4.15.18-stable review

------------------------
NOTE, this is the last expected 4.15.y release. After this one, the tree is end-of-life. Please move to 4.16.y at this point in time.
------------------------

This is the start of the stable review cycle for the 4.15.18 release. There are 53 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 Thu Apr 19 15:57:06 UTC 2018. Anything received after that time might be too late.

The whole patch series can be found in one patch at:

	https://www.kernel.org/pub/linux/kernel/v4.x/stable-review/patch-4.15.18-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-4.15.y
and the diffstat can be found below.

thanks,

greg k-h

-------------
Pseudo-Shortlog of commits:

Greg Kroah-Hartman <[email protected]>

    Linux 4.15.18-rc1

Amir Goldstein <[email protected]>
ovl: set lower layer st_dev only if setting lower st_ino

Sudhir Sreedharan <[email protected]>

    rtl8187: Fix NULL pointer dereference in priv->conf_mutex

Hans de Goede <[email protected]>
Bluetooth: hci_bcm: Treat Interrupt ACPI resources as always being active-low

Szymon Janc <[email protected]>
Bluetooth: Fix connection if directed advertising and privacy is used

Al Viro <[email protected]>

    getname_kernel() needs to make sure that ->name != ->iname in long case

Michael S. Tsirkin <[email protected]>
mm/gup_benchmark: handle gup failures

Michael S. Tsirkin <[email protected]>
get_user_pages_fast(): return -EFAULT on access_ok failure

Heiko Carstens <[email protected]>

    s390/compat: fix setup_frame32

Vasily Gorbik <[email protected]>
s390/ipl: ensure loadparm valid flag is set

Julian Wiedmann <[email protected]>
s390/qdio: don't merge ERROR output buffers

Julian Wiedmann <[email protected]>
s390/qdio: don't retry EQBS after CCQ 96

Dan Williams <[email protected]>
nfit: fix region registration vs block-data-window ranges

Tetsuo Handa <[email protected]>
block/loop: fix deadlock after loop_set_status

John Johansen <[email protected]>
apparmor: fix resource audit messages when auditing peer

John Johansen <[email protected]>
apparmor: fix display of .ns_name for containers

John Johansen <[email protected]>
apparmor: fix logging of the existence test for signals

Bill Kuzeja <[email protected]>
scsi: qla2xxx: Fix small memory leak in qla2x00_probe_one on probe failure

J. Bruce Fields <[email protected]>
nfsd: fix incorrect umasks

Mike Kravetz <[email protected]>
hugetlbfs: fix bug in pgoff overflow checking

Simon Gaiser <[email protected]>
xen: xenbus_dev_frontend: Fix XS_TRANSACTION_END handling

Amir Goldstein <[email protected]>
ovl: fix lookup with middle layer opaque dir and absolute path redirects

Ming Lei <[email protected]>
blk-mq: don't keep offline CPUs mapped to hctx 0

Ming Lei <[email protected]>
blk-mq: order getting budget and driver tag

Yury Norov <[email protected]>
lib: fix stall in __bitmap_parselist()

Keith Busch <[email protected]>
nvme: Skip checking heads without namespaces

Bart Van Assche <[email protected]>
block: Change a rcu_read_{lock,unlock}_sched() pair into rcu_read_{lock,unlock}()

Yunlong Song <[email protected]>
f2fs: fix heap mode to reset it back

Eric Biggers <[email protected]>
sunrpc: remove incorrect HMAC request initialization

Li RongQing <[email protected]>
x86/apic: Fix signedness bug in APIC ID validity checks

Toke Høiland-Jørgensen <[email protected]>
ath9k: Protect queue draining by rcu_read_lock()

Marek Szyprowski <[email protected]>
hwmon: (ina2xx) Fix access to uninitialized mutex

Yazen Ghannam <[email protected]>
x86/mce/AMD: Get address from already initialized block

Prashant Bhole <[email protected]>
perf/core: Fix use-after-free in uprobe_perf_close()

Nicholas Piggin <[email protected]>
KVM: PPC: Book3S HV: trace_tlbie must not be called in realmode

Dexuan Cui <[email protected]>
PCI: hv: Fix 2 hang issues in hv_compose_msi_msg()

Dexuan Cui <[email protected]>
PCI: hv: Serialize the present and eject work items

Dexuan Cui <[email protected]>
Drivers: hv: vmbus: do not mark HV_PCIE as perf_device

Helge Deller <[email protected]>
parisc: Fix HPMC handler by increasing size to multiple of 16 bytes

Helge Deller <[email protected]>
parisc: Fix out of array access in match_pci_device()

Corey Minyard <[email protected]>
ipmi: Fix some error cleanup issues

Kieran Bingham <[email protected]>
media: v4l: vsp1: Fix header display list status check in continuous mode

Mauro Carvalho Chehab <[email protected]>
media: v4l2-compat-ioctl32: don't oops on overlay

Phil Elwell <[email protected]>
lan78xx: Correctly indicate invalid OTP

Eric Auger <[email protected]>
vhost: Fix vhost_copy_to_user()

Sabrina Dubroca <[email protected]>
ip_gre: clear feature flags when incompatible o_flags are set

Guillaume Nault <[email protected]>
l2tp: fix race in duplicate tunnel detection

Guillaume Nault <[email protected]>
l2tp: fix races in tunnel creation

Stefan Hajnoczi <[email protected]>
vhost: fix vhost_vq_access_ok() log check

Tejaswi Tanikella <[email protected]>
slip: Check if rstate is initialized before uncompressing

Ka-Cheong Poon <[email protected]>
rds: MP-RDS may use an invalid c_path

Bassem Boubaker <[email protected]>
cdc_ether: flag the Cinterion AHS8 modem by gemalto as WWAN

Jozsef Kadlecsik <[email protected]>
netfilter: ipset: Missing nfnl_lock()/nfnl_unlock() is added to ip_set_net_exit()

Manasi Navare <[email protected]>
drm/i915/edp: Do not do link training fallback or prune modes on EDP

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

Diffstat:

 Makefile                                           |   4 +-
 arch/parisc/kernel/drivers.c                       |   4 +
 arch/parisc/kernel/hpmc.S                          |   6 +-
 arch/powerpc/kvm/book3s_hv_rm_mmu.c                |   4 -
 arch/s390/kernel/compat_signal.c                   |   2 +-
 arch/s390/kernel/ipl.c                             |   1 +
 arch/x86/include/asm/apic.h                        |   4 +-
 arch/x86/kernel/acpi/boot.c                        |  13 +-
 arch/x86/kernel/apic/apic_common.c                 |   2 +-
 arch/x86/kernel/apic/apic_numachip.c               |   2 +-
 arch/x86/kernel/apic/x2apic.h                      |   2 +-
 arch/x86/kernel/apic/x2apic_phys.c                 |   2 +-
 arch/x86/kernel/apic/x2apic_uv_x.c                 |   2 +-
 arch/x86/kernel/cpu/mcheck/mce_amd.c               |  15 ++
 arch/x86/xen/apic.c                                |   2 +-
 block/blk-core.c                                   |   4 +-
 block/blk-mq-cpumap.c                              |   5 -
 block/blk-mq.c                                     |  21 +-
 drivers/acpi/nfit/core.c                           |  22 +-
 drivers/block/loop.c                               |  12 +-
 drivers/bluetooth/hci_bcm.c                        |  20 +-
 drivers/char/ipmi/ipmi_si_intf.c                   |  18 +-
 drivers/gpu/drm/i915/intel_dp_link_training.c      |  26 ++-
 drivers/hv/channel_mgmt.c                          |   2 +-
 drivers/hwmon/ina2xx.c                             |   3 +-
 drivers/media/platform/vsp1/vsp1_dl.c              |   3 +-
 drivers/media/v4l2-core/v4l2-compat-ioctl32.c      |   4 +-
 drivers/net/slip/slhc.c                            |   5 +
 drivers/net/usb/cdc_ether.c                        |   6 +
 drivers/net/usb/lan78xx.c                          |   3 +-
 drivers/net/wireless/ath/ath9k/xmit.c              |   4 +
 drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c |   2 +-
 drivers/nvme/host/core.c                           |   1 +
 drivers/pci/host/pci-hyperv.c                      |  92 +++++++--
 drivers/s390/cio/qdio_main.c                       |  42 ++--
 drivers/scsi/qla2xxx/qla_os.c                      |  44 ++--
 drivers/vhost/vhost.c                              |  10 +-
 drivers/xen/xenbus/xenbus_dev_frontend.c           |   2 +-
 fs/f2fs/gc.c                                       |   5 +-
 fs/f2fs/segment.c                                  |   3 +-
 fs/hugetlbfs/inode.c                               |  10 +-
 fs/namei.c                                         |   3 +-
 fs/nfsd/nfs4proc.c                                 |  12 +-
 fs/nfsd/nfs4xdr.c                                  |   8 +-
 fs/nfsd/xdr4.h                                     |   2 +
 fs/overlayfs/inode.c                               |   7 +-
 fs/overlayfs/namei.c                               |   9 +
 include/net/bluetooth/hci_core.h                   |   2 +-
 include/net/slhc_vj.h                              |   1 +
 kernel/events/core.c                               |   6 +
 lib/bitmap.c                                       |   2 +-
 lib/test_bitmap.c                                  |   4 +
 mm/gup.c                                           |   5 +-
 mm/gup_benchmark.c                                 |   4 +-
 net/bluetooth/hci_conn.c                           |  29 ++-
 net/bluetooth/hci_event.c                          |  15 +-
 net/bluetooth/l2cap_core.c                         |   2 +-
 net/ipv4/ip_gre.c                                  |   6 +
 net/l2tp/l2tp_core.c                               | 225 +++++++++------------
 net/l2tp/l2tp_core.h                               |   4 +-
 net/l2tp/l2tp_netlink.c                            |  22 +-
 net/l2tp/l2tp_ppp.c                                |   9 +
 net/netfilter/ipset/ip_set_core.c                  |   2 +
 net/rds/send.c                                     |  15 +-
 net/sunrpc/auth_gss/gss_krb5_crypto.c              |   3 -
 security/apparmor/apparmorfs.c                     |   4 +-
 security/apparmor/include/audit.h                  |   8 +-
 security/apparmor/include/sig_names.h              |   4 +-
 security/apparmor/ipc.c                            |   2 +-
 69 files changed, 504 insertions(+), 345 deletions(-)

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

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

From: Manasi Navare <[email protected]>

commit a306343bcd7df89d9d45a601929e26866e7b7a81 upstream.

In case of eDP because the panel has a fixed mode, the link rate and lane count at which it is trained corresponds to the link BW required to support the native resolution of the panel. In case of panles with lower resolutions where fewer lanes are hooked up internally, that number is reflected in the MAX_LANE_COUNT DPCD register of the panel. So it is pointless to fallback to lower link rate/lane count in case of link training failure on eDP connector since the lower link BW will not support the native resolution of the panel and we cannot prune the preferred mode on the eDP connector.

In case of Link training failure on the eDP panel, something is wrong in the HW internally and hence driver errors out with a loud and clear DRM_ERROR message.

v2:
* Fix the DEBUG_ERROR and add {} in else (Ville Syrjala)

Reference: https://bugs.freedesktop.org/show_bug.cgi?id=103369

---
 drivers/gpu/drm/i915/intel_dp_link_training.c |   26 +++++++++++++++++---------
 1 file changed, 17 insertions(+), 9 deletions(-)

@@ -328,14 +328,22 @@ intel_dp_start_link_train(struct intel_d
 	return;
 
  failure_handling:
-	DRM_DEBUG_KMS("[CONNECTOR:%d:%s] Link Training failed at link rate = %d, lane count = %d",
-		      intel_connector->base.base.id,
-		      intel_connector->base.name,
-		      intel_dp->link_rate, intel_dp->lane_count);
-	if (!intel_dp_get_link_train_fallback_values(intel_dp,
-						     intel_dp->link_rate,
-						     intel_dp->lane_count))
-		/* Schedule a Hotplug Uevent to userspace to start modeset */
-		schedule_work(&intel_connector->modeset_retry_work);
+	/* Dont fallback and prune modes if its eDP */
+	if (!intel_dp_is_edp(intel_dp)) {
+		DRM_DEBUG_KMS("[CONNECTOR:%d:%s] Link Training failed at link rate = %d, lane count = %d",
+			      intel_connector->base.base.id,
+			      intel_connector->base.name,
+			      intel_dp->link_rate, intel_dp->lane_count);
+		if (!intel_dp_get_link_train_fallback_values(intel_dp,
+							     intel_dp->link_rate,
+							     intel_dp->lane_count))
+			/* Schedule a Hotplug Uevent to userspace to start modeset */
+			schedule_work(&intel_connector->modeset_retry_work);
+	} else {
+		DRM_ERROR("[CONNECTOR:%d:%s] Link Training failed at link rate = %d, lane count = %d",
+			  intel_connector->base.base.id,
+			  intel_connector->base.name,
+			  intel_dp->link_rate, intel_dp->lane_count);
+	}
 	return;
 }

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

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

From: Jozsef Kadlecsik <[email protected]>

commit f998b6b10144cd9809da6af02758615f789e8aa1 upstream.

Patch "netfilter: ipset: use nfnl_mutex_is_locked" is added the real mutex locking check, which revealed the missing locking in ip_set_net_exit().

---
 net/netfilter/ipset/ip_set_core.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -2055,6 +2055,7 @@ ip_set_net_exit(struct net *net)
 
 	inst->is_deleted = true; /* flag for ip_set_nfnl_put */
 
+	nfnl_lock(NFNL_SUBSYS_IPSET);
 	for (i = 0; i < inst->ip_set_max; i++) {
 		set = ip_set(inst, i);
 		if (set) {

@@ -2062,6 +2063,7 @@ ip_set_net_exit(struct net *net)
 			ip_set_destroy_set(set);
 		}
 	}
+	nfnl_unlock(NFNL_SUBSYS_IPSET);
 	kfree(rcu_dereference_protected(inst->ip_set_list, 1));
 }
 

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

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

From: Bassem Boubaker <[email protected]>

[ Upstream commit 53765341ee821c0a0f1dec41adc89c9096ad694c ]

The Cinterion AHS8 is a 3G device with one embedded WWAN interface using cdc_ether as a driver.

The modem is controlled via AT commands through the exposed TTYs.

AT+CGDCONT write command can be used to activate or deactivate a WWAN connection for a PDP context defined with the same command. UE supports one WWAN adapter.

---
 drivers/net/usb/cdc_ether.c |    6 ++++++
 1 file changed, 6 insertions(+)

@@ -896,6 +896,12 @@ static const struct usb_device_id	produc
 				      USB_CDC_PROTO_NONE),
 	.driver_info = (unsigned long)&wwan_info,
 }, {
+	/* Cinterion AHS3 modem by GEMALTO */
+	USB_DEVICE_AND_INTERFACE_INFO(0x1e2d, 0x0055, USB_CLASS_COMM,
+				      USB_CDC_SUBCLASS_ETHERNET,
+				      USB_CDC_PROTO_NONE),
+	.driver_info = (unsigned long)&wwan_info,
+}, {
 	USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ETHERNET,
 			USB_CDC_PROTO_NONE),
 	.driver_info = (unsigned long) &cdc_info,

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

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

From: Ka-Cheong Poon <[email protected]>

[ Upstream commit a43cced9a348901f9015f4730b70b69e7c41a9c9 ]

rds_sendmsg() calls rds_send_mprds_hash() to find a c_path to use to send a message. Suppose the RDS connection is not yet up. In rds_send_mprds_hash(), it does

	if (conn->c_npaths == 0)
		wait_event_interruptible(conn->c_hs_waitq,
					 (conn->c_npaths != 0));

If it is interrupted before the connection is set up, rds_send_mprds_hash() will return a non-zero hash value. Hence rds_sendmsg() will use a non-zero c_path to send the message. But if the RDS connection ends up to be non-MP capable, the message will be lost as only the zero c_path can be used.

---
 net/rds/send.c |   15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU

@@ -986,10 +986,15 @@ static int rds_send_mprds_hash(struct rd
 	if (conn->c_npaths == 0 && hash != 0) {
 		rds_send_ping(conn, 0);
 
-		if (conn->c_npaths == 0) {
-			wait_event_interruptible(conn->c_hs_waitq,
-						 (conn->c_npaths != 0));
-		}
+		/* The underlying connection is not up yet.  Need to wait
+		 * until it is up to be sure that the non-zero c_path can be
+		 * used.  But if we are interrupted, we have to use the zero
+		 * c_path in case the connection ends up being non-MP capable.
+		 */
+		if (conn->c_npaths == 0)
+			if (wait_event_interruptible(conn->c_hs_waitq,
+						     conn->c_npaths != 0))
+				hash = 0;
 		if (conn->c_npaths == 1)
 			hash = 0;
 	}

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

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

From: Tejaswi Tanikella <[email protected]>

[ Upstream commit 3f01ddb962dc506916c243f9524e8bef97119b77 ]

On receiving a packet the state index points to the rstate which must be used to fill up IP and TCP headers. But if the state index points to a rstate which is unitialized, i.e. filled with zeros, it gets stuck in an infinite loop inside ip_fast_csum trying to compute the ip checsum of a header with zero length.

89.666953:   <2> [<ffffff9dd3e94d38>] slhc_uncompress+0x464/0x468
89.666965:   <2> [<ffffff9dd3e87d88>] ppp_receive_nonmp_frame+0x3b4/0x65c
89.666978:   <2> [<ffffff9dd3e89dd4>] ppp_receive_frame+0x64/0x7e0
89.666991:   <2> [<ffffff9dd3e8a708>] ppp_input+0x104/0x198
89.667005:   <2> [<ffffff9dd3e93868>] pppopns_recv_core+0x238/0x370
89.667027:   <2> [<ffffff9dd4428fc8>] __sk_receive_skb+0xdc/0x250
89.667040:   <2> [<ffffff9dd3e939e4>] pppopns_recv+0x44/0x60
89.667053:   <2> [<ffffff9dd4426848>] __sock_queue_rcv_skb+0x16c/0x24c
89.667065:   <2> [<ffffff9dd4426954>] sock_queue_rcv_skb+0x2c/0x38
89.667085:   <2> [<ffffff9dd44f7358>] raw_rcv+0x124/0x154
89.667098:   <2> [<ffffff9dd44f7568>] raw_local_deliver+0x1e0/0x22c
89.667117:   <2> [<ffffff9dd44c8ba0>] ip_local_deliver_finish+0x70/0x24c
89.667131:   <2> [<ffffff9dd44c92f4>] ip_local_deliver+0x100/0x10c

./scripts/faddr2line vmlinux slhc_uncompress+0x464/0x468 output:
ip_fast_csum at arch/arm64/include/asm/checksum.h:40 (inlined by) slhc_uncompress at drivers/net/slip/slhc.c:615

Adding a variable to indicate if the current rstate is initialized. If such a packet arrives, move to toss state.

