUDE] = 0;
-	pmc->sfcount[MCAST_EXCLUDE] = 1;
 }
 
 /* Join a multicast group

Greg Kroah-Hartman

author maintainer

2017-07-03 13:34 UTC #9 lore raw

PATCH 9/101 igmp: add a missing spin_lock_init()

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: WANG Cong <[email protected]>

[ Upstream commit b4846fc3c8559649277e3e4e6b5cec5348a8d208 ]

Andrey reported a lockdep warning on non-initialized spinlock:

INFO: trying to register non-static key.
the code is fine but needs lockdep annotation.
turning off the locking correctness validator.

 CPU: 1 PID: 4099 Comm: a.out Not tainted 4.12.0-rc6+ #9
 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
 Call Trace:
  __dump_stack lib/dump_stack.c:16
  dump_stack+0x292/0x395 lib/dump_stack.c:52
  register_lock_class+0x717/0x1aa0 kernel/locking/lockdep.c:755
  ? 0xffffffffa0000000
  __lock_acquire+0x269/0x3690 kernel/locking/lockdep.c:3255
  lock_acquire+0x22d/0x560 kernel/locking/lockdep.c:3855
  __raw_spin_lock_bh ./include/linux/spinlock_api_smp.h:135
  _raw_spin_lock_bh+0x36/0x50 kernel/locking/spinlock.c:175
  spin_lock_bh ./include/linux/spinlock.h:304
  ip_mc_clear_src+0x27/0x1e0 net/ipv4/igmp.c:2076
  igmpv3_clear_delrec+0xee/0x4f0 net/ipv4/igmp.c:1194
  ip_mc_destroy_dev+0x4e/0x190 net/ipv4/igmp.c:1736

We miss a spin_lock_init() in igmpv3_add_delrec(), probably because previously we never use it on this code path. Since we already unlink it from the global mc_tomb list, it is probably safe not to acquire this spinlock here. It does not harm to have it although, to avoid conditional locking.

Fixes c38b7d327aaf ("igmp: acquire pmc lock for ip_mc_clear_src()")

Reported-by Andrey Konovalov <[email protected]>

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

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

---
 net/ipv4/igmp.c |    1 +
 1 file changed, 1 insertion(+)

net/ipv4/igmp.c +1 -0

@@ -1102,6 +1102,7 @@ static void igmpv3_add_delrec(struct in_
 	pmc = kzalloc(sizeof(*pmc), GFP_KERNEL);
 	if (!pmc)
 		return;
+	spin_lock_init(&pmc->lock);
 	spin_lock_bh(&im->lock);
 	pmc->interface = im->interface;
 	in_dev_hold(in_dev);

Greg Kroah-Hartman

author maintainer

2017-07-03 13:38 UTC #10 lore raw

PATCH 10/101 ipv6: fix calling in6_ifa_hold incorrectly for dad work

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Xin Long <[email protected]>

[ Upstream commit f8a894b218138888542a5058d0e902378fd0d4ec ]

Now when starting the dad work in addrconf_mod_dad_work, if the dad work is idle and queued, it needs to hold ifa.

The problem is there's one gap in [1], during which if the pending dad work is removed elsewhere. It will miss to hold ifa, but the dad word is still idea and queue.

        if (!delayed_work_pending(&ifp->dad_work))
                in6_ifa_hold(ifp);
                    <--------------[1]
        mod_delayed_work(addrconf_wq, &ifp->dad_work, delay);

An use-after-free issue can be caused by this.

Chen Wei found this issue when WARN_ON(!hlist_unhashed(&ifp->addr_lst)) in net6_ifa_finish_destroy was hit because of it.

As Hannes' suggestion, this patch is to fix it by holding ifa first in addrconf_mod_dad_work, then calling mod_delayed_work and putting ifa if the dad_work is already in queue.

Note that this patch did not choose to fix it with:

  if (!mod_delayed_work(delay))
          in6_ifa_hold(ifp);

As with it, when delay == 0, dad_work would be scheduled immediately, all addrconf_mod_dad_work(0) callings had to be moved under ifp->lock.

Reported-by Wei Chen <[email protected]>

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

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

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

---
 net/ipv6/addrconf.c |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

net/ipv6/addrconf.c +3 -3

@@ -291,9 +291,9 @@ static void addrconf_mod_rs_timer(struct
 static void addrconf_mod_dad_work(struct inet6_ifaddr *ifp,
 				   unsigned long delay)
 {
-	if (!delayed_work_pending(&ifp->dad_work))
-		in6_ifa_hold(ifp);
-	mod_delayed_work(addrconf_wq, &ifp->dad_work, delay);
+	in6_ifa_hold(ifp);
+	if (mod_delayed_work(addrconf_wq, &ifp->dad_work, delay))
+		in6_ifa_put(ifp);
 }
 
 static int snmp6_alloc_dev(struct inet6_dev *idev)

Greg Kroah-Hartman

author maintainer

2017-07-03 13:37 UTC #11 lore raw

PATCH 11/101 net/mlx5: Wait for FW readiness before initializing command interface

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Eli Cohen <[email protected]>

[ Upstream commit 6c780a0267b8a1075f40b39851132eeaefefcff5 ]

Before attempting to initialize the command interface we must wait till the fw_initializing bit is clear.

If we fail to meet this condition the hardware will drop our configuration, specifically the descriptors page address. This scenario can happen when the firmware is still executing an FLR flow and did not finish yet so the driver needs to wait for that to finish.

Fixes e3297246c2c8 ('net/mlx5_core: Wait for FW readiness on startup')

Signed-off-by Eli Cohen <[email protected]>

Signed-off-by Saeed Mahameed <[email protected]>

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

---
 drivers/net/ethernet/mellanox/mlx5/core/main.c |   14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

drivers/net/ethernet/mellanox/mlx5/core/main.c +12 -2

@@ -153,8 +153,9 @@ static struct mlx5_profile profile[] = {
 	},
 };
 
-#define FW_INIT_TIMEOUT_MILI	2000
-#define FW_INIT_WAIT_MS		2
+#define FW_INIT_TIMEOUT_MILI		2000
+#define FW_INIT_WAIT_MS			2
+#define FW_PRE_INIT_TIMEOUT_MILI	10000
 
 static int wait_fw_init(struct mlx5_core_dev *dev, u32 max_wait_mili)
 {

@@ -934,6 +935,15 @@ static int mlx5_load_one(struct mlx5_cor
 	 */
 	dev->state = MLX5_DEVICE_STATE_UP;
 
+	/* wait for firmware to accept initialization segments configurations
+	 */
+	err = wait_fw_init(dev, FW_PRE_INIT_TIMEOUT_MILI);
+	if (err) {
+		dev_err(&dev->pdev->dev, "Firmware over %d MS in pre-initializing state, aborting\n",
+			FW_PRE_INIT_TIMEOUT_MILI);
+		goto out;
+	}
+
 	err = mlx5_cmd_init(dev);
 	if (err) {
 		dev_err(&pdev->dev, "Failed initializing command interface, aborting\n");

Greg Kroah-Hartman

author maintainer

2017-07-03 13:37 UTC #12 lore raw

PATCH 12/101 decnet: always not take dst->__refcnt when inserting dst into hash table

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Wei Wang <[email protected]>

[ Upstream commit 76371d2e3ad1f84426a30ebcd8c3b9b98f4c724f ]

In the existing dn_route.c code, dn_route_output_slow() takes dst->__refcnt before calling dn_insert_route() while dn_route_input_slow() does not take dst->__refcnt before calling dn_insert_route(). This makes the whole routing code very buggy.
In dn_dst_check_expire(), dnrt_free() is called when rt expires. This makes the routes inserted by dn_route_output_slow() not able to be freed as the refcnt is not released.
In dn_dst_gc(), dnrt_drop() is called to release rt which could potentially cause the dst->__refcnt to be dropped to -1.
In dn_run_flush(), dst_free() is called to release all the dst. Again, it makes the dst inserted by dn_route_output_slow() not able to be released and also, it does not wait on the rcu and could potentially cause crash in the path where other users still refer to this dst.

This patch makes sure both input and output path do not take dst->__refcnt before calling dn_insert_route() and also makes sure dnrt_free()/dst_free() is called when removing dst from the hash table. The only difference between those 2 calls is that dnrt_free() waits on the rcu while dst_free() does not.

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

Acked-by Martin KaFai Lau <[email protected]>

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

---
 net/decnet/dn_route.c |   14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

net/decnet/dn_route.c +4 ~~-10~~

@@ -188,12 +188,6 @@ static inline void dnrt_free(struct dn_r
 	call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free);
 }
 
-static inline void dnrt_drop(struct dn_route *rt)
-{
-	dst_release(&rt->dst);
-	call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free);
-}
-
 static void dn_dst_check_expire(unsigned long dummy)
 {
 	int i;

@@ -248,7 +242,7 @@ static int dn_dst_gc(struct dst_ops *ops
 			}
 			*rtp = rt->dst.dn_next;
 			rt->dst.dn_next = NULL;
-			dnrt_drop(rt);
+			dnrt_free(rt);
 			break;
 		}
 		spin_unlock_bh(&dn_rt_hash_table[i].lock);

@@ -350,7 +344,7 @@ static int dn_insert_route(struct dn_rou
 			dst_use(&rth->dst, now);
 			spin_unlock_bh(&dn_rt_hash_table[hash].lock);
 
-			dnrt_drop(rt);
+			dst_free(&rt->dst);
 			*rp = rth;
 			return 0;
 		}

@@ -380,7 +374,7 @@ static void dn_run_flush(unsigned long d
 		for(; rt; rt = next) {
 			next = rcu_dereference_raw(rt->dst.dn_next);
 			RCU_INIT_POINTER(rt->dst.dn_next, NULL);
-			dst_free((struct dst_entry *)rt);
+			dnrt_free(rt);
 		}
 
 nothing_to_declare:

@@ -1187,7 +1181,7 @@ make_route:
 	if (dev_out->flags & IFF_LOOPBACK)
 		flags |= RTCF_LOCAL;
 
-	rt = dst_alloc(&dn_dst_ops, dev_out, 1, DST_OBSOLETE_NONE, DST_HOST);
+	rt = dst_alloc(&dn_dst_ops, dev_out, 0, DST_OBSOLETE_NONE, DST_HOST);
 	if (rt == NULL)
 		goto e_nobufs;

Greg Kroah-Hartman

author maintainer

2017-07-03 13:34 UTC #13 lore raw

PATCH 13/101 net: 8021q: Fix one possible panic caused by BUG_ON in free_netdev

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Gao Feng <[email protected]>

[ Upstream commit 9745e362add89432d2c951272a99b0a5fe4348a9 ]

The register_vlan_device would invoke free_netdev directly, when register_vlan_dev failed. It would trigger the BUG_ON in free_netdev if the dev was already registered. In this case, the netdev would be freed in netdev_run_todo later.

So add one condition check now. Only when dev is not registered, then free it directly.

The following is the part coredump when netdev_upper_dev_link failed in register_vlan_dev. I removed the lines which are too long.

[  411.237457] ------------[ cut here ]------------
[  411.237458] kernel BUG at net/core/dev.c:7998!
[  411.237484] invalid opcode: 0000 [#1] SMP
[  411.237705]  [last unloaded: 8021q]
[  411.237718] CPU: 1 PID: 12845 Comm: vconfig Tainted: G            E   4.12.0-rc5+ #6
[  411.237737] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 07/02/2015
[  411.237764] task: ffff9cbeb6685580 task.stack: ffffa7d2807d8000
[  411.237782] RIP: 0010:free_netdev+0x116/0x120
[  411.237794] RSP: 0018:ffffa7d2807dbdb0 EFLAGS: 00010297
[  411.237808] RAX: 0000000000000002 RBX: ffff9cbeb6ba8fd8 RCX: 0000000000001878
[  411.237826] RDX: 0000000000000001 RSI: 0000000000000282 RDI: 0000000000000000
[  411.237844] RBP: ffffa7d2807dbdc8 R08: 0002986100029841 R09: 0002982100029801
[  411.237861] R10: 0004000100029980 R11: 0004000100029980 R12: ffff9cbeb6ba9000
[  411.238761] R13: ffff9cbeb6ba9060 R14: ffff9cbe60f1a000 R15: ffff9cbeb6ba9000
[  411.239518] FS:  00007fb690d81700(0000) GS:ffff9cbebb640000(0000) knlGS:0000000000000000
[  411.239949] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  411.240454] CR2: 00007f7115624000 CR3: 0000000077cdf000 CR4: 00000000003406e0
[  411.240936] Call Trace:
[  411.241462]  vlan_ioctl_handler+0x3f1/0x400 [8021q]
[  411.241910]  sock_ioctl+0x18b/0x2c0
[  411.242394]  do_vfs_ioctl+0xa1/0x5d0
[  411.242853]  ? sock_alloc_file+0xa6/0x130
[  411.243465]  SyS_ioctl+0x79/0x90
[  411.243900]  entry_SYSCALL_64_fastpath+0x1e/0xa9
[  411.244425] RIP: 0033:0x7fb69089a357
[  411.244863] RSP: 002b:00007ffcd04e0fc8 EFLAGS: 00000202 ORIG_RAX: 0000000000000010
[  411.245445] RAX: ffffffffffffffda RBX: 00007ffcd04e2884 RCX: 00007fb69089a357
[  411.245903] RDX: 00007ffcd04e0fd0 RSI: 0000000000008983 RDI: 0000000000000003
[  411.246527] RBP: 00007ffcd04e0fd0 R08: 0000000000000000 R09: 1999999999999999
[  411.246976] R10: 000000000000053f R11: 0000000000000202 R12: 0000000000000004
[  411.247414] R13: 00007ffcd04e1128 R14: 00007ffcd04e2888 R15: 0000000000000001
[  411.249129] RIP: free_netdev+0x116/0x120 RSP: ffffa7d2807dbdb0

Signed-off-by Gao Feng <[email protected]>

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

---
 net/8021q/vlan.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

net/8021q/vlan.c +2 -1

@@ -278,7 +278,8 @@ static int register_vlan_device(struct n
 	return 0;
 
 out_free_newdev:
-	free_netdev(new_dev);
+	if (new_dev->reg_state == NETREG_UNINITIALIZED)
+		free_netdev(new_dev);
 	return err;
 }

Greg Kroah-Hartman

author maintainer

2017-07-03 13:38 UTC #14 lore raw

PATCH 14/101 sfc: provide dummy definitions of vswitch functions

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Bert Kenward <[email protected]>

efx_probe_all() calls efx->type->vswitching_probe during probe. For SFC4000 (Falcon) NICs this function is not defined, leading to a BUG with the top of the call stack similar to:

  ? efx_pci_probe_main+0x29a/0x830
  efx_pci_probe+0x7d3/0xe70

vswitching_restore and vswitching_remove also need to be defined.

Fixed in mainline by:
commit 5a6681e22c14 ("sfc: separate out SFC4000 ("Falcon") support into new sfc-falcon driver")

Fixes 6d8aaaf6f798 ("sfc: create VEB vswitch and vport above default firmware setup")

Signed-off-by Bert Kenward <[email protected]>

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

---
 drivers/net/ethernet/sfc/falcon.c |   10 ++++++++++
 1 file changed, 10 insertions(+)

drivers/net/ethernet/sfc/falcon.c +10 -0

@@ -2796,6 +2796,11 @@ const struct efx_nic_type falcon_a1_nic_
 	.timer_period_max =  1 << FRF_AB_TC_TIMER_VAL_WIDTH,
 	.offload_features = NETIF_F_IP_CSUM,
 	.mcdi_max_ver = -1,
+#ifdef CONFIG_SFC_SRIOV
+	.vswitching_probe = efx_port_dummy_op_int,
+	.vswitching_restore = efx_port_dummy_op_int,
+	.vswitching_remove = efx_port_dummy_op_void,
+#endif
 };
 
 const struct efx_nic_type falcon_b0_nic_type = {

@@ -2897,4 +2902,9 @@ const struct efx_nic_type falcon_b0_nic_
 	.offload_features = NETIF_F_IP_CSUM | NETIF_F_RXHASH | NETIF_F_NTUPLE,
 	.mcdi_max_ver = -1,
 	.max_rx_ip_filters = FR_BZ_RX_FILTER_TBL0_ROWS,
+#ifdef CONFIG_SFC_SRIOV
+	.vswitching_probe = efx_port_dummy_op_int,
+	.vswitching_restore = efx_port_dummy_op_int,
+	.vswitching_remove = efx_port_dummy_op_void,
+#endif
 };

Greg Kroah-Hartman

author maintainer

2017-07-03 13:38 UTC #15 lore raw

PATCH 15/101 ipv6: Do not leak throw route references

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Serhey Popovych <[email protected]>

[ Upstream commit 07f615574f8ac499875b21c1142f26308234a92c ]

While commit 73ba57bfae4a ("ipv6: fix backtracking for throw routes") does good job on error propagation to the fib_rules_lookup() in fib rules core framework that also corrects throw routes handling, it does not solve route reference leakage problem happened when we return -EAGAIN to the fib_rules_lookup() and leave routing table entry referenced in arg->result.

If rule with matched throw route isn't last matched in the list we overwrite arg->result losing reference on throw route stored previously forever.

We also partially revert commit ab997ad40839 ("ipv6: fix the incorrect return value of throw route") since we never return routing table entry with dst.error == -EAGAIN when CONFIG_IPV6_MULTIPLE_TABLES is on. Also there is no point to check for RTF_REJECT flag since it is always set throw route.

Fixes 73ba57bfae4a ("ipv6: fix backtracking for throw routes")

Signed-off-by Serhey Popovych <[email protected]>

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

---
 net/ipv6/fib6_rules.c |   22 ++++++----------------
 net/ipv6/ip6_fib.c    |    3 +--
 2 files changed, 7 insertions(+), 18 deletions(-)

net/ipv6/fib6_rules.c +6 ~~-16~~

@@ -32,7 +32,6 @@ struct fib6_rule {
 struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
 				   int flags, pol_lookup_t lookup)
 {
-	struct rt6_info *rt;
 	struct fib_lookup_arg arg = {
 		.lookup_ptr = lookup,
 		.flags = FIB_LOOKUP_NOREF,

@@ -41,21 +40,11 @@ struct dst_entry *fib6_rule_lookup(struc
 	fib_rules_lookup(net->ipv6.fib6_rules_ops,
 			 flowi6_to_flowi(fl6), flags, &arg);
 
-	rt = arg.result;
+	if (arg.result)
+		return arg.result;
 
-	if (!rt) {
-		dst_hold(&net->ipv6.ip6_null_entry->dst);
-		return &net->ipv6.ip6_null_entry->dst;
-	}
-
-	if (rt->rt6i_flags & RTF_REJECT &&
-	    rt->dst.error == -EAGAIN) {
-		ip6_rt_put(rt);
-		rt = net->ipv6.ip6_null_entry;
-		dst_hold(&rt->dst);
-	}
-
-	return &rt->dst;
+	dst_hold(&net->ipv6.ip6_null_entry->dst);
+	return &net->ipv6.ip6_null_entry->dst;
 }
 
 static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,

@@ -116,7 +105,8 @@ static int fib6_rule_action(struct fib_r
 			flp6->saddr = saddr;
 		}
 		err = rt->dst.error;
-		goto out;
+		if (err != -EAGAIN)
+			goto out;
 	}
 again:
 	ip6_rt_put(rt);

net/ipv6/ip6_fib.c +1 -2

@@ -290,8 +290,7 @@ struct dst_entry *fib6_rule_lookup(struc
 	struct rt6_info *rt;
 
 	rt = lookup(net, net->ipv6.fib6_main_tbl, fl6, flags);
-	if (rt->rt6i_flags & RTF_REJECT &&
-	    rt->dst.error == -EAGAIN) {
+	if (rt->dst.error == -EAGAIN) {
 		ip6_rt_put(rt);
 		rt = net->ipv6.ip6_null_entry;
 		dst_hold(&rt->dst);

Greg Kroah-Hartman

author maintainer

2017-07-03 13:38 UTC #16 lore raw

PATCH 16/101 rtnetlink: add IFLA_GROUP to ifla_policy

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Serhey Popovych <[email protected]>

[ Upstream commit db833d40ad3263b2ee3b59a1ba168bb3cfed8137 ]

Network interface groups support added while ago, however there is no IFLA_GROUP attribute description in policy and netlink message size calculations until now.

Add IFLA_GROUP attribute to the policy.

Fixes cbda10fa97d7 ("net_device: add support for network device groups")

Signed-off-by Serhey Popovych <[email protected]>

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

---
 net/core/rtnetlink.c |    2 ++
 1 file changed, 2 insertions(+)

net/core/rtnetlink.c +2 -0

@@ -897,6 +897,7 @@ static noinline size_t if_nlmsg_size(con
 	       + nla_total_size(1) /* IFLA_LINKMODE */
 	       + nla_total_size(4) /* IFLA_CARRIER_CHANGES */
 	       + nla_total_size(4) /* IFLA_LINK_NETNSID */
+	       + nla_total_size(4) /* IFLA_GROUP */
 	       + nla_total_size(ext_filter_mask
 			        & RTEXT_FILTER_VF ? 4 : 0) /* IFLA_NUM_VF */
 	       + rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */

@@ -1371,6 +1372,7 @@ static const struct nla_policy ifla_poli
 	[IFLA_PHYS_SWITCH_ID]	= { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN },
 	[IFLA_LINK_NETNSID]	= { .type = NLA_S32 },
 	[IFLA_PROTO_DOWN]	= { .type = NLA_U8 },
+	[IFLA_GROUP]		= { .type = NLA_U32 },
 };
 
 static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {

Greg Kroah-Hartman

author maintainer

2017-07-03 13:38 UTC #17 lore raw

PATCH 17/101 netfilter: xt_TCPMSS: add more sanity tests on tcph->doff

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Eric Dumazet <[email protected]>

commit 2638fd0f92d4397884fd991d8f4925cb3f081901 upstream.

Denys provided an awesome KASAN report pointing to an use after free in xt_TCPMSS

I have provided three patches to fix this issue, either in xt_TCPMSS or in xt_tcpudp.c. It seems xt_TCPMSS patch has the smallest possible impact.

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

Reported-by Denys Fedoryshchenko <[email protected]>

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

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

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

net/netfilter/xt_TCPMSS.c +5 -1

@@ -104,7 +104,7 @@ tcpmss_mangle_packet(struct sk_buff *skb
 	tcph = (struct tcphdr *)(skb_network_header(skb) + tcphoff);
 	tcp_hdrlen = tcph->doff * 4;
 
-	if (len < tcp_hdrlen)
+	if (len < tcp_hdrlen || tcp_hdrlen < sizeof(struct tcphdr))
 		return -1;
 
 	if (info->mss == XT_TCPMSS_CLAMP_PMTU) {

@@ -156,6 +156,10 @@ tcpmss_mangle_packet(struct sk_buff *skb
 	if (len > tcp_hdrlen)
 		return 0;
 
+	/* tcph->doff has 4 bits, do not wrap it to 0 */
+	if (tcp_hdrlen >= 15 * 4)
+		return 0;
+
 	/*
 	 * MSS Option not found ?! add it..
 	 */

Greg Kroah-Hartman

author maintainer

2017-07-03 13:38 UTC #18 lore raw

PATCH 18/101 netfilter: synproxy: fix conntrackd interaction

[1] http://bugs.launchpad.net/bugs/1709032

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Eric Leblond <[email protected]>

commit 87e94dbc210a720a34be5c1174faee5c84be963e upstream.

This patch fixes the creation of connection tracking entry from netlink when synproxy is used. It was missing the addition of the synproxy extension.

This was causing kernel crashes when a conntrack entry created by conntrackd was used after the switch of traffic from active node to the passive node.

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

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

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

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

net/netfilter/nf_conntrack_netlink.c +4 -0

@@ -45,6 +45,8 @@
 #include <net/netfilter/nf_conntrack_zones.h>
 #include <net/netfilter/nf_conntrack_timestamp.h>
 #include <net/netfilter/nf_conntrack_labels.h>
+#include <net/netfilter/nf_conntrack_seqadj.h>
+#include <net/netfilter/nf_conntrack_synproxy.h>
 #ifdef CONFIG_NF_NAT_NEEDED
 #include <net/netfilter/nf_nat_core.h>
 #include <net/netfilter/nf_nat_l4proto.h>

@@ -1798,6 +1800,8 @@ ctnetlink_create_conntrack(struct net *n
 	nf_ct_tstamp_ext_add(ct, GFP_ATOMIC);
 	nf_ct_ecache_ext_add(ct, 0, 0, GFP_ATOMIC);
 	nf_ct_labels_ext_add(ct);
+	nfct_seqadj_ext_add(ct);
+	nfct_synproxy_ext_add(ct);
 
 	/* we must add conntrack extensions before confirmation. */
 	ct->status |= IPS_CONFIRMED;

Stefan Bader

2017-08-17 05:57 UTC #19 lore raw

Re: [PATCH 4.4 018/101] netfilter: synproxy: fix conntrackd interaction

Quoted 1 line · Greg Kroah-Hartman

4.4-stable review patch. If anyone has any objections, please let me know.

We found that pulling below patch into stable trees without also pulling

commit 9c3f3794926a997b1cab6c42480ff300efa2d162

Author: Liping Zhang <[email protected]>
Date:   Sat Mar 25 16:35:29 2017 +0800

netfilter: nf_ct_ext: fix possible panic after nf_ct_extend_unregister

will result in a regression, at least in 4.4.y[1]. Stable maintainers who picked up below patch might want to consider picking up above fix.

-Stefan

Quoted 45 lines

------------------
From: Eric Leblond <[email protected]>
commit 87e94dbc210a720a34be5c1174faee5c84be963e upstream.
This patch fixes the creation of connection tracking entry from netlink when synproxy is used. It was missing the addition of the synproxy extension.
This was causing kernel crashes when a conntrack entry created by conntrackd was used after the switch of traffic from active node to the passive node.
Signed-off-by Eric Leblond <[email protected]>
Signed-off-by Pablo Neira Ayuso <[email protected]>
Signed-off-by Greg Kroah-Hartman <[email protected]>
---
 net/netfilter/nf_conntrack_netlink.c |    4 ++++
 1 file changed, 4 insertions(+)
net/netfilter/nf_conntrack_netlink.c +4 -0
@@ -45,6 +45,8 @@
 #include <net/netfilter/nf_conntrack_zones.h>
 #include <net/netfilter/nf_conntrack_timestamp.h>
 #include <net/netfilter/nf_conntrack_labels.h>
+#include <net/netfilter/nf_conntrack_seqadj.h>
+#include <net/netfilter/nf_conntrack_synproxy.h>
 #ifdef CONFIG_NF_NAT_NEEDED
 #include <net/netfilter/nf_nat_core.h>
 #include <net/netfilter/nf_nat_l4proto.h>
@@ -1798,6 +1800,8 @@ ctnetlink_create_conntrack(struct net *n
 	nf_ct_tstamp_ext_add(ct, GFP_ATOMIC);
 	nf_ct_ecache_ext_add(ct, 0, 0, GFP_ATOMIC);
 	nf_ct_labels_ext_add(ct);
+	nfct_seqadj_ext_add(ct);
+	nfct_synproxy_ext_add(ct);
 
 	/* we must add conntrack extensions before confirmation. */
 	ct->status |= IPS_CONFIRMED;

Greg Kroah-Hartman

author maintainer

2017-08-17 16:47 UTC #20 lore raw

Re: [PATCH 4.4 018/101] netfilter: synproxy: fix conntrackd interaction

Quoted 5 lines · Stefan Bader

Quoted 1 line · Greg Kroah-Hartman
4.4-stable review patch. If anyone has any objections, please let me know.
We found that pulling below patch into stable trees without also pulling

Quoted 8 lines

commit 9c3f3794926a997b1cab6c42480ff300efa2d162
Author: Liping Zhang <[email protected]>
Date:   Sat Mar 25 16:35:29 2017 +0800
netfilter: nf_ct_ext: fix possible panic after nf_ct_extend_unregister
will result in a regression, at least in 4.4.y[1]. Stable maintainers who picked up below patch might want to consider picking up above fix.

