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

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

From: Marcel Holtmann marcel@holtmann.org

commit af3d5d1c87664a4f150fcf3534c6567cb19909b0 upstream.

When doing option parsing for standard type values of 1, 2 or 4 octets, the value is converted directly into a variable instead of a pointer. To avoid being tricked into being a pointer, check that for these option types that sizes actually match. In L2CAP every option is fixed size and thus it is prudent anyway to ensure that the remote side sends us the right option size along with option paramters.

If the option size is not matching the option type, then that option is silently ignored. It is a protocol violation and instead of trying to give the remote attacker any further hints just pretend that option is not present and proceed with the default values. Implementation following the specification and its qualification procedures will always use the correct size and thus not being impacted here.

To keep the code readable and consistent accross all options, a few cosmetic changes were also required.

Signed-off-by: Marcel Holtmann marcel@holtmann.org Reviewed-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Johan Hedberg johan.hedberg@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- net/bluetooth/l2cap_core.c | 77 ++++++++++++++++++++++++++------------------- 1 file changed, 46 insertions(+), 31 deletions(-)

--- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -3342,10 +3342,14 @@ static int l2cap_parse_conf_req(struct l

switch (type) { case L2CAP_CONF_MTU: + if (olen != 2) + break; mtu = val; break;

case L2CAP_CONF_FLUSH_TO: + if (olen != 2) + break; chan->flush_to = val; break;

@@ -3353,26 +3357,30 @@ static int l2cap_parse_conf_req(struct l break;

case L2CAP_CONF_RFC: - if (olen == sizeof(rfc)) - memcpy(&rfc, (void *) val, olen); + if (olen != sizeof(rfc)) + break; + memcpy(&rfc, (void *) val, olen); break;

case L2CAP_CONF_FCS: + if (olen != 1) + break; if (val == L2CAP_FCS_NONE) set_bit(CONF_RECV_NO_FCS, &chan->conf_state); break;

case L2CAP_CONF_EFS: - if (olen == sizeof(efs)) { - remote_efs = 1; - memcpy(&efs, (void *) val, olen); - } + if (olen != sizeof(efs)) + break; + remote_efs = 1; + memcpy(&efs, (void *) val, olen); break;

case L2CAP_CONF_EWS: + if (olen != 2) + break; if (!(chan->conn->local_fixed_chan & L2CAP_FC_A2MP)) return -ECONNREFUSED; - set_bit(FLAG_EXT_CTRL, &chan->flags); set_bit(CONF_EWS_RECV, &chan->conf_state); chan->tx_win_max = L2CAP_DEFAULT_EXT_WINDOW; @@ -3382,7 +3390,6 @@ static int l2cap_parse_conf_req(struct l default: if (hint) break; - result = L2CAP_CONF_UNKNOWN; *((u8 *) ptr++) = type; break; @@ -3550,55 +3557,60 @@ static int l2cap_parse_conf_rsp(struct l

switch (type) { case L2CAP_CONF_MTU: + if (olen != 2) + break; if (val < L2CAP_DEFAULT_MIN_MTU) { *result = L2CAP_CONF_UNACCEPT; chan->imtu = L2CAP_DEFAULT_MIN_MTU; } else chan->imtu = val; - l2cap_add_conf_opt(&ptr, L2CAP_CONF_MTU, 2, chan->imtu, endptr - ptr); + l2cap_add_conf_opt(&ptr, L2CAP_CONF_MTU, 2, chan->imtu, + endptr - ptr); break;

case L2CAP_CONF_FLUSH_TO: + if (olen != 2) + break; chan->flush_to = val; - l2cap_add_conf_opt(&ptr, L2CAP_CONF_FLUSH_TO, - 2, chan->flush_to, endptr - ptr); + l2cap_add_conf_opt(&ptr, L2CAP_CONF_FLUSH_TO, 2, + chan->flush_to, endptr - ptr); break;

case L2CAP_CONF_RFC: - if (olen == sizeof(rfc)) - memcpy(&rfc, (void *)val, olen); - + if (olen != sizeof(rfc)) + break; + memcpy(&rfc, (void *)val, olen); if (test_bit(CONF_STATE2_DEVICE, &chan->conf_state) && rfc.mode != chan->mode) return -ECONNREFUSED; - chan->fcs = 0; - - l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, - sizeof(rfc), (unsigned long) &rfc, endptr - ptr); + l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, sizeof(rfc), + (unsigned long) &rfc, endptr - ptr); break;

case L2CAP_CONF_EWS: + if (olen != 2) + break; chan->ack_win = min_t(u16, val, chan->ack_win); l2cap_add_conf_opt(&ptr, L2CAP_CONF_EWS, 2, chan->tx_win, endptr - ptr); break;

case L2CAP_CONF_EFS: - if (olen == sizeof(efs)) { - memcpy(&efs, (void *)val, olen); - - if (chan->local_stype != L2CAP_SERV_NOTRAFIC && - efs.stype != L2CAP_SERV_NOTRAFIC && - efs.stype != chan->local_stype) - return -ECONNREFUSED; - - l2cap_add_conf_opt(&ptr, L2CAP_CONF_EFS, sizeof(efs), - (unsigned long) &efs, endptr - ptr); - } + if (olen != sizeof(efs)) + break; + memcpy(&efs, (void *)val, olen); + if (chan->local_stype != L2CAP_SERV_NOTRAFIC && + efs.stype != L2CAP_SERV_NOTRAFIC && + efs.stype != chan->local_stype) + return -ECONNREFUSED; + l2cap_add_conf_opt(&ptr, L2CAP_CONF_EFS, sizeof(efs), + (unsigned long) &efs, endptr - ptr); break;

case L2CAP_CONF_FCS: + if (olen != 1) + break; if (*result == L2CAP_CONF_PENDING) if (val == L2CAP_FCS_NONE) set_bit(CONF_RECV_NO_FCS, @@ -3730,10 +3742,13 @@ static void l2cap_conf_rfc_get(struct l2

switch (type) { case L2CAP_CONF_RFC: - if (olen == sizeof(rfc)) - memcpy(&rfc, (void *)val, olen); + if (olen != sizeof(rfc)) + break; + memcpy(&rfc, (void *)val, olen); break; case L2CAP_CONF_EWS: + if (olen != 2) + break; txwin_ext = val; break; }

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

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

[ Upstream commit ace6033ec5c356615eaa3582fb1946e9eaff6662 ]

User space Android code identifies pixclock == 0 as a sign for emulation and will set the frame rate to 60 fps when reading this value, which is the desired outcome.

Signed-off-by: Christoffer Dall christoffer.dall@linaro.org Signed-off-by: Peter Maydell peter.maydell@linaro.org Signed-off-by: Roman Kiryanov rkir@google.com Signed-off-by: Bartlomiej Zolnierkiewicz b.zolnierkie@samsung.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/video/fbdev/goldfishfb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/video/fbdev/goldfishfb.c +++ b/drivers/video/fbdev/goldfishfb.c @@ -234,7 +234,7 @@ static int goldfish_fb_probe(struct plat fb->fb.var.activate = FB_ACTIVATE_NOW; fb->fb.var.height = readl(fb->reg_base + FB_GET_PHYS_HEIGHT); fb->fb.var.width = readl(fb->reg_base + FB_GET_PHYS_WIDTH); - fb->fb.var.pixclock = 10000; + fb->fb.var.pixclock = 0;

fb->fb.var.red.offset = 11; fb->fb.var.red.length = 5;

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

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

From: Eric Dumazet edumazet@google.com

[ Upstream commit e0aa67709f89d08c8d8e5bdd9e0b649df61d0090 ]

When a dual stack dccp listener accepts an ipv4 flow, it should not attempt to use an ipv6 header or inet6_iif() helper.

Fixes: 3df80d9320bc ("[DCCP]: Introduce DCCPv6") Signed-off-by: Eric Dumazet edumazet@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/dccp/ipv6.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -433,8 +433,8 @@ static struct sock *dccp_v6_request_recv newnp->ipv6_mc_list = NULL; newnp->ipv6_ac_list = NULL; newnp->ipv6_fl_list = NULL; - newnp->mcast_oif = inet6_iif(skb); - newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; + newnp->mcast_oif = inet_iif(skb); + newnp->mcast_hops = ip_hdr(skb)->ttl;

/* * No need to charge this sock to the relevant IPv6 refcnt debug socks count

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

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

From: Bjorn Helgaas bhelgaas@google.com

[ Upstream commit fae846e2b7124d4b076ef17791c73addf3b26350 ]

The device ID alone does not uniquely identify a device. Test both the vendor and device ID to make sure we don't mistakenly think some other vendor's 0xB410 device is a Digium HFC4S. Also, instead of the bare hex ID, use the same constant (PCI_DEVICE_ID_DIGIUM_HFC4S) used in the device ID table.

No functional change intended.

Signed-off-by: Bjorn Helgaas bhelgaas@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/isdn/hardware/mISDN/hfcmulti.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/drivers/isdn/hardware/mISDN/hfcmulti.c +++ b/drivers/isdn/hardware/mISDN/hfcmulti.c @@ -4367,7 +4367,8 @@ setup_pci(struct hfc_multi *hc, struct p if (m->clock2) test_and_set_bit(HFC_CHIP_CLOCK2, &hc->chip);

- if (ent->device == 0xB410) { + if (ent->vendor == PCI_VENDOR_ID_DIGIUM && + ent->device == PCI_DEVICE_ID_DIGIUM_HFC4S) { test_and_set_bit(HFC_CHIP_B410P, &hc->chip); test_and_set_bit(HFC_CHIP_PCM_MASTER, &hc->chip); test_and_clear_bit(HFC_CHIP_PCM_SLAVE, &hc->chip);

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

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

From: Christoph Paasch cpaasch@apple.com

[ Upstream commit 398f0132c14754fcd03c1c4f8e7176d001ce8ea1 ]

Since commit fc62814d690c ("net/packet: fix 4gb buffer limit due to overflow check") one can now allocate packet ring buffers >= UINT_MAX. However, syzkaller found that that triggers a warning:

[ 21.100000] WARNING: CPU: 2 PID: 2075 at mm/page_alloc.c:4584 __alloc_pages_nod0 [ 21.101490] Modules linked in: [ 21.101921] CPU: 2 PID: 2075 Comm: syz-executor.0 Not tainted 5.0.0 #146 [ 21.102784] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 0.5.1 01/01/2011 [ 21.103887] RIP: 0010:__alloc_pages_nodemask+0x2a0/0x630 [ 21.104640] Code: fe ff ff 65 48 8b 04 25 c0 de 01 00 48 05 90 0f 00 00 41 bd 01 00 00 00 48 89 44 24 48 e9 9c fe 3 [ 21.107121] RSP: 0018:ffff88805e1cf920 EFLAGS: 00010246 [ 21.107819] RAX: 0000000000000000 RBX: ffffffff85a488a0 RCX: 0000000000000000 [ 21.108753] RDX: 0000000000000000 RSI: dffffc0000000000 RDI: 0000000000000000 [ 21.109699] RBP: 1ffff1100bc39f28 R08: ffffed100bcefb67 R09: ffffed100bcefb67 [ 21.110646] R10: 0000000000000001 R11: ffffed100bcefb66 R12: 000000000000000d [ 21.111623] R13: 0000000000000000 R14: ffff88805e77d888 R15: 000000000000000d [ 21.112552] FS: 00007f7c7de05700(0000) GS:ffff88806d100000(0000) knlGS:0000000000000000 [ 21.113612] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 21.114405] CR2: 000000000065c000 CR3: 000000005e58e006 CR4: 00000000001606e0 [ 21.115367] Call Trace: [ 21.115705] ? __alloc_pages_slowpath+0x21c0/0x21c0 [ 21.116362] alloc_pages_current+0xac/0x1e0 [ 21.116923] kmalloc_order+0x18/0x70 [ 21.117393] kmalloc_order_trace+0x18/0x110 [ 21.117949] packet_set_ring+0x9d5/0x1770 [ 21.118524] ? packet_rcv_spkt+0x440/0x440 [ 21.119094] ? lock_downgrade+0x620/0x620 [ 21.119646] ? __might_fault+0x177/0x1b0 [ 21.120177] packet_setsockopt+0x981/0x2940 [ 21.120753] ? __fget+0x2fb/0x4b0 [ 21.121209] ? packet_release+0xab0/0xab0 [ 21.121740] ? sock_has_perm+0x1cd/0x260 [ 21.122297] ? selinux_secmark_relabel_packet+0xd0/0xd0 [ 21.123013] ? __fget+0x324/0x4b0 [ 21.123451] ? selinux_netlbl_socket_setsockopt+0x101/0x320 [ 21.124186] ? selinux_netlbl_sock_rcv_skb+0x3a0/0x3a0 [ 21.124908] ? __lock_acquire+0x529/0x3200 [ 21.125453] ? selinux_socket_setsockopt+0x5d/0x70 [ 21.126075] ? __sys_setsockopt+0x131/0x210 [ 21.126533] ? packet_release+0xab0/0xab0 [ 21.127004] __sys_setsockopt+0x131/0x210 [ 21.127449] ? kernel_accept+0x2f0/0x2f0 [ 21.127911] ? ret_from_fork+0x8/0x50 [ 21.128313] ? do_raw_spin_lock+0x11b/0x280 [ 21.128800] __x64_sys_setsockopt+0xba/0x150 [ 21.129271] ? lockdep_hardirqs_on+0x37f/0x560 [ 21.129769] do_syscall_64+0x9f/0x450 [ 21.130182] entry_SYSCALL_64_after_hwframe+0x49/0xbe

We should allocate with __GFP_NOWARN to handle this.

Cc: Kal Conley kal.conley@dectris.com Cc: Andrey Konovalov andreyknvl@google.com Fixes: fc62814d690c ("net/packet: fix 4gb buffer limit due to overflow check") Signed-off-by: Christoph Paasch cpaasch@apple.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/packet/af_packet.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -4232,7 +4232,7 @@ static struct pgv *alloc_pg_vec(struct t struct pgv *pg_vec; int i;

- pg_vec = kcalloc(block_nr, sizeof(struct pgv), GFP_KERNEL); + pg_vec = kcalloc(block_nr, sizeof(struct pgv), GFP_KERNEL | __GFP_NOWARN); if (unlikely(!pg_vec)) goto out;

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

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

From: Aaro Koskinen aaro.koskinen@nokia.com

[ Upstream commit 223a960c01227e4dbcb6f9fa06b47d73bda21274 ]

When using 16K DMA buffers and ring mode, the DES3 refill is not working correctly as the function is using a bogus pointer for checking the private data. As a result stale pointers will remain in the RX descriptor ring, so DMA will now likely overwrite/corrupt some already freed memory.

As simple reproducer, just receive some UDP traffic:

# ifconfig eth0 down; ifconfig eth0 mtu 9000; ifconfig eth0 up # iperf3 -c 192.168.253.40 -u -b 0 -R

If you didn't crash by now check the RX descriptors to find non-contiguous RX buffers:

cat /sys/kernel/debug/stmmaceth/eth0/descriptors_status [...] 1 [0x2be5020]: 0xa3220321 0x9ffc1ffc 0x72d70082 0x130e207e ^^^^^^^^^^^^^^^^^^^^^ 2 [0x2be5040]: 0xa3220321 0x9ffc1ffc 0x72998082 0x1311a07e ^^^^^^^^^^^^^^^^^^^^^

A simple ping test will now report bad data:

# ping -s 8200 192.168.253.40 PING 192.168.253.40 (192.168.253.40) 8200(8228) bytes of data. 8208 bytes from 192.168.253.40: icmp_seq=1 ttl=64 time=1.00 ms wrong data byte #8144 should be 0xd0 but was 0x88

Fix the wrong pointer. Also we must refill DES3 only if the DMA buffer size is 16K.

Fixes: 54139cf3bb33 ("net: stmmac: adding multiple buffers for rx") Signed-off-by: Aaro Koskinen aaro.koskinen@nokia.com Acked-by: Jose Abreu joabreu@synopsys.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/stmicro/stmmac/ring_mode.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

--- a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c +++ b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c @@ -114,10 +114,11 @@ static unsigned int stmmac_is_jumbo_frm(

static void stmmac_refill_desc3(void *priv_ptr, struct dma_desc *p) { - struct stmmac_priv *priv = (struct stmmac_priv *)priv_ptr; + struct stmmac_rx_queue *rx_q = priv_ptr; + struct stmmac_priv *priv = rx_q->priv_data;

/* Fill DES3 in case of RING mode */ - if (priv->dma_buf_sz >= BUF_SIZE_8KiB) + if (priv->dma_buf_sz == BUF_SIZE_16KiB) p->des3 = cpu_to_le32(le32_to_cpu(p->des2) + BUF_SIZE_8KiB); }

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

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

From: Maxime Chevallier maxime.chevallier@bootlin.com

[ Upstream commit a4dc6a49156b1f8d6e17251ffda17c9e6a5db78a ]

When using fanouts with AF_PACKET, the demux functions such as fanout_demux_cpu will return an index in the fanout socket array, which corresponds to the selected socket.

The ordering of this array depends on the order the sockets were added to a given fanout group, so for FANOUT_CPU this means sockets are bound to cpus in the order they are configured, which is OK.

However, when stopping then restarting the interface these sockets are bound to, the sockets are reassigned to the fanout group in the reverse order, due to the fact that they were inserted at the head of the interface's AF_PACKET socket list.

This means that traffic that was directed to the first socket in the fanout group is now directed to the last one after an interface restart.

In the case of FANOUT_CPU, traffic from CPU0 will be directed to the socket that used to receive traffic from the last CPU after an interface restart.

This commit introduces a helper to add a socket at the tail of a list, then uses it to register AF_PACKET sockets.

Note that this changes the order in which sockets are listed in /proc and with sock_diag.

Fixes: dc99f600698d ("packet: Add fanout support") Signed-off-by: Maxime Chevallier maxime.chevallier@bootlin.com Acked-by: Willem de Bruijn willemb@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/sock.h | 6 ++++++ net/packet/af_packet.c | 2 +- 2 files changed, 7 insertions(+), 1 deletion(-)

--- a/include/net/sock.h +++ b/include/net/sock.h @@ -682,6 +682,12 @@ static inline void sk_add_node_rcu(struc hlist_add_head_rcu(&sk->sk_node, list); }

+static inline void sk_add_node_tail_rcu(struct sock *sk, struct hlist_head *list) +{ + sock_hold(sk); + hlist_add_tail_rcu(&sk->sk_node, list); +} + static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list) { hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list); --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3281,7 +3281,7 @@ static int packet_create(struct net *net }

mutex_lock(&net->packet.sklist_lock); - sk_add_node_rcu(sk, &net->packet.sklist); + sk_add_node_tail_rcu(sk, &net->packet.sklist); mutex_unlock(&net->packet.sklist_lock);

preempt_disable();

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

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

From: Eric Dumazet edumazet@google.com

[ Upstream commit 89e4130939a20304f4059ab72179da81f5347528 ]

When a dual stack tcp listener accepts an ipv4 flow, it should not attempt to use an ipv6 header or tcp_v6_iif() helper.

Fixes: 1397ed35f22d ("ipv6: add flowinfo for tcp6 pkt_options for all cases") Fixes: df3687ffc665 ("ipv6: add the IPV6_FL_F_REFLECT flag to IPV6_FL_A_GET") Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet edumazet@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv6/tcp_ipv6.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

--- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1083,11 +1083,11 @@ static struct sock *tcp_v6_syn_recv_sock newnp->ipv6_fl_list = NULL; newnp->pktoptions = NULL; newnp->opt = NULL; - newnp->mcast_oif = tcp_v6_iif(skb); - newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; - newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb)); + newnp->mcast_oif = inet_iif(skb); + newnp->mcast_hops = ip_hdr(skb)->ttl; + newnp->rcv_flowinfo = 0; if (np->repflow) - newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb)); + newnp->flow_label = 0;

/* * No need to charge this sock to the relevant IPv6 refcnt debug socks count

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

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

From: Dean Nelson dnelson@redhat.com

[ Upstream commit cd35ef91490ad8049dd180bb060aff7ee192eda9 ]

For the non-XDP case, commit 773225388dae15e72790 ("net: thunderx: Optimize page recycling for XDP") added code to nicvf_free_rbdr() that, when releasing the additional receive buffer page reference held for recycling, repeatedly calls put_page() until the page's _refcount goes to zero. Which results in the page being freed.

This is not okay if the page's _refcount was greater than 1 (in the non-XDP case), because nicvf_free_rbdr() should not be subtracting more than what nicvf_alloc_page() had previously added to the page's _refcount, which was only 1 (in the non-XDP case).

This can arise if a received packet is still being processed and the receive buffer (i.e., skb->head) has not yet been freed via skb_free_head() when nicvf_free_rbdr() is spinning through the aforementioned put_page() loop.

If this should occur, when the received packet finishes processing and skb_free_head() is called, various problems can ensue. Exactly what, depends on whether the page has already been reallocated or not, anything from "BUG: Bad page state ... ", to "Unable to handle kernel NULL pointer dereference ..." or "Unable to handle kernel paging request...".

So this patch changes nicvf_free_rbdr() to only call put_page() once for pages held for recycling (in the non-XDP case).