---
 drivers/net/slip/slhc.c |    5 +++++
 include/net/slhc_vj.h   |    1 +
 2 files changed, 6 insertions(+)

@@ -509,6 +509,10 @@ slhc_uncompress(struct slcompress *comp,
 		if(x < 0 || x > comp->rslot_limit)
 			goto bad;
 
+		/* Check if the cstate is initialized */
+		if (!comp->rstate[x].initialized)
+			goto bad;
+
 		comp->flags &=~ SLF_TOSS;
 		comp->recv_current = x;
 	} else {

@@ -673,6 +677,7 @@ slhc_remember(struct slcompress *comp, u
 	if (cs->cs_tcp.doff > 5)
 	  memcpy(cs->cs_tcpopt, icp + ihl*4 + sizeof(struct tcphdr), (cs->cs_tcp.doff - 5) * 4);
 	cs->cs_hsize = ihl*2 + cs->cs_tcp.doff*2;
+	cs->initialized = true;
 	/* Put headers back on packet
 	 * Neither header checksum is recalculated
 	 */

@@ -127,6 +127,7 @@ typedef __u32 int32;
  */
 struct cstate {
 	byte_t	cs_this;	/* connection id number (xmit) */
+	bool	initialized;	/* true if initialized */
 	struct cstate *next;	/* next in ring (xmit) */
 	struct iphdr cs_ip;	/* ip/tcp hdr from most recent packet */
 	struct tcphdr cs_tcp;

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

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

From: Stefan Hajnoczi <[email protected]>

[ Upstream commit d14d2b78090c7de0557362b26a4ca591aa6a9faa ]

Commit d65026c6c62e7d9616c8ceb5a53b68bcdc050525 ("vhost: validate log when IOTLB is enabled") introduced a regression. The logic was originally:

  if (vq->iotlb)
      return 1;
  return A && B;

After the patch the short-circuit logic for A was inverted:

  if (A || vq->iotlb)
      return A;
  return B;

This patch fixes the regression by rewriting the checks in the obvious way, no longer returning A when vq->iotlb is non-NULL (which is hard to understand).

---
 drivers/vhost/vhost.c |    8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

@@ -1256,10 +1256,12 @@ static int vq_log_access_ok(struct vhost
 /* Caller should have vq mutex and device mutex */
 int vhost_vq_access_ok(struct vhost_virtqueue *vq)
 {
-	int ret = vq_log_access_ok(vq, vq->log_base);
+	if (!vq_log_access_ok(vq, vq->log_base))
+		return 0;
 
-	if (ret || vq->iotlb)
-		return ret;
+	/* Access validation occurs at prefetch time with IOTLB */
+	if (vq->iotlb)
+		return 1;
 
 	return vq_access_ok(vq, vq->num, vq->desc, vq->avail, vq->used);
 }

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

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

From: Guillaume Nault <[email protected]>

[ Upstream commit 6b9f34239b00e6956a267abed2bc559ede556ad6 ]

l2tp_tunnel_create() inserts the new tunnel into the namespace's tunnel list and sets the socket's ->sk_user_data field, before returning it to the caller. Therefore, there are two ways the tunnel can be accessed and freed, before the caller even had the opportunity to take a reference. In practice, syzbot could crash the module by closing the socket right after a new tunnel was returned to pppol2tp_create().

This patch moves tunnel registration out of l2tp_tunnel_create(), so that the caller can safely hold a reference before publishing the tunnel. This second step is done with the new l2tp_tunnel_register() function, which is now responsible for associating the tunnel to its socket and for inserting it into the namespace's list.

While moving the code to l2tp_tunnel_register(), a few modifications have been done. First, the socket validation tests are done in a helper function, for clarity. Also, modifying the socket is now done after having inserted the tunnel to the namespace's tunnels list. This will allow insertion to fail, without having to revert theses modifications in the error path (a followup patch will check for duplicate tunnels before insertion). Either the socket is a kernel socket which we control, or it is a user-space socket for which we have a reference on the file descriptor. In any case, the socket isn't going to be closed from under us.

---
 net/l2tp/l2tp_core.c    |  192 +++++++++++++++++++++---------------------------
 net/l2tp/l2tp_core.h    |    3 
 net/l2tp/l2tp_netlink.c |   16 +++-
 net/l2tp/l2tp_ppp.c     |    9 ++
 4 files changed, 110 insertions(+), 110 deletions(-)

@@ -1445,74 +1445,11 @@ int l2tp_tunnel_create(struct net *net,
 {
 	struct l2tp_tunnel *tunnel = NULL;
 	int err;
-	struct socket *sock = NULL;
-	struct sock *sk = NULL;
-	struct l2tp_net *pn;
 	enum l2tp_encap_type encap = L2TP_ENCAPTYPE_UDP;
 
-	/* Get the tunnel socket from the fd, which was opened by
-	 * the userspace L2TP daemon. If not specified, create a
-	 * kernel socket.
-	 */
-	if (fd < 0) {
-		err = l2tp_tunnel_sock_create(net, tunnel_id, peer_tunnel_id,
-				cfg, &sock);
-		if (err < 0)
-			goto err;
-	} else {
-		sock = sockfd_lookup(fd, &err);
-		if (!sock) {
-			pr_err("tunl %u: sockfd_lookup(fd=%d) returned %d\n",
-			       tunnel_id, fd, err);
-			err = -EBADF;
-			goto err;
-		}
-
-		/* Reject namespace mismatches */
-		if (!net_eq(sock_net(sock->sk), net)) {
-			pr_err("tunl %u: netns mismatch\n", tunnel_id);
-			err = -EINVAL;
-			goto err;
-		}
-	}
-
-	sk = sock->sk;
-
 	if (cfg != NULL)
 		encap = cfg->encap;
 
-	/* Quick sanity checks */
-	err = -EPROTONOSUPPORT;
-	if (sk->sk_type != SOCK_DGRAM) {
-		pr_debug("tunl %hu: fd %d wrong socket type\n",
-			 tunnel_id, fd);
-		goto err;
-	}
-	switch (encap) {
-	case L2TP_ENCAPTYPE_UDP:
-		if (sk->sk_protocol != IPPROTO_UDP) {
-			pr_err("tunl %hu: fd %d wrong protocol, got %d, expected %d\n",
-			       tunnel_id, fd, sk->sk_protocol, IPPROTO_UDP);
-			goto err;
-		}
-		break;
-	case L2TP_ENCAPTYPE_IP:
-		if (sk->sk_protocol != IPPROTO_L2TP) {
-			pr_err("tunl %hu: fd %d wrong protocol, got %d, expected %d\n",
-			       tunnel_id, fd, sk->sk_protocol, IPPROTO_L2TP);
-			goto err;
-		}
-		break;
-	}
-
-	/* Check if this socket has already been prepped */
-	tunnel = l2tp_tunnel(sk);
-	if (tunnel != NULL) {
-		/* This socket has already been prepped */
-		err = -EBUSY;
-		goto err;
-	}
-
 	tunnel = kzalloc(sizeof(struct l2tp_tunnel), GFP_KERNEL);
 	if (tunnel == NULL) {
 		err = -ENOMEM;

@@ -1529,72 +1466,113 @@ int l2tp_tunnel_create(struct net *net,
 	rwlock_init(&tunnel->hlist_lock);
 	tunnel->acpt_newsess = true;
 
-	/* The net we belong to */
-	tunnel->l2tp_net = net;
-	pn = l2tp_pernet(net);
-
 	if (cfg != NULL)
 		tunnel->debug = cfg->debug;
 
-	/* Mark socket as an encapsulation socket. See net/ipv4/udp.c */
 	tunnel->encap = encap;
-	if (encap == L2TP_ENCAPTYPE_UDP) {
-		struct udp_tunnel_sock_cfg udp_cfg = { };
-
-		udp_cfg.sk_user_data = tunnel;
-		udp_cfg.encap_type = UDP_ENCAP_L2TPINUDP;
-		udp_cfg.encap_rcv = l2tp_udp_encap_recv;
-		udp_cfg.encap_destroy = l2tp_udp_encap_destroy;
-
-		setup_udp_tunnel_sock(net, sock, &udp_cfg);
-	} else {
-		sk->sk_user_data = tunnel;
-	}
 
-	/* Bump the reference count. The tunnel context is deleted
-	 * only when this drops to zero. A reference is also held on
-	 * the tunnel socket to ensure that it is not released while
-	 * the tunnel is extant. Must be done before sk_destruct is
-	 * set.
-	 */
 	refcount_set(&tunnel->ref_count, 1);
-	sock_hold(sk);
-	tunnel->sock = sk;
 	tunnel->fd = fd;
 
-	/* Hook on the tunnel socket destructor so that we can cleanup
-	 * if the tunnel socket goes away.
-	 */
-	tunnel->old_sk_destruct = sk->sk_destruct;
-	sk->sk_destruct = &l2tp_tunnel_destruct;
-	lockdep_set_class_and_name(&sk->sk_lock.slock, &l2tp_socket_class, "l2tp_sock");
-
-	sk->sk_allocation = GFP_ATOMIC;
-
 	/* Init delete workqueue struct */
 	INIT_WORK(&tunnel->del_work, l2tp_tunnel_del_work);
 
-	/* Add tunnel to our list */
 	INIT_LIST_HEAD(&tunnel->list);
-	spin_lock_bh(&pn->l2tp_tunnel_list_lock);
-	list_add_rcu(&tunnel->list, &pn->l2tp_tunnel_list);
-	spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
 
 	err = 0;
 err:
 	if (tunnelp)
 		*tunnelp = tunnel;
 
-	/* If tunnel's socket was created by the kernel, it doesn't
-	 *  have a file.
-	 */
-	if (sock && sock->file)
-		sockfd_put(sock);
-
 	return err;
 }
 EXPORT_SYMBOL_GPL(l2tp_tunnel_create);
 
+static int l2tp_validate_socket(const struct sock *sk, const struct net *net,
+				enum l2tp_encap_type encap)
+{
+	if (!net_eq(sock_net(sk), net))
+		return -EINVAL;
+
+	if (sk->sk_type != SOCK_DGRAM)
+		return -EPROTONOSUPPORT;
+
+	if ((encap == L2TP_ENCAPTYPE_UDP && sk->sk_protocol != IPPROTO_UDP) ||
+	    (encap == L2TP_ENCAPTYPE_IP && sk->sk_protocol != IPPROTO_L2TP))
+		return -EPROTONOSUPPORT;
+
+	if (sk->sk_user_data)
+		return -EBUSY;
+
+	return 0;
+}
+
+int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
+			 struct l2tp_tunnel_cfg *cfg)
+{
+	struct l2tp_net *pn;
+	struct socket *sock;
+	struct sock *sk;
+	int ret;
+
+	if (tunnel->fd < 0) {
+		ret = l2tp_tunnel_sock_create(net, tunnel->tunnel_id,
+					      tunnel->peer_tunnel_id, cfg,
+					      &sock);
+		if (ret < 0)
+			goto err;
+	} else {
+		sock = sockfd_lookup(tunnel->fd, &ret);
+		if (!sock)
+			goto err;
+
+		ret = l2tp_validate_socket(sock->sk, net, tunnel->encap);
+		if (ret < 0)
+			goto err_sock;
+	}
+
+	sk = sock->sk;
+
+	sock_hold(sk);
+	tunnel->sock = sk;
+	tunnel->l2tp_net = net;
+
+	pn = l2tp_pernet(net);
+	spin_lock_bh(&pn->l2tp_tunnel_list_lock);
+	list_add_rcu(&tunnel->list, &pn->l2tp_tunnel_list);
+	spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
+
+	if (tunnel->encap == L2TP_ENCAPTYPE_UDP) {
+		struct udp_tunnel_sock_cfg udp_cfg = {
+			.sk_user_data = tunnel,
+			.encap_type = UDP_ENCAP_L2TPINUDP,
+			.encap_rcv = l2tp_udp_encap_recv,
+			.encap_destroy = l2tp_udp_encap_destroy,
+		};
+
+		setup_udp_tunnel_sock(net, sock, &udp_cfg);
+	} else {
+		sk->sk_user_data = tunnel;
+	}
+
+	tunnel->old_sk_destruct = sk->sk_destruct;
+	sk->sk_destruct = &l2tp_tunnel_destruct;
+	lockdep_set_class_and_name(&sk->sk_lock.slock, &l2tp_socket_class,
+				   "l2tp_sock");
+	sk->sk_allocation = GFP_ATOMIC;
+
+	if (tunnel->fd >= 0)
+		sockfd_put(sock);
+
+	return 0;
+
+err_sock:
+	sockfd_put(sock);
+err:
+	return ret;
+}
+EXPORT_SYMBOL_GPL(l2tp_tunnel_register);
+
 /* This function is used by the netlink TUNNEL_DELETE command.
  */
 void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel)

@@ -231,6 +231,9 @@ struct l2tp_tunnel *l2tp_tunnel_find_nth
 int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id,
 		       u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg,
 		       struct l2tp_tunnel **tunnelp);
+int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
+			 struct l2tp_tunnel_cfg *cfg);
+
 void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel);
 void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel);
 struct l2tp_session *l2tp_session_create(int priv_size,

@@ -251,9 +251,19 @@ static int l2tp_nl_cmd_tunnel_create(str
 		break;
 	}
 
-	if (ret >= 0)
-		ret = l2tp_tunnel_notify(&l2tp_nl_family, info,
-					 tunnel, L2TP_CMD_TUNNEL_CREATE);
+	if (ret < 0)
+		goto out;
+
+	l2tp_tunnel_inc_refcount(tunnel);
+	ret = l2tp_tunnel_register(tunnel, net, &cfg);
+	if (ret < 0) {
+		kfree(tunnel);
+		goto out;
+	}
+	ret = l2tp_tunnel_notify(&l2tp_nl_family, info, tunnel,
+				 L2TP_CMD_TUNNEL_CREATE);
+	l2tp_tunnel_dec_refcount(tunnel);
+
 out:
 	return ret;
 }

@@ -698,6 +698,15 @@ static int pppol2tp_connect(struct socke
 			error = l2tp_tunnel_create(sock_net(sk), fd, ver, tunnel_id, peer_tunnel_id, &tcfg, &tunnel);
 			if (error < 0)
 				goto end;
+
+			l2tp_tunnel_inc_refcount(tunnel);
+			error = l2tp_tunnel_register(tunnel, sock_net(sk),
+						     &tcfg);
+			if (error < 0) {
+				kfree(tunnel);
+				goto end;
+			}
+			drop_tunnel = true;
 		}
 	} else {
 		/* Error if we can't find the tunnel */

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

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

From: Guillaume Nault <[email protected]>

[ Upstream commit f6cd651b056ffd3b4e8496afd44d4ed44bf69136 ]

We can't use l2tp_tunnel_find() to prevent l2tp_nl_cmd_tunnel_create() from creating a duplicate tunnel. A tunnel can be concurrently registered after l2tp_tunnel_find() returns. Therefore, searching for duplicates must be done at registration time.

Finally, remove l2tp_tunnel_find() entirely as it isn't use anywhere anymore.

---
 net/l2tp/l2tp_core.c    |   35 ++++++++++++++---------------------
 net/l2tp/l2tp_core.h    |    1 -
 net/l2tp/l2tp_netlink.c |    6 ------
 3 files changed, 14 insertions(+), 28 deletions(-)

@@ -335,26 +335,6 @@ err_tlock:
 }
 EXPORT_SYMBOL_GPL(l2tp_session_register);
 
-/* Lookup a tunnel by id
- */
-struct l2tp_tunnel *l2tp_tunnel_find(const struct net *net, u32 tunnel_id)
-{
-	struct l2tp_tunnel *tunnel;
-	struct l2tp_net *pn = l2tp_pernet(net);
-
-	rcu_read_lock_bh();
-	list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
-		if (tunnel->tunnel_id == tunnel_id) {
-			rcu_read_unlock_bh();
-			return tunnel;
-		}
-	}
-	rcu_read_unlock_bh();
-
-	return NULL;
-}
-EXPORT_SYMBOL_GPL(l2tp_tunnel_find);
-
 struct l2tp_tunnel *l2tp_tunnel_find_nth(const struct net *net, int nth)
 {
 	struct l2tp_net *pn = l2tp_pernet(net);

@@ -1510,6 +1490,7 @@ static int l2tp_validate_socket(const st
 int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
 			 struct l2tp_tunnel_cfg *cfg)
 {
+	struct l2tp_tunnel *tunnel_walk;
 	struct l2tp_net *pn;
 	struct socket *sock;
 	struct sock *sk;

@@ -1538,7 +1519,16 @@ int l2tp_tunnel_register(struct l2tp_tun
 	tunnel->l2tp_net = net;
 
 	pn = l2tp_pernet(net);
+
 	spin_lock_bh(&pn->l2tp_tunnel_list_lock);
+	list_for_each_entry(tunnel_walk, &pn->l2tp_tunnel_list, list) {
+		if (tunnel_walk->tunnel_id == tunnel->tunnel_id) {
+			spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
+
+			ret = -EEXIST;
+			goto err_sock;
+		}
+	}
 	list_add_rcu(&tunnel->list, &pn->l2tp_tunnel_list);
 	spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
 

@@ -1567,7 +1557,10 @@ int l2tp_tunnel_register(struct l2tp_tun
 	return 0;
 
 err_sock:
-	sockfd_put(sock);
+	if (tunnel->fd < 0)
+		sock_release(sock);
+	else
+		sockfd_put(sock);
 err:
 	return ret;
 }

@@ -225,7 +225,6 @@ struct l2tp_session *l2tp_session_get(co
 struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth);
 struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net,
 						const char *ifname);
-struct l2tp_tunnel *l2tp_tunnel_find(const struct net *net, u32 tunnel_id);
 struct l2tp_tunnel *l2tp_tunnel_find_nth(const struct net *net, int nth);
 
 int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id,

@@ -236,12 +236,6 @@ static int l2tp_nl_cmd_tunnel_create(str
 	if (info->attrs[L2TP_ATTR_DEBUG])
 		cfg.debug = nla_get_u32(info->attrs[L2TP_ATTR_DEBUG]);
 
-	tunnel = l2tp_tunnel_find(net, tunnel_id);
-	if (tunnel != NULL) {
-		ret = -EEXIST;
-		goto out;
-	}
-
 	ret = -EINVAL;
 	switch (cfg.encap) {
 	case L2TP_ENCAPTYPE_UDP:

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

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

From: Sabrina Dubroca <[email protected]>

[ Upstream commit 1cc5954f44150bb70cac07c3cc5df7cf0dfb61ec ]

Commit dd9d598c6657 ("ip_gre: add the support for i/o_flags update via netlink") added the ability to change o_flags, but missed that the GSO/LLTX features are disabled by default, and only enabled some gre features are unused. Thus we also need to disable the GSO/LLTX features on the device when the TUNNEL_SEQ or TUNNEL_CSUM flags are set.