Thanks, I've now picked this one up too.

greg k-h

Greg Kroah-Hartman

author maintainer

2017-07-03 13:38 UTC #21 lore raw

PATCH 19/101 NFSv4: fix a reference leak caused WARNING messages

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Kinglong Mee <[email protected]>

commit 366a1569bff3fe14abfdf9285e31e05e091745f5 upstream.

Because nfs4_opendata_access() has close the state when access is denied, so the state isn't leak.
Rather than revert the commit a974deee47, I'd like clean the strange state close.

[ 1615.094218] ------------[ cut here ]------------
[ 1615.094607] WARNING: CPU: 0 PID: 23702 at lib/list_debug.c:31 __list_add_valid+0x8e/0xa0
[ 1615.094913] list_add double add: new=ffff9d7901d9f608, prev=ffff9d7901d9f608, next=ffff9d7901ee8dd0.
[ 1615.095458] Modules linked in: nfsv4(E) nfs(E) nfsd(E) tun bridge stp llc fuse ip_set nfnetlink vmw_vsock_vmci_transport vsock f2fs snd_seq_midi snd_seq_midi_event fscrypto coretemp ppdev crct10dif_pclmul crc32_pclmul ghash_clmulni_intel intel_rapl_perf vmw_balloon snd_ens1371 joydev gameport snd_ac97_codec ac97_bus snd_seq snd_pcm snd_rawmidi snd_timer snd_seq_device snd soundcore nfit parport_pc parport acpi_cpufreq tpm_tis tpm_tis_core tpm i2c_piix4 vmw_vmci shpchp auth_rpcgss nfs_acl lockd(E) grace sunrpc(E) xfs libcrc32c vmwgfx drm_kms_helper ttm drm crc32c_intel mptspi e1000 serio_raw scsi_transport_spi mptscsih mptbase ata_generic pata_acpi fjes [last unloaded: nfs]
[ 1615.097663] CPU: 0 PID: 23702 Comm: fstest Tainted: G        W   E   4.11.0-rc1+ #517
[ 1615.098015] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 07/02/2015
[ 1615.098807] Call Trace:
[ 1615.099183]  dump_stack+0x63/0x86
[ 1615.099578]  __warn+0xcb/0xf0
[ 1615.099967]  warn_slowpath_fmt+0x5f/0x80
[ 1615.100370]  __list_add_valid+0x8e/0xa0
[ 1615.100760]  nfs4_put_state_owner+0x75/0xc0 [nfsv4]
[ 1615.101136]  __nfs4_close+0x109/0x140 [nfsv4]
[ 1615.101524]  nfs4_close_state+0x15/0x20 [nfsv4]
[ 1615.101949]  nfs4_close_context+0x21/0x30 [nfsv4]
[ 1615.102691]  __put_nfs_open_context+0xb8/0x110 [nfs]
[ 1615.103155]  put_nfs_open_context+0x10/0x20 [nfs]
[ 1615.103586]  nfs4_file_open+0x13b/0x260 [nfsv4]
[ 1615.103978]  do_dentry_open+0x20a/0x2f0
[ 1615.104369]  ? nfs4_copy_file_range+0x30/0x30 [nfsv4]
[ 1615.104739]  vfs_open+0x4c/0x70
[ 1615.105106]  ? may_open+0x5a/0x100
[ 1615.105469]  path_openat+0x623/0x1420
[ 1615.105823]  do_filp_open+0x91/0x100
[ 1615.106174]  ? __alloc_fd+0x3f/0x170
[ 1615.106568]  do_sys_open+0x130/0x220
[ 1615.106920]  ? __put_cred+0x3d/0x50
[ 1615.107256]  SyS_open+0x1e/0x20
[ 1615.107588]  entry_SYSCALL_64_fastpath+0x1a/0xa9
[ 1615.107922] RIP: 0033:0x7fab599069b0
[ 1615.108247] RSP: 002b:00007ffcf0600d78 EFLAGS: 00000246 ORIG_RAX: 0000000000000002
[ 1615.108575] RAX: ffffffffffffffda RBX: 00007fab59bcfae0 RCX: 00007fab599069b0
[ 1615.108896] RDX: 0000000000000200 RSI: 0000000000000200 RDI: 00007ffcf060255e
[ 1615.109211] RBP: 0000000000040010 R08: 0000000000000000 R09: 0000000000000016
[ 1615.109515] R10: 00000000000006a1 R11: 0000000000000246 R12: 0000000000041000
[ 1615.109806] R13: 0000000000040010 R14: 0000000000001000 R15: 0000000000002710
[ 1615.110152] ---[ end trace 96ed63b1306bf2f3 ]---

Fixes a974deee47 ("NFSv4: Fix memory and state leak in...")

Signed-off-by Kinglong Mee <[email protected]>

Signed-off-by Anna Schumaker <[email protected]>

Cc Trond Myklebust <[email protected]>

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

---
 fs/nfs/nfs4proc.c |    2 --
 1 file changed, 2 deletions(-)

fs/nfs/nfs4proc.c +0 -2

@@ -2188,8 +2188,6 @@ static int nfs4_opendata_access(struct r
 	if ((mask & ~cache.mask & (MAY_READ | MAY_EXEC)) == 0)
 		return 0;
 
-	/* even though OPEN succeeded, access is denied. Close the file */
-	nfs4_close_state(state, fmode);
 	return -EACCES;
 }

Greg Kroah-Hartman

author maintainer

2017-07-03 13:37 UTC #22 lore raw

PATCH 20/101 drm/ast: Handle configuration without P2A bridge

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Russell Currey <[email protected]>

commit 71f677a91046599ece96ebab21df956ce909c456 upstream.

The ast driver configures a window to enable access into BMC memory space in order to read some configuration registers.

If this window is disabled, which it can be from the BMC side, the ast driver can't function.

Closing this window is a necessity for security if a machine's host side and BMC side are controlled by different parties; i.e. a cloud provider offering machines "bare metal".

A recent patch went in to try to check if that window is open but it does so by trying to access the registers in question and testing if the result is 0xffffffff.

This method will trigger a PCIe error when the window is closed which on some systems will be fatal (it will trigger an EEH for example on POWER which will take out the device).

This patch improves this in two ways:

- First, if the firmware has put properties in the device-tree
containing the relevant configuration information, we use these.

- Otherwise, a bit in one of the SCU scratch registers (which
are readable via the VGA register space and writeable by the BMC) will indicate if the BMC has closed the window. This bit has been defined by Y.C Chen from Aspeed.

If the window is closed and the configuration isn't available from the device-tree, some sane defaults are used. Those defaults are hopefully sufficient for standard video modes used on a server.

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

Acked-by Joel Stanley <[email protected]>

Signed-off-by Benjamin Herrenschmidt <[email protected]>

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

Cc Ben Hutchings <[email protected]>

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

---
 drivers/gpu/drm/ast/ast_drv.h  |    6 
 drivers/gpu/drm/ast/ast_main.c |  264 +++++++++++++++++++++++++----------------
 drivers/gpu/drm/ast/ast_post.c |    7 -
 3 files changed, 168 insertions(+), 109 deletions(-)

drivers/gpu/drm/ast/ast_drv.h +5 -1

@@ -113,7 +113,11 @@ struct ast_private {
 	struct ttm_bo_kmap_obj cache_kmap;
 	int next_cursor;
 	bool support_wide_screen;
-	bool DisableP2A;
+	enum {
+		ast_use_p2a,
+		ast_use_dt,
+		ast_use_defaults
+	} config_mode;
 
 	enum ast_tx_chip tx_chip_type;
 	u8 dp501_maxclk;

drivers/gpu/drm/ast/ast_main.c +161 ~~-103~~

314 lines not on this page · raw message

drivers/gpu/drm/ast/ast_post.c +2 -5

@@ -375,17 +375,14 @@ void ast_post_gpu(struct drm_device *dev
 	ast_enable_mmio(dev);
 	ast_set_def_ext_reg(dev);
 
-	if (ast->DisableP2A == false)
-	{
+	if (ast->config_mode == ast_use_p2a) {
 		if (ast->chip == AST2300 || ast->chip == AST2400)
 			ast_init_dram_2300(dev);
 		else
 			ast_init_dram_reg(dev);
 
 		ast_init_3rdtx(dev);
-	}
-	else
-	{
+	} else {
 		if (ast->tx_chip_type != AST_TX_NONE)
 			ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xa3, 0xcf, 0x80);	/* Enable DVO */
 	}

Greg Kroah-Hartman

author maintainer

2017-07-03 13:37 UTC #23 lore raw

PATCH 21/101 mm, swap_cgroup: reschedule when neeed in swap_cgroup_swapoff()

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: David Rientjes <[email protected]>

commit 460bcec84e11c75122ace5976214abbc596eb91b upstream.

We got need_resched() warnings in swap_cgroup_swapoff() because swap_cgroup_ctrl[type].length is particularly large.

Reschedule when needed.

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

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

Acked-by Michal Hocko <[email protected]>

Cc Johannes Weiner <[email protected]>

Cc Vladimir Davydov <[email protected]>

Cc KAMEZAWA Hiroyuki <[email protected]>

Cc Ben Hutchings <[email protected]>

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

---
 mm/swap_cgroup.c |    2 ++
 1 file changed, 2 insertions(+)

mm/swap_cgroup.c +2 -0

@@ -205,6 +205,8 @@ void swap_cgroup_swapoff(int type)
 			struct page *page = map[i];
 			if (page)
 				__free_page(page);
+			if (!(i % SWAP_CLUSTER_MAX))
+				cond_resched();
 		}
 		vfree(map);
 	}

Greg Kroah-Hartman

author maintainer

2017-07-03 13:37 UTC #24 lore raw

PATCH 22/101 MIPS: Avoid accidental raw backtrace

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: James Hogan <[email protected]>

commit 854236363370995a609a10b03e35fd3dc5e9e4a1 upstream.

Since commit 81a76d7119f6 ("MIPS: Avoid using unwind_stack() with usermode") show_backtrace() invokes the raw backtracer when cp0_status & ST0_KSU indicates user mode to fix issues on EVA kernels where user and kernel address spaces overlap.

However this is used by show_stack() which creates its own pt_regs on the stack and leaves cp0_status uninitialised in most of the code paths. This results in the non deterministic use of the raw back tracer depending on the previous stack content.

show_stack() deals exclusively with kernel mode stacks anyway, so explicitly initialise regs.cp0_status to KSU_KERNEL (i.e. 0) to ensure we get a useful backtrace.

Fixes 81a76d7119f6 ("MIPS: Avoid using unwind_stack() with usermode")

Signed-off-by James Hogan <[email protected]>

Patchwork: https://patchwork.linux-mips.org/patch/16656/

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

---
 arch/mips/kernel/traps.c |    2 ++
 1 file changed, 2 insertions(+)

arch/mips/kernel/traps.c +2 -0

@@ -194,6 +194,8 @@ void show_stack(struct task_struct *task
 {
 	struct pt_regs regs;
 	mm_segment_t old_fs = get_fs();
+
+	regs.cp0_status = KSU_KERNEL;
 	if (sp) {
 		regs.regs[29] = (unsigned long)sp;
 		regs.regs[31] = 0;

Greg Kroah-Hartman

author maintainer

2017-07-03 13:37 UTC #25 lore raw

PATCH 23/101 MIPS: pm-cps: Drop manual cache-line alignment of ready_count

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Paul Burton <[email protected]>

commit 161c51ccb7a6faf45ffe09aa5cf1ad85ccdad503 upstream.

We allocate memory for a ready_count variable per-CPU, which is accessed via a cached non-coherent TLB mapping to perform synchronisation between threads within the core using LL/SC instructions. In order to ensure that the variable is contained within its own data cache line we allocate 2 lines worth of memory & align the resulting pointer to a line boundary. This is however unnecessary, since kmalloc is guaranteed to return memory which is at least cache-line aligned (see ARCH_DMA_MINALIGN). Stop the redundant manual alignment.

Besides cleaning up the code & avoiding needless work, this has the side effect of avoiding an arithmetic error found by Bryan on 64 bit systems due to the 32 bit size of the former dlinesz. This led the ready_count variable to have its upper 32b cleared erroneously for MIPS64 kernels, causing problems when ready_count was later used on MIPS64 via cpuidle.

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

Fixes 3179d37ee1ed ("MIPS: pm-cps: add PM state entry code for CPS systems")

Reported-by Bryan O'Donoghue <[email protected]>

Reviewed-by Bryan O'Donoghue <[email protected]>

Tested-by Bryan O'Donoghue <[email protected]>

Patchwork: https://patchwork.linux-mips.org/patch/15383/

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

---
 arch/mips/kernel/pm-cps.c |    9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

arch/mips/kernel/pm-cps.c +1 -8

@@ -55,7 +55,6 @@ DECLARE_BITMAP(state_support, CPS_PM_STA
  * state. Actually per-core rather than per-CPU.
  */
 static DEFINE_PER_CPU_ALIGNED(u32*, ready_count);
-static DEFINE_PER_CPU_ALIGNED(void*, ready_count_alloc);
 
 /* Indicates online CPUs coupled with the current CPU */
 static DEFINE_PER_CPU_ALIGNED(cpumask_t, online_coupled);

@@ -625,7 +624,6 @@ static int __init cps_gen_core_entries(u
 {
 	enum cps_pm_state state;
 	unsigned core = cpu_data[cpu].core;
-	unsigned dlinesz = cpu_data[cpu].dcache.linesz;
 	void *entry_fn, *core_rc;
 
 	for (state = CPS_PM_NC_WAIT; state < CPS_PM_STATE_COUNT; state++) {

@@ -645,16 +643,11 @@ static int __init cps_gen_core_entries(u
 	}
 
 	if (!per_cpu(ready_count, core)) {
-		core_rc = kmalloc(dlinesz * 2, GFP_KERNEL);
+		core_rc = kmalloc(sizeof(u32), GFP_KERNEL);
 		if (!core_rc) {
 			pr_err("Failed allocate core %u ready_count\n", core);
 			return -ENOMEM;
 		}
-		per_cpu(ready_count_alloc, core) = core_rc;
-
-		/* Ensure ready_count is aligned to a cacheline boundary */
-		core_rc += dlinesz - 1;
-		core_rc = (void *)((unsigned long)core_rc & ~(dlinesz - 1));
 		per_cpu(ready_count, core) = core_rc;
 	}

Greg Kroah-Hartman

author maintainer

2017-07-03 13:34 UTC #26 lore raw

PATCH 24/101 MIPS: Fix IRQ tracing & lockdep when rescheduling

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Paul Burton <[email protected]>

commit d8550860d910c6b7b70f830f59003b33daaa52c9 upstream.

When the scheduler sets TIF_NEED_RESCHED & we call into the scheduler from arch/mips/kernel/entry.S we disable interrupts. This is true regardless of whether we reach work_resched from syscall_exit_work, resume_userspace or by looping after calling schedule(). Although we disable interrupts in these paths we don't call trace_hardirqs_off() before calling into C code which may acquire locks, and we therefore leave lockdep with an inconsistent view of whether interrupts are disabled or not when CONFIG_PROVE_LOCKING & CONFIG_DEBUG_LOCKDEP are both enabled.

Without tracing this interrupt state lockdep will print warnings such as the following once a task returns from a syscall via syscall_exit_partial with TIF_NEED_RESCHED set:

[   49.927678] ------------[ cut here ]------------
[   49.934445] WARNING: CPU: 0 PID: 1 at kernel/locking/lockdep.c:3687 check_flags.part.41+0x1dc/0x1e8
[   49.946031] DEBUG_LOCKS_WARN_ON(current->hardirqs_enabled)
[   49.946355] CPU: 0 PID: 1 Comm: init Not tainted 4.10.0-00439-gc9fd5d362289-dirty #197
[   49.963505] Stack : 0000000000000000 ffffffff81bb5d6a 0000000000000006 ffffffff801ce9c4
[   49.974431]         0000000000000000 0000000000000000 0000000000000000 000000000000004a
[   49.985300]         ffffffff80b7e487 ffffffff80a24498 a8000000ff160000 ffffffff80ede8b8
[   49.996194]         0000000000000001 0000000000000000 0000000000000000 0000000077c8030c
[   50.007063]         000000007fd8a510 ffffffff801cd45c 0000000000000000 a8000000ff127c88
[   50.017945]         0000000000000000 ffffffff801cf928 0000000000000001 ffffffff80a24498
[   50.028827]         0000000000000000 0000000000000001 0000000000000000 0000000000000000
[   50.039688]         0000000000000000 a8000000ff127bd0 0000000000000000 ffffffff805509bc
[   50.050575]         00000000140084e0 0000000000000000 0000000000000000 0000000000040a00
[   50.061448]         0000000000000000 ffffffff8010e1b0 0000000000000000 ffffffff805509bc
[   50.072327]         ...
[   50.076087] Call Trace:
[   50.079869] [<ffffffff8010e1b0>] show_stack+0x80/0xa8
[   50.086577] [<ffffffff805509bc>] dump_stack+0x10c/0x190
[   50.093498] [<ffffffff8015dde0>] __warn+0xf0/0x108
[   50.099889] [<ffffffff8015de34>] warn_slowpath_fmt+0x3c/0x48
[   50.107241] [<ffffffff801c15b4>] check_flags.part.41+0x1dc/0x1e8
[   50.114961] [<ffffffff801c239c>] lock_is_held_type+0x8c/0xb0
[   50.122291] [<ffffffff809461b8>] __schedule+0x8c0/0x10f8
[   50.129221] [<ffffffff80946a60>] schedule+0x30/0x98
[   50.135659] [<ffffffff80106278>] work_resched+0x8/0x34
[   50.142397] ---[ end trace 0cb4f6ef5b99fe21 ]---
[   50.148405] possible reason: unannotated irqs-off.
[   50.154600] irq event stamp: 400463
[   50.159566] hardirqs last  enabled at (400463): [<ffffffff8094edc8>] _raw_spin_unlock_irqrestore+0x40/0xa8
[   50.171981] hardirqs last disabled at (400462): [<ffffffff8094eb98>] _raw_spin_lock_irqsave+0x30/0xb0
[   50.183897] softirqs last  enabled at (400450): [<ffffffff8016580c>] __do_softirq+0x4ac/0x6a8
[   50.195015] softirqs last disabled at (400425): [<ffffffff80165e78>] irq_exit+0x110/0x128

Fix this by using the TRACE_IRQS_OFF macro to call trace_hardirqs_off() when CONFIG_TRACE_IRQFLAGS is enabled. This is done before invoking schedule() following the work_resched label because:

1) Interrupts are disabled regardless of the path we take to reach work_resched() & schedule().

2) Performing the tracing here avoids the need to do it in paths which disable interrupts but don't call out to C code before hitting a path which uses the RESTORE_SOME macro that will call trace_hardirqs_on() or trace_hardirqs_off() as appropriate.

We call trace_hardirqs_on() using the TRACE_IRQS_ON macro before calling syscall_trace_leave() for similar reasons, ensuring that lockdep has a consistent view of state after we re-enable interrupts.

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

Fixes 1da177e4c3f4 ("Linux-2.6.12-rc2")

Patchwork: https://patchwork.linux-mips.org/patch/15385/

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

---
 arch/mips/kernel/entry.S |    3 +++
 1 file changed, 3 insertions(+)

arch/mips/kernel/entry.S +3 -0

@@ -11,6 +11,7 @@
 #include <asm/asm.h>
 #include <asm/asmmacro.h>
 #include <asm/compiler.h>
+#include <asm/irqflags.h>
 #include <asm/regdef.h>
 #include <asm/mipsregs.h>
 #include <asm/stackframe.h>

@@ -137,6 +138,7 @@ work_pending:
 	andi	t0, a2, _TIF_NEED_RESCHED # a2 is preloaded with TI_FLAGS
 	beqz	t0, work_notifysig
 work_resched:
+	TRACE_IRQS_OFF
 	jal	schedule
 
 	local_irq_disable		# make sure need_resched and

@@ -173,6 +175,7 @@ syscall_exit_work:
 	beqz	t0, work_pending	# trace bit set?
 	local_irq_enable		# could let syscall_trace_leave()
 					# call schedule() instead
+	TRACE_IRQS_ON
 	move	a0, sp
 	jal	syscall_trace_leave
 	b	resume_userspace

Greg Kroah-Hartman

author maintainer

2017-07-03 13:37 UTC #27 lore raw

PATCH 25/101 ALSA: hda - Fix endless loop of codec configure

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Takashi Iwai <[email protected]>

commit d94815f917da770d42c377786dc428f542e38f71 upstream.

azx_codec_configure() loops over the codecs found on the given controller via a linked list. The code used to work in the past, but in the current version, this may lead to an endless loop when a codec binding returns an error.

The culprit is that the snd_hda_codec_configure() unregisters the device upon error, and this eventually deletes the given codec object from the bus. Since the list is initialized via list_del_init(), the next object points to the same device itself. This behavior change was introduced at splitting the HD-audio code code, and forgotten to adapt it here.

For fixing this bug, just use a *_safe() version of list iteration.

Fixes d068ebc25e6e ("ALSA: hda - Move some codes up to hdac_bus struct")

Reported-by Daniel Vetter <[email protected]>

Signed-off-by Takashi Iwai <[email protected]>

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

---
 sound/pci/hda/hda_codec.h      |    2 ++
 sound/pci/hda/hda_controller.c |    8 ++++++--
 2 files changed, 8 insertions(+), 2 deletions(-)

sound/pci/hda/hda_codec.h +2 -0

@@ -294,6 +294,8 @@ struct hda_codec {
 
 #define list_for_each_codec(c, bus) \
 	list_for_each_entry(c, &(bus)->core.codec_list, core.list)
+#define list_for_each_codec_safe(c, n, bus)				\
+	list_for_each_entry_safe(c, n, &(bus)->core.codec_list, core.list)
 
 /* snd_hda_codec_read/write optional flags */
 #define HDA_RW_NO_RESPONSE_FALLBACK	(1 << 0)

sound/pci/hda/hda_controller.c +6 -2

@@ -1128,8 +1128,12 @@ EXPORT_SYMBOL_GPL(azx_probe_codecs);
 /* configure each codec instance */
 int azx_codec_configure(struct azx *chip)
 {
-	struct hda_codec *codec;
-	list_for_each_codec(codec, &chip->bus) {
+	struct hda_codec *codec, *next;
+
+	/* use _safe version here since snd_hda_codec_configure() deregisters
+	 * the device upon error and deletes itself from the bus list.
+	 */
+	list_for_each_codec_safe(codec, next, &chip->bus) {
 		snd_hda_codec_configure(codec);
 	}
 	return 0;

Greg Kroah-Hartman

author maintainer

2017-07-03 13:34 UTC #28 lore raw

PATCH 26/101 ALSA: hda - set input_path bitmap to zero after moving it to new place

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Hui Wang <[email protected]>

commit a8f20fd25bdce81a8e41767c39f456d346b63427 upstream.

Recently we met a problem, the codec has valid adcs and input pins, and they can form valid input paths, but the driver does not build valid controls for them like "Mic boost", "Capture Volume" and "Capture Switch".

Through debugging, I found the driver needs to shrink the invalid adcs and input paths for this machine, so it will move the whole column bitmap value to the previous column, after moving it, the driver forgets to set the original column bitmap value to zero, as a result, the driver will invalidate the path whose index value is the original colume bitmap value. After executing this function, all valid input paths are invalidated by a mistake, there are no any valid input paths, so the driver won't build controls for them.

Fixes 3a65bcdc577a ("ALSA: hda - Fix inconsistent input_paths after ADC reduction")

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

Signed-off-by Takashi Iwai <[email protected]>

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

---
 sound/pci/hda/hda_generic.c |    1 +
 1 file changed, 1 insertion(+)

sound/pci/hda/hda_generic.c +1 -0

@@ -3190,6 +3190,7 @@ static int check_dyn_adc_switch(struct h
 						spec->input_paths[i][nums]);
 					spec->input_paths[i][nums] =
 						spec->input_paths[i][n];
+					spec->input_paths[i][n] = 0;
 				}
 			}
 			nums++;

Greg Kroah-Hartman

author maintainer

2017-07-03 13:37 UTC #29 lore raw

PATCH 27/101 drm/vmwgfx: Free hash table allocated by cmdbuf managed res mgr

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Deepak Rawat <[email protected]>

commit 82fcee526ba8ca2c5d378bdf51b21b7eb058fe3a upstream.

The hash table created during vmw_cmdbuf_res_man_create was never freed. This causes memory leak in context creation. Added the corresponding drm_ht_remove in vmw_cmdbuf_res_man_destroy.

Tested for memory leak by running piglit overnight and kernel memory is not inflated which earlier was.

Signed-off-by Deepak Rawat <[email protected]>

Reviewed-by Sinclair Yeh <[email protected]>

Signed-off-by Thomas Hellstrom <[email protected]>

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

---
 drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c |    1 +
 1 file changed, 1 insertion(+)

drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c +1 -0

@@ -321,6 +321,7 @@ void vmw_cmdbuf_res_man_destroy(struct v
 	list_for_each_entry_safe(entry, next, &man->list, head)
 		vmw_cmdbuf_res_free(man, entry);
 
+	drm_ht_remove(&man->resources);
 	kfree(man);
 }

Greg Kroah-Hartman

author maintainer

2017-07-03 13:37 UTC #30 lore raw

PATCH 28/101 usb: gadget: f_fs: Fix possibe deadlock

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Baolin Wang <[email protected]>

commit b3ce3ce02d146841af012d08506b4071db8ffde3 upstream.

When system try to close /dev/usb-ffs/adb/ep0 on one core, at the same time another core try to attach new UDC, which will cause deadlock as below scenario. Thus we should release ffs lock before issuing unregister_gadget_item().

