4.9.39-stable review

Cc Eduardo Valentin <[email protected]>

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

---
 drivers/net/xen-netfront.c |   14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

drivers/net/xen-netfront.c +11 -3

@@ -281,6 +281,7 @@ static void xennet_alloc_rx_buffers(stru
 {
 	RING_IDX req_prod = queue->rx.req_prod_pvt;
 	int notify;
+	int err = 0;
 
 	if (unlikely(!netif_carrier_ok(queue->info->netdev)))
 		return;

@@ -295,8 +296,10 @@ static void xennet_alloc_rx_buffers(stru
 		struct xen_netif_rx_request *req;
 
 		skb = xennet_alloc_one_rx_buffer(queue);
-		if (!skb)
+		if (!skb) {
+			err = -ENOMEM;
 			break;
+		}
 
 		id = xennet_rxidx(req_prod);

@@ -320,8 +323,13 @@ 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.sring->req_prod < NET_RX_SLOTS_MIN) {
+	/* Try again later if there are not enough requests or skb allocation
+	 * failed.
+	 * Enough requests is quantified as the sum of newly created slots and
+	 * the unconsumed slots at the backend.
+	 */
+	if (req_prod - queue->rx.rsp_cons < NET_RX_SLOTS_MIN ||
+	    unlikely(err)) {
 		mod_timer(&queue->rx_refill_timer, jiffies + (HZ/10));
 		return;
 	}

Greg Kroah-Hartman

author maintainer

2017-07-19 10:23 UTC #2 lore raw

PATCH 2/72 net_sched: fix error recovery at qdisc creation

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

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

From: Eric Dumazet <[email protected]>

commit 87b60cfacf9f17cf71933c6e33b66e68160af71d upstream.

Dmitry reported uses after free in qdisc code [1]

The problem here is that ops->init() can return an error.

qdisc_create_dflt() then call ops->destroy(),
while qdisc_create() does _not_ call it.

Four qdisc chose to call their own ops->destroy(), assuming their caller would not.

This patch makes sure qdisc_create() calls ops->destroy() and fixes the four qdisc to avoid double free.

[1]

BUG: KASAN: use-after-free in mq_destroy+0x242/0x290 net/sched/sch_mq.c:33 at addr ffff8801d415d440
Read of size 8 by task syz-executor2/5030
CPU: 0 PID: 5030 Comm: syz-executor2 Not tainted 4.3.5-smp-DEV #119
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
 0000000000000046 ffff8801b435b870 ffffffff81bbbed4 ffff8801db000400
 ffff8801d415d440 ffff8801d415dc40 ffff8801c4988510 ffff8801b435b898
 ffffffff816682b1 ffff8801b435b928 ffff8801d415d440 ffff8801c49880c0
Call Trace:
 [<ffffffff81bbbed4>] __dump_stack lib/dump_stack.c:15 [inline]
 [<ffffffff81bbbed4>] dump_stack+0x6c/0x98 lib/dump_stack.c:51
 [<ffffffff816682b1>] kasan_object_err+0x21/0x70 mm/kasan/report.c:158
 [<ffffffff81668524>] print_address_description mm/kasan/report.c:196 [inline]
 [<ffffffff81668524>] kasan_report_error+0x1b4/0x4b0 mm/kasan/report.c:285
 [<ffffffff81668953>] kasan_report mm/kasan/report.c:305 [inline]
 [<ffffffff81668953>] __asan_report_load8_noabort+0x43/0x50 mm/kasan/report.c:326
 [<ffffffff82527b02>] mq_destroy+0x242/0x290 net/sched/sch_mq.c:33
 [<ffffffff82524bdd>] qdisc_destroy+0x12d/0x290 net/sched/sch_generic.c:953
 [<ffffffff82524e30>] qdisc_create_dflt+0xf0/0x120 net/sched/sch_generic.c:848
 [<ffffffff8252550d>] attach_default_qdiscs net/sched/sch_generic.c:1029 [inline]
 [<ffffffff8252550d>] dev_activate+0x6ad/0x880 net/sched/sch_generic.c:1064
 [<ffffffff824b1db1>] __dev_open+0x221/0x320 net/core/dev.c:1403
 [<ffffffff824b24ce>] __dev_change_flags+0x15e/0x3e0 net/core/dev.c:6858
 [<ffffffff824b27de>] dev_change_flags+0x8e/0x140 net/core/dev.c:6926
 [<ffffffff824f5bf6>] dev_ifsioc+0x446/0x890 net/core/dev_ioctl.c:260
 [<ffffffff824f61fa>] dev_ioctl+0x1ba/0xb80 net/core/dev_ioctl.c:546
 [<ffffffff82430509>] sock_do_ioctl+0x99/0xb0 net/socket.c:879
 [<ffffffff82430d30>] sock_ioctl+0x2a0/0x390 net/socket.c:958
 [<ffffffff816f3b68>] vfs_ioctl fs/ioctl.c:44 [inline]
 [<ffffffff816f3b68>] do_vfs_ioctl+0x8a8/0xe50 fs/ioctl.c:611
 [<ffffffff816f41a4>] SYSC_ioctl fs/ioctl.c:626 [inline]
 [<ffffffff816f41a4>] SyS_ioctl+0x94/0xc0 fs/ioctl.c:617
 [<ffffffff8123e357>] entry_SYSCALL_64_fastpath+0x12/0x17

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

Reported-by Dmitry Vyukov <[email protected]>

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

---
 net/sched/sch_api.c    |    2 ++
 net/sched/sch_hhf.c    |    8 ++++++--
 net/sched/sch_mq.c     |   10 +++-------
 net/sched/sch_mqprio.c |   19 ++++++-------------
 net/sched/sch_sfq.c    |    3 ++-
 5 files changed, 19 insertions(+), 23 deletions(-)

net/sched/sch_api.c +2 -0

@@ -1008,6 +1008,8 @@ static struct Qdisc *qdisc_create(struct
 
 		return sch;
 	}
+	/* ops->init() failed, we call ->destroy() like qdisc_create_dflt() */
+	ops->destroy(sch);
 err_out3:
 	dev_put(dev);
 	kfree((char *) sch - sch->padded);

net/sched/sch_hhf.c +6 -2

@@ -627,7 +627,9 @@ static int hhf_init(struct Qdisc *sch, s
 			q->hhf_arrays[i] = hhf_zalloc(HHF_ARRAYS_LEN *
 						      sizeof(u32));
 			if (!q->hhf_arrays[i]) {
-				hhf_destroy(sch);
+				/* Note: hhf_destroy() will be called
+				 * by our caller.
+				 */
 				return -ENOMEM;
 			}
 		}

@@ -638,7 +640,9 @@ static int hhf_init(struct Qdisc *sch, s
 			q->hhf_valid_bits[i] = hhf_zalloc(HHF_ARRAYS_LEN /
 							  BITS_PER_BYTE);
 			if (!q->hhf_valid_bits[i]) {
-				hhf_destroy(sch);
+				/* Note: hhf_destroy() will be called
+				 * by our caller.
+				 */
 				return -ENOMEM;
 			}
 		}

net/sched/sch_mq.c +3 -7

@@ -52,7 +52,7 @@ static int mq_init(struct Qdisc *sch, st
 	/* pre-allocate qdiscs, attachment can't fail */
 	priv->qdiscs = kcalloc(dev->num_tx_queues, sizeof(priv->qdiscs[0]),
 			       GFP_KERNEL);
-	if (priv->qdiscs == NULL)
+	if (!priv->qdiscs)
 		return -ENOMEM;
 
 	for (ntx = 0; ntx < dev->num_tx_queues; ntx++) {

@@ -60,18 +60,14 @@ static int mq_init(struct Qdisc *sch, st
 		qdisc = qdisc_create_dflt(dev_queue, get_default_qdisc_ops(dev, ntx),
 					  TC_H_MAKE(TC_H_MAJ(sch->handle),
 						    TC_H_MIN(ntx + 1)));
-		if (qdisc == NULL)
-			goto err;
+		if (!qdisc)
+			return -ENOMEM;
 		priv->qdiscs[ntx] = qdisc;
 		qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
 	}
 
 	sch->flags |= TCQ_F_MQROOT;
 	return 0;
-
-err:
-	mq_destroy(sch);
-	return -ENOMEM;
 }
 
 static void mq_attach(struct Qdisc *sch)

net/sched/sch_mqprio.c +6 ~~-13~~

@@ -118,10 +118,8 @@ static int mqprio_init(struct Qdisc *sch
 	/* pre-allocate qdisc, attachment can't fail */
 	priv->qdiscs = kcalloc(dev->num_tx_queues, sizeof(priv->qdiscs[0]),
 			       GFP_KERNEL);
-	if (priv->qdiscs == NULL) {
-		err = -ENOMEM;
-		goto err;
-	}
+	if (!priv->qdiscs)
+		return -ENOMEM;
 
 	for (i = 0; i < dev->num_tx_queues; i++) {
 		dev_queue = netdev_get_tx_queue(dev, i);

@@ -129,10 +127,9 @@ static int mqprio_init(struct Qdisc *sch
 					  get_default_qdisc_ops(dev, i),
 					  TC_H_MAKE(TC_H_MAJ(sch->handle),
 						    TC_H_MIN(i + 1)));
-		if (qdisc == NULL) {
-			err = -ENOMEM;
-			goto err;
-		}
+		if (!qdisc)
+			return -ENOMEM;
+
 		priv->qdiscs[i] = qdisc;
 		qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
 	}

@@ -148,7 +145,7 @@ static int mqprio_init(struct Qdisc *sch
 		priv->hw_owned = 1;
 		err = dev->netdev_ops->ndo_setup_tc(dev, sch->handle, 0, &tc);
 		if (err)
-			goto err;
+			return err;
 	} else {
 		netdev_set_num_tc(dev, qopt->num_tc);
 		for (i = 0; i < qopt->num_tc; i++)

@@ -162,10 +159,6 @@ static int mqprio_init(struct Qdisc *sch
 
 	sch->flags |= TCQ_F_MQROOT;
 	return 0;
-
-err:
-	mqprio_destroy(sch);
-	return err;
 }
 
 static void mqprio_attach(struct Qdisc *sch)

net/sched/sch_sfq.c +2 -1

@@ -742,9 +742,10 @@ static int sfq_init(struct Qdisc *sch, s
 	q->ht = sfq_alloc(sizeof(q->ht[0]) * q->divisor);
 	q->slots = sfq_alloc(sizeof(q->slots[0]) * q->maxflows);
 	if (!q->ht || !q->slots) {
-		sfq_destroy(sch);
+		/* Note: sfq_destroy() will be called by our caller */
 		return -ENOMEM;
 	}
+
 	for (i = 0; i < q->divisor; i++)
 		q->ht[i] = SFQ_EMPTY_SLOT;

Greg Kroah-Hartman

author maintainer

2017-07-19 10:23 UTC #3 lore raw

PATCH 3/72 net: sched: Fix one possible panic when no destroy callback

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

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

From: Gao Feng <[email protected]>

commit c1a4872ebfb83b1af7144f7b29ac8c4b344a12a8 upstream.

When qdisc fail to init, qdisc_create would invoke the destroy callback to cleanup. But there is no check if the callback exists really. So it would cause the panic if there is no real destroy callback like the qdisc codel, fq, and so on.

Take codel as an example following:
When a malicious user constructs one invalid netlink msg, it would cause codel_init->codel_change->nla_parse_nested failed.
Then kernel would invoke the destroy callback directly but qdisc codel doesn't define one. It causes one panic as a result.

Now add one the check for destroy to avoid the possible panic.

Fixes 87b60cfacf9f ("net_sched: fix error recovery at qdisc creation")

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

Acked-by Eric Dumazet <[email protected]>

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

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

net/sched/sch_api.c +2 -1

@@ -1009,7 +1009,8 @@ static struct Qdisc *qdisc_create(struct
 		return sch;
 	}
 	/* ops->init() failed, we call ->destroy() like qdisc_create_dflt() */
-	ops->destroy(sch);
+	if (ops->destroy)
+		ops->destroy(sch);
 err_out3:
 	dev_put(dev);
 	kfree((char *) sch - sch->padded);

Greg Kroah-Hartman

author maintainer

2017-07-19 10:25 UTC #4 lore raw

PATCH 4/72 net/phy: micrel: configure intterupts after autoneg workaround

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

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

From: Zach Brown <[email protected]>

commit b866203d872d5deeafcecd25ea429d6748b5bd56 upstream.

The commit ("net/phy: micrel: Add workaround for bad autoneg") fixes an autoneg failure case by resetting the hardware. This turns off intterupts. Things will work themselves out if the phy polls, as it will figure out it's state during a poll. However if the phy uses only intterupts, the phy will stall, since interrupts are off. This patch fixes the issue by calling config_intr after resetting the phy.

Fixes d2fd719bcb0e ("net/phy: micrel: Add workaround for bad autoneg ")

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

Reviewed-by Andrew Lunn <[email protected]>

Reviewed-by Florian Fainelli <[email protected]>

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

---
 drivers/net/phy/micrel.c |    2 ++
 1 file changed, 2 insertions(+)

drivers/net/phy/micrel.c +2 -0

@@ -622,6 +622,8 @@ static int ksz9031_read_status(struct ph
 	if ((regval & 0xFF) == 0xFF) {
 		phy_init_hw(phydev);
 		phydev->link = 0;
+		if (phydev->drv->config_intr && phy_interrupt_is_valid(phydev))
+			phydev->drv->config_intr(phydev);
 	}
 
 	return 0;

Greg Kroah-Hartman

author maintainer

2017-07-19 10:25 UTC #5 lore raw

PATCH 5/72 ipv6: avoid unregistering inet6_dev for loopback

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

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

From: WANG Cong <[email protected]>

commit 60abc0be96e00ca71bac083215ac91ad2e575096 upstream.

The per netns loopback_dev->ip6_ptr is unregistered and set to NULL when its mtu is set to smaller than IPV6_MIN_MTU, this leads to that we could set rt->rt6i_idev NULL after a rt6_uncached_list_flush_dev() and then crash after another call.

In this case we should just bring its inet6_dev down, rather than unregistering it, at least prior to commit 176c39af29bc ("netns: fix addrconf_ifdown kernel panic") we always override the case for loopback.

Thanks a lot to Andrey for finding a reliable reproducer.

Fixes 176c39af29bc ("netns: fix addrconf_ifdown kernel panic")

Reported-by Andrey Konovalov <[email protected]>

Cc Andrey Konovalov <[email protected]>

Cc Daniel Lezcano <[email protected]>

Cc David Ahern <[email protected]>

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

Acked-by David Ahern <[email protected]>

Tested-by Andrey Konovalov <[email protected]>

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

---
 net/ipv6/addrconf.c |    5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

net/ipv6/addrconf.c +3 -2

@@ -3316,6 +3316,7 @@ static int addrconf_notify(struct notifi
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct netdev_notifier_changeupper_info *info;
 	struct inet6_dev *idev = __in6_dev_get(dev);
+	struct net *net = dev_net(dev);
 	int run_pending = 0;
 	int err;

@@ -3331,7 +3332,7 @@ static int addrconf_notify(struct notifi
 	case NETDEV_CHANGEMTU:
 		/* if MTU under IPV6_MIN_MTU stop IPv6 on this interface. */
 		if (dev->mtu < IPV6_MIN_MTU) {
-			addrconf_ifdown(dev, 1);
+			addrconf_ifdown(dev, dev != net->loopback_dev);
 			break;
 		}

@@ -3447,7 +3448,7 @@ static int addrconf_notify(struct notifi
 			 * IPV6_MIN_MTU stop IPv6 on this interface.
 			 */
 			if (dev->mtu < IPV6_MIN_MTU)
-				addrconf_ifdown(dev, 1);
+				addrconf_ifdown(dev, dev != net->loopback_dev);
 		}
 		break;

Greg Kroah-Hartman

author maintainer

2017-07-19 10:25 UTC #6 lore raw

PATCH 6/72 net: dp83640: Avoid NULL pointer dereference.

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

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

From: Richard Cochran <[email protected]>

commit db9d8b29d19d2801793e4419f4c6272bf8951c62 upstream.

The function, skb_complete_tx_timestamp(), used to allow passing in a NULL pointer for the time stamps, but that was changed in commit 62bccb8cdb69051b95a55ab0c489e3cab261c8ef ("net-timestamp: Make the clone operation stand-alone from phy timestamping"), and the existing call sites, all of which are in the dp83640 driver, were fixed up.

Even though the kernel-doc was subsequently updated in commit 7a76a021cd5a292be875fbc616daf03eab1e6996 ("net-timestamp: Update skb_complete_tx_timestamp comment"), still a bug fix from Manfred Rudigier came into the driver using the old semantics. Probably Manfred derived that patch from an older kernel version.

This fix should be applied to the stable trees as well.

Fixes 81e8f2e930fe ("net: dp83640: Fix tx timestamp overflow handling.")

Signed-off-by Richard Cochran <[email protected]>

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

---
 drivers/net/phy/dp83640.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

drivers/net/phy/dp83640.c +1 -1

@@ -908,7 +908,7 @@ static void decode_txts(struct dp83640_p
 	if (overflow) {
 		pr_debug("tx timestamp queue overflow, count %d\n", overflow);
 		while (skb) {
-			skb_complete_tx_timestamp(skb, NULL);
+			kfree_skb(skb);
 			skb = skb_dequeue(&dp83640->tx_queue);
 		}
 		return;

Greg Kroah-Hartman

author maintainer

2017-07-19 10:24 UTC #7 lore raw

PATCH 7/72 tcp: reset sk_rx_dst in tcp_disconnect()

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

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

From: WANG Cong <[email protected]>

commit d747a7a51b00984127a88113cdbbc26f91e9d815 upstream.

We have to reset the sk->sk_rx_dst when we disconnect a TCP connection, because otherwise when we re-connect it this dst reference is simply overridden in tcp_finish_connect().

This fixes a dst leak which leads to a loopback dev refcnt leak. It is a long-standing bug, Kevin reported a very similar (if not same) bug before. Thanks to Andrei for providing such a reliable reproducer which greatly narrows down the problem.

Fixes 41063e9dd119 ("ipv4: Early TCP socket demux.")

Reported-by Andrei Vagin <[email protected]>

Reported-by Kevin Xu <[email protected]>

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

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

---
 net/ipv4/tcp.c |    2 ++
 1 file changed, 2 insertions(+)

net/ipv4/tcp.c +2 -0

@@ -2300,6 +2300,8 @@ int tcp_disconnect(struct sock *sk, int
 	tcp_init_send_head(sk);
 	memset(&tp->rx_opt, 0, sizeof(tp->rx_opt));
 	__sk_dst_reset(sk);
+	dst_release(sk->sk_rx_dst);
+	sk->sk_rx_dst = NULL;
 	tcp_saved_syn_free(tp);
 
 	WARN_ON(inet->inet_num && !icsk->icsk_bind_hash);

Greg Kroah-Hartman

author maintainer

2017-07-19 10:24 UTC #8 lore raw

PATCH 8/72 net: prevent sign extension in dev_get_stats()

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

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

From: Eric Dumazet <[email protected]>

commit 6f64ec74515925cced6df4571638b5a099a49aae upstream.

Similar to the fix provided by Dominik Heidler in commit 9b3dc0a17d73 ("l2tp: cast l2tp traffic counter to unsigned") we need to take care of 32bit kernels in dev_get_stats().

When using atomic_long_read(), we add a 'long' to u64 and might misinterpret high order bit, unless we cast to unsigned.

Fixes caf586e5f23ce ("net: add a core netdev->rx_dropped counter")

Fixes 015f0688f57ca ("net: net: add a core netdev->tx_dropped counter")

Fixes 6e7333d315a76 ("net: add rx_nohandler stat counter")

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

Cc Jarod Wilson <[email protected]>

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

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

net/core/dev.c +3 -3

@@ -7563,9 +7563,9 @@ struct rtnl_link_stats64 *dev_get_stats(
 	} else {
 		netdev_stats_to_stats64(storage, &dev->stats);
 	}
-	storage->rx_dropped += atomic_long_read(&dev->rx_dropped);
-	storage->tx_dropped += atomic_long_read(&dev->tx_dropped);
-	storage->rx_nohandler += atomic_long_read(&dev->rx_nohandler);
+	storage->rx_dropped += (unsigned long)atomic_long_read(&dev->rx_dropped);
+	storage->tx_dropped += (unsigned long)atomic_long_read(&dev->tx_dropped);
+	storage->rx_nohandler += (unsigned long)atomic_long_read(&dev->rx_nohandler);
 	return storage;
 }
 EXPORT_SYMBOL(dev_get_stats);

Greg Kroah-Hartman

author maintainer

2017-07-19 10:25 UTC #9 lore raw

PATCH 9/72 bridge: mdb: fix leak on complete_info ptr on fail path

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

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

From: Eduardo Valentin <[email protected]>

commit 1bfb159673957644951ab0a8d2aec44b93ddb1ae upstream.