These two examples should result in the same features being set:

    ip link add gre_none type gre local 192.168.0.10 remote 192.168.0.20 ttl 255 key 0

    ip link set gre_none type gre seq
    ip link add gre_seq type gre local 192.168.0.10 remote 192.168.0.20 ttl 255 key 1 seq

---
 net/ipv4/ip_gre.c |    6 ++++++
 1 file changed, 6 insertions(+)

@@ -796,8 +796,14 @@ static void ipgre_link_update(struct net
 		    tunnel->encap.type == TUNNEL_ENCAP_NONE) {
 			dev->features |= NETIF_F_GSO_SOFTWARE;
 			dev->hw_features |= NETIF_F_GSO_SOFTWARE;
+		} else {
+			dev->features &= ~NETIF_F_GSO_SOFTWARE;
+			dev->hw_features &= ~NETIF_F_GSO_SOFTWARE;
 		}
 		dev->features |= NETIF_F_LLTX;
+	} else {
+		dev->hw_features &= ~NETIF_F_GSO_SOFTWARE;
+		dev->features &= ~(NETIF_F_LLTX | NETIF_F_GSO_SOFTWARE);
 	}
 }
 

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

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

From: Eric Auger <[email protected]>

[ Upstream commit 7ced6c98c7ab7a1f6743931e28671b833af79b1e ]

vhost_copy_to_user is used to copy vring used elements to userspace. We should use VHOST_ADDR_USED instead of VHOST_ADDR_DESC.

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

@@ -756,7 +756,7 @@ static int vhost_copy_to_user(struct vho
 		struct iov_iter t;
 		void __user *uaddr = vhost_vq_meta_fetch(vq,
 				     (u64)(uintptr_t)to, size,
-				     VHOST_ADDR_DESC);
+				     VHOST_ADDR_USED);
 
 		if (uaddr)
 			return __copy_to_user(uaddr, from, size);

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

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

From: Phil Elwell <[email protected]>

[ Upstream commit 4bfc33807a9a02764bdd1e42e794b3b401240f27 ]

lan78xx_read_otp tries to return -EINVAL in the event of invalid OTP content, but the value gets overwritten before it is returned and the read goes ahead anyway. Make the read conditional as it should be and preserve the error code.

---
 drivers/net/usb/lan78xx.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -928,7 +928,8 @@ static int lan78xx_read_otp(struct lan78
 			offset += 0x100;
 		else
 			ret = -EINVAL;
-		ret = lan78xx_read_raw_otp(dev, offset, length, data);
+		if (!ret)
+			ret = lan78xx_read_raw_otp(dev, offset, length, data);
 	}
 
 	return ret;

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

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

From: Mauro Carvalho Chehab <[email protected]>

commit 85ea29f19eab56ec16ec6b92bc67305998706afa upstream.

At put_v4l2_window32(), it tries to access kp->clips. However, kp points to an userspace pointer. So, it should be obtained via get_user(), otherwise it can OOPS:

vivid-000: ================== END STATUS ==================

 BUG: unable to handle kernel paging request at 00000000fffb18e0
 IP: [<ffffffffc05468d9>] __put_v4l2_format32+0x169/0x220 [videodev]
 PGD 3f5776067 PUD 3f576f067 PMD 3f5769067 PTE 800000042548f067
 Oops: 0001 [#1] SMP
 Modules linked in: vivid videobuf2_vmalloc videobuf2_memops v4l2_dv_timings videobuf2_core v4l2_common videodev media xt_CHECKSUM iptable_mangle ipt_MASQUERADE nf_nat_masquerade_ipv4 iptable_nat nf_nat_ipv4 nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_conntrack nf_conntrack tun bridge stp llc ebtable_filter ebtables ip6table_filter ip6_tables bluetooth rfkill binfmt_misc snd_hda_codec_hdmi i915 snd_hda_intel snd_hda_controller snd_hda_codec intel_rapl x86_pkg_temp_thermal snd_hwdep intel_powerclamp snd_pcm coretemp snd_seq_midi kvm_intel kvm snd_seq_midi_event snd_rawmidi i2c_algo_bit drm_kms_helper snd_seq drm crct10dif_pclmul e1000e snd_seq_device crc32_pclmul snd_timer ghash_clmulni_intel snd mei_me mei ptp pps_core soundcore lpc_ich video crc32c_intel [last unloaded: media]
 CPU: 2 PID: 28332 Comm: v4l2-compliance Not tainted 3.18.102+ #107
 Hardware name:                  /NUC5i7RYB, BIOS RYBDWi35.86A.0364.2017.0511.0949 05/11/2017
 task: ffff8804293f8000 ti: ffff8803f5640000 task.ti: ffff8803f5640000
 RIP: 0010:[<ffffffffc05468d9>]  [<ffffffffc05468d9>] __put_v4l2_format32+0x169/0x220 [videodev]
 RSP: 0018:ffff8803f5643e28  EFLAGS: 00010246
 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 00000000fffb1ab4
 RDX: 00000000fffb1a68 RSI: 00000000fffb18d8 RDI: 00000000fffb1aa8
 RBP: ffff8803f5643e48 R08: 0000000000000001 R09: ffff8803f54b0378
 R10: 0000000000000000 R11: 0000000000000168 R12: 00000000fffb18c0
 R13: 00000000fffb1a94 R14: 00000000fffb18c8 R15: 0000000000000000
 FS:  0000000000000000(0000) GS:ffff880456d00000(0063) knlGS:00000000f7100980
 CS:  0010 DS: 002b ES: 002b CR0: 0000000080050033
 CR2: 00000000fffb18e0 CR3: 00000003f552b000 CR4: 00000000003407e0
 Stack:
  00000000fffb1a94 00000000c0cc5640 0000000000000056 ffff8804274f3600
  ffff8803f5643ed0 ffffffffc0547e16 0000000000000003 ffff8803f5643eb0
  ffffffff81301460 ffff88009db44b01 ffff880441942520 ffff8800c0d05640
 Call Trace:
  [<ffffffffc0547e16>] v4l2_compat_ioctl32+0x12d6/0x1b1d [videodev]
  [<ffffffff81301460>] ? file_has_perm+0x70/0xc0
  [<ffffffff81252a2c>] compat_SyS_ioctl+0xec/0x1200
  [<ffffffff8173241a>] sysenter_dispatch+0x7/0x21
 Code: 00 00 48 8b 80 48 c0 ff ff 48 83 e8 38 49 39 c6 0f 87 2b ff ff ff 49 8d 45 1c e8 a3 ce e3 c0 85 c0 0f 85 1a ff ff ff 41 8d 40 ff <4d> 8b 64 24 20 41 89 d5 48 8d 44 40 03 4d 8d 34 c4 eb 15 0f 1f
 RIP  [<ffffffffc05468d9>] __put_v4l2_format32+0x169/0x220 [videodev]
 RSP <ffff8803f5643e28>
 CR2: 00000000fffb18e0

Tested with vivid driver on Kernel v3.18.102.

Same bug happens upstream too:

 BUG: KASAN: user-memory-access in __put_v4l2_format32+0x98/0x4d0 [videodev]
 Read of size 8 at addr 00000000ffe48400 by task v4l2-compliance/8713

 CPU: 0 PID: 8713 Comm: v4l2-compliance Not tainted 4.16.0-rc4+ #108
 Hardware name:  /NUC5i7RYB, BIOS RYBDWi35.86A.0364.2017.0511.0949 05/11/2017
 Call Trace:
  dump_stack+0x5c/0x7c
  kasan_report+0x164/0x380
  ? __put_v4l2_format32+0x98/0x4d0 [videodev]
  __put_v4l2_format32+0x98/0x4d0 [videodev]
  v4l2_compat_ioctl32+0x1aec/0x27a0 [videodev]
  ? __fsnotify_inode_delete+0x20/0x20
  ? __put_v4l2_format32+0x4d0/0x4d0 [videodev]
  compat_SyS_ioctl+0x646/0x14d0
  ? do_ioctl+0x30/0x30
  do_fast_syscall_32+0x191/0x3f4
  entry_SYSENTER_compat+0x6b/0x7a
 ==================================================================
 Disabling lock debugging due to kernel taint
 BUG: unable to handle kernel paging request at 00000000ffe48400
 IP: __put_v4l2_format32+0x98/0x4d0 [videodev]
 PGD 3a22fb067 P4D 3a22fb067 PUD 39b6f0067 PMD 39b6f1067 PTE 80000003256af067
 Oops: 0001 [#1] SMP KASAN
 Modules linked in: vivid videobuf2_vmalloc videobuf2_dma_contig videobuf2_memops v4l2_tpg v4l2_dv_timings videobuf2_v4l2 videobuf2_common v4l2_common videodev xt_CHECKSUM iptable_mangle ipt_MASQUERADE nf_nat_masquerade_ipv4 iptable_nat nf_nat_ipv4 nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_conntrack nf_conntrack libcrc32c tun bridge stp llc ebtable_filter ebtables ip6table_filter ip6_tables bluetooth rfkill ecdh_generic binfmt_misc snd_hda_codec_hdmi intel_rapl x86_pkg_temp_thermal intel_powerclamp i915 coretemp snd_hda_intel snd_hda_codec kvm_intel snd_hwdep snd_hda_core kvm snd_pcm irqbypass crct10dif_pclmul crc32_pclmul snd_seq_midi ghash_clmulni_intel snd_seq_midi_event i2c_algo_bit intel_cstate snd_rawmidi intel_uncore snd_seq drm_kms_helper e1000e snd_seq_device snd_timer intel_rapl_perf
  drm ptp snd mei_me mei lpc_ich pps_core soundcore video crc32c_intel
 CPU: 0 PID: 8713 Comm: v4l2-compliance Tainted: G    B            4.16.0-rc4+ #108
 Hardware name:  /NUC5i7RYB, BIOS RYBDWi35.86A.0364.2017.0511.0949 05/11/2017
 RIP: 0010:__put_v4l2_format32+0x98/0x4d0 [videodev]
 RSP: 0018:ffff8803b9be7d30 EFLAGS: 00010282
 RAX: 0000000000000000 RBX: ffff8803ac983e80 RCX: ffffffff8cd929f2
 RDX: 1ffffffff1d0a149 RSI: 0000000000000297 RDI: 0000000000000297
 RBP: 00000000ffe485c0 R08: fffffbfff1cf5123 R09: ffffffff8e7a8948
 R10: 0000000000000001 R11: fffffbfff1cf5122 R12: 00000000ffe483e0
 R13: 00000000ffe485c4 R14: ffff8803ac985918 R15: 00000000ffe483e8
 FS:  0000000000000000(0000) GS:ffff880407400000(0063) knlGS:00000000f7a46980
 CS:  0010 DS: 002b ES: 002b CR0: 0000000080050033
 CR2: 00000000ffe48400 CR3: 00000003a83f2003 CR4: 00000000003606f0
 Call Trace:
  v4l2_compat_ioctl32+0x1aec/0x27a0 [videodev]
  ? __fsnotify_inode_delete+0x20/0x20
  ? __put_v4l2_format32+0x4d0/0x4d0 [videodev]
  compat_SyS_ioctl+0x646/0x14d0
  ? do_ioctl+0x30/0x30
  do_fast_syscall_32+0x191/0x3f4
  entry_SYSENTER_compat+0x6b/0x7a
 Code: 4c 89 f7 4d 8d 7c 24 08 e8 e6 a4 69 cb 48 8b 83 98 1a 00 00 48 83 e8 10 49 39 c7 0f 87 9d 01 00 00 49 8d 7c 24 20 e8 c8 a4 69 cb <4d> 8b 74 24 20 4c 89 ef 4c 89 fe ba 10 00 00 00 e8 23 d9 08 cc
 RIP: __put_v4l2_format32+0x98/0x4d0 [videodev] RSP: ffff8803b9be7d30
 CR2: 00000000ffe48400

---
 drivers/media/v4l2-core/v4l2-compat-ioctl32.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

@@ -101,7 +101,7 @@ static int get_v4l2_window32(struct v4l2
 static int put_v4l2_window32(struct v4l2_window __user *kp,
 			     struct v4l2_window32 __user *up)
 {
-	struct v4l2_clip __user *kclips = kp->clips;
+	struct v4l2_clip __user *kclips;
 	struct v4l2_clip32 __user *uclips;
 	compat_caddr_t p;
 	u32 clipcount;

@@ -116,6 +116,8 @@ static int put_v4l2_window32(struct v4l2
 	if (!clipcount)
 		return 0;
 
+	if (get_user(kclips, &kp->clips))
+		return -EFAULT;
 	if (get_user(p, &up->clips))
 		return -EFAULT;
 	uclips = compat_ptr(p);

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

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

From: Kieran Bingham <[email protected]>

commit 613928e85317b945c863bb893f5737d2f22f5425 upstream.

To allow dual pipelines utilising two WPF entities when available, the VSP was updated to support header-mode display list in continuous pipelines.

A small bug in the status check of the command register causes the second pipeline to be directly afflicted by the running of the first; appearing as a perceived performance issue with stuttering display.

Fix the vsp1_dl_list_hw_update_pending() call to ensure that the read comparison corresponds to the correct pipeline.

---
 drivers/media/platform/vsp1/vsp1_dl.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -509,7 +509,8 @@ static bool vsp1_dl_list_hw_update_pendi
 		return !!(vsp1_read(vsp1, VI6_DL_BODY_SIZE)
 			  & VI6_DL_BODY_SIZE_UPD);
 	else
-		return !!(vsp1_read(vsp1, VI6_CMD(dlm->index) & VI6_CMD_UPDHDR));
+		return !!(vsp1_read(vsp1, VI6_CMD(dlm->index))
+			  & VI6_CMD_UPDHDR);
 }
 
 static void vsp1_dl_list_hw_enqueue(struct vsp1_dl_list *dl)

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

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

From: Corey Minyard <[email protected]>

commit cc095f0ac1f7c200e51a5c2a78a43c9f42049dbb upstream.

device_remove_group() was called on any cleanup, even if the device attrs had not been added yet. That can occur in certain error scenarios, so add a flag to know if it has been added.

Also make sure we remove the dev if we added it ourselves.

---
 drivers/char/ipmi/ipmi_si_intf.c |   18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

@@ -252,6 +252,9 @@ struct smi_info {
 	/* Default driver model device. */
 	struct platform_device *pdev;
 
+	/* Have we added the device group to the device? */
+	bool dev_group_added;
+
 	/* Counters and things for the proc filesystem. */
 	atomic_t stats[SI_NUM_STATS];
 

@@ -2025,8 +2028,8 @@ int ipmi_si_add_smi(struct si_sm_io *io)
 	if (initialized) {
 		rv = try_smi_init(new_smi);
 		if (rv) {
-			mutex_unlock(&smi_infos_lock);
 			cleanup_one_si(new_smi);
+			mutex_unlock(&smi_infos_lock);
 			return rv;
 		}
 	}

@@ -2185,6 +2188,7 @@ static int try_smi_init(struct smi_info
 			rv);
 		goto out_err_stop_timer;
 	}
+	new_smi->dev_group_added = true;
 
 	rv = ipmi_register_smi(&handlers,
 			       new_smi,

@@ -2238,7 +2242,10 @@ static int try_smi_init(struct smi_info
 	return 0;
 
 out_err_remove_attrs:
-	device_remove_group(new_smi->io.dev, &ipmi_si_dev_attr_group);
+	if (new_smi->dev_group_added) {
+		device_remove_group(new_smi->io.dev, &ipmi_si_dev_attr_group);
+		new_smi->dev_group_added = false;
+	}
 	dev_set_drvdata(new_smi->io.dev, NULL);
 
 out_err_stop_timer:

@@ -2286,6 +2293,7 @@ out_err:
 		else
 			platform_device_put(new_smi->pdev);
 		new_smi->pdev = NULL;
+		new_smi->io.dev = NULL;
 	}
 
 	kfree(init_name);

@@ -2382,8 +2390,10 @@ static void cleanup_one_si(struct smi_in
 		}
 	}
 
-	device_remove_group(to_clean->io.dev, &ipmi_si_dev_attr_group);
-	dev_set_drvdata(to_clean->io.dev, NULL);
+	if (to_clean->dev_group_added)
+		device_remove_group(to_clean->io.dev, &ipmi_si_dev_attr_group);
+	if (to_clean->io.dev)
+		dev_set_drvdata(to_clean->io.dev, NULL);
 
 	list_del(&to_clean->link);
 

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

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

From: Helge Deller <[email protected]>

commit 615b2665fd20c327b631ff1e79426775de748094 upstream.

As found by the ubsan checker, the value of the 'index' variable can be out of range for the bc[] array:

UBSAN: Undefined behaviour in arch/parisc/kernel/drivers.c:655:21
index 6 is out of range for type 'char [6]'
Backtrace:
 [<104fa850>] __ubsan_handle_out_of_bounds+0x68/0x80
 [<1019d83c>] check_parent+0xc0/0x170
 [<1019d91c>] descend_children+0x30/0x6c
 [<1059e164>] device_for_each_child+0x60/0x98
 [<1019cd54>] parse_tree_node+0x40/0x54
 [<1019d86c>] check_parent+0xf0/0x170
 [<1019d91c>] descend_children+0x30/0x6c
 [<1059e164>] device_for_each_child+0x60/0x98
 [<1019d938>] descend_children+0x4c/0x6c
 [<1059e164>] device_for_each_child+0x60/0x98
 [<1019cd54>] parse_tree_node+0x40/0x54
 [<1019cffc>] hwpath_to_device+0xa4/0xc4

---
 arch/parisc/kernel/drivers.c |    4 ++++
 1 file changed, 4 insertions(+)

@@ -651,6 +651,10 @@ static int match_pci_device(struct devic
 					(modpath->mod == PCI_FUNC(devfn)));
 	}
 
+	/* index might be out of bounds for bc[] */
+	if (index >= 6)
+		return 0;
+
 	id = PCI_SLOT(pdev->devfn) | (PCI_FUNC(pdev->devfn) << 5);
 	return (modpath->bc[index] == id);
 }

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

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

From: Helge Deller <[email protected]>

commit d5654e156bc4d68a87bbaa6d7e020baceddf6e68 upstream.

Make sure that the HPMC (High Priority Machine Check) handler is 16-byte aligned and that it's length in the IVT is a multiple of 16 bytes. Otherwise PDC may decide not to call the HPMC crash handler.

---
 arch/parisc/kernel/hpmc.S |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

@@ -84,6 +84,7 @@ END(hpmc_pim_data)
 	.text
 
 	.import intr_save, code
+	.align 16
 ENTRY_CFI(os_hpmc)
 .os_hpmc:
 

@@ -300,12 +301,15 @@ os_hpmc_6:
 
 	b .
 	nop
+	.align 16	/* make function length multiple of 16 bytes */
 ENDPROC_CFI(os_hpmc)
 .os_hpmc_end:
 
 
 	__INITRODATA
+.globl os_hpmc_size
 	.align 4
-	.export os_hpmc_size
+	.type   os_hpmc_size, @object
+	.size   os_hpmc_size, 4
 os_hpmc_size:
 	.word .os_hpmc_end-.os_hpmc

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

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

From: Dexuan Cui <[email protected]>

commit 238064f13d057390a8c5e1a6a80f4f0a0ec46499 upstream.

The pci-hyperv driver's channel callback hv_pci_onchannelcallback() is not really a hot path, so we don't need to mark it as a perf_device, meaning with this patch all HV_PCIE channels' target_cpu will be CPU0.

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

@@ -71,7 +71,7 @@ static const struct vmbus_device vmbus_d
 	/* PCIE */
 	{ .dev_type = HV_PCIE,
 	  HV_PCIE_GUID,
-	  .perf_device = true,
+	  .perf_device = false,
 	},
 
 	/* Synthetic Frame Buffer */

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

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

From: Dexuan Cui <[email protected]>

commit 021ad274d7dc31611d4f47f7dd4ac7a224526f30 upstream.