Fixes: 773225388dae ("net: thunderx: Optimize page recycling for XDP") Signed-off-by: Dean Nelson dnelson@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/cavium/thunder/nicvf_queues.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-)

--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c @@ -364,11 +364,10 @@ static void nicvf_free_rbdr(struct nicvf while (head < rbdr->pgcnt) { pgcache = &rbdr->pgcache[head]; if (pgcache->page && page_ref_count(pgcache->page) != 0) { - if (!rbdr->is_xdp) { - put_page(pgcache->page); - continue; + if (rbdr->is_xdp) { + page_ref_sub(pgcache->page, + pgcache->ref_count - 1); } - page_ref_sub(pgcache->page, pgcache->ref_count - 1); put_page(pgcache->page); } head++;

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

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

From: Xin Long lucien.xin@gmail.com

[ Upstream commit 273160ffc6b993c7c91627f5a84799c66dfe4dee ]

sctp_hdr(skb) only works when skb->transport_header is set properly.

But in Netfilter, skb->transport_header for ipv6 is not guaranteed to be right value for sctphdr. It would cause to fail to check the checksum for sctp packets.

So fix it by using offset, which is always right in all places.

v1->v2: - Fix the changelog.

Fixes: e6d8b64b34aa ("net: sctp: fix and consolidate SCTP checksumming code") Reported-by: Li Shuang shuali@redhat.com Signed-off-by: Xin Long lucien.xin@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/sctp/checksum.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/include/net/sctp/checksum.h +++ b/include/net/sctp/checksum.h @@ -60,7 +60,7 @@ static inline __wsum sctp_csum_combine(_ static inline __le32 sctp_compute_cksum(const struct sk_buff *skb, unsigned int offset) { - struct sctphdr *sh = sctp_hdr(skb); + struct sctphdr *sh = (struct sctphdr *)(skb->data + offset); __le32 ret, old = sh->checksum; const struct skb_checksum_ops ops = { .update = sctp_csum_update,

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

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

From: Finn Thain fthain@telegraphics.com.au

[ Upstream commit bb9e5c5bcd76f4474eac3baf643d7a39f7bac7bb ]

The bug that Stan reported is as follows. After a restart, a 16-bit NIC may be incorrectly identified as a 32-bit NIC and stop working.

mac8390 slot.E: Memory length resource not found, probing mac8390 slot.E: Farallon EtherMac II-C (type farallon) mac8390 slot.E: MAC 00:00:c5:30:c2:99, IRQ 61, 32 KB shared memory at 0xfeed0000, 32-bit access.

The bug never arises after a cold start and only intermittently after a warm start. (I didn't investigate why the bug is intermittent.)

It turns out that memcpy_toio() is deprecated and memcmp_withio() also has issues. Replacing these calls with mmio accessors fixes the problem.

Reported-and-tested-by: Stan Johnson userm57@yahoo.com Fixes: 2964db0f5904 ("m68k: Mac DP8390 update") Signed-off-by: Finn Thain fthain@telegraphics.com.au Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/8390/mac8390.c | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-)

--- a/drivers/net/ethernet/8390/mac8390.c +++ b/drivers/net/ethernet/8390/mac8390.c @@ -156,8 +156,6 @@ static void dayna_block_output(struct ne #define memcpy_fromio(a, b, c) memcpy((a), (void *)(b), (c)) #define memcpy_toio(a, b, c) memcpy((void *)(a), (b), (c))

-#define memcmp_withio(a, b, c) memcmp((a), (void *)(b), (c)) - /* Slow Sane (16-bit chunk memory read/write) Cabletron uses this */ static void slow_sane_get_8390_hdr(struct net_device *dev, struct e8390_pkt_hdr *hdr, int ring_page); @@ -237,19 +235,26 @@ static enum mac8390_type __init mac8390_

static enum mac8390_access __init mac8390_testio(volatile unsigned long membase) { - unsigned long outdata = 0xA5A0B5B0; - unsigned long indata = 0x00000000; + u32 outdata = 0xA5A0B5B0; + u32 indata = 0; + /* Try writing 32 bits */ - memcpy_toio(membase, &outdata, 4); - /* Now compare them */ - if (memcmp_withio(&outdata, membase, 4) == 0) + nubus_writel(outdata, membase); + /* Now read it back */ + indata = nubus_readl(membase); + if (outdata == indata) return ACCESS_32; + + outdata = 0xC5C0D5D0; + indata = 0; + /* Write 16 bit output */ word_memcpy_tocard(membase, &outdata, 4); /* Now read it back */ word_memcpy_fromcard(&indata, membase, 4); if (outdata == indata) return ACCESS_16; + return ACCESS_UNKNOWN; }

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

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

From: Eric Dumazet edumazet@google.com

commit 9180bb4f046064dfa4541488102703b402bb04e1 upstream.

In my latest patch I missed one rcu_read_unlock(), in case device is down.

Fixes: 4477138fa0ae ("tun: properly test for IFF_UP") Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/net/tun.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1569,6 +1569,7 @@ drop: rcu_read_lock(); if (unlikely(!(tun->dev->flags & IFF_UP))) { err = -EIO; + rcu_read_unlock(); goto drop; }

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

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

From: Michal Suchanek msuchanek@suse.de

commit 815069ca57c142eb71d27439bc27f41a433a67b3 upstream.

Note that unlike RFI which is patched only in kernel the nospec state reflects settings at the time the module was loaded.

Iterating all modules and re-patching every time the settings change is not implemented.

Based on lwsync patching.

Signed-off-by: Michal Suchanek msuchanek@suse.de Signed-off-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/powerpc/include/asm/setup.h | 7 +++++++ arch/powerpc/kernel/module.c | 6 ++++++ arch/powerpc/kernel/security.c | 2 +- arch/powerpc/lib/feature-fixups.c | 16 +++++++++++++--- 4 files changed, 27 insertions(+), 4 deletions(-)

--- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -53,6 +53,13 @@ enum l1d_flush_type { void setup_rfi_flush(enum l1d_flush_type, bool enable); void do_rfi_flush_fixups(enum l1d_flush_type types); void do_barrier_nospec_fixups(bool enable); +extern bool barrier_nospec_enabled; + +#ifdef CONFIG_PPC_BOOK3S_64 +void do_barrier_nospec_fixups_range(bool enable, void *start, void *end); +#else +static inline void do_barrier_nospec_fixups_range(bool enable, void *start, void *end) { }; +#endif

#endif /* !__ASSEMBLY__ */

--- a/arch/powerpc/kernel/module.c +++ b/arch/powerpc/kernel/module.c @@ -72,6 +72,12 @@ int module_finalize(const Elf_Ehdr *hdr, do_feature_fixups(powerpc_firmware_features, (void *)sect->sh_addr, (void *)sect->sh_addr + sect->sh_size); + + sect = find_section(hdr, sechdrs, "__spec_barrier_fixup"); + if (sect != NULL) + do_barrier_nospec_fixups_range(barrier_nospec_enabled, + (void *)sect->sh_addr, + (void *)sect->sh_addr + sect->sh_size); #endif

sect = find_section(hdr, sechdrs, "__lwsync_fixup"); --- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -15,7 +15,7 @@

unsigned long powerpc_security_features __read_mostly = SEC_FTR_DEFAULT;

-static bool barrier_nospec_enabled; +bool barrier_nospec_enabled;

static void enable_barrier_nospec(bool enable) { --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -278,14 +278,14 @@ void do_rfi_flush_fixups(enum l1d_flush_ : "unknown"); }

-void do_barrier_nospec_fixups(bool enable) +void do_barrier_nospec_fixups_range(bool enable, void *fixup_start, void *fixup_end) { unsigned int instr, *dest; long *start, *end; int i;

- start = PTRRELOC(&__start___barrier_nospec_fixup), - end = PTRRELOC(&__stop___barrier_nospec_fixup); + start = fixup_start; + end = fixup_end;

instr = 0x60000000; /* nop */

@@ -304,6 +304,16 @@ void do_barrier_nospec_fixups(bool enabl printk(KERN_DEBUG "barrier-nospec: patched %d locations\n", i); }

+void do_barrier_nospec_fixups(bool enable) +{ + void *start, *end; + + start = PTRRELOC(&__start___barrier_nospec_fixup), + end = PTRRELOC(&__stop___barrier_nospec_fixup); + + do_barrier_nospec_fixups_range(enable, start, end); +} + #endif /* CONFIG_PPC_BOOK3S_64 */

void do_lwsync_fixups(unsigned long value, void *fixup_start, void *fixup_end)

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

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

From: Michael Ellerman mpe@ellerman.id.au

commit ddf35cf3764b5a182b178105f57515b42e2634f8 upstream.

Based on the x86 commit doing the same.

See commit 304ec1b05031 ("x86/uaccess: Use __uaccess_begin_nospec() and uaccess_try_nospec") and b3bbfb3fb5d2 ("x86: Introduce __uaccess_begin_nospec() and uaccess_try_nospec") for more detail.

In all cases we are ordering the load from the potentially user-controlled pointer vs a previous branch based on an access_ok() check or similar.

Base on a patch from Michal Suchanek.

Signed-off-by: Michal Suchanek msuchanek@suse.de Signed-off-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/powerpc/include/asm/uaccess.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-)

--- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -238,6 +238,7 @@ do { \ __chk_user_ptr(ptr); \ if (!is_kernel_addr((unsigned long)__gu_addr)) \ might_fault(); \ + barrier_nospec(); \ __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \ (x) = (__typeof__(*(ptr)))__gu_val; \ __gu_err; \ @@ -249,8 +250,10 @@ do { \ __long_type(*(ptr)) __gu_val = 0; \ const __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ might_fault(); \ - if (access_ok(VERIFY_READ, __gu_addr, (size))) \ + if (access_ok(VERIFY_READ, __gu_addr, (size))) { \ + barrier_nospec(); \ __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \ + } \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ __gu_err; \ }) @@ -261,6 +264,7 @@ do { \ __long_type(*(ptr)) __gu_val; \ const __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ __chk_user_ptr(ptr); \ + barrier_nospec(); \ __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ __gu_err; \ @@ -288,15 +292,19 @@ static inline unsigned long raw_copy_fro

switch (n) { case 1: + barrier_nospec(); __get_user_size(*(u8 *)to, from, 1, ret); break; case 2: + barrier_nospec(); __get_user_size(*(u16 *)to, from, 2, ret); break; case 4: + barrier_nospec(); __get_user_size(*(u32 *)to, from, 4, ret); break; case 8: + barrier_nospec(); __get_user_size(*(u64 *)to, from, 8, ret); break; } @@ -304,6 +312,7 @@ static inline unsigned long raw_copy_fro return 0; }

+ barrier_nospec(); return __copy_tofrom_user((__force void __user *)to, from, n); }

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

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

From: Michal Suchanek msuchanek@suse.de

commit a377514519b9a20fa1ea9adddbb4129573129cef upstream.