We currently get the following kmemleak report:
unreferenced object 0xffff8800039d9820 (size 32):
comm "softirq", pid 0, jiffies 4295212383 (age 792.416s) hex dump (first 32 bytes):

    00 0c e0 03 00 88 ff ff ff 02 00 00 00 00 00 00  ................
    00 00 00 01 ff 11 00 02 86 dd 00 00 ff ff ff ff  ................
  backtrace:
    [<ffffffff8152b4aa>] kmemleak_alloc+0x4a/0xa0
    [<ffffffff811d8ec8>] kmem_cache_alloc_trace+0xb8/0x1c0
    [<ffffffffa0389683>] __br_mdb_notify+0x2a3/0x300 [bridge]
    [<ffffffffa038a0ce>] br_mdb_notify+0x6e/0x70 [bridge]
    [<ffffffffa0386479>] br_multicast_add_group+0x109/0x150 [bridge]
    [<ffffffffa0386518>] br_ip6_multicast_add_group+0x58/0x60 [bridge]
    [<ffffffffa0387fb5>] br_multicast_rcv+0x1d5/0xdb0 [bridge]
    [<ffffffffa037d7cf>] br_handle_frame_finish+0xcf/0x510 [bridge]
    [<ffffffffa03a236b>] br_nf_hook_thresh.part.27+0xb/0x10 [br_netfilter]
    [<ffffffffa03a3738>] br_nf_hook_thresh+0x48/0xb0 [br_netfilter]
    [<ffffffffa03a3fb9>] br_nf_pre_routing_finish_ipv6+0x109/0x1d0 [br_netfilter]
    [<ffffffffa03a4400>] br_nf_pre_routing_ipv6+0xd0/0x14c [br_netfilter]
    [<ffffffffa03a3c27>] br_nf_pre_routing+0x197/0x3d0 [br_netfilter]
    [<ffffffff814a2952>] nf_iterate+0x52/0x60
    [<ffffffff814a29bc>] nf_hook_slow+0x5c/0xb0
    [<ffffffffa037ddf4>] br_handle_frame+0x1a4/0x2c0 [bridge]

This happens when switchdev_port_obj_add() fails. This patch frees complete_info object in the fail path.

Reviewed-by Vallish Vaidyeshwara <[email protected]>

Signed-off-by Eduardo Valentin <[email protected]>

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

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

net/bridge/br_mdb.c +2 -1

@@ -323,7 +323,8 @@ static void __br_mdb_notify(struct net_d
 			__mdb_entry_to_br_ip(entry, &complete_info->ip);
 			mdb.obj.complete_priv = complete_info;
 			mdb.obj.complete = br_mdb_complete;
-			switchdev_port_obj_add(port_dev, &mdb.obj);
+			if (switchdev_port_obj_add(port_dev, &mdb.obj))
+				kfree(complete_info);
 		}
 	} else if (port_dev && type == RTM_DELMDB) {
 		switchdev_port_obj_del(port_dev, &mdb.obj);

Greg Kroah-Hartman

author maintainer

2017-07-19 10:24 UTC #10 lore raw

PATCH 10/72 rocker: move dereference before free

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

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

From: Dan Carpenter <[email protected]>

commit acb4b7df48b539cb391287921de57e4e5fae3460 upstream.

My static checker complains that ofdpa_neigh_del() can sometimes free
"found". It just makes sense to use it first before deleting it.

Fixes ecf244f753e0 ("rocker: fix maybe-uninitialized warning")

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

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

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

drivers/net/ethernet/rocker/rocker_ofdpa.c +1 -1

@@ -1505,8 +1505,8 @@ static int ofdpa_port_ipv4_nh(struct ofd
 		*index = entry->index;
 		resolved = false;
 	} else if (removing) {
-		ofdpa_neigh_del(trans, found);
 		*index = found->index;
+		ofdpa_neigh_del(trans, found);
 	} else if (updating) {
 		ofdpa_neigh_update(found, trans, NULL, false);
 		resolved = !is_zero_ether_addr(found->eth_dst);

Greg Kroah-Hartman

author maintainer

2017-07-19 10:26 UTC #11 lore raw

PATCH 11/72 bpf: prevent leaking pointer via xadd on unpriviledged

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

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

From: Daniel Borkmann <[email protected]>

commit 6bdf6abc56b53103324dfd270a86580306e1a232 upstream.

Leaking kernel addresses on unpriviledged is generally disallowed, for example, verifier rejects the following:

0: (b7) r0 = 0
1: (18) r2 = 0xffff897e82304400
3: (7b) *(u64 *)(r1 +48) = r2
R2 leaks addr into ctx

Doing pointer arithmetic on them is also forbidden, so that they don't turn into unknown value and then get leaked out. However, there's xadd as a special case, where we don't check the src reg for being a pointer register, e.g. the following will pass:

0: (b7) r0 = 0
1: (7b) *(u64 *)(r1 +48) = r0
2: (18) r2 = 0xffff897e82304400 ; map
4: (db) lock *(u64 *)(r1 +48) += r2
5: (95) exit

We could store the pointer into skb->cb, loose the type context, and then read it out from there again to leak it eventually out of a map value. Or more easily in a different variant, too:

0: (bf) r6 = r1
1: (7a) *(u64 *)(r10 -8) = 0
2: (bf) r2 = r10
3: (07) r2 += -8
4: (18) r1 = 0x0
6: (85) call bpf_map_lookup_elem#1
7: (15) if r0 == 0x0 goto pc+3 R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R6=ctx R10=fp 8: (b7) r3 = 0
9: (7b) *(u64 *)(r0 +0) = r3
10: (db) lock *(u64 *)(r0 +0) += r6
11: (b7) r0 = 0
12: (95) exit

from 7 to 11: R0=inv,min_value=0,max_value=0 R6=ctx R10=fp 11: (b7) r0 = 0
12: (95) exit

Prevent this by checking xadd src reg for pointer types. Also add a couple of test cases related to this.

Fixes 1be7f75d1668 ("bpf: enable non-root eBPF programs")

Fixes 17a5267067f3 ("bpf: verifier (add verifier core)")

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

Acked-by Alexei Starovoitov <[email protected]>

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

Acked-by Edward Cree <[email protected]>

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

---
 kernel/bpf/verifier.c |    5 +++++
 1 file changed, 5 insertions(+)

kernel/bpf/verifier.c +5 -0

@@ -885,6 +885,11 @@ static int check_xadd(struct bpf_verifie
 	if (err)
 		return err;
 
+	if (is_pointer_value(env, insn->src_reg)) {
+		verbose("R%d leaks addr into mem\n", insn->src_reg);
+		return -EACCES;
+	}
+
 	/* check whether atomic_add can read the memory */
 	err = check_mem_access(env, insn->dst_reg, insn->off,
 			       BPF_SIZE(insn->code), BPF_READ, -1);

Greg Kroah-Hartman

author maintainer

2017-07-19 10:25 UTC #12 lore raw

PATCH 13/72 net/mlx5: Cancel delayed recovery work when unloading the driver

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

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

From: Mohamad Haj Yahia <[email protected]>

commit 2a0165a034ac024b60cca49c61e46f4afa2e4d98 upstream.

Draining the health workqueue will ignore future health works including the one that report hardware failure and thus we can't enter error state Instead cancel the recovery flow and make sure only recovery flow won't be scheduled.

Fixes 5e44fca50470 ('net/mlx5: Only cancel recovery work when cleaning up device')

Signed-off-by Mohamad Haj Yahia <[email protected]>

Signed-off-by Moshe Shemesh <[email protected]>

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

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

---
 drivers/net/ethernet/mellanox/mlx5/core/health.c |   15 ++++++++++++++-
 drivers/net/ethernet/mellanox/mlx5/core/main.c   |    2 +-
 include/linux/mlx5/driver.h                      |    1 +
 3 files changed, 16 insertions(+), 2 deletions(-)

drivers/net/ethernet/mellanox/mlx5/core/health.c +14 -1

@@ -67,6 +67,7 @@ enum {
 
 enum {
 	MLX5_DROP_NEW_HEALTH_WORK,
+	MLX5_DROP_NEW_RECOVERY_WORK,
 };
 
 static u8 get_nic_state(struct mlx5_core_dev *dev)

@@ -193,7 +194,7 @@ static void health_care(struct work_stru
 	mlx5_handle_bad_state(dev);
 
 	spin_lock(&health->wq_lock);
-	if (!test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags))
+	if (!test_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags))
 		schedule_delayed_work(&health->recover_work, recover_delay);
 	else
 		dev_err(&dev->pdev->dev,

@@ -328,6 +329,7 @@ void mlx5_start_health_poll(struct mlx5_
 	init_timer(&health->timer);
 	health->sick = 0;
 	clear_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags);
+	clear_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags);
 	health->health = &dev->iseg->health;
 	health->health_counter = &dev->iseg->health_counter;

@@ -350,11 +352,22 @@ void mlx5_drain_health_wq(struct mlx5_co
 
 	spin_lock(&health->wq_lock);
 	set_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags);
+	set_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags);
 	spin_unlock(&health->wq_lock);
 	cancel_delayed_work_sync(&health->recover_work);
 	cancel_work_sync(&health->work);
 }
 
+void mlx5_drain_health_recovery(struct mlx5_core_dev *dev)
+{
+	struct mlx5_core_health *health = &dev->priv.health;
+
+	spin_lock(&health->wq_lock);
+	set_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags);
+	spin_unlock(&health->wq_lock);
+	cancel_delayed_work_sync(&dev->priv.health.recover_work);
+}
+
 void mlx5_health_cleanup(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_health *health = &dev->priv.health;

drivers/net/ethernet/mellanox/mlx5/core/main.c +1 -1

@@ -1169,7 +1169,7 @@ static int mlx5_unload_one(struct mlx5_c
 	int err = 0;
 
 	if (cleanup)
-		mlx5_drain_health_wq(dev);
+		mlx5_drain_health_recovery(dev);
 
 	mutex_lock(&dev->intf_state_mutex);
 	if (test_bit(MLX5_INTERFACE_STATE_DOWN, &dev->intf_state)) {

include/linux/mlx5/driver.h +1 -0

@@ -788,6 +788,7 @@ int mlx5_health_init(struct mlx5_core_de
 void mlx5_start_health_poll(struct mlx5_core_dev *dev);
 void mlx5_stop_health_poll(struct mlx5_core_dev *dev);
 void mlx5_drain_health_wq(struct mlx5_core_dev *dev);
+void mlx5_drain_health_recovery(struct mlx5_core_dev *dev);
 int mlx5_buf_alloc_node(struct mlx5_core_dev *dev, int size,
 			struct mlx5_buf *buf, int node);
 int mlx5_buf_alloc(struct mlx5_core_dev *dev, int size, struct mlx5_buf *buf);

Greg Kroah-Hartman

author maintainer

2017-07-19 10:24 UTC #13 lore raw

PATCH 14/72 liquidio: fix bug in soft reset failure detection

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

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

From: Derek Chickles <[email protected]>

commit 05a6b4cae8c0cc1680c9dd33a97a49a13c0f01bc upstream.

The code that detects a failed soft reset of Octeon is comparing the wrong value against the reset value of the Octeon SLI_SCRATCH_1 register, resulting in an inability to detect a soft reset failure. Fix it by using the correct value in the comparison, which is any non-zero value.

Fixes f21fb3ed364b ("Add support of Cavium Liquidio ethernet adapters")

Fixes c0eab5b3580a ("liquidio: CN23XX firmware download")

Signed-off-by Derek Chickles <[email protected]>

Signed-off-by Satanand Burla <[email protected]>

Signed-off-by Raghu Vatsavayi <[email protected]>

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

Reviewed-by Leon Romanovsky <[email protected]>

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

---
 drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c |    2 +-
 drivers/net/ethernet/cavium/liquidio/cn66xx_device.c    |    2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c +1 -1

@@ -230,7 +230,7 @@ static int cn23xx_pf_soft_reset(struct o
 	/* Wait for 100ms as Octeon resets. */
 	mdelay(100);
 
-	if (octeon_read_csr64(oct, CN23XX_SLI_SCRATCH1) == 0x1234ULL) {
+	if (octeon_read_csr64(oct, CN23XX_SLI_SCRATCH1)) {
 		dev_err(&oct->pci_dev->dev, "OCTEON[%d]: Soft reset failed\n",
 			oct->octeon_id);
 		return 1;

drivers/net/ethernet/cavium/liquidio/cn66xx_device.c +1 -1

@@ -48,7 +48,7 @@ int lio_cn6xxx_soft_reset(struct octeon_
 	/* Wait for 10ms as Octeon resets. */
 	mdelay(100);
 
-	if (octeon_read_csr64(oct, CN6XXX_SLI_SCRATCH1) == 0x1234ULL) {
+	if (octeon_read_csr64(oct, CN6XXX_SLI_SCRATCH1)) {
 		dev_err(&oct->pci_dev->dev, "Soft reset failed\n");
 		return 1;
 	}

Greg Kroah-Hartman

author maintainer

2017-07-19 10:25 UTC #14 lore raw

PATCH 15/72 net/mlx5e: Fix TX carrier errors report in get stats ndo

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

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

From: Gal Pressman <[email protected]>

commit 8ff93de7668bd81bc8efa819d1184ebd48fae72d upstream.

Symbol error during carrier counter from PPCNT was mistakenly reported as TX carrier errors in get_stats ndo, although it's an RX counter.

Fixes 269e6b3af3bf ("net/mlx5e: Report additional error statistics in get stats ndo")

Signed-off-by Gal Pressman <[email protected]>

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

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

---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c |    2 --
 1 file changed, 2 deletions(-)

drivers/net/ethernet/mellanox/mlx5/core/en_main.c +0 -2

@@ -2671,8 +2671,6 @@ mlx5e_get_stats(struct net_device *dev,
 		PPORT_802_3_GET(pstats, a_frame_check_sequence_errors);
 	stats->rx_frame_errors = PPORT_802_3_GET(pstats, a_alignment_errors);
 	stats->tx_aborted_errors = PPORT_2863_GET(pstats, if_out_discards);
-	stats->tx_carrier_errors =
-		PPORT_802_3_GET(pstats, a_symbol_error_during_carrier);
 	stats->rx_errors = stats->rx_length_errors + stats->rx_crc_errors +
 			   stats->rx_frame_errors;
 	stats->tx_errors = stats->tx_aborted_errors + stats->tx_carrier_errors;

Greg Kroah-Hartman

author maintainer

2017-07-19 10:25 UTC #15 lore raw

PATCH 16/72 ipv6: dad: dont remove dynamic addresses if link is down

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

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

From: Sabrina Dubroca <[email protected]>

commit ec8add2a4c9df723c94a863b8fcd6d93c472deed upstream.

Currently, when the link for $DEV is down, this command succeeds but the address is removed immediately by DAD (1):

    ip addr add 1111::12/64 dev $DEV valid_lft 3600 preferred_lft 1800

In the same situation, this will succeed and not remove the address (2):

    ip addr add 1111::12/64 dev $DEV
    ip addr change 1111::12/64 dev $DEV valid_lft 3600 preferred_lft 1800

The comment in addrconf_dad_begin() when !IF_READY makes it look like this is the intended behavior, but doesn't explain why:

* If the device is not ready:
* - keep it tentative if it is a permanent address.
* - otherwise, kill it.

We clearly cannot prevent userspace from doing (2), but we can make (1) work consistently with (2).

addrconf_dad_stop() is only called in two cases: if DAD failed, or to skip DAD when the link is down. In that second case, the fix is to avoid deleting the address, like we already do for permanent addresses.

Fixes 3c21edbd1137 ("[IPV6]: Defer IPv6 device initialization until the link becomes ready.")

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

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

---
 net/ipv6/addrconf.c |   18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

net/ipv6/addrconf.c +9 -9

@@ -1875,15 +1875,7 @@ static void addrconf_dad_stop(struct ine
 	if (dad_failed)
 		ifp->flags |= IFA_F_DADFAILED;
 
-	if (ifp->flags&IFA_F_PERMANENT) {
-		spin_lock_bh(&ifp->lock);
-		addrconf_del_dad_work(ifp);
-		ifp->flags |= IFA_F_TENTATIVE;
-		spin_unlock_bh(&ifp->lock);
-		if (dad_failed)
-			ipv6_ifa_notify(0, ifp);
-		in6_ifa_put(ifp);
-	} else if (ifp->flags&IFA_F_TEMPORARY) {
+	if (ifp->flags&IFA_F_TEMPORARY) {
 		struct inet6_ifaddr *ifpub;
 		spin_lock_bh(&ifp->lock);
 		ifpub = ifp->ifpub;

@@ -1896,6 +1888,14 @@ static void addrconf_dad_stop(struct ine
 			spin_unlock_bh(&ifp->lock);
 		}
 		ipv6_del_addr(ifp);
+	} else if (ifp->flags&IFA_F_PERMANENT || !dad_failed) {
+		spin_lock_bh(&ifp->lock);
+		addrconf_del_dad_work(ifp);
+		ifp->flags |= IFA_F_TENTATIVE;
+		spin_unlock_bh(&ifp->lock);
+		if (dad_failed)
+			ipv6_ifa_notify(0, ifp);
+		in6_ifa_put(ifp);
 	} else {
 		ipv6_del_addr(ifp);
 	}

Greg Kroah-Hartman

author maintainer

2017-07-19 10:24 UTC #16 lore raw

PATCH 17/72 vxlan: fix hlist corruption

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

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

From: Jiri Benc <[email protected]>

[ Upstream commit 69e766612c4bcb79e19cebed9eed61d4222c1d47 ]

It's not a good idea to add the same hlist_node to two different hash lists. This leads to various hard to debug memory corruptions.

Fixes b1be00a6c39f ("vxlan: support both IPv4 and IPv6 sockets in a single vxlan device")

Signed-off-by Jiri Benc <[email protected]>

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

---
 drivers/net/vxlan.c |   30 ++++++++++++++++++++----------
 include/net/vxlan.h |   10 +++++++++-
 2 files changed, 29 insertions(+), 11 deletions(-)

drivers/net/vxlan.c +20 ~~-10~~

@@ -227,15 +227,15 @@ static struct vxlan_sock *vxlan_find_soc
 
 static struct vxlan_dev *vxlan_vs_find_vni(struct vxlan_sock *vs, __be32 vni)
 {
-	struct vxlan_dev *vxlan;
+	struct vxlan_dev_node *node;
 
 	/* For flow based devices, map all packets to VNI 0 */
 	if (vs->flags & VXLAN_F_COLLECT_METADATA)
 		vni = 0;
 
-	hlist_for_each_entry_rcu(vxlan, vni_head(vs, vni), hlist) {
-		if (vxlan->default_dst.remote_vni == vni)
-			return vxlan;
+	hlist_for_each_entry_rcu(node, vni_head(vs, vni), hlist) {
+		if (node->vxlan->default_dst.remote_vni == vni)
+			return node->vxlan;
 	}
 
 	return NULL;

@@ -2309,17 +2309,22 @@ static void vxlan_vs_del_dev(struct vxla
 	struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
 
 	spin_lock(&vn->sock_lock);
-	hlist_del_init_rcu(&vxlan->hlist);
+	hlist_del_init_rcu(&vxlan->hlist4.hlist);
+#if IS_ENABLED(CONFIG_IPV6)
+	hlist_del_init_rcu(&vxlan->hlist6.hlist);
+#endif
 	spin_unlock(&vn->sock_lock);
 }
 
-static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan)
+static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan,
+			     struct vxlan_dev_node *node)
 {
 	struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
 	__be32 vni = vxlan->default_dst.remote_vni;
 
+	node->vxlan = vxlan;
 	spin_lock(&vn->sock_lock);
-	hlist_add_head_rcu(&vxlan->hlist, vni_head(vs, vni));
+	hlist_add_head_rcu(&node->hlist, vni_head(vs, vni));
 	spin_unlock(&vn->sock_lock);
 }

@@ -2778,6 +2783,7 @@ static int __vxlan_sock_add(struct vxlan
 {
 	struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
 	struct vxlan_sock *vs = NULL;
+	struct vxlan_dev_node *node;
 
 	if (!vxlan->cfg.no_share) {
 		spin_lock(&vn->sock_lock);

@@ -2795,12 +2801,16 @@ static int __vxlan_sock_add(struct vxlan
 	if (IS_ERR(vs))
 		return PTR_ERR(vs);
 #if IS_ENABLED(CONFIG_IPV6)
-	if (ipv6)
+	if (ipv6) {
 		rcu_assign_pointer(vxlan->vn6_sock, vs);
-	else
+		node = &vxlan->hlist6;
+	} else
 #endif
+	{
 		rcu_assign_pointer(vxlan->vn4_sock, vs);
-	vxlan_vs_add_dev(vs, vxlan);
+		node = &vxlan->hlist4;
+	}
+	vxlan_vs_add_dev(vs, vxlan, node);
 	return 0;
 }

include/net/vxlan.h +9 -1

@@ -221,9 +221,17 @@ struct vxlan_config {
 	bool			no_share;
 };
 
+struct vxlan_dev_node {
+	struct hlist_node hlist;
+	struct vxlan_dev *vxlan;
+};
+
 /* Pseudo network device */
 struct vxlan_dev {
-	struct hlist_node hlist;	/* vni hash table */
+	struct vxlan_dev_node hlist4;	/* vni hash table for IPv4 socket */
+#if IS_ENABLED(CONFIG_IPV6)
+	struct vxlan_dev_node hlist6;	/* vni hash table for IPv6 socket */
+#endif
 	struct list_head  next;		/* vxlan's per namespace list */
 	struct vxlan_sock __rcu *vn4_sock;	/* listening socket for IPv4 */
 #if IS_ENABLED(CONFIG_IPV6)

Greg Kroah-Hartman

author maintainer

2017-07-19 10:25 UTC #17 lore raw

PATCH 18/72 net: core: Fix slab-out-of-bounds in netdev_stats_to_stats64

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

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

From: Alban Browaeys <[email protected]>

commit 9af9959e142c274f4a30fefb71d97d2b028b337f upstream.

commit 9256645af098 ("net/core: relax BUILD_BUG_ON in netdev_stats_to_stats64") made an attempt to read beyond the size of the source a possibility.

Fix to only copy src size to dest. As dest might be bigger than src.