[   52.642225] c1 ======================================================
[   52.642228] c1 [ INFO: possible circular locking dependency detected ]
[   52.642236] c1 4.4.6+ #1 Tainted: G        W  O
[   52.642241] c1 -------------------------------------------------------
[   52.642245] c1 usb ffs open/2808 is trying to acquire lock:
[   52.642270] c0  (udc_lock){+.+.+.}, at: [<ffffffc00065aeec>]
		usb_gadget_unregister_driver+0x3c/0xc8
[   52.642272] c1  but task is already holding lock:
[   52.642283] c0  (ffs_lock){+.+.+.}, at: [<ffffffc00066b244>]
		ffs_data_clear+0x30/0x140
[   52.642285] c1 which lock already depends on the new lock.
[   52.642287] c1
               the existing dependency chain (in reverse order) is:
[   52.642295] c0
	       -> #1 (ffs_lock){+.+.+.}:
[   52.642307] c0        [<ffffffc00012340c>] __lock_acquire+0x20f0/0x2238
[   52.642314] c0        [<ffffffc000123b54>] lock_acquire+0xe4/0x298
[   52.642322] c0        [<ffffffc000aaf6e8>] mutex_lock_nested+0x7c/0x3cc
[   52.642328] c0        [<ffffffc00066f7bc>] ffs_func_bind+0x504/0x6e8
[   52.642334] c0        [<ffffffc000654004>] usb_add_function+0x84/0x184
[   52.642340] c0        [<ffffffc000658ca4>] configfs_composite_bind+0x264/0x39c
[   52.642346] c0        [<ffffffc00065b348>] udc_bind_to_driver+0x58/0x11c
[   52.642352] c0        [<ffffffc00065b49c>] usb_udc_attach_driver+0x90/0xc8
[   52.642358] c0        [<ffffffc0006598e0>] gadget_dev_desc_UDC_store+0xd4/0x128
[   52.642369] c0        [<ffffffc0002c14e8>] configfs_write_file+0xd0/0x13c
[   52.642376] c0        [<ffffffc00023c054>] vfs_write+0xb8/0x214
[   52.642381] c0        [<ffffffc00023cad4>] SyS_write+0x54/0xb0
[   52.642388] c0        [<ffffffc000085ff0>] el0_svc_naked+0x24/0x28
[   52.642395] c0
              -> #0 (udc_lock){+.+.+.}:
[   52.642401] c0        [<ffffffc00011e3d0>] print_circular_bug+0x84/0x2e4
[   52.642407] c0        [<ffffffc000123454>] __lock_acquire+0x2138/0x2238
[   52.642412] c0        [<ffffffc000123b54>] lock_acquire+0xe4/0x298
[   52.642420] c0        [<ffffffc000aaf6e8>] mutex_lock_nested+0x7c/0x3cc
[   52.642427] c0        [<ffffffc00065aeec>] usb_gadget_unregister_driver+0x3c/0xc8
[   52.642432] c0        [<ffffffc00065995c>] unregister_gadget_item+0x28/0x44
[   52.642439] c0        [<ffffffc00066b34c>] ffs_data_clear+0x138/0x140
[   52.642444] c0        [<ffffffc00066b374>] ffs_data_reset+0x20/0x6c
[   52.642450] c0        [<ffffffc00066efd0>] ffs_data_closed+0xac/0x12c
[   52.642454] c0        [<ffffffc00066f070>] ffs_ep0_release+0x20/0x2c
[   52.642460] c0        [<ffffffc00023dbe4>] __fput+0xb0/0x1f4
[   52.642466] c0        [<ffffffc00023dd9c>] ____fput+0x20/0x2c
[   52.642473] c0        [<ffffffc0000ee944>] task_work_run+0xb4/0xe8
[   52.642482] c0        [<ffffffc0000cd45c>] do_exit+0x360/0xb9c
[   52.642487] c0        [<ffffffc0000cf228>] do_group_exit+0x4c/0xb0
[   52.642494] c0        [<ffffffc0000dd3c8>] get_signal+0x380/0x89c
[   52.642501] c0        [<ffffffc00008a8f0>] do_signal+0x154/0x518
[   52.642507] c0        [<ffffffc00008af00>] do_notify_resume+0x70/0x78
[   52.642512] c0        [<ffffffc000085ee8>] work_pending+0x1c/0x20
[   52.642514] c1
              other info that might help us debug this:
[   52.642517] c1  Possible unsafe locking scenario:
[   52.642518] c1        CPU0                    CPU1
[   52.642520] c1        ----                    ----
[   52.642525] c0   lock(ffs_lock);
[   52.642529] c0                                lock(udc_lock);
[   52.642533] c0                                lock(ffs_lock);
[   52.642537] c0   lock(udc_lock);
[   52.642539] c1
                      *** DEADLOCK ***
[   52.642543] c1 1 lock held by usb ffs open/2808:
[   52.642555] c0  #0:  (ffs_lock){+.+.+.}, at: [<ffffffc00066b244>]
		ffs_data_clear+0x30/0x140
[   52.642557] c1 stack backtrace:
[   52.642563] c1 CPU: 1 PID: 2808 Comm: usb ffs open Tainted: G
[   52.642565] c1 Hardware name: Spreadtrum SP9860g Board (DT)
[   52.642568] c1 Call trace:
[   52.642573] c1 [<ffffffc00008b430>] dump_backtrace+0x0/0x170
[   52.642577] c1 [<ffffffc00008b5c0>] show_stack+0x20/0x28
[   52.642583] c1 [<ffffffc000422694>] dump_stack+0xa8/0xe0
[   52.642587] c1 [<ffffffc00011e548>] print_circular_bug+0x1fc/0x2e4
[   52.642591] c1 [<ffffffc000123454>] __lock_acquire+0x2138/0x2238
[   52.642595] c1 [<ffffffc000123b54>] lock_acquire+0xe4/0x298
[   52.642599] c1 [<ffffffc000aaf6e8>] mutex_lock_nested+0x7c/0x3cc
[   52.642604] c1 [<ffffffc00065aeec>] usb_gadget_unregister_driver+0x3c/0xc8
[   52.642608] c1 [<ffffffc00065995c>] unregister_gadget_item+0x28/0x44
[   52.642613] c1 [<ffffffc00066b34c>] ffs_data_clear+0x138/0x140
[   52.642618] c1 [<ffffffc00066b374>] ffs_data_reset+0x20/0x6c
[   52.642621] c1 [<ffffffc00066efd0>] ffs_data_closed+0xac/0x12c
[   52.642625] c1 [<ffffffc00066f070>] ffs_ep0_release+0x20/0x2c
[   52.642629] c1 [<ffffffc00023dbe4>] __fput+0xb0/0x1f4
[   52.642633] c1 [<ffffffc00023dd9c>] ____fput+0x20/0x2c
[   52.642636] c1 [<ffffffc0000ee944>] task_work_run+0xb4/0xe8
[   52.642640] c1 [<ffffffc0000cd45c>] do_exit+0x360/0xb9c
[   52.642644] c1 [<ffffffc0000cf228>] do_group_exit+0x4c/0xb0
[   52.642647] c1 [<ffffffc0000dd3c8>] get_signal+0x380/0x89c
[   52.642651] c1 [<ffffffc00008a8f0>] do_signal+0x154/0x518
[   52.642656] c1 [<ffffffc00008af00>] do_notify_resume+0x70/0x78
[   52.642659] c1 [<ffffffc000085ee8>] work_pending+0x1c/0x20

Acked-by Michal Nazarewicz <[email protected]>

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

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

Cc Jerry Zhang <[email protected]>

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

---
 drivers/usb/gadget/function/f_fs.c |    8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

drivers/usb/gadget/function/f_fs.c +6 -2

@@ -3463,6 +3463,7 @@ static void ffs_closed(struct ffs_data *
 {
 	struct ffs_dev *ffs_obj;
 	struct f_fs_opts *opts;
+	struct config_item *ci;
 
 	ENTER();
 	ffs_dev_lock();

@@ -3486,8 +3487,11 @@ static void ffs_closed(struct ffs_data *
 	    || !atomic_read(&opts->func_inst.group.cg_item.ci_kref.refcount))
 		goto done;
 
-	unregister_gadget_item(ffs_obj->opts->
-			       func_inst.group.cg_item.ci_parent->ci_parent);
+	ci = opts->func_inst.group.cg_item.ci_parent->ci_parent;
+	ffs_dev_unlock();
+
+	unregister_gadget_item(ci);
+	return;
 done:
 	ffs_dev_unlock();
 }

Greg Kroah-Hartman

author maintainer

2017-07-03 13:37 UTC #31 lore raw

PATCH 29/101 sysctl: enable strict writes

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Kees Cook <[email protected]>

commit 41662f5cc55335807d39404371cfcbb1909304c4 upstream.

SYSCTL_WRITES_WARN was added in commit f4aacea2f5d1 ("sysctl: allow for strict write position handling"), and released in v3.16 in August of 2014. Since then I can find only 1 instance of non-zero offset writing[1], and it was fixed immediately in CRIU[2]. As such, it appears safe to flip this to the strict state now.

[1] https://www.google.com/search?q="when%20file%20position%20was%20not%200"
[2] http://lists.openvz.org/pipermail/criu/2015-April/019819.html

Signed-off-by Kees Cook <[email protected]>

Cc "Eric W. Biederman" <[email protected]>

Cc Sumit Semwal <[email protected]>

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

---
 Documentation/sysctl/kernel.txt |   15 +++++++--------
 kernel/sysctl.c                 |    2 +-
 2 files changed, 8 insertions(+), 9 deletions(-)

Documentation/sysctl/kernel.txt +7 -8

@@ -810,14 +810,13 @@ via the /proc/sys interface:
        Each write syscall must fully contain the sysctl value to be
        written, and multiple writes on the same sysctl file descriptor
        will rewrite the sysctl value, regardless of file position.
-   0 - (default) Same behavior as above, but warn about processes that
-       perform writes to a sysctl file descriptor when the file position
-       is not 0.
-   1 - Respect file position when writing sysctl strings. Multiple writes
-       will append to the sysctl value buffer. Anything past the max length
-       of the sysctl value buffer will be ignored. Writes to numeric sysctl
-       entries must always be at file position 0 and the value must be
-       fully contained in the buffer sent in the write syscall.
+   0 - Same behavior as above, but warn about processes that perform writes
+       to a sysctl file descriptor when the file position is not 0.
+   1 - (default) Respect file position when writing sysctl strings. Multiple
+       writes will append to the sysctl value buffer. Anything past the max
+       length of the sysctl value buffer will be ignored. Writes to numeric
+       sysctl entries must always be at file position 0 and the value must
+       be fully contained in the buffer sent in the write syscall.
 
 ==============================================================

kernel/sysctl.c +1 -1

@@ -174,7 +174,7 @@ extern int no_unaligned_warning;
 #define SYSCTL_WRITES_WARN	 0
 #define SYSCTL_WRITES_STRICT	 1
 
-static int sysctl_writes_strict = SYSCTL_WRITES_WARN;
+static int sysctl_writes_strict = SYSCTL_WRITES_STRICT;
 
 static int proc_do_cad_pid(struct ctl_table *table, int write,
 		  void __user *buffer, size_t *lenp, loff_t *ppos);

Greg Kroah-Hartman

author maintainer

2017-07-03 13:34 UTC #32 lore raw

PATCH 30/101 block: fix module reference leak on put_disk() call for cgroups throttle

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Roman Pen <[email protected]>

commit 39a169b62b415390398291080dafe63aec751e0a upstream.

get_disk(),get_gendisk() calls have non explicit side effect: they increase the reference on the disk owner module.

The following is the correct sequence how to get a disk reference and to put it:

    disk = get_gendisk(...);

    /* use disk */

    owner = disk->fops->owner;
    put_disk(disk);
    module_put(owner);

fs/block_dev.c is aware of this required module_put() call, but f.e. blkg_conf_finish(), which is located in block/blk-cgroup.c, does not put a module reference. To see a leakage in action cgroups throttle config can be used. In the following script I'm removing throttle for /dev/ram0 (actually this is NOP, because throttle was never set for this device):

    # lsmod | grep brd
    brd                     5175  0
    # i=100; while [ $i -gt 0 ]; do echo "1:0 0" > \
        /sys/fs/cgroup/blkio/blkio.throttle.read_bps_device; i=$(($i - 1)); \
    done
    # lsmod | grep brd
    brd                     5175  100

Now brd module has 100 references.

The issue is fixed by calling module_put() just right away put_disk().

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

Cc Gi-Oh Kim <[email protected]>

Cc Tejun Heo <[email protected]>

Cc Jens Axboe <[email protected]>

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

Cc Sumit Semwal <[email protected]>

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

---
 block/blk-cgroup.c |    9 +++++++++
 1 file changed, 9 insertions(+)

block/blk-cgroup.c +9 -0

@@ -788,6 +788,7 @@ int blkg_conf_prep(struct blkcg *blkcg,
 {
 	struct gendisk *disk;
 	struct blkcg_gq *blkg;
+	struct module *owner;
 	unsigned int major, minor;
 	int key_len, part, ret;
 	char *body;

@@ -804,7 +805,9 @@ int blkg_conf_prep(struct blkcg *blkcg,
 	if (!disk)
 		return -ENODEV;
 	if (part) {
+		owner = disk->fops->owner;
 		put_disk(disk);
+		module_put(owner);
 		return -ENODEV;
 	}

@@ -820,7 +823,9 @@ int blkg_conf_prep(struct blkcg *blkcg,
 		ret = PTR_ERR(blkg);
 		rcu_read_unlock();
 		spin_unlock_irq(disk->queue->queue_lock);
+		owner = disk->fops->owner;
 		put_disk(disk);
+		module_put(owner);
 		/*
 		 * If queue was bypassing, we should retry.  Do so after a
 		 * short msleep().  It isn't strictly necessary but queue

@@ -851,9 +856,13 @@ EXPORT_SYMBOL_GPL(blkg_conf_prep);
 void blkg_conf_finish(struct blkg_conf_ctx *ctx)
 	__releases(ctx->disk->queue->queue_lock) __releases(rcu)
 {
+	struct module *owner;
+
 	spin_unlock_irq(ctx->disk->queue->queue_lock);
 	rcu_read_unlock();
+	owner = ctx->disk->fops->owner;
 	put_disk(ctx->disk);
+	module_put(owner);
 }
 EXPORT_SYMBOL_GPL(blkg_conf_finish);

Greg Kroah-Hartman

author maintainer

2017-07-03 13:34 UTC #33 lore raw

PATCH 31/101 mm: numa: avoid waiting on freed migrated pages

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Mark Rutland <[email protected]>

commit 3c226c637b69104f6b9f1c6ec5b08d7b741b3229 upstream.

In do_huge_pmd_numa_page(), we attempt to handle a migrating thp pmd by waiting until the pmd is unlocked before we return and retry. However, we can race with migrate_misplaced_transhuge_page():

    // do_huge_pmd_numa_page                // migrate_misplaced_transhuge_page()
    // Holds 0 refs on page                 // Holds 2 refs on page

    vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
    /* ... */
    if (pmd_trans_migrating(*vmf->pmd)) {
            page = pmd_page(*vmf->pmd);
            spin_unlock(vmf->ptl);
                                            ptl = pmd_lock(mm, pmd);
                                            if (page_count(page) != 2)) {
                                                    /* roll back */
                                            }
                                            /* ... */
                                            mlock_migrate_page(new_page, page);
                                            /* ... */
                                            spin_unlock(ptl);
                                            put_page(page);
                                            put_page(page); // page freed here
            wait_on_page_locked(page);
            goto out;
    }

This can result in the freed page having its waiters flag set unexpectedly, which trips the PAGE_FLAGS_CHECK_AT_PREP checks in the page alloc/free functions. This has been observed on arm64 KVM guests.

We can avoid this by having do_huge_pmd_numa_page() take a reference on the page before dropping the pmd lock, mirroring what we do in __migration_entry_wait().

When we hit the race, migrate_misplaced_transhuge_page() will see the reference and abort the migration, as it may do today in other cases.

Fixes b8916634b77bffb2 ("mm: Prevent parallel splits during THP migration")

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

Signed-off-by Mark Rutland <[email protected]>

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

Acked-by Steve Capper <[email protected]>

Acked-by Kirill A. Shutemov <[email protected]>

Acked-by Vlastimil Babka <[email protected]>

Cc Mel Gorman <[email protected]>

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

---
 mm/huge_memory.c |    6 ++++++
 1 file changed, 6 insertions(+)

mm/huge_memory.c +6 -0

@@ -1363,8 +1363,11 @@ int do_huge_pmd_numa_page(struct mm_stru
 	 */
 	if (unlikely(pmd_trans_migrating(*pmdp))) {
 		page = pmd_page(*pmdp);
+		if (!get_page_unless_zero(page))
+			goto out_unlock;
 		spin_unlock(ptl);
 		wait_on_page_locked(page);
+		put_page(page);
 		goto out;
 	}

@@ -1396,8 +1399,11 @@ int do_huge_pmd_numa_page(struct mm_stru
 
 	/* Migration could have started since the pmd_trans_migrating check */
 	if (!page_locked) {
+		if (!get_page_unless_zero(page))
+			goto out_unlock;
 		spin_unlock(ptl);
 		wait_on_page_locked(page);
+		put_page(page);
 		page_nid = -1;
 		goto out;
 	}

Greg Kroah-Hartman

author maintainer

2017-07-03 13:38 UTC #34 lore raw

PATCH 33/101 scsi: sd: Fix wrong DPOFUA disable in sd_read_cache_type

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Damien Le Moal <[email protected]>

[ Upstream commit 26f2819772af891dee2843e1f8662c58e5129d5f ]

Zoned block devices force the use of READ/WRITE(16) commands by setting sdkp->use_16_for_rw and clearing sdkp->use_10_for_rw. This result in DPOFUA always being disabled for these drives as the assumed use of the deprecated READ/WRITE(6) commands only looks at sdkp->use_10_for_rw. Strenghten the test by also checking that sdkp->use_16_for_rw is false.

Signed-off-by Damien Le Moal <[email protected]>

Reviewed-by Hannes Reinecke <[email protected]>

Signed-off-by Martin K. Petersen <[email protected]>

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

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

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

drivers/scsi/sd.c +2 -1

@@ -2566,7 +2566,8 @@ sd_read_cache_type(struct scsi_disk *sdk
 		if (sdp->broken_fua) {
 			sd_first_printk(KERN_NOTICE, sdkp, "Disabling FUA\n");
 			sdkp->DPOFUA = 0;
-		} else if (sdkp->DPOFUA && !sdkp->device->use_10_for_rw) {
+		} else if (sdkp->DPOFUA && !sdkp->device->use_10_for_rw &&
+			   !sdkp->device->use_16_for_rw) {
 			sd_first_printk(KERN_NOTICE, sdkp,
 				  "Uses READ/WRITE(6), disabling FUA\n");
 			sdkp->DPOFUA = 0;

Greg Kroah-Hartman

author maintainer

2017-07-03 13:38 UTC #35 lore raw

PATCH 34/101 scsi: lpfc: Set elsiocb contexts to NULL after freeing it

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Johannes Thumshirn <[email protected]>

[ Upstream commit 8667f515952feefebb3c0f8d9a9266c91b101a46 ]

Set the elsiocb contexts to NULL after freeing as others depend on it.

Signed-off-by Johannes Thumshirn <[email protected]>

Acked-by Dick Kennedy <[email protected]>

Signed-off-by Martin K. Petersen <[email protected]>

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

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

---
 drivers/scsi/lpfc/lpfc_els.c |    2 ++
 1 file changed, 2 insertions(+)

drivers/scsi/lpfc/lpfc_els.c +2 -0

@@ -3563,12 +3563,14 @@ lpfc_els_free_iocb(struct lpfc_hba *phba
 		} else {
 			buf_ptr1 = (struct lpfc_dmabuf *) elsiocb->context2;
 			lpfc_els_free_data(phba, buf_ptr1);
+			elsiocb->context2 = NULL;
 		}
 	}
 
 	if (elsiocb->context3) {
 		buf_ptr = (struct lpfc_dmabuf *) elsiocb->context3;
 		lpfc_els_free_bpl(phba, buf_ptr);
+		elsiocb->context3 = NULL;
 	}
 	lpfc_sli_release_iocbq(phba, elsiocb);
 	return 0;

Greg Kroah-Hartman

author maintainer

2017-07-03 13:38 UTC #36 lore raw

PATCH 35/101 qla2xxx: Fix erroneous invalid handle message

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Quinn Tran <[email protected]>

[ Upstream commit 4f060736f29a960aba8e781a88837464756200a8 ]

Termination of Immediate Notify IOCB was using wrong IOCB handle. IOCB completion code was unable to find appropriate code path due to wrong handle.

Following message is seen in the logs.

"Error entry - invalid handle/queue (ffff)."

Signed-off-by Quinn Tran <[email protected]>

Signed-off-by Himanshu Madhani <[email protected]>

Reviewed-by Christoph Hellwig <[email protected]>

[ bvanassche: Fixed word order in patch title ]

Signed-off-by Bart Van Assche <[email protected]>

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

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

---
 drivers/scsi/qla2xxx/qla_isr.c    |    4 ++++
 drivers/scsi/qla2xxx/qla_target.c |    2 +-
 2 files changed, 5 insertions(+), 1 deletion(-)

drivers/scsi/qla2xxx/qla_isr.c +4 -0

@@ -2466,6 +2466,10 @@ qla2x00_error_entry(scsi_qla_host_t *vha
 	if (pkt->entry_status & RF_BUSY)
 		res = DID_BUS_BUSY << 16;
 
+	if (pkt->entry_type == NOTIFY_ACK_TYPE &&
+	    pkt->handle == QLA_TGT_SKIP_HANDLE)
+		return;
+
 	sp = qla2x00_get_sp_from_handle(vha, func, req, pkt);
 	if (sp) {
 		sp->done(ha, sp, res);

drivers/scsi/qla2xxx/qla_target.c +1 -1

@@ -2865,7 +2865,7 @@ static int __qlt_send_term_imm_notif(str
 
 	pkt->entry_type = NOTIFY_ACK_TYPE;
 	pkt->entry_count = 1;
-	pkt->handle = QLA_TGT_SKIP_HANDLE | CTIO_COMPLETION_HANDLE_MARK;
+	pkt->handle = QLA_TGT_SKIP_HANDLE;
 
 	nack = (struct nack_to_isp *)pkt;
 	nack->ox_id = ntfy->ox_id;

Greg Kroah-Hartman

author maintainer

2017-07-03 13:38 UTC #37 lore raw

PATCH 37/101 net: mvneta: Fix for_each_present_cpu usage

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Gregory CLEMENT <[email protected]>

commit 129219e4950a3fcf9323b3bbd8b224c7aa873985 upstream.

This patch convert the for_each_present in on_each_cpu, instead of applying on the present cpus it will be applied only on the online cpus. This fix a bug reported on
http://thread.gmane.org/gmane.linux.ports.arm.kernel/468173.

Using the macro on_each_cpu (instead of a for_each_* loop) also ensures that all the calls will be done all at once.

Fixes f86428854480 ("net: mvneta: Statically assign queues to CPUs")

Reported-by Stefan Roese <[email protected]>

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

Signed-off-by Amit Pundir <[email protected]>

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

---
 drivers/net/ethernet/marvell/mvneta.c |    8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

drivers/net/ethernet/marvell/mvneta.c +3 -5

@@ -2446,7 +2446,7 @@ static void mvneta_start_dev(struct mvne
 	mvneta_port_enable(pp);
 
 	/* Enable polling on the port */
-	for_each_present_cpu(cpu) {
+	for_each_online_cpu(cpu) {
 		struct mvneta_pcpu_port *port = per_cpu_ptr(pp->ports, cpu);
 
 		napi_enable(&port->napi);

@@ -2472,7 +2472,7 @@ static void mvneta_stop_dev(struct mvnet
 
 	phy_stop(pp->phy_dev);
 
-	for_each_present_cpu(cpu) {
+	for_each_online_cpu(cpu) {
 		struct mvneta_pcpu_port *port = per_cpu_ptr(pp->ports, cpu);
 
 		napi_disable(&port->napi);

@@ -2902,13 +2902,11 @@ err_cleanup_rxqs:
 static int mvneta_stop(struct net_device *dev)
 {
 	struct mvneta_port *pp = netdev_priv(dev);
-	int cpu;
 
 	mvneta_stop_dev(pp);
 	mvneta_mdio_remove(pp);
 	unregister_cpu_notifier(&pp->cpu_notifier);
-	for_each_present_cpu(cpu)
-		smp_call_function_single(cpu, mvneta_percpu_disable, pp, true);
+	on_each_cpu(mvneta_percpu_disable, pp, true);
 	free_percpu_irq(dev->irq, pp->ports);
 	mvneta_cleanup_rxqs(pp);
 	mvneta_cleanup_txqs(pp);

Greg Kroah-Hartman

author maintainer

2017-07-03 13:34 UTC #38 lore raw

PATCH 38/101 MIPS: ath79: fix regression in PCI window initialization

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Felix Fietkau <[email protected]>

commit 9184dc8ffa56844352b3b9860e562ec4ee41176f upstream.

ath79_ddr_pci_win_base has the type void __iomem *, so register offsets need to be a multiple of 4.

Cc Alban Bedel <[email protected]>

Fixes 24b0e3e84fbf ("MIPS: ath79: Improve the DDR controller interface")

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

Patchwork: https://patchwork.linux-mips.org/patch/13258/

Signed-off-by Amit Pundir <[email protected]>

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

---
 arch/mips/ath79/common.c |   16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

arch/mips/ath79/common.c +8 -8

@@ -76,14 +76,14 @@ void ath79_ddr_set_pci_windows(void)
 {
 	BUG_ON(!ath79_ddr_pci_win_base);
 
-	__raw_writel(AR71XX_PCI_WIN0_OFFS, ath79_ddr_pci_win_base + 0);
-	__raw_writel(AR71XX_PCI_WIN1_OFFS, ath79_ddr_pci_win_base + 1);
-	__raw_writel(AR71XX_PCI_WIN2_OFFS, ath79_ddr_pci_win_base + 2);
-	__raw_writel(AR71XX_PCI_WIN3_OFFS, ath79_ddr_pci_win_base + 3);
-	__raw_writel(AR71XX_PCI_WIN4_OFFS, ath79_ddr_pci_win_base + 4);
-	__raw_writel(AR71XX_PCI_WIN5_OFFS, ath79_ddr_pci_win_base + 5);
-	__raw_writel(AR71XX_PCI_WIN6_OFFS, ath79_ddr_pci_win_base + 6);
-	__raw_writel(AR71XX_PCI_WIN7_OFFS, ath79_ddr_pci_win_base + 7);
+	__raw_writel(AR71XX_PCI_WIN0_OFFS, ath79_ddr_pci_win_base + 0x0);
+	__raw_writel(AR71XX_PCI_WIN1_OFFS, ath79_ddr_pci_win_base + 0x4);
+	__raw_writel(AR71XX_PCI_WIN2_OFFS, ath79_ddr_pci_win_base + 0x8);
+	__raw_writel(AR71XX_PCI_WIN3_OFFS, ath79_ddr_pci_win_base + 0xc);
+	__raw_writel(AR71XX_PCI_WIN4_OFFS, ath79_ddr_pci_win_base + 0x10);
+	__raw_writel(AR71XX_PCI_WIN5_OFFS, ath79_ddr_pci_win_base + 0x14);
+	__raw_writel(AR71XX_PCI_WIN6_OFFS, ath79_ddr_pci_win_base + 0x18);
+	__raw_writel(AR71XX_PCI_WIN7_OFFS, ath79_ddr_pci_win_base + 0x1c);
 }
 EXPORT_SYMBOL_GPL(ath79_ddr_set_pci_windows);

Greg Kroah-Hartman

author maintainer

2017-07-03 13:38 UTC #39 lore raw

PATCH 39/101 net: korina: Fix NAPI versus resources freeing

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Florian Fainelli <[email protected]>

commit e6afb1ad88feddf2347ea779cfaf4d03d3cd40b6 upstream.

Commit beb0babfb77e ("korina: disable napi on close and restart") introduced calls to napi_disable() that were missing before, unfortunately this leaves a small window during which NAPI has a chance to run, yet we just freed resources since korina_free_ring() has been called:

Fix this by disabling NAPI first then freeing resource, and make sure that we also cancel the restart task before doing the resource freeing.

Fixes beb0babfb77e ("korina: disable napi on close and restart")

Reported-by Alexandros C. Couloumbis <[email protected]>

Signed-off-by Amit Pundir <[email protected]>

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

---
 drivers/net/ethernet/korina.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

drivers/net/ethernet/korina.c +4 -4

@@ -900,10 +900,10 @@ static void korina_restart_task(struct w
 				DMA_STAT_DONE | DMA_STAT_HALT | DMA_STAT_ERR,
 				&lp->rx_dma_regs->dmasm);
 
-	korina_free_ring(dev);
-
 	napi_disable(&lp->napi);
 
+	korina_free_ring(dev);
+
 	if (korina_init(dev) < 0) {
 		printk(KERN_ERR "%s: cannot restart device\n", dev->name);
 		return;

@@ -1064,12 +1064,12 @@ static int korina_close(struct net_devic
 	tmp = tmp | DMA_STAT_DONE | DMA_STAT_HALT | DMA_STAT_ERR;
 	writel(tmp, &lp->rx_dma_regs->dmasm);
 
-	korina_free_ring(dev);
-
 	napi_disable(&lp->napi);
 
 	cancel_work_sync(&lp->restart_task);
 
+	korina_free_ring(dev);
+
 	free_irq(lp->rx_irq, dev);
 	free_irq(lp->tx_irq, dev);
 	free_irq(lp->ovr_irq, dev);

Greg Kroah-Hartman

author maintainer

2017-07-03 13:38 UTC #40 lore raw

PATCH 40/101 MIPS: ralink: MT7688 pinmux fixes

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: John Crispin <[email protected]>

commit e906a5f67e5a3337d696ec848e9c28fc68b39aa3 upstream.

A few fixes to the pinmux data, 2 new muxes and a minor whitespace cleanup.