We now have barrier_nospec as mitigation so print it in cpu_show_spectre_v1() when enabled.

Signed-off-by: Michal Suchanek msuchanek@suse.de Signed-off-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/powerpc/kernel/security.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -120,6 +120,9 @@ ssize_t cpu_show_spectre_v1(struct devic if (!security_ftr_enabled(SEC_FTR_BNDS_CHK_SPEC_BAR)) return sprintf(buf, "Not affected\n");

+ if (barrier_nospec_enabled) + return sprintf(buf, "Mitigation: __user pointer sanitization\n"); + return sprintf(buf, "Vulnerable\n"); }

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

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

From: Diana Craciun diana.craciun@nxp.com

commit cf175dc315f90185128fb061dc05b6fbb211aa2f upstream.

The speculation barrier can be disabled from the command line with the parameter: "nospectre_v1".

Signed-off-by: Diana Craciun diana.craciun@nxp.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/powerpc/kernel/security.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-)

--- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -16,6 +16,7 @@ unsigned long powerpc_security_features __read_mostly = SEC_FTR_DEFAULT;

bool barrier_nospec_enabled; +static bool no_nospec;

static void enable_barrier_nospec(bool enable) { @@ -42,9 +43,18 @@ void setup_barrier_nospec(void) enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && security_ftr_enabled(SEC_FTR_BNDS_CHK_SPEC_BAR);

- enable_barrier_nospec(enable); + if (!no_nospec) + enable_barrier_nospec(enable); }

+static int __init handle_nospectre_v1(char *p) +{ + no_nospec = true; + + return 0; +} +early_param("nospectre_v1", handle_nospectre_v1); + #ifdef CONFIG_DEBUG_FS static int barrier_nospec_set(void *data, u64 val) {

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

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

From: Michael Ellerman mpe@ellerman.id.au

commit 179ab1cbf883575c3a585bcfc0f2160f1d22a149 upstream.

Add a config symbol to encode which platforms support the barrier_nospec speculation barrier. Currently this is just Book3S 64 but we will add Book3E in a future patch.

Signed-off-by: Diana Craciun diana.craciun@nxp.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/powerpc/Kconfig | 7 ++++++- arch/powerpc/include/asm/barrier.h | 6 +++--- arch/powerpc/include/asm/setup.h | 2 +- arch/powerpc/kernel/Makefile | 3 ++- arch/powerpc/kernel/module.c | 4 +++- arch/powerpc/kernel/vmlinux.lds.S | 4 +++- arch/powerpc/lib/feature-fixups.c | 6 ++++-- 7 files changed, 22 insertions(+), 10 deletions(-)

--- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -164,7 +164,7 @@ config PPC select GENERIC_CLOCKEVENTS_BROADCAST if SMP select GENERIC_CMOS_UPDATE select GENERIC_CPU_AUTOPROBE - select GENERIC_CPU_VULNERABILITIES if PPC_BOOK3S_64 + select GENERIC_CPU_VULNERABILITIES if PPC_BARRIER_NOSPEC select GENERIC_IRQ_SHOW select GENERIC_IRQ_SHOW_LEVEL select GENERIC_SMP_IDLE_THREAD @@ -236,6 +236,11 @@ config PPC # Please keep this list sorted alphabetically. #

+config PPC_BARRIER_NOSPEC + bool + default y + depends on PPC_BOOK3S_64 + config GENERIC_CSUM def_bool n

--- a/arch/powerpc/include/asm/barrier.h +++ b/arch/powerpc/include/asm/barrier.h @@ -76,7 +76,7 @@ do { \ ___p1; \ })

-#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_BARRIER_NOSPEC /* * Prevent execution of subsequent instructions until preceding branches have * been fully resolved and are no longer executing speculatively. @@ -86,10 +86,10 @@ do { \ // This also acts as a compiler barrier due to the memory clobber. #define barrier_nospec() asm (stringify_in_c(barrier_nospec_asm) ::: "memory")

-#else /* !CONFIG_PPC_BOOK3S_64 */ +#else /* !CONFIG_PPC_BARRIER_NOSPEC */ #define barrier_nospec_asm #define barrier_nospec() -#endif +#endif /* CONFIG_PPC_BARRIER_NOSPEC */

#include <asm-generic/barrier.h>

--- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -56,7 +56,7 @@ void setup_barrier_nospec(void); void do_barrier_nospec_fixups(bool enable); extern bool barrier_nospec_enabled;

-#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_BARRIER_NOSPEC void do_barrier_nospec_fixups_range(bool enable, void *start, void *end); #else static inline void do_barrier_nospec_fixups_range(bool enable, void *start, void *end) { }; --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -45,9 +45,10 @@ obj-$(CONFIG_VDSO32) += vdso32/ obj-$(CONFIG_PPC_WATCHDOG) += watchdog.o obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o -obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o security.o +obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_book3e.o +obj-$(CONFIG_PPC_BARRIER_NOSPEC) += security.o obj-$(CONFIG_PPC64) += vdso64/ obj-$(CONFIG_ALTIVEC) += vecemu.o obj-$(CONFIG_PPC_970_NAP) += idle_power4.o --- a/arch/powerpc/kernel/module.c +++ b/arch/powerpc/kernel/module.c @@ -72,13 +72,15 @@ int module_finalize(const Elf_Ehdr *hdr, do_feature_fixups(powerpc_firmware_features, (void *)sect->sh_addr, (void *)sect->sh_addr + sect->sh_size); +#endif /* CONFIG_PPC64 */

+#ifdef CONFIG_PPC_BARRIER_NOSPEC sect = find_section(hdr, sechdrs, "__spec_barrier_fixup"); if (sect != NULL) do_barrier_nospec_fixups_range(barrier_nospec_enabled, (void *)sect->sh_addr, (void *)sect->sh_addr + sect->sh_size); -#endif +#endif /* CONFIG_PPC_BARRIER_NOSPEC */

sect = find_section(hdr, sechdrs, "__lwsync_fixup"); if (sect != NULL) --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -153,14 +153,16 @@ SECTIONS *(__rfi_flush_fixup) __stop___rfi_flush_fixup = .; } +#endif /* CONFIG_PPC64 */

+#ifdef CONFIG_PPC_BARRIER_NOSPEC . = ALIGN(8); __spec_barrier_fixup : AT(ADDR(__spec_barrier_fixup) - LOAD_OFFSET) { __start___barrier_nospec_fixup = .; *(__barrier_nospec_fixup) __stop___barrier_nospec_fixup = .; } -#endif +#endif /* CONFIG_PPC_BARRIER_NOSPEC */

EXCEPTION_TABLE(0)

--- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -304,6 +304,9 @@ void do_barrier_nospec_fixups_range(bool printk(KERN_DEBUG "barrier-nospec: patched %d locations\n", i); }

+#endif /* CONFIG_PPC_BOOK3S_64 */ + +#ifdef CONFIG_PPC_BARRIER_NOSPEC void do_barrier_nospec_fixups(bool enable) { void *start, *end; @@ -313,8 +316,7 @@ void do_barrier_nospec_fixups(bool enabl

do_barrier_nospec_fixups_range(enable, start, end); } - -#endif /* CONFIG_PPC_BOOK3S_64 */ +#endif /* CONFIG_PPC_BARRIER_NOSPEC */

void do_lwsync_fixups(unsigned long value, void *fixup_start, void *fixup_end) {

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

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

From: Diana Craciun diana.craciun@nxp.com

commit 406d2b6ae3420f5bb2b3db6986dc6f0b6dbb637b upstream.

In a subsequent patch we will enable building security.c for Book3E. However the NXP platforms are not vulnerable to Meltdown, so make the Meltdown vulnerability reporting PPC_BOOK3S_64 specific.

Signed-off-by: Diana Craciun diana.craciun@nxp.com [mpe: Split out of larger patch] Signed-off-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/powerpc/kernel/security.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -92,6 +92,7 @@ static __init int barrier_nospec_debugfs device_initcall(barrier_nospec_debugfs_init); #endif /* CONFIG_DEBUG_FS */

+#ifdef CONFIG_PPC_BOOK3S_64 ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) { bool thread_priv; @@ -124,6 +125,7 @@ ssize_t cpu_show_meltdown(struct device

return sprintf(buf, "Vulnerable\n"); } +#endif

ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf) {

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

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

From: Diana Craciun diana.craciun@nxp.com

commit c28218d4abbf4f2035495334d8bfcba64bda4787 upstream.

Used barrier_nospec to sanitize the syscall table.

Signed-off-by: Diana Craciun diana.craciun@nxp.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/powerpc/kernel/entry_32.S | 10 ++++++++++ 1 file changed, 10 insertions(+)

--- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -33,6 +33,7 @@ #include <asm/unistd.h> #include <asm/ptrace.h> #include <asm/export.h> +#include <asm/barrier.h>

/* * MSR_KERNEL is > 0x10000 on 4xx/Book-E since it include MSR_CE. @@ -358,6 +359,15 @@ syscall_dotrace_cont: ori r10,r10,sys_call_table@l slwi r0,r0,2 bge- 66f + + barrier_nospec_asm + /* + * Prevent the load of the handler below (based on the user-passed + * system call number) being speculatively executed until the test + * against NR_syscalls and branch to .66f above has + * committed. + */ + lwzx r10,r10,r0 /* Fetch system call handler [ptr] */ mtlr r10 addi r9,r1,STACK_FRAME_OVERHEAD

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

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

From: Michael Ellerman mpe@ellerman.id.au

commit dc8c6cce9a26a51fc19961accb978217a3ba8c75 upstream.

Add security feature flags to indicate the need for software to flush the count cache on context switch, and for the presence of a hardware assisted count cache flush.

Signed-off-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/powerpc/include/asm/security_features.h | 6 ++++++ 1 file changed, 6 insertions(+)

--- a/arch/powerpc/include/asm/security_features.h +++ b/arch/powerpc/include/asm/security_features.h @@ -59,6 +59,9 @@ static inline bool security_ftr_enabled( // Indirect branch prediction cache disabled #define SEC_FTR_COUNT_CACHE_DISABLED 0x0000000000000020ull

+// bcctr 2,0,0 triggers a hardware assisted count cache flush +#define SEC_FTR_BCCTR_FLUSH_ASSIST 0x0000000000000800ull +

// Features indicating need for Spectre/Meltdown mitigations

@@ -74,6 +77,9 @@ static inline bool security_ftr_enabled( // Firmware configuration indicates user favours security over performance #define SEC_FTR_FAVOUR_SECURITY 0x0000000000000200ull

+// Software required to flush count cache on context switch +#define SEC_FTR_FLUSH_COUNT_CACHE 0x0000000000000400ull +

// Features enabled by default #define SEC_FTR_DEFAULT \

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

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

From: Michael Ellerman mpe@ellerman.id.au

commit ba72dc171954b782a79d25e0f4b3ed91090c3b1e upstream.