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

 BUG: KASAN: slab-out-of-bounds in netdev_stats_to_stats64+0xe/0x30 at addr ffff8801be248b20
 Read of size 192 by task VBoxNetAdpCtl/6734
 CPU: 1 PID: 6734 Comm: VBoxNetAdpCtl Tainted: G           O    4.11.4prahal+intel+ #118
 Hardware name: LENOVO 20CDCTO1WW/20CDCTO1WW, BIOS GQET52WW (1.32 ) 05/04/2017
 Call Trace:
  dump_stack+0x63/0x86
  kasan_object_err+0x1c/0x70
  kasan_report+0x270/0x520
  ? netdev_stats_to_stats64+0xe/0x30
  ? sched_clock_cpu+0x1b/0x190
  ? __module_address+0x3e/0x3b0
  ? unwind_next_frame+0x1ea/0xb00
  check_memory_region+0x13c/0x1a0
  memcpy+0x23/0x50
  netdev_stats_to_stats64+0xe/0x30
  dev_get_stats+0x1b9/0x230
  rtnl_fill_stats+0x44/0xc00
  ? nla_put+0xc6/0x130
  rtnl_fill_ifinfo+0xe9e/0x3700
  ? rtnl_fill_vfinfo+0xde0/0xde0
  ? sched_clock+0x9/0x10
  ? sched_clock+0x9/0x10
  ? sched_clock_local+0x120/0x130
  ? __module_address+0x3e/0x3b0
  ? unwind_next_frame+0x1ea/0xb00
  ? sched_clock+0x9/0x10
  ? sched_clock+0x9/0x10
  ? sched_clock_cpu+0x1b/0x190
  ? VBoxNetAdpLinuxIOCtlUnlocked+0x14b/0x280 [vboxnetadp]
  ? depot_save_stack+0x1d8/0x4a0
  ? depot_save_stack+0x34f/0x4a0
  ? depot_save_stack+0x34f/0x4a0
  ? save_stack+0xb1/0xd0
  ? save_stack_trace+0x16/0x20
  ? save_stack+0x46/0xd0
  ? kasan_slab_alloc+0x12/0x20
  ? __kmalloc_node_track_caller+0x10d/0x350
  ? __kmalloc_reserve.isra.36+0x2c/0xc0
  ? __alloc_skb+0xd0/0x560
  ? rtmsg_ifinfo_build_skb+0x61/0x120
  ? rtmsg_ifinfo.part.25+0x16/0xb0
  ? rtmsg_ifinfo+0x47/0x70
  ? register_netdev+0x15/0x30
  ? vboxNetAdpOsCreate+0xc0/0x1c0 [vboxnetadp]
  ? vboxNetAdpCreate+0x210/0x400 [vboxnetadp]
  ? VBoxNetAdpLinuxIOCtlUnlocked+0x14b/0x280 [vboxnetadp]
  ? do_vfs_ioctl+0x17f/0xff0
  ? SyS_ioctl+0x74/0x80
  ? do_syscall_64+0x182/0x390
  ? __alloc_skb+0xd0/0x560
  ? __alloc_skb+0xd0/0x560
  ? save_stack_trace+0x16/0x20
  ? init_object+0x64/0xa0
  ? ___slab_alloc+0x1ae/0x5c0
  ? ___slab_alloc+0x1ae/0x5c0
  ? __alloc_skb+0xd0/0x560
  ? sched_clock+0x9/0x10
  ? kasan_unpoison_shadow+0x35/0x50
  ? kasan_kmalloc+0xad/0xe0
  ? __kmalloc_node_track_caller+0x246/0x350
  ? __alloc_skb+0xd0/0x560
  ? kasan_unpoison_shadow+0x35/0x50
  ? memset+0x31/0x40
  ? __alloc_skb+0x31f/0x560
  ? napi_consume_skb+0x320/0x320
  ? br_get_link_af_size_filtered+0xb7/0x120 [bridge]
  ? if_nlmsg_size+0x440/0x630
  rtmsg_ifinfo_build_skb+0x83/0x120
  rtmsg_ifinfo.part.25+0x16/0xb0
  rtmsg_ifinfo+0x47/0x70
  register_netdevice+0xa2b/0xe50
  ? __kmalloc+0x171/0x2d0
  ? netdev_change_features+0x80/0x80
  register_netdev+0x15/0x30
  vboxNetAdpOsCreate+0xc0/0x1c0 [vboxnetadp]
  vboxNetAdpCreate+0x210/0x400 [vboxnetadp]
  ? vboxNetAdpComposeMACAddress+0x1d0/0x1d0 [vboxnetadp]
  ? kasan_check_write+0x14/0x20
  VBoxNetAdpLinuxIOCtlUnlocked+0x14b/0x280 [vboxnetadp]
  ? VBoxNetAdpLinuxOpen+0x20/0x20 [vboxnetadp]
  ? lock_acquire+0x11c/0x270
  ? __audit_syscall_entry+0x2fb/0x660
  do_vfs_ioctl+0x17f/0xff0
  ? __audit_syscall_entry+0x2fb/0x660
  ? ioctl_preallocate+0x1d0/0x1d0
  ? __audit_syscall_entry+0x2fb/0x660
  ? kmem_cache_free+0xb2/0x250
  ? syscall_trace_enter+0x537/0xd00
  ? exit_to_usermode_loop+0x100/0x100
  SyS_ioctl+0x74/0x80
  ? do_sys_open+0x350/0x350
  ? do_vfs_ioctl+0xff0/0xff0
  do_syscall_64+0x182/0x390
  entry_SYSCALL64_slow_path+0x25/0x25
 RIP: 0033:0x7f7e39a1ae07
 RSP: 002b:00007ffc6f04c6d8 EFLAGS: 00000206 ORIG_RAX: 0000000000000010
 RAX: ffffffffffffffda RBX: 00007ffc6f04c730 RCX: 00007f7e39a1ae07
 RDX: 00007ffc6f04c730 RSI: 00000000c0207601 RDI: 0000000000000007
 RBP: 00007ffc6f04c700 R08: 00007ffc6f04c780 R09: 0000000000000008
 R10: 0000000000000541 R11: 0000000000000206 R12: 0000000000000007
 R13: 00000000c0207601 R14: 00007ffc6f04c730 R15: 0000000000000012
 Object at ffff8801be248008, in cache kmalloc-4096 size: 4096
 Allocated:
 PID = 6734
  save_stack_trace+0x16/0x20
  save_stack+0x46/0xd0
  kasan_kmalloc+0xad/0xe0
  __kmalloc+0x171/0x2d0
  alloc_netdev_mqs+0x8a7/0xbe0
  vboxNetAdpOsCreate+0x65/0x1c0 [vboxnetadp]
  vboxNetAdpCreate+0x210/0x400 [vboxnetadp]
  VBoxNetAdpLinuxIOCtlUnlocked+0x14b/0x280 [vboxnetadp]
  do_vfs_ioctl+0x17f/0xff0
  SyS_ioctl+0x74/0x80
  do_syscall_64+0x182/0x390
  return_from_SYSCALL_64+0x0/0x6a
 Freed:
 PID = 5600
  save_stack_trace+0x16/0x20
  save_stack+0x46/0xd0
  kasan_slab_free+0x73/0xc0
  kfree+0xe4/0x220
  kvfree+0x25/0x30
  single_release+0x74/0xb0
  __fput+0x265/0x6b0
  ____fput+0x9/0x10
  task_work_run+0xd5/0x150
  exit_to_usermode_loop+0xe2/0x100
  do_syscall_64+0x26c/0x390
  return_from_SYSCALL_64+0x0/0x6a
 Memory state around the buggy address:
  ffff8801be248a80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
  ffff8801be248b00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
 >ffff8801be248b80: 00 00 00 00 00 00 00 00 00 00 00 07 fc fc fc fc
                                                     ^
  ffff8801be248c00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
  ffff8801be248c80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 ==================================================================

Signed-off-by Alban Browaeys <[email protected]>

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

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

net/core/dev.c +1 -1

@@ -7531,7 +7531,7 @@ void netdev_stats_to_stats64(struct rtnl
 {
 #if BITS_PER_LONG == 64
 	BUILD_BUG_ON(sizeof(*stats64) < sizeof(*netdev_stats));
-	memcpy(stats64, netdev_stats, sizeof(*stats64));
+	memcpy(stats64, netdev_stats, sizeof(*netdev_stats));
 	/* zero out counters that only exist in rtnl_link_stats64 */
 	memset((char *)stats64 + sizeof(*netdev_stats), 0,
 	       sizeof(*stats64) - sizeof(*netdev_stats));

Greg Kroah-Hartman

author maintainer

2017-07-19 10:26 UTC #18 lore raw

PATCH 20/72 vrf: fix bug_on triggered by rx when destroying a vrf

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

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

From: Nikolay Aleksandrov <[email protected]>

commit f630c38ef0d785101363a8992bbd4f302180f86f upstream.

When destroying a VRF device we cleanup the slaves in its ndo_uninit() function, but that causes packets to be switched (skb->dev == vrf being destroyed) even though we're pass the point where the VRF should be receiving any packets while it is being dismantled. This causes a BUG_ON to trigger if we have raw sockets (trace below).
The reason is that the inetdev of the VRF has been destroyed but we're still sending packets up the stack with it, so let's free the slaves in the dellink callback as David Ahern suggested.

Note that this fix doesn't prevent packets from going up when the VRF device is admin down.

[   35.631371] ------------[ cut here ]------------
[   35.631603] kernel BUG at net/ipv4/fib_frontend.c:285!
[   35.631854] invalid opcode: 0000 [#1] SMP
[   35.631977] Modules linked in:
[   35.632081] CPU: 2 PID: 22 Comm: ksoftirqd/2 Not tainted 4.12.0-rc7+ #45
[   35.632247] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140531_083030-gandalf 04/01/2014
[   35.632477] task: ffff88005ad68000 task.stack: ffff88005ad64000
[   35.632632] RIP: 0010:fib_compute_spec_dst+0xfc/0x1ee
[   35.632769] RSP: 0018:ffff88005ad67978 EFLAGS: 00010202
[   35.632910] RAX: 0000000000000001 RBX: ffff880059a7f200 RCX: 0000000000000000
[   35.633084] RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffffffff82274af0
[   35.633256] RBP: ffff88005ad679f8 R08: 000000000001ef70 R09: 0000000000000046
[   35.633430] R10: ffff88005ad679f8 R11: ffff880037731cb0 R12: 0000000000000001
[   35.633603] R13: ffff8800599e3000 R14: 0000000000000000 R15: ffff8800599cb852
[   35.634114] FS:  0000000000000000(0000) GS:ffff88005d900000(0000) knlGS:0000000000000000
[   35.634306] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   35.634456] CR2: 00007f3563227095 CR3: 000000000201d000 CR4: 00000000000406e0
[   35.634632] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[   35.634865] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[   35.635055] Call Trace:
[   35.635271]  ? __lock_acquire+0xf0d/0x1117
[   35.635522]  ipv4_pktinfo_prepare+0x82/0x151
[   35.635831]  raw_rcv_skb+0x17/0x3c
[   35.636062]  raw_rcv+0xe5/0xf7
[   35.636287]  raw_local_deliver+0x169/0x1d9
[   35.636534]  ip_local_deliver_finish+0x87/0x1c4
[   35.636820]  ip_local_deliver+0x63/0x7f
[   35.637058]  ip_rcv_finish+0x340/0x3a1
[   35.637295]  ip_rcv+0x314/0x34a
[   35.637525]  __netif_receive_skb_core+0x49f/0x7c5
[   35.637780]  ? lock_acquire+0x13f/0x1d7
[   35.638018]  ? lock_acquire+0x15e/0x1d7
[   35.638259]  __netif_receive_skb+0x1e/0x94
[   35.638502]  ? __netif_receive_skb+0x1e/0x94
[   35.638748]  netif_receive_skb_internal+0x74/0x300
[   35.639002]  ? dev_gro_receive+0x2ed/0x411
[   35.639246]  ? lock_is_held_type+0xc4/0xd2
[   35.639491]  napi_gro_receive+0x105/0x1a0
[   35.639736]  receive_buf+0xc32/0xc74
[   35.639965]  ? detach_buf+0x67/0x153
[   35.640201]  ? virtqueue_get_buf_ctx+0x120/0x176
[   35.640453]  virtnet_poll+0x128/0x1c5
[   35.640690]  net_rx_action+0x103/0x343
[   35.640932]  __do_softirq+0x1c7/0x4b7
[   35.641171]  run_ksoftirqd+0x23/0x5c
[   35.641403]  smpboot_thread_fn+0x24f/0x26d
[   35.641646]  ? sort_range+0x22/0x22
[   35.641878]  kthread+0x129/0x131
[   35.642104]  ? __list_add+0x31/0x31
[   35.642335]  ? __list_add+0x31/0x31
[   35.642568]  ret_from_fork+0x2a/0x40
[   35.642804] Code: 05 bd 87 a3 00 01 e8 1f ef 98 ff 4d 85 f6 48 c7 c7 f0 4a 27 82 41 0f 94 c4 31 c9 31 d2 41 0f b6 f4 e8 04 71 a1 ff 45 84 e4 74 02 <0f> 0b 0f b7 93 c4 00 00 00 4d 8b a5 80 05 00 00 48 03 93 d0 00
[   35.644342] RIP: fib_compute_spec_dst+0xfc/0x1ee RSP: ffff88005ad67978

Fixes 193125dbd8eb ("net: Introduce VRF device driver")

Reported-by Chris Cormier <[email protected]>

Signed-off-by Nikolay Aleksandrov <[email protected]>

Acked-by David Ahern <[email protected]>

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

---
 drivers/net/vrf.c |   11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

drivers/net/vrf.c +6 -5

@@ -787,15 +787,10 @@ static int vrf_del_slave(struct net_devi
 static void vrf_dev_uninit(struct net_device *dev)
 {
 	struct net_vrf *vrf = netdev_priv(dev);
-	struct net_device *port_dev;
-	struct list_head *iter;
 
 	vrf_rtable_release(dev, vrf);
 	vrf_rt6_release(dev, vrf);
 
-	netdev_for_each_lower_dev(dev, port_dev, iter)
-		vrf_del_slave(dev, port_dev);
-
 	free_percpu(dev->dstats);
 	dev->dstats = NULL;
 }

@@ -1232,6 +1227,12 @@ static int vrf_validate(struct nlattr *t
 
 static void vrf_dellink(struct net_device *dev, struct list_head *head)
 {
+	struct net_device *port_dev;
+	struct list_head *iter;
+
+	netdev_for_each_lower_dev(dev, port_dev, iter)
+		vrf_del_slave(dev, port_dev);
+
 	unregister_netdevice_queue(dev, head);
 }

Greg Kroah-Hartman

author maintainer

2017-07-19 10:25 UTC #19 lore raw

PATCH 21/72 rds: tcp: use sock_create_lite() to create the accept socket

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

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

From: Sowmini Varadhan <[email protected]>

commit 0933a578cd55b02dc80f219dc8f2efb17ec61c9a upstream.

There are two problems with calling sock_create_kern() from rds_tcp_accept_one()
1. it sets up a new_sock->sk that is wasteful, because this ->sk is going to get replaced by inet_accept() in the subsequent ->accept()
2. The new_sock->sk is a leaked reference in sock_graft() which expects to find a null parent->sk

Avoid these problems by calling sock_create_lite().

Signed-off-by Sowmini Varadhan <[email protected]>

Acked-by Santosh Shilimkar <[email protected]>

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

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

net/rds/tcp_listen.c +1 -1

@@ -129,7 +129,7 @@ int rds_tcp_accept_one(struct socket *so
 	if (!sock) /* module unload or netns delete in progress */
 		return -ENETUNREACH;
 
-	ret = sock_create_kern(sock_net(sock->sk), sock->sk->sk_family,
+	ret = sock_create_lite(sock->sk->sk_family,
 			       sock->sk->sk_type, sock->sk->sk_protocol,
 			       &new_sock);
 	if (ret)

Greg Kroah-Hartman

author maintainer

2017-07-19 10:25 UTC #20 lore raw

PATCH 23/72 brcmfmac: Fix a memory leak in error handling path in brcmf_cfg80211_attach

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

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

From: Christophe Jaillet <[email protected]>

commit 57c00f2fac512837f8de73474ec1f54020015bae upstream.

If 'wiphy_new()' fails, we leak 'ops'. Add a new label in the error handling path to free it in such a case.

Fixes 5c22fb85102a7 ("brcmfmac: add wowl gtk rekeying offload support")

Signed-off-by Christophe JAILLET <[email protected]>

Signed-off-by Kalle Valo <[email protected]>

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

---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +2 -1

@@ -6876,7 +6876,7 @@ struct brcmf_cfg80211_info *brcmf_cfg802
 	wiphy = wiphy_new(ops, sizeof(struct brcmf_cfg80211_info));
 	if (!wiphy) {
 		brcmf_err("Could not allocate wiphy device\n");
-		return NULL;
+		goto ops_out;
 	}
 	memcpy(wiphy->perm_addr, drvr->mac, ETH_ALEN);
 	set_wiphy_dev(wiphy, busdev);

@@ -7010,6 +7010,7 @@ priv_out:
 	ifp->vif = NULL;
 wiphy_out:
 	brcmf_free_wiphy(wiphy);
+ops_out:
 	kfree(ops);
 	return NULL;
 }

Greg Kroah-Hartman

author maintainer

2017-07-19 10:26 UTC #21 lore raw

PATCH 24/72 brcmfmac: Fix glom_skb leak in brcmf_sdiod_recv_chain

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

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

From: Peter S. Housel <[email protected]>

commit 5ea59db8a375216e6c915c5586f556766673b5a7 upstream.

An earlier change to this function (3bdae810721b) fixed a leak in the case of an unsuccessful call to brcmf_sdiod_buffrw(). However, the glom_skb buffer, used for emulating a scattering read, is never used or referenced after its contents are copied into the destination buffers, and therefore always needs to be freed by the end of the function.

Fixes 3bdae810721b ("brcmfmac: Fix glob_skb leak in brcmf_sdiod_recv_chain")

Fixes a413e39a38573 ("brcmfmac: fix brcmf_sdcard_recv_chain() for host without sg support")

Signed-off-by Peter S. Housel <[email protected]>

Signed-off-by Arend van Spriel <[email protected]>

Signed-off-by Kalle Valo <[email protected]>

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

---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c |    7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c +3 -4

@@ -705,7 +705,7 @@ done:
 int brcmf_sdiod_recv_chain(struct brcmf_sdio_dev *sdiodev,
 			   struct sk_buff_head *pktq, uint totlen)
 {
-	struct sk_buff *glom_skb;
+	struct sk_buff *glom_skb = NULL;
 	struct sk_buff *skb;
 	u32 addr = sdiodev->sbwad;
 	int err = 0;

@@ -726,10 +726,8 @@ int brcmf_sdiod_recv_chain(struct brcmf_
 			return -ENOMEM;
 		err = brcmf_sdiod_buffrw(sdiodev, SDIO_FUNC_2, false, addr,
 					 glom_skb);
-		if (err) {
-			brcmu_pkt_buf_free_skb(glom_skb);
+		if (err)
 			goto done;
-		}
 
 		skb_queue_walk(pktq, skb) {
 			memcpy(skb->data, glom_skb->data, skb->len);

@@ -740,6 +738,7 @@ int brcmf_sdiod_recv_chain(struct brcmf_
 					    pktq);
 
 done:
+	brcmu_pkt_buf_free_skb(glom_skb);
 	return err;
 }

Greg Kroah-Hartman

author maintainer

2017-07-19 10:26 UTC #22 lore raw

PATCH 25/72 sfc: dont read beyond unicast address list

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

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

From: Bert Kenward <[email protected]>

[ Upstream commit c70d68150f71b84cea6997a53493e17bf18a54db ]

If we have more than 32 unicast MAC addresses assigned to an interface we will read beyond the end of the address table in the driver when adding filters. The next 256 entries store multicast addresses, so we will end up attempting to insert duplicate filters, which is mostly harmless. If we add more than 288 unicast addresses we will then read past the multicast address table, which is likely to be more exciting.

Fixes 12fb0da45c9a ("sfc: clean fallbacks between promisc/normal in efx_ef10_filter_sync_rx_mode")

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

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

---
 drivers/net/ethernet/sfc/ef10.c |    8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

drivers/net/ethernet/sfc/ef10.c +3 -5

@@ -4399,12 +4399,9 @@ static void efx_ef10_filter_uc_addr_list
 	struct efx_ef10_filter_table *table = efx->filter_state;
 	struct net_device *net_dev = efx->net_dev;
 	struct netdev_hw_addr *uc;
-	int addr_count;
 	unsigned int i;
 
-	addr_count = netdev_uc_count(net_dev);
 	table->uc_promisc = !!(net_dev->flags & IFF_PROMISC);
-	table->dev_uc_count = 1 + addr_count;
 	ether_addr_copy(table->dev_uc_list[0].addr, net_dev->dev_addr);
 	i = 1;
 	netdev_for_each_uc_addr(uc, net_dev) {

@@ -4415,6 +4412,8 @@ static void efx_ef10_filter_uc_addr_list
 		ether_addr_copy(table->dev_uc_list[i].addr, uc->addr);
 		i++;
 	}
+
+	table->dev_uc_count = i;
 }
 
 static void efx_ef10_filter_mc_addr_list(struct efx_nic *efx)

@@ -4422,11 +4421,10 @@ static void efx_ef10_filter_mc_addr_list
 	struct efx_ef10_filter_table *table = efx->filter_state;
 	struct net_device *net_dev = efx->net_dev;
 	struct netdev_hw_addr *mc;
-	unsigned int i, addr_count;
+	unsigned int i;
 
 	table->mc_promisc = !!(net_dev->flags & (IFF_PROMISC | IFF_ALLMULTI));
 
-	addr_count = netdev_mc_count(net_dev);
 	i = 0;
 	netdev_for_each_mc_addr(mc, net_dev) {
 		if (i >= EFX_EF10_FILTER_DEV_MC_MAX) {

Greg Kroah-Hartman

author maintainer

2017-07-19 10:26 UTC #23 lore raw

PATCH 26/72 cfg80211: Define nla_policy for NL80211_ATTR_LOCAL_MESH_POWER_MODE

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

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

From: Srinivas Dasari <[email protected]>

commit 8feb69c7bd89513be80eb19198d48f154b254021 upstream.