Signed-off-by John Crispin <[email protected]>

Patchwork: https://patchwork.linux-mips.org/patch/11991/

Signed-off-by Amit Pundir <[email protected]>

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

---
 arch/mips/ralink/mt7620.c |   80 ++++++++++++++++++++++++++++------------------
 1 file changed, 50 insertions(+), 30 deletions(-)

arch/mips/ralink/mt7620.c +50 ~~-30~~

@@ -107,31 +107,31 @@ static struct rt2880_pmx_group mt7620a_p
 };
 
 static struct rt2880_pmx_func pwm1_grp_mt7628[] = {
-	FUNC("sdcx", 3, 19, 1),
+	FUNC("sdxc d6", 3, 19, 1),
 	FUNC("utif", 2, 19, 1),
 	FUNC("gpio", 1, 19, 1),
-	FUNC("pwm", 0, 19, 1),
+	FUNC("pwm1", 0, 19, 1),
 };
 
 static struct rt2880_pmx_func pwm0_grp_mt7628[] = {
-	FUNC("sdcx", 3, 18, 1),
+	FUNC("sdxc d7", 3, 18, 1),
 	FUNC("utif", 2, 18, 1),
 	FUNC("gpio", 1, 18, 1),
-	FUNC("pwm", 0, 18, 1),
+	FUNC("pwm0", 0, 18, 1),
 };
 
 static struct rt2880_pmx_func uart2_grp_mt7628[] = {
-	FUNC("sdcx", 3, 20, 2),
+	FUNC("sdxc d5 d4", 3, 20, 2),
 	FUNC("pwm", 2, 20, 2),
 	FUNC("gpio", 1, 20, 2),
-	FUNC("uart", 0, 20, 2),
+	FUNC("uart2", 0, 20, 2),
 };
 
 static struct rt2880_pmx_func uart1_grp_mt7628[] = {
-	FUNC("sdcx", 3, 45, 2),
+	FUNC("sw_r", 3, 45, 2),
 	FUNC("pwm", 2, 45, 2),
 	FUNC("gpio", 1, 45, 2),
-	FUNC("uart", 0, 45, 2),
+	FUNC("uart1", 0, 45, 2),
 };
 
 static struct rt2880_pmx_func i2c_grp_mt7628[] = {

@@ -143,21 +143,21 @@ static struct rt2880_pmx_func i2c_grp_mt
 
 static struct rt2880_pmx_func refclk_grp_mt7628[] = { FUNC("reclk", 0, 36, 1) };
 static struct rt2880_pmx_func perst_grp_mt7628[] = { FUNC("perst", 0, 37, 1) };
-static struct rt2880_pmx_func wdt_grp_mt7628[] = { FUNC("wdt", 0, 15, 38) };
+static struct rt2880_pmx_func wdt_grp_mt7628[] = { FUNC("wdt", 0, 38, 1) };
 static struct rt2880_pmx_func spi_grp_mt7628[] = { FUNC("spi", 0, 7, 4) };
 
 static struct rt2880_pmx_func sd_mode_grp_mt7628[] = {
 	FUNC("jtag", 3, 22, 8),
 	FUNC("utif", 2, 22, 8),
 	FUNC("gpio", 1, 22, 8),
-	FUNC("sdcx", 0, 22, 8),
+	FUNC("sdxc", 0, 22, 8),
 };
 
 static struct rt2880_pmx_func uart0_grp_mt7628[] = {
 	FUNC("-", 3, 12, 2),
 	FUNC("-", 2, 12, 2),
 	FUNC("gpio", 1, 12, 2),
-	FUNC("uart", 0, 12, 2),
+	FUNC("uart0", 0, 12, 2),
 };
 
 static struct rt2880_pmx_func i2s_grp_mt7628[] = {

@@ -171,7 +171,7 @@ static struct rt2880_pmx_func spi_cs1_gr
 	FUNC("-", 3, 6, 1),
 	FUNC("refclk", 2, 6, 1),
 	FUNC("gpio", 1, 6, 1),
-	FUNC("spi", 0, 6, 1),
+	FUNC("spi cs1", 0, 6, 1),
 };
 
 static struct rt2880_pmx_func spis_grp_mt7628[] = {

@@ -188,28 +188,44 @@ static struct rt2880_pmx_func gpio_grp_m
 	FUNC("gpio", 0, 11, 1),
 };
 
-#define MT7628_GPIO_MODE_MASK	0x3
-
-#define MT7628_GPIO_MODE_PWM1	30
-#define MT7628_GPIO_MODE_PWM0	28
-#define MT7628_GPIO_MODE_UART2	26
-#define MT7628_GPIO_MODE_UART1	24
-#define MT7628_GPIO_MODE_I2C	20
-#define MT7628_GPIO_MODE_REFCLK	18
-#define MT7628_GPIO_MODE_PERST	16
-#define MT7628_GPIO_MODE_WDT	14
-#define MT7628_GPIO_MODE_SPI	12
-#define MT7628_GPIO_MODE_SDMODE	10
-#define MT7628_GPIO_MODE_UART0	8
-#define MT7628_GPIO_MODE_I2S	6
-#define MT7628_GPIO_MODE_CS1	4
-#define MT7628_GPIO_MODE_SPIS	2
-#define MT7628_GPIO_MODE_GPIO	0
+static struct rt2880_pmx_func wled_kn_grp_mt7628[] = {
+	FUNC("rsvd", 3, 35, 1),
+	FUNC("rsvd", 2, 35, 1),
+	FUNC("gpio", 1, 35, 1),
+	FUNC("wled_kn", 0, 35, 1),
+};
+
+static struct rt2880_pmx_func wled_an_grp_mt7628[] = {
+	FUNC("rsvd", 3, 35, 1),
+	FUNC("rsvd", 2, 35, 1),
+	FUNC("gpio", 1, 35, 1),
+	FUNC("wled_an", 0, 35, 1),
+};
+
+#define MT7628_GPIO_MODE_MASK		0x3
+
+#define MT7628_GPIO_MODE_WLED_KN	48
+#define MT7628_GPIO_MODE_WLED_AN	32
+#define MT7628_GPIO_MODE_PWM1		30
+#define MT7628_GPIO_MODE_PWM0		28
+#define MT7628_GPIO_MODE_UART2		26
+#define MT7628_GPIO_MODE_UART1		24
+#define MT7628_GPIO_MODE_I2C		20
+#define MT7628_GPIO_MODE_REFCLK		18
+#define MT7628_GPIO_MODE_PERST		16
+#define MT7628_GPIO_MODE_WDT		14
+#define MT7628_GPIO_MODE_SPI		12
+#define MT7628_GPIO_MODE_SDMODE		10
+#define MT7628_GPIO_MODE_UART0		8
+#define MT7628_GPIO_MODE_I2S		6
+#define MT7628_GPIO_MODE_CS1		4
+#define MT7628_GPIO_MODE_SPIS		2
+#define MT7628_GPIO_MODE_GPIO		0
 
 static struct rt2880_pmx_group mt7628an_pinmux_data[] = {
 	GRP_G("pmw1", pwm1_grp_mt7628, MT7628_GPIO_MODE_MASK,
 				1, MT7628_GPIO_MODE_PWM1),
-	GRP_G("pmw1", pwm0_grp_mt7628, MT7628_GPIO_MODE_MASK,
+	GRP_G("pmw0", pwm0_grp_mt7628, MT7628_GPIO_MODE_MASK,
 				1, MT7628_GPIO_MODE_PWM0),
 	GRP_G("uart2", uart2_grp_mt7628, MT7628_GPIO_MODE_MASK,
 				1, MT7628_GPIO_MODE_UART2),

@@ -233,6 +249,10 @@ static struct rt2880_pmx_group mt7628an_
 				1, MT7628_GPIO_MODE_SPIS),
 	GRP_G("gpio", gpio_grp_mt7628, MT7628_GPIO_MODE_MASK,
 				1, MT7628_GPIO_MODE_GPIO),
+	GRP_G("wled_an", wled_an_grp_mt7628, MT7628_GPIO_MODE_MASK,
+				1, MT7628_GPIO_MODE_WLED_AN),
+	GRP_G("wled_kn", wled_kn_grp_mt7628, MT7628_GPIO_MODE_MASK,
+				1, MT7628_GPIO_MODE_WLED_KN),
 	{ 0 }
 };

Greg Kroah-Hartman

author maintainer

2017-07-03 13:38 UTC #41 lore raw

PATCH 41/101 MIPS: ralink: fix USB frequency scaling

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: John Crispin <[email protected]>

commit fad2522272ed5ed451d2d7b1dc547ddf3781cc7e upstream.

Commit 418d29c87061 ("MIPS: ralink: Unify SoC id handling") was not fully correct. The logic for the SoC check got inverted. We need to check if it is not a MT76x8.

Signed-off-by John Crispin <[email protected]>

Patchwork: https://patchwork.linux-mips.org/patch/11992/

Signed-off-by Amit Pundir <[email protected]>

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

---
 arch/mips/ralink/mt7620.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

arch/mips/ralink/mt7620.c +1 -1

@@ -459,7 +459,7 @@ void __init ralink_clk_init(void)
 	ralink_clk_add("10000c00.uartlite", periph_rate);
 	ralink_clk_add("10180000.wmac", xtal_rate);
 
-	if (IS_ENABLED(CONFIG_USB) && is_mt76x8()) {
+	if (IS_ENABLED(CONFIG_USB) && !is_mt76x8()) {
 		/*
 		 * When the CPU goes into sleep mode, the BUS clock will be
 		 * too low for USB to function properly. Adjust the busses

Greg Kroah-Hartman

author maintainer

2017-07-03 13:34 UTC #42 lore raw

PATCH 42/101 MIPS: ralink: Fix invalid assignment of SoC type

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: John Crispin <[email protected]>

commit 0af3a40f09a2a85089037a0b5b51471fa48b229e upstream.

Commit 418d29c87061 ("MIPS: ralink: Unify SoC id handling") introduced broken code. We obviously need to assign the value.

Signed-off-by John Crispin <[email protected]>

Patchwork: https://patchwork.linux-mips.org/patch/11993/

Signed-off-by Amit Pundir <[email protected]>

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

---
 arch/mips/ralink/rt288x.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

arch/mips/ralink/rt288x.c +1 -1

@@ -109,5 +109,5 @@ void prom_soc_init(struct ralink_soc_inf
 	soc_info->mem_size_max = RT2880_MEM_SIZE_MAX;
 
 	rt2880_pinmux_data = rt2880_pinmux_data_act;
-	ralink_soc == RT2880_SOC;
+	ralink_soc = RT2880_SOC;
 }

Greg Kroah-Hartman

author maintainer

2017-07-03 13:40 UTC #43 lore raw

PATCH 43/101 MIPS: ralink: fix MT7628 pinmux typos

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Álvaro Fernández Rojas <[email protected]>

commit d7146829c9da24e285cb1b1f2156b5b3e2d40c07 upstream.

Signed-off-by Álvaro Fernández Rojas <[email protected]>

Patchwork: https://patchwork.linux-mips.org/patch/13306/

Signed-off-by Amit Pundir <[email protected]>

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

---
 arch/mips/ralink/mt7620.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

arch/mips/ralink/mt7620.c +2 -2

@@ -223,9 +223,9 @@ static struct rt2880_pmx_func wled_an_gr
 #define MT7628_GPIO_MODE_GPIO		0
 
 static struct rt2880_pmx_group mt7628an_pinmux_data[] = {
-	GRP_G("pmw1", pwm1_grp_mt7628, MT7628_GPIO_MODE_MASK,
+	GRP_G("pwm1", pwm1_grp_mt7628, MT7628_GPIO_MODE_MASK,
 				1, MT7628_GPIO_MODE_PWM1),
-	GRP_G("pmw0", pwm0_grp_mt7628, MT7628_GPIO_MODE_MASK,
+	GRP_G("pwm0", pwm0_grp_mt7628, MT7628_GPIO_MODE_MASK,
 				1, MT7628_GPIO_MODE_PWM0),
 	GRP_G("uart2", uart2_grp_mt7628, MT7628_GPIO_MODE_MASK,
 				1, MT7628_GPIO_MODE_UART2),

Greg Kroah-Hartman

author maintainer

2017-07-03 13:41 UTC #44 lore raw

PATCH 44/101 MIPS: ralink: fix MT7628 wled_an pinmux gpio

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Álvaro Fernández Rojas <[email protected]>

commit 07b50db6e685172a41b9978aebffb2438166d9b6 upstream.

Signed-off-by Álvaro Fernández Rojas <[email protected]>

Patchwork: https://patchwork.linux-mips.org/patch/13307/

Signed-off-by Amit Pundir <[email protected]>

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

---
 arch/mips/ralink/mt7620.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

arch/mips/ralink/mt7620.c +4 -4

@@ -196,10 +196,10 @@ static struct rt2880_pmx_func wled_kn_gr
 };
 
 static struct rt2880_pmx_func wled_an_grp_mt7628[] = {
-	FUNC("rsvd", 3, 35, 1),
-	FUNC("rsvd", 2, 35, 1),
-	FUNC("gpio", 1, 35, 1),
-	FUNC("wled_an", 0, 35, 1),
+	FUNC("rsvd", 3, 44, 1),
+	FUNC("rsvd", 2, 44, 1),
+	FUNC("gpio", 1, 44, 1),
+	FUNC("wled_an", 0, 44, 1),
 };
 
 #define MT7628_GPIO_MODE_MASK		0x3

Greg Kroah-Hartman

author maintainer

2017-07-03 13:34 UTC #45 lore raw

PATCH 46/101 bgmac: fix a missing check for build_skb

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: wangweidong <[email protected]>

commit f1640c3ddeec12804bc9a21feee85fc15aca95f6 upstream.

when build_skb failed, it may occure a NULL pointer. So add a 'NULL check' for it.

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

Signed-off-by Amit Pundir <[email protected]>

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

---
 drivers/net/ethernet/broadcom/bgmac.c |    5 +++++
 1 file changed, 5 insertions(+)

drivers/net/ethernet/broadcom/bgmac.c +5 -0

@@ -469,6 +469,11 @@ static int bgmac_dma_rx_read(struct bgma
 			len -= ETH_FCS_LEN;
 
 			skb = build_skb(buf, BGMAC_RX_ALLOC_SIZE);
+			if (unlikely(skb)) {
+				bgmac_err(bgmac, "build_skb failed\n");
+				put_page(virt_to_head_page(buf));
+				break;
+			}
 			skb_put(skb, BGMAC_RX_FRAME_OFFSET +
 				BGMAC_RX_BUF_OFFSET + len);
 			skb_pull(skb, BGMAC_RX_FRAME_OFFSET +

Greg Kroah-Hartman

author maintainer

2017-07-03 13:34 UTC #46 lore raw

PATCH 48/101 bgmac: Fix reversed test of build_skb() return value.

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: David S. Miller <[email protected]>

commit 750afbf8ee9c6a1c74a1fe5fc9852146b1d72687 upstream.

Fixes f1640c3ddeec ("bgmac: fix a missing check for build_skb")

Signed-off-by Amit Pundir <[email protected]>

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

---
 drivers/net/ethernet/broadcom/bgmac.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

drivers/net/ethernet/broadcom/bgmac.c +1 -1

@@ -469,7 +469,7 @@ static int bgmac_dma_rx_read(struct bgma
 			len -= ETH_FCS_LEN;
 
 			skb = build_skb(buf, BGMAC_RX_ALLOC_SIZE);
-			if (unlikely(skb)) {
+			if (unlikely(!skb)) {
 				bgmac_err(bgmac, "build_skb failed\n");
 				put_page(virt_to_head_page(buf));
 				break;

Greg Kroah-Hartman

author maintainer

2017-07-03 13:34 UTC #47 lore raw

PATCH 49/101 net: bgmac: Fix SOF bit checking

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Florian Fainelli <[email protected]>

commit d2b13233879ca1268a1c027d4573109e5a777811 upstream.

We are checking for the Start of Frame bit in the ctl1 word, while this bit is set in the ctl0 word instead. Read the ctl0 word and update the check to verify that.

Fixes 9cde94506eac ("bgmac: implement scatter/gather support")

Signed-off-by Amit Pundir <[email protected]>

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

---
 drivers/net/ethernet/broadcom/bgmac.c |    5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

drivers/net/ethernet/broadcom/bgmac.c +3 -2

@@ -255,15 +255,16 @@ static void bgmac_dma_tx_free(struct bgm
 	while (ring->start != ring->end) {
 		int slot_idx = ring->start % BGMAC_TX_RING_SLOTS;
 		struct bgmac_slot_info *slot = &ring->slots[slot_idx];
-		u32 ctl1;
+		u32 ctl0, ctl1;
 		int len;
 
 		if (slot_idx == empty_slot)
 			break;
 
+		ctl0 = le32_to_cpu(ring->cpu_base[slot_idx].ctl0);
 		ctl1 = le32_to_cpu(ring->cpu_base[slot_idx].ctl1);
 		len = ctl1 & BGMAC_DESC_CTL1_LEN;
-		if (ctl1 & BGMAC_DESC_CTL0_SOF)
+		if (ctl0 & BGMAC_DESC_CTL0_SOF)
 			/* Unmap no longer used buffer */
 			dma_unmap_single(dma_dev, slot->dma_addr, len,
 					 DMA_TO_DEVICE);

Greg Kroah-Hartman

author maintainer

2017-07-03 13:34 UTC #48 lore raw

PATCH 50/101 net: bgmac: Start transmit queue in bgmac_open

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Florian Fainelli <[email protected]>

commit c3897f2a69e54dd113fc9abd2daf872e5b495798 upstream.

The driver does not start the transmit queue in bgmac_open(). If the queue was stopped prior to closing then re-opening the interface, we would never be able to wake-up again.

Fixes dd4544f05469 ("bgmac: driver for GBit MAC core on BCMA bus")

Signed-off-by Amit Pundir <[email protected]>

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

---
 drivers/net/ethernet/broadcom/bgmac.c |    3 +++
 1 file changed, 3 insertions(+)

drivers/net/ethernet/broadcom/bgmac.c +3 -0

@@ -1309,6 +1309,9 @@ static int bgmac_open(struct net_device
 	phy_start(bgmac->phy_dev);
 
 	netif_carrier_on(net_dev);
+
+	netif_start_queue(net_dev);
+
 	return 0;
 }

Greg Kroah-Hartman

author maintainer

2017-07-03 13:38 UTC #49 lore raw

PATCH 51/101 net: bgmac: Remove superflous netif_carrier_on()

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Florian Fainelli <[email protected]>

commit 3894396e64994f31c3ef5c7e6f63dded0593e567 upstream.

bgmac_open() calls phy_start() to initialize the PHY state machine, which will set the interface's carrier state accordingly, no need to force that as this could be conflicting with the PHY state determined by PHYLIB.

Fixes dd4544f05469 ("bgmac: driver for GBit MAC core on BCMA bus")

Signed-off-by Amit Pundir <[email protected]>

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

---
 drivers/net/ethernet/broadcom/bgmac.c |    2 --
 1 file changed, 2 deletions(-)

drivers/net/ethernet/broadcom/bgmac.c +0 -2

@@ -1308,8 +1308,6 @@ static int bgmac_open(struct net_device
 
 	phy_start(bgmac->phy_dev);
 
-	netif_carrier_on(net_dev);
-
 	netif_start_queue(net_dev);
 
 	return 0;

Greg Kroah-Hartman

author maintainer

2017-07-03 13:38 UTC #50 lore raw

PATCH 52/101 powerpc/eeh: Enable IO path on permanent error

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Gavin Shan <[email protected]>

[ Upstream commit 387bbc974f6adf91aa635090f73434ed10edd915 ]

We give up recovery on permanent error, simply shutdown the affected devices and remove them. If the devices can't be put into quiet state, they spew more traffic that is likely to cause another unexpected EEH error. This was observed on "p8dtu2u" machine:

   0002:00:00.0 PCI bridge: IBM Device 03dc
   0002:01:00.0 Ethernet controller: Intel Corporation \
                Ethernet Controller X710/X557-AT 10GBASE-T (rev 02)
   0002:01:00.1 Ethernet controller: Intel Corporation \
                Ethernet Controller X710/X557-AT 10GBASE-T (rev 02)
   0002:01:00.2 Ethernet controller: Intel Corporation \
                Ethernet Controller X710/X557-AT 10GBASE-T (rev 02)
   0002:01:00.3 Ethernet controller: Intel Corporation \
                Ethernet Controller X710/X557-AT 10GBASE-T (rev 02)

On P8 PowerNV platform, the IO path is frozen when shutdowning the devices, meaning the memory registers are inaccessible. It is why the devices can't be put into quiet state before removing them. This fixes the issue by enabling IO path prior to putting the devices into quiet state.

Reported-by Pridhiviraj Paidipeddi <[email protected]>

Signed-off-by Gavin Shan <[email protected]>

Acked-by Russell Currey <[email protected]>

Signed-off-by Michael Ellerman <[email protected]>

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

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

---
 arch/powerpc/kernel/eeh.c |   10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

arch/powerpc/kernel/eeh.c +9 -1

@@ -304,9 +304,17 @@ void eeh_slot_error_detail(struct eeh_pe
 	 *
 	 * For pHyp, we have to enable IO for log retrieval. Otherwise,
 	 * 0xFF's is always returned from PCI config space.
+	 *
+	 * When the @severity is EEH_LOG_PERM, the PE is going to be
+	 * removed. Prior to that, the drivers for devices included in
+	 * the PE will be closed. The drivers rely on working IO path
+	 * to bring the devices to quiet state. Otherwise, PCI traffic
+	 * from those devices after they are removed is like to cause
+	 * another unexpected EEH error.
 	 */
 	if (!(pe->type & EEH_PE_PHB)) {
-		if (eeh_has_flag(EEH_ENABLE_IO_FOR_LOG))
+		if (eeh_has_flag(EEH_ENABLE_IO_FOR_LOG) ||
+		    severity == EEH_LOG_PERM)
 			eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
 
 		/*

Greg Kroah-Hartman

author maintainer

2017-07-03 13:40 UTC #51 lore raw

PATCH 53/101 gianfar: Do not reuse pages from emergency reserve

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Eric Dumazet <[email protected]>

[ Upstream commit 69fed99baac186013840ced3524562841296034f ]

A driver using dev_alloc_page() must not reuse a page that had to use emergency memory reserve.

Otherwise all packets using this page will be immediately dropped, unless for very specific sockets having SOCK_MEMALLOC bit set.

This issue might be hard to debug, because only a fraction of the RX ring buffer would suffer from drops.

Fixes 75354148ce69 ("gianfar: Add paged allocation and Rx S/G")

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

Cc Claudiu Manoil <[email protected]>

Acked-by Claudiu Manoil <[email protected]>

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

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

---
 drivers/net/ethernet/freescale/gianfar.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

drivers/net/ethernet/freescale/gianfar.c +1 -1

@@ -2939,7 +2939,7 @@ static bool gfar_add_rx_frag(struct gfar
 				size, GFAR_RXB_TRUESIZE);
 
 	/* try reuse page */
-	if (unlikely(page_count(page) != 1))
+	if (unlikely(page_count(page) != 1 || page_is_pfmemalloc(page)))
 		return false;
 
 	/* change offset to the other half */

Greg Kroah-Hartman

author maintainer

2017-07-03 13:38 UTC #52 lore raw

PATCH 54/101 Btrfs: fix truncate down when no_holes feature is enabled

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Liu Bo <[email protected]>

[ Upstream commit 91298eec05cd8d4e828cf7ee5d4a6334f70cf69a ]

For such a file mapping,

[0-4k][hole][8k-12k]

In NO_HOLES mode, we don't have the [hole] extent any more.
Commit c1aa45759e90 ("Btrfs: fix shrinking truncate when the no_holes feature is enabled")
fixed disk isize not being updated in NO_HOLES mode when data is not flushed.

However, even if data has been flushed, we can still have trouble in updating disk isize since we updated disk isize to 'start' of the last evicted extent.

Reviewed-by Chris Mason <[email protected]>

Signed-off-by Liu Bo <[email protected]>

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

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

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

---
 fs/btrfs/inode.c |   13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

fs/btrfs/inode.c +12 -1

@@ -4397,8 +4397,19 @@ search_again:
 		if (found_type > min_type) {
 			del_item = 1;
 		} else {
-			if (item_end < new_size)
+			if (item_end < new_size) {
+				/*
+				 * With NO_HOLES mode, for the following mapping
+				 *
+				 * [0-4k][hole][8k-12k]
+				 *
+				 * if truncating isize down to 6k, it ends up
+				 * isize being 8k.
+				 */
+				if (btrfs_fs_incompat(root->fs_info, NO_HOLES))
+					last_size = new_size;
 				break;
+			}
 			if (found_key.offset >= new_size)
 				del_item = 1;
 			else

Greg Kroah-Hartman

author maintainer

2017-07-03 13:34 UTC #53 lore raw

PATCH 55/101 virtio_console: fix a crash in config_work_handler

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: "G. Campana" <[email protected]>

[ Upstream commit 8379cadf71c3ee8173a1c6fc1ea7762a9638c047 ]

Using control_work instead of config_work as the 3rd argument to container_of results in an invalid portdev pointer. Indeed, the work structure is initialized as below:

    INIT_WORK(&portdev->config_work, &config_work_handler);

It leads to a crash when portdev->vdev is dereferenced later. This bug
is triggered when the guest uses a virtio-console without multiport feature and receives a config_changed virtio interrupt.

Signed-off-by G. Campana <[email protected]>

Reviewed-by Amit Shah <[email protected]>

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

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

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

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

drivers/char/virtio_console.c +1 -1

@@ -1864,7 +1864,7 @@ static void config_work_handler(struct w
 {
 	struct ports_device *portdev;
 
-	portdev = container_of(work, struct ports_device, control_work);
+	portdev = container_of(work, struct ports_device, config_work);
 	if (!use_multiport(portdev)) {
 		struct virtio_device *vdev;
 		struct port *port;

Greg Kroah-Hartman

author maintainer

2017-07-03 13:39 UTC #54 lore raw

PATCH 56/101 swiotlb-xen: update dev_addr after swapping pages

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Stefano Stabellini <[email protected]>

[ Upstream commit f1225ee4c8fcf09afaa199b8b1f0450f38b8cd11 ]

In xen_swiotlb_map_page and xen_swiotlb_map_sg_attrs, if the original page is not suitable, we swap it for another page from the swiotlb pool.

In these cases, we don't update the previously calculated dma address for the page before calling xen_dma_map_page. Thus, we end up calling xen_dma_map_page passing the wrong dev_addr, resulting in xen_dma_map_page mistakenly assuming that the page is foreign when it is local.

Fix the bug by updating dev_addr appropriately.

This change has no effect on x86, because xen_dma_map_page is a stub there.

Signed-off-by Stefano Stabellini <[email protected]>

Signed-off-by Pooya Keshavarzi <[email protected]>

Tested-by Pooya Keshavarzi <[email protected]>

Reviewed-by Boris Ostrovsky <[email protected]>

Signed-off-by Konrad Rzeszutek Wilk <[email protected]>

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

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

---
 drivers/xen/swiotlb-xen.c |    5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

drivers/xen/swiotlb-xen.c +3 -2

@@ -409,9 +409,9 @@ dma_addr_t xen_swiotlb_map_page(struct d
 	if (map == SWIOTLB_MAP_ERROR)
 		return DMA_ERROR_CODE;
 
+	dev_addr = xen_phys_to_bus(map);
 	xen_dma_map_page(dev, pfn_to_page(map >> PAGE_SHIFT),
 					dev_addr, map & ~PAGE_MASK, size, dir, attrs);
-	dev_addr = xen_phys_to_bus(map);
 
 	/*
 	 * Ensure that the address returned is DMA'ble

@@ -567,13 +567,14 @@ xen_swiotlb_map_sg_attrs(struct device *
 				sg_dma_len(sgl) = 0;
 				return 0;
 			}
+			dev_addr = xen_phys_to_bus(map);
 			xen_dma_map_page(hwdev, pfn_to_page(map >> PAGE_SHIFT),
 						dev_addr,
 						map & ~PAGE_MASK,
 						sg->length,
 						dir,
 						attrs);
-			sg->dma_address = xen_phys_to_bus(map);
+			sg->dma_address = dev_addr;
 		} else {
 			/* we are not interested in the dma_addr returned by
 			 * xen_dma_map_page, only in the potential cache flushes executed

Greg Kroah-Hartman

author maintainer

2017-07-03 13:40 UTC #55 lore raw

PATCH 57/101 net: sctp: fix array overrun read on sctp_timer_tbl

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Colin Ian King <[email protected]>

[ Upstream commit 0e73fc9a56f22f2eec4d2b2910c649f7af67b74d ]

The comparison on the timeout can lead to an array overrun read on sctp_timer_tbl because of an off-by-one error. Fix this by using < instead of <= and also compare to the array size rather than SCTP_EVENT_TIMEOUT_MAX.