Use the existing hypercall to determine the appropriate settings for the count cache flush, and then call the generic powerpc code to set it up based on the security feature flags.

Signed-off-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/powerpc/include/asm/hvcall.h | 2 ++ arch/powerpc/platforms/pseries/setup.c | 7 +++++++ 2 files changed, 9 insertions(+)

--- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -340,10 +340,12 @@ #define H_CPU_CHAR_BRANCH_HINTS_HONORED (1ull << 58) // IBM bit 5 #define H_CPU_CHAR_THREAD_RECONFIG_CTRL (1ull << 57) // IBM bit 6 #define H_CPU_CHAR_COUNT_CACHE_DISABLED (1ull << 56) // IBM bit 7 +#define H_CPU_CHAR_BCCTR_FLUSH_ASSIST (1ull << 54) // IBM bit 9

#define H_CPU_BEHAV_FAVOUR_SECURITY (1ull << 63) // IBM bit 0 #define H_CPU_BEHAV_L1D_FLUSH_PR (1ull << 62) // IBM bit 1 #define H_CPU_BEHAV_BNDS_CHK_SPEC_BAR (1ull << 61) // IBM bit 2 +#define H_CPU_BEHAV_FLUSH_COUNT_CACHE (1ull << 58) // IBM bit 5

/* Flag values used in H_REGISTER_PROC_TBL hcall */ #define PROC_TABLE_OP_MASK 0x18 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -484,6 +484,12 @@ static void init_cpu_char_feature_flags( if (result->character & H_CPU_CHAR_COUNT_CACHE_DISABLED) security_ftr_set(SEC_FTR_COUNT_CACHE_DISABLED);

+ if (result->character & H_CPU_CHAR_BCCTR_FLUSH_ASSIST) + security_ftr_set(SEC_FTR_BCCTR_FLUSH_ASSIST); + + if (result->behaviour & H_CPU_BEHAV_FLUSH_COUNT_CACHE) + security_ftr_set(SEC_FTR_FLUSH_COUNT_CACHE); + /* * The features below are enabled by default, so we instead look to see * if firmware has *disabled* them, and clear them if so. @@ -534,6 +540,7 @@ void pseries_setup_rfi_flush(void) security_ftr_enabled(SEC_FTR_L1D_FLUSH_PR);

setup_rfi_flush(types, enable); + setup_count_cache_flush(); }

static void __init pSeries_setup_arch(void)

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

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

From: Diana Craciun diana.craciun@nxp.com

commit 76a5eaa38b15dda92cd6964248c39b5a6f3a4e9d upstream.

In order to protect against speculation attacks (Spectre variant 2) on NXP PowerPC platforms, the branch predictor should be flushed when the privillege level is changed. This patch is adding the infrastructure to fixup at runtime the code sections that are performing the branch predictor flush depending on a boot arg parameter which is added later in a separate patch.

Signed-off-by: Diana Craciun diana.craciun@nxp.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/powerpc/include/asm/feature-fixups.h | 12 ++++++++++++ arch/powerpc/include/asm/setup.h | 2 ++ arch/powerpc/kernel/vmlinux.lds.S | 8 ++++++++ arch/powerpc/lib/feature-fixups.c | 23 +++++++++++++++++++++++ 4 files changed, 45 insertions(+)

--- a/arch/powerpc/include/asm/feature-fixups.h +++ b/arch/powerpc/include/asm/feature-fixups.h @@ -219,6 +219,17 @@ label##3: \ FTR_ENTRY_OFFSET 953b-954b; \ .popsection;

+#define START_BTB_FLUSH_SECTION \ +955: \ + +#define END_BTB_FLUSH_SECTION \ +956: \ + .pushsection __btb_flush_fixup,"a"; \ + .align 2; \ +957: \ + FTR_ENTRY_OFFSET 955b-957b; \ + FTR_ENTRY_OFFSET 956b-957b; \ + .popsection;

#ifndef __ASSEMBLY__ #include <linux/types.h> @@ -228,6 +239,7 @@ extern long __start___stf_entry_barrier_ extern long __start___stf_exit_barrier_fixup, __stop___stf_exit_barrier_fixup; extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup; extern long __start___barrier_nospec_fixup, __stop___barrier_nospec_fixup; +extern long __start__btb_flush_fixup, __stop__btb_flush_fixup;

void apply_feature_fixups(void); void setup_feature_keys(void); --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -66,6 +66,8 @@ void do_barrier_nospec_fixups_range(bool static inline void do_barrier_nospec_fixups_range(bool enable, void *start, void *end) { }; #endif

+void do_btb_flush_fixups(void); + #endif /* !__ASSEMBLY__ */

#endif /* _ASM_POWERPC_SETUP_H */ --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -164,6 +164,14 @@ SECTIONS } #endif /* CONFIG_PPC_BARRIER_NOSPEC */

+#ifdef CONFIG_PPC_FSL_BOOK3E + . = ALIGN(8); + __spec_btb_flush_fixup : AT(ADDR(__spec_btb_flush_fixup) - LOAD_OFFSET) { + __start__btb_flush_fixup = .; + *(__btb_flush_fixup) + __stop__btb_flush_fixup = .; + } +#endif EXCEPTION_TABLE(0)

NOTES :kernel :notes --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -347,6 +347,29 @@ void do_barrier_nospec_fixups_range(bool

printk(KERN_DEBUG "barrier-nospec: patched %d locations\n", i); } + +static void patch_btb_flush_section(long *curr) +{ + unsigned int *start, *end; + + start = (void *)curr + *curr; + end = (void *)curr + *(curr + 1); + for (; start < end; start++) { + pr_devel("patching dest %lx\n", (unsigned long)start); + patch_instruction(start, PPC_INST_NOP); + } +} + +void do_btb_flush_fixups(void) +{ + long *start, *end; + + start = PTRRELOC(&__start__btb_flush_fixup); + end = PTRRELOC(&__stop__btb_flush_fixup); + + for (; start < end; start += 2) + patch_btb_flush_section(start); +} #endif /* CONFIG_PPC_FSL_BOOK3E */

void do_lwsync_fixups(unsigned long value, void *fixup_start, void *fixup_end)

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

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

From: Diana Craciun diana.craciun@nxp.com

commit 7d8bad99ba5a22892f0cad6881289fdc3875a930 upstream.

Currently for CONFIG_PPC_FSL_BOOK3E the spectre_v2 file is incorrect:

$ cat /sys/devices/system/cpu/vulnerabilities/spectre_v2 "Mitigation: Software count cache flush"

Which is wrong. Fix it to report vulnerable for now.

Fixes: ee13cb249fab ("powerpc/64s: Add support for software count cache flush") Cc: stable@vger.kernel.org # v4.19+ Signed-off-by: Diana Craciun diana.craciun@nxp.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/powerpc/kernel/security.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -22,7 +22,7 @@ enum count_cache_flush_type { COUNT_CACHE_FLUSH_SW = 0x2, COUNT_CACHE_FLUSH_HW = 0x4, }; -static enum count_cache_flush_type count_cache_flush_type; +static enum count_cache_flush_type count_cache_flush_type = COUNT_CACHE_FLUSH_NONE;

bool barrier_nospec_enabled; static bool no_nospec;

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

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

From: Diana Craciun diana.craciun@nxp.com

commit f633a8ad636efb5d4bba1a047d4a0f1ef719aa06 upstream.

When the command line argument is present, the Spectre variant 2 mitigations are disabled.

Signed-off-by: Diana Craciun diana.craciun@nxp.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/powerpc/include/asm/setup.h | 5 +++++ arch/powerpc/kernel/security.c | 21 +++++++++++++++++++++ 2 files changed, 26 insertions(+)

--- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -66,6 +66,11 @@ void do_barrier_nospec_fixups_range(bool static inline void do_barrier_nospec_fixups_range(bool enable, void *start, void *end) { }; #endif

+#ifdef CONFIG_PPC_FSL_BOOK3E +void setup_spectre_v2(void); +#else +static inline void setup_spectre_v2(void) {}; +#endif void do_btb_flush_fixups(void);

#endif /* !__ASSEMBLY__ */ --- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -26,6 +26,10 @@ static enum count_cache_flush_type count

bool barrier_nospec_enabled; static bool no_nospec; +static bool btb_flush_enabled; +#ifdef CONFIG_PPC_FSL_BOOK3E +static bool no_spectrev2; +#endif

static void enable_barrier_nospec(bool enable) { @@ -101,6 +105,23 @@ static __init int barrier_nospec_debugfs device_initcall(barrier_nospec_debugfs_init); #endif /* CONFIG_DEBUG_FS */

+#ifdef CONFIG_PPC_FSL_BOOK3E +static int __init handle_nospectre_v2(char *p) +{ + no_spectrev2 = true; + + return 0; +} +early_param("nospectre_v2", handle_nospectre_v2); +void setup_spectre_v2(void) +{ + if (no_spectrev2) + do_btb_flush_fixups(); + else + btb_flush_enabled = true; +} +#endif /* CONFIG_PPC_FSL_BOOK3E */ + #ifdef CONFIG_PPC_BOOK3S_64 ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) {

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

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

From: Diana Craciun diana.craciun@nxp.com

commit 7fef436295bf6c05effe682c8797dfcb0deb112a upstream.

In order to protect against speculation attacks on indirect branches, the branch predictor is flushed at kernel entry to protect for the following situations: - userspace process attacking another userspace process - userspace process attacking the kernel Basically when the privillege level change (i.e.the kernel is entered), the branch predictor state is flushed.