Buffer overread may happen as nl80211_set_station() reads 4 bytes from the attribute NL80211_ATTR_LOCAL_MESH_POWER_MODE without validating the size of data received when userspace sends less than 4 bytes of data with NL80211_ATTR_LOCAL_MESH_POWER_MODE. Define nla_policy for NL80211_ATTR_LOCAL_MESH_POWER_MODE to avoid the buffer overread.

Fixes 3b1c5a5307f ("{cfg,nl}80211: mesh power mode primitives and userspace access")

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

---
 net/wireless/nl80211.c |    1 +
 1 file changed, 1 insertion(+)

net/wireless/nl80211.c +1 -0

@@ -362,6 +362,7 @@ static const struct nla_policy nl80211_p
 	[NL80211_ATTR_SCAN_FLAGS] = { .type = NLA_U32 },
 	[NL80211_ATTR_P2P_CTWINDOW] = { .type = NLA_U8 },
 	[NL80211_ATTR_P2P_OPPPS] = { .type = NLA_U8 },
+	[NL80211_ATTR_LOCAL_MESH_POWER_MODE] = {. type = NLA_U32 },
 	[NL80211_ATTR_ACL_POLICY] = {. type = NLA_U32 },
 	[NL80211_ATTR_MAC_ADDRS] = { .type = NLA_NESTED },
 	[NL80211_ATTR_STA_CAPABILITY] = { .type = NLA_U16 },

Greg Kroah-Hartman

author maintainer

2017-07-19 10:26 UTC #24 lore raw

PATCH 27/72 cfg80211: Validate frequencies nested in NL80211_ATTR_SCAN_FREQUENCIES

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

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

From: Srinivas Dasari <[email protected]>

commit d7f13f7450369281a5d0ea463cc69890a15923ae upstream.

validate_scan_freqs() retrieves frequencies from attributes nested in the attribute NL80211_ATTR_SCAN_FREQUENCIES with nla_get_u32(), which reads 4 bytes from each attribute without validating the size of data received. Attributes nested in NL80211_ATTR_SCAN_FREQUENCIES don't have an nla policy.

Validate size of each attribute before parsing to avoid potential buffer overread.

Fixes 2a519311926 ("cfg80211/nl80211: scanning (and mac80211 update to use it)")

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

---
 net/wireless/nl80211.c |    4 ++++
 1 file changed, 4 insertions(+)

net/wireless/nl80211.c +4 -0

@@ -6327,6 +6327,10 @@ static int validate_scan_freqs(struct nl
 	struct nlattr *attr1, *attr2;
 	int n_channels = 0, tmp1, tmp2;
 
+	nla_for_each_nested(attr1, freqs, tmp1)
+		if (nla_len(attr1) != sizeof(u32))
+			return 0;
+
 	nla_for_each_nested(attr1, freqs, tmp1) {
 		n_channels++;
 		/*

Greg Kroah-Hartman

author maintainer

2017-07-19 10:24 UTC #25 lore raw

PATCH 28/72 cfg80211: Check if PMKID attribute is of expected size

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

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

From: Srinivas Dasari <[email protected]>

commit 9361df14d1cbf966409d5d6f48bb334384fbe138 upstream.

nla policy checks for only maximum length of the attribute data when the attribute type is NLA_BINARY. If userspace sends less data than specified, the wireless drivers may access illegal memory. When type is NLA_UNSPEC, nla policy check ensures that userspace sends minimum specified length number of bytes.

Remove type assignment to NLA_BINARY from nla_policy of NL80211_ATTR_PMKID to make this NLA_UNSPEC and to make sure minimum WLAN_PMKID_LEN bytes are received from userspace with NL80211_ATTR_PMKID.

Fixes 67fbb16be69d ("nl80211: PMKSA caching support")

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

---
 net/wireless/nl80211.c |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

net/wireless/nl80211.c +1 -2

@@ -305,8 +305,7 @@ static const struct nla_policy nl80211_p
 	[NL80211_ATTR_WPA_VERSIONS] = { .type = NLA_U32 },
 	[NL80211_ATTR_PID] = { .type = NLA_U32 },
 	[NL80211_ATTR_4ADDR] = { .type = NLA_U8 },
-	[NL80211_ATTR_PMKID] = { .type = NLA_BINARY,
-				 .len = WLAN_PMKID_LEN },
+	[NL80211_ATTR_PMKID] = { .len = WLAN_PMKID_LEN },
 	[NL80211_ATTR_DURATION] = { .type = NLA_U32 },
 	[NL80211_ATTR_COOKIE] = { .type = NLA_U64 },
 	[NL80211_ATTR_TX_RATES] = { .type = NLA_NESTED },

Greg Kroah-Hartman

author maintainer

2017-07-19 10:26 UTC #26 lore raw

PATCH 29/72 cfg80211: Check if NAN service ID is of expected size

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

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

From: Srinivas Dasari <[email protected]>

commit 0a27844ce86d039d74221dd56cd8c0349b146b63 upstream.

nla policy checks for only maximum length of the attribute data when the attribute type is NLA_BINARY. If userspace sends less data than specified, cfg80211 may access illegal memory. When type is NLA_UNSPEC, nla policy check ensures that userspace sends minimum specified length number of bytes.

Remove type assignment to NLA_BINARY from nla_policy of NL80211_NAN_FUNC_SERVICE_ID to make these NLA_UNSPEC and to make sure minimum NL80211_NAN_FUNC_SERVICE_ID_LEN bytes are received from userspace with NL80211_NAN_FUNC_SERVICE_ID.

Fixes a442b761b24 ("cfg80211: add add_nan_func / del_nan_func")

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

---
 net/wireless/nl80211.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

net/wireless/nl80211.c +1 -1

@@ -512,7 +512,7 @@ nl80211_bss_select_policy[NL80211_BSS_SE
 static const struct nla_policy
 nl80211_nan_func_policy[NL80211_NAN_FUNC_ATTR_MAX + 1] = {
 	[NL80211_NAN_FUNC_TYPE] = { .type = NLA_U8 },
-	[NL80211_NAN_FUNC_SERVICE_ID] = { .type = NLA_BINARY,
+	[NL80211_NAN_FUNC_SERVICE_ID] = {
 				    .len = NL80211_NAN_FUNC_SERVICE_ID_LEN },
 	[NL80211_NAN_FUNC_PUBLISH_TYPE] = { .type = NLA_U8 },
 	[NL80211_NAN_FUNC_PUBLISH_BCAST] = { .type = NLA_FLAG },

Greg Kroah-Hartman

author maintainer

2017-07-19 10:26 UTC #27 lore raw

PATCH 30/72 irqchip/gic-v3: Fix out-of-bound access in gic_set_affinity

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

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

From: Suzuki K Poulose <[email protected]>

commit 866d7c1b0a3c70387646c4e455e727a58c5d465a upstream.

The GICv3 driver doesn't check if the target CPU for gic_set_affinity is valid before going ahead and making the changes. This triggers the following splat with KASAN:

[  141.189434] BUG: KASAN: global-out-of-bounds in gic_set_affinity+0x8c/0x140
[  141.189704] Read of size 8 at addr ffff200009741d20 by task swapper/1/0
[  141.189958]
[  141.190158] CPU: 1 PID: 0 Comm: swapper/1 Not tainted 4.12.0-rc7
[  141.190458] Hardware name: Foundation-v8A (DT)
[  141.190658] Call trace:
[  141.190908] [<ffff200008089d70>] dump_backtrace+0x0/0x328
[  141.191224] [<ffff20000808a1b4>] show_stack+0x14/0x20
[  141.191507] [<ffff200008504c3c>] dump_stack+0xa4/0xc8
[  141.191858] [<ffff20000826c19c>] print_address_description+0x13c/0x250
[  141.192219] [<ffff20000826c5c8>] kasan_report+0x210/0x300
[  141.192547] [<ffff20000826ad54>] __asan_load8+0x84/0x98
[  141.192874] [<ffff20000854eeec>] gic_set_affinity+0x8c/0x140
[  141.193158] [<ffff200008148b14>] irq_do_set_affinity+0x54/0xb8
[  141.193473] [<ffff200008148d2c>] irq_set_affinity_locked+0x64/0xf0
[  141.193828] [<ffff200008148e00>] __irq_set_affinity+0x48/0x78
[  141.194158] [<ffff200008bc48a4>] arm_perf_starting_cpu+0x104/0x150
[  141.194513] [<ffff2000080d73bc>] cpuhp_invoke_callback+0x17c/0x1f8
[  141.194783] [<ffff2000080d94ec>] notify_cpu_starting+0x8c/0xb8
[  141.195130] [<ffff2000080911ec>] secondary_start_kernel+0x15c/0x200
[  141.195390] [<0000000080db81b4>] 0x80db81b4
[  141.195603]
[  141.195685] The buggy address belongs to the variable:
[  141.196012]  __cpu_logical_map+0x200/0x220
[  141.196176]
[  141.196315] Memory state around the buggy address:
[  141.196586]  ffff200009741c00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[  141.196913]  ffff200009741c80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[  141.197158] >ffff200009741d00: 00 00 00 00 fa fa fa fa 00 00 00 00 00 00 00 00
[  141.197487]                                ^
[  141.197758]  ffff200009741d80: 00 00 00 00 00 00 00 00 fa fa fa fa 00 00 00 00
[  141.198060]  ffff200009741e00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[  141.198358] ==================================================================
[  141.198609] Disabling lock debugging due to kernel taint
[  141.198961] CPU1: Booted secondary processor [410fd051]

This patch adds the check to make sure the cpu is valid.

Fixes commit 021f653791ad17e03f98 ("irqchip: gic-v3: Initial support for GICv3")

Signed-off-by Suzuki K Poulose <[email protected]>

Signed-off-by Marc Zyngier <[email protected]>

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

---
 drivers/irqchip/irq-gic-v3.c |    3 +++
 1 file changed, 3 insertions(+)

drivers/irqchip/irq-gic-v3.c +3 -0

@@ -646,6 +646,9 @@ static int gic_set_affinity(struct irq_d
 	int enabled;
 	u64 val;
 
+	if (cpu >= nr_cpu_ids)
+		return -EINVAL;
+
 	if (gic_irq_in_rdist(d))
 		return -EINVAL;

Greg Kroah-Hartman

author maintainer

2017-07-19 10:26 UTC #28 lore raw

PATCH 31/72 parisc: Report SIGSEGV instead of SIGBUS when running out of stack

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

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

From: Helge Deller <[email protected]>

commit 247462316f85a9e0479445c1a4223950b68ffac1 upstream.

When a process runs out of stack the parisc kernel wrongly faults with SIGBUS instead of the expected SIGSEGV signal.

This example shows how the kernel faults:
do_page_fault() command='a.out' type=15 address=0xfaac2000 in libc-2.24.so[f8308000+16c000] trap #15: Data TLB miss fault, vm_start = 0xfa2c2000, vm_end = 0xfaac2000

The vma->vm_end value is the first address which does not belong to the vma, so adjust the check to include vma->vm_end to the range for which to send the SIGSEGV signal.

This patch unbreaks building the debian libsigsegv package.

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

---
 arch/parisc/mm/fault.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

arch/parisc/mm/fault.c +1 -1

@@ -366,7 +366,7 @@ bad_area:
 		case 15:	/* Data TLB miss fault/Data page fault */
 			/* send SIGSEGV when outside of vma */
 			if (!vma ||
-			    address < vma->vm_start || address > vma->vm_end) {
+			    address < vma->vm_start || address >= vma->vm_end) {
 				si.si_signo = SIGSEGV;
 				si.si_code = SEGV_MAPERR;
 				break;

Greg Kroah-Hartman

author maintainer

2017-07-19 10:26 UTC #29 lore raw

PATCH 32/72 parisc: use compat_sys_keyctl()

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

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

From: Eric Biggers <[email protected]>

commit b0f94efd5aa8daa8a07d7601714c2573266cd4c9 upstream.

Architectures with a compat syscall table must put compat_sys_keyctl() in it, not sys_keyctl(). The parisc architecture was not doing this; fix it.

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

Acked-by Helge Deller <[email protected]>

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

---
 arch/parisc/kernel/syscall_table.S |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

arch/parisc/kernel/syscall_table.S +1 -1

@@ -361,7 +361,7 @@
 	ENTRY_SAME(ni_syscall)	/* 263: reserved for vserver */
 	ENTRY_SAME(add_key)
 	ENTRY_SAME(request_key)		/* 265 */
-	ENTRY_SAME(keyctl)
+	ENTRY_COMP(keyctl)
 	ENTRY_SAME(ioprio_set)
 	ENTRY_SAME(ioprio_get)
 	ENTRY_SAME(inotify_init)

Greg Kroah-Hartman

author maintainer

2017-07-19 10:26 UTC #30 lore raw

PATCH 33/72 parisc: DMA API: return error instead of BUG_ON for dma ops on non dma devs

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

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

From: Thomas Bogendoerfer <[email protected]>

commit 33f9e02495d15a061f0c94ef46f5103a2d0c20f3 upstream.

Enabling parport pc driver on a B2600 (and probably other 64bit PARISC systems) produced following BUG:

CPU: 0 PID: 1 Comm: swapper Not tainted 4.12.0-rc5-30198-g1132d5e #156

task: 000000009e050000 task.stack: 000000009e04c000

YZrvWESTHLNXBCVMcbcbcbcbOGFRQPDI
PSW: 00001000000001101111111100001111 Not tainted

r00-03  000000ff0806ff0f 000000009e04c990 0000000040871b78 000000009e04cac0
r04-07  0000000040c14de0 ffffffffffffffff 000000009e07f098 000000009d82d200
r08-11  000000009d82d210 0000000000000378 0000000000000000 0000000040c345e0
r12-15  0000000000000005 0000000040c345e0 0000000000000000 0000000040c9d5e0
r16-19  0000000040c345e0 00000000f00001c4 00000000f00001bc 0000000000000061
r20-23  000000009e04ce28 0000000000000010 0000000000000010 0000000040b89e40
r24-27  0000000000000003 0000000000ffffff 000000009d82d210 0000000040c14de0
r28-31  0000000000000000 000000009e04ca90 000000009e04cb40 0000000000000000

sr00-03 0000000000000000 0000000000000000 0000000000000000 0000000000000000 sr04-07 0000000000000000 0000000000000000 0000000000000000 0000000000000000

IASQ: 0000000000000000 0000000000000000 IAOQ: 00000000404aece0 00000000404aece4
IIR: 03ffe01f ISR: 0000000010340000 IOR: 000001781304cac8
CPU: 0 CR30: 000000009e04c000 CR31: 00000000e2976de2
ORIG_R28: 0000000000000200
IAOQ[0]: sba_dma_supported+0x80/0xd0
IAOQ[1]: sba_dma_supported+0x84/0xd0
RP(r2): parport_pc_probe_port+0x178/0x1200

Cause is a call to dma_coerce_mask_and_coherenet in parport_pc_probe_port, which PARISC DMA API doesn't handle very nicely. This commit gives back DMA_ERROR_CODE for DMA API calls, if device isn't capable of DMA transaction.

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

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

---
 arch/parisc/include/asm/dma-mapping.h |   11 +++++++----
 drivers/parisc/ccio-dma.c             |   12 ++++++++++++
 drivers/parisc/dino.c                 |    5 ++++-
 drivers/parisc/lba_pci.c              |    6 ++++--
 drivers/parisc/sba_iommu.c            |   14 ++++++++++++++
 5 files changed, 41 insertions(+), 7 deletions(-)

arch/parisc/include/asm/dma-mapping.h +7 -4

@@ -20,6 +20,8 @@
 ** flush/purge and allocate "regular" cacheable pages for everything.
 */
 
+#define DMA_ERROR_CODE	(~(dma_addr_t)0)
+
 #ifdef CONFIG_PA11
 extern struct dma_map_ops pcxl_dma_ops;
 extern struct dma_map_ops pcx_dma_ops;

@@ -54,12 +56,13 @@ parisc_walk_tree(struct device *dev)
 			break;
 		}
 	}
-	BUG_ON(!dev->platform_data);
 	return dev->platform_data;
 }
-		
-#define GET_IOC(dev) (HBA_DATA(parisc_walk_tree(dev))->iommu)
-	
+
+#define GET_IOC(dev) ({					\
+	void *__pdata = parisc_walk_tree(dev);		\
+	__pdata ? HBA_DATA(__pdata)->iommu : NULL;	\
+})
 
 #ifdef CONFIG_IOMMU_CCIO
 struct parisc_device;

drivers/parisc/ccio-dma.c +12 -0

@@ -741,6 +741,8 @@ ccio_map_single(struct device *dev, void
 
 	BUG_ON(!dev);
 	ioc = GET_IOC(dev);
+	if (!ioc)
+		return DMA_ERROR_CODE;
 
 	BUG_ON(size <= 0);

@@ -814,6 +816,10 @@ ccio_unmap_page(struct device *dev, dma_
 	
 	BUG_ON(!dev);
 	ioc = GET_IOC(dev);
+	if (!ioc) {
+		WARN_ON(!ioc);
+		return;
+	}
 
 	DBG_RUN("%s() iovp 0x%lx/%x\n",
 		__func__, (long)iova, size);

@@ -918,6 +924,8 @@ ccio_map_sg(struct device *dev, struct s
 	
 	BUG_ON(!dev);
 	ioc = GET_IOC(dev);
+	if (!ioc)
+		return 0;
 	
 	DBG_RUN_SG("%s() START %d entries\n", __func__, nents);

@@ -990,6 +998,10 @@ ccio_unmap_sg(struct device *dev, struct
 
 	BUG_ON(!dev);
 	ioc = GET_IOC(dev);
+	if (!ioc) {
+		WARN_ON(!ioc);
+		return;
+	}
 
 	DBG_RUN_SG("%s() START %d entries, %p,%x\n",
 		__func__, nents, sg_virt(sglist), sglist->length);

drivers/parisc/dino.c +4 -1

@@ -154,7 +154,10 @@ struct dino_device
 };
 
 /* Looks nice and keeps the compiler happy */
-#define DINO_DEV(d) ((struct dino_device *) d)
+#define DINO_DEV(d) ({				\
+	void *__pdata = d;			\
+	BUG_ON(!__pdata);			\
+	(struct dino_device *)__pdata; })
 
 
 /*

drivers/parisc/lba_pci.c +4 -2

@@ -111,8 +111,10 @@ static u32 lba_t32;
 
 
 /* Looks nice and keeps the compiler happy */
-#define LBA_DEV(d) ((struct lba_device *) (d))
-
+#define LBA_DEV(d) ({				\
+	void *__pdata = d;			\
+	BUG_ON(!__pdata);			\
+	(struct lba_device *)__pdata; })
 
 /*
 ** Only allow 8 subsidiary busses per LBA

drivers/parisc/sba_iommu.c +14 -0

@@ -691,6 +691,8 @@ static int sba_dma_supported( struct dev
 		return 0;
 
 	ioc = GET_IOC(dev);
+	if (!ioc)
+		return 0;
 
 	/*
 	 * check if mask is >= than the current max IO Virt Address

@@ -722,6 +724,8 @@ sba_map_single(struct device *dev, void
 	int pide;
 
 	ioc = GET_IOC(dev);
+	if (!ioc)
+		return DMA_ERROR_CODE;
 
 	/* save offset bits */
 	offset = ((dma_addr_t) (long) addr) & ~IOVP_MASK;

@@ -813,6 +817,10 @@ sba_unmap_page(struct device *dev, dma_a
 	DBG_RUN("%s() iovp 0x%lx/%x\n", __func__, (long) iova, size);
 
 	ioc = GET_IOC(dev);
+	if (!ioc) {
+		WARN_ON(!ioc);
+		return;
+	}
 	offset = iova & ~IOVP_MASK;
 	iova ^= offset;        /* clear offset bits */
 	size += offset;

@@ -952,6 +960,8 @@ sba_map_sg(struct device *dev, struct sc
 	DBG_RUN_SG("%s() START %d entries\n", __func__, nents);
 
 	ioc = GET_IOC(dev);
+	if (!ioc)
+		return 0;
 
 	/* Fast path single entry scatterlists. */
 	if (nents == 1) {

@@ -1037,6 +1047,10 @@ sba_unmap_sg(struct device *dev, struct
 		__func__, nents, sg_virt(sglist), sglist->length);
 
 	ioc = GET_IOC(dev);
+	if (!ioc) {
+		WARN_ON(!ioc);
+		return;
+	}
 
 #ifdef SBA_COLLECT_STATS
 	ioc->usg_calls++;

Greg Kroah-Hartman

author maintainer

2017-07-19 10:24 UTC #31 lore raw

PATCH 34/72 parisc/mm: Ensure IRQs are off in switch_mm()

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

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

From: Helge Deller <[email protected]>

commit 649aa24254e85bf6bd7807dd372d083707852b1f upstream.

This is because of commit f98db6013c55 ("sched/core: Add switch_mm_irqs_off() and use it in the scheduler") in which switch_mm_irqs_off() is called by the scheduler, vs switch_mm() which is used by use_mm().

This patch lets the parisc code mirror the x86 and powerpc code, ie. it disables interrupts in switch_mm(), and optimises the scheduler case by defining switch_mm_irqs_off().