Fixes CoverityScan CID#1397639 ("Out-of-bounds read")

Signed-off-by Colin Ian King <[email protected]>

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

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

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

net/sctp/debug.c +1 -1

@@ -166,7 +166,7 @@ static const char *const sctp_timer_tbl[
 /* Lookup timer debug name. */
 const char *sctp_tname(const sctp_subtype_t id)
 {
-	if (id.timeout <= SCTP_EVENT_TIMEOUT_MAX)
+	if (id.timeout < ARRAY_SIZE(sctp_timer_tbl))
 		return sctp_timer_tbl[id.timeout];
 	return "unknown_timer";
 }

Ben Hutchings

2017-07-04 18:48 UTC #56 lore raw

Re: [PATCH 4.4 057/101] net: sctp: fix array overrun read on sctp_timer_tbl

Quoted 11 lines · Greg Kroah-Hartman

4.4-stable review patch. If anyone has any objections, please let me know.
------------------
From: Colin Ian King <[email protected]>
[ Upstream commit 0e73fc9a56f22f2eec4d2b2910c649f7af67b74d ]
The comparison on the timeout can lead to an array overrun read on sctp_timer_tbl because of an off-by-one error.

[...]

The off-by-one error was only introduced in 4.11 by:

commit 7b9438de0cd4b46a6914416bfede6cf839cd9e68

Author: Xin Long <[email protected]>
Date:   Wed Jan 18 00:44:43 2017 +0800

sctp: add stream reconf timer

So it is harmless but also useless to apply this to 4.4 and 4.9.

Ben.

Signature · 2 lines

Ben Hutchings
Software Developer, Codethink Ltd.

Greg Kroah-Hartman

author maintainer

2017-07-05 12:17 UTC #57 lore raw

Re: [PATCH 4.4 057/101] net: sctp: fix array overrun read on sctp_timer_tbl

Quoted 16 lines · Ben Hutchings

Quoted 11 lines · Greg Kroah-Hartman
4.4-stable review patch. If anyone has any objections, please let me know.
------------------
From: Colin Ian King <[email protected]>
[ Upstream commit 0e73fc9a56f22f2eec4d2b2910c649f7af67b74d ]
The comparison on the timeout can lead to an array overrun read on sctp_timer_tbl because of an off-by-one error.
[...]
The off-by-one error was only introduced in 4.11 by:

Quoted 7 lines

commit 7b9438de0cd4b46a6914416bfede6cf839cd9e68
Author: Xin Long <[email protected]>
Date:   Wed Jan 18 00:44:43 2017 +0800
sctp: add stream reconf timer
So it is harmless but also useless to apply this to 4.4 and 4.9.

Thanks, I've now dropped it from both of those trees.

greg k-h

Greg Kroah-Hartman

author maintainer

2017-07-03 13:40 UTC #58 lore raw

PATCH 58/101 xen-netfront: Fix Rx stall during network stress and OOM

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Vineeth Remanan Pillai <[email protected]>

[ Upstream commit 90c311b0eeead647b708a723dbdde1eda3dcad05 ]

During an OOM scenario, request slots could not be created as skb allocation fails. So the netback cannot pass in packets and netfront wrongly assumes that there is no more work to be done and it disables polling. This causes Rx to stall.

The issue is with the retry logic which schedules the timer if the created slots are less than NET_RX_SLOTS_MIN. The count of new request slots to be pushed are calculated as a difference between new req_prod and rsp_cons which could be more than the actual slots, if there are unconsumed responses.

The fix is to calculate the count of newly created slots as the difference between new req_prod and old req_prod.

Signed-off-by Vineeth Remanan Pillai <[email protected]>

Reviewed-by Juergen Gross <[email protected]>

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

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

---
 drivers/net/xen-netfront.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

drivers/net/xen-netfront.c +1 -1

@@ -321,7 +321,7 @@ static void xennet_alloc_rx_buffers(stru
 	queue->rx.req_prod_pvt = req_prod;
 
 	/* Not enough requests? Try again later. */
-	if (req_prod - queue->rx.rsp_cons < NET_RX_SLOTS_MIN) {
+	if (req_prod - queue->rx.sring->req_prod < NET_RX_SLOTS_MIN) {
 		mod_timer(&queue->rx_refill_timer, jiffies + (HZ/10));
 		return;
 	}

Greg Kroah-Hartman

author maintainer

2017-07-03 13:34 UTC #59 lore raw

PATCH 59/101 scsi: virtio_scsi: Reject commands when virtqueue is broken

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Eric Farman <[email protected]>

[ Upstream commit 773c7220e22d193e5667c352fcbf8d47eefc817f ]

In the case of a graceful set of detaches, where the virtio-scsi-ccw disk is removed from the guest prior to the controller, the guest behaves quite normally. Specifically, the detach gets us into sd_sync_cache to issue a Synchronize Cache(10) command, which immediately fails (and is retried a couple of times) because the device has been removed. Later, the removal of the controller sees two CRWs presented, but there's no further indication of the removal from the guest viewpoint.

 [   17.217458] sd 0:0:0:0: [sda] Synchronizing SCSI cache
 [   17.219257] sd 0:0:0:0: [sda] Synchronize Cache(10) failed: Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK
 [   21.449400] crw_info : CRW reports slct=0, oflw=0, chn=1, rsc=3, anc=0, erc=4, rsid=2
 [   21.449406] crw_info : CRW reports slct=0, oflw=0, chn=0, rsc=3, anc=0, erc=4, rsid=0

However, on s390, the SCSI disks can be removed "by surprise" when an entire controller (host) is removed and all associated disks are removed via the loop in scsi_forget_host. The same call to sd_sync_cache is made, but because the controller has already been removed, the Synchronize Cache(10) command is neither issued (and then failed) nor rejected.

That the I/O isn't returned means the guest cannot have other devices added nor removed, and other tasks (such as shutdown or reboot) issued by the guest will not complete either. The virtio ring has already been marked as broken (via virtio_break_device in virtio_ccw_remove), but we still attempt to queue the command only to have it remain there. The calling sequence provides a bit of distinction for us:

virtscsi_queuecommand()
-> virtscsi_kick_cmd()

    -> virtscsi_add_cmd()
     -> virtqueue_add_sgs()
      -> virtqueue_add()
         if success
           return 0
         elseif vq->broken or vring_mapping_error()
           return -EIO
         else
           return -ENOSPC

A return of ENOSPC is generally a temporary condition, so returning "host busy" from virtscsi_queuecommand makes sense here, to have it redriven in a moment or two. But the EIO return code is more of a permanent error and so it would be wise to return the I/O itself and allow the calling thread to finish gracefully. The result is these four kernel messages in the guest (the fourth one does not occur prior to this patch):

 [   22.921562] crw_info : CRW reports slct=0, oflw=0, chn=1, rsc=3, anc=0, erc=4, rsid=2
 [   22.921580] crw_info : CRW reports slct=0, oflw=0, chn=0, rsc=3, anc=0, erc=4, rsid=0
 [   22.921978] sd 0:0:0:0: [sda] Synchronizing SCSI cache
 [   22.921993] sd 0:0:0:0: [sda] Synchronize Cache(10) failed: Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK

I opted to fill in the same response data that is returned from the more graceful device detach, where the disk device is removed prior to the controller device.

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

Reviewed-by Fam Zheng <[email protected]>

Signed-off-by Martin K. Petersen <[email protected]>

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

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

---
 drivers/scsi/virtio_scsi.c |   11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

drivers/scsi/virtio_scsi.c +10 -1

@@ -533,7 +533,9 @@ static int virtscsi_queuecommand(struct
 {
 	struct Scsi_Host *shost = virtio_scsi_host(vscsi->vdev);
 	struct virtio_scsi_cmd *cmd = scsi_cmd_priv(sc);
+	unsigned long flags;
 	int req_size;
+	int ret;
 
 	BUG_ON(scsi_sg_count(sc) > shost->sg_tablesize);

@@ -561,8 +563,15 @@ static int virtscsi_queuecommand(struct
 		req_size = sizeof(cmd->req.cmd);
 	}
 
-	if (virtscsi_kick_cmd(req_vq, cmd, req_size, sizeof(cmd->resp.cmd)) != 0)
+	ret = virtscsi_kick_cmd(req_vq, cmd, req_size, sizeof(cmd->resp.cmd));
+	if (ret == -EIO) {
+		cmd->resp.cmd.response = VIRTIO_SCSI_S_BAD_TARGET;
+		spin_lock_irqsave(&req_vq->vq_lock, flags);
+		virtscsi_complete_cmd(vscsi, cmd);
+		spin_unlock_irqrestore(&req_vq->vq_lock, flags);
+	} else if (ret != 0) {
 		return SCSI_MLQUEUE_HOST_BUSY;
+	}
 	return 0;
 }

Greg Kroah-Hartman

author maintainer

2017-07-03 13:40 UTC #60 lore raw

PATCH 60/101 platform/x86: ideapad-laptop: handle ACPI event 1

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Zach Ploskey <[email protected]>

[ Upstream commit cfee5d63767b2e7997c1f36420d008abbe61565c ]

On Ideapad laptops, ACPI event 1 is currently not handled. Many models log "ideapad_laptop: Unknown event: 1" every 20 seconds or so while running on battery power. Some convertible laptops receive this event when switching in and out of tablet mode.

This adds and additional case for event 1 in ideapad_acpi_notify to call ideapad_input_report(priv, vpc_bit), so that the event is reported to userspace and we avoid unnecessary logging.

Fixes bug #107481 (https://bugzilla.kernel.org/show_bug.cgi?id=107481)
Fixes bug #65751 (https://bugzilla.kernel.org/show_bug.cgi?id=65751)

Signed-off-by Zach Ploskey <[email protected]>

Signed-off-by Andy Shevchenko <[email protected]>

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

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

---
 drivers/platform/x86/ideapad-laptop.c |    1 +
 1 file changed, 1 insertion(+)

drivers/platform/x86/ideapad-laptop.c +1 -0

@@ -807,6 +807,7 @@ static void ideapad_acpi_notify(acpi_han
 			case 11:
 			case 7:
 			case 6:
+			case 1:
 				ideapad_input_report(priv, vpc_bit);
 				break;
 			case 5:

Greg Kroah-Hartman

author maintainer

2017-07-03 13:40 UTC #61 lore raw

PATCH 61/101 amd-xgbe: Check xgbe_init() return code

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: "Lendacky, Thomas" <[email protected]>

[ Upstream commit 738f7f647371ff4cfc9646c99dba5b58ad142db3 ]

The xgbe_init() routine returns a return code indicating success or failure, but the return code is not checked. Add code to xgbe_init() to issue a message when failures are seen and add code to check the xgbe_init() return code.

Signed-off-by Tom Lendacky <[email protected]>

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

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

---
 drivers/net/ethernet/amd/xgbe/xgbe-dev.c |    4 +++-
 drivers/net/ethernet/amd/xgbe/xgbe-drv.c |    4 +++-
 2 files changed, 6 insertions(+), 2 deletions(-)

drivers/net/ethernet/amd/xgbe/xgbe-dev.c +3 -1

@@ -2732,8 +2732,10 @@ static int xgbe_init(struct xgbe_prv_dat
 
 	/* Flush Tx queues */
 	ret = xgbe_flush_tx_queues(pdata);
-	if (ret)
+	if (ret) {
+		netdev_err(pdata->netdev, "error flushing TX queues\n");
 		return ret;
+	}
 
 	/*
 	 * Initialize DMA related features

drivers/net/ethernet/amd/xgbe/xgbe-drv.c +3 -1

@@ -877,7 +877,9 @@ static int xgbe_start(struct xgbe_prv_da
 
 	DBGPR("-->xgbe_start\n");
 
-	hw_if->init(pdata);
+	ret = hw_if->init(pdata);
+	if (ret)
+		return ret;
 
 	ret = phy_if->phy_start(pdata);
 	if (ret)

Greg Kroah-Hartman

author maintainer

2017-07-03 13:35 UTC #62 lore raw

PATCH 62/101 net: dsa: Check return value of phy_connect_direct()

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Florian Fainelli <[email protected]>

[ Upstream commit 4078b76cac68e50ccf1f76a74e7d3d5788aec3fe ]

We need to check the return value of phy_connect_direct() in dsa_slave_phy_connect() otherwise we may be continuing the initialization of a slave network device with a PHY that already attached somewhere else and which will soon be in error because the PHY device is in error.

The conditions for such an error to occur are that we have a port of our switch that is not disabled, and has the same port number as a PHY address (say both 5) that can be probed using the DSA slave MII bus. We end-up having this slave network device find a PHY at the same address as our port number, and we try to attach to it.

A slave network (e.g: port 0) has already attached to our PHY device, and we try to re-attach it with a different network device, but since we ignore the error we would end-up initializating incorrect device references by the time the slave network interface is opened.

The code has been (re)organized several times, making it hard to provide an exact Fixes tag, this is a bugfix nonetheless.

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

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

---
 net/dsa/slave.c |    6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

net/dsa/slave.c +2 -4

@@ -1006,10 +1006,8 @@ static int dsa_slave_phy_connect(struct
 	/* Use already configured phy mode */
 	if (p->phy_interface == PHY_INTERFACE_MODE_NA)
 		p->phy_interface = p->phy->interface;
-	phy_connect_direct(slave_dev, p->phy, dsa_slave_adjust_link,
-			   p->phy_interface);
-
-	return 0;
+	return phy_connect_direct(slave_dev, p->phy, dsa_slave_adjust_link,
+				  p->phy_interface);
 }
 
 static int dsa_slave_phy_setup(struct dsa_slave_priv *p,

Greg Kroah-Hartman

author maintainer

2017-07-03 13:39 UTC #63 lore raw

PATCH 64/101 vfio/spapr: fail tce_iommu_attach_group() when iommu_data is null

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Greg Kurz <[email protected]>

[ Upstream commit bd00fdf198e2da475a2f4265a83686ab42d998a8 ]

The recently added mediated VFIO driver doesn't know about powerpc iommu. It thus doesn't register a struct iommu_table_group in the iommu group upon device creation. The iommu_data pointer hence remains null.

This causes a kernel oops when userspace tries to set the iommu type of a container associated with a mediated device to VFIO_SPAPR_TCE_v2_IOMMU.

[   82.585440] mtty mtty: MDEV: Registered
[   87.655522] iommu: Adding device 83b8f4f2-509f-382f-3c1e-e6bfe0fa1001 to group 10
[   87.655527] vfio_mdev 83b8f4f2-509f-382f-3c1e-e6bfe0fa1001: MDEV: group_id = 10
[  116.297184] Unable to handle kernel paging request for data at address 0x00000030
[  116.297389] Faulting instruction address: 0xd000000007870524
[  116.297465] Oops: Kernel access of bad area, sig: 11 [#1]
[  116.297611] SMP NR_CPUS=2048
[  116.297611] NUMA
[  116.297627] PowerNV
...
[  116.297954] CPU: 33 PID: 7067 Comm: qemu-system-ppc Not tainted 4.10.0-rc5-mdev-test #8
[  116.297993] task: c000000e7718b680 task.stack: c000000e77214000
[  116.298025] NIP: d000000007870524 LR: d000000007870518 CTR: 0000000000000000
[  116.298064] REGS: c000000e77217990 TRAP: 0300   Not tainted  (4.10.0-rc5-mdev-test)
[  116.298103] MSR: 9000000000009033 <SF,HV,EE,ME,IR,DR,RI,LE>
[  116.298107]   CR: 84004444  XER: 00000000
[  116.298154] CFAR: c00000000000888c DAR: 0000000000000030 DSISR: 40000000 SOFTE: 1
               GPR00: d000000007870518 c000000e77217c10 d00000000787b0ed c000000eed2103c0
               GPR04: 0000000000000000 0000000000000000 c000000eed2103e0 0000000f24320000
               GPR08: 0000000000000104 0000000000000001 0000000000000000 d0000000078729b0
               GPR12: c00000000025b7e0 c00000000fe08400 0000000000000001 000001002d31d100
               GPR16: 000001002c22c850 00003ffff315c750 0000000043145680 0000000043141bc0
               GPR20: ffffffffffffffed fffffffffffff000 0000000020003b65 d000000007706018
               GPR24: c000000f16cf0d98 d000000007706000 c000000003f42980 c000000003f42980
               GPR28: c000000f1575ac00 c000000003f429c8 0000000000000000 c000000eed2103c0
[  116.298504] NIP [d000000007870524] tce_iommu_attach_group+0x10c/0x360 [vfio_iommu_spapr_tce]
[  116.298555] LR [d000000007870518] tce_iommu_attach_group+0x100/0x360 [vfio_iommu_spapr_tce]
[  116.298601] Call Trace:
[  116.298610] [c000000e77217c10] [d000000007870518] tce_iommu_attach_group+0x100/0x360 [vfio_iommu_spapr_tce] (unreliable)
[  116.298671] [c000000e77217cb0] [d0000000077033a0] vfio_fops_unl_ioctl+0x278/0x3e0 [vfio]
[  116.298713] [c000000e77217d40] [c0000000002a3ebc] do_vfs_ioctl+0xcc/0x8b0
[  116.298745] [c000000e77217de0] [c0000000002a4700] SyS_ioctl+0x60/0xc0
[  116.298782] [c000000e77217e30] [c00000000000b220] system_call+0x38/0xfc
[  116.298812] Instruction dump:
[  116.298828] 7d3f4b78 409effc8 3d220000 e9298020 3c800140 38a00018 608480c0 e8690028
[  116.298869] 4800249d e8410018 7c7f1b79 41820230 <e93e0030> 2fa90000 419e0114 e9090020
[  116.298914] ---[ end trace 1e10b0ced08b9120 ]---

This patch fixes the oops.

Reported-by Vaibhav Jain <[email protected]>

Signed-off-by Greg Kurz <[email protected]>

Signed-off-by Alex Williamson <[email protected]>

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

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

---
 drivers/vfio/vfio_iommu_spapr_tce.c |    4 ++++
 1 file changed, 4 insertions(+)

drivers/vfio/vfio_iommu_spapr_tce.c +4 -0

@@ -1163,6 +1163,10 @@ static int tce_iommu_attach_group(void *
 	/* pr_debug("tce_vfio: Attaching group #%u to iommu %p\n",
 			iommu_group_id(iommu_group), iommu_group); */
 	table_group = iommu_group_get_iommudata(iommu_group);
+	if (!table_group) {
+		ret = -ENODEV;
+		goto unlock_exit;
+	}
 
 	if (tce_groups_attached(container) && (!table_group->ops ||
 			!table_group->ops->take_ownership ||

Greg Kroah-Hartman

author maintainer

2017-07-03 13:39 UTC #64 lore raw

PATCH 65/101 virtio_net: fix PAGE_SIZE > 64k

4.4-stable review patch. If anyone has any objections, please let me know.

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

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

[ Upstream commit d0fa28f00052391b5df328f502fbbdd4444938b7 ]

I don't have any guests with PAGE_SIZE > 64k but the code seems to be clearly broken in that case
as PAGE_SIZE / MERGEABLE_BUFFER_ALIGN will need
more than 8 bit and so the code in mergeable_ctx_to_buf_address does not give us the actual true size.

Cc John Fastabend <[email protected]>

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

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

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

---
 drivers/net/virtio_net.c |   10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

drivers/net/virtio_net.c +9 -1

@@ -47,8 +47,16 @@ module_param(gso, bool, 0444);
  */
 DECLARE_EWMA(pkt_len, 1, 64)
 
+/* With mergeable buffers we align buffer address and use the low bits to
+ * encode its true size. Buffer size is up to 1 page so we need to align to
+ * square root of page size to ensure we reserve enough bits to encode the true
+ * size.
+ */
+#define MERGEABLE_BUFFER_MIN_ALIGN_SHIFT ((PAGE_SHIFT + 1) / 2)
+
 /* Minimum alignment for mergeable packet buffers. */
-#define MERGEABLE_BUFFER_ALIGN max(L1_CACHE_BYTES, 256)
+#define MERGEABLE_BUFFER_ALIGN max(L1_CACHE_BYTES, \
+				   1 << MERGEABLE_BUFFER_MIN_ALIGN_SHIFT)
 
 #define VIRTNET_DRIVER_VERSION "1.0.0"

Greg Kroah-Hartman

author maintainer

2017-07-03 13:35 UTC #65 lore raw

PATCH 66/101 vxlan: do not age static remote mac entries

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Balakrishnan Raman <[email protected]>

[ Upstream commit efb5f68f32995c146944a9d4257c3cf8eae2c4a1 ]

Mac aging is applicable only for dynamically learnt remote mac entries. Check for user configured static remote mac entries and skip aging.

Signed-off-by Balakrishnan Raman <[email protected]>

Signed-off-by Roopa Prabhu <[email protected]>

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

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

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

drivers/net/vxlan.c +1 -1

@@ -2240,7 +2240,7 @@ static void vxlan_cleanup(unsigned long
 				= container_of(p, struct vxlan_fdb, hlist);
 			unsigned long timeout;
 
-			if (f->state & NUD_PERMANENT)
+			if (f->state & (NUD_PERMANENT | NUD_NOARP))
 				continue;
 
 			timeout = f->used + vxlan->cfg.age_interval * HZ;

Greg Kroah-Hartman

author maintainer

2017-07-03 13:39 UTC #66 lore raw

PATCH 67/101 ibmveth: Add a proper check for the availability of the checksum features

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Thomas Huth <[email protected]>

[ Upstream commit 23d28a859fb847fd7fcfbd31acb3b160abb5d6ae ]

When using the ibmveth driver in a KVM/QEMU based VM, it currently always prints out a scary error message like this when it is started:

ibmveth 71000003 (unregistered net_device): unable to change checksum offload settings. 1 rc=-2 ret_attr=71000003

This happens because the driver always tries to enable the checksum offloading without checking for the availability of this feature first. QEMU does not support checksum offloading for the spapr-vlan device, thus we always get the error message here.
According to the LoPAPR specification, the "ibm,illan-options" property of the corresponding device tree node should be checked first to see whether the H_ILLAN_ATTRIUBTES hypercall and thus the checksum offloading feature is available. Thus let's do this in the ibmveth driver, too, so that the error message is really only limited to cases where something goes wrong, and does not occur if the feature is just missing.

Signed-off-by Thomas Huth <[email protected]>

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

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

---
 drivers/net/ethernet/ibm/ibmveth.c |    7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

drivers/net/ethernet/ibm/ibmveth.c +5 -2

@@ -1602,8 +1602,11 @@ static int ibmveth_probe(struct vio_dev
 	netdev->netdev_ops = &ibmveth_netdev_ops;
 	netdev->ethtool_ops = &netdev_ethtool_ops;
 	SET_NETDEV_DEV(netdev, &dev->dev);
-	netdev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM |
-		NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+	netdev->hw_features = NETIF_F_SG;
+	if (vio_get_attribute(dev, "ibm,illan-options", NULL) != NULL) {
+		netdev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
+				       NETIF_F_RXCSUM;
+	}
 
 	netdev->features |= netdev->hw_features;

Greg Kroah-Hartman

author maintainer

2017-07-03 13:39 UTC #67 lore raw

PATCH 68/101 kernel/panic.c: add missing \n

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Jiri Slaby <[email protected]>

[ Upstream commit ff7a28a074ccbea999dadbb58c46212cf90984c6 ]

When a system panics, the "Rebooting in X seconds.." message is never printed because it lacks a new line. Fix it.

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

Signed-off-by Jiri Slaby <[email protected]>

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

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

---
 kernel/panic.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

kernel/panic.c +1 -1

@@ -167,7 +167,7 @@ void panic(const char *fmt, ...)
 		 * Delay timeout seconds before rebooting the machine.
 		 * We can't use the "normal" timers since we just panicked.
 		 */
-		pr_emerg("Rebooting in %d seconds..", panic_timeout);
+		pr_emerg("Rebooting in %d seconds..\n", panic_timeout);
 
 		for (i = 0; i < panic_timeout * 1000; i += PANIC_TIMER_STEP) {
 			touch_nmi_watchdog();

Greg Kroah-Hartman

author maintainer

2017-07-03 13:35 UTC #68 lore raw

PATCH 69/101 HID: i2c-hid: Add sleep between POWER ON and RESET

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Brendan McGrath <[email protected]>

[ Upstream commit a89af4abdf9b353cdd6f61afc0eaaac403304873 ]

Support for the Asus Touchpad was recently added. It turns out this device can fail initialisation (and become unusable) when the RESET command is sent too soon after the POWER ON command.

Unfortunately the i2c-hid specification does not specify the need for a delay between these two commands. But it was discovered the Windows driver has a 1ms delay.

As a result, this patch modifies the i2c-hid module to add a sleep inbetween the POWER ON and RESET commands which lasts between 1ms and 5ms.

See https://github.com/vlasenko/hid-asus-dkms/issues/24 for further details.

Signed-off-by Brendan McGrath <[email protected]>

Reviewed-by Benjamin Tissoires <[email protected]>

Signed-off-by Jiri Kosina <[email protected]>

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

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

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

drivers/hid/i2c-hid/i2c-hid.c +9 -0

@@ -364,6 +364,15 @@ static int i2c_hid_hwreset(struct i2c_cl
 	if (ret)
 		return ret;
 
+	/*
+	 * The HID over I2C specification states that if a DEVICE needs time
+	 * after the PWR_ON request, it should utilise CLOCK stretching.
+	 * However, it has been observered that the Windows driver provides a
+	 * 1ms sleep between the PWR_ON and RESET requests and that some devices
+	 * rely on this.
+	 */
+	usleep_range(1000, 5000);
+
 	i2c_hid_dbg(ihid, "resetting...\n");
 
 	ret = i2c_hid_command(client, &hid_reset_cmd, NULL, 0);

Greg Kroah-Hartman

author maintainer

2017-07-03 13:35 UTC #69 lore raw

PATCH 70/101 scsi: lpfc: avoid double free of resource identifiers

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Roberto Sassu <[email protected]>

[ Upstream commit cd60be4916ae689387d04b86b6fc15931e4c95ae ]

Set variables initialized in lpfc_sli4_alloc_resource_identifiers() to NULL if an error occurred. Otherwise, lpfc_sli4_driver_resource_unset() attempts to free the memory again.

Signed-off-by Roberto Sassu <[email protected]>

Signed-off-by Johannes Thumshirn <[email protected]>

Acked-by James Smart <[email protected]>

Signed-off-by Martin K. Petersen <[email protected]>

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

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

---
 drivers/scsi/lpfc/lpfc_sli.c |    7 +++++++
 1 file changed, 7 insertions(+)

drivers/scsi/lpfc/lpfc_sli.c +7 -0

@@ -5887,18 +5887,25 @@ lpfc_sli4_alloc_resource_identifiers(str
 
  free_vfi_bmask:
 	kfree(phba->sli4_hba.vfi_bmask);
+	phba->sli4_hba.vfi_bmask = NULL;
  free_xri_ids:
 	kfree(phba->sli4_hba.xri_ids);
+	phba->sli4_hba.xri_ids = NULL;
  free_xri_bmask:
 	kfree(phba->sli4_hba.xri_bmask);
+	phba->sli4_hba.xri_bmask = NULL;
  free_vpi_ids:
 	kfree(phba->vpi_ids);
+	phba->vpi_ids = NULL;
  free_vpi_bmask:
 	kfree(phba->vpi_bmask);
+	phba->vpi_bmask = NULL;
  free_rpi_ids:
 	kfree(phba->sli4_hba.rpi_ids);
+	phba->sli4_hba.rpi_ids = NULL;
  free_rpi_bmask:
 	kfree(phba->sli4_hba.rpi_bmask);
+	phba->sli4_hba.rpi_bmask = NULL;
  err_exit:
 	return rc;
 }

Greg Kroah-Hartman

author maintainer

2017-07-03 13:35 UTC #70 lore raw

PATCH 71/101 spi: davinci: use dma_mapping_error()

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Kevin Hilman <[email protected]>

[ Upstream commit c5a2a394835f473ae23931eda5066d3771d7b2f8 ]

The correct error checking for dma_map_single() is to use dma_mapping_error().