Signed-off-by: Diana Craciun diana.craciun@nxp.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/powerpc/kernel/head_booke.h | 6 ++++++ arch/powerpc/kernel/head_fsl_booke.S | 15 +++++++++++++++ 2 files changed, 21 insertions(+)

--- a/arch/powerpc/kernel/head_booke.h +++ b/arch/powerpc/kernel/head_booke.h @@ -43,6 +43,9 @@ andi. r11, r11, MSR_PR; /* check whether user or kernel */\ mr r11, r1; \ beq 1f; \ +START_BTB_FLUSH_SECTION \ + BTB_FLUSH(r11) \ +END_BTB_FLUSH_SECTION \ /* if from user, start at top of this thread's kernel stack */ \ lwz r11, THREAD_INFO-THREAD(r10); \ ALLOC_STACK_FRAME(r11, THREAD_SIZE); \ @@ -128,6 +131,9 @@ stw r9,_CCR(r8); /* save CR on stack */\ mfspr r11,exc_level_srr1; /* check whether user or kernel */\ DO_KVM BOOKE_INTERRUPT_##intno exc_level_srr1; \ +START_BTB_FLUSH_SECTION \ + BTB_FLUSH(r10) \ +END_BTB_FLUSH_SECTION \ andi. r11,r11,MSR_PR; \ mfspr r11,SPRN_SPRG_THREAD; /* if from user, start at top of */\ lwz r11,THREAD_INFO-THREAD(r11); /* this thread's kernel stack */\ --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -452,6 +452,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) mfcr r13 stw r13, THREAD_NORMSAVE(3)(r10) DO_KVM BOOKE_INTERRUPT_DTLB_MISS SPRN_SRR1 +START_BTB_FLUSH_SECTION + mfspr r11, SPRN_SRR1 + andi. r10,r11,MSR_PR + beq 1f + BTB_FLUSH(r10) +1: +END_BTB_FLUSH_SECTION mfspr r10, SPRN_DEAR /* Get faulting address */

/* If we are faulting a kernel address, we have to use the @@ -546,6 +553,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) mfcr r13 stw r13, THREAD_NORMSAVE(3)(r10) DO_KVM BOOKE_INTERRUPT_ITLB_MISS SPRN_SRR1 +START_BTB_FLUSH_SECTION + mfspr r11, SPRN_SRR1 + andi. r10,r11,MSR_PR + beq 1f + BTB_FLUSH(r10) +1: +END_BTB_FLUSH_SECTION + mfspr r10, SPRN_SRR0 /* Get faulting address */

/* If we are faulting a kernel address, we have to use the

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

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

From: Diana Craciun diana.craciun@nxp.com

commit 3bc8ea8603ae4c1e09aca8de229ad38b8091fcb3 upstream.

If the user choses not to use the mitigations, replace the code sequence with nops.

Signed-off-by: Diana Craciun diana.craciun@nxp.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/powerpc/kernel/setup-common.c | 1 + 1 file changed, 1 insertion(+)

--- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -938,6 +938,7 @@ void __init setup_arch(char **cmdline_p) ppc_md.setup_arch();

setup_barrier_nospec(); + setup_spectre_v2();

paging_init();

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

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

From: Diana Craciun diana.craciun@nxp.com

commit 039daac5526932ec731e4499613018d263af8b3e upstream.

Fixed the following build warning: powerpc-linux-gnu-ld: warning: orphan section `__btb_flush_fixup' from `arch/powerpc/kernel/head_44x.o' being placed in section `__btb_flush_fixup'.

Signed-off-by: Diana Craciun diana.craciun@nxp.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/powerpc/kernel/head_booke.h | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-)

--- a/arch/powerpc/kernel/head_booke.h +++ b/arch/powerpc/kernel/head_booke.h @@ -32,6 +32,16 @@ */ #define THREAD_NORMSAVE(offset) (THREAD_NORMSAVES + (offset * 4))

+#ifdef CONFIG_PPC_FSL_BOOK3E +#define BOOKE_CLEAR_BTB(reg) \ +START_BTB_FLUSH_SECTION \ + BTB_FLUSH(reg) \ +END_BTB_FLUSH_SECTION +#else +#define BOOKE_CLEAR_BTB(reg) +#endif + + #define NORMAL_EXCEPTION_PROLOG(intno) \ mtspr SPRN_SPRG_WSCRATCH0, r10; /* save one register */ \ mfspr r10, SPRN_SPRG_THREAD; \ @@ -43,9 +53,7 @@ andi. r11, r11, MSR_PR; /* check whether user or kernel */\ mr r11, r1; \ beq 1f; \ -START_BTB_FLUSH_SECTION \ - BTB_FLUSH(r11) \ -END_BTB_FLUSH_SECTION \ + BOOKE_CLEAR_BTB(r11) \ /* if from user, start at top of this thread's kernel stack */ \ lwz r11, THREAD_INFO-THREAD(r10); \ ALLOC_STACK_FRAME(r11, THREAD_SIZE); \ @@ -131,9 +139,7 @@ END_BTB_FLUSH_SECTION \ stw r9,_CCR(r8); /* save CR on stack */\ mfspr r11,exc_level_srr1; /* check whether user or kernel */\ DO_KVM BOOKE_INTERRUPT_##intno exc_level_srr1; \ -START_BTB_FLUSH_SECTION \ - BTB_FLUSH(r10) \ -END_BTB_FLUSH_SECTION \ + BOOKE_CLEAR_BTB(r10) \ andi. r11,r11,MSR_PR; \ mfspr r11,SPRN_SPRG_THREAD; /* if from user, start at top of */\ lwz r11,THREAD_INFO-THREAD(r11); /* this thread's kernel stack */\

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

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

From: Michael Ellerman mpe@ellerman.id.au

commit 92edf8df0ff2ae86cc632eeca0e651fd8431d40d upstream.

When I updated the spectre_v2 reporting to handle software count cache flush I got the logic wrong when there's no software count cache enabled at all.

The result is that on systems with the software count cache flush disabled we print:

Mitigation: Indirect branch cache disabled, Software count cache flush

Which correctly indicates that the count cache is disabled, but incorrectly says the software count cache flush is enabled.

The root of the problem is that we are trying to handle all combinations of options. But we know now that we only expect to see the software count cache flush enabled if the other options are false.

So split the two cases, which simplifies the logic and fixes the bug. We were also missing a space before "(hardware accelerated)".

The result is we see one of:

Mitigation: Indirect branch serialisation (kernel only) Mitigation: Indirect branch cache disabled Mitigation: Software count cache flush Mitigation: Software count cache flush (hardware accelerated)

Fixes: ee13cb249fab ("powerpc/64s: Add support for software count cache flush") Cc: stable@vger.kernel.org # v4.19+ Signed-off-by: Michael Ellerman mpe@ellerman.id.au Reviewed-by: Michael Neuling mikey@neuling.org Reviewed-by: Diana Craciun diana.craciun@nxp.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/powerpc/kernel/security.c | 23 ++++++++--------------- 1 file changed, 8 insertions(+), 15 deletions(-)

--- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -189,29 +189,22 @@ ssize_t cpu_show_spectre_v2(struct devic bcs = security_ftr_enabled(SEC_FTR_BCCTRL_SERIALISED); ccd = security_ftr_enabled(SEC_FTR_COUNT_CACHE_DISABLED);

- if (bcs || ccd || count_cache_flush_type != COUNT_CACHE_FLUSH_NONE) { - bool comma = false; + if (bcs || ccd) { seq_buf_printf(&s, "Mitigation: ");

- if (bcs) { + if (bcs) seq_buf_printf(&s, "Indirect branch serialisation (kernel only)"); - comma = true; - }

- if (ccd) { - if (comma) - seq_buf_printf(&s, ", "); - seq_buf_printf(&s, "Indirect branch cache disabled"); - comma = true; - } - - if (comma) + if (bcs && ccd) seq_buf_printf(&s, ", ");

- seq_buf_printf(&s, "Software count cache flush"); + if (ccd) + seq_buf_printf(&s, "Indirect branch cache disabled"); + } else if (count_cache_flush_type != COUNT_CACHE_FLUSH_NONE) { + seq_buf_printf(&s, "Mitigation: Software count cache flush");

if (count_cache_flush_type == COUNT_CACHE_FLUSH_HW) - seq_buf_printf(&s, "(hardware accelerated)"); + seq_buf_printf(&s, " (hardware accelerated)"); } else if (btb_flush_enabled) { seq_buf_printf(&s, "Mitigation: Branch predictor state flush"); } else {

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

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

From: Josef Bacik josef@toxicpanda.com

commit 2cc8334270e281815c3850c3adea363c51f21e0d upstream.

When Filipe added the recursive directory logging stuff in 2f2ff0ee5e430 ("Btrfs: fix metadata inconsistencies after directory fsync") he specifically didn't take the directory i_mutex for the children directories that we need to log because of lockdep. This is generally fine, but can lead to this WARN_ON() tripping if we happen to run delayed deletion's in between our first search and our second search of dir_item/dir_indexes for this directory. We expect this to happen, so the WARN_ON() isn't necessary. Drop the WARN_ON() and add a comment so we know why this case can happen.

CC: stable@vger.kernel.org # 4.4+ Reviewed-by: Filipe Manana fdmanana@suse.com Signed-off-by: Josef Bacik josef@toxicpanda.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/btrfs/tree-log.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-)

--- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3422,9 +3422,16 @@ static noinline int log_dir_items(struct } btrfs_release_path(path);

- /* find the first key from this transaction again */ + /* + * Find the first key from this transaction again. See the note for + * log_new_dir_dentries, if we're logging a directory recursively we + * won't be holding its i_mutex, which means we can modify the directory + * while we're logging it. If we remove an entry between our first + * search and this search we'll not find the key again and can just + * bail. + */ ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0); - if (WARN_ON(ret != 0)) + if (ret != 0) goto done;

/*

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

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

From: Kohji Okuno okuno.kohji@jp.panasonic.com

commit 91740fc8242b4f260cfa4d4536d8551804777fae upstream.

In the current cpuidle implementation for i.MX6q, the CPU that sets 'WAIT_UNCLOCKED' and the CPU that returns to 'WAIT_CLOCKED' are always the same. While the CPU that sets 'WAIT_UNCLOCKED' is in IDLE state of "WAIT", if the other CPU wakes up and enters IDLE state of "WFI" istead of "WAIT", this CPU can not wake up at expired time. Because, in the case of "WFI", the CPU must be waked up by the local timer interrupt. But, while 'WAIT_UNCLOCKED' is set, the local timer is stopped, when all CPUs execute "wfi" instruction. As a result, the local timer interrupt is not fired. In this situation, this CPU will wake up by IRQ different from local timer. (e.g. broacast timer)

So, this fix changes CPU to return to 'WAIT_CLOCKED'.