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

---
 arch/parisc/include/asm/mmu_context.h |   15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

arch/parisc/include/asm/mmu_context.h +13 -2

@@ -49,15 +49,26 @@ static inline void load_context(mm_conte
 	mtctl(__space_to_prot(context), 8);
 }
 
-static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk)
+static inline void switch_mm_irqs_off(struct mm_struct *prev,
+		struct mm_struct *next, struct task_struct *tsk)
 {
-
 	if (prev != next) {
 		mtctl(__pa(next->pgd), 25);
 		load_context(next->context);
 	}
 }
 
+static inline void switch_mm(struct mm_struct *prev,
+		struct mm_struct *next, struct task_struct *tsk)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	switch_mm_irqs_off(prev, next, tsk);
+	local_irq_restore(flags);
+}
+#define switch_mm_irqs_off switch_mm_irqs_off
+
 #define deactivate_mm(tsk,mm)	do { } while (0)
 
 static inline void activate_mm(struct mm_struct *prev, struct mm_struct *next)

Greg Kroah-Hartman

author maintainer

2017-07-19 10:26 UTC #32 lore raw

PATCH 35/72 tools/lib/lockdep: Reduce MAX_LOCK_DEPTH to avoid overflowing lock_chain/: Depth

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

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

From: Ben Hutchings <[email protected]>

commit 98dcea0cfd04e083ac74137ceb9a632604740e2d upstream.

liblockdep has been broken since commit 75dd602a5198 ("lockdep: Fix lock_chain::base size"), as that adds a check that MAX_LOCK_DEPTH is within the range of lock_chain::depth and in liblockdep it is much too large.

That should have resulted in a compiler error, but didn't because:

- the check uses ARRAY_SIZE(), which isn't yet defined in liblockdep so is assumed to be an (undeclared) function
- putting a function call inside a BUILD_BUG_ON() expression quietly turns it into some nonsense involving a variable-length array

It did produce a compiler warning, but I didn't notice because liblockdep already produces too many warnings if -Wall is enabled (which I'll fix shortly).

Even before that commit, which reduced lock_chain::depth from 8 bits to 6, MAX_LOCK_DEPTH was too large.

Signed-off-by Ben Hutchings <[email protected]>

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

Cc Linus Torvalds <[email protected]>

Cc Peter Zijlstra <[email protected]>

Cc Thomas Gleixner <[email protected]>

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]>

---
 tools/lib/lockdep/uinclude/linux/lockdep.h |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

tools/lib/lockdep/uinclude/linux/lockdep.h +1 -1

@@ -8,7 +8,7 @@
 #include <linux/utsname.h>
 #include <linux/compiler.h>
 
-#define MAX_LOCK_DEPTH 2000UL
+#define MAX_LOCK_DEPTH 63UL
 
 #define asmlinkage
 #define __visible

Greg Kroah-Hartman

author maintainer

2017-07-19 10:27 UTC #33 lore raw

PATCH 36/72 thp, mm: fix crash due race in MADV_FREE handling

https://www.sr71.net/~dave/intel/log2.c

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

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

From: Kirill A. Shutemov <[email protected]>

commit bbf29ffc7f963bb894f84f0580c70cfea01c3892 upstream.

Reinette reported the following crash:

  BUG: Bad page state in process log2exe  pfn:57600
  page:ffffea00015d8000 count:0 mapcount:0 mapping:          (null) index:0x20200
  flags: 0x4000000000040019(locked|uptodate|dirty|swapbacked)
  raw: 4000000000040019 0000000000000000 0000000000020200 00000000ffffffff
  raw: ffffea00015d8020 ffffea00015d8020 0000000000000000 0000000000000000
  page dumped because: PAGE_FLAGS_CHECK_AT_FREE flag(s) set
  bad because of flags: 0x1(locked)
  Modules linked in: rfcomm 8021q bnep intel_rapl x86_pkg_temp_thermal coretemp efivars btusb btrtl btbcm pwm_lpss_pci snd_hda_codec_hdmi btintel pwm_lpss snd_hda_codec_realtek snd_soc_skl snd_hda_codec_generic snd_soc_skl_ipc spi_pxa2xx_platform snd_soc_sst_ipc snd_soc_sst_dsp i2c_designware_platform i2c_designware_core snd_hda_ext_core snd_soc_sst_match snd_hda_intel snd_hda_codec mei_me snd_hda_core mei snd_soc_rt286 snd_soc_rl6347a snd_soc_core efivarfs
  CPU: 1 PID: 354 Comm: log2exe Not tainted 4.12.0-rc7-test-test #19
  Hardware name: Intel corporation NUC6CAYS/NUC6CAYB, BIOS AYAPLCEL.86A.0027.2016.1108.1529 11/08/2016
  Call Trace:
   bad_page+0x16a/0x1f0
   free_pages_check_bad+0x117/0x190
   free_hot_cold_page+0x7b1/0xad0
   __put_page+0x70/0xa0
   madvise_free_huge_pmd+0x627/0x7b0
   madvise_free_pte_range+0x6f8/0x1150
   __walk_page_range+0x6b5/0xe30
   walk_page_range+0x13b/0x310
   madvise_free_page_range.isra.16+0xad/0xd0
   madvise_free_single_vma+0x2e4/0x470
   SyS_madvise+0x8ce/0x1450

If somebody frees the page under us and we hold the last reference to it, put_page() would attempt to free the page before unlocking it.

The fix is trivial reorder of operations.

Dave said:
"I came up with the exact same patch. For posterity, here's the test
case, generated by syzkaller and trimmed down by Reinette:

And the config that helps detect this:

https://www.sr71.net/~dave/intel/config-log2"

Fixes b8d3c4c3009d ("mm/huge_memory.c: don't split THP page when MADV_FREE syscall is called")

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

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

Reported-by Reinette Chatre <[email protected]>

Acked-by Dave Hansen <[email protected]>

Acked-by Michal Hocko <[email protected]>

Acked-by Minchan Kim <[email protected]>

Cc Huang Ying <[email protected]>

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

---
 mm/huge_memory.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

mm/huge_memory.c +1 -1

@@ -1373,8 +1373,8 @@ bool madvise_free_huge_pmd(struct mmu_ga
 		get_page(page);
 		spin_unlock(ptl);
 		split_huge_page(page);
-		put_page(page);
 		unlock_page(page);
+		put_page(page);
 		goto out_unlocked;
 	}

Greg Kroah-Hartman

author maintainer

2017-07-19 10:26 UTC #34 lore raw

PATCH 37/72 kernel/extable.c: mark core_kernel_text notrace

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

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

From: Marcin Nowakowski <[email protected]>

commit c0d80ddab89916273cb97114889d3f337bc370ae upstream.

core_kernel_text is used by MIPS in its function graph trace processing, so having this method traced leads to an infinite set of recursive calls such as:

  Call Trace:
     ftrace_return_to_handler+0x50/0x128
     core_kernel_text+0x10/0x1b8
     prepare_ftrace_return+0x6c/0x114
     ftrace_graph_caller+0x20/0x44
     return_to_handler+0x10/0x30
     return_to_handler+0x0/0x30
     return_to_handler+0x0/0x30
     ftrace_ops_no_ops+0x114/0x1bc
     core_kernel_text+0x10/0x1b8
     core_kernel_text+0x10/0x1b8
     core_kernel_text+0x10/0x1b8
     ftrace_ops_no_ops+0x114/0x1bc
     core_kernel_text+0x10/0x1b8
     prepare_ftrace_return+0x6c/0x114
     ftrace_graph_caller+0x20/0x44
     (...)

Mark the function notrace to avoid it being traced.

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

Signed-off-by Marcin Nowakowski <[email protected]>

Reviewed-by Masami Hiramatsu <[email protected]>

Cc Peter Zijlstra <[email protected]>

Cc Thomas Meyer <[email protected]>

Cc Ingo Molnar <[email protected]>

Cc Steven Rostedt <[email protected]>

Cc Daniel Borkmann <[email protected]>

Cc Paul Gortmaker <[email protected]>

Cc Thomas Gleixner <[email protected]>

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

---
 kernel/extable.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

kernel/extable.c +1 -1

@@ -66,7 +66,7 @@ static inline int init_kernel_text(unsig
 	return 0;
 }
 
-int core_kernel_text(unsigned long addr)
+int notrace core_kernel_text(unsigned long addr)
 {
 	if (addr >= (unsigned long)_stext &&
 	    addr < (unsigned long)_etext)

Greg Kroah-Hartman

author maintainer

2017-07-19 10:24 UTC #35 lore raw

PATCH 38/72 mm/list_lru.c: fix list_lru_count_node() to be race free

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

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

From: Sahitya Tummala <[email protected]>

commit 2c80cd57c74339889a8752b20862a16c28929c3a upstream.

list_lru_count_node() iterates over all memcgs to get the total number of entries on the node but it can race with memcg_drain_all_list_lrus(), which migrates the entries from a dead cgroup to another. This can return incorrect number of entries from list_lru_count_node().

Fix this by keeping track of entries per node and simply return it in list_lru_count_node().

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

Signed-off-by Sahitya Tummala <[email protected]>

Acked-by Vladimir Davydov <[email protected]>

Cc Jan Kara <[email protected]>

Cc Alexander Polakov <[email protected]>

Cc Al Viro <[email protected]>

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

---
 include/linux/list_lru.h |    1 +
 mm/list_lru.c            |   14 ++++++--------
 2 files changed, 7 insertions(+), 8 deletions(-)

include/linux/list_lru.h +1 -0

@@ -44,6 +44,7 @@ struct list_lru_node {
 	/* for cgroup aware lrus points to per cgroup lists, otherwise NULL */
 	struct list_lru_memcg	*memcg_lrus;
 #endif
+	long nr_items;
 } ____cacheline_aligned_in_smp;
 
 struct list_lru {

mm/list_lru.c +6 -8

@@ -117,6 +117,7 @@ bool list_lru_add(struct list_lru *lru,
 		l = list_lru_from_kmem(nlru, item);
 		list_add_tail(item, &l->list);
 		l->nr_items++;
+		nlru->nr_items++;
 		spin_unlock(&nlru->lock);
 		return true;
 	}

@@ -136,6 +137,7 @@ bool list_lru_del(struct list_lru *lru,
 		l = list_lru_from_kmem(nlru, item);
 		list_del_init(item);
 		l->nr_items--;
+		nlru->nr_items--;
 		spin_unlock(&nlru->lock);
 		return true;
 	}

@@ -183,15 +185,10 @@ EXPORT_SYMBOL_GPL(list_lru_count_one);
 
 unsigned long list_lru_count_node(struct list_lru *lru, int nid)
 {
-	long count = 0;
-	int memcg_idx;
+	struct list_lru_node *nlru;
 
-	count += __list_lru_count_one(lru, nid, -1);
-	if (list_lru_memcg_aware(lru)) {
-		for_each_memcg_cache_index(memcg_idx)
-			count += __list_lru_count_one(lru, nid, memcg_idx);
-	}
-	return count;
+	nlru = &lru->node[nid];
+	return nlru->nr_items;
 }
 EXPORT_SYMBOL_GPL(list_lru_count_node);

@@ -226,6 +223,7 @@ restart:
 			assert_spin_locked(&nlru->lock);
 		case LRU_REMOVED:
 			isolated++;
+			nlru->nr_items--;
 			/*
 			 * If the lru lock has been dropped, our list
 			 * traversal is now invalid and so we have to

Greg Kroah-Hartman

author maintainer

2017-07-19 10:24 UTC #36 lore raw

PATCH 39/72 fs/dcache.c: fix spin lockup issue on nlru->lock

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

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

From: Sahitya Tummala <[email protected]>

commit b17c070fb624cf10162cf92ea5e1ec25cd8ac176 upstream.

__list_lru_walk_one() acquires nlru spin lock (nlru->lock) for longer duration if there are more number of items in the lru list. As per the current code, it can hold the spin lock for upto maximum UINT_MAX entries at a time. So if there are more number of items in the lru list, then "BUG: spinlock lockup suspected" is observed in the below path:

spin_bug+0x90
do_raw_spin_lock+0xfc
_raw_spin_lock+0x28
list_lru_add+0x28
dput+0x1c8
path_put+0x20
terminate_walk+0x3c
path_lookupat+0x100
filename_lookup+0x6c
user_path_at_empty+0x54
SyS_faccessat+0xd0
el0_svc_naked+0x24

This nlru->lock is acquired by another CPU in this path -

d_lru_shrink_move+0x34
dentry_lru_isolate_shrink+0x48
__list_lru_walk_one.isra.10+0x94
list_lru_walk_node+0x40
shrink_dcache_sb+0x60
do_remount_sb+0xbc
do_emergency_remount+0xb0
process_one_work+0x228
worker_thread+0x2e0
kthread+0xf4
ret_from_fork+0x10

Fix this lockup by reducing the number of entries to be shrinked from the lru list to 1024 at once. Also, add cond_resched() before processing the lru list again.

Link http://marc.info/?t=149722864900001&r=1&w=2

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

Signed-off-by Sahitya Tummala <[email protected]>

Suggested-by Jan Kara <[email protected]>

Acked-by Vladimir Davydov <[email protected]>

Cc Alexander Polakov <[email protected]>

Cc Al Viro <[email protected]>

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

---
 fs/dcache.c |    5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

fs/dcache.c +3 -2

@@ -1133,11 +1133,12 @@ void shrink_dcache_sb(struct super_block
 		LIST_HEAD(dispose);
 
 		freed = list_lru_walk(&sb->s_dentry_lru,
-			dentry_lru_isolate_shrink, &dispose, UINT_MAX);
+			dentry_lru_isolate_shrink, &dispose, 1024);
 
 		this_cpu_sub(nr_dentry_unused, freed);
 		shrink_dentry_list(&dispose);
-	} while (freed > 0);
+		cond_resched();
+	} while (list_lru_count(&sb->s_dentry_lru) > 0);
 }
 EXPORT_SYMBOL(shrink_dcache_sb);

Greg Kroah-Hartman

author maintainer

2017-07-19 10:24 UTC #37 lore raw

PATCH 40/72 checkpatch: silence perl 5.26.0 unescaped left brace warnings

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

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

From: Cyril Bur <[email protected]>

commit 8d81ae05d0176da1c54aeaed697fa34be5c5575e upstream.

As of perl 5, version 26, subversion 0 (v5.26.0) some new warnings have occurred when running checkpatch.

Unescaped left brace in regex is deprecated here (and will be fatal in Perl 5.30), passed through in regex; marked by <-- HERE in m/^(.\s*){ <-- HERE \s*/ at scripts/checkpatch.pl line 3544.

Unescaped left brace in regex is deprecated here (and will be fatal in Perl 5.30), passed through in regex; marked by <-- HERE in m/^(.\s*){ <-- HERE \s*/ at scripts/checkpatch.pl line 3885.

Unescaped left brace in regex is deprecated here (and will be fatal in Perl 5.30), passed through in regex; marked by <-- HERE in m/^(\+.*(?:do|\))){ <-- HERE / at scripts/checkpatch.pl line 4374.

It seems perfectly reasonable to do as the warning suggests and simply escape the left brace in these three locations.

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

Signed-off-by Cyril Bur <[email protected]>

Acked-by Joe Perches <[email protected]>

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

---
 scripts/checkpatch.pl |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

scripts/checkpatch.pl +3 -3

@@ -3499,7 +3499,7 @@ sub process {
 				$fixedline =~ s/\s*=\s*$/ = {/;
 				fix_insert_line($fixlinenr, $fixedline);
 				$fixedline = $line;
-				$fixedline =~ s/^(.\s*){\s*/$1/;
+				$fixedline =~ s/^(.\s*)\{\s*/$1/;
 				fix_insert_line($fixlinenr, $fixedline);
 			}
 		}

@@ -3840,7 +3840,7 @@ sub process {
 				my $fixedline = rtrim($prevrawline) . " {";
 				fix_insert_line($fixlinenr, $fixedline);
 				$fixedline = $rawline;
-				$fixedline =~ s/^(.\s*){\s*/$1\t/;
+				$fixedline =~ s/^(.\s*)\{\s*/$1\t/;
 				if ($fixedline !~ /^\+\s*$/) {
 					fix_insert_line($fixlinenr, $fixedline);
 				}

@@ -4329,7 +4329,7 @@ sub process {
 			if (ERROR("SPACING",
 				  "space required before the open brace '{'\n" . $herecurr) &&
 			    $fix) {
-				$fixed[$fixlinenr] =~ s/^(\+.*(?:do|\))){/$1 {/;
+				$fixed[$fixlinenr] =~ s/^(\+.*(?:do|\)))\{/$1 {/;
 			}
 		}

Greg Kroah-Hartman

author maintainer

2017-07-19 10:24 UTC #38 lore raw

PATCH 41/72 binfmt_elf: use ELF_ET_DYN_BASE only for PIE

Link http://lkml.kernel.org/r/20170621173201.GA114489@beast open here

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

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

From: Kees Cook <[email protected]>

commit eab09532d40090698b05a07c1c87f39fdbc5fab5 upstream.

The ELF_ET_DYN_BASE position was originally intended to keep loaders away from ET_EXEC binaries. (For example, running "/lib/ld-linux.so.2 /bin/cat" might cause the subsequent load of /bin/cat into where the loader had been loaded.)

With the advent of PIE (ET_DYN binaries with an INTERP Program Header), ELF_ET_DYN_BASE continued to be used since the kernel was only looking at ET_DYN. However, since ELF_ET_DYN_BASE is traditionally set at the top 1/3rd of the TASK_SIZE, a substantial portion of the address space is unused.

For 32-bit tasks when RLIMIT_STACK is set to RLIM_INFINITY, programs are loaded above the mmap region. This means they can be made to collide (CVE-2017-1000370) or nearly collide (CVE-2017-1000371) with pathological stack regions.

Lowering ELF_ET_DYN_BASE solves both by moving programs below the mmap region in all cases, and will now additionally avoid programs falling back to the mmap region by enforcing MAP_FIXED for program loads (i.e. if it would have collided with the stack, now it will fail to load instead of falling back to the mmap region).

To allow for a lower ELF_ET_DYN_BASE, loaders (ET_DYN without INTERP) are loaded into the mmap region, leaving space available for either an ET_EXEC binary with a fixed location or PIE being loaded into mmap by the loader. Only PIE programs are loaded offset from ELF_ET_DYN_BASE, which means architectures can now safely lower their values without risk of loaders colliding with their subsequently loaded programs.

For 64-bit, ELF_ET_DYN_BASE is best set to 4GB to allow runtimes to use the entire 32-bit address space for 32-bit pointers.

Thanks to PaX Team, Daniel Micay, and Rik van Riel for inspiration and suggestions on how to implement this solution.

Fixes d1fd836dcf00 ("mm: split ET_DYN ASLR from mmap ASLR")

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

Acked-by Rik van Riel <[email protected]>

Cc Daniel Micay <[email protected]>

Cc Qualys Security Advisory <[email protected]>

Cc Thomas Gleixner <[email protected]>

Cc Ingo Molnar <[email protected]>

Cc "H. Peter Anvin" <[email protected]>

Cc Alexander Viro <[email protected]>

Cc Dmitry Safonov <[email protected]>

Cc Andy Lutomirski <[email protected]>

Cc Grzegorz Andrejczuk <[email protected]>

Cc Masahiro Yamada <[email protected]>

Cc Benjamin Herrenschmidt <[email protected]>

Cc Catalin Marinas <[email protected]>

Cc Heiko Carstens <[email protected]>

Cc James Hogan <[email protected]>

Cc Martin Schwidefsky <[email protected]>

Cc Michael Ellerman <[email protected]>

Cc Paul Mackerras <[email protected]>

Cc Pratyush Anand <[email protected]>

Cc Russell King <[email protected]>

Cc Will Deacon <[email protected]>

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

---
 arch/x86/include/asm/elf.h |   13 +++++----
 fs/binfmt_elf.c            |   59 ++++++++++++++++++++++++++++++++++++++-------
 2 files changed, 58 insertions(+), 14 deletions(-)

arch/x86/include/asm/elf.h +7 -6

@@ -245,12 +245,13 @@ extern int force_personality32;
 #define CORE_DUMP_USE_REGSET
 #define ELF_EXEC_PAGESIZE	4096
 
-/* This is the location that an ET_DYN program is loaded if exec'ed.  Typical
-   use of this is to invoke "./ld.so someprog" to test out a new version of
-   the loader.  We need to make sure that it is out of the way of the program
-   that it will "exec", and that there is sufficient room for the brk.  */
-
-#define ELF_ET_DYN_BASE		(TASK_SIZE / 3 * 2)
+/*
+ * This is the base location for PIE (ET_DYN with INTERP) loads. On
+ * 64-bit, this is raised to 4GB to leave the entire 32-bit address
+ * space open for things that want to use the area for 32-bit pointers.
+ */
+#define ELF_ET_DYN_BASE		(mmap_is_ia32() ? 0x000400000UL : \
+						  0x100000000UL)
 
 /* This yields a mask that user programs can use to figure out what
    instruction set this CPU supports.  This could be done in user space,

fs/binfmt_elf.c +51 -8

68 lines not on this page · raw message

Greg Kroah-Hartman

author maintainer

2017-07-19 10:26 UTC #39 lore raw

PATCH 42/72 arm: move ELF_ET_DYN_BASE to 4MB

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

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

From: Kees Cook <[email protected]>

commit 6a9af90a3bcde217a1c053e135f5f43e5d5fafbd upstream.

Now that explicitly executed loaders are loaded in the mmap region, we have more freedom to decide where we position PIE binaries in the address space to avoid possible collisions with mmap or stack regions.

4MB is chosen here mainly to have parity with x86, where this is the traditional minimum load location, likely to avoid historically requiring a 4MB page table entry when only a portion of the first 4MB would be used (since the NULL address is avoided).

For ARM the position could be 0x8000, the standard ET_EXEC load address, but that is needlessly close to the NULL address, and anyone running PIE on 32-bit ARM will have an MMU, so the tight mapping is not needed.