Signed-off-by Kevin Hilman <[email protected]>

Signed-off-by Mark Brown <[email protected]>

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

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

---
 drivers/spi/spi-davinci.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

drivers/spi/spi-davinci.c +2 -2

@@ -651,7 +651,7 @@ static int davinci_spi_bufs(struct spi_d
 			buf = t->rx_buf;
 		t->rx_dma = dma_map_single(&spi->dev, buf,
 				t->len, DMA_FROM_DEVICE);
-		if (!t->rx_dma) {
+		if (dma_mapping_error(&spi->dev, !t->rx_dma)) {
 			ret = -EFAULT;
 			goto err_rx_map;
 		}

@@ -665,7 +665,7 @@ static int davinci_spi_bufs(struct spi_d
 			buf = (void *)t->tx_buf;
 		t->tx_dma = dma_map_single(&spi->dev, buf,
 				t->len, DMA_TO_DEVICE);
-		if (!t->tx_dma) {
+		if (dma_mapping_error(&spi->dev, t->tx_dma)) {
 			ret = -EFAULT;
 			goto err_tx_map;
 		}

Ben Hutchings

2017-07-05 14:24 UTC #71 lore raw

Re: [PATCH 4.4 071/101] spi: davinci: use dma_mapping_error()

Quoted 23 lines · Greg Kroah-Hartman

4.4-stable review patch. If anyone has any objections, please let me know.
------------------
From: Kevin Hilman <[email protected]>
[ Upstream commit c5a2a394835f473ae23931eda5066d3771d7b2f8 ]
The correct error checking for dma_map_single() is to use dma_mapping_error().
Signed-off-by Kevin Hilman <[email protected]>
Signed-off-by Mark Brown <[email protected]>
Signed-off-by Sasha Levin <[email protected]>
Signed-off-by Greg Kroah-Hartman <[email protected]>
---
 drivers/spi/spi-davinci.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

drivers/spi/spi-davinci.c static int davinci_spi_bufs(struct spi_d · line 654

Quoted 5 lines

drivers/spi/spi-davinci.c +1 -1

@@ -651,7 +651,7 @@ static int davinci_spi_bufs(struct spi_d
 			buf = t->rx_buf;
 		t->rx_dma = dma_map_single(&spi->dev, buf,
 				t->len, DMA_FROM_DEVICE);
-		if (!t->rx_dma) {
+		if (dma_mapping_error(&spi->dev, !t->rx_dma)) {

[...]

The '!' needs to be deleted. This appears to have been fixed upstream by:

commit 8aedbf580d21121d2a032e4c8ea12d8d2d85e275

Author: Fabien Parent <[email protected]>
Date:   Thu Feb 23 19:01:56 2017 +0100

spi: davinci: Use SPI framework to handle DMA mapping

which is not suitable for stable.

Ben.

Signature · 2 lines

Ben Hutchings
Software Developer, Codethink Ltd.

Greg Kroah-Hartman

author maintainer

2018-04-06 08:21 UTC #72 lore raw

Re: [PATCH 4.4 071/101] spi: davinci: use dma_mapping_error()

Quoted 34 lines · Ben Hutchings

Quoted 23 lines · Greg Kroah-Hartman
4.4-stable review patch. If anyone has any objections, please let me know.
------------------
From: Kevin Hilman <[email protected]>
[ Upstream commit c5a2a394835f473ae23931eda5066d3771d7b2f8 ]
The correct error checking for dma_map_single() is to use dma_mapping_error().
Signed-off-by Kevin Hilman <[email protected]>
Signed-off-by Mark Brown <[email protected]>
Signed-off-by Sasha Levin <[email protected]>
Signed-off-by Greg Kroah-Hartman <[email protected]>
---
 drivers/spi/spi-davinci.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/spi/spi-davinci.c static int davinci_spi_bufs(struct spi_d · line 654
Quoted 5 lines
drivers/spi/spi-davinci.c +1 -1
@@ -651,7 +651,7 @@ static int davinci_spi_bufs(struct spi_d
 			buf = t->rx_buf;
 		t->rx_dma = dma_map_single(&spi->dev, buf,
 				t->len, DMA_FROM_DEVICE);
-		if (!t->rx_dma) {
+		if (dma_mapping_error(&spi->dev, !t->rx_dma)) {
[...]
The '!' needs to be deleted. This appears to have been fixed upstream by:

Quoted 7 lines

commit 8aedbf580d21121d2a032e4c8ea12d8d2d85e275
Author: Fabien Parent <[email protected]>
Date:   Thu Feb 23 19:01:56 2017 +0100
spi: davinci: Use SPI framework to handle DMA mapping
which is not suitable for stable.

Sorry for the delay, now fixed up.

greg k-h

Greg Kroah-Hartman

author maintainer

2017-07-03 13:39 UTC #73 lore raw

PATCH 72/101 arm64: assembler: make adr_l work in modules under KASLR

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Ard Biesheuvel <[email protected]>

[ Upstream commit 41c066f2c4d436c535616fe182331766c57838f0 ]

When CONFIG_RANDOMIZE_MODULE_REGION_FULL=y, the offset between loaded modules and the core kernel may exceed 4 GB, putting symbols exported by the core kernel out of the reach of the ordinary adrp/add instruction pairs used to generate relative symbol references. So make the adr_l macro emit a movz/movk sequence instead when executing in module context.

While at it, remove the pointless special case for the stack pointer.

Acked-by Mark Rutland <[email protected]>

Acked-by Will Deacon <[email protected]>

Signed-off-by Ard Biesheuvel <[email protected]>

Signed-off-by Catalin Marinas <[email protected]>

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

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

---
 arch/arm64/include/asm/assembler.h |   36 +++++++++++++++++++++++++++---------
 1 file changed, 27 insertions(+), 9 deletions(-)

arch/arm64/include/asm/assembler.h +27 -9

@@ -147,22 +147,25 @@ lr	.req	x30		// link register
 
 /*
  * Pseudo-ops for PC-relative adr/ldr/str <reg>, <symbol> where
- * <symbol> is within the range +/- 4 GB of the PC.
+ * <symbol> is within the range +/- 4 GB of the PC when running
+ * in core kernel context. In module context, a movz/movk sequence
+ * is used, since modules may be loaded far away from the kernel
+ * when KASLR is in effect.
  */
 	/*
 	 * @dst: destination register (64 bit wide)
 	 * @sym: name of the symbol
-	 * @tmp: optional scratch register to be used if <dst> == sp, which
-	 *       is not allowed in an adrp instruction
 	 */
-	.macro	adr_l, dst, sym, tmp=
-	.ifb	\tmp
+	.macro	adr_l, dst, sym
+#ifndef MODULE
 	adrp	\dst, \sym
 	add	\dst, \dst, :lo12:\sym
-	.else
-	adrp	\tmp, \sym
-	add	\dst, \tmp, :lo12:\sym
-	.endif
+#else
+	movz	\dst, #:abs_g3:\sym
+	movk	\dst, #:abs_g2_nc:\sym
+	movk	\dst, #:abs_g1_nc:\sym
+	movk	\dst, #:abs_g0_nc:\sym
+#endif
 	.endm
 
 	/*

@@ -173,6 +176,7 @@ lr	.req	x30		// link register
 	 *       the address
 	 */
 	.macro	ldr_l, dst, sym, tmp=
+#ifndef MODULE
 	.ifb	\tmp
 	adrp	\dst, \sym
 	ldr	\dst, [\dst, :lo12:\sym]

@@ -180,6 +184,15 @@ lr	.req	x30		// link register
 	adrp	\tmp, \sym
 	ldr	\dst, [\tmp, :lo12:\sym]
 	.endif
+#else
+	.ifb	\tmp
+	adr_l	\dst, \sym
+	ldr	\dst, [\dst]
+	.else
+	adr_l	\tmp, \sym
+	ldr	\dst, [\tmp]
+	.endif
+#endif
 	.endm
 
 	/*

@@ -189,8 +202,13 @@ lr	.req	x30		// link register
 	 *       while <src> needs to be preserved.
 	 */
 	.macro	str_l, src, sym, tmp
+#ifndef MODULE
 	adrp	\tmp, \sym
 	str	\src, [\tmp, :lo12:\sym]
+#else
+	adr_l	\tmp, \sym
+	str	\src, [\tmp]
+#endif
 	.endm
 
 /*

Ard Biesheuvel

2017-07-04 09:24 UTC #74 lore raw

Re: [PATCH 4.4 072/101] arm64: assembler: make adr_l work in modules under KASLR

Quoted 9 lines · Greg Kroah-Hartman

4.4-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ard Biesheuvel <[email protected]>
[ Upstream commit 41c066f2c4d436c535616fe182331766c57838f0 ]

Quoted 8 lines

When CONFIG_RANDOMIZE_MODULE_REGION_FULL=y, the offset between loaded modules and the core kernel may exceed 4 GB, putting symbols exported by the core kernel out of the reach of the ordinary adrp/add instruction pairs used to generate relative symbol references. So make the adr_l macro emit a movz/movk sequence instead when executing in module context.
While at it, remove the pointless special case for the stack pointer.

As it turns out, this 'pointless special case' was not so pointless in v4.4, and removing it breaks the build.

Given that the only in-module user of adr_l is the new scalar AES code, which is not backported to v4.4, there is really no point in backporting this to v4.4.

Signature · 1 line

Ard.

Quoted 87 lines

Acked-by Mark Rutland <[email protected]>

Acked-by Will Deacon <[email protected]>

Signed-off-by Ard Biesheuvel <[email protected]>

Signed-off-by Catalin Marinas <[email protected]>

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

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

---
 arch/arm64/include/asm/assembler.h |   36 +++++++++++++++++++++++++++---------
 1 file changed, 27 insertions(+), 9 deletions(-)

arch/arm64/include/asm/assembler.h +27 -9

@@ -147,22 +147,25 @@ lr        .req    x30             // link register
 
 /*
  * Pseudo-ops for PC-relative adr/ldr/str <reg>, <symbol> where
- * <symbol> is within the range +/- 4 GB of the PC.
+ * <symbol> is within the range +/- 4 GB of the PC when running
+ * in core kernel context. In module context, a movz/movk sequence
+ * is used, since modules may be loaded far away from the kernel
+ * when KASLR is in effect.
  */
        /*
         * @dst: destination register (64 bit wide)
         * @sym: name of the symbol
-        * @tmp: optional scratch register to be used if <dst> == sp, which
-        *       is not allowed in an adrp instruction
         */
-       .macro  adr_l, dst, sym, tmp=
-       .ifb    \tmp
+       .macro  adr_l, dst, sym
+#ifndef MODULE
        adrp    \dst, \sym
        add     \dst, \dst, :lo12:\sym
-       .else
-       adrp    \tmp, \sym
-       add     \dst, \tmp, :lo12:\sym
-       .endif
+#else
+       movz    \dst, #:abs_g3:\sym
+       movk    \dst, #:abs_g2_nc:\sym
+       movk    \dst, #:abs_g1_nc:\sym
+       movk    \dst, #:abs_g0_nc:\sym
+#endif
        .endm
 
        /*

@@ -173,6 +176,7 @@ lr  .req    x30             // link register
         *       the address
         */
        .macro  ldr_l, dst, sym, tmp=
+#ifndef MODULE
        .ifb    \tmp
        adrp    \dst, \sym
        ldr     \dst, [\dst, :lo12:\sym]

@@ -180,6 +184,15 @@ lr .req    x30             // link register
        adrp    \tmp, \sym
        ldr     \dst, [\tmp, :lo12:\sym]
        .endif
+#else
+       .ifb    \tmp
+       adr_l   \dst, \sym
+       ldr     \dst, [\dst]
+       .else
+       adr_l   \tmp, \sym
+       ldr     \dst, [\tmp]
+       .endif
+#endif
        .endm
 
        /*

@@ -189,8 +202,13 @@ lr .req    x30             // link register
         *       while <src> needs to be preserved.
         */
        .macro  str_l, src, sym, tmp
+#ifndef MODULE
        adrp    \tmp, \sym
        str     \src, [\tmp, :lo12:\sym]
+#else
+       adr_l   \tmp, \sym
+       str     \src, [\tmp]
+#endif
        .endm
 
 /*

Greg Kroah-Hartman

author maintainer

2017-07-04 09:29 UTC #75 lore raw

Re: [PATCH 4.4 072/101] arm64: assembler: make adr_l work in modules under KASLR

Quoted 19 lines · Ard Biesheuvel

Quoted 9 lines · Greg Kroah-Hartman
4.4-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ard Biesheuvel <[email protected]>
[ Upstream commit 41c066f2c4d436c535616fe182331766c57838f0 ]
Quoted 8 lines
When CONFIG_RANDOMIZE_MODULE_REGION_FULL=y, the offset between loaded modules and the core kernel may exceed 4 GB, putting symbols exported by the core kernel out of the reach of the ordinary adrp/add instruction pairs used to generate relative symbol references. So make the adr_l macro emit a movz/movk sequence instead when executing in module context.
While at it, remove the pointless special case for the stack pointer.

Quoted 6 lines

As it turns out, this 'pointless special case' was not so pointless in v4.4, and removing it breaks the build.
Given that the only in-module user of adr_l is the new scalar AES code, which is not backported to v4.4, there is really no point in backporting this to v4.4.

Yes, I dropped it from the tree about 2 hours ago after the build-bots reported it killed things :)

thanks,

greg k-h

Greg Kroah-Hartman

author maintainer

2017-07-03 13:35 UTC #76 lore raw

PATCH 73/101 mac80211: initialize SMPS field in HT capabilities

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Felix Fietkau <[email protected]>

[ Upstream commit 43071d8fb3b7f589d72663c496a6880fb097533c ]

ibss and mesh modes copy the ht capabilites from the band without overriding the SMPS state. Unfortunately the default value 0 for the SMPS field means static SMPS instead of disabled.

This results in HT ibss and mesh setups using only single-stream rates, even though SMPS is not supposed to be active.

Initialize SMPS to disabled for all bands on ieee80211_hw_register to ensure that the value is sane where it is not overriden with the real SMPS state.

Reported-by Elektra Wagenrad <[email protected]>

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

[move VHT TODO comment to a better place]

Signed-off-by Johannes Berg <[email protected]>

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

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

---
 net/mac80211/main.c |   13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

net/mac80211/main.c +9 -4

@@ -891,12 +891,17 @@ int ieee80211_register_hw(struct ieee802
 		supp_ht = supp_ht || sband->ht_cap.ht_supported;
 		supp_vht = supp_vht || sband->vht_cap.vht_supported;
 
-		if (sband->ht_cap.ht_supported)
-			local->rx_chains =
-				max(ieee80211_mcs_to_chains(&sband->ht_cap.mcs),
-				    local->rx_chains);
+		if (!sband->ht_cap.ht_supported)
+			continue;
 
 		/* TODO: consider VHT for RX chains, hopefully it's the same */
+		local->rx_chains =
+			max(ieee80211_mcs_to_chains(&sband->ht_cap.mcs),
+			    local->rx_chains);
+
+		/* no need to mask, SM_PS_DISABLED has all bits set */
+		sband->ht_cap.cap |= WLAN_HT_CAP_SM_PS_DISABLED <<
+			             IEEE80211_HT_CAP_SM_PS_SHIFT;
 	}
 
 	/* if low-level driver supports AP, we also support VLAN */

Greg Kroah-Hartman

author maintainer

2017-07-03 13:39 UTC #77 lore raw

PATCH 74/101 x86/mpx: Use compatible types in comparison to fix sparse error

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Tobias Klauser <[email protected]>

[ Upstream commit 453828625731d0ba7218242ef6ec88f59408f368 ]

info->si_addr is of type void __user *, so it should be compared against something from the same address space.

This fixes the following sparse error:

arch/x86/mm/mpx.c:296:27: error: incompatible types in comparison expression (different address spaces)

Signed-off-by Tobias Klauser <[email protected]>

Cc Dave Hansen <[email protected]>

Cc Linus Torvalds <[email protected]>

Cc Peter Zijlstra <[email protected]>

Cc Thomas Gleixner <[email protected]>

Signed-off-by Ingo Molnar <[email protected]>

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

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

---
 arch/x86/mm/mpx.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

arch/x86/mm/mpx.c +1 -1

@@ -293,7 +293,7 @@ siginfo_t *mpx_generate_siginfo(struct p
 	 * We were not able to extract an address from the instruction,
 	 * probably because there was something invalid in it.
 	 */
-	if (info->si_addr == (void *)-1) {
+	if (info->si_addr == (void __user *)-1) {
 		err = -EINVAL;
 		goto err_out;
 	}

Greg Kroah-Hartman

author maintainer

2017-07-03 13:35 UTC #78 lore raw

PATCH 75/101 coredump: Ensure proper size of sparse core files

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Dave Kleikamp <[email protected]>

[ Upstream commit 4d22c75d4c7b5c5f4bd31054f09103ee490878fd ]

If the last section of a core file ends with an unmapped or zero page, the size of the file does not correspond with the last dump_skip() call. gdb complains that the file is truncated and can be confusing to users.

After all of the vma sections are written, make sure that the file size is no smaller than the current file position.

This problem can be demonstrated with gdb's bigcore testcase on the sparc architecture.

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

Cc Alexander Viro <[email protected]>

Signed-off-by Al Viro <[email protected]>

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

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

---
 fs/binfmt_elf.c          |    1 +
 fs/coredump.c            |   18 ++++++++++++++++++
 include/linux/coredump.h |    1 +
 3 files changed, 20 insertions(+)

fs/binfmt_elf.c +1 -0

@@ -2295,6 +2295,7 @@ static int elf_core_dump(struct coredump
 				goto end_coredump;
 		}
 	}
+	dump_truncate(cprm);
 
 	if (!elf_core_write_extra_data(cprm))
 		goto end_coredump;

fs/coredump.c +18 -0

@@ -810,3 +810,21 @@ int dump_align(struct coredump_params *c
 	return mod ? dump_skip(cprm, align - mod) : 1;
 }
 EXPORT_SYMBOL(dump_align);
+
+/*
+ * Ensures that file size is big enough to contain the current file
+ * postion. This prevents gdb from complaining about a truncated file
+ * if the last "write" to the file was dump_skip.
+ */
+void dump_truncate(struct coredump_params *cprm)
+{
+	struct file *file = cprm->file;
+	loff_t offset;
+
+	if (file->f_op->llseek && file->f_op->llseek != no_llseek) {
+		offset = file->f_op->llseek(file, 0, SEEK_CUR);
+		if (i_size_read(file->f_mapping->host) < offset)
+			do_truncate(file->f_path.dentry, offset, 0, file);
+	}
+}
+EXPORT_SYMBOL(dump_truncate);

include/linux/coredump.h +1 -0

@@ -14,6 +14,7 @@ struct coredump_params;
 extern int dump_skip(struct coredump_params *cprm, size_t nr);
 extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr);
 extern int dump_align(struct coredump_params *cprm, int align);
+extern void dump_truncate(struct coredump_params *cprm);
 #ifdef CONFIG_COREDUMP
 extern void do_coredump(const siginfo_t *siginfo);
 #else

Greg Kroah-Hartman

author maintainer

2017-07-03 13:39 UTC #79 lore raw

PATCH 76/101 swiotlb: ensure that page-sized mappings are page-aligned

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Nikita Yushchenko <[email protected]>

[ Upstream commit 602d9858f07c72eab64f5f00e2fae55f9902cfbe ]

Some drivers do depend on page mappings to be page aligned.

Swiotlb already enforces such alignment for mappings greater than page, extend that to page-sized mappings as well.

Without this fix, nvme hits BUG() in nvme_setup_prps(), because that routine assumes page-aligned mappings.

Signed-off-by Nikita Yushchenko <[email protected]>

Reviewed-by Christoph Hellwig <[email protected]>

Reviewed-by Sagi Grimberg <[email protected]>

Signed-off-by Konrad Rzeszutek Wilk <[email protected]>

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

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

---
 lib/swiotlb.c |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

lib/swiotlb.c +3 -3

@@ -452,11 +452,11 @@ phys_addr_t swiotlb_tbl_map_single(struc
 		    : 1UL << (BITS_PER_LONG - IO_TLB_SHIFT);
 
 	/*
-	 * For mappings greater than a page, we limit the stride (and
-	 * hence alignment) to a page size.
+	 * For mappings greater than or equal to a page, we limit the stride
+	 * (and hence alignment) to a page size.
 	 */
 	nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
-	if (size > PAGE_SIZE)
+	if (size >= PAGE_SIZE)
 		stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT));
 	else
 		stride = 1;

Greg Kroah-Hartman

author maintainer

2017-07-03 13:35 UTC #80 lore raw

PATCH 77/101 s390/ctl_reg: make __ctl_load a full memory barrier

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Heiko Carstens <[email protected]>

[ Upstream commit e991c24d68b8c0ba297eeb7af80b1e398e98c33f ]

We have quite a lot of code that depends on the order of the __ctl_load inline assemby and subsequent memory accesses, like e.g. disabling lowcore protection and the writing to lowcore.

Since the __ctl_load macro does not have memory barrier semantics, nor any other dependencies the compiler is, theoretically, free to shuffle code around. Or in other words: storing to lowcore could happen before lowcore protection is disabled.

In order to avoid this class of potential bugs simply add a full memory barrier to the __ctl_load macro.

Signed-off-by Heiko Carstens <[email protected]>

Signed-off-by Martin Schwidefsky <[email protected]>

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

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

---
 arch/s390/include/asm/ctl_reg.h |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

arch/s390/include/asm/ctl_reg.h +3 -1

@@ -15,7 +15,9 @@
 	BUILD_BUG_ON(sizeof(addrtype) != (high - low + 1) * sizeof(long));\
 	asm volatile(							\
 		"	lctlg	%1,%2,%0\n"				\
-		: : "Q" (*(addrtype *)(&array)), "i" (low), "i" (high));\
+		:							\
+		: "Q" (*(addrtype *)(&array)), "i" (low), "i" (high)	\
+		: "memory");						\
 }
 
 #define __ctl_store(array, low, high) {					\

Greg Kroah-Hartman

author maintainer

2017-07-03 13:39 UTC #81 lore raw

PATCH 78/101 be2net: fix status check in be_cmd_pmac_add()

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Ivan Vecera <[email protected]>

[ Upstream commit fe68d8bfe59c561664aa87d827aa4b320eb08895 ]

Return value from be_mcc_notify_wait() contains a base completion status together with an additional status. The base_status() macro need to be used to access base status.

Fixes e3a7ae2 be2net: Changing MAC Address of a VF was broken

Cc Sathya Perla <[email protected]>

Cc Ajit Khaparde <[email protected]>

Cc Sriharsha Basavapatna <[email protected]>

Cc Somnath Kotur <[email protected]>

Signed-off-by Ivan Vecera <[email protected]>

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

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

---
 drivers/net/ethernet/emulex/benet/be_cmds.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

drivers/net/ethernet/emulex/benet/be_cmds.c +1 -1

@@ -1052,7 +1052,7 @@ int be_cmd_pmac_add(struct be_adapter *a
 err:
 	spin_unlock_bh(&adapter->mcc_lock);
 
-	 if (status == MCC_STATUS_UNAUTHORIZED_REQUEST)
+	 if (base_status(status) == MCC_STATUS_UNAUTHORIZED_REQUEST)
 		status = -EPERM;
 
 	return status;

Greg Kroah-Hartman

author maintainer

2017-07-03 13:39 UTC #82 lore raw

PATCH 79/101 perf probe: Fix to show correct locations for events on modules

Link http://lkml.kernel.org/r/148411436777.9978.1440275861947194930.stgit@devbox open here

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Masami Hiramatsu <[email protected]>

[ Upstream commit d2d4edbebe07ddb77980656abe7b9bc7a9e0cdf7 ]

Fix to show correct locations for events on modules by relocating given address instead of retrying after failure.

This happens when the module text size is big enough, bigger than sh_addr, because the original code retries with given address + sh_addr if it failed to find CU DIE at the given address.

Any address smaller than sh_addr always fails and it retries with the correct address, but addresses bigger than sh_addr will get a CU DIE which is on the given address (not adjusted by sh_addr).

In my environment(x86-64), the sh_addr of ".text" section is 0x10030. Since i915 is a huge kernel module, we can see this issue as below.

  $ grep "[Tt] .*\[i915\]" /proc/kallsyms | sort | head -n1
  ffffffffc0270000 t i915_switcheroo_can_switch	[i915]

ffffffffc0270000 + 0x10030 = ffffffffc0280030, so we'll check symbols cross this boundary.

  $ grep "[Tt] .*\[i915\]" /proc/kallsyms | grep -B1 ^ffffffffc028\
  | head -n 2
  ffffffffc027ff80 t haswell_init_clock_gating	[i915]
  ffffffffc0280110 t valleyview_init_clock_gating	[i915]

So setup probes on both function and see what happen.

  $ sudo ./perf probe -m i915 -a haswell_init_clock_gating \
        -a valleyview_init_clock_gating
  Added new events:
    probe:haswell_init_clock_gating (on haswell_init_clock_gating in i915)
    probe:valleyview_init_clock_gating (on valleyview_init_clock_gating in i915)

You can now use it in all perf tools, such as:

perf record -e probe:valleyview_init_clock_gating -aR sleep 1

  $ sudo ./perf probe -l
    probe:haswell_init_clock_gating (on haswell_init_clock_gating@gpu/drm/i915/intel_pm.c in i915)
    probe:valleyview_init_clock_gating (on i915_vga_set_decode:4@gpu/drm/i915/i915_drv.c in i915)

As you can see, haswell_init_clock_gating is correctly shown, but valleyview_init_clock_gating is not.

With this patch, both events are shown correctly.

  $ sudo ./perf probe -l
    probe:haswell_init_clock_gating (on haswell_init_clock_gating@gpu/drm/i915/intel_pm.c in i915)
    probe:valleyview_init_clock_gating (on valleyview_init_clock_gating@gpu/drm/i915/intel_pm.c in i915)

Committer notes:

In my case:

  # perf probe -m i915 -a haswell_init_clock_gating -a valleyview_init_clock_gating
  Added new events:
    probe:haswell_init_clock_gating (on haswell_init_clock_gating in i915)
    probe:valleyview_init_clock_gating (on valleyview_init_clock_gating in i915)

You can now use it in all perf tools, such as:

perf record -e probe:valleyview_init_clock_gating -aR sleep 1

  # perf probe -l
    probe:haswell_init_clock_gating (on i915_getparam+432@gpu/drm/i915/i915_drv.c in i915)
    probe:valleyview_init_clock_gating (on __i915_printk+240@gpu/drm/i915/i915_drv.c in i915)
  #

  # readelf -SW /lib/modules/4.9.0+/build/vmlinux | egrep -w '.text|Name'
   [Nr] Name   Type      Address          Off    Size   ES Flg Lk Inf Al
   [ 1] .text  PROGBITS  ffffffff81000000 200000 822fd3 00  AX  0   0 4096
  #

So both are b0rked, now with the fix:

  # perf probe -m i915 -a haswell_init_clock_gating -a valleyview_init_clock_gating
  Added new events:
    probe:haswell_init_clock_gating (on haswell_init_clock_gating in i915)
    probe:valleyview_init_clock_gating (on valleyview_init_clock_gating in i915)

You can now use it in all perf tools, such as:

perf record -e probe:valleyview_init_clock_gating -aR sleep 1

  # perf probe -l
    probe:haswell_init_clock_gating (on haswell_init_clock_gating@gpu/drm/i915/intel_pm.c in i915)
    probe:valleyview_init_clock_gating (on valleyview_init_clock_gating@gpu/drm/i915/intel_pm.c in i915)
  #

Both looks correct.