When we hot-remove the device, we first receive a PCI_EJECT message and then receive a PCI_BUS_RELATIONS message with bus_rel->device_count == 0.

The first message is offloaded to hv_eject_device_work(), and the second is offloaded to pci_devices_present_work(). Both the paths can be running list_del(&hpdev->list_entry), causing general protection fault, because system_wq can run them concurrently.

The patch eliminates the race condition.

Since access to present/eject work items is serialized, we do not need the hbus->enum_sem anymore, so remove it.

---
 drivers/pci/host/pci-hyperv.c |   34 ++++++++++++++++------------------
 1 file changed, 16 insertions(+), 18 deletions(-)

@@ -457,7 +457,6 @@ struct hv_pcibus_device {
 	spinlock_t device_list_lock;	/* Protect lists below */
 	void __iomem *cfg_addr;
 
-	struct semaphore enum_sem;
 	struct list_head resources_for_children;
 
 	struct list_head children;

@@ -471,6 +470,8 @@ struct hv_pcibus_device {
 	struct retarget_msi_interrupt retarget_msi_interrupt_params;
 
 	spinlock_t retarget_msi_interrupt_lock;
+
+	struct workqueue_struct *wq;
 };
 
 /*

@@ -1600,12 +1601,8 @@ static struct hv_pci_dev *get_pcichild_w
  * It must also treat the omission of a previously observed device as
  * notification that the device no longer exists.
  *
- * Note that this function is a work item, and it may not be
- * invoked in the order that it was queued.  Back to back
- * updates of the list of present devices may involve queuing
- * multiple work items, and this one may run before ones that
- * were sent later. As such, this function only does something
- * if is the last one in the queue.
+ * Note that this function is serialized with hv_eject_device_work(),
+ * because both are pushed to the ordered workqueue hbus->wq.
  */
 static void pci_devices_present_work(struct work_struct *work)
 {

@@ -1626,11 +1623,6 @@ static void pci_devices_present_work(str
 
 	INIT_LIST_HEAD(&removed);
 
-	if (down_interruptible(&hbus->enum_sem)) {
-		put_hvpcibus(hbus);
-		return;
-	}
-
 	/* Pull this off the queue and process it if it was the last one. */
 	spin_lock_irqsave(&hbus->device_list_lock, flags);
 	while (!list_empty(&hbus->dr_list)) {

@@ -1647,7 +1639,6 @@ static void pci_devices_present_work(str
 	spin_unlock_irqrestore(&hbus->device_list_lock, flags);
 
 	if (!dr) {
-		up(&hbus->enum_sem);
 		put_hvpcibus(hbus);
 		return;
 	}

@@ -1734,7 +1725,6 @@ static void pci_devices_present_work(str
 		break;
 	}
 
-	up(&hbus->enum_sem);
 	put_hvpcibus(hbus);
 	kfree(dr);
 }

@@ -1780,7 +1770,7 @@ static void hv_pci_devices_present(struc
 	spin_unlock_irqrestore(&hbus->device_list_lock, flags);
 
 	get_hvpcibus(hbus);
-	schedule_work(&dr_wrk->wrk);
+	queue_work(hbus->wq, &dr_wrk->wrk);
 }
 
 /**

@@ -1858,7 +1848,7 @@ static void hv_pci_eject_device(struct h
 	get_pcichild(hpdev, hv_pcidev_ref_pnp);
 	INIT_WORK(&hpdev->wrk, hv_eject_device_work);
 	get_hvpcibus(hpdev->hbus);
-	schedule_work(&hpdev->wrk);
+	queue_work(hpdev->hbus->wq, &hpdev->wrk);
 }
 
 /**

@@ -2471,13 +2461,18 @@ static int hv_pci_probe(struct hv_device
 	spin_lock_init(&hbus->config_lock);
 	spin_lock_init(&hbus->device_list_lock);
 	spin_lock_init(&hbus->retarget_msi_interrupt_lock);
-	sema_init(&hbus->enum_sem, 1);
 	init_completion(&hbus->remove_event);
+	hbus->wq = alloc_ordered_workqueue("hv_pci_%x", 0,
+					   hbus->sysdata.domain);
+	if (!hbus->wq) {
+		ret = -ENOMEM;
+		goto free_bus;
+	}
 
 	ret = vmbus_open(hdev->channel, pci_ring_size, pci_ring_size, NULL, 0,
 			 hv_pci_onchannelcallback, hbus);
 	if (ret)
-		goto free_bus;
+		goto destroy_wq;
 
 	hv_set_drvdata(hdev, hbus);
 

@@ -2546,6 +2541,8 @@ free_config:
 	hv_free_config_window(hbus);
 close:
 	vmbus_close(hdev->channel);
+destroy_wq:
+	destroy_workqueue(hbus->wq);
 free_bus:
 	free_page((unsigned long)hbus);
 	return ret;

@@ -2625,6 +2622,7 @@ static int hv_pci_remove(struct hv_devic
 	irq_domain_free_fwnode(hbus->sysdata.fwnode);
 	put_hvpcibus(hbus);
 	wait_for_completion(&hbus->remove_event);
+	destroy_workqueue(hbus->wq);
 	free_page((unsigned long)hbus);
 	return 0;
 }

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

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

From: Dexuan Cui <[email protected]>

commit de0aa7b2f97d348ba7d1e17a00744c989baa0cb6 upstream.

1. With the patch "x86/vector/msi: Switch to global reservation mode", the recent v4.15 and newer kernels always hang for 1-vCPU Hyper-V VM with SR-IOV. This is because when we reach hv_compose_msi_msg() by request_irq() -> request_threaded_irq() ->__setup_irq()->irq_startup() -> __irq_startup() -> irq_domain_activate_irq() -> ... -> msi_domain_activate() -> ... -> hv_compose_msi_msg(), local irq is disabled in __setup_irq().

Note: when we reach hv_compose_msi_msg() by another code path:
pci_enable_msix_range() -> ... -> irq_domain_activate_irq() -> ... -> hv_compose_msi_msg(), local irq is not disabled.

hv_compose_msi_msg() depends on an interrupt from the host. With interrupts disabled, a UP VM always hangs in the busy loop in the function, because the interrupt callback hv_pci_onchannelcallback() can not be called.

We can do nothing but work it around by polling the channel. This is ugly, but we don't have any other choice.

2. If the host is ejecting the VF device before we reach hv_compose_msi_msg(), in a UP VM, we can hang in hv_compose_msi_msg() forever, because at this time the host doesn't respond to the CREATE_INTERRUPT request. This issue exists the first day the pci-hyperv driver appears in the kernel.

Luckily, this can also by worked around by polling the channel for the PCI_EJECT message and hpdev->state, and by checking the PCI vendor ID.

Note: actually the above 2 issues also happen to a SMP VM, if "hbus->hdev->channel->target_cpu == smp_processor_id()" is true.

---
 drivers/pci/host/pci-hyperv.c |   58 +++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 57 insertions(+), 1 deletion(-)

@@ -531,6 +531,8 @@ struct hv_pci_compl {
 	s32 completion_status;
 };
 
+static void hv_pci_onchannelcallback(void *context);
+
 /**
  * hv_pci_generic_compl() - Invoked for a completion packet
  * @context:		Set up by the sender of the packet.

@@ -675,6 +677,31 @@ static void _hv_pcifront_read_config(str
 	}
 }
 
+static u16 hv_pcifront_get_vendor_id(struct hv_pci_dev *hpdev)
+{
+	u16 ret;
+	unsigned long flags;
+	void __iomem *addr = hpdev->hbus->cfg_addr + CFG_PAGE_OFFSET +
+			     PCI_VENDOR_ID;
+
+	spin_lock_irqsave(&hpdev->hbus->config_lock, flags);
+
+	/* Choose the function to be read. (See comment above) */
+	writel(hpdev->desc.win_slot.slot, hpdev->hbus->cfg_addr);
+	/* Make sure the function was chosen before we start reading. */
+	mb();
+	/* Read from that function's config space. */
+	ret = readw(addr);
+	/*
+	 * mb() is not required here, because the spin_unlock_irqrestore()
+	 * is a barrier.
+	 */
+
+	spin_unlock_irqrestore(&hpdev->hbus->config_lock, flags);
+
+	return ret;
+}
+
 /**
  * _hv_pcifront_write_config() - Internal PCI config write
  * @hpdev:	The PCI driver's representation of the device

@@ -1117,8 +1144,37 @@ static void hv_compose_msi_msg(struct ir
 	 * Since this function is called with IRQ locks held, can't
 	 * do normal wait for completion; instead poll.
 	 */
-	while (!try_wait_for_completion(&comp.comp_pkt.host_event))
+	while (!try_wait_for_completion(&comp.comp_pkt.host_event)) {
+		/* 0xFFFF means an invalid PCI VENDOR ID. */
+		if (hv_pcifront_get_vendor_id(hpdev) == 0xFFFF) {
+			dev_err_once(&hbus->hdev->device,
+				     "the device has gone\n");
+			goto free_int_desc;
+		}
+
+		/*
+		 * When the higher level interrupt code calls us with
+		 * interrupt disabled, we must poll the channel by calling
+		 * the channel callback directly when channel->target_cpu is
+		 * the current CPU. When the higher level interrupt code
+		 * calls us with interrupt enabled, let's add the
+		 * local_bh_disable()/enable() to avoid race.
+		 */
+		local_bh_disable();
+
+		if (hbus->hdev->channel->target_cpu == smp_processor_id())
+			hv_pci_onchannelcallback(hbus);
+
+		local_bh_enable();
+
+		if (hpdev->state == hv_pcichild_ejecting) {
+			dev_err_once(&hbus->hdev->device,
+				     "the device is being ejected\n");
+			goto free_int_desc;
+		}
+
 		udelay(100);
+	}
 
 	if (comp.comp_pkt.completion_status < 0) {
 		dev_err(&hbus->hdev->device,

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

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

From: Nicholas Piggin <[email protected]>

commit 19ce7909ed11c49f7eddf59e7f49cd3062bf83d5 upstream.

This crashes with a "Bad real address for load" attempting to load from the vmalloc region in realmode (faulting address is in DAR).

  Oops: Bad interrupt in KVM entry/exit code, sig: 6 [#1]
  LE SMP NR_CPUS=2048 NUMA PowerNV
  CPU: 53 PID: 6582 Comm: qemu-system-ppc Not tainted 4.16.0-01530-g43d1859f0994
  NIP:  c0000000000155ac LR: c0000000000c2430 CTR: c000000000015580
  REGS: c000000fff76dd80 TRAP: 0200   Not tainted  (4.16.0-01530-g43d1859f0994)
  MSR:  9000000000201003 <SF,HV,ME,RI,LE>  CR: 48082222  XER: 00000000
  CFAR: 0000000102900ef0 DAR: d00017fffd941a28 DSISR: 00000040 SOFTE: 3
  NIP [c0000000000155ac] perf_trace_tlbie+0x2c/0x1a0
  LR [c0000000000c2430] do_tlbies+0x230/0x2f0

I suspect the reason is the per-cpu data is not in the linear chunk. This could be restored if that was able to be fixed, but for now, just remove the tracepoints.

---
 arch/powerpc/kvm/book3s_hv_rm_mmu.c |    4 ----
 1 file changed, 4 deletions(-)

@@ -470,8 +470,6 @@ static void do_tlbies(struct kvm *kvm, u
 		for (i = 0; i < npages; ++i) {
 			asm volatile(PPC_TLBIE_5(%0,%1,0,0,0) : :
 				     "r" (rbvalues[i]), "r" (kvm->arch.lpid));
-			trace_tlbie(kvm->arch.lpid, 0, rbvalues[i],
-				kvm->arch.lpid, 0, 0, 0);
 		}
 		asm volatile("eieio; tlbsync; ptesync" : : : "memory");
 		kvm->arch.tlbie_lock = 0;

@@ -481,8 +479,6 @@ static void do_tlbies(struct kvm *kvm, u
 		for (i = 0; i < npages; ++i) {
 			asm volatile(PPC_TLBIEL(%0,%1,0,0,0) : :
 				     "r" (rbvalues[i]), "r" (0));
-			trace_tlbie(kvm->arch.lpid, 1, rbvalues[i],
-				0, 0, 0, 0);
 		}
 		asm volatile("ptesync" : : : "memory");
 	}

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

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

From: Prashant Bhole <[email protected]>

commit 621b6d2ea297d0fb6030452c5bcd221f12165fcf upstream.

A use-after-free bug was caught by KASAN while running usdt related code (BCC project. bcc/tests/python/test_usdt2.py):

	==================================================================
	BUG: KASAN: use-after-free in uprobe_perf_close+0x222/0x3b0
	Read of size 4 at addr ffff880384f9b4a4 by task test_usdt2.py/870

	CPU: 4 PID: 870 Comm: test_usdt2.py Tainted: G        W         4.16.0-next-20180409 #215
	Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014
	Call Trace:
	 dump_stack+0xc7/0x15b
	 ? show_regs_print_info+0x5/0x5
	 ? printk+0x9c/0xc3
	 ? kmsg_dump_rewind_nolock+0x6e/0x6e
	 ? uprobe_perf_close+0x222/0x3b0
	 print_address_description+0x83/0x3a0
	 ? uprobe_perf_close+0x222/0x3b0
	 kasan_report+0x1dd/0x460
	 ? uprobe_perf_close+0x222/0x3b0
	 uprobe_perf_close+0x222/0x3b0
	 ? probes_open+0x180/0x180
	 ? free_filters_list+0x290/0x290
	 trace_uprobe_register+0x1bb/0x500
	 ? perf_event_attach_bpf_prog+0x310/0x310
	 ? probe_event_disable+0x4e0/0x4e0
	 perf_uprobe_destroy+0x63/0xd0
	 _free_event+0x2bc/0xbd0
	 ? lockdep_rcu_suspicious+0x100/0x100
	 ? ring_buffer_attach+0x550/0x550
	 ? kvm_sched_clock_read+0x1a/0x30
	 ? perf_event_release_kernel+0x3e4/0xc00
	 ? __mutex_unlock_slowpath+0x12e/0x540
	 ? wait_for_completion+0x430/0x430
	 ? lock_downgrade+0x3c0/0x3c0
	 ? lock_release+0x980/0x980
	 ? do_raw_spin_trylock+0x118/0x150
	 ? do_raw_spin_unlock+0x121/0x210
	 ? do_raw_spin_trylock+0x150/0x150
	 perf_event_release_kernel+0x5d4/0xc00
	 ? put_event+0x30/0x30
	 ? fsnotify+0xd2d/0xea0
	 ? sched_clock_cpu+0x18/0x1a0
	 ? __fsnotify_update_child_dentry_flags.part.0+0x1b0/0x1b0
	 ? pvclock_clocksource_read+0x152/0x2b0
	 ? pvclock_read_flags+0x80/0x80
	 ? kvm_sched_clock_read+0x1a/0x30
	 ? sched_clock_cpu+0x18/0x1a0
	 ? pvclock_clocksource_read+0x152/0x2b0
	 ? locks_remove_file+0xec/0x470
	 ? pvclock_read_flags+0x80/0x80
	 ? fcntl_setlk+0x880/0x880
	 ? ima_file_free+0x8d/0x390
	 ? lockdep_rcu_suspicious+0x100/0x100
	 ? ima_file_check+0x110/0x110
	 ? fsnotify+0xea0/0xea0
	 ? kvm_sched_clock_read+0x1a/0x30
	 ? rcu_note_context_switch+0x600/0x600
	 perf_release+0x21/0x40
	 __fput+0x264/0x620
	 ? fput+0xf0/0xf0
	 ? do_raw_spin_unlock+0x121/0x210
	 ? do_raw_spin_trylock+0x150/0x150
	 ? SyS_fchdir+0x100/0x100
	 ? fsnotify+0xea0/0xea0
	 task_work_run+0x14b/0x1e0
	 ? task_work_cancel+0x1c0/0x1c0
	 ? copy_fd_bitmaps+0x150/0x150
	 ? vfs_read+0xe5/0x260
	 exit_to_usermode_loop+0x17b/0x1b0
	 ? trace_event_raw_event_sys_exit+0x1a0/0x1a0
	 do_syscall_64+0x3f6/0x490
	 ? syscall_return_slowpath+0x2c0/0x2c0
	 ? lockdep_sys_exit+0x1f/0xaa
	 ? syscall_return_slowpath+0x1a3/0x2c0
	 ? lockdep_sys_exit+0x1f/0xaa
	 ? prepare_exit_to_usermode+0x11c/0x1e0
	 ? enter_from_user_mode+0x30/0x30
	random: crng init done
	 ? __put_user_4+0x1c/0x30
	 entry_SYSCALL_64_after_hwframe+0x3d/0xa2
	RIP: 0033:0x7f41d95f9340
	RSP: 002b:00007fffe71e4268 EFLAGS: 00000246 ORIG_RAX: 0000000000000003
	RAX: 0000000000000000 RBX: 000000000000000d RCX: 00007f41d95f9340
	RDX: 0000000000000000 RSI: 0000000000002401 RDI: 000000000000000d
	RBP: 0000000000000000 R08: 00007f41ca8ff700 R09: 00007f41d996dd1f
	R10: 00007fffe71e41e0 R11: 0000000000000246 R12: 00007fffe71e4330
	R13: 0000000000000000 R14: fffffffffffffffc R15: 00007fffe71e4290

	Allocated by task 870:
	 kasan_kmalloc+0xa0/0xd0
	 kmem_cache_alloc_node+0x11a/0x430
	 copy_process.part.19+0x11a0/0x41c0
	 _do_fork+0x1be/0xa20
	 do_syscall_64+0x198/0x490
	 entry_SYSCALL_64_after_hwframe+0x3d/0xa2

	Freed by task 0:
	 __kasan_slab_free+0x12e/0x180
	 kmem_cache_free+0x102/0x4d0
	 free_task+0xfe/0x160
	 __put_task_struct+0x189/0x290
	 delayed_put_task_struct+0x119/0x250
	 rcu_process_callbacks+0xa6c/0x1b60
	 __do_softirq+0x238/0x7ae

	The buggy address belongs to the object at ffff880384f9b480
	 which belongs to the cache task_struct of size 12928

It occurs because task_struct is freed before perf_event which refers to the task and task flags are checked while teardown of the event. perf_event_alloc() assigns task_struct to hw.target of perf_event, but there is no reference counting for it.

As a fix we get_task_struct() in perf_event_alloc() at above mentioned assignment and put_task_struct() in _free_event().

---
 kernel/events/core.c |    6 ++++++
 1 file changed, 6 insertions(+)

@@ -4112,6 +4112,9 @@ static void _free_event(struct perf_even
 	if (event->ctx)
 		put_ctx(event->ctx);
 
+	if (event->hw.target)
+		put_task_struct(event->hw.target);
+
 	exclusive_event_destroy(event);
 	module_put(event->pmu->module);
 

@@ -9456,6 +9459,7 @@ perf_event_alloc(struct perf_event_attr
 		 * and we cannot use the ctx information because we need the
 		 * pmu before we get a ctx.
 		 */
+		get_task_struct(task);
 		event->hw.target = task;
 	}
 

@@ -9571,6 +9575,8 @@ err_ns:
 		perf_detach_cgroup(event);
 	if (event->ns)
 		put_pid_ns(event->ns);
+	if (event->hw.target)
+		put_task_struct(event->hw.target);
 	kfree(event);
 
 	return ERR_PTR(err);

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

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

From: Yazen Ghannam <[email protected]>

commit 27bd59502702fe51d9eb00450a75b727ec6bfcb4 upstream.