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

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

Cc Russell King <[email protected]>

Cc Catalin Marinas <[email protected]>

Cc Will Deacon <[email protected]>

Cc Benjamin Herrenschmidt <[email protected]>

Cc Paul Mackerras <[email protected]>

Cc Michael Ellerman <[email protected]>

Cc Martin Schwidefsky <[email protected]>

Cc Heiko Carstens <[email protected]>

Cc James Hogan <[email protected]>

Cc Pratyush Anand <[email protected]>

Cc Ingo Molnar <[email protected]>

Cc "H. Peter Anvin" <[email protected]>

Cc Alexander Viro <[email protected]>

Cc Andy Lutomirski <[email protected]>

Cc Daniel Micay <[email protected]>

Cc Dmitry Safonov <[email protected]>

Cc Grzegorz Andrejczuk <[email protected]>

Cc Kees Cook <[email protected]>

Cc Masahiro Yamada <[email protected]>

Cc Qualys Security Advisory <[email protected]>

Cc Rik van Riel <[email protected]>

Cc Thomas Gleixner <[email protected]>

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

---
 arch/arm/include/asm/elf.h |    8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

arch/arm/include/asm/elf.h +2 -6

@@ -112,12 +112,8 @@ int dump_task_regs(struct task_struct *t
 #define CORE_DUMP_USE_REGSET
 #define ELF_EXEC_PAGESIZE	4096
 
-/* This is the location that an ET_DYN program is loaded if exec'ed.  Typical
-   use of this is to invoke "./ld.so someprog" to test out a new version of
-   the loader.  We need to make sure that it is out of the way of the program
-   that it will "exec", and that there is sufficient room for the brk.  */
-
-#define ELF_ET_DYN_BASE	(TASK_SIZE / 3 * 2)
+/* This is the base location for PIE (ET_DYN with INTERP) loads. */
+#define ELF_ET_DYN_BASE		0x400000UL
 
 /* When the program starts, a1 contains a pointer to a function to be 
    registered with atexit, as per the SVR4 ABI.  A value of 0 means we

Greg Kroah-Hartman

author maintainer

2017-07-19 10:24 UTC #40 lore raw

PATCH 43/72 arm64: move ELF_ET_DYN_BASE to 4GB / 4MB

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

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

From: Kees Cook <[email protected]>

commit 02445990a96e60a67526510d8b00f7e3d14101c3 upstream.

For 64-bit, align to 4GB to allow runtimes to use the entire 32-bit address space for 32-bit pointers. On 32-bit use 4MB, to match ARM. This could be 0x8000, the standard ET_EXEC load address, but that is needlessly close to the NULL address, and anyone running arm compat PIE will have an MMU, so the tight mapping is not needed.

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

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

Cc Ard Biesheuvel <[email protected]>

Cc Catalin Marinas <[email protected]>

Cc Mark Rutland <[email protected]>

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

---
 arch/arm64/include/asm/elf.h |   12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

arch/arm64/include/asm/elf.h +6 -6

@@ -113,12 +113,11 @@
 #define ELF_EXEC_PAGESIZE	PAGE_SIZE
 
 /*
- * This is the location that an ET_DYN program is loaded if exec'ed.  Typical
- * use of this is to invoke "./ld.so someprog" to test out a new version of
- * the loader.  We need to make sure that it is out of the way of the program
- * that it will "exec", and that there is sufficient room for the brk.
+ * This is the base location for PIE (ET_DYN with INTERP) loads. On
+ * 64-bit, this is raised to 4GB to leave the entire 32-bit address
+ * space open for things that want to use the area for 32-bit pointers.
  */
-#define ELF_ET_DYN_BASE	(2 * TASK_SIZE_64 / 3)
+#define ELF_ET_DYN_BASE		0x100000000UL
 
 #ifndef __ASSEMBLY__

@@ -169,7 +168,8 @@ extern int arch_setup_additional_pages(s
 
 #ifdef CONFIG_COMPAT
 
-#define COMPAT_ELF_ET_DYN_BASE		(2 * TASK_SIZE_32 / 3)
+/* PIE load location for compat arm. Must match ARM ELF_ET_DYN_BASE. */
+#define COMPAT_ELF_ET_DYN_BASE		0x000400000UL
 
 /* AArch32 registers. */
 #define COMPAT_ELF_NGREG		18

Greg Kroah-Hartman

author maintainer

2017-07-19 10:26 UTC #41 lore raw

PATCH 44/72 powerpc: move ELF_ET_DYN_BASE to 4GB / 4MB

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

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

From: Kees Cook <[email protected]>

commit 47ebb09d54856500c5a5e14824781902b3bb738e upstream.

For 64-bit, align to 4GB to allow runtimes to use the entire 32-bit address space for 32-bit pointers. On 32-bit use 4MB, which is the traditional x86 minimum load location, likely to avoid historically requiring a 4MB page table entry when only a portion of the first 4MB would be used (since the NULL address is avoided).

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

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

Tested-by Michael Ellerman <[email protected]>

Acked-by Michael Ellerman <[email protected]>

Cc Russell King <[email protected]>

Cc Catalin Marinas <[email protected]>

Cc Will Deacon <[email protected]>

Cc Benjamin Herrenschmidt <[email protected]>

Cc Paul Mackerras <[email protected]>

Cc Martin Schwidefsky <[email protected]>

Cc Heiko Carstens <[email protected]>

Cc James Hogan <[email protected]>

Cc Pratyush Anand <[email protected]>

Cc Ingo Molnar <[email protected]>

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

---
 arch/powerpc/include/asm/elf.h |   13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

arch/powerpc/include/asm/elf.h +7 -6

@@ -23,12 +23,13 @@
 #define CORE_DUMP_USE_REGSET
 #define ELF_EXEC_PAGESIZE	PAGE_SIZE
 
-/* This is the location that an ET_DYN program is loaded if exec'ed.  Typical
-   use of this is to invoke "./ld.so someprog" to test out a new version of
-   the loader.  We need to make sure that it is out of the way of the program
-   that it will "exec", and that there is sufficient room for the brk.  */
-
-#define ELF_ET_DYN_BASE	0x20000000
+/*
+ * This is the base location for PIE (ET_DYN with INTERP) loads. On
+ * 64-bit, this is raised to 4GB to leave the entire 32-bit address
+ * space open for things that want to use the area for 32-bit pointers.
+ */
+#define ELF_ET_DYN_BASE		(is_32bit_task() ? 0x000400000UL : \
+						   0x100000000UL)
 
 #define ELF_CORE_EFLAGS (is_elf2_task() ? 2 : 0)

Greg Kroah-Hartman

author maintainer

2017-07-19 10:26 UTC #42 lore raw

PATCH 45/72 s390: reduce ELF_ET_DYN_BASE

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

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

From: Kees Cook <[email protected]>

commit a73dc5370e153ac63718d850bddf0c9aa9d871e6 upstream.

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

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

Cc Russell King <[email protected]>

Cc Catalin Marinas <[email protected]>

Cc Will Deacon <[email protected]>

Cc Benjamin Herrenschmidt <[email protected]>

Cc Paul Mackerras <[email protected]>

Cc Michael Ellerman <[email protected]>

Cc Martin Schwidefsky <[email protected]>

Cc Heiko Carstens <[email protected]>

Cc James Hogan <[email protected]>

Cc Pratyush Anand <[email protected]>

Cc Ingo Molnar <[email protected]>

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

---
 arch/s390/include/asm/elf.h |   15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

arch/s390/include/asm/elf.h +7 -8

@@ -158,14 +158,13 @@ extern unsigned int vdso_enabled;
 #define CORE_DUMP_USE_REGSET
 #define ELF_EXEC_PAGESIZE	4096
 
-/* This is the location that an ET_DYN program is loaded if exec'ed.  Typical
-   use of this is to invoke "./ld.so someprog" to test out a new version of
-   the loader.  We need to make sure that it is out of the way of the program
-   that it will "exec", and that there is sufficient room for the brk. 64-bit
-   tasks are aligned to 4GB. */
-#define ELF_ET_DYN_BASE (is_compat_task() ? \
-				(STACK_TOP / 3 * 2) : \
-				(STACK_TOP / 3 * 2) & ~((1UL << 32) - 1))
+/*
+ * This is the base location for PIE (ET_DYN with INTERP) loads. On
+ * 64-bit, this is raised to 4GB to leave the entire 32-bit address
+ * space open for things that want to use the area for 32-bit pointers.
+ */
+#define ELF_ET_DYN_BASE		(is_compat_task() ? 0x000400000UL : \
+						    0x100000000UL)
 
 /* This yields a mask that user programs can use to figure out what
    instruction set this CPU supports. */

Greg Kroah-Hartman

author maintainer

2017-07-19 10:24 UTC #43 lore raw

PATCH 46/72 exec: Limit arg stack to at most 75% of _STK_LIM

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

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

From: Kees Cook <[email protected]>

commit da029c11e6b12f321f36dac8771e833b65cec962 upstream.

To avoid pathological stack usage or the need to special-case setuid execs, just limit all arg stack usage to at most 75% of _STK_LIM (6MB).

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

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

---
 fs/exec.c |   11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

fs/exec.c +6 -5

@@ -215,8 +215,7 @@ static struct page *get_arg_page(struct
 
 	if (write) {
 		unsigned long size = bprm->vma->vm_end - bprm->vma->vm_start;
-		unsigned long ptr_size;
-		struct rlimit *rlim;
+		unsigned long ptr_size, limit;
 
 		/*
 		 * Since the stack will hold pointers to the strings, we

@@ -245,14 +244,16 @@ static struct page *get_arg_page(struct
 			return page;
 
 		/*
-		 * Limit to 1/4-th the stack size for the argv+env strings.
+		 * Limit to 1/4 of the max stack size or 3/4 of _STK_LIM
+		 * (whichever is smaller) for the argv+env strings.
 		 * This ensures that:
 		 *  - the remaining binfmt code will not run out of stack space,
 		 *  - the program will have a reasonable amount of stack left
 		 *    to work from.
 		 */
-		rlim = current->signal->rlim;
-		if (size > READ_ONCE(rlim[RLIMIT_STACK].rlim_cur) / 4)
+		limit = _STK_LIM / 4 * 3;
+		limit = min(limit, rlimit(RLIMIT_STACK) / 4);
+		if (size > limit)
 			goto fail;
 	}

Greg Kroah-Hartman

author maintainer

2017-07-19 10:26 UTC #44 lore raw

PATCH 47/72 ARM64: dts: marvell: armada37xx: Fix timer interrupt specifiers

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

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

From: Marc Zyngier <[email protected]>

commit 88cda00733f0731711c76e535d4972c296ac512e upstream.

Contrary to popular belief, PPIs connected to a GICv3 to not have an affinity field similar to that of GICv2. That is consistent with the fact that GICv3 is designed to accomodate thousands of CPUs, and fitting them as a bitmap in a byte is... difficult.

Fixes adbc3695d9e4 ("arm64: dts: add the Marvell Armada 3700 family and a development board")

Signed-off-by Marc Zyngier <[email protected]>

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

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

---
 arch/arm64/boot/dts/marvell/armada-37xx.dtsi |   12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

arch/arm64/boot/dts/marvell/armada-37xx.dtsi +4 -8

@@ -75,14 +75,10 @@
 
 	timer {
 		compatible = "arm,armv8-timer";
-		interrupts = <GIC_PPI 13
-			(GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_HIGH)>,
-			     <GIC_PPI 14
-			(GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_HIGH)>,
-			     <GIC_PPI 11
-			(GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_HIGH)>,
-			     <GIC_PPI 10
-			(GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_HIGH)>;
+		interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_PPI 14 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_PPI 10 IRQ_TYPE_LEVEL_HIGH>;
 	};
 
 	soc {

Greg Kroah-Hartman

author maintainer

2017-07-19 10:26 UTC #45 lore raw

PATCH 48/72 vt: fix unchecked __put_user() in tioclinux ioctls

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

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

From: Adam Borowski <[email protected]>

commit 6987dc8a70976561d22450b5858fc9767788cc1c upstream.

Only read access is checked before this call.

Actually, at the moment this is not an issue, as every in-tree arch does the same manual checks for VERIFY_READ vs VERIFY_WRITE, relying on the MMU to tell them apart, but this wasn't the case in the past and may happen again on some odd arch in the future.

If anyone cares about 3.7 and earlier, this is a security hole (untested) on real 80386 CPUs.

Signed-off-by Adam Borowski <[email protected]>

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

---
 drivers/tty/vt/vt.c |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

drivers/tty/vt/vt.c +3 -3

@@ -2711,13 +2711,13 @@ int tioclinux(struct tty_struct *tty, un
 	 * related to the kernel should not use this.
 	 */
 			data = vt_get_shift_state();
-			ret = __put_user(data, p);
+			ret = put_user(data, p);
 			break;
 		case TIOCL_GETMOUSEREPORTING:
 			console_lock();	/* May be overkill */
 			data = mouse_reporting();
 			console_unlock();
-			ret = __put_user(data, p);
+			ret = put_user(data, p);
 			break;
 		case TIOCL_SETVESABLANK:
 			console_lock();

@@ -2726,7 +2726,7 @@ int tioclinux(struct tty_struct *tty, un
 			break;
 		case TIOCL_GETKMSGREDIRECT:
 			data = vt_get_kmsg_redirect();
-			ret = __put_user(data, p);
+			ret = put_user(data, p);
 			break;
 		case TIOCL_SETKMSGREDIRECT:
 			if (!capable(CAP_SYS_ADMIN)) {

Greg Kroah-Hartman

author maintainer

2017-07-19 10:24 UTC #46 lore raw

PATCH 49/72 rcu: Add memory barriers for NOCB leader wakeup

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

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

From: Paul E. McKenney <[email protected]>

commit 6b5fc3a1331810db407c9e0e673dc1837afdc9d0 upstream.

Wait/wakeup operations do not guarantee ordering on their own. Instead, either locking or memory barriers are required. This commit therefore adds memory barriers to wake_nocb_leader() and nocb_leader_wait().

Signed-off-by Paul E. McKenney <[email protected]>

Tested-by Krister Johansen <[email protected]>

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

---
 kernel/rcu/tree_plugin.h |    2 ++
 1 file changed, 2 insertions(+)

kernel/rcu/tree_plugin.h +2 -0

@@ -1767,6 +1767,7 @@ static void wake_nocb_leader(struct rcu_
 	if (READ_ONCE(rdp_leader->nocb_leader_sleep) || force) {
 		/* Prior smp_mb__after_atomic() orders against prior enqueue. */
 		WRITE_ONCE(rdp_leader->nocb_leader_sleep, false);
+		smp_mb(); /* ->nocb_leader_sleep before swake_up(). */
 		swake_up(&rdp_leader->nocb_wq);
 	}
 }

@@ -2021,6 +2022,7 @@ wait_again:
 	 * nocb_gp_head, where they await a grace period.
 	 */
 	gotcbs = false;
+	smp_mb(); /* wakeup before ->nocb_head reads. */
 	for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) {
 		rdp->nocb_gp_head = READ_ONCE(rdp->nocb_head);
 		if (!rdp->nocb_gp_head)

Greg Kroah-Hartman

author maintainer

2017-07-19 10:27 UTC #47 lore raw

PATCH 50/72 nvmem: core: fix leaks on registration errors

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

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

From: Johan Hovold <[email protected]>

commit 3360acdf839170b612f5b212539694c20e3f16d0 upstream.

Make sure to deregister and release the nvmem device and underlying memory on registration errors.

Note that the private data must be freed using put_device() once the struct device has been initialised.

Also note that there's a related reference leak in the deregistration function as reported by Mika Westerberg which is being fixed separately.

Fixes b6c217ab9be6 ("nvmem: Add backwards compatibility support for older EEPROM drivers.")

Fixes eace75cfdcf7 ("nvmem: Add a simple NVMEM framework for nvmem providers")

Cc Andrew Lunn <[email protected]>

Cc Srinivas Kandagatla <[email protected]>

Cc Mika Westerberg <[email protected]>

Signed-off-by Johan Hovold <[email protected]>

Acked-by Andrey Smirnov <[email protected]>

Signed-off-by Srinivas Kandagatla <[email protected]>

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

---
 drivers/nvmem/core.c |   13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

drivers/nvmem/core.c +8 -5

@@ -488,21 +488,24 @@ struct nvmem_device *nvmem_register(cons
 
 	rval = device_add(&nvmem->dev);
 	if (rval)
-		goto out;
+		goto err_put_device;
 
 	if (config->compat) {
 		rval = nvmem_setup_compat(nvmem, config);
 		if (rval)
-			goto out;
+			goto err_device_del;
 	}
 
 	if (config->cells)
 		nvmem_add_cells(nvmem, config);
 
 	return nvmem;
-out:
-	ida_simple_remove(&nvmem_ida, nvmem->id);
-	kfree(nvmem);
+
+err_device_del:
+	device_del(&nvmem->dev);
+err_put_device:
+	put_device(&nvmem->dev);
+
 	return ERR_PTR(rval);
 }
 EXPORT_SYMBOL_GPL(nvmem_register);

Greg Kroah-Hartman

author maintainer

2017-07-19 10:24 UTC #48 lore raw

PATCH 51/72 mnt: In umount propagation reparent in a separate pass

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

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

From: Eric W. Biederman <[email protected]>

commit 570487d3faf2a1d8a220e6ee10f472163123d7da upstream.

It was observed that in some pathlogical cases that the current code does not unmount everything it should. After investigation it was determined that the issue is that mnt_change_mntpoint can can change which mounts are available to be unmounted during mount propagation which is wrong.

The trivial reproducer is:

$ cat ./pathological.sh

mount -t tmpfs test-base /mnt
cd /mnt
mkdir 1 2 1/1
mount --bind 1 1
mount --make-shared 1
mount --bind 1 2
mount --bind 1/1 1/1
mount --bind 1/1 1/1
echo
grep test-base /proc/self/mountinfo
umount 1/1
echo
grep test-base /proc/self/mountinfo

$ unshare -Urm ./pathological.sh

The expected output looks like:
46 31 0:25 / /mnt rw,relatime - tmpfs test-base rw,uid=1000,gid=1000 47 46 0:25 /1 /mnt/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000 48 46 0:25 /1 /mnt/2 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000 49 54 0:25 /1/1 /mnt/1/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000 50 53 0:25 /1/1 /mnt/2/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000 51 49 0:25 /1/1 /mnt/1/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000 54 47 0:25 /1/1 /mnt/1/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000 53 48 0:25 /1/1 /mnt/2/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000 52 50 0:25 /1/1 /mnt/2/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000

46 31 0:25 / /mnt rw,relatime - tmpfs test-base rw,uid=1000,gid=1000 47 46 0:25 /1 /mnt/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000 48 46 0:25 /1 /mnt/2 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000

The output without the fix looks like:
46 31 0:25 / /mnt rw,relatime - tmpfs test-base rw,uid=1000,gid=1000 47 46 0:25 /1 /mnt/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000 48 46 0:25 /1 /mnt/2 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000 49 54 0:25 /1/1 /mnt/1/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000 50 53 0:25 /1/1 /mnt/2/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000 51 49 0:25 /1/1 /mnt/1/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000 54 47 0:25 /1/1 /mnt/1/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000 53 48 0:25 /1/1 /mnt/2/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000 52 50 0:25 /1/1 /mnt/2/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000

That last mount in the output was in the propgation tree to be unmounted but was missed because the mnt_change_mountpoint changed it's parent before the walk through the mount propagation tree observed it.

Fixes 1064f874abc0 ("mnt: Tuck mounts under others instead of creating shadow/side mounts.")

Acked-by Andrei Vagin <[email protected]>

Reviewed-by Ram Pai <[email protected]>

Signed-off-by "Eric W. Biederman" <[email protected]>

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

---
 fs/mount.h     |    1 +
 fs/namespace.c |    1 +
 fs/pnode.c     |   35 ++++++++++++++++++++++++++++++-----
 3 files changed, 32 insertions(+), 5 deletions(-)

fs/mount.h +1 -0

@@ -58,6 +58,7 @@ struct mount {
 	struct mnt_namespace *mnt_ns;	/* containing namespace */
 	struct mountpoint *mnt_mp;	/* where is it mounted */
 	struct hlist_node mnt_mp_list;	/* list mounts with the same mountpoint */
+	struct list_head mnt_reparent;	/* reparent list entry */
 #ifdef CONFIG_FSNOTIFY
 	struct hlist_head mnt_fsnotify_marks;
 	__u32 mnt_fsnotify_mask;

fs/namespace.c +1 -0

@@ -237,6 +237,7 @@ static struct mount *alloc_vfsmnt(const
 		INIT_LIST_HEAD(&mnt->mnt_slave_list);
 		INIT_LIST_HEAD(&mnt->mnt_slave);
 		INIT_HLIST_NODE(&mnt->mnt_mp_list);
+		INIT_LIST_HEAD(&mnt->mnt_reparent);
 #ifdef CONFIG_FSNOTIFY
 		INIT_HLIST_HEAD(&mnt->mnt_fsnotify_marks);
 #endif

fs/pnode.c +30 -5

@@ -441,7 +441,7 @@ static void mark_umount_candidates(struc
  * NOTE: unmounting 'mnt' naturally propagates to all other mounts its
  * parent propagates to.
  */
-static void __propagate_umount(struct mount *mnt)
+static void __propagate_umount(struct mount *mnt, struct list_head *to_reparent)
 {
 	struct mount *parent = mnt->mnt_parent;
 	struct mount *m;

@@ -466,17 +466,38 @@ static void __propagate_umount(struct mo
 		 */
 		topper = find_topper(child);
 		if (topper)
-			mnt_change_mountpoint(child->mnt_parent, child->mnt_mp,
-					      topper);
+			list_add_tail(&topper->mnt_reparent, to_reparent);
 
-		if (list_empty(&child->mnt_mounts)) {
+		if (topper || list_empty(&child->mnt_mounts)) {
 			list_del_init(&child->mnt_child);
+			list_del_init(&child->mnt_reparent);
 			child->mnt.mnt_flags |= MNT_UMOUNT;
 			list_move_tail(&child->mnt_list, &mnt->mnt_list);
 		}
 	}
 }
 
+static void reparent_mounts(struct list_head *to_reparent)
+{
+	while (!list_empty(to_reparent)) {
+		struct mount *mnt, *parent;
+		struct mountpoint *mp;
+
+		mnt = list_first_entry(to_reparent, struct mount, mnt_reparent);
+		list_del_init(&mnt->mnt_reparent);
+
+		/* Where should this mount be reparented to? */
+		mp = mnt->mnt_mp;
+		parent = mnt->mnt_parent;
+		while (parent->mnt.mnt_flags & MNT_UMOUNT) {
+			mp = parent->mnt_mp;
+			parent = parent->mnt_parent;
+		}
+
+		mnt_change_mountpoint(parent, mp, mnt);
+	}
+}
+
 /*
  * collect all mounts that receive propagation from the mount in @list,
  * and return these additional mounts in the same list.