Signed-off-by Masami Hiramatsu <[email protected]>

Tested-by Arnaldo Carvalho de Melo <[email protected]>

Cc Jiri Olsa <[email protected]>

Cc Namhyung Kim <[email protected]>

Cc Peter Zijlstra <[email protected]>

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

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

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

---
 tools/perf/util/probe-finder.c |   10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

tools/perf/util/probe-finder.c +3 -7

@@ -1460,16 +1460,12 @@ int debuginfo__find_probe_point(struct d
 	Dwarf_Addr _addr = 0, baseaddr = 0;
 	const char *fname = NULL, *func = NULL, *basefunc = NULL, *tmp;
 	int baseline = 0, lineno = 0, ret = 0;
-	bool reloc = false;
 
-retry:
+	/* We always need to relocate the address for aranges */
+	if (debuginfo__get_text_offset(dbg, &baseaddr) == 0)
+		addr += baseaddr;
 	/* Find cu die */
 	if (!dwarf_addrdie(dbg->dbg, (Dwarf_Addr)addr, &cudie)) {
-		if (!reloc && debuginfo__get_text_offset(dbg, &baseaddr) == 0) {
-			addr += baseaddr;
-			reloc = true;
-			goto retry;
-		}
 		pr_warning("Failed to find debug information for address %lx\n",
 			   addr);
 		ret = -EINVAL;

Greg Kroah-Hartman

author maintainer

2017-07-03 13:35 UTC #83 lore raw

PATCH 80/101 net/mlx4_core: Eliminate warning messages for SRQ_LIMIT under SRIOV

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Jack Morgenstein <[email protected]>

[ Upstream commit 9577b174cd0323d287c994ef0891db71666d0765 ]

When running SRIOV, warnings for SRQ LIMIT events flood the Hypervisor's message log when (correct, normally operating) apps use SRQ LIMIT events as a trigger to post WQEs to SRQs.

Add more information to the existing debug printout for SRQ_LIMIT, and output the warning messages only for the SRQ CATAS ERROR event.

Fixes acba2420f9d2 ("mlx4_core: Add wrapper functions and comm channel and slave event support to EQs")

Fixes e0debf9cb50d ("mlx4_core: Reduce warning message for SRQ_LIMIT event to debug level")

Signed-off-by Jack Morgenstein <[email protected]>

Signed-off-by Tariq Toukan <[email protected]>

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

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

---
 drivers/net/ethernet/mellanox/mlx4/eq.c |   23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

drivers/net/ethernet/mellanox/mlx4/eq.c +14 -9

@@ -542,8 +542,9 @@ static int mlx4_eq_int(struct mlx4_dev *
 			break;
 
 		case MLX4_EVENT_TYPE_SRQ_LIMIT:
-			mlx4_dbg(dev, "%s: MLX4_EVENT_TYPE_SRQ_LIMIT\n",
-				 __func__);
+			mlx4_dbg(dev, "%s: MLX4_EVENT_TYPE_SRQ_LIMIT. srq_no=0x%x, eq 0x%x\n",
+				 __func__, be32_to_cpu(eqe->event.srq.srqn),
+				 eq->eqn);
 		case MLX4_EVENT_TYPE_SRQ_CATAS_ERROR:
 			if (mlx4_is_master(dev)) {
 				/* forward only to slave owning the SRQ */

@@ -558,15 +559,19 @@ static int mlx4_eq_int(struct mlx4_dev *
 						  eq->eqn, eq->cons_index, ret);
 					break;
 				}
-				mlx4_warn(dev, "%s: slave:%d, srq_no:0x%x, event: %02x(%02x)\n",
-					  __func__, slave,
-					  be32_to_cpu(eqe->event.srq.srqn),
-					  eqe->type, eqe->subtype);
+				if (eqe->type ==
+				    MLX4_EVENT_TYPE_SRQ_CATAS_ERROR)
+					mlx4_warn(dev, "%s: slave:%d, srq_no:0x%x, event: %02x(%02x)\n",
+						  __func__, slave,
+						  be32_to_cpu(eqe->event.srq.srqn),
+						  eqe->type, eqe->subtype);
 
 				if (!ret && slave != dev->caps.function) {
-					mlx4_warn(dev, "%s: sending event %02x(%02x) to slave:%d\n",
-						  __func__, eqe->type,
-						  eqe->subtype, slave);
+					if (eqe->type ==
+					    MLX4_EVENT_TYPE_SRQ_CATAS_ERROR)
+						mlx4_warn(dev, "%s: sending event %02x(%02x) to slave:%d\n",
+							  __func__, eqe->type,
+							  eqe->subtype, slave);
 					mlx4_slave_event(dev, slave, eqe);
 					break;
 				}

Greg Kroah-Hartman

author maintainer

2017-07-03 13:39 UTC #84 lore raw

PATCH 81/101 sctp: check af before verify address in sctp_addr_id2transport

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Xin Long <[email protected]>

[ Upstream commit 912964eacb111551db73429719eb5fadcab0ff8a ]

Commit 6f29a1306131 ("sctp: sctp_addr_id2transport should verify the addr before looking up assoc") invoked sctp_verify_addr to verify the addr.

But it didn't check af variable beforehand, once users pass an address with family = 0 through sockopt, sctp_get_af_specific will return NULL and NULL pointer dereference will be caused by af->sockaddr_len.

This patch is to fix it by returning NULL if af variable is NULL.

Fixes 6f29a1306131 ("sctp: sctp_addr_id2transport should verify the addr before looking up assoc")

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

Acked-by Marcelo Ricardo Leitner <[email protected]>

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

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

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

net/sctp/socket.c +1 -1

@@ -239,7 +239,7 @@ static struct sctp_transport *sctp_addr_
 	union sctp_addr *laddr = (union sctp_addr *)addr;
 	struct sctp_transport *transport;
 
-	if (sctp_verify_addr(sk, laddr, af->sockaddr_len))
+	if (!af || sctp_verify_addr(sk, laddr, af->sockaddr_len))
 		return NULL;
 
 	addr_asoc = sctp_endpoint_lookup_assoc(sctp_sk(sk)->ep,

Greg Kroah-Hartman

author maintainer

2017-07-03 13:35 UTC #85 lore raw

PATCH 82/101 ravb: Fix use-after-free on `ifconfig eth0 down`

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Eugeniu Rosca <[email protected]>

[ Upstream commit 79514ef670e9e575a1fe36922268c439d0f0ca8a ]

Commit a47b70ea86bd ("ravb: unmap descriptors when freeing rings") has introduced the issue seen in [1] reproduced on H3ULCB board.

Fix this by relocating the RX skb ringbuffer free operation, so that swiotlb page unmapping can be done first. Freeing of aligned TX buffers is not relevant to the issue seen in [1]. Still, reposition TX free calls as well, to have all kfree() operations performed consistently _after_ dma_unmap_*()/dma_free_*().

[1] Console screenshot with the problem reproduced:

salvator-x login: root

root@salvator-x:~# ifconfig eth0 up
Micrel KSZ9031 Gigabit PHY e6800000.ethernet-ffffffff:00: \
       attached PHY driver [Micrel KSZ9031 Gigabit PHY]   \
       (mii_bus:phy_addr=e6800000.ethernet-ffffffff:00, irq=235)
IPv6: ADDRCONF(NETDEV_UP): eth0: link is not ready
root@salvator-x:~#
root@salvator-x:~# ifconfig eth0 down

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

BUG: KASAN: use-after-free in swiotlb_tbl_unmap_single+0xc4/0x35c
Write of size 1538 at addr ffff8006d884f780 by task ifconfig/1649

CPU: 0 PID: 1649 Comm: ifconfig Not tainted 4.12.0-rc4-00004-g112eb07287d1 #32
Hardware name: Renesas H3ULCB board based on r8a7795 (DT)
Call trace:
[<ffff20000808f11c>] dump_backtrace+0x0/0x3a4
[<ffff20000808f4d4>] show_stack+0x14/0x1c
[<ffff20000865970c>] dump_stack+0xf8/0x150
[<ffff20000831f8b0>] print_address_description+0x7c/0x330
[<ffff200008320010>] kasan_report+0x2e0/0x2f4
[<ffff20000831eac0>] check_memory_region+0x20/0x14c
[<ffff20000831f054>] memcpy+0x48/0x68
[<ffff20000869ed50>] swiotlb_tbl_unmap_single+0xc4/0x35c
[<ffff20000869fcf4>] unmap_single+0x90/0xa4
[<ffff20000869fd14>] swiotlb_unmap_page+0xc/0x14
[<ffff2000080a2974>] __swiotlb_unmap_page+0xcc/0xe4
[<ffff2000088acdb8>] ravb_ring_free+0x514/0x870
[<ffff2000088b25dc>] ravb_close+0x288/0x36c
[<ffff200008aaf8c4>] __dev_close_many+0x14c/0x174
[<ffff200008aaf9b4>] __dev_close+0xc8/0x144
[<ffff200008ac2100>] __dev_change_flags+0xd8/0x194
[<ffff200008ac221c>] dev_change_flags+0x60/0xb0
[<ffff200008ba2dec>] devinet_ioctl+0x484/0x9d4
[<ffff200008ba7b78>] inet_ioctl+0x190/0x194
[<ffff200008a78c44>] sock_do_ioctl+0x78/0xa8
[<ffff200008a7a128>] sock_ioctl+0x110/0x3c4
[<ffff200008365a70>] vfs_ioctl+0x90/0xa0
[<ffff200008365dbc>] do_vfs_ioctl+0x148/0xc38
[<ffff2000083668f0>] SyS_ioctl+0x44/0x74
[<ffff200008083770>] el0_svc_naked+0x24/0x28

The buggy address belongs to the page:
page:ffff7e001b6213c0 count:0 mapcount:0 mapping:          (null) index:0x0
flags: 0x4000000000000000()
raw: 4000000000000000 0000000000000000 0000000000000000 00000000ffffffff
raw: 0000000000000000 ffff7e001b6213e0 0000000000000000 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff8006d884f680: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
 ffff8006d884f700: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
>ffff8006d884f780: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
                   ^
 ffff8006d884f800: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
 ffff8006d884f880: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
==================================================================

Disabling lock debugging due to kernel taint
root@salvator-x:~#

Fixes a47b70ea86bd ("ravb: unmap descriptors when freeing rings")

Signed-off-by Eugeniu Rosca <[email protected]>

Acked-by Sergei Shtylyov <[email protected]>

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

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

---
 drivers/net/ethernet/renesas/ravb_main.c |   24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

drivers/net/ethernet/renesas/ravb_main.c +12 ~~-12~~

@@ -221,18 +221,6 @@ static void ravb_ring_free(struct net_de
 	int ring_size;
 	int i;
 
-	/* Free RX skb ringbuffer */
-	if (priv->rx_skb[q]) {
-		for (i = 0; i < priv->num_rx_ring[q]; i++)
-			dev_kfree_skb(priv->rx_skb[q][i]);
-	}
-	kfree(priv->rx_skb[q]);
-	priv->rx_skb[q] = NULL;
-
-	/* Free aligned TX buffers */
-	kfree(priv->tx_align[q]);
-	priv->tx_align[q] = NULL;
-
 	if (priv->rx_ring[q]) {
 		for (i = 0; i < priv->num_rx_ring[q]; i++) {
 			struct ravb_ex_rx_desc *desc = &priv->rx_ring[q][i];

@@ -261,6 +249,18 @@ static void ravb_ring_free(struct net_de
 		priv->tx_ring[q] = NULL;
 	}
 
+	/* Free RX skb ringbuffer */
+	if (priv->rx_skb[q]) {
+		for (i = 0; i < priv->num_rx_ring[q]; i++)
+			dev_kfree_skb(priv->rx_skb[q][i]);
+	}
+	kfree(priv->rx_skb[q]);
+	priv->rx_skb[q] = NULL;
+
+	/* Free aligned TX buffers */
+	kfree(priv->tx_align[q]);
+	priv->tx_align[q] = NULL;
+
 	/* Free TX skb ringbuffer.
 	 * SKBs are freed by ravb_tx_free() call above.
 	 */

Greg Kroah-Hartman

author maintainer

2017-07-03 13:39 UTC #86 lore raw

PATCH 83/101 jump label: fix passing kbuild_cflags when checking for asm goto support

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Gleb Fotengauer-Malinovskiy <[email protected]>

commit 7292ae3d5a18fb922be496e6bb687647193569b4 upstream.

The latest change of asm goto support check added passing of KBUILD_CFLAGS to compiler. When these flags reference gcc plugins that are not built yet, the check fails.

When one runs "make bzImage" followed by "make modules", the kernel is always built with HAVE_JUMP_LABEL disabled, while the modules are built depending on CONFIG_JUMP_LABEL. If HAVE_JUMP_LABEL macro happens to be different, modules are built with undefined references, e.g.:

ERROR: "static_key_slow_inc" [net/netfilter/xt_TEE.ko] undefined!
ERROR: "static_key_slow_dec" [net/netfilter/xt_TEE.ko] undefined!
ERROR: "static_key_slow_dec" [net/netfilter/nft_meta.ko] undefined!
ERROR: "static_key_slow_inc" [net/netfilter/nft_meta.ko] undefined!
ERROR: "nf_hooks_needed" [net/netfilter/ipvs/ip_vs.ko] undefined!
ERROR: "nf_hooks_needed" [net/ipv6/ipv6.ko] undefined!
ERROR: "static_key_count" [net/ipv6/ipv6.ko] undefined!
ERROR: "static_key_slow_inc" [net/ipv6/ipv6.ko] undefined!

This change moves the check before all these references are added to KBUILD_CFLAGS. This is correct because subsequent KBUILD_CFLAGS modifications are not relevant to this check.

Reported-by Anton V. Boyarshinov <[email protected]>

Fixes 35f860f9ba6a ("jump label: pass kbuild_cflags when checking for asm goto support")

Signed-off-by Gleb Fotengauer-Malinovskiy <[email protected]>

Signed-off-by Dmitry V. Levin <[email protected]>

Acked-by Steven Rostedt (VMware) <[email protected]>

Acked-by David Lin <[email protected]>

Signed-off-by Masahiro Yamada <[email protected]>

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

---
 Makefile |   12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

Makefile +6 -6

@@ -633,6 +633,12 @@ endif
 # Tell gcc to never replace conditional load with a non-conditional one
 KBUILD_CFLAGS	+= $(call cc-option,--param=allow-store-data-races=0)
 
+# check for 'asm goto'
+ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC) $(KBUILD_CFLAGS)), y)
+	KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO
+	KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO
+endif
+
 ifdef CONFIG_READABLE_ASM
 # Disable optimizations that make assembler listings hard to read.
 # reorder blocks reorders the control in the function

@@ -788,12 +794,6 @@ KBUILD_CFLAGS   += $(call cc-option,-Wer
 # use the deterministic mode of AR if available
 KBUILD_ARFLAGS := $(call ar-option,D)
 
-# check for 'asm goto'
-ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC) $(KBUILD_CFLAGS)), y)
-	KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO
-	KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO
-endif
-
 include scripts/Makefile.kasan
 include scripts/Makefile.extrawarn

Greg Kroah-Hartman

author maintainer

2017-07-03 13:39 UTC #87 lore raw

PATCH 84/101 xfrm: fix stack access out of bounds with CONFIG_XFRM_SUB_POLICY

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Sabrina Dubroca <[email protected]>

commit 9b3eb54106cf6acd03f07cf0ab01c13676a226c2 upstream.

When CONFIG_XFRM_SUB_POLICY=y, xfrm_dst stores a copy of the flowi for that dst. Unfortunately, the code that allocates and fills this copy doesn't care about what type of flowi (flowi, flowi4, flowi6) gets passed. In multiple code paths (from raw_sendmsg, from TCP when replying to a FIN, in vxlan, geneve, and gre), the flowi that gets passed to xfrm is actually an on-stack flowi4, so we end up reading stuff from the stack past the end of the flowi4 struct.

Since xfrm_dst->origin isn't used anywhere following commit ca116922afa8 ("xfrm: Eliminate "fl" and "pol" args to xfrm_bundle_ok()."), just get rid of it. xfrm_dst->partner isn't used either, so get rid of that too.

Fixes 9d6ec938019c ("ipv4: Use flowi4 in public route lookup interfaces.")

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

Signed-off-by Steffen Klassert <[email protected]>

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

---
 include/net/xfrm.h     |   10 ----------
 net/xfrm/xfrm_policy.c |   47 -----------------------------------------------
 2 files changed, 57 deletions(-)

include/net/xfrm.h +0 ~~-10~~

@@ -948,10 +948,6 @@ struct xfrm_dst {
 	struct flow_cache_object flo;
 	struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX];
 	int num_pols, num_xfrms;
-#ifdef CONFIG_XFRM_SUB_POLICY
-	struct flowi *origin;
-	struct xfrm_selector *partner;
-#endif
 	u32 xfrm_genid;
 	u32 policy_genid;
 	u32 route_mtu_cached;

@@ -967,12 +963,6 @@ static inline void xfrm_dst_destroy(stru
 	dst_release(xdst->route);
 	if (likely(xdst->u.dst.xfrm))
 		xfrm_state_put(xdst->u.dst.xfrm);
-#ifdef CONFIG_XFRM_SUB_POLICY
-	kfree(xdst->origin);
-	xdst->origin = NULL;
-	kfree(xdst->partner);
-	xdst->partner = NULL;
-#endif
 }
 #endif

net/xfrm/xfrm_policy.c +0 ~~-47~~

59 lines not on this page · raw message

Greg Kroah-Hartman

author maintainer

2017-07-03 13:39 UTC #88 lore raw

PATCH 85/101 xfrm: NULL dereference on allocation failure

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Dan Carpenter <[email protected]>

commit e747f64336fc15e1c823344942923195b800aa1e upstream.

The default error code in pfkey_msg2xfrm_state() is -ENOBUFS. We added a new call to security_xfrm_state_alloc() which sets "err" to zero so there several places where we can return ERR_PTR(0) if kmalloc() fails. The caller is expecting error pointers so it leads to a NULL dereference.

Fixes df71837d5024 ("[LSM-IPSec]: Security association restriction.")

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

Signed-off-by Steffen Klassert <[email protected]>

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

---
 net/key/af_key.c |    1 +
 1 file changed, 1 insertion(+)

net/key/af_key.c +1 -0

@@ -1135,6 +1135,7 @@ static struct xfrm_state * pfkey_msg2xfr
 			goto out;
 	}
 
+	err = -ENOBUFS;
 	key = ext_hdrs[SADB_EXT_KEY_AUTH - 1];
 	if (sa->sadb_sa_auth) {
 		int keysize = 0;

Greg Kroah-Hartman

author maintainer

2017-07-03 13:39 UTC #89 lore raw

PATCH 86/101 xfrm: Oops on error in pfkey_msg2xfrm_state()

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Dan Carpenter <[email protected]>

commit 1e3d0c2c70cd3edb5deed186c5f5c75f2b84a633 upstream.

There are some missing error codes here so we accidentally return NULL instead of an error pointer. It results in a NULL pointer dereference.

Fixes df71837d5024 ("[LSM-IPSec]: Security association restriction.")

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

Signed-off-by Steffen Klassert <[email protected]>

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

---
 net/key/af_key.c |   16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

net/key/af_key.c +12 -4

@@ -1147,8 +1147,10 @@ static struct xfrm_state * pfkey_msg2xfr
 		if (key)
 			keysize = (key->sadb_key_bits + 7) / 8;
 		x->aalg = kmalloc(sizeof(*x->aalg) + keysize, GFP_KERNEL);
-		if (!x->aalg)
+		if (!x->aalg) {
+			err = -ENOMEM;
 			goto out;
+		}
 		strcpy(x->aalg->alg_name, a->name);
 		x->aalg->alg_key_len = 0;
 		if (key) {

@@ -1167,8 +1169,10 @@ static struct xfrm_state * pfkey_msg2xfr
 				goto out;
 			}
 			x->calg = kmalloc(sizeof(*x->calg), GFP_KERNEL);
-			if (!x->calg)
+			if (!x->calg) {
+				err = -ENOMEM;
 				goto out;
+			}
 			strcpy(x->calg->alg_name, a->name);
 			x->props.calgo = sa->sadb_sa_encrypt;
 		} else {

@@ -1182,8 +1186,10 @@ static struct xfrm_state * pfkey_msg2xfr
 			if (key)
 				keysize = (key->sadb_key_bits + 7) / 8;
 			x->ealg = kmalloc(sizeof(*x->ealg) + keysize, GFP_KERNEL);
-			if (!x->ealg)
+			if (!x->ealg) {
+				err = -ENOMEM;
 				goto out;
+			}
 			strcpy(x->ealg->alg_name, a->name);
 			x->ealg->alg_key_len = 0;
 			if (key) {

@@ -1228,8 +1234,10 @@ static struct xfrm_state * pfkey_msg2xfr
 		struct xfrm_encap_tmpl *natt;
 
 		x->encap = kmalloc(sizeof(*x->encap), GFP_KERNEL);
-		if (!x->encap)
+		if (!x->encap) {
+			err = -ENOMEM;
 			goto out;
+		}
 
 		natt = x->encap;
 		n_type = ext_hdrs[SADB_X_EXT_NAT_T_TYPE-1];

Greg Kroah-Hartman

author maintainer

2017-07-03 13:39 UTC #90 lore raw

PATCH 87/101 watchdog: bcm281xx: Fix use of uninitialized spinlock.

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Eric Anholt <[email protected]>

commit fedf266f9955d9a019643cde199a2fd9a0259f6f upstream.

The bcm_kona_wdt_set_resolution_reg() call takes the spinlock, so initialize it earlier. Fixes a warning at boot with lock debugging enabled.

Fixes 6adb730dc208 ("watchdog: bcm281xx: Watchdog Driver")

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

Reviewed-by Florian Fainelli <[email protected]>

Reviewed-by Guenter Roeck <[email protected]>

Signed-off-by Guenter Roeck <[email protected]>

Signed-off-by Wim Van Sebroeck <[email protected]>

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

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

drivers/watchdog/bcm_kona_wdt.c +2 -1

@@ -304,6 +304,8 @@ static int bcm_kona_wdt_probe(struct pla
 	if (!wdt)
 		return -ENOMEM;
 
+	spin_lock_init(&wdt->lock);
+
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	wdt->base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(wdt->base))

@@ -316,7 +318,6 @@ static int bcm_kona_wdt_probe(struct pla
 		return ret;
 	}
 
-	spin_lock_init(&wdt->lock);
 	platform_set_drvdata(pdev, wdt);
 	watchdog_set_drvdata(&bcm_kona_wdt_wdd, wdt);
 	bcm_kona_wdt_wdd.parent = &pdev->dev;

Greg Kroah-Hartman

author maintainer

2017-07-03 13:40 UTC #91 lore raw

PATCH 88/101 sched/loadavg: Avoid loadavg spikes caused by delayed NO_HZ accounting

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Matt Fleming <[email protected]>

commit 6e5f32f7a43f45ee55c401c0b9585eb01f9629a8 upstream.

If we crossed a sample window while in NO_HZ we will add LOAD_FREQ to the pending sample window time on exit, setting the next update not one window into the future, but two.

This situation on exiting NO_HZ is described by:

this_rq->calc_load_update < jiffies < calc_load_update

In this scenario, what we should be doing is:

this_rq->calc_load_update = calc_load_update [ next window ]

But what we actually do is:

this_rq->calc_load_update = calc_load_update + LOAD_FREQ [ next+1 window ]

This has the effect of delaying load average updates for potentially up to ~9seconds.

This can result in huge spikes in the load average values due to per-cpu uninterruptible task counts being out of sync when accumulated across all CPUs.

It's safe to update the per-cpu active count if we wake between sample windows because any load that we left in 'calc_load_idle' will have been zero'd when the idle load was folded in calc_global_load().

This issue is easy to reproduce before,

commit 9d89c257dfb9 ("sched/fair: Rewrite runnable load and utilization average tracking")

just by forking short-lived process pipelines built from ps(1) and grep(1) in a loop. I'm unable to reproduce the spikes after that commit, but the bug still seems to be present from code review.

Signed-off-by Matt Fleming <[email protected]>

Signed-off-by Peter Zijlstra (Intel) <[email protected]>

Cc Frederic Weisbecker <[email protected]>

Cc Linus Torvalds <[email protected]>

Cc Mike Galbraith <[email protected]>

Cc Morten Rasmussen <[email protected]>

Cc Peter Zijlstra <[email protected]>

Cc Thomas Gleixner <[email protected]>

Cc Vincent Guittot <[email protected]>

Fixes commit 5167e8d ("sched/nohz: Rewrite and fix load-avg computation -- again")

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

Signed-off-by Ingo Molnar <[email protected]>

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

---
 kernel/sched/loadavg.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

kernel/sched/loadavg.c +2 -2

@@ -201,8 +201,9 @@ void calc_load_exit_idle(void)
 	struct rq *this_rq = this_rq();
 
 	/*
-	 * If we're still before the sample window, we're done.
+	 * If we're still before the pending sample window, we're done.
 	 */
+	this_rq->calc_load_update = calc_load_update;
 	if (time_before(jiffies, this_rq->calc_load_update))
 		return;

@@ -211,7 +212,6 @@ void calc_load_exit_idle(void)
 	 * accounted through the nohz accounting, so skip the entire deal and
 	 * sync up for the next window.
 	 */
-	this_rq->calc_load_update = calc_load_update;
 	if (time_before(jiffies, this_rq->calc_load_update + 10))
 		this_rq->calc_load_update += LOAD_FREQ;
 }

Greg Kroah-Hartman

author maintainer

2017-07-03 13:35 UTC #92 lore raw

PATCH 89/101 ARM64/ACPI: Fix BAD_MADT_GICC_ENTRY() macro implementation

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Lorenzo Pieralisi <[email protected]>

commit cb7cf772d83d2d4e6995c5bb9e0fb59aea8f7080 upstream.

The BAD_MADT_GICC_ENTRY() macro checks if a GICC MADT entry passes muster from an ACPI specification standpoint. Current macro detects the MADT GICC entry length through ACPI firmware version (it changed from 76 to 80 bytes in the transition from ACPI 5.1 to ACPI 6.0 specification) but always uses (erroneously) the ACPICA (latest) struct (ie struct acpi_madt_generic_interrupt - that is 80-bytes long) length to check if the current GICC entry memory record exceeds the MADT table end in memory as defined by the MADT table header itself, which may result in false negatives depending on the ACPI firmware version and how the MADT entries are laid out in memory (ie on ACPI 5.1 firmware MADT GICC entries are 76 bytes long, so by adding 80 to a GICC entry start address in memory the resulting address may well be past the actual MADT end, triggering a false negative).

Fix the BAD_MADT_GICC_ENTRY() macro by reshuffling the condition checks and update them to always use the firmware version specific MADT GICC entry length in order to carry out boundary checks.

Fixes b6cfb277378e ("ACPI / ARM64: add BAD_MADT_GICC_ENTRY() macro")

Reported-by Julien Grall <[email protected]>

Acked-by Will Deacon <[email protected]>

Acked-by Marc Zyngier <[email protected]>

Signed-off-by Lorenzo Pieralisi <[email protected]>

Cc Julien Grall <[email protected]>

Cc Hanjun Guo <[email protected]>

Cc Al Stone <[email protected]>

Signed-off-by Catalin Marinas <[email protected]>

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

---
 arch/arm64/include/asm/acpi.h |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

arch/arm64/include/asm/acpi.h +3 -3

@@ -22,9 +22,9 @@
 #define ACPI_MADT_GICC_LENGTH	\
 	(acpi_gbl_FADT.header.revision < 6 ? 76 : 80)
 
-#define BAD_MADT_GICC_ENTRY(entry, end)						\
-	(!(entry) || (unsigned long)(entry) + sizeof(*(entry)) > (end) ||	\
-	 (entry)->header.length != ACPI_MADT_GICC_LENGTH)
+#define BAD_MADT_GICC_ENTRY(entry, end)					\
+	(!(entry) || (entry)->header.length != ACPI_MADT_GICC_LENGTH ||	\
+	(unsigned long)(entry) + ACPI_MADT_GICC_LENGTH > (end))
 
 /* Basic configuration for ACPI */
 #ifdef	CONFIG_ACPI

Greg Kroah-Hartman

author maintainer

2017-07-03 13:35 UTC #93 lore raw

PATCH 90/101 ARM: 8685/1: ensure memblock-limit is pmd-aligned

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Doug Berger <[email protected]>

commit 9e25ebfe56ece7541cd10a20d715cbdd148a2e06 upstream.

The pmd containing memblock_limit is cleared by prepare_page_table() which creates the opportunity for early_alloc() to allocate unmapped memory if memblock_limit is not pmd aligned causing a boot-time hang.

Commit 965278dcb8ab ("ARM: 8356/1: mm: handle non-pmd-aligned end of RAM") attempted to resolve this problem, but there is a path through the adjust_lowmem_bounds() routine where if all memory regions start and end on pmd-aligned addresses the memblock_limit will be set to arm_lowmem_limit.