The block address is saved after the block is initialized when threshold_init_device() is called.

Use the saved block address, if available, rather than trying to rediscover it.

This will avoid a call trace, when resuming from suspend, due to the rdmsr_safe_on_cpu() call in get_block_address(). The rdmsr_safe_on_cpu() call issues an IPI but we're running with interrupts disabled. This triggers:

    WARNING: CPU: 0 PID: 11523 at kernel/smp.c:291 smp_call_function_single+0xdc/0xe0

---
 arch/x86/kernel/cpu/mcheck/mce_amd.c |   15 +++++++++++++++
 1 file changed, 15 insertions(+)

--
To unsubscribe from this list: send the line "unsubscribe linux-edac" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html

@@ -416,6 +416,21 @@ static u32 get_block_address(unsigned in
 {
 	u32 addr = 0, offset = 0;
 
+	if ((bank >= mca_cfg.banks) || (block >= NR_BLOCKS))
+		return addr;
+
+	/* Get address from already initialized block. */
+	if (per_cpu(threshold_banks, cpu)) {
+		struct threshold_bank *bankp = per_cpu(threshold_banks, cpu)[bank];
+
+		if (bankp && bankp->blocks) {
+			struct threshold_block *blockp = &bankp->blocks[block];
+
+			if (blockp)
+				return blockp->address;
+		}
+	}
+
 	if (mce_flags.smca) {
 		if (!block) {
 			addr = MSR_AMD64_SMCA_MCx_MISC(bank);

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

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

From: Marek Szyprowski <[email protected]>

commit 0c4c5860e9983eb3da7a3d73ca987643c3ed034b upstream.

Initialize data->config_lock mutex before it is used by the driver code.

This fixes following warning on Odroid XU3 boards:

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

CPU: 5 PID: 1 Comm: swapper/0 Not tainted 4.15.0-rc7-next-20180115-00001-gb75575dee3f2 #107
Hardware name: SAMSUNG EXYNOS (Flattened Device Tree)
[<c0111504>] (unwind_backtrace) from [<c010dbec>] (show_stack+0x10/0x14)
[<c010dbec>] (show_stack) from [<c09b3f74>] (dump_stack+0x90/0xc8)
[<c09b3f74>] (dump_stack) from [<c0179528>] (register_lock_class+0x1c0/0x59c)
[<c0179528>] (register_lock_class) from [<c017bd1c>] (__lock_acquire+0x78/0x1850)
[<c017bd1c>] (__lock_acquire) from [<c017de30>] (lock_acquire+0xc8/0x2b8)
[<c017de30>] (lock_acquire) from [<c09ca59c>] (__mutex_lock+0x60/0xa0c)
[<c09ca59c>] (__mutex_lock) from [<c09cafd0>] (mutex_lock_nested+0x1c/0x24)
[<c09cafd0>] (mutex_lock_nested) from [<c068b0d0>] (ina2xx_set_shunt+0x70/0xb0)
[<c068b0d0>] (ina2xx_set_shunt) from [<c068b218>] (ina2xx_probe+0x88/0x1b0)
[<c068b218>] (ina2xx_probe) from [<c0673d90>] (i2c_device_probe+0x1e0/0x2d0)
[<c0673d90>] (i2c_device_probe) from [<c053a268>] (driver_probe_device+0x2b8/0x4a0)
[<c053a268>] (driver_probe_device) from [<c053a54c>] (__driver_attach+0xfc/0x120)
[<c053a54c>] (__driver_attach) from [<c05384cc>] (bus_for_each_dev+0x58/0x7c)
[<c05384cc>] (bus_for_each_dev) from [<c0539590>] (bus_add_driver+0x174/0x250)
[<c0539590>] (bus_add_driver) from [<c053b5e0>] (driver_register+0x78/0xf4)
[<c053b5e0>] (driver_register) from [<c0675ef0>] (i2c_register_driver+0x38/0xa8)
[<c0675ef0>] (i2c_register_driver) from [<c0102b40>] (do_one_initcall+0x48/0x18c)
[<c0102b40>] (do_one_initcall) from [<c0e00df0>] (kernel_init_freeable+0x110/0x1d4)
[<c0e00df0>] (kernel_init_freeable) from [<c09c8120>] (kernel_init+0x8/0x114)
[<c09c8120>] (kernel_init) from [<c01010b4>] (ret_from_fork+0x14/0x20)

---
 drivers/hwmon/ina2xx.c |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

@@ -454,6 +454,7 @@ static int ina2xx_probe(struct i2c_clien
 
 	/* set the device type */
 	data->config = &ina2xx_config[chip];
+	mutex_init(&data->config_lock);
 
 	if (of_property_read_u32(dev->of_node, "shunt-resistor", &val) < 0) {
 		struct ina2xx_platform_data *pdata = dev_get_platdata(dev);

@@ -480,8 +481,6 @@ static int ina2xx_probe(struct i2c_clien
 		return -ENODEV;
 	}
 
-	mutex_init(&data->config_lock);
-
 	data->groups[group++] = &ina2xx_group;
 	if (id->driver_data == ina226)
 		data->groups[group++] = &ina226_group;

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

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

From: Toke Høiland-Jørgensen <[email protected]>

commit 182b1917109892ab9f26d66bfdcbc4ba6f0a0a65 upstream.

When ath9k was switched over to use the mac80211 intermediate queues, node cleanup now drains the mac80211 queues. However, this call path is not protected by rcu_read_lock() as it was previously entirely internal to the driver which uses its own locking.

This leads to a possible rcu_dereference() without holding rcu_read_lock(); but only if a station is cleaned up while having packets queued on the TXQ. Fix this by adding the rcu_read_lock() to the caller in ath9k.

---
 drivers/net/wireless/ath/ath9k/xmit.c |    4 ++++
 1 file changed, 4 insertions(+)

@@ -2892,6 +2892,8 @@ void ath_tx_node_cleanup(struct ath_soft
 	struct ath_txq *txq;
 	int tidno;
 
+	rcu_read_lock();
+
 	for (tidno = 0; tidno < IEEE80211_NUM_TIDS; tidno++) {
 		tid = ath_node_to_tid(an, tidno);
 		txq = tid->txq;

@@ -2909,6 +2911,8 @@ void ath_tx_node_cleanup(struct ath_soft
 		if (!an->sta)
 			break; /* just one multicast ath_atx_tid */
 	}
+
+	rcu_read_unlock();
 }
 
 #ifdef CONFIG_ATH9K_TX99

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

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

From: Li RongQing <[email protected]>

commit a774635db5c430cbf21fa5d2f2df3d23aaa8e782 upstream.

The APIC ID as parsed from ACPI MADT is validity checked with the apic->apic_id_valid() callback, which depends on the selected APIC type.

For non X2APIC types APIC IDs >= 0xFF are invalid, but values > 0x7FFFFFFF are detected as valid. This happens because the 'apicid' argument of the apic_id_valid() callback is type 'int'. So the resulting comparison

apicid < 0xFF

evaluates to true for all unsigned int values > 0x7FFFFFFF which are handed to default_apic_id_valid(). As a consequence, invalid APIC IDs in !X2APIC mode are considered valid and accounted as possible CPUs.

Change the apicid argument type of the apic_id_valid() callback to u32 so the evaluation is unsigned and returns the correct result.

[ tglx: Massaged changelog ]

---
 arch/x86/include/asm/apic.h          |    4 ++--
 arch/x86/kernel/acpi/boot.c          |   13 ++++++++-----
 arch/x86/kernel/apic/apic_common.c   |    2 +-
 arch/x86/kernel/apic/apic_numachip.c |    2 +-
 arch/x86/kernel/apic/x2apic.h        |    2 +-
 arch/x86/kernel/apic/x2apic_phys.c   |    2 +-
 arch/x86/kernel/apic/x2apic_uv_x.c   |    2 +-
 arch/x86/xen/apic.c                  |    2 +-
 8 files changed, 16 insertions(+), 13 deletions(-)

@@ -319,7 +319,7 @@ struct apic {
 	/* Probe, setup and smpboot functions */
 	int	(*probe)(void);
 	int	(*acpi_madt_oem_check)(char *oem_id, char *oem_table_id);
-	int	(*apic_id_valid)(int apicid);
+	int	(*apic_id_valid)(u32 apicid);
 	int	(*apic_id_registered)(void);
 
 	bool	(*check_apicid_used)(physid_mask_t *map, int apicid);

@@ -492,7 +492,7 @@ static inline unsigned int read_apic_id(
 	return apic->get_apic_id(reg);
 }
 
-extern int default_apic_id_valid(int apicid);
+extern int default_apic_id_valid(u32 apicid);
 extern int default_acpi_madt_oem_check(char *, char *);
 extern void default_setup_apic_routing(void);
 

@@ -200,7 +200,7 @@ acpi_parse_x2apic(struct acpi_subtable_h
 {
 	struct acpi_madt_local_x2apic *processor = NULL;
 #ifdef CONFIG_X86_X2APIC
-	int apic_id;
+	u32 apic_id;
 	u8 enabled;
 #endif
 

@@ -222,10 +222,13 @@ acpi_parse_x2apic(struct acpi_subtable_h
 	 * to not preallocating memory for all NR_CPUS
 	 * when we use CPU hotplug.
 	 */
-	if (!apic->apic_id_valid(apic_id) && enabled)
-		printk(KERN_WARNING PREFIX "x2apic entry ignored\n");
-	else
-		acpi_register_lapic(apic_id, processor->uid, enabled);
+	if (!apic->apic_id_valid(apic_id)) {
+		if (enabled)
+			pr_warn(PREFIX "x2apic entry ignored\n");
+		return 0;
+	}
+
+	acpi_register_lapic(apic_id, processor->uid, enabled);
 #else
 	printk(KERN_WARNING PREFIX "x2apic entry ignored\n");
 #endif

@@ -40,7 +40,7 @@ int default_check_phys_apicid_present(in
 	return physid_isset(phys_apicid, phys_cpu_present_map);
 }
 
-int default_apic_id_valid(int apicid)
+int default_apic_id_valid(u32 apicid)
 {
 	return (apicid < 255);
 }

@@ -56,7 +56,7 @@ static u32 numachip2_set_apic_id(unsigne
 	return id << 24;
 }
 
-static int numachip_apic_id_valid(int apicid)
+static int numachip_apic_id_valid(u32 apicid)
 {
 	/* Trust what bootloader passes in MADT */
 	return 1;

@@ -1,6 +1,6 @@
 /* Common bits for X2APIC cluster/physical modes. */
 
-int x2apic_apic_id_valid(int apicid);
+int x2apic_apic_id_valid(u32 apicid);
 int x2apic_apic_id_registered(void);
 void __x2apic_send_IPI_dest(unsigned int apicid, int vector, unsigned int dest);
 unsigned int x2apic_get_apic_id(unsigned long id);

@@ -101,7 +101,7 @@ static int x2apic_phys_probe(void)
 }
 
 /* Common x2apic functions, also used by x2apic_cluster */
-int x2apic_apic_id_valid(int apicid)
+int x2apic_apic_id_valid(u32 apicid)
 {
 	return 1;
 }

@@ -554,7 +554,7 @@ static void uv_send_IPI_all(int vector)
 	uv_send_IPI_mask(cpu_online_mask, vector);
 }
 
-static int uv_apic_id_valid(int apicid)
+static int uv_apic_id_valid(u32 apicid)
 {
 	return 1;
 }

@@ -112,7 +112,7 @@ static int xen_madt_oem_check(char *oem_
 	return xen_pv_domain();
 }
 
-static int xen_id_always_valid(int apicid)
+static int xen_id_always_valid(u32 apicid)
 {
 	return 1;
 }

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

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

From: Eric Biggers <[email protected]>

commit f3aefb6a7066e24bfea7fcf1b07907576de69d63 upstream.

make_checksum_hmac_md5() is allocating an HMAC transform and doing crypto API calls in the following order:

crypto_ahash_init()
crypto_ahash_setkey()
crypto_ahash_digest()

This is wrong because it makes no sense to init() the request before a key has been set, given that the initial state depends on the key. And digest() is short for init() + update() + final(), so in this case there's no need to explicitly call init() at all.

Before commit 9fa68f620041 ("crypto: hash - prevent using keyed hashes without setting key") the extra init() had no real effect, at least for the software HMAC implementation. (There are also hardware drivers that implement HMAC-MD5, and it's not immediately obvious how gracefully they handle init() before setkey().) But now the crypto API detects this incorrect initialization and returns -ENOKEY. This is breaking NFS mounts in some cases.

Fix it by removing the incorrect call to crypto_ahash_init().

---
 net/sunrpc/auth_gss/gss_krb5_crypto.c |    3 ---
 1 file changed, 3 deletions(-)

@@ -237,9 +237,6 @@ make_checksum_hmac_md5(struct krb5_ctx *
 
 	ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL);
 
-	err = crypto_ahash_init(req);
-	if (err)
-		goto out;
 	err = crypto_ahash_setkey(hmac_md5, cksumkey, kctx->gk5e->keylength);
 	if (err)
 		goto out;

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

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

From: Yunlong Song <[email protected]>

commit b94929d975c8423defc9aededb0f499ff936b509 upstream.

Commit 7a20b8a61eff81bdb7097a578752a74860e9d142 ("f2fs: allocate node and hot data in the beginning of partition") introduces another mount option, heap, to reset it back. But it does not do anything for heap mode, so fix it.

---
 fs/f2fs/gc.c      |    5 +++--
 fs/f2fs/segment.c |    3 ++-
 2 files changed, 5 insertions(+), 3 deletions(-)

@@ -191,8 +191,9 @@ static void select_policy(struct f2fs_sb
 	if (gc_type != FG_GC && p->max_search > sbi->max_victim_search)
 		p->max_search = sbi->max_victim_search;
 
-	/* let's select beginning hot/small space first */
-	if (type == CURSEG_HOT_DATA || IS_NODESEG(type))
+	/* let's select beginning hot/small space first in no_heap mode*/
+	if (test_opt(sbi, NOHEAP) &&
+		(type == CURSEG_HOT_DATA || IS_NODESEG(type)))
 		p->offset = 0;
 	else
 		p->offset = SIT_I(sbi)->last_victim[p->gc_mode];

@@ -2155,7 +2155,8 @@ static unsigned int __get_next_segno(str
 	if (sbi->segs_per_sec != 1)
 		return CURSEG_I(sbi, type)->segno;
 
-	if (type == CURSEG_HOT_DATA || IS_NODESEG(type))
+	if (test_opt(sbi, NOHEAP) &&
+		(type == CURSEG_HOT_DATA || IS_NODESEG(type)))
 		return 0;
 
 	if (SIT_I(sbi)->last_victim[ALLOC_NEXT])

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

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

From: Bart Van Assche <[email protected]>

commit 818e0fa293ca836eba515615c64680ea916fd7cd upstream.

scsi_device_quiesce() uses synchronize_rcu() to guarantee that the effect of blk_set_preempt_only() will be visible for percpu_ref_tryget() calls that occur after the queue unfreeze by using the approach explained in https://lwn.net/Articles/573497/. The rcu read lock and unlock calls in blk_queue_enter() form a pair with the synchronize_rcu() call in scsi_device_quiesce(). Both scsi_device_quiesce() and blk_queue_enter() must either use regular RCU or RCU-sched. Since neither the RCU-protected code in blk_queue_enter() nor blk_queue_usage_counter_release() sleeps, regular RCU protection is sufficient. Note: scsi_device_quiesce() does not have to be modified since it already uses synchronize_rcu().

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

@@ -823,7 +823,7 @@ int blk_queue_enter(struct request_queue
 		bool success = false;
 		int ret;
 
-		rcu_read_lock_sched();
+		rcu_read_lock();
 		if (percpu_ref_tryget_live(&q->q_usage_counter)) {
 			/*
 			 * The code that sets the PREEMPT_ONLY flag is

@@ -836,7 +836,7 @@ int blk_queue_enter(struct request_queue
 				percpu_ref_put(&q->q_usage_counter);
 			}
 		}
-		rcu_read_unlock_sched();
+		rcu_read_unlock();
 
 		if (success)
 			return 0;

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

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

From: Keith Busch <[email protected]>

commit 2079699c10c8c60a9572540c2f77d045abf036eb upstream.

If a task is holding a reference to a namespace on a removed controller, the head will not be released. If the same controller is added again later, its namespaces may not be successfully added. Instead, the user will see kernel message "Duplicate IDs for nsid <X>".

This patch fixes that by skipping heads that don't have namespaces when considering if a new namespace is safe to add.

---
 drivers/nvme/host/core.c |    1 +
 1 file changed, 1 insertion(+)

@@ -2720,6 +2720,7 @@ static int __nvme_check_ids(struct nvme_
 
 	list_for_each_entry(h, &subsys->nsheads, entry) {
 		if (nvme_ns_ids_valid(&new->ids) &&
+		    !list_empty(&h->list) &&
 		    nvme_ns_ids_equal(&new->ids, &h->ids))
 			return -EINVAL;
 	}

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

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

From: Yury Norov <[email protected]>

commit 8351760ff5b2042039554b4948ddabaac644a976 upstream.

syzbot is catching stalls at __bitmap_parselist()
(https://syzkaller.appspot.com/bug?id=ad7e0351fbc90535558514a71cd3edc11681997a).
The trigger is

  unsigned long v = 0;
  bitmap_parselist("7:,", &v, BITS_PER_LONG);

which results in hitting infinite loop at

    while (a <= b) {
	    off = min(b - a + 1, used_size);
	    bitmap_set(maskp, a, off);
	    a += group_size;
    }

due to used_size == group_size == 0.

---
 lib/bitmap.c      |    2 +-
 lib/test_bitmap.c |    4 ++++
 2 files changed, 5 insertions(+), 1 deletion(-)

@@ -607,7 +607,7 @@ static int __bitmap_parselist(const char
 		/* if no digit is after '-', it's wrong*/
 		if (at_start && in_range)
 			return -EINVAL;
-		if (!(a <= b) || !(used_size <= group_size))
+		if (!(a <= b) || group_size == 0 || !(used_size <= group_size))
 			return -EINVAL;
 		if (b >= nmaskbits)
 			return -ERANGE;

@@ -218,6 +218,10 @@ static const struct test_bitmap_parselis
 	{-EINVAL, "-1",	NULL, 8, 0},
 	{-EINVAL, "-0",	NULL, 8, 0},
 	{-EINVAL, "10-1", NULL, 8, 0},
+	{-EINVAL, "0-31:", NULL, 8, 0},
+	{-EINVAL, "0-31:0", NULL, 8, 0},
+	{-EINVAL, "0-31:0/0", NULL, 8, 0},
+	{-EINVAL, "0-31:1/0", NULL, 8, 0},
 	{-EINVAL, "0-31:10/1", NULL, 8, 0},
 };
 

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

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

From: Ming Lei <[email protected]>

commit 0bca799b92807ee9be0890690f5dde7d8c6a8e25 upstream.