@@ -487,11 +508,15 @@ static void __propagate_umount(struct mo
 int propagate_umount(struct list_head *list)
 {
 	struct mount *mnt;
+	LIST_HEAD(to_reparent);
 
 	list_for_each_entry_reverse(mnt, list, mnt_list)
 		mark_umount_candidates(mnt);
 
 	list_for_each_entry(mnt, list, mnt_list)
-		__propagate_umount(mnt);
+		__propagate_umount(mnt, &to_reparent);
+
+	reparent_mounts(&to_reparent);
+
 	return 0;
 }

Greg Kroah-Hartman

author maintainer

2017-07-19 10:24 UTC #49 lore raw

PATCH 52/72 mnt: In propgate_umount handle visiting mounts in any order

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

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

From: Eric W. Biederman <[email protected]>

commit 99b19d16471e9c3faa85cad38abc9cbbe04c6d55 upstream.

While investigating some poor umount performance I realized that in the case of overlapping mount trees where some of the mounts are locked the code has been failing to unmount all of the mounts it should have been unmounting.

This failure to unmount all of the necessary
mounts can be reproduced with:

$ cat locked_mounts_test.sh

mount -t tmpfs test-base /mnt
mount --make-shared /mnt
mkdir -p /mnt/b

mount -t tmpfs test1 /mnt/b
mount --make-shared /mnt/b
mkdir -p /mnt/b/10

mount -t tmpfs test2 /mnt/b/10
mount --make-shared /mnt/b/10
mkdir -p /mnt/b/10/20

mount --rbind /mnt/b /mnt/b/10/20

unshare -Urm --propagation unchaged /bin/sh -c 'sleep 5; if [ $(grep test /proc/self/mountinfo | wc -l) -eq 1 ] ; then echo SUCCESS ; else echo FAILURE ; fi' sleep 1
umount -l /mnt/b
wait %%

$ unshare -Urm ./locked_mounts_test.sh

This failure is corrected by removing the prepass that marks mounts that may be umounted.

A first pass is added that umounts mounts if possible and if not sets mount mark if they could be unmounted if they weren't locked and adds them to a list to umount possibilities. This first pass reconsiders the mounts parent if it is on the list of umount possibilities, ensuring that information of umoutability will pass from child to mount parent.

A second pass then walks through all mounts that are umounted and processes their children unmounting them or marking them for reparenting.

A last pass cleans up the state on the mounts that could not be umounted and if applicable reparents them to their first parent that remained mounted.

While a bit longer than the old code this code is much more robust as it allows information to flow up from the leaves and down from the trunk making the order in which mounts are encountered in the umount propgation tree irrelevant.

Fixes 0c56fe31420c ("mnt: Don't propagate unmounts to locked mounts")

Reviewed-by Andrei Vagin <[email protected]>

Signed-off-by "Eric W. Biederman" <[email protected]>

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

---
 fs/mount.h     |    2 
 fs/namespace.c |    2 
 fs/pnode.c     |  150 +++++++++++++++++++++++++++++++++------------------------
 3 files changed, 91 insertions(+), 63 deletions(-)

fs/mount.h +1 -1

@@ -58,7 +58,7 @@ struct mount {
 	struct mnt_namespace *mnt_ns;	/* containing namespace */
 	struct mountpoint *mnt_mp;	/* where is it mounted */
 	struct hlist_node mnt_mp_list;	/* list mounts with the same mountpoint */
-	struct list_head mnt_reparent;	/* reparent list entry */
+	struct list_head mnt_umounting; /* list entry for umount propagation */
 #ifdef CONFIG_FSNOTIFY
 	struct hlist_head mnt_fsnotify_marks;
 	__u32 mnt_fsnotify_mask;

fs/namespace.c +1 -1

@@ -237,7 +237,7 @@ static struct mount *alloc_vfsmnt(const
 		INIT_LIST_HEAD(&mnt->mnt_slave_list);
 		INIT_LIST_HEAD(&mnt->mnt_slave);
 		INIT_HLIST_NODE(&mnt->mnt_mp_list);
-		INIT_LIST_HEAD(&mnt->mnt_reparent);
+		INIT_LIST_HEAD(&mnt->mnt_umounting);
 #ifdef CONFIG_FSNOTIFY
 		INIT_HLIST_HEAD(&mnt->mnt_fsnotify_marks);
 #endif

fs/pnode.c +89 ~~-61~~

190 lines not on this page · raw message

Greg Kroah-Hartman

author maintainer

2017-07-19 10:27 UTC #50 lore raw

PATCH 53/72 mnt: Make propagate_umount less slow for overlapping mount propagation trees

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

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

From: Eric W. Biederman <[email protected]>

commit 296990deb389c7da21c78030376ba244dc1badf5 upstream.

Andrei Vagin pointed out that time to executue propagate_umount can go non-linear (and take a ludicrious amount of time) when the mount propogation trees of the mounts to be unmunted by a lazy unmount overlap.

Make the walk of the mount propagation trees nearly linear by remembering which mounts have already been visited, allowing subsequent walks to detect when walking a mount propgation tree or a subtree of a mount propgation tree would be duplicate work and to skip them entirely.

Walk the list of mounts whose propgatation trees need to be traversed from the mount highest in the mount tree to mounts lower in the mount tree so that odds are higher that the code will walk the largest trees first, allowing later tree walks to be skipped entirely.

Add cleanup_umount_visitation to remover the code's memory of which mounts have been visited.

Add the functions last_slave and skip_propagation_subtree to allow skipping appropriate parts of the mount propagation tree without needing to change the logic of the rest of the code.

A script to generate overlapping mount propagation trees:

$ cat runs.h
set -e
mount -t tmpfs zdtm /mnt
mkdir -p /mnt/1 /mnt/2
mount -t tmpfs zdtm /mnt/1
mount --make-shared /mnt/1
mkdir /mnt/1/1

iteration=10
if [ -n "$1" ] ; then
iteration=$1
fi

for i in $(seq $iteration); do

	mount --bind /mnt/1/1 /mnt/1/1

done

mount --rbind /mnt/1 /mnt/2

TIMEFORMAT='%Rs'
nr=$(( ( 2 ** ( $iteration + 1 ) ) + 1 ))
echo -n "umount -l /mnt/1 -> $nr "
time umount -l /mnt/1

nr=$(cat /proc/self/mountinfo | grep zdtm | wc -l ) time umount -l /mnt/2

$ for i in $(seq 9 19); do echo $i; unshare -Urm bash ./run.sh $i; done

Here are the performance numbers with and without the patch:

     mhash |  8192   |  8192  | 1048576 | 1048576
    mounts | before  | after  |  before | after
    ------------------------------------------------
      1025 |  0.040s | 0.016s |  0.038s | 0.019s
      2049 |  0.094s | 0.017s |  0.080s | 0.018s
      4097 |  0.243s | 0.019s |  0.206s | 0.023s
      8193 |  1.202s | 0.028s |  1.562s | 0.032s
     16385 |  9.635s | 0.036s |  9.952s | 0.041s
     32769 | 60.928s | 0.063s | 44.321s | 0.064s
     65537 |         | 0.097s |         | 0.097s
    131073 |         | 0.233s |         | 0.176s
    262145 |         | 0.653s |         | 0.344s
    524289 |         | 2.305s |         | 0.735s

1048577 | | 7.107s | | 2.603s

Andrei Vagin reports fixing the performance problem is part of the work to fix CVE-2016-6213.

Fixes a05964f3917c ("[PATCH] shared mounts handling: umount")

Reported-by Andrei Vagin <[email protected]>

Reviewed-by Andrei Vagin <[email protected]>

Signed-off-by "Eric W. Biederman" <[email protected]>

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

---
 fs/pnode.c |   63 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 62 insertions(+), 1 deletion(-)

fs/pnode.c +62 -1

@@ -24,6 +24,11 @@ static inline struct mount *first_slave(
 	return list_entry(p->mnt_slave_list.next, struct mount, mnt_slave);
 }
 
+static inline struct mount *last_slave(struct mount *p)
+{
+	return list_entry(p->mnt_slave_list.prev, struct mount, mnt_slave);
+}
+
 static inline struct mount *next_slave(struct mount *p)
 {
 	return list_entry(p->mnt_slave.next, struct mount, mnt_slave);

@@ -164,6 +169,19 @@ static struct mount *propagation_next(st
 	}
 }
 
+static struct mount *skip_propagation_subtree(struct mount *m,
+						struct mount *origin)
+{
+	/*
+	 * Advance m such that propagation_next will not return
+	 * the slaves of m.
+	 */
+	if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))
+		m = last_slave(m);
+
+	return m;
+}
+
 static struct mount *next_group(struct mount *m, struct mount *origin)
 {
 	while (1) {

@@ -507,6 +525,15 @@ static void restore_mounts(struct list_h
 	}
 }
 
+static void cleanup_umount_visitations(struct list_head *visited)
+{
+	while (!list_empty(visited)) {
+		struct mount *mnt =
+			list_first_entry(visited, struct mount, mnt_umounting);
+		list_del_init(&mnt->mnt_umounting);
+	}
+}
+
 /*
  * collect all mounts that receive propagation from the mount in @list,
  * and return these additional mounts in the same list.

@@ -519,11 +546,23 @@ int propagate_umount(struct list_head *l
 	struct mount *mnt;
 	LIST_HEAD(to_restore);
 	LIST_HEAD(to_umount);
+	LIST_HEAD(visited);
 
-	list_for_each_entry(mnt, list, mnt_list) {
+	/* Find candidates for unmounting */
+	list_for_each_entry_reverse(mnt, list, mnt_list) {
 		struct mount *parent = mnt->mnt_parent;
 		struct mount *m;
 
+		/*
+		 * If this mount has already been visited it is known that it's
+		 * entire peer group and all of their slaves in the propagation
+		 * tree for the mountpoint has already been visited and there is
+		 * no need to visit them again.
+		 */
+		if (!list_empty(&mnt->mnt_umounting))
+			continue;
+
+		list_add_tail(&mnt->mnt_umounting, &visited);
 		for (m = propagation_next(parent, parent); m;
 		     m = propagation_next(m, parent)) {
 			struct mount *child = __lookup_mnt(&m->mnt,

@@ -531,6 +570,27 @@ int propagate_umount(struct list_head *l
 			if (!child)
 				continue;
 
+			if (!list_empty(&child->mnt_umounting)) {
+				/*
+				 * If the child has already been visited it is
+				 * know that it's entire peer group and all of
+				 * their slaves in the propgation tree for the
+				 * mountpoint has already been visited and there
+				 * is no need to visit this subtree again.
+				 */
+				m = skip_propagation_subtree(m, parent);
+				continue;
+			} else if (child->mnt.mnt_flags & MNT_UMOUNT) {
+				/*
+				 * We have come accross an partially unmounted
+				 * mount in list that has not been visited yet.
+				 * Remember it has been visited and continue
+				 * about our merry way.
+				 */
+				list_add_tail(&child->mnt_umounting, &visited);
+				continue;
+			}
+
 			/* Check the child and parents while progress is made */
 			while (__propagate_umount(child,
 						  &to_umount, &to_restore)) {

@@ -544,6 +604,7 @@ int propagate_umount(struct list_head *l
 
 	umount_list(&to_umount, &to_restore);
 	restore_mounts(&to_restore);
+	cleanup_umount_visitations(&visited);
 	list_splice_tail(&to_umount, list);
 
 	return 0;

Greg Kroah-Hartman

author maintainer

2017-07-19 10:27 UTC #51 lore raw

PATCH 54/72 selftests/capabilities: Fix the test_execve test

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

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

From: Andy Lutomirski <[email protected]>

commit 796a3bae2fba6810427efdb314a1c126c9490fb3 upstream.

test_execve does rather odd mount manipulations to safely create temporary setuid and setgid executables that aren't visible to the rest of the system. Those executables end up in the test's cwd, but that cwd is MNT_DETACHed.

The core namespace code considers MNT_DETACHed trees to belong to no mount namespace at all and, in general, MNT_DETACHed trees are only barely function. This interacted with commit 380cf5ba6b0a ("fs:
Treat foreign mounts as nosuid") to cause all MNT_DETACHed trees to act as though they're nosuid, breaking the test.

Fix it by just not detaching the tree. It's still in a private mount namespace and is therefore still invisible to the rest of the system (except via /proc, and the same nosuid logic will protect all other programs on the system from believing in test_execve's setuid bits).

While we're at it, fix some blatant whitespace problems.

Reported-by Naresh Kamboju <[email protected]>

Fixes 380cf5ba6b0a ("fs: Treat foreign mounts as nosuid")

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

Cc Kees Cook <[email protected]>

Cc Shuah Khan <[email protected]>

Cc Greg KH <[email protected]>

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

Acked-by Greg Kroah-Hartman <[email protected]>

Signed-off-by Shuah Khan <[email protected]>

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

---
 tools/testing/selftests/capabilities/test_execve.c |    7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

tools/testing/selftests/capabilities/test_execve.c +2 -5

@@ -138,9 +138,6 @@ static void chdir_to_tmpfs(void)
 
 	if (chdir(cwd) != 0)
 		err(1, "chdir to private tmpfs");
-
-	if (umount2(".", MNT_DETACH) != 0)
-		err(1, "detach private tmpfs");
 }
 
 static void copy_fromat_to(int fromfd, const char *fromname, const char *toname)

@@ -248,7 +245,7 @@ static int do_tests(int uid, const char
 			err(1, "chown");
 		if (chmod("validate_cap_sgidnonroot", S_ISGID | 0710) != 0)
 			err(1, "chmod");
-}
+	}
 
 	capng_get_caps_process();

@@ -384,7 +381,7 @@ static int do_tests(int uid, const char
 	} else {
 		printf("[RUN]\tNon-root +ia, sgidnonroot => i\n");
 		exec_other_validate_cap("./validate_cap_sgidnonroot",
-						false, false, true, false);
+					false, false, true, false);
 
 		if (fork_wait()) {
 			printf("[RUN]\tNon-root +ia, sgidroot => i\n");

Greg Kroah-Hartman

author maintainer

2017-07-19 10:27 UTC #52 lore raw

PATCH 57/72 crypto: atmel - only treat EBUSY as transient if backlog

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

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

From: Gilad Ben-Yossef <[email protected]>

commit 1606043f214f912a52195293614935811a6e3e53 upstream.

The Atmel SHA driver was treating -EBUSY as indication of queueing to backlog without checking that backlog is enabled for the request.

Fix it by checking request flags.

Signed-off-by Gilad Ben-Yossef <[email protected]>

Signed-off-by Herbert Xu <[email protected]>

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

---
 drivers/crypto/atmel-sha.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

drivers/crypto/atmel-sha.c +3 -1

@@ -1000,7 +1000,9 @@ static int atmel_sha_finup(struct ahash_
 	ctx->flags |= SHA_FLAGS_FINUP;
 
 	err1 = atmel_sha_update(req);
-	if (err1 == -EINPROGRESS || err1 == -EBUSY)
+	if (err1 == -EINPROGRESS ||
+	    (err1 == -EBUSY && (ahash_request_flags(req) &
+				CRYPTO_TFM_REQ_MAY_BACKLOG)))
 		return err1;
 
 	/*

Greg Kroah-Hartman

author maintainer

2017-07-19 10:27 UTC #53 lore raw

PATCH 58/72 crypto: sha1-ssse3 - Disable avx2

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

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

From: Herbert Xu <[email protected]>

commit b82ce24426a4071da9529d726057e4e642948667 upstream.

It has been reported that sha1-avx2 can cause page faults by reading beyond the end of the input. This patch disables it until it can be fixed.

Fixes 7c1da8d0d046 ("crypto: sha - SHA1 transform x86_64 AVX2")

Reported-by Jan Stancek <[email protected]>

Signed-off-by Herbert Xu <[email protected]>

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

---
 arch/x86/crypto/sha1_ssse3_glue.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

arch/x86/crypto/sha1_ssse3_glue.c +1 -1

@@ -201,7 +201,7 @@ asmlinkage void sha1_transform_avx2(u32
 
 static bool avx2_usable(void)
 {
-	if (avx_usable() && boot_cpu_has(X86_FEATURE_AVX2)
+	if (false && avx_usable() && boot_cpu_has(X86_FEATURE_AVX2)
 		&& boot_cpu_has(X86_FEATURE_BMI1)
 		&& boot_cpu_has(X86_FEATURE_BMI2))
 		return true;

Greg Kroah-Hartman

author maintainer

2017-07-19 10:24 UTC #54 lore raw

PATCH 61/72 Revert "sched/core: Optimize SCHED_SMT"

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

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

From: Greg Kroah-Hartman <[email protected]>

This reverts commit 1b568f0aabf280555125bc7cefc08321ff0ebaba.

For the 4.9 kernel tree, this patch causes scheduler regressions. It is fixed in newer kernels with a large number of individual patches, the sum of which is too big for the stable kernel tree.

Ingo recommended just reverting the single patch for this tree, as it's much simpler.

Reported-by Ben Guthro <[email protected]>

Cc Ingo Molnar <[email protected]>

Cc Peter Zijlstra <[email protected]>

Cc Linus Torvalds <[email protected]>

Cc Mike Galbraith <[email protected]>

Cc Thomas Gleixner <[email protected]>

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

---
 kernel/sched/core.c  |   19 -------------------
 kernel/sched/fair.c  |    8 +-------
 kernel/sched/sched.h |   23 ++++++-----------------
 3 files changed, 7 insertions(+), 43 deletions(-)

kernel/sched/core.c +0 ~~-19~~

@@ -7422,22 +7422,6 @@ int sched_cpu_dying(unsigned int cpu)
 }
 #endif
 
-#ifdef CONFIG_SCHED_SMT
-DEFINE_STATIC_KEY_FALSE(sched_smt_present);
-
-static void sched_init_smt(void)
-{
-	/*
-	 * We've enumerated all CPUs and will assume that if any CPU
-	 * has SMT siblings, CPU0 will too.
-	 */
-	if (cpumask_weight(cpu_smt_mask(0)) > 1)
-		static_branch_enable(&sched_smt_present);
-}
-#else
-static inline void sched_init_smt(void) { }
-#endif
-
 void __init sched_init_smp(void)
 {
 	cpumask_var_t non_isolated_cpus;

@@ -7467,9 +7451,6 @@ void __init sched_init_smp(void)
 
 	init_sched_rt_class();
 	init_sched_dl_class();
-
-	sched_init_smt();
-
 	sched_smp_initialized = true;
 }

kernel/sched/fair.c +1 -7

@@ -5376,7 +5376,7 @@ static inline bool test_idle_cores(int c
  * Since SMT siblings share all cache levels, inspecting this limited remote
  * state should be fairly cheap.
  */
-void __update_idle_core(struct rq *rq)
+void update_idle_core(struct rq *rq)
 {
 	int core = cpu_of(rq);
 	int cpu;

@@ -5408,9 +5408,6 @@ static int select_idle_core(struct task_
 	struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
 	int core, cpu, wrap;
 
-	if (!static_branch_likely(&sched_smt_present))
-		return -1;
-
 	if (!test_idle_cores(target, false))
 		return -1;

@@ -5444,9 +5441,6 @@ static int select_idle_smt(struct task_s
 {
 	int cpu;
 
-	if (!static_branch_likely(&sched_smt_present))
-		return -1;
-
 	for_each_cpu(cpu, cpu_smt_mask(target)) {
 		if (!cpumask_test_cpu(cpu, tsk_cpus_allowed(p)))
 			continue;

kernel/sched/sched.h +6 ~~-17~~

@@ -43,6 +43,12 @@ extern void cpu_load_update_active(struc
 static inline void cpu_load_update_active(struct rq *this_rq) { }
 #endif
 
+#ifdef CONFIG_SCHED_SMT
+extern void update_idle_core(struct rq *rq);
+#else
+static inline void update_idle_core(struct rq *rq) { }
+#endif
+
 /*
  * Helpers for converting nanosecond timing to jiffy resolution
  */

@@ -731,23 +737,6 @@ static inline int cpu_of(struct rq *rq)
 #endif
 }
 
-
-#ifdef CONFIG_SCHED_SMT
-
-extern struct static_key_false sched_smt_present;
-
-extern void __update_idle_core(struct rq *rq);
-
-static inline void update_idle_core(struct rq *rq)
-{
-	if (static_branch_unlikely(&sched_smt_present))
-		__update_idle_core(rq);
-}
-
-#else
-static inline void update_idle_core(struct rq *rq) { }
-#endif
-
 DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
 #define cpu_rq(cpu)		(&per_cpu(runqueues, (cpu)))

Greg Kroah-Hartman

author maintainer

2017-07-19 10:27 UTC #55 lore raw

PATCH 62/72 sched/fair, cpumask: Export for_each_cpu_wrap()

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

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

From: Peter Zijlstra <[email protected]>

commit c6508a39640b9a27fc2bc10cb708152672c82045 upstream.

commit c743f0a5c50f2fcbc628526279cfa24f3dabe182 upstream.

More users for for_each_cpu_wrap() have appeared. Promote the construct to generic cpumask interface.

The implementation is slightly modified to reduce arguments.