Signed-off-by: Kohji Okuno okuno.kohji@jp.panasonic.com Fixes: e5f9dec8ff5f ("ARM: imx6q: support WAIT mode using cpuidle") Cc: stable@vger.kernel.org Signed-off-by: Shawn Guo shawnguo@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm/mach-imx/cpuidle-imx6q.c | 27 ++++++++++----------------- 1 file changed, 10 insertions(+), 17 deletions(-)

--- a/arch/arm/mach-imx/cpuidle-imx6q.c +++ b/arch/arm/mach-imx/cpuidle-imx6q.c @@ -16,30 +16,23 @@ #include "cpuidle.h" #include "hardware.h"

-static atomic_t master = ATOMIC_INIT(0); -static DEFINE_SPINLOCK(master_lock); +static int num_idle_cpus = 0; +static DEFINE_SPINLOCK(cpuidle_lock);

static int imx6q_enter_wait(struct cpuidle_device *dev, struct cpuidle_driver *drv, int index) { - if (atomic_inc_return(&master) == num_online_cpus()) { - /* - * With this lock, we prevent other cpu to exit and enter - * this function again and become the master. - */ - if (!spin_trylock(&master_lock)) - goto idle; + spin_lock(&cpuidle_lock); + if (++num_idle_cpus == num_online_cpus()) imx6_set_lpm(WAIT_UNCLOCKED); - cpu_do_idle(); - imx6_set_lpm(WAIT_CLOCKED); - spin_unlock(&master_lock); - goto done; - } + spin_unlock(&cpuidle_lock);

-idle: cpu_do_idle(); -done: - atomic_dec(&master); + + spin_lock(&cpuidle_lock); + if (num_idle_cpus-- == num_online_cpus()) + imx6_set_lpm(WAIT_CLOCKED); + spin_unlock(&cpuidle_lock);

return index; }

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

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

From: Olga Kornievskaia kolga@netapp.com

commit 0cb98abb5bd13b9a636bde603d952d722688b428 upstream.

Allow the async rpc task for finish and update the open state if needed, then free the slot. Otherwise, the async rpc unable to decode the reply.

Signed-off-by: Olga Kornievskaia kolga@netapp.com Fixes: ae55e59da0e4 ("pnfs: Don't release the sequence slot...") Cc: stable@vger.kernel.org # v4.18+ Signed-off-by: Trond Myklebust trond.myklebust@hammerspace.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/nfs/nfs4proc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2746,7 +2746,8 @@ static int _nfs4_open_and_get_state(stru nfs4_schedule_stateid_recovery(server, state); } out: - nfs4_sequence_free_slot(&opendata->o_res.seq_res); + if (!opendata->cancelled) + nfs4_sequence_free_slot(&opendata->o_res.seq_res); return ret; }

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

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

From: Gustavo A. R. Silva gustavo@embeddedor.com

commit 2b1d9c8f87235f593826b9cf46ec10247741fff9 upstream.

info->stream is indirectly controlled by user-space, hence leading to a potential exploitation of the Spectre variant 1 vulnerability.

This issue was detected with the help of Smatch:

sound/core/rawmidi.c:604 __snd_rawmidi_info_select() warn: potential spectre issue 'rmidi->streams' [r] (local cap)

Fix this by sanitizing info->stream before using it to index rmidi->streams.

Notice that given that speculation windows are large, the policy is to kill the speculation on the first load and not worry if it can be completed with a dependent load/store [1].

[1] https://lore.kernel.org/lkml/20180423164740.GY17484@dhcp22.suse.cz/

Cc: stable@vger.kernel.org Signed-off-by: Gustavo A. R. Silva gustavo@embeddedor.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- sound/core/rawmidi.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -29,6 +29,7 @@ #include <linux/mutex.h> #include <linux/module.h> #include <linux/delay.h> +#include <linux/nospec.h> #include <sound/rawmidi.h> #include <sound/info.h> #include <sound/control.h> @@ -591,6 +592,7 @@ static int __snd_rawmidi_info_select(str return -ENXIO; if (info->stream < 0 || info->stream > 1) return -EINVAL; + info->stream = array_index_nospec(info->stream, 2); pstr = &rmidi->streams[info->stream]; if (pstr->substream_count == 0) return -ENOENT;

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

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

From: Takashi Iwai tiwai@suse.de

commit ca0214ee2802dd47239a4e39fb21c5b00ef61b22 upstream.

The PCM OSS emulation converts and transfers the data on the fly via "plugins". The data is converted over the dynamically allocated buffer for each plugin, and recently syzkaller caught OOB in this flow.

Although the bisection by syzbot pointed out to the commit 65766ee0bf7f ("ALSA: oss: Use kvzalloc() for local buffer allocations"), this is merely a commit to replace vmalloc() with kvmalloc(), hence it can't be the cause. The further debug action revealed that this happens in the case where a slave PCM doesn't support only the stereo channels while the OSS stream is set up for a mono channel. Below is a brief explanation:

At each OSS parameter change, the driver sets up the PCM hw_params again in snd_pcm_oss_change_params_lock(). This is also the place where plugins are created and local buffers are allocated. The problem is that the plugins are created before the final hw_params is determined. Namely, two snd_pcm_hw_param_near() calls for setting the period size and periods may influence on the final result of channels, rates, etc, too, while the current code has already created plugins beforehand with the premature values. So, the plugin believes that channels=1, while the actual I/O is with channels=2, which makes the driver reading/writing over the allocated buffer size.

The fix is simply to move the plugin allocation code after the final hw_params call.

Reported-by: syzbot+d4503ae45b65c5bc1194@syzkaller.appspotmail.com Cc: stable@vger.kernel.org Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- sound/core/oss/pcm_oss.c | 43 ++++++++++++++++++++++--------------------- 1 file changed, 22 insertions(+), 21 deletions(-)

--- a/sound/core/oss/pcm_oss.c +++ b/sound/core/oss/pcm_oss.c @@ -940,6 +940,28 @@ static int snd_pcm_oss_change_params_loc oss_frame_size = snd_pcm_format_physical_width(params_format(params)) * params_channels(params) / 8;

+ err = snd_pcm_oss_period_size(substream, params, sparams); + if (err < 0) + goto failure; + + n = snd_pcm_plug_slave_size(substream, runtime->oss.period_bytes / oss_frame_size); + err = snd_pcm_hw_param_near(substream, sparams, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, n, NULL); + if (err < 0) + goto failure; + + err = snd_pcm_hw_param_near(substream, sparams, SNDRV_PCM_HW_PARAM_PERIODS, + runtime->oss.periods, NULL); + if (err < 0) + goto failure; + + snd_pcm_kernel_ioctl(substream, SNDRV_PCM_IOCTL_DROP, NULL); + + err = snd_pcm_kernel_ioctl(substream, SNDRV_PCM_IOCTL_HW_PARAMS, sparams); + if (err < 0) { + pcm_dbg(substream->pcm, "HW_PARAMS failed: %i\n", err); + goto failure; + } + #ifdef CONFIG_SND_PCM_OSS_PLUGINS snd_pcm_oss_plugin_clear(substream); if (!direct) { @@ -974,27 +996,6 @@ static int snd_pcm_oss_change_params_loc } #endif

- err = snd_pcm_oss_period_size(substream, params, sparams); - if (err < 0) - goto failure; - - n = snd_pcm_plug_slave_size(substream, runtime->oss.period_bytes / oss_frame_size); - err = snd_pcm_hw_param_near(substream, sparams, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, n, NULL); - if (err < 0) - goto failure; - - err = snd_pcm_hw_param_near(substream, sparams, SNDRV_PCM_HW_PARAM_PERIODS, - runtime->oss.periods, NULL); - if (err < 0) - goto failure; - - snd_pcm_kernel_ioctl(substream, SNDRV_PCM_IOCTL_DROP, NULL); - - if ((err = snd_pcm_kernel_ioctl(substream, SNDRV_PCM_IOCTL_HW_PARAMS, sparams)) < 0) { - pcm_dbg(substream->pcm, "HW_PARAMS failed: %i\n", err); - goto failure; - } - if (runtime->oss.trigger) { sw_params->start_threshold = 1; } else {

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

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

From: Kailang Yang kailang@realtek.com

commit 136824efaab2c095fc911048f7c7ddeda258c965 upstream.

This patch will enable WYSE AIO for Headset mode.

Signed-off-by: Kailang Yang kailang@realtek.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- sound/pci/hda/patch_realtek.c | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+)

--- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5436,6 +5436,9 @@ enum { ALC298_FIXUP_TPT470_DOCK, ALC255_FIXUP_DUMMY_LINEOUT_VERB, ALC255_FIXUP_DELL_HEADSET_MIC, + ALC225_FIXUP_DELL_WYSE_AIO_MIC_NO_PRESENCE, + ALC225_FIXUP_WYSE_AUTO_MUTE, + ALC225_FIXUP_WYSE_DISABLE_MIC_VREF, };

static const struct hda_fixup alc269_fixups[] = { @@ -6311,6 +6314,28 @@ static const struct hda_fixup alc269_fix .chained = true, .chain_id = ALC269_FIXUP_HEADSET_MIC }, + [ALC225_FIXUP_DELL_WYSE_AIO_MIC_NO_PRESENCE] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x16, 0x01011020 }, /* Rear Line out */ + { 0x19, 0x01a1913c }, /* use as Front headset mic, without its own jack detect */ + { } + }, + .chained = true, + .chain_id = ALC225_FIXUP_WYSE_AUTO_MUTE + }, + [ALC225_FIXUP_WYSE_AUTO_MUTE] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_auto_mute_via_amp, + .chained = true, + .chain_id = ALC225_FIXUP_WYSE_DISABLE_MIC_VREF + }, + [ALC225_FIXUP_WYSE_DISABLE_MIC_VREF] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_disable_mic_vref, + .chained = true, + .chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC + }, };

static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -6369,6 +6394,7 @@ static const struct snd_pci_quirk alc269 SND_PCI_QUIRK(0x1028, 0x0871, "Dell Precision 3630", ALC255_FIXUP_DELL_HEADSET_MIC), SND_PCI_QUIRK(0x1028, 0x0872, "Dell Precision 3630", ALC255_FIXUP_DELL_HEADSET_MIC), SND_PCI_QUIRK(0x1028, 0x0873, "Dell Precision 3930", ALC255_FIXUP_DUMMY_LINEOUT_VERB), + SND_PCI_QUIRK(0x1028, 0x08ad, "Dell WYSE AIO", ALC225_FIXUP_DELL_WYSE_AIO_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0935, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB), SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),

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

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

From: Fredrik Noring noring@nocrew.org

commit 54a7151b1496cddbb7a83546b7998103e98edc88 upstream.

Fix commit 56067812d5b0 ("kbuild: modversions: add infrastructure for emitting relative CRCs") where CRCs are interpreted in host byte order rather than proper kernel byte order. The bug is conditional on CONFIG_MODULE_REL_CRCS.

For example, when loading a BE module into a BE kernel compiled with a LE system, the error "disagrees about version of symbol module_layout" is produced. A message such as "Found checksum D7FA6856 vs module 5668FAD7" will be given with debug enabled, which indicates an obvious endian problem within __kcrctab within the kernel image.

The general solution is to use the macro TO_NATIVE, as is done in similar cases throughout modpost.c. With this correction it has been verified that a BE kernel compiled with a LE system accepts BE modules.

This change has also been verified with a LE kernel compiled with a LE system, in which case TO_NATIVE returns its value unmodified since the byte orders match. This is by far the common case.