This patch orders getting budget and driver tag by making sure to acquire driver tag after budget is got, this way can help to avoid the following race:

1) before dispatch request from scheduler queue, get one budget first, then dequeue a request, call it request A.

2) in another IO path for dispatching request B which is from hctx->dispatch, driver tag is got, then try to get budget in blk_mq_dispatch_rq_list(), unfortunately the budget is held by request A.

3) meantime blk_mq_dispatch_rq_list() is called for dispatching request A, and try to get driver tag first, unfortunately no driver tag is available because the driver tag is held by request B

4) both two IO pathes can't move on, and IO stall is caused.

This issue can be observed when running dbench on USB storage.

This patch fixes this issue by always getting budget before getting driver tag.

---
 block/blk-mq.c |   21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)

@@ -1096,7 +1096,12 @@ bool blk_mq_dispatch_rq_list(struct requ
 		blk_status_t ret;
 
 		rq = list_first_entry(list, struct request, queuelist);
-		if (!blk_mq_get_driver_tag(rq, &hctx, false)) {
+
+		hctx = blk_mq_map_queue(rq->q, rq->mq_ctx->cpu);
+		if (!got_budget && !blk_mq_get_dispatch_budget(hctx))
+			break;
+
+		if (!blk_mq_get_driver_tag(rq, NULL, false)) {
 			/*
 			 * The initial allocation attempt failed, so we need to
 			 * rerun the hardware queue when a tag is freed. The

@@ -1105,8 +1110,7 @@ bool blk_mq_dispatch_rq_list(struct requ
 			 * we'll re-run it below.
 			 */
 			if (!blk_mq_mark_tag_wait(&hctx, rq)) {
-				if (got_budget)
-					blk_mq_put_dispatch_budget(hctx);
+				blk_mq_put_dispatch_budget(hctx);
 				/*
 				 * For non-shared tags, the RESTART check
 				 * will suffice.

@@ -1117,11 +1121,6 @@ bool blk_mq_dispatch_rq_list(struct requ
 			}
 		}
 
-		if (!got_budget && !blk_mq_get_dispatch_budget(hctx)) {
-			blk_mq_put_driver_tag(rq);
-			break;
-		}
-
 		list_del_init(&rq->queuelist);
 
 		bd.rq = rq;

@@ -1619,11 +1618,11 @@ static void __blk_mq_try_issue_directly(
 	if (q->elevator)
 		goto insert;
 
-	if (!blk_mq_get_driver_tag(rq, NULL, false))
+	if (!blk_mq_get_dispatch_budget(hctx))
 		goto insert;
 
-	if (!blk_mq_get_dispatch_budget(hctx)) {
-		blk_mq_put_driver_tag(rq);
+	if (!blk_mq_get_driver_tag(rq, NULL, false)) {
+		blk_mq_put_dispatch_budget(hctx);
 		goto insert;
 	}
 

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

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

From: Ming Lei <[email protected]>

commit bffa9909a6b48d8ca3398dec601bc9162a4020c4 upstream.

blk-mq doesn't remap queue after CPU topo is changed, that said when some of these offline CPUs become online, they are still mapped to hctx 0, then hctx 0 may become the bottleneck of IO dispatch and completion.

This patch sets up the mapping from the beginning, and aligns to queue mapping for PCI device (blk_mq_pci_map_queues()).

---
 block/blk-mq-cpumap.c |    5 -----
 1 file changed, 5 deletions(-)

@@ -16,11 +16,6 @@
 
 static int cpu_to_queue_index(unsigned int nr_queues, const int cpu)
 {
-	/*
-	 * Non present CPU will be mapped to queue index 0.
-	 */
-	if (!cpu_present(cpu))
-		return 0;
 	return cpu % nr_queues;
 }
 

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

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

From: Amir Goldstein <[email protected]>

commit 3ec9b3fafcaf441cc4d46b9742cd6ec0c79f8df0 upstream.

As of now if we encounter an opaque dir while looking for a dentry, we set d->last=true. This means that there is no need to look further in any of the lower layers. This works fine as long as there are no redirets or relative redircts. But what if there is an absolute redirect on the children dentry of opaque directory. We still need to continue to look into next lower layer. This patch fixes it.

Here is an example to demonstrate the issue. Say you have following setup.

upper:  /redirect (redirect=/a/b/c)
lower1: /a/[b]/c       ([b] is opaque) (c has absolute redirect=/a/b/d/)
lower0: /a/b/d/foo

Now "redirect" dir should merge with lower1:/a/b/c/ and lower0:/a/b/d. Note, despite the fact lower1:/a/[b] is opaque, we need to continue to look into lower0 because children c has an absolute redirect.

Following is a reproducer.

Watch me make foo disappear:

 $ mkdir lower middle upper work work2 merged
 $ mkdir lower/origin
 $ touch lower/origin/foo
 $ mount -t overlay none merged/ \
         -olowerdir=lower,upperdir=middle,workdir=work2
 $ mkdir merged/pure
 $ mv merged/origin merged/pure/redirect
 $ umount merged
 $ mount -t overlay none merged/ \
         -olowerdir=middle:lower,upperdir=upper,workdir=work
 $ mv merged/pure/redirect merged/redirect

Now you see foo inside a twice redirected merged dir:

 $ ls merged/redirect
 foo
 $ umount merged
 $ mount -t overlay none merged/ \
         -olowerdir=middle:lower,upperdir=upper,workdir=work

After mount cycle you don't see foo inside the same dir:

 $ ls merged/redirect

During middle layer lookup, the opaqueness of middle/pure is left in the lookup state and then middle/pure/redirect is wrongly treated as opaque.

---
 fs/overlayfs/namei.c |    9 +++++++++
 1 file changed, 9 insertions(+)

@@ -55,6 +55,15 @@ static int ovl_check_redirect(struct den
 			if (s == next)
 				goto invalid;
 		}
+		/*
+		 * One of the ancestor path elements in an absolute path
+		 * lookup in ovl_lookup_layer() could have been opaque and
+		 * that will stop further lookup in lower layers (d->stop=true)
+		 * But we have found an absolute redirect in decendant path
+		 * element and that should force continue lookup in lower
+		 * layers (reset d->stop).
+		 */
+		d->stop = false;
 	} else {
 		if (strchr(buf, '/') != NULL)
 			goto invalid;

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

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

From: Simon Gaiser <[email protected]>

commit 2a22ee6c3ab1d761bc9c04f1e4117edd55b82f09 upstream.

Commit fd8aa9095a95 ("xen: optimize xenbus driver for multiple concurrent xenstore accesses") made a subtle change to the semantic of xenbus_dev_request_and_reply() and xenbus_transaction_end().

Before on an error response to XS_TRANSACTION_END xenbus_dev_request_and_reply() would not decrement the active transaction counter. But xenbus_transaction_end() has always counted the transaction as finished regardless of the response.

The new behavior is that xenbus_dev_request_and_reply() and xenbus_transaction_end() will always count the transaction as finished regardless the response code (handled in xs_request_exit()).

But xenbus_dev_frontend tries to end a transaction on closing of the device if the XS_TRANSACTION_END failed before. Trying to close the transaction twice corrupts the reference count. So fix this by also considering a transaction closed if we have sent XS_TRANSACTION_END once regardless of the return code.

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

@@ -365,7 +365,7 @@ void xenbus_dev_queue_reply(struct xb_re
 			if (WARN_ON(rc))
 				goto out;
 		}
-	} else if (req->msg.type == XS_TRANSACTION_END) {
+	} else if (req->type == XS_TRANSACTION_END) {
 		trans = xenbus_get_transaction(u, req->msg.tx_id);
 		if (WARN_ON(!trans))
 			goto out;

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

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

From: Mike Kravetz <[email protected]>

commit 5df63c2a149ae65a9ec239e7c2af44efa6f79beb upstream.

This is a fix for a regression in 32 bit kernels caused by an invalid check for pgoff overflow in hugetlbfs mmap setup. The check incorrectly specified that the size of a loff_t was the same as the size of a long. The regression prevents mapping hugetlbfs files at offsets greater than 4GB on 32 bit kernels.

On 32 bit kernels conversion from a page based unsigned long can not overflow a loff_t byte offset. Therefore, skip this check if sizeof(unsigned long) != sizeof(loff_t).

---
 fs/hugetlbfs/inode.c |   10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

@@ -148,10 +148,14 @@ static int hugetlbfs_file_mmap(struct fi
 
 	/*
 	 * page based offset in vm_pgoff could be sufficiently large to
-	 * overflow a (l)off_t when converted to byte offset.
+	 * overflow a loff_t when converted to byte offset.  This can
+	 * only happen on architectures where sizeof(loff_t) ==
+	 * sizeof(unsigned long).  So, only check in those instances.
 	 */
-	if (vma->vm_pgoff & PGOFF_LOFFT_MAX)
-		return -EINVAL;
+	if (sizeof(unsigned long) == sizeof(loff_t)) {
+		if (vma->vm_pgoff & PGOFF_LOFFT_MAX)
+			return -EINVAL;
+	}
 
 	/* must be huge page aligned */
 	if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT))

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

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

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

commit 880a3a5325489a143269a8e172e7563ebf9897bc upstream.

We're neglecting to clear the umask after it's set, which can cause a later unrelated rpc to (incorrectly) use the same umask if it happens to be processed by the same thread.

There's a more subtle problem here too:

An NFSv4 compound request is decoded all in one pass before any operations are executed.

Currently we're setting current->fs->umask at the time we decode the compound. In theory a single compound could contain multiple creates each setting a umask. In that case we'd end up using whichever umask was passed in the *last* operation as the umask for all the creates, whether that was correct or not.

So, we should just be saving the umask at decode time and waiting to set it until we actually process the corresponding operation.

In practice it's unlikely any client would do multiple creates in a single compound. And even if it did they'd likely be from the same process (hence carry the same umask). So this is a little academic, but we should get it right anyway.

---
 fs/nfsd/nfs4proc.c |   12 ++++++++++--
 fs/nfsd/nfs4xdr.c  |    8 +++-----
 fs/nfsd/xdr4.h     |    2 ++
 3 files changed, 15 insertions(+), 7 deletions(-)

@@ -32,6 +32,7 @@
  *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
  *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
+#include <linux/fs_struct.h>
 #include <linux/file.h>
 #include <linux/falloc.h>
 #include <linux/slab.h>

@@ -252,11 +253,13 @@ do_open_lookup(struct svc_rqst *rqstp, s
 		 * Note: create modes (UNCHECKED,GUARDED...) are the same
 		 * in NFSv4 as in v3 except EXCLUSIVE4_1.
 		 */
+		current->fs->umask = open->op_umask;
 		status = do_nfsd_create(rqstp, current_fh, open->op_fname.data,
 					open->op_fname.len, &open->op_iattr,
 					*resfh, open->op_createmode,
 					(u32 *)open->op_verf.data,
 					&open->op_truncate, &open->op_created);
+		current->fs->umask = 0;
 
 		if (!status && open->op_label.len)
 			nfsd4_security_inode_setsecctx(*resfh, &open->op_label, open->op_bmval);

@@ -603,6 +606,7 @@ nfsd4_create(struct svc_rqst *rqstp, str
 	if (status)
 		return status;
 
+	current->fs->umask = create->cr_umask;
 	switch (create->cr_type) {
 	case NF4LNK:
 		status = nfsd_symlink(rqstp, &cstate->current_fh,

@@ -611,20 +615,22 @@ nfsd4_create(struct svc_rqst *rqstp, str
 		break;
 
 	case NF4BLK:
+		status = nfserr_inval;
 		rdev = MKDEV(create->cr_specdata1, create->cr_specdata2);
 		if (MAJOR(rdev) != create->cr_specdata1 ||
 		    MINOR(rdev) != create->cr_specdata2)
-			return nfserr_inval;
+			goto out_umask;
 		status = nfsd_create(rqstp, &cstate->current_fh,
 				     create->cr_name, create->cr_namelen,
 				     &create->cr_iattr, S_IFBLK, rdev, &resfh);
 		break;
 
 	case NF4CHR:
+		status = nfserr_inval;
 		rdev = MKDEV(create->cr_specdata1, create->cr_specdata2);
 		if (MAJOR(rdev) != create->cr_specdata1 ||
 		    MINOR(rdev) != create->cr_specdata2)
-			return nfserr_inval;
+			goto out_umask;
 		status = nfsd_create(rqstp, &cstate->current_fh,
 				     create->cr_name, create->cr_namelen,
 				     &create->cr_iattr,S_IFCHR, rdev, &resfh);

@@ -668,6 +674,8 @@ nfsd4_create(struct svc_rqst *rqstp, str
 	fh_dup2(&cstate->current_fh, &resfh);
 out:
 	fh_put(&resfh);
+out_umask:
+	current->fs->umask = 0;
 	return status;
 }
 

@@ -33,7 +33,6 @@
  *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 
-#include <linux/fs_struct.h>
 #include <linux/file.h>
 #include <linux/slab.h>
 #include <linux/namei.h>

@@ -683,7 +682,7 @@ nfsd4_decode_create(struct nfsd4_compoun
 
 	status = nfsd4_decode_fattr(argp, create->cr_bmval, &create->cr_iattr,
 				    &create->cr_acl, &create->cr_label,
-				    &current->fs->umask);
+				    &create->cr_umask);
 	if (status)
 		goto out;
 

@@ -928,7 +927,6 @@ nfsd4_decode_open(struct nfsd4_compounda
 	case NFS4_OPEN_NOCREATE:
 		break;
 	case NFS4_OPEN_CREATE:
-		current->fs->umask = 0;
 		READ_BUF(4);
 		open->op_createmode = be32_to_cpup(p++);
 		switch (open->op_createmode) {

@@ -936,7 +934,7 @@ nfsd4_decode_open(struct nfsd4_compounda
 		case NFS4_CREATE_GUARDED:
 			status = nfsd4_decode_fattr(argp, open->op_bmval,
 				&open->op_iattr, &open->op_acl, &open->op_label,
-				&current->fs->umask);
+				&open->op_umask);
 			if (status)
 				goto out;
 			break;

@@ -951,7 +949,7 @@ nfsd4_decode_open(struct nfsd4_compounda
 			COPYMEM(open->op_verf.data, NFS4_VERIFIER_SIZE);
 			status = nfsd4_decode_fattr(argp, open->op_bmval,
 				&open->op_iattr, &open->op_acl, &open->op_label,
-				&current->fs->umask);
+				&open->op_umask);
 			if (status)
 				goto out;
 			break;

@@ -118,6 +118,7 @@ struct nfsd4_create {
 	} u;
 	u32		cr_bmval[3];        /* request */
 	struct iattr	cr_iattr;           /* request */
+	int		cr_umask;           /* request */
 	struct nfsd4_change_info  cr_cinfo; /* response */
 	struct nfs4_acl *cr_acl;
 	struct xdr_netobj cr_label;

@@ -228,6 +229,7 @@ struct nfsd4_open {
 	u32		op_why_no_deleg;    /* response - DELEG_NONE_EXT only */
 	u32		op_create;     	    /* request */
 	u32		op_createmode;      /* request */
+	int		op_umask;           /* request */
 	u32		op_bmval[3];        /* request */
 	struct iattr	op_iattr;           /* UNCHECKED4, GUARDED4, EXCLUSIVE4_1 */
 	nfs4_verifier	op_verf __attribute__((aligned(32)));

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

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

From: Bill Kuzeja <[email protected]>

commit 6d6340672ba3a99c4cf7af79c2edf7aa25595c84 upstream.

The code that fixes the crashes in the following commit introduced a small memory leak:

commit 6a2cf8d3663e ("scsi: qla2xxx: Fix crashes in qla2x00_probe_one on probe failure")

Fixing this requires a bit of reworking, which I've explained. Also provide some code cleanup.

There is a small window in qla2x00_probe_one where if qla2x00_alloc_queues fails, we end up never freeing req and rsp and leak 0xc0 and 0xc8 bytes respectively (the sizes of req and rsp).

I originally put in checks to test for this condition which were based on the incorrect assumption that if ha->rsp_q_map and ha->req_q_map were allocated, then rsp and req were allocated as well. This is incorrect. There is a window between these allocations:

       ret = qla2x00_mem_alloc(ha, req_length, rsp_length, &req, &rsp);
                goto probe_hw_failed;

[if successful, both rsp and req allocated]

       base_vha = qla2x00_create_host(sht, ha);
                goto probe_hw_failed;

       ret = qla2x00_request_irqs(ha, rsp);
                goto probe_failed;

       if (qla2x00_alloc_queues(ha, req, rsp)) {
                goto probe_failed;

[if successful, now ha->rsp_q_map and ha->req_q_map allocated]

To simplify this, we should just set req and rsp to NULL after we free them. Sounds simple enough? The problem is that req and rsp are pointers defined in the qla2x00_probe_one and they are not always passed by reference to the routines that free them.

Here are paths which can free req and rsp:

PATH 1:
qla2x00_probe_one
ret = qla2x00_mem_alloc(ha, req_length, rsp_length, &req, &rsp); [req and rsp are passed by reference, but if this fails, we currently
do not NULL out req and rsp. Easily fixed]

PATH 2:
qla2x00_probe_one
failing in qla2x00_request_irqs or qla2x00_alloc_queues

      probe_failed:
         qla2x00_free_device(base_vha);
            qla2x00_free_req_que(ha, req)
            qla2x00_free_rsp_que(ha, rsp)

PATH 3:
qla2x00_probe_one:
failing in qla2x00_mem_alloc or qla2x00_create_host

      probe_hw_failed:
         qla2x00_free_req_que(ha, req)
         qla2x00_free_rsp_que(ha, rsp)

PATH 1: This should currently work, but it doesn't because rsp and rsp are not set to NULL in qla2x00_mem_alloc. Easily remedied.

PATH 2: req and rsp aren't passed in at all to qla2x00_free_device but are derived from ha->req_q_map[0] and ha->rsp_q_map[0]. These are only set up if qla2x00_alloc_queues succeeds.

In qla2x00_free_queues, we are protected from crashing if these don't exist because req_qid_map and rsp_qid_map are only set on their allocation. We are guarded in this way:

        for (cnt = 0; cnt < ha->max_req_queues; cnt++) {
                if (!test_bit(cnt, ha->req_qid_map))
                        continue;

PATH 3: This works. We haven't freed req or rsp yet (or they were never allocated if qla2x00_mem_alloc failed), so we'll attempt to free them here.

To summarize, there are a few small changes to make this work correctly and (and for some cleanup):

1) (For PATH 1) Set *rsp and *req to NULL in case of failure in qla2x00_mem_alloc so these are correctly set to NULL back in qla2x00_probe_one

2) After jumping to probe_failed: and calling qla2x00_free_device, explicitly set rsp and req to NULL so further calls with these pointers do not crash, i.e. the free queue calls in the probe_hw_failed section we fall through to.

3) Fix return code check in the call to qla2x00_alloc_queues. We currently drop the return code on the floor. The probe fails but the caller of the probe doesn't have an error code, so it attaches to pci. This can result in a crash on module shutdown.