Signed-off-by Peter Zijlstra (Intel) <[email protected]>

Cc Lauro Ramos Venancio <[email protected]>

Cc Linus Torvalds <[email protected]>

Cc Mike Galbraith <[email protected]>

Cc Peter Zijlstra <[email protected]>

Cc Rik van Riel <[email protected]>

Cc Thomas Gleixner <[email protected]>

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

Signed-off-by Ingo Molnar <[email protected]>

Signed-off-by Mel Gorman <[email protected]>

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

---
 include/linux/cpumask.h |   17 +++++++++++++++++
 kernel/sched/fair.c     |   45 ++++-----------------------------------------
 lib/cpumask.c           |   32 ++++++++++++++++++++++++++++++++
 3 files changed, 53 insertions(+), 41 deletions(-)

include/linux/cpumask.h +17 -0

@@ -236,6 +236,23 @@ unsigned int cpumask_local_spread(unsign
 		(cpu) = cpumask_next_zero((cpu), (mask)),	\
 		(cpu) < nr_cpu_ids;)
 
+extern int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap);
+
+/**
+ * for_each_cpu_wrap - iterate over every cpu in a mask, starting at a specified location
+ * @cpu: the (optionally unsigned) integer iterator
+ * @mask: the cpumask poiter
+ * @start: the start location
+ *
+ * The implementation does not assume any bit in @mask is set (including @start).
+ *
+ * After the loop, cpu is >= nr_cpu_ids.
+ */
+#define for_each_cpu_wrap(cpu, mask, start)					\
+	for ((cpu) = cpumask_next_wrap((start)-1, (mask), (start), false);	\
+	     (cpu) < nr_cpumask_bits;						\
+	     (cpu) = cpumask_next_wrap((cpu), (mask), (start), true))
+
 /**
  * for_each_cpu_and - iterate over every cpu in both masks
  * @cpu: the (optionally unsigned) integer iterator

kernel/sched/fair.c +4 ~~-41~~

75 lines not on this page · raw message

lib/cpumask.c +32 -0

@@ -43,6 +43,38 @@ int cpumask_any_but(const struct cpumask
 }
 EXPORT_SYMBOL(cpumask_any_but);
 
+/**
+ * cpumask_next_wrap - helper to implement for_each_cpu_wrap
+ * @n: the cpu prior to the place to search
+ * @mask: the cpumask pointer
+ * @start: the start point of the iteration
+ * @wrap: assume @n crossing @start terminates the iteration
+ *
+ * Returns >= nr_cpu_ids on completion
+ *
+ * Note: the @wrap argument is required for the start condition when
+ * we cannot assume @start is set in @mask.
+ */
+int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap)
+{
+	int next;
+
+again:
+	next = cpumask_next(n, mask);
+
+	if (wrap && n < start && next >= start) {
+		return nr_cpumask_bits;
+
+	} else if (next >= nr_cpumask_bits) {
+		wrap = true;
+		n = -1;
+		goto again;
+	}
+
+	return next;
+}
+EXPORT_SYMBOL(cpumask_next_wrap);
+
 /* These are not inline because of header tangles. */
 #ifdef CONFIG_CPUMASK_OFFSTACK
 /**

Greg Kroah-Hartman

author maintainer

2017-07-19 10:27 UTC #56 lore raw

PATCH 63/72 sched/topology: Fix building of overlapping sched-groups

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

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

From: Peter Zijlstra <[email protected]>

commit 0372dd2736e02672ac6e189c31f7d8c02ad543cd upstream.

When building the overlapping groups, we very obviously should start with the previous domain of _this_ @cpu, not CPU-0.

This can be readily demonstrated with a topology like:

node 0 1 2 3

    0:  10  20  30  20
    1:  20  10  20  30
    2:  30  20  10  20
    3:  20  30  20  10

Where (for example) CPU1 ends up generating the following nonsensical groups:

[] CPU1 attaching sched-domain:
[] domain 0: span 0-2 level NUMA
[] groups: 1 2 0
[] domain 1: span 0-3 level NUMA
[] groups: 1-3 (cpu_capacity = 3072) 0-1,3 (cpu_capacity = 3072)

Where the fact that domain 1 doesn't include a group with span 0-2 is the obvious fail.

With patch this looks like:

[] CPU1 attaching sched-domain:
[] domain 0: span 0-2 level NUMA
[] groups: 1 0 2
[] domain 1: span 0-3 level NUMA
[] groups: 0-2 (cpu_capacity = 3072) 0,2-3 (cpu_capacity = 3072)

Debugged-by Lauro Ramos Venancio <[email protected]>

Signed-off-by Peter Zijlstra (Intel) <[email protected]>

Cc Linus Torvalds <[email protected]>

Cc Mike Galbraith <[email protected]>

Cc Peter Zijlstra <[email protected]>

Cc Thomas Gleixner <[email protected]>

Fixes e3589f6c81e4 ("sched: Allow for overlapping sched_domain spans")

Signed-off-by Ingo Molnar <[email protected]>

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

---
 kernel/sched/core.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

kernel/sched/core.c +1 -1

@@ -6148,7 +6148,7 @@ build_overlap_sched_groups(struct sched_
 
 	cpumask_clear(covered);
 
-	for_each_cpu(i, span) {
+	for_each_cpu_wrap(i, span, cpu) {
 		struct cpumask *sg_span;
 
 		if (cpumask_test_cpu(i, covered))

Greg Kroah-Hartman

author maintainer

2017-07-19 10:27 UTC #57 lore raw

PATCH 64/72 sched/topology: Optimize build_group_mask()

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

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

From: Lauro Ramos Venancio <[email protected]>

commit f32d782e31bf079f600dcec126ed117b0577e85c upstream.

The group mask is always used in intersection with the group CPUs. So, when building the group mask, we don't have to care about CPUs that are not part of the group.

Signed-off-by Lauro Ramos Venancio <[email protected]>

Signed-off-by Peter Zijlstra (Intel) <[email protected]>

Cc Linus Torvalds <[email protected]>

Cc Mike Galbraith <[email protected]>

Cc Peter Zijlstra <[email protected]>

Cc Thomas Gleixner <[email protected]>

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

kernel/sched/core.c +2 -2

@@ -6113,12 +6113,12 @@ enum s_alloc {
  */
 static void build_group_mask(struct sched_domain *sd, struct sched_group *sg)
 {
-	const struct cpumask *span = sched_domain_span(sd);
+	const struct cpumask *sg_span = sched_group_cpus(sg);
 	struct sd_data *sdd = sd->private;
 	struct sched_domain *sibling;
 	int i;
 
-	for_each_cpu(i, span) {
+	for_each_cpu(i, sg_span) {
 		sibling = *per_cpu_ptr(sdd->sd, i);
 		if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
 			continue;

Greg Kroah-Hartman

author maintainer

2017-07-19 10:24 UTC #58 lore raw

PATCH 65/72 sched/topology: Fix overlapping sched_group_mask

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

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

From: Peter Zijlstra <[email protected]>

commit 73bb059f9b8a00c5e1bf2f7ca83138c05d05e600 upstream.

The point of sched_group_mask is to select those CPUs from sched_group_cpus that can actually arrive at this balance domain.

The current code gets it wrong, as can be readily demonstrated with a topology like:

node 0 1 2 3

    0:  10  20  30  20
    1:  20  10  20  30
    2:  30  20  10  20
    3:  20  30  20  10

Where (for example) domain 1 on CPU1 ends up with a mask that includes CPU0:

[] CPU1 attaching sched-domain:
[] domain 0: span 0-2 level NUMA
[] groups: 1 (mask: 1), 2, 0
[] domain 1: span 0-3 level NUMA
[] groups: 0-2 (mask: 0-2) (cpu_capacity: 3072), 0,2-3 (cpu_capacity: 3072)

This causes sched_balance_cpu() to compute the wrong CPU and consequently should_we_balance() will terminate early resulting in missed load-balance opportunities.

The fixed topology looks like:

[] CPU1 attaching sched-domain:
[] domain 0: span 0-2 level NUMA
[] groups: 1 (mask: 1), 2, 0
[] domain 1: span 0-3 level NUMA
[] groups: 0-2 (mask: 1) (cpu_capacity: 3072), 0,2-3 (cpu_capacity: 3072)

(note: this relies on OVERLAP domains to always have children, this is
true because the regular topology domains are still here -- this is before degenerate trimming)

Debugged-by Lauro Ramos Venancio <[email protected]>

Signed-off-by Peter Zijlstra (Intel) <[email protected]>

Cc Linus Torvalds <[email protected]>

Cc Mike Galbraith <[email protected]>

Cc Peter Zijlstra <[email protected]>

Cc Thomas Gleixner <[email protected]>

Fixes e3589f6c81e4 ("sched: Allow for overlapping sched_domain spans")

Signed-off-by Ingo Molnar <[email protected]>

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

---
 kernel/sched/core.c |   18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

kernel/sched/core.c +17 -1

@@ -6102,6 +6102,9 @@ enum s_alloc {
  * Build an iteration mask that can exclude certain CPUs from the upwards
  * domain traversal.
  *
+ * Only CPUs that can arrive at this group should be considered to continue
+ * balancing.
+ *
  * Asymmetric node setups can result in situations where the domain tree is of
  * unequal depth, make sure to skip domains that already cover the entire
  * range.

@@ -6120,11 +6123,24 @@ static void build_group_mask(struct sche
 
 	for_each_cpu(i, sg_span) {
 		sibling = *per_cpu_ptr(sdd->sd, i);
-		if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
+
+		/*
+		 * Can happen in the asymmetric case, where these siblings are
+		 * unused. The mask will not be empty because those CPUs that
+		 * do have the top domain _should_ span the domain.
+		 */
+		if (!sibling->child)
+			continue;
+
+		/* If we would not end up here, we can't continue from here */
+		if (!cpumask_equal(sg_span, sched_domain_span(sibling->child)))
 			continue;
 
 		cpumask_set_cpu(i, sched_group_mask(sg));
 	}
+
+	/* We must not have empty masks here */
+	WARN_ON_ONCE(cpumask_empty(sched_group_mask(sg)));
 }
 
 /*

Greg Kroah-Hartman

author maintainer

2017-07-19 10:27 UTC #59 lore raw

PATCH 66/72 PM / wakeirq: Convert to SRCU

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

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

From: Thomas Gleixner <[email protected]>

commit ea0212f40c6bc0594c8eff79266759e3ecd4bacc upstream.

The wakeirq infrastructure uses RCU to protect the list of wakeirqs. That breaks the irq bus locking infrastructure, which is allows sleeping functions to be called so interrupt controllers behind slow busses, e.g. i2c, can be handled.

The wakeirq functions hold rcu_read_lock and call into irq functions, which in case of interrupts using the irq bus locking will trigger a might_sleep() splat.

Convert the wakeirq infrastructure to Sleepable RCU and unbreak it.

Fixes 4990d4fe327b (PM / Wakeirq: Add automated device wake IRQ handling)

Reported-by Brian Norris <[email protected]>

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

Reviewed-by Paul E. McKenney <[email protected]>

Tested-by Tony Lindgren <[email protected]>

Tested-by Brian Norris <[email protected]>

Signed-off-by Rafael J. Wysocki <[email protected]>

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

---
 drivers/base/power/wakeup.c |   32 ++++++++++++++++++--------------
 1 file changed, 18 insertions(+), 14 deletions(-)

drivers/base/power/wakeup.c +18 ~~-14~~

@@ -60,6 +60,8 @@ static LIST_HEAD(wakeup_sources);
 
 static DECLARE_WAIT_QUEUE_HEAD(wakeup_count_wait_queue);
 
+DEFINE_STATIC_SRCU(wakeup_srcu);
+
 static struct wakeup_source deleted_ws = {
 	.name = "deleted",
 	.lock =  __SPIN_LOCK_UNLOCKED(deleted_ws.lock),

@@ -198,7 +200,7 @@ void wakeup_source_remove(struct wakeup_
 	spin_lock_irqsave(&events_lock, flags);
 	list_del_rcu(&ws->entry);
 	spin_unlock_irqrestore(&events_lock, flags);
-	synchronize_rcu();
+	synchronize_srcu(&wakeup_srcu);
 }
 EXPORT_SYMBOL_GPL(wakeup_source_remove);

@@ -332,12 +334,12 @@ void device_wakeup_detach_irq(struct dev
 void device_wakeup_arm_wake_irqs(void)
 {
 	struct wakeup_source *ws;
+	int srcuidx;
 
-	rcu_read_lock();
+	srcuidx = srcu_read_lock(&wakeup_srcu);
 	list_for_each_entry_rcu(ws, &wakeup_sources, entry)
 		dev_pm_arm_wake_irq(ws->wakeirq);
-
-	rcu_read_unlock();
+	srcu_read_unlock(&wakeup_srcu, srcuidx);
 }
 
 /**

@@ -348,12 +350,12 @@ void device_wakeup_arm_wake_irqs(void)
 void device_wakeup_disarm_wake_irqs(void)
 {
 	struct wakeup_source *ws;
+	int srcuidx;
 
-	rcu_read_lock();
+	srcuidx = srcu_read_lock(&wakeup_srcu);
 	list_for_each_entry_rcu(ws, &wakeup_sources, entry)
 		dev_pm_disarm_wake_irq(ws->wakeirq);
-
-	rcu_read_unlock();
+	srcu_read_unlock(&wakeup_srcu, srcuidx);
 }
 
 /**

@@ -805,10 +807,10 @@ EXPORT_SYMBOL_GPL(pm_wakeup_event);
 void pm_print_active_wakeup_sources(void)
 {
 	struct wakeup_source *ws;
-	int active = 0;
+	int srcuidx, active = 0;
 	struct wakeup_source *last_activity_ws = NULL;
 
-	rcu_read_lock();
+	srcuidx = srcu_read_lock(&wakeup_srcu);
 	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
 		if (ws->active) {
 			pr_info("active wakeup source: %s\n", ws->name);

@@ -824,7 +826,7 @@ void pm_print_active_wakeup_sources(void
 	if (!active && last_activity_ws)
 		pr_info("last active wakeup source: %s\n",
 			last_activity_ws->name);
-	rcu_read_unlock();
+	srcu_read_unlock(&wakeup_srcu, srcuidx);
 }
 EXPORT_SYMBOL_GPL(pm_print_active_wakeup_sources);

@@ -951,8 +953,9 @@ void pm_wakep_autosleep_enabled(bool set
 {
 	struct wakeup_source *ws;
 	ktime_t now = ktime_get();
+	int srcuidx;
 
-	rcu_read_lock();
+	srcuidx = srcu_read_lock(&wakeup_srcu);
 	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
 		spin_lock_irq(&ws->lock);
 		if (ws->autosleep_enabled != set) {

@@ -966,7 +969,7 @@ void pm_wakep_autosleep_enabled(bool set
 		}
 		spin_unlock_irq(&ws->lock);
 	}
-	rcu_read_unlock();
+	srcu_read_unlock(&wakeup_srcu, srcuidx);
 }
 #endif /* CONFIG_PM_AUTOSLEEP */

@@ -1027,15 +1030,16 @@ static int print_wakeup_source_stats(str
 static int wakeup_sources_stats_show(struct seq_file *m, void *unused)
 {
 	struct wakeup_source *ws;
+	int srcuidx;
 
 	seq_puts(m, "name\t\tactive_count\tevent_count\twakeup_count\t"
 		"expire_count\tactive_since\ttotal_time\tmax_time\t"
 		"last_change\tprevent_suspend_time\n");
 
-	rcu_read_lock();
+	srcuidx = srcu_read_lock(&wakeup_srcu);
 	list_for_each_entry_rcu(ws, &wakeup_sources, entry)
 		print_wakeup_source_stats(m, ws);
-	rcu_read_unlock();
+	srcu_read_unlock(&wakeup_srcu, srcuidx);
 
 	print_wakeup_source_stats(m, &deleted_ws);

Greg Kroah-Hartman

author maintainer

2017-07-19 10:27 UTC #60 lore raw

PATCH 67/72 PM / QoS: return -EINVAL for bogus strings

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

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

From: Dan Carpenter <[email protected]>

commit 2ca30331c156ca9e97643ad05dd8930b8fe78b01 upstream.

In the current code, if the user accidentally writes a bogus command to this sysfs file, then we set the latency tolerance to an uninitialized variable.

Fixes 2d984ad132a8 (PM / QoS: Introcuce latency tolerance device PM QoS type)

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

Acked-by Pavel Machek <[email protected]>

Signed-off-by Rafael J. Wysocki <[email protected]>

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

---
 drivers/base/power/sysfs.c |    2 ++
 1 file changed, 2 insertions(+)

drivers/base/power/sysfs.c +2 -0

@@ -268,6 +268,8 @@ static ssize_t pm_qos_latency_tolerance_
 			value = PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT;
 		else if (!strcmp(buf, "any") || !strcmp(buf, "any\n"))
 			value = PM_QOS_LATENCY_ANY;
+		else
+			return -EINVAL;
 	}
 	ret = dev_pm_qos_update_user_latency_tolerance(dev, value);
 	return ret < 0 ? ret : n;

Greg Kroah-Hartman

author maintainer

2017-07-19 10:27 UTC #61 lore raw

PATCH 68/72 tracing: Use SOFTIRQ_OFFSET for softirq dectection for more accurate results

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

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

From: Pavankumar Kondeti <[email protected]>

commit c59f29cb144a6a0dfac16ede9dc8eafc02dc56ca upstream.

The 's' flag is supposed to indicate that a softirq is running. This can be detected by testing the preempt_count with SOFTIRQ_OFFSET.

The current code tests the preempt_count with SOFTIRQ_MASK, which would be true even when softirqs are disabled but not serving a softirq.

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

Signed-off-by Pavankumar Kondeti <[email protected]>

Signed-off-by Steven Rostedt <[email protected]>

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

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

---
 kernel/trace/trace.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

kernel/trace/trace.c +1 -1

@@ -1906,7 +1906,7 @@ tracing_generic_entry_update(struct trac
 #endif
 		((pc & NMI_MASK    ) ? TRACE_FLAG_NMI     : 0) |
 		((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) |
-		((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) |
+		((pc & SOFTIRQ_OFFSET) ? TRACE_FLAG_SOFTIRQ : 0) |
 		(tif_need_resched() ? TRACE_FLAG_NEED_RESCHED : 0) |
 		(test_preempt_need_resched() ? TRACE_FLAG_PREEMPT_RESCHED : 0);
 }

Greg Kroah-Hartman

author maintainer

2017-07-19 10:25 UTC #62 lore raw

PATCH 72/72 kvm: vmx: allow host to access guest MSR_IA32_BNDCFGS

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

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

From: Haozhong Zhang <[email protected]>

commit 691bd4340bef49cf7e5855d06cf24444b5bf2d85 upstream.

It's easier for host applications, such as QEMU, if they can always access guest MSR_IA32_BNDCFGS in VMCS, even though MPX is disabled in guest cpuid.

Signed-off-by Haozhong Zhang <[email protected]>

Signed-off-by Paolo Bonzini <[email protected]>

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

---
 arch/x86/kvm/vmx.c |    6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

arch/x86/kvm/vmx.c +4 -2

@@ -2987,7 +2987,8 @@ static int vmx_get_msr(struct kvm_vcpu *
 		msr_info->data = vmcs_readl(GUEST_SYSENTER_ESP);
 		break;
 	case MSR_IA32_BNDCFGS:
-		if (!kvm_mpx_supported() || !guest_cpuid_has_mpx(vcpu))
+		if (!kvm_mpx_supported() ||
+		    (!msr_info->host_initiated && !guest_cpuid_has_mpx(vcpu)))
 			return 1;
 		msr_info->data = vmcs_read64(GUEST_BNDCFGS);
 		break;

@@ -3069,7 +3070,8 @@ static int vmx_set_msr(struct kvm_vcpu *
 		vmcs_writel(GUEST_SYSENTER_ESP, data);
 		break;
 	case MSR_IA32_BNDCFGS:
-		if (!kvm_mpx_supported() || !guest_cpuid_has_mpx(vcpu))
+		if (!kvm_mpx_supported() ||
+		    (!msr_info->host_initiated && !guest_cpuid_has_mpx(vcpu)))
 			return 1;
 		if (is_noncanonical_address(data & PAGE_MASK) ||
 		    (data & MSR_IA32_BNDCFGS_RSVD))

Sumit Semwal

2017-07-19 15:59 UTC #63 lore raw

Hi Greg,

Quoted 8 lines · Greg Kroah-Hartman

This is the start of the stable review cycle for the 4.9.39 release. There are 72 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Fri Jul 21 10:23:57 UTC 2017. Anything received after that time might be too late.

For arm64, built and boot tested with defconfig on hikey, no regressions noted.

Quoted 10 lines

The whole patch series can be found in one patch at:
        kernel.org/pub/linux/kernel/v4.x/stable-review/patch-4.9.39-rc1.gz
or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-4.9.y
and the diffstat can be found below.
thanks,
greg k-h

Best,
Sumit.

Greg Kroah-Hartman

author maintainer

2017-07-20 05:08 UTC #64 lore raw

Quoted 8 lines · Sumit Semwal

Hi Greg,
Quoted 5 lines · Greg Kroah-Hartman
This is the start of the stable review cycle for the 4.9.39 release. There are 72 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Quoted 4 lines

Quoted 3 lines
Responses should be made by Fri Jul 21 10:23:57 UTC 2017. Anything received after that time might be too late.
For arm64, built and boot tested with defconfig on hikey, no regressions noted.

Thanks for testing and letting me know.

greg k-h

Guenter Roeck

2017-07-19 20:34 UTC #65 lore raw

Quoted 8 lines · Greg Kroah-Hartman

This is the start of the stable review cycle for the 4.9.39 release. There are 72 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Fri Jul 21 10:23:57 UTC 2017. Anything received after that time might be too late.

Build results:

	total: 145 pass: 145 fail: 0
Qemu test results:
	total: 122 pass: 122 fail: 0

Details are available at http://kerneltests.org/builders.

Guenter

Shuah Khan

2017-07-19 23:39 UTC #66 lore raw