Since arm_lowmem_limit can be affected by the vmalloc early parameter, the value of arm_lowmem_limit may not be pmd-aligned. This commit corrects this oversight such that memblock_limit is always rounded down to pmd-alignment.

Fixes 965278dcb8ab ("ARM: 8356/1: mm: handle non-pmd-aligned end of RAM")

Signed-off-by Doug Berger <[email protected]>

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

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

---
 arch/arm/mm/mmu.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

arch/arm/mm/mmu.c +4 -4

@@ -1184,15 +1184,15 @@ void __init sanity_check_meminfo(void)
 
 	high_memory = __va(arm_lowmem_limit - 1) + 1;
 
+	if (!memblock_limit)
+		memblock_limit = arm_lowmem_limit;
+
 	/*
 	 * Round the memblock limit down to a pmd size.  This
 	 * helps to ensure that we will allocate memory from the
 	 * last full pmd, which should be mapped.
 	 */
-	if (memblock_limit)
-		memblock_limit = round_down(memblock_limit, PMD_SIZE);
-	if (!memblock_limit)
-		memblock_limit = arm_lowmem_limit;
+	memblock_limit = round_down(memblock_limit, PMD_SIZE);
 
 	memblock_set_current_limit(memblock_limit);
 }

Greg Kroah-Hartman

author maintainer

2017-07-03 13:40 UTC #94 lore raw

PATCH 91/101 x86/mpx: Correctly report do_mpx_bt_fault() failures to user-space

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Joerg Roedel <[email protected]>

commit 5ed386ec09a5d75bcf073967e55e895c2607a5c3 upstream.

When this function fails it just sends a SIGSEGV signal to user-space using force_sig(). This signal is missing essential information about the cause, e.g. the trap_nr or an error code.

Fix this by propagating the error to the only caller of mpx_handle_bd_fault(), do_bounds(), which sends the correct SIGSEGV signal to the process.

Cc Andy Lutomirski <[email protected]>

Cc Borislav Petkov <[email protected]>

Cc Brian Gerst <[email protected]>

Cc Dave Hansen <[email protected]>

Cc Denys Vlasenko <[email protected]>

Cc H. Peter Anvin <[email protected]>

Cc Josh Poimboeuf <[email protected]>

Cc Linus Torvalds <[email protected]>

Cc Peter Zijlstra <[email protected]>

Cc Thomas Gleixner <[email protected]>

Fixes fe3d197f84319 ('x86, mpx: On-demand kernel allocation of bounds tables')

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

Signed-off-by Ingo Molnar <[email protected]>

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

---
 arch/x86/mm/mpx.c |   10 +---------
 1 file changed, 1 insertion(+), 9 deletions(-)

arch/x86/mm/mpx.c +1 -9

@@ -525,15 +525,7 @@ int mpx_handle_bd_fault(void)
 	if (!kernel_managing_mpx_tables(current->mm))
 		return -EINVAL;
 
-	if (do_mpx_bt_fault()) {
-		force_sig(SIGSEGV, current);
-		/*
-		 * The force_sig() is essentially "handling" this
-		 * exception, so we do not pass up the error
-		 * from do_mpx_bt_fault().
-		 */
-	}
-	return 0;
+	return do_mpx_bt_fault();
 }
 
 /*

Greg Kroah-Hartman

author maintainer

2017-07-03 13:35 UTC #95 lore raw

PATCH 92/101 x86/mm: Fix flush_tlb_page() on Xen

Link http://lkml.kernel.org/r/10ed0e4dfea64daef10b87fb85df1746999b4dba.1492844372.git.luto@kernel.org open here

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Andy Lutomirski <[email protected]>

commit dbd68d8e84c606673ebbcf15862f8c155fa92326 upstream.

flush_tlb_page() passes a bogus range to flush_tlb_others() and expects the latter to fix it up. native_flush_tlb_others() has the fixup but Xen's version doesn't. Move the fixup to flush_tlb_others().

AFAICS the only real effect is that, without this fix, Xen would flush everything instead of just the one page on remote vCPUs in when flush_tlb_page() was called.

Signed-off-by Andy Lutomirski <[email protected]>

Reviewed-by Boris Ostrovsky <[email protected]>

Cc Andrew Morton <[email protected]>

Cc Borislav Petkov <[email protected]>

Cc Brian Gerst <[email protected]>

Cc Dave Hansen <[email protected]>

Cc Denys Vlasenko <[email protected]>

Cc H. Peter Anvin <[email protected]>

Cc Josh Poimboeuf <[email protected]>

Cc Juergen Gross <[email protected]>

Cc Konrad Rzeszutek Wilk <[email protected]>

Cc Linus Torvalds <[email protected]>

Cc Michal Hocko <[email protected]>

Cc Nadav Amit <[email protected]>

Cc Peter Zijlstra <[email protected]>

Cc Rik van Riel <[email protected]>

Cc Thomas Gleixner <[email protected]>

Fixes e7b52ffd45a6 ("x86/flush_tlb: try flush_tlb_single one by one in flush_tlb_range")

Signed-off-by Ingo Molnar <[email protected]>

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

---
 arch/x86/mm/tlb.c |    4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

arch/x86/mm/tlb.c +1 -3

@@ -134,8 +134,6 @@ void native_flush_tlb_others(const struc
 {
 	struct flush_tlb_info info;
 
-	if (end == 0)
-		end = start + PAGE_SIZE;
 	info.flush_mm = mm;
 	info.flush_start = start;
 	info.flush_end = end;

@@ -264,7 +262,7 @@ void flush_tlb_page(struct vm_area_struc
 	}
 
 	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
-		flush_tlb_others(mm_cpumask(mm), mm, start, 0UL);
+		flush_tlb_others(mm_cpumask(mm), mm, start, start + PAGE_SIZE);
 
 	preempt_enable();
 }

Greg Kroah-Hartman

author maintainer

2017-07-03 13:40 UTC #96 lore raw

PATCH 93/101 ocfs2: o2hb: revert hb threshold to keep compatible

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Junxiao Bi <[email protected]>

commit 33496c3c3d7b88dcbe5e55aa01288b05646c6aca upstream.

Configfs is the interface for ocfs2-tools to set configure to kernel and $configfs_dir/cluster/$clustername/heartbeat/dead_threshold is the one used to configure heartbeat dead threshold. Kernel has a default value of it but user can set O2CB_HEARTBEAT_THRESHOLD in /etc/sysconfig/o2cb to override it.

Commit 45b997737a80 ("ocfs2/cluster: use per-attribute show and store methods") changed heartbeat dead threshold name while ocfs2-tools did not, so ocfs2-tools won't set this configurable and the default value is always used. So revert it.

Fixes 45b997737a80 ("ocfs2/cluster: use per-attribute show and store methods")

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

Signed-off-by Junxiao Bi <[email protected]>

Acked-by Joseph Qi <[email protected]>

Cc Mark Fasheh <[email protected]>

Cc Joel Becker <[email protected]>

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

---
 fs/ocfs2/cluster/heartbeat.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

fs/ocfs2/cluster/heartbeat.c +4 -4

@@ -2070,13 +2070,13 @@ unlock:
 	spin_unlock(&o2hb_live_lock);
 }
 
-static ssize_t o2hb_heartbeat_group_threshold_show(struct config_item *item,
+static ssize_t o2hb_heartbeat_group_dead_threshold_show(struct config_item *item,
 		char *page)
 {
 	return sprintf(page, "%u\n", o2hb_dead_threshold);
 }
 
-static ssize_t o2hb_heartbeat_group_threshold_store(struct config_item *item,
+static ssize_t o2hb_heartbeat_group_dead_threshold_store(struct config_item *item,
 		const char *page, size_t count)
 {
 	unsigned long tmp;

@@ -2125,11 +2125,11 @@ static ssize_t o2hb_heartbeat_group_mode
 
 }
 
-CONFIGFS_ATTR(o2hb_heartbeat_group_, threshold);
+CONFIGFS_ATTR(o2hb_heartbeat_group_, dead_threshold);
 CONFIGFS_ATTR(o2hb_heartbeat_group_, mode);
 
 static struct configfs_attribute *o2hb_heartbeat_group_attrs[] = {
-	&o2hb_heartbeat_group_attr_threshold,
+	&o2hb_heartbeat_group_attr_dead_threshold,
 	&o2hb_heartbeat_group_attr_mode,
 	NULL,
 };

Greg Kroah-Hartman

author maintainer

2017-07-03 13:35 UTC #97 lore raw

PATCH 94/101 iommu/vt-d: Dont over-free page table directories

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: David Dillow <[email protected]>

commit f7116e115acdd74bc75a4daf6492b11d43505125 upstream.

dma_pte_free_level() recurses down the IOMMU page tables and frees directory pages that are entirely contained in the given PFN range. Unfortunately, it incorrectly calculates the starting address covered by the PTE under consideration, which can lead to it clearing an entry that is still in use.

This occurs if we have a scatterlist with an entry that has a length greater than 1026 MB and is aligned to 2 MB for both the IOMMU and physical addresses. For example, if __domain_mapping() is asked to map a two-entry scatterlist with 2 MB and 1028 MB segments to PFN 0xffff80000, it will ask if dma_pte_free_pagetable() is asked to PFNs from 0xffff80200 to 0xffffc05ff, it will also incorrectly clear the PFNs from 0xffff80000 to 0xffff801ff because of this issue. The current code will set level_pfn to 0xffff80200, and 0xffff80200-0xffffc01ff fits inside the range being cleared. Properly setting the level_pfn for the current level under consideration catches that this PTE is outside of the range being cleared.

This patch also changes the value passed into dma_pte_free_level() when it recurses. This only affects the first PTE of the range being cleared, and is handled by the existing code that ensures we start our cursor no lower than start_pfn.

This was found when using dma_map_sg() to map large chunks of contiguous memory, which immediatedly led to faults on the first access of the erroneously-deleted mappings.

Fixes 3269ee0bd668 ("intel-iommu: Fix leaks in pagetable freeing")

Reviewed-by Benjamin Serebrin <[email protected]>

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

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

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

drivers/iommu/intel-iommu.c +1 -1

@@ -1137,7 +1137,7 @@ static void dma_pte_free_level(struct dm
 		if (!dma_pte_present(pte) || dma_pte_superpage(pte))
 			goto next;
 
-		level_pfn = pfn & level_mask(level - 1);
+		level_pfn = pfn & level_mask(level);
 		level_pte = phys_to_virt(dma_pte_addr(pte));
 
 		if (level > 2)

Greg Kroah-Hartman

author maintainer

2017-07-03 13:40 UTC #98 lore raw

PATCH 95/101 iommu: Handle default domain attach failure

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Robin Murphy <[email protected]>

commit 797a8b4d768c58caac58ee3e8cb36a164d1b7751 upstream.

We wouldn't normally expect ops->attach_dev() to fail, but on IOMMUs with limited hardware resources, or generally misconfigured systems, it is certainly possible. We report failure correctly from the external iommu_attach_device() interface, but do not do so in iommu_group_add() when attaching to the default domain. The result of failure there is that the device, group and domain all get left in a broken, part-configured state which leads to weird errors and misbehaviour down the line when IOMMU API calls sort-of-but-don't-quite work.

Check the return value of __iommu_attach_device() on the default domain, and refactor the error handling paths to cope with its failure and clean up correctly in such cases.

Fixes e39cb8a3aa98 ("iommu: Make sure a device is always attached to a domain")

Reported-by Punit Agrawal <[email protected]>

Signed-off-by Robin Murphy <[email protected]>

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

---
 drivers/iommu/iommu.c |   37 ++++++++++++++++++++++++-------------
 1 file changed, 24 insertions(+), 13 deletions(-)

drivers/iommu/iommu.c +24 ~~-13~~

@@ -391,36 +391,30 @@ int iommu_group_add_device(struct iommu_
 	device->dev = dev;
 
 	ret = sysfs_create_link(&dev->kobj, &group->kobj, "iommu_group");
-	if (ret) {
-		kfree(device);
-		return ret;
-	}
+	if (ret)
+		goto err_free_device;
 
 	device->name = kasprintf(GFP_KERNEL, "%s", kobject_name(&dev->kobj));
 rename:
 	if (!device->name) {
-		sysfs_remove_link(&dev->kobj, "iommu_group");
-		kfree(device);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto err_remove_link;
 	}
 
 	ret = sysfs_create_link_nowarn(group->devices_kobj,
 				       &dev->kobj, device->name);
 	if (ret) {
-		kfree(device->name);
 		if (ret == -EEXIST && i >= 0) {
 			/*
 			 * Account for the slim chance of collision
 			 * and append an instance to the name.
 			 */
+			kfree(device->name);
 			device->name = kasprintf(GFP_KERNEL, "%s.%d",
 						 kobject_name(&dev->kobj), i++);
 			goto rename;
 		}
-
-		sysfs_remove_link(&dev->kobj, "iommu_group");
-		kfree(device);
-		return ret;
+		goto err_free_name;
 	}
 
 	kobject_get(group->devices_kobj);

@@ -432,8 +426,10 @@ rename:
 	mutex_lock(&group->mutex);
 	list_add_tail(&device->list, &group->devices);
 	if (group->domain)
-		__iommu_attach_device(group->domain, dev);
+		ret = __iommu_attach_device(group->domain, dev);
 	mutex_unlock(&group->mutex);
+	if (ret)
+		goto err_put_group;
 
 	/* Notify any listeners about change to group. */
 	blocking_notifier_call_chain(&group->notifier,

@@ -444,6 +440,21 @@ rename:
 	pr_info("Adding device %s to group %d\n", dev_name(dev), group->id);
 
 	return 0;
+
+err_put_group:
+	mutex_lock(&group->mutex);
+	list_del(&device->list);
+	mutex_unlock(&group->mutex);
+	dev->iommu_group = NULL;
+	kobject_put(group->devices_kobj);
+err_free_name:
+	kfree(device->name);
+err_remove_link:
+	sysfs_remove_link(&dev->kobj, "iommu_group");
+err_free_device:
+	kfree(device);
+	pr_err("Failed to add device %s to group %d: %d\n", dev_name(dev), group->id, ret);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(iommu_group_add_device);

Ben Hutchings

2017-07-05 18:52 UTC #99 lore raw

Re: [PATCH 4.4 095/101] iommu: Handle default domain attach failure

Quoted 20 lines · Greg Kroah-Hartman

4.4-stable review patch. If anyone has any objections, please let me know.
------------------
From: Robin Murphy <[email protected]>
commit 797a8b4d768c58caac58ee3e8cb36a164d1b7751 upstream.
We wouldn't normally expect ops->attach_dev() to fail, but on IOMMUs with limited hardware resources, or generally misconfigured systems, it is certainly possible. We report failure correctly from the external iommu_attach_device() interface, but do not do so in iommu_group_add() when attaching to the default domain. The result of failure there is that the device, group and domain all get left in a broken, part-configured state which leads to weird errors and misbehaviour down the line when IOMMU API calls sort-of-but-don't-quite work.
Check the return value of __iommu_attach_device() on the default domain, and refactor the error handling paths to cope with its failure and clean up correctly in such cases.

[...]

drivers/iommu/iommu.c rename: · line 432

Quoted 9 lines

drivers/iommu/iommu.c +3 -1

@@ -432,8 +426,10 @@ rename:
 	mutex_lock(&group->mutex);
 	list_add_tail(&device->list, &group->devices);
 	if (group->domain)
-		__iommu_attach_device(group->domain, dev);
+		ret = __iommu_attach_device(group->domain, dev);
 	mutex_unlock(&group->mutex);
+	if (ret)
+		goto err_put_group;

It's still (briefly) possible for other tasks to observe the device in the broken state. Shouldn't the error check be done before mutex_unlock()?

Quoted 14 lines

drivers/iommu/iommu.c +8 -0

 	/* Notify any listeners about change to group. */
 	blocking_notifier_call_chain(&group->notifier,

@@ -444,6 +440,21 @@ rename:
 	pr_info("Adding device %s to group %d\n", dev_name(dev), group->id);
 
 	return 0;
+
+err_put_group:
+	mutex_lock(&group->mutex);
+	list_del(&device->list);
+	mutex_unlock(&group->mutex);
+	dev->iommu_group = NULL;
+	kobject_put(group->devices_kobj);
+err_free_name:

drivers/iommu/iommu.c rename: · line 460

Quoted 10 lines

drivers/iommu/iommu.c +7 -0

+	kfree(device->name);
+err_remove_link:
+	sysfs_remove_link(&dev->kobj, "iommu_group");
+err_free_device:
+	kfree(device);
+	pr_err("Failed to add device %s to group %d: %d\n", dev_name(dev), group->id, ret);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(iommu_group_add_device);

It seems like this cleanup statement in iommu_group_remove_device() should also be done here under err_put_group:

	sysfs_remove_link(group->devices_kobj, device->name);

Ben.

Signature · 2 lines

Ben Hutchings
Software Developer, Codethink Ltd.

Greg Kroah-Hartman

author maintainer

2017-07-03 13:40 UTC #100 lore raw

PATCH 96/101 iommu/amd: Fix incorrect error handling in amd_iommu_bind_pasid()

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Pan Bian <[email protected]>

commit 73dbd4a4230216b6a5540a362edceae0c9b4876b upstream.

In function amd_iommu_bind_pasid(), the control flow jumps to label out_free when pasid_state->mm and mm is NULL. And mmput(mm) is called. In function mmput(mm), mm is referenced without validation. This will result in a NULL dereference bug. This patch fixes the bug.

Signed-off-by Pan Bian <[email protected]>

Fixes f0aac63b873b ('iommu/amd: Don't hold a reference to mm_struct')

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

---
 drivers/iommu/amd_iommu_v2.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

drivers/iommu/amd_iommu_v2.c +1 -1

@@ -699,9 +699,9 @@ out_clear_state:
 
 out_unregister:
 	mmu_notifier_unregister(&pasid_state->mn, mm);
+	mmput(mm);
 
 out_free:
-	mmput(mm);
 	free_pasid_state(pasid_state);
 
 out:

Greg Kroah-Hartman

author maintainer

2017-07-03 13:40 UTC #101 lore raw

PATCH 97/101 cpufreq: s3c2416: double free on driver init error path

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Dan Carpenter <[email protected]>

commit a69261e4470d680185a15f748d9cdafb37c57a33 upstream.

The "goto err_armclk;" error path already does a clk_put(s3c_freq->hclk); so this is a double free.

Fixes 34ee55075265 ([CPUFREQ] Add S3C2416/S3C2450 cpufreq driver)

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

Reviewed-by Krzysztof Kozlowski <[email protected]>

Acked-by Viresh Kumar <[email protected]>

Signed-off-by Rafael J. Wysocki <[email protected]>

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

---
 drivers/cpufreq/s3c2416-cpufreq.c |    1 -
 1 file changed, 1 deletion(-)

drivers/cpufreq/s3c2416-cpufreq.c +0 -1

@@ -400,7 +400,6 @@ static int s3c2416_cpufreq_driver_init(s
 	rate = clk_get_rate(s3c_freq->hclk);
 	if (rate < 133 * 1000 * 1000) {
 		pr_err("cpufreq: HCLK not at 133MHz\n");
-		clk_put(s3c_freq->hclk);
 		ret = -EINVAL;
 		goto err_armclk;
 	}

Greg Kroah-Hartman

author maintainer

2017-07-03 13:40 UTC #102 lore raw

PATCH 98/101 KVM: x86: fix emulation of RSM and IRET instructions

4.4-stable review patch. If anyone has any objections, please let me know.

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

From: Ladi Prosek <[email protected]>

commit 6ed071f051e12cf7baa1b69d3becb8f232fdfb7b upstream.

On AMD, the effect of set_nmi_mask called by emulate_iret_real and em_rsm on hflags is reverted later on in x86_emulate_instruction where hflags are overwritten with ctxt->emul_flags (the kvm_set_hflags call). This manifests as a hang when rebooting Windows VMs with QEMU, OVMF, and >1 vcpu.

Instead of trying to merge ctxt->emul_flags into vcpu->arch.hflags after an instruction is emulated, this commit deletes emul_flags altogether and makes the emulator access vcpu->arch.hflags using two new accessors. This way all changes, on the emulator side as well as in functions called from the emulator and accessing vcpu state with emul_to_vcpu, are preserved.

More details on the bug and its manifestation with Windows and OVMF:

It's a KVM bug in the interaction between SMI/SMM and NMI, specific to AMD. I believe that the SMM part explains why we started seeing this only with OVMF.

KVM masks and unmasks NMI when entering and leaving SMM. When KVM emulates the RSM instruction in em_rsm, the set_nmi_mask call doesn't stick because later on in x86_emulate_instruction we overwrite arch.hflags with ctxt->emul_flags, effectively reverting the effect of the set_nmi_mask call. The AMD-specific hflag of interest here is HF_NMI_MASK.

When rebooting the system, Windows sends an NMI IPI to all but the current cpu to shut them down. Only after all of them are parked in HLT will the initiating cpu finish the restart. If NMI is masked, other cpus never get the memo and the initiating cpu spins forever, waiting for hal!HalpInterruptProcessorsStarted to drop. That's the symptom we observe.

Fixes a584539b24b8 ("KVM: x86: pass the whole hflags field to emulator and back")

Signed-off-by Ladi Prosek <[email protected]>

Signed-off-by Paolo Bonzini <[email protected]>

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

---
 arch/x86/include/asm/kvm_emulate.h |    4 +++-
 arch/x86/kvm/emulate.c             |   16 +++++++++-------
 arch/x86/kvm/x86.c                 |   15 ++++++++++++---
 3 files changed, 24 insertions(+), 11 deletions(-)

arch/x86/include/asm/kvm_emulate.h +3 -1

@@ -221,6 +221,9 @@ struct x86_emulate_ops {
 	void (*get_cpuid)(struct x86_emulate_ctxt *ctxt,
 			  u32 *eax, u32 *ebx, u32 *ecx, u32 *edx);
 	void (*set_nmi_mask)(struct x86_emulate_ctxt *ctxt, bool masked);
+
+	unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt);
+	void (*set_hflags)(struct x86_emulate_ctxt *ctxt, unsigned hflags);
 };
 
 typedef u32 __attribute__((vector_size(16))) sse128_t;

@@ -290,7 +293,6 @@ struct x86_emulate_ctxt {
 
 	/* interruptibility state, as a result of execution of STI or MOV SS */
 	int interruptibility;
-	int emul_flags;
 
 	bool perm_ok; /* do not check permissions if true */
 	bool ud;	/* inject an #UD if host doesn't support insn */

arch/x86/kvm/emulate.c +9 -7

@@ -2531,7 +2531,7 @@ static int em_rsm(struct x86_emulate_ctx
 	u64 smbase;
 	int ret;
 
-	if ((ctxt->emul_flags & X86EMUL_SMM_MASK) == 0)
+	if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_MASK) == 0)
 		return emulate_ud(ctxt);
 
 	/*

@@ -2580,11 +2580,11 @@ static int em_rsm(struct x86_emulate_ctx
 		return X86EMUL_UNHANDLEABLE;
 	}
 
-	if ((ctxt->emul_flags & X86EMUL_SMM_INSIDE_NMI_MASK) == 0)
+	if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_INSIDE_NMI_MASK) == 0)
 		ctxt->ops->set_nmi_mask(ctxt, false);
 
-	ctxt->emul_flags &= ~X86EMUL_SMM_INSIDE_NMI_MASK;
-	ctxt->emul_flags &= ~X86EMUL_SMM_MASK;
+	ctxt->ops->set_hflags(ctxt, ctxt->ops->get_hflags(ctxt) &
+		~(X86EMUL_SMM_INSIDE_NMI_MASK | X86EMUL_SMM_MASK));
 	return X86EMUL_CONTINUE;
 }

@@ -5296,6 +5296,7 @@ int x86_emulate_insn(struct x86_emulate_
 	const struct x86_emulate_ops *ops = ctxt->ops;
 	int rc = X86EMUL_CONTINUE;
 	int saved_dst_type = ctxt->dst.type;
+	unsigned emul_flags;
 
 	ctxt->mem_read.pos = 0;

@@ -5310,6 +5311,7 @@ int x86_emulate_insn(struct x86_emulate_
 		goto done;
 	}
 
+	emul_flags = ctxt->ops->get_hflags(ctxt);
 	if (unlikely(ctxt->d &
 		     (No64|Undefined|Sse|Mmx|Intercept|CheckPerm|Priv|Prot|String))) {
 		if ((ctxt->mode == X86EMUL_MODE_PROT64 && (ctxt->d & No64)) ||

@@ -5343,7 +5345,7 @@ int x86_emulate_insn(struct x86_emulate_
 				fetch_possible_mmx_operand(ctxt, &ctxt->dst);
 		}
 
-		if (unlikely(ctxt->emul_flags & X86EMUL_GUEST_MASK) && ctxt->intercept) {
+		if (unlikely(emul_flags & X86EMUL_GUEST_MASK) && ctxt->intercept) {
 			rc = emulator_check_intercept(ctxt, ctxt->intercept,
 						      X86_ICPT_PRE_EXCEPT);
 			if (rc != X86EMUL_CONTINUE)

@@ -5372,7 +5374,7 @@ int x86_emulate_insn(struct x86_emulate_
 				goto done;
 		}
 
-		if (unlikely(ctxt->emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) {
+		if (unlikely(emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) {
 			rc = emulator_check_intercept(ctxt, ctxt->intercept,
 						      X86_ICPT_POST_EXCEPT);
 			if (rc != X86EMUL_CONTINUE)

@@ -5426,7 +5428,7 @@ int x86_emulate_insn(struct x86_emulate_
 
 special_insn:
 
-	if (unlikely(ctxt->emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) {
+	if (unlikely(emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) {
 		rc = emulator_check_intercept(ctxt, ctxt->intercept,
 					      X86_ICPT_POST_MEMACCESS);
 		if (rc != X86EMUL_CONTINUE)

arch/x86/kvm/x86.c +12 -3

@@ -4999,6 +4999,16 @@ static void emulator_set_nmi_mask(struct
 	kvm_x86_ops->set_nmi_mask(emul_to_vcpu(ctxt), masked);
 }
 
+static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt)
+{
+	return emul_to_vcpu(ctxt)->arch.hflags;
+}
+
+static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_flags)
+{
+	kvm_set_hflags(emul_to_vcpu(ctxt), emul_flags);
+}
+
 static const struct x86_emulate_ops emulate_ops = {
 	.read_gpr            = emulator_read_gpr,
 	.write_gpr           = emulator_write_gpr,

@@ -5038,6 +5048,8 @@ static const struct x86_emulate_ops emul
 	.intercept           = emulator_intercept,
 	.get_cpuid           = emulator_get_cpuid,
 	.set_nmi_mask        = emulator_set_nmi_mask,
+	.get_hflags          = emulator_get_hflags,
+	.set_hflags          = emulator_set_hflags,
 };
 
 static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)

@@ -5090,7 +5102,6 @@ static void init_emulate_ctxt(struct kvm
 	BUILD_BUG_ON(HF_GUEST_MASK != X86EMUL_GUEST_MASK);
 	BUILD_BUG_ON(HF_SMM_MASK != X86EMUL_SMM_MASK);
 	BUILD_BUG_ON(HF_SMM_INSIDE_NMI_MASK != X86EMUL_SMM_INSIDE_NMI_MASK);
-	ctxt->emul_flags = vcpu->arch.hflags;
 
 	init_decode_cache(ctxt);
 	vcpu->arch.emulate_regs_need_sync_from_vcpu = false;

@@ -5486,8 +5497,6 @@ restart:
 		unsigned long rflags = kvm_x86_ops->get_rflags(vcpu);
 		toggle_interruptibility(vcpu, ctxt->interruptibility);
 		vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
-		if (vcpu->arch.hflags != ctxt->emul_flags)
-			kvm_set_hflags(vcpu, ctxt->emul_flags);
 		kvm_rip_write(vcpu, ctxt->eip);
 		if (r == EMULATE_DONE)
 			kvm_vcpu_check_singlestep(vcpu, rflags, &r);

Guenter Roeck

2017-07-03 19:37 UTC #103 lore raw