4) Remove unnecessary NULL checks in qla2x00_free_req_que, qla2x00_free_rsp_que, and the egregious NULL checks before kfrees and vfrees in qla2x00_mem_free.

I tested this out running a scenario where the card breaks at various times during initialization. I made sure I forced every error exit path in qla2x00_probe_one.

---
 drivers/scsi/qla2xxx/qla_os.c |   44 ++++++++++++++++++++----------------------
 1 file changed, 21 insertions(+), 23 deletions(-)

@@ -466,9 +466,6 @@ fail_req_map:
 
 static void qla2x00_free_req_que(struct qla_hw_data *ha, struct req_que *req)
 {
-	if (!ha->req_q_map)
-		return;
-
 	if (IS_QLAFX00(ha)) {
 		if (req && req->ring_fx00)
 			dma_free_coherent(&ha->pdev->dev,

@@ -479,17 +476,14 @@ static void qla2x00_free_req_que(struct
 		(req->length + 1) * sizeof(request_t),
 		req->ring, req->dma);
 
-	if (req) {
+	if (req)
 		kfree(req->outstanding_cmds);
-		kfree(req);
-	}
+
+	kfree(req);
 }
 
 static void qla2x00_free_rsp_que(struct qla_hw_data *ha, struct rsp_que *rsp)
 {
-	if (!ha->rsp_q_map)
-		return;
-
 	if (IS_QLAFX00(ha)) {
 		if (rsp && rsp->ring)
 			dma_free_coherent(&ha->pdev->dev,

@@ -500,8 +494,7 @@ static void qla2x00_free_rsp_que(struct
 		(rsp->length + 1) * sizeof(response_t),
 		rsp->ring, rsp->dma);
 	}
-	if (rsp)
-		kfree(rsp);
+	kfree(rsp);
 }
 
 static void qla2x00_free_queues(struct qla_hw_data *ha)

@@ -3083,7 +3076,8 @@ qla2x00_probe_one(struct pci_dev *pdev,
 		goto probe_failed;
 
 	/* Alloc arrays of request and response ring ptrs */
-	if (qla2x00_alloc_queues(ha, req, rsp)) {
+	ret = qla2x00_alloc_queues(ha, req, rsp);
+	if (ret) {
 		ql_log(ql_log_fatal, base_vha, 0x003d,
 		    "Failed to allocate memory for queue pointers..."
 		    "aborting.\n");

@@ -3384,8 +3378,15 @@ probe_failed:
 	}
 
 	qla2x00_free_device(base_vha);
-
 	scsi_host_put(base_vha->host);
+	/*
+	 * Need to NULL out local req/rsp after
+	 * qla2x00_free_device => qla2x00_free_queues frees
+	 * what these are pointing to. Or else we'll
+	 * fall over below in qla2x00_free_req/rsp_que.
+	 */
+	req = NULL;
+	rsp = NULL;
 
 probe_hw_failed:
 	qla2x00_mem_free(ha);

@@ -4078,6 +4079,7 @@ fail_npiv_info:
 	(*rsp)->dma = 0;
 fail_rsp_ring:
 	kfree(*rsp);
+	*rsp = NULL;
 fail_rsp:
 	dma_free_coherent(&ha->pdev->dev, ((*req)->length + 1) *
 		sizeof(request_t), (*req)->ring, (*req)->dma);

@@ -4085,6 +4087,7 @@ fail_rsp:
 	(*req)->dma = 0;
 fail_req_ring:
 	kfree(*req);
+	*req = NULL;
 fail_req:
 	dma_free_coherent(&ha->pdev->dev, sizeof(struct ct_sns_pkt),
 		ha->ct_sns, ha->ct_sns_dma);

@@ -4452,16 +4455,11 @@ qla2x00_mem_free(struct qla_hw_data *ha)
 		dma_free_coherent(&ha->pdev->dev, ha->init_cb_size,
 			ha->init_cb, ha->init_cb_dma);
 
-	if (ha->optrom_buffer)
-		vfree(ha->optrom_buffer);
-	if (ha->nvram)
-		kfree(ha->nvram);
-	if (ha->npiv_info)
-		kfree(ha->npiv_info);
-	if (ha->swl)
-		kfree(ha->swl);
-	if (ha->loop_id_map)
-		kfree(ha->loop_id_map);
+	vfree(ha->optrom_buffer);
+	kfree(ha->nvram);
+	kfree(ha->npiv_info);
+	kfree(ha->swl);
+	kfree(ha->loop_id_map);
 
 	ha->srb_mempool = NULL;
 	ha->ctx_mempool = NULL;

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

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

From: John Johansen <[email protected]>

commit 98cf5bbff413eadf1b9cb195a7b80cc61c72a50e upstream.

The existence test is not being properly logged as the signal mapping maps it to the last entry in the named signal table. This is done to help catch bugs by making the 0 mapped signal value invalid so that we can catch the signal value not being filled in.

When fixing the off-by-one comparision logic the reporting of the existence test was broken, because the logic behind the mapped named table was hidden. Fix this by adding a define for the name lookup and using it.

---
 security/apparmor/include/sig_names.h |    4 +++-
 security/apparmor/ipc.c               |    2 +-
 2 files changed, 4 insertions(+), 2 deletions(-)

@@ -2,6 +2,8 @@
 
 #define SIGUNKNOWN 0
 #define MAXMAPPED_SIG 35
+#define MAXMAPPED_SIGNAME (MAXMAPPED_SIG + 1)
+
 /* provide a mapping of arch signal to internal signal # for mediation
  * those that are always an alias SIGCLD for SIGCLHD and SIGPOLL for SIGIO
  * map to the same entry those that may/or may not get a separate entry

@@ -56,7 +58,7 @@ static const int sig_map[MAXMAPPED_SIG]
 };
 
 /* this table is ordered post sig_map[sig] mapping */
-static const char *const sig_names[MAXMAPPED_SIG + 1] = {
+static const char *const sig_names[MAXMAPPED_SIGNAME] = {
 	"unknown",
 	"hup",
 	"int",

@@ -174,7 +174,7 @@ static void audit_signal_cb(struct audit
 			audit_signal_mask(ab, aad(sa)->denied);
 		}
 	}
-	if (aad(sa)->signal < MAXMAPPED_SIG)
+	if (aad(sa)->signal < MAXMAPPED_SIGNAME)
 		audit_log_format(ab, " signal=%s", sig_names[aad(sa)->signal]);
 	else
 		audit_log_format(ab, " signal=rtmin+%d",

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

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

From: John Johansen <[email protected]>

commit 040d9e2bce0a5b321c402b79ee43a8e8d2fd3b06 upstream.

The .ns_name should not be virtualized by the current ns view. It needs to report the ns base name as that is being used during startup as part of determining apparmor policy namespace support.

---
 security/apparmor/apparmorfs.c |    4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

@@ -1189,9 +1189,7 @@ static int seq_ns_level_show(struct seq_
 static int seq_ns_name_show(struct seq_file *seq, void *v)
 {
 	struct aa_label *label = begin_current_label_crit_section();
-
-	seq_printf(seq, "%s\n", aa_ns_name(labels_ns(label),
-					   labels_ns(label), true));
+	seq_printf(seq, "%s\n", labels_ns(label)->base.name);
 	end_current_label_crit_section(label);
 
 	return 0;

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

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

From: John Johansen <[email protected]>

commit b5beb07ad32ab533027aa988d96a44965ec116f7 upstream.

Resource auditing is using the peer field which is not available when the rlim data struct is used, because it is a different element of the same union. Accessing peer during resource auditing could cause garbage log entries or even oops the kernel.

Move the rlim data block into the same struct as the peer field so they can be used together.

---
 security/apparmor/include/audit.h |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

@@ -126,6 +126,10 @@ struct apparmor_audit_data {
 					const char *target;
 					kuid_t ouid;
 				} fs;
+				struct {
+					int rlim;
+					unsigned long max;
+				} rlim;
 				int signal;
 			};
 		};

@@ -135,10 +139,6 @@ struct apparmor_audit_data {
 			long pos;
 		} iface;
 		struct {
-			int rlim;
-			unsigned long max;
-		} rlim;
-		struct {
 			const char *src_name;
 			const char *type;
 			const char *trans;

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

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

From: Tetsuo Handa <[email protected]>

commit 1e047eaab3bb5564f25b41e9cd3a053009f4e789 upstream.

syzbot is reporting deadlocks at __blkdev_get() [1].

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

[   92.493919] systemd-udevd   D12696   525      1 0x00000000
[   92.495891] Call Trace:
[   92.501560]  schedule+0x23/0x80
[   92.502923]  schedule_preempt_disabled+0x5/0x10
[   92.504645]  __mutex_lock+0x416/0x9e0
[   92.510760]  __blkdev_get+0x73/0x4f0
[   92.512220]  blkdev_get+0x12e/0x390
[   92.518151]  do_dentry_open+0x1c3/0x2f0
[   92.519815]  path_openat+0x5d9/0xdc0
[   92.521437]  do_filp_open+0x7d/0xf0
[   92.527365]  do_sys_open+0x1b8/0x250
[   92.528831]  do_syscall_64+0x6e/0x270
[   92.530341]  entry_SYSCALL_64_after_hwframe+0x42/0xb7

[   92.931922] 1 lock held by systemd-udevd/525:
[   92.933642]  #0: 00000000a2849e25 (&bdev->bd_mutex){+.+.}, at: __blkdev_get+0x73/0x4f0

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

The reason of deadlock turned out that wait_event_interruptible() in blk_queue_enter() got stuck with bdev->bd_mutex held at __blkdev_put() due to q->mq_freeze_depth == 1.

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

[   92.787172] a.out           S12584   634    633 0x80000002
[   92.789120] Call Trace:
[   92.796693]  schedule+0x23/0x80
[   92.797994]  blk_queue_enter+0x3cb/0x540
[   92.803272]  generic_make_request+0xf0/0x3d0
[   92.807970]  submit_bio+0x67/0x130
[   92.810928]  submit_bh_wbc+0x15e/0x190
[   92.812461]  __block_write_full_page+0x218/0x460
[   92.815792]  __writepage+0x11/0x50
[   92.817209]  write_cache_pages+0x1ae/0x3d0
[   92.825585]  generic_writepages+0x5a/0x90
[   92.831865]  do_writepages+0x43/0xd0
[   92.836972]  __filemap_fdatawrite_range+0xc1/0x100
[   92.838788]  filemap_write_and_wait+0x24/0x70
[   92.840491]  __blkdev_put+0x69/0x1e0
[   92.841949]  blkdev_close+0x16/0x20
[   92.843418]  __fput+0xda/0x1f0
[   92.844740]  task_work_run+0x87/0xb0
[   92.846215]  do_exit+0x2f5/0xba0
[   92.850528]  do_group_exit+0x34/0xb0
[   92.852018]  SyS_exit_group+0xb/0x10
[   92.853449]  do_syscall_64+0x6e/0x270
[   92.854944]  entry_SYSCALL_64_after_hwframe+0x42/0xb7

[   92.943530] 1 lock held by a.out/634:
[   92.945105]  #0: 00000000a2849e25 (&bdev->bd_mutex){+.+.}, at: __blkdev_put+0x3c/0x1e0

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

The reason of q->mq_freeze_depth == 1 turned out that loop_set_status() forgot to call blk_mq_unfreeze_queue() at error paths for info->lo_encrypt_type != NULL case.

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

[   37.509497] CPU: 2 PID: 634 Comm: a.out Tainted: G        W        4.16.0+ #457
[   37.513608] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 05/19/2017
[   37.518832] RIP: 0010:blk_freeze_queue_start+0x17/0x40
[   37.521778] RSP: 0018:ffffb0c2013e7c60 EFLAGS: 00010246
[   37.524078] RAX: 0000000000000000 RBX: ffff8b07b1519798 RCX: 0000000000000000
[   37.527015] RDX: 0000000000000002 RSI: ffffb0c2013e7cc0 RDI: ffff8b07b1519798
[   37.529934] RBP: ffffb0c2013e7cc0 R08: 0000000000000008 R09: 47a189966239b898
[   37.532684] R10: dad78b99b278552f R11: 9332dca72259d5ef R12: ffff8b07acd73678
[   37.535452] R13: 0000000000004c04 R14: 0000000000000000 R15: ffff8b07b841e940
[   37.538186] FS:  00007fede33b9740(0000) GS:ffff8b07b8e80000(0000) knlGS:0000000000000000
[   37.541168] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   37.543590] CR2: 00000000206fdf18 CR3: 0000000130b30006 CR4: 00000000000606e0
[   37.546410] Call Trace:
[   37.547902]  blk_freeze_queue+0x9/0x30
[   37.549968]  loop_set_status+0x67/0x3c0 [loop]
[   37.549975]  loop_set_status64+0x3b/0x70 [loop]
[   37.549986]  lo_ioctl+0x223/0x810 [loop]
[   37.549995]  blkdev_ioctl+0x572/0x980
[   37.550003]  block_ioctl+0x34/0x40
[   37.550006]  do_vfs_ioctl+0xa7/0x6d0
[   37.550017]  ksys_ioctl+0x6b/0x80
[   37.573076]  SyS_ioctl+0x5/0x10
[   37.574831]  do_syscall_64+0x6e/0x270
[   37.576769]  entry_SYSCALL_64_after_hwframe+0x42/0xb7

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

[1] https://syzkaller.appspot.com/bug?id=cd662bc3f6022c0979d01a262c318fab2ee9b56f

---
 drivers/block/loop.c |   12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

@@ -1103,11 +1103,15 @@ loop_set_status(struct loop_device *lo,
 	if (info->lo_encrypt_type) {
 		unsigned int type = info->lo_encrypt_type;
 
-		if (type >= MAX_LO_CRYPT)
-			return -EINVAL;
+		if (type >= MAX_LO_CRYPT) {
+			err = -EINVAL;
+			goto exit;
+		}
 		xfer = xfer_funcs[type];
-		if (xfer == NULL)
-			return -EINVAL;
+		if (xfer == NULL) {
+			err = -EINVAL;
+			goto exit;
+		}
 	} else
 		xfer = NULL;
 

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

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

From: Dan Williams <[email protected]>

commit 8d0d8ed3356aa9ed43b819aaedd39b08ca453007 upstream.

Commit 1cf03c00e7c1 "nfit: scrub and register regions in a workqueue" mistakenly attempts to register a region per BLK aperture. There is nothing to register for individual apertures as they belong as a set to a BLK aperture group that are registered with a corresponding DIMM-control-region. Filter them for registration to prevent some needless devm_kzalloc() allocations.

---
 drivers/acpi/nfit/core.c |   22 ++++++++++++++--------
 1 file changed, 14 insertions(+), 8 deletions(-)

@@ -2998,15 +2998,21 @@ static void acpi_nfit_scrub(struct work_
 static int acpi_nfit_register_regions(struct acpi_nfit_desc *acpi_desc)
 {
 	struct nfit_spa *nfit_spa;
-	int rc;
 
-	list_for_each_entry(nfit_spa, &acpi_desc->spas, list)
-		if (nfit_spa_type(nfit_spa->spa) == NFIT_SPA_DCR) {
-			/* BLK regions don't need to wait for ars results */
-			rc = acpi_nfit_register_region(acpi_desc, nfit_spa);
-			if (rc)
-				return rc;
-		}
+	list_for_each_entry(nfit_spa, &acpi_desc->spas, list) {
+		int rc, type = nfit_spa_type(nfit_spa->spa);
+
+		/* PMEM and VMEM will be registered by the ARS workqueue */
+		if (type == NFIT_SPA_PM || type == NFIT_SPA_VOLATILE)
+			continue;
+		/* BLK apertures belong to BLK region registration below */
+		if (type == NFIT_SPA_BDW)
+			continue;
+		/* BLK regions don't need to wait for ARS results */
+		rc = acpi_nfit_register_region(acpi_desc, nfit_spa);
+		if (rc)
+			return rc;
+	}
 
 	acpi_desc->ars_start_flags = 0;
 	if (!acpi_desc->cancel)

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

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

From: Julian Wiedmann <[email protected]>

commit dae55b6fef58530c13df074bcc182c096609339e upstream.

Immediate retry of EQBS after CCQ 96 means that we potentially misreport the state of buffers inspected during the first EQBS call.

This occurs when
1. the first EQBS finds all inspected buffers still in the initial state set by the driver (ie INPUT EMPTY or OUTPUT PRIMED),
2. the EQBS terminates early with CCQ 96, and
3. by the time that the second EQBS comes around, the state of those previously inspected buffers has changed.

If the state reported by the second EQBS is 'driver-owned', all we know is that the previous buffers are driver-owned now as well. But we can't tell if they all have the same state. So for instance
- the second EQBS reports OUTPUT EMPTY, but any number of the previous buffers could be OUTPUT ERROR by now,
- the second EQBS reports OUTPUT ERROR, but any number of the previous buffers could be OUTPUT EMPTY by now.

Effectively, this can result in both over- and underreporting of errors.

If the state reported by the second EQBS is 'HW-owned', that doesn't guarantee that the previous buffers have not been switched to driver-owned in the mean time. So for instance
- the second EQBS reports INPUT EMPTY, but any number of the previous buffers could be INPUT PRIMED (or INPUT ERROR) by now.

This would result in failure to process pending work on the queue. If it's the final check before yielding initiative, this can cause a (temporary) queue stall due to IRQ avoidance.

---
 drivers/s390/cio/qdio_main.c |   11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

@@ -127,7 +127,7 @@ static inline int qdio_check_ccq(struct
 static int qdio_do_eqbs(struct qdio_q *q, unsigned char *state,
 			int start, int count, int auto_ack)
 {
-	int rc, tmp_count = count, tmp_start = start, nr = q->nr, retried = 0;
+	int rc, tmp_count = count, tmp_start = start, nr = q->nr;
 	unsigned int ccq = 0;
 
 	qperf_inc(q, eqbs);

@@ -150,14 +150,7 @@ again:
 		qperf_inc(q, eqbs_partial);
 		DBF_DEV_EVENT(DBF_WARN, q->irq_ptr, "EQBS part:%02x",
 			tmp_count);
-		/*
-		 * Retry once, if that fails bail out and process the
-		 * extracted buffers before trying again.
-		 */
-		if (!retried++)
-			goto again;
-		else
-			return count - tmp_count;
+		return count - tmp_count;
 	}
 
 	DBF_ERROR("%4x EQBS ERROR", SCH_NO(q));

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

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

From: Julian Wiedmann <[email protected]>

commit 0cf1e05157b9e5530dcc3ca9fec9bf617fc93375 upstream.

On an Output queue, both EMPTY and PENDING buffer states imply that the buffer is ready for completion-processing by the upper-layer drivers.

So for a non-QEBSM Output queue, get_buf_states() merges mixed batches of PENDING and EMPTY buffers into one large batch of EMPTY buffers. The upper-layer driver (ie. qeth) later distuingishes PENDING from EMPTY by inspecting the slsb_state for QDIO_OUTBUF_STATE_FLAG_PENDING.

But the merge logic in get_buf_states() contains a bug that causes us to erronously also merge ERROR buffers into such a batch of EMPTY buffers (ERROR is 0xaf, EMPTY is 0xa1; so ERROR & EMPTY == EMPTY). Effectively, most outbound ERROR buffers are currently discarded silently and processed as if they had succeeded.

Note that this affects _all_ non-QEBSM device types, not just IQD with CQ.

Fix it by explicitly spelling out the exact conditions for merging.

For extracting the "get initial state" part out of the loop, this relies on the fact that get_buf_states() is never called with a count of 0. The QEBSM path already strictly requires this, and the two callers with variable 'count' make sure of it.

---
 drivers/s390/cio/qdio_main.c |   31 ++++++++++++++++++++-----------
 1 file changed, 20 insertions(+), 11 deletions(-)

@@ -206,7 +206,10 @@ again:
 	return 0;
 }
 
-/* returns number of examined buffers and their common state in *state */
+/*
+ * Returns number of examined buffers and their common state in *state.
+ * Requested number of buffers-to-examine must be > 0.
+ */
 static inline int get_buf_states(struct qdio_q *q, unsigned int bufnr,
 				 unsigned char *state, unsigned int count,
 				 int auto_ack, int merge_pending)

@@ -217,17 +220,23 @@ static inline int get_buf_states(struct
 	if (is_qebsm(q))
 		return qdio_do_eqbs(q, state, bufnr, count, auto_ack);
 
-	for (i = 0; i < count; i++) {
-		if (!__state) {
-			__state = q->slsb.val[bufnr];
-			if (merge_pending && __state == SLSB_P_OUTPUT_PENDING)
-				__state = SLSB_P_OUTPUT_EMPTY;
-		} else if (merge_pending) {
-			if ((q->slsb.val[bufnr] & __state) != __state)
-				break;
-		} else if (q->slsb.val[bufnr] != __state)
-			break;
+	/* get initial state: */
+	__state = q->slsb.val[bufnr];
+	if (merge_pending && __state == SLSB_P_OUTPUT_PENDING)
+		__state = SLSB_P_OUTPUT_EMPTY;
+
+	for (i = 1; i < count; i++) {
 		bufnr = next_buf(bufnr);
+
+		/* merge PENDING into EMPTY: */
+		if (merge_pending &&
+		    q->slsb.val[bufnr] == SLSB_P_OUTPUT_PENDING &&
+		    __state == SLSB_P_OUTPUT_EMPTY)
+			continue;
+
+		/* stop if next state differs from initial state: */
+		if (q->slsb.val[bufnr] != __state)
+			break;
 	}
 	*state = __state;
 	return i;

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

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

From: Vasily Gorbik <[email protected]>

commit 15deb080a6087b73089139569558965750e69d67 upstream.

When loadparm is set in reipl parm block, the kernel should also set DIAG308_FLAGS_LP_VALID flag.

This fixes loadparm ignoring during z/VM fcp -> ccw reipl and kvm direct boot -> ccw reipl.

---
 arch/s390/kernel/ipl.c |    1 +
 1 file changed, 1 insertion(+)

@@ -779,6 +779,7 @@ static ssize_t reipl_generic_loadparm_st
 	/* copy and convert to ebcdic */
 	memcpy(ipb->hdr.loadparm, buf, lp_len);
 	ASCEBC(ipb->hdr.loadparm, LOADPARM_LEN);
+	ipb->hdr.flags |= DIAG308_FLAGS_LP_VALID;
 	return len;
 }
 

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

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

From: Heiko Carstens <[email protected]>

commit 8b09ca746a643ca452cd41a522046a96ee5a55fd upstream.

Git commit c60a03fee0e5 ("s390: switch to {get,put}_compat_sigset()") contains a typo and now copies the wrong pointer to user space. Use the correct pointer instead.

---
 arch/s390/kernel/compat_signal.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -379,7 +379,7 @@ static int setup_frame32(struct ksignal
 	if (put_compat_sigset((compat_sigset_t __user *)frame->sc.oldmask,
 			      set, sizeof(compat_sigset_t)))
 		return -EFAULT;
-	if (__put_user(ptr_to_compat(&frame->sc), &frame->sc.sregs))
+	if (__put_user(ptr_to_compat(&frame->sregs), &frame->sc.sregs))
 		return -EFAULT;
 
 	/* Store registers needed to create the signal frame */

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

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

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

commit c61611f70958d86f659bca25c02ae69413747a8d upstream.

get_user_pages_fast is supposed to be a faster drop-in equivalent of get_user_pages. As such, callers expect it to return a negative return code when passed an invalid address, and never expect it to return 0 when passed a positive number of pages, since its documentation says:

* Returns number of pages pinned. This may be fewer than the number
* requested. If nr_pages is 0 or negative, returns 0. If no pages
* were pinned, returns -errno.

When get_user_pages_fast fall back on get_user_pages this is exactly what happens. Unfortunately the implementation is inconsistent: it returns 0 if passed a kernel address, confusing callers: for example, the following is pretty common but does not appear to do the right thing with a kernel address:

        ret = get_user_pages_fast(addr, 1, writeable, &page);
        if (ret < 0)
                return ret;

Change get_user_pages_fast to return -EFAULT when supplied a kernel address to make it match expectations.

All callers have been audited for consistency with the documented semantics.

---
 mm/gup.c |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

@@ -1816,9 +1816,12 @@ int get_user_pages_fast(unsigned long st
 	len = (unsigned long) nr_pages << PAGE_SHIFT;
 	end = start + len;
 
+	if (nr_pages <= 0)
+		return 0;
+
 	if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ,
 					(void __user *)start, len)))
-		return 0;
+		return -EFAULT;
 
 	if (gup_fast_permitted(start, nr_pages, write)) {
 		local_irq_disable();

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

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

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

commit 09e35a4a1ca8b9988ca9b8557d17948cd6c0808b upstream.

Patch series "mm/get_user_pages_fast fixes, cleanups", v2.

Turns out get_user_pages_fast and __get_user_pages_fast return different values on error when given a single page: __get_user_pages_fast returns
0. get_user_pages_fast returns either 0 or an error.

Callers of get_user_pages_fast expect an error so fix it up to return an error consistently.

Stress the difference between get_user_pages_fast and __get_user_pages_fast to make sure callers aren't confused.

This patch (of 3):

__gup_benchmark_ioctl does not handle the case where get_user_pages_fast fails:

- a negative return code will cause a buffer overrun

- returning with partial success will cause use of uninitialized memory.

---
 mm/gup_benchmark.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

@@ -23,7 +23,7 @@ static int __gup_benchmark_ioctl(unsigne
 	struct page **pages;
 
 	nr_pages = gup->size / PAGE_SIZE;
-	pages = kvmalloc(sizeof(void *) * nr_pages, GFP_KERNEL);
+	pages = kvzalloc(sizeof(void *) * nr_pages, GFP_KERNEL);
 	if (!pages)
 		return -ENOMEM;
 

@@ -41,6 +41,8 @@ static int __gup_benchmark_ioctl(unsigne
 		}
 
 		nr = get_user_pages_fast(addr, nr, gup->flags & 1, pages + i);
+		if (nr <= 0)
+			break;
 		i += nr;
 	}
 	end_time = ktime_get();

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

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

From: Al Viro <[email protected]>

commit 30ce4d1903e1d8a7ccd110860a5eef3c638ed8be upstream.

missed it in "kill struct filename.separate" several years ago.

---
 fs/namei.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -222,9 +222,10 @@ getname_kernel(const char * filename)
 	if (len <= EMBEDDED_NAME_MAX) {
 		result->name = (char *)result->iname;
 	} else if (len <= PATH_MAX) {
+		const size_t size = offsetof(struct filename, iname[1]);
 		struct filename *tmp;
 
-		tmp = kmalloc(sizeof(*tmp), GFP_KERNEL);
+		tmp = kmalloc(size, GFP_KERNEL);
 		if (unlikely(!tmp)) {
 			__putname(result);
 			return ERR_PTR(-ENOMEM);

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

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

From: Szymon Janc <[email protected]>

commit 082f2300cfa1a3d9d5221c38c5eba85d4ab98bd8 upstream.

Local random address needs to be updated before creating connection if RPA from LE Direct Advertising Report was resolved in host. Otherwise remote device might ignore connection request due to address mismatch.

This was affecting following qualification test cases:
GAP/CONN/SCEP/BV-03-C, GAP/CONN/GCEP/BV-05-C, GAP/CONN/DCEP/BV-05-C

Before patch:
< HCI Command: LE Set Random Address (0x08|0x0005) plen 6 #11350 [hci0] 84680.231216

        Address: 56:BC:E8:24:11:68 (Resolvable)
          Identity type: Random (0x01)
          Identity: F2:F1:06:3D:9C:42 (Static)

      LE Set Random Address (0x08|0x0005) ncmd 1
        Status: Success (0x00)
< HCI Command: LE Set Scan Parameters (0x08|0x000b) plen 7         #11352 [hci0] 84680.246417
        Type: Passive (0x00)
        Interval: 60.000 msec (0x0060)
        Window: 30.000 msec (0x0030)
        Own address type: Random (0x01)
        Filter policy: Accept all advertisement, inc. directed unresolved RPA (0x02)

      LE Set Scan Parameters (0x08|0x000b) ncmd 1
        Status: Success (0x00)
< HCI Command: LE Set Scan Enable (0x08|0x000c) plen 2             #11354 [hci0] 84680.249466
        Scanning: Enabled (0x01)
        Filter duplicates: Enabled (0x01)

      LE Set Scan Enable (0x08|0x000c) ncmd 1
        Status: Success (0x00)

      LE Direct Advertising Report (0x0b)
        Num reports: 1
        Event type: Connectable directed - ADV_DIRECT_IND (0x01)
        Address type: Random (0x01)
        Address: 53:38:DA:46:8C:45 (Resolvable)
          Identity type: Public (0x00)
          Identity: 11:22:33:44:55:66 (OUI 11-22-33)
        Direct address type: Random (0x01)
        Direct address: 7C:D6:76:8C:DF:82 (Resolvable)
          Identity type: Random (0x01)
          Identity: F2:F1:06:3D:9C:42 (Static)
        RSSI: -74 dBm (0xb6)
< HCI Command: LE Set Scan Enable (0x08|0x000c) plen 2             #11357 [hci0] 84680.458737
        Scanning: Disabled (0x00)
        Filter duplicates: Disabled (0x00)

      LE Set Scan Enable (0x08|0x000c) ncmd 1
        Status: Success (0x00)
< HCI Command: LE Create Connection (0x08|0x000d) plen 25          #11359 [hci0] 84680.470444
        Scan interval: 60.000 msec (0x0060)
        Scan window: 60.000 msec (0x0060)
        Filter policy: White list is not used (0x00)
        Peer address type: Random (0x01)
        Peer address: 53:38:DA:46:8C:45 (Resolvable)
          Identity type: Public (0x00)
          Identity: 11:22:33:44:55:66 (OUI 11-22-33)
        Own address type: Random (0x01)
        Min connection interval: 30.00 msec (0x0018)
        Max connection interval: 50.00 msec (0x0028)
        Connection latency: 0 (0x0000)
        Supervision timeout: 420 msec (0x002a)
        Min connection length: 0.000 msec (0x0000)
        Max connection length: 0.000 msec (0x0000)

      LE Create Connection (0x08|0x000d) ncmd 1
        Status: Success (0x00)

< HCI Command: LE Create Connection Cancel (0x08|0x000e) plen 0 #11361 [hci0] 84682.545385

      LE Create Connection Cancel (0x08|0x000e) ncmd 1
        Status: Success (0x00)

      LE Connection Complete (0x01)
        Status: Unknown Connection Identifier (0x02)
        Handle: 0
        Role: Master (0x00)
        Peer address type: Public (0x00)
        Peer address: 00:00:00:00:00:00 (OUI 00-00-00)
        Connection interval: 0.00 msec (0x0000)
        Connection latency: 0 (0x0000)
        Supervision timeout: 0 msec (0x0000)
        Master clock accuracy: 0x00

After patch:
< HCI Command: LE Set Scan Parameters (0x08|0x000b) plen 7 #210 [hci0] 667.152459

        Type: Passive (0x00)
        Interval: 60.000 msec (0x0060)
        Window: 30.000 msec (0x0030)
        Own address type: Random (0x01)
        Filter policy: Accept all advertisement, inc. directed unresolved RPA (0x02)

      LE Set Scan Parameters (0x08|0x000b) ncmd 1
        Status: Success (0x00)
< HCI Command: LE Set Scan Enable (0x08|0x000c) plen 2        #212 [hci0] 667.153704
        Scanning: Enabled (0x01)
        Filter duplicates: Enabled (0x01)

      LE Set Scan Enable (0x08|0x000c) ncmd 1
        Status: Success (0x00)

      LE Direct Advertising Report (0x0b)
        Num reports: 1
        Event type: Connectable directed - ADV_DIRECT_IND (0x01)
        Address type: Random (0x01)
        Address: 50:52:D9:A6:48:A0 (Resolvable)
          Identity type: Public (0x00)
          Identity: 11:22:33:44:55:66 (OUI 11-22-33)
        Direct address type: Random (0x01)
        Direct address: 7C:C1:57:A5:B7:A8 (Resolvable)
          Identity type: Random (0x01)
          Identity: F4:28:73:5D:38:B0 (Static)
        RSSI: -70 dBm (0xba)
< HCI Command: LE Set Scan Enable (0x08|0x000c) plen 2       #215 [hci0] 667.182704
        Scanning: Disabled (0x00)
        Filter duplicates: Disabled (0x00)

      LE Set Scan Enable (0x08|0x000c) ncmd 1
        Status: Success (0x00)
< HCI Command: LE Set Random Address (0x08|0x0005) plen 6    #217 [hci0] 667.183645
        Address: 7C:C1:57:A5:B7:A8 (Resolvable)
          Identity type: Random (0x01)
          Identity: F4:28:73:5D:38:B0 (Static)

      LE Set Random Address (0x08|0x0005) ncmd 1
        Status: Success (0x00)
< HCI Command: LE Create Connection (0x08|0x000d) plen 25    #219 [hci0] 667.184613
        Scan interval: 60.000 msec (0x0060)
        Scan window: 60.000 msec (0x0060)
        Filter policy: White list is not used (0x00)
        Peer address type: Random (0x01)
        Peer address: 50:52:D9:A6:48:A0 (Resolvable)
          Identity type: Public (0x00)
          Identity: 11:22:33:44:55:66 (OUI 11-22-33)
        Own address type: Random (0x01)
        Min connection interval: 30.00 msec (0x0018)
        Max connection interval: 50.00 msec (0x0028)
        Connection latency: 0 (0x0000)
        Supervision timeout: 420 msec (0x002a)
        Min connection length: 0.000 msec (0x0000)
        Max connection length: 0.000 msec (0x0000)

      LE Create Connection (0x08|0x000d) ncmd 1
        Status: Success (0x00)

      LE Connection Complete (0x01)
        Status: Success (0x00)
        Handle: 0
        Role: Master (0x00)
        Peer address type: Random (0x01)
        Peer address: 50:52:D9:A6:48:A0 (Resolvable)
          Identity type: Public (0x00)
          Identity: 11:22:33:44:55:66 (OUI 11-22-33)
        Connection interval: 50.00 msec (0x0028)
        Connection latency: 0 (0x0000)
        Supervision timeout: 420 msec (0x002a)
        Master clock accuracy: 0x07
@ MGMT Event: Device Connected (0x000b) plen 13          {0x0002} [hci0] 667.485996
        LE Address: 11:22:33:44:55:66 (OUI 11-22-33)
        Flags: 0x00000000
        Data length: 0

---
 include/net/bluetooth/hci_core.h |    2 +-
 net/bluetooth/hci_conn.c         |   29 +++++++++++++++++++++--------
 net/bluetooth/hci_event.c        |   15 +++++++++++----
 net/bluetooth/l2cap_core.c       |    2 +-
 4 files changed, 34 insertions(+), 14 deletions(-)

@@ -895,7 +895,7 @@ struct hci_conn *hci_connect_le_scan(str
 				     u16 conn_timeout);
 struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst,
 				u8 dst_type, u8 sec_level, u16 conn_timeout,
-				u8 role);
+				u8 role, bdaddr_t *direct_rpa);
 struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst,
 				 u8 sec_level, u8 auth_type);
 struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst,

@@ -749,18 +749,31 @@ static bool conn_use_rpa(struct hci_conn
 }
 
 static void hci_req_add_le_create_conn(struct hci_request *req,
-				       struct hci_conn *conn)
+				       struct hci_conn *conn,
+				       bdaddr_t *direct_rpa)
 {
 	struct hci_cp_le_create_conn cp;
 	struct hci_dev *hdev = conn->hdev;
 	u8 own_addr_type;
 
-	/* Update random address, but set require_privacy to false so
-	 * that we never connect with an non-resolvable address.
+	/* If direct address was provided we use it instead of current
+	 * address.
 	 */
-	if (hci_update_random_address(req, false, conn_use_rpa(conn),
-				      &own_addr_type))
-		return;
+	if (direct_rpa) {
+		if (bacmp(&req->hdev->random_addr, direct_rpa))
+			hci_req_add(req, HCI_OP_LE_SET_RANDOM_ADDR, 6,
+								direct_rpa);
+
+		/* direct address is always RPA */
+		own_addr_type = ADDR_LE_DEV_RANDOM;
+	} else {
+		/* Update random address, but set require_privacy to false so
+		 * that we never connect with an non-resolvable address.
+		 */
+		if (hci_update_random_address(req, false, conn_use_rpa(conn),
+					      &own_addr_type))
+			return;
+	}
 
 	memset(&cp, 0, sizeof(cp));
 

@@ -825,7 +838,7 @@ static void hci_req_directed_advertising
 
 struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst,
 				u8 dst_type, u8 sec_level, u16 conn_timeout,
-				u8 role)
+				u8 role, bdaddr_t *direct_rpa)
 {
 	struct hci_conn_params *params;
 	struct hci_conn *conn;

@@ -940,7 +953,7 @@ struct hci_conn *hci_connect_le(struct h
 		hci_dev_set_flag(hdev, HCI_LE_SCAN_INTERRUPTED);
 	}
 
-	hci_req_add_le_create_conn(&req, conn);
+	hci_req_add_le_create_conn(&req, conn, direct_rpa);
 
 create_conn:
 	err = hci_req_run(&req, create_le_conn_complete);

@@ -4648,7 +4648,8 @@ static void hci_le_conn_update_complete_
 /* This function requires the caller holds hdev->lock */
 static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev,
 					      bdaddr_t *addr,
-					      u8 addr_type, u8 adv_type)
+					      u8 addr_type, u8 adv_type,
+					      bdaddr_t *direct_rpa)
 {
 	struct hci_conn *conn;
 	struct hci_conn_params *params;

@@ -4699,7 +4700,8 @@ static struct hci_conn *check_pending_le
 	}
 
 	conn = hci_connect_le(hdev, addr, addr_type, BT_SECURITY_LOW,
-			      HCI_LE_AUTOCONN_TIMEOUT, HCI_ROLE_MASTER);
+			      HCI_LE_AUTOCONN_TIMEOUT, HCI_ROLE_MASTER,
+			      direct_rpa);
 	if (!IS_ERR(conn)) {
 		/* If HCI_AUTO_CONN_EXPLICIT is set, conn is already owned
 		 * by higher layer that tried to connect, if no then