Fixes: 56067812d5b0 ("kbuild: modversions: add infrastructure for emitting relative CRCs") Signed-off-by: Fredrik Noring noring@nocrew.org Cc: stable@vger.kernel.org Signed-off-by: Masahiro Yamada yamada.masahiro@socionext.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- scripts/mod/modpost.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -645,7 +645,7 @@ static void handle_modversions(struct mo info->sechdrs[sym->st_shndx].sh_offset - (info->hdr->e_type != ET_REL ? info->sechdrs[sym->st_shndx].sh_addr : 0); - crc = *crcp; + crc = TO_NATIVE(*crcp); } sym_update_crc(symname + strlen(CRC_PFX), mod, crc, export);

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

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

From: Darrick J. Wong darrick.wong@oracle.com

commit e6a9467ea14bae8691b0f72c500510c42ea8edb8 upstream.

ocfs2_reflink_inodes_lock() can swap the inode1/inode2 variables so that we always grab cluster locks in order of increasing inode number.

Unfortunately, we forget to swap the inode record buffer head pointers when we've done this, which leads to incorrect bookkeepping when we're trying to make the two inodes have the same refcount tree.

This has the effect of causing filesystem shutdowns if you're trying to reflink data from inode 100 into inode 97, where inode 100 already has a refcount tree attached and inode 97 doesn't. The reflink code decides to copy the refcount tree pointer from 100 to 97, but uses inode 97's inode record to open the tree root (which it doesn't have) and blows up. This issue causes filesystem shutdowns and metadata corruption!

Link: http://lkml.kernel.org/r/20190312214910.GK20533@magnolia Fixes: 29ac8e856cb369 ("ocfs2: implement the VFS clone_range, copy_range, and dedupe_range features") Signed-off-by: Darrick J. Wong darrick.wong@oracle.com Reviewed-by: Joseph Qi jiangqi903@gmail.com Cc: Mark Fasheh mfasheh@versity.com Cc: Joel Becker jlbec@evilplan.org Cc: Junxiao Bi junxiao.bi@oracle.com Cc: Joseph Qi joseph.qi@huawei.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/ocfs2/refcounttree.c | 42 ++++++++++++++++++++++++------------------ 1 file changed, 24 insertions(+), 18 deletions(-)

--- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -4716,22 +4716,23 @@ out:

/* Lock an inode and grab a bh pointing to the inode. */ static int ocfs2_reflink_inodes_lock(struct inode *s_inode, - struct buffer_head **bh1, + struct buffer_head **bh_s, struct inode *t_inode, - struct buffer_head **bh2) + struct buffer_head **bh_t) { - struct inode *inode1; - struct inode *inode2; + struct inode *inode1 = s_inode; + struct inode *inode2 = t_inode; struct ocfs2_inode_info *oi1; struct ocfs2_inode_info *oi2; + struct buffer_head *bh1 = NULL; + struct buffer_head *bh2 = NULL; bool same_inode = (s_inode == t_inode); + bool need_swap = (inode1->i_ino > inode2->i_ino); int status;

/* First grab the VFS and rw locks. */ lock_two_nondirectories(s_inode, t_inode); - inode1 = s_inode; - inode2 = t_inode; - if (inode1->i_ino > inode2->i_ino) + if (need_swap) swap(inode1, inode2);

status = ocfs2_rw_lock(inode1, 1); @@ -4754,17 +4755,13 @@ static int ocfs2_reflink_inodes_lock(str trace_ocfs2_double_lock((unsigned long long)oi1->ip_blkno, (unsigned long long)oi2->ip_blkno);

- if (*bh1) - *bh1 = NULL; - if (*bh2) - *bh2 = NULL; - /* We always want to lock the one with the lower lockid first. */ if (oi1->ip_blkno > oi2->ip_blkno) mlog_errno(-ENOLCK);

/* lock id1 */ - status = ocfs2_inode_lock_nested(inode1, bh1, 1, OI_LS_REFLINK_TARGET); + status = ocfs2_inode_lock_nested(inode1, &bh1, 1, + OI_LS_REFLINK_TARGET); if (status < 0) { if (status != -ENOENT) mlog_errno(status); @@ -4773,15 +4770,25 @@ static int ocfs2_reflink_inodes_lock(str

/* lock id2 */ if (!same_inode) { - status = ocfs2_inode_lock_nested(inode2, bh2, 1, + status = ocfs2_inode_lock_nested(inode2, &bh2, 1, OI_LS_REFLINK_TARGET); if (status < 0) { if (status != -ENOENT) mlog_errno(status); goto out_cl1; } - } else - *bh2 = *bh1; + } else { + bh2 = bh1; + } + + /* + * If we swapped inode order above, we have to swap the buffer heads + * before passing them back to the caller. + */ + if (need_swap) + swap(bh1, bh2); + *bh_s = bh1; + *bh_t = bh2;

trace_ocfs2_double_lock_end( (unsigned long long)OCFS2_I(inode1)->ip_blkno, @@ -4791,8 +4798,7 @@ static int ocfs2_reflink_inodes_lock(str

out_cl1: ocfs2_inode_unlock(inode1, 1); - brelse(*bh1); - *bh1 = NULL; + brelse(bh1); out_rw2: ocfs2_rw_unlock(inode2, 1); out_i2:

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

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

From: Martin K. Petersen martin.petersen@oracle.com

commit 1d5de5bd311be7cd54f02f7cd164f0349a75c876 upstream.

Commit a83da8a4509d ("scsi: sd: Optimal I/O size should be a multiple of physical block size") split one conditional into several separate statements in an effort to provide more accurate warning messages when a device reports a nonsensical value. However, this reorganization accidentally dropped the precondition of the reported value being larger than zero. This lead to a warning getting emitted on devices that do not report an optimal I/O size at all.

Remain silent if a device does not report an optimal I/O size.

Fixes: a83da8a4509d ("scsi: sd: Optimal I/O size should be a multiple of physical block size") Cc: Randy Dunlap rdunlap@infradead.org Cc: stable@vger.kernel.org Reported-by: Hussam Al-Tayeb ht990332@gmx.com Tested-by: Hussam Al-Tayeb ht990332@gmx.com Reviewed-by: Bart Van Assche bvanassche@acm.org Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

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

--- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3084,6 +3084,9 @@ static bool sd_validate_opt_xfer_size(st unsigned int opt_xfer_bytes = logical_to_bytes(sdp, sdkp->opt_xfer_blocks);

+ if (sdkp->opt_xfer_blocks == 0) + return false; + if (sdkp->opt_xfer_blocks > dev_max) { sd_first_printk(KERN_WARNING, sdkp, "Optimal transfer size %u logical blocks " \

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

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

From: Steffen Maier maier@linux.ibm.com

commit 242ec1455151267fe35a0834aa9038e4c4670884 upstream.

Suppose more than one non-NPIV FCP device is active on the same channel. Send I/O to storage and have some of the pending I/O run into a SCSI command timeout, e.g. due to bit errors on the fibre. Now the error situation stops. However, we saw FCP requests continue to timeout in the channel. The abort will be successful, but the subsequent TUR fails. Scsi_eh starts. The LUN reset fails. The target reset fails. The host reset only did an FCP device recovery. However, for non-NPIV FCP devices, this does not close and reopen ports on the SAN-side if other non-NPIV FCP device(s) share the same open ports.

In order to resolve the continuing FCP request timeouts, we need to explicitly close and reopen ports on the SAN-side.

This was missing since the beginning of zfcp in v2.6.0 history commit ea127f975424 ("[PATCH] s390 (7/7): zfcp host adapter.").

Note: The FSF requests for forced port reopen could run into FSF request timeouts due to other reasons. This would trigger an internal FCP device recovery. Pending forced port reopen recoveries would get dismissed. So some ports might not get fully reopened during this host reset handler. However, subsequent I/O would trigger the above described escalation and eventually all ports would be forced reopen to resolve any continuing FCP request timeouts due to earlier bit errors.

Signed-off-by: Steffen Maier maier@linux.ibm.com Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: stable@vger.kernel.org #3.0+ Reviewed-by: Jens Remus jremus@linux.ibm.com Reviewed-by: Benjamin Block bblock@linux.ibm.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/s390/scsi/zfcp_erp.c | 14 ++++++++++++++ drivers/s390/scsi/zfcp_ext.h | 2 ++ drivers/s390/scsi/zfcp_scsi.c | 4 ++++ 3 files changed, 20 insertions(+)

--- a/drivers/s390/scsi/zfcp_erp.c +++ b/drivers/s390/scsi/zfcp_erp.c @@ -652,6 +652,20 @@ static void zfcp_erp_strategy_memwait(st add_timer(&erp_action->timer); }

+void zfcp_erp_port_forced_reopen_all(struct zfcp_adapter *adapter, + int clear, char *dbftag) +{ + unsigned long flags; + struct zfcp_port *port; + + write_lock_irqsave(&adapter->erp_lock, flags); + read_lock(&adapter->port_list_lock); + list_for_each_entry(port, &adapter->port_list, list) + _zfcp_erp_port_forced_reopen(port, clear, dbftag); + read_unlock(&adapter->port_list_lock); + write_unlock_irqrestore(&adapter->erp_lock, flags); +} + static void _zfcp_erp_port_reopen_all(struct zfcp_adapter *adapter, int clear, char *id) { --- a/drivers/s390/scsi/zfcp_ext.h +++ b/drivers/s390/scsi/zfcp_ext.h @@ -68,6 +68,8 @@ extern void zfcp_erp_clear_port_status(s extern int zfcp_erp_port_reopen(struct zfcp_port *, int, char *); extern void zfcp_erp_port_shutdown(struct zfcp_port *, int, char *); extern void zfcp_erp_port_forced_reopen(struct zfcp_port *, int, char *); +extern void zfcp_erp_port_forced_reopen_all(struct zfcp_adapter *adapter, + int clear, char *dbftag); extern void zfcp_erp_set_lun_status(struct scsi_device *, u32); extern void zfcp_erp_clear_lun_status(struct scsi_device *, u32); extern void zfcp_erp_lun_reopen(struct scsi_device *, int, char *); --- a/drivers/s390/scsi/zfcp_scsi.c +++ b/drivers/s390/scsi/zfcp_scsi.c @@ -327,6 +327,10 @@ static int zfcp_scsi_eh_host_reset_handl struct zfcp_adapter *adapter = zfcp_sdev->port->adapter; int ret = SUCCESS, fc_ret;

+ if (!(adapter->connection_features & FSF_FEATURE_NPIV_MODE)) { + zfcp_erp_port_forced_reopen_all(adapter, 0, "schrh_p"); + zfcp_erp_wait(adapter); + } zfcp_erp_adapter_reopen(adapter, 0, "schrh_1"); zfcp_erp_wait(adapter); fc_ret = fc_block_scsi_eh(scpnt);

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

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

From: Ian Abbott abbotti@mev.co.uk

commit bafd9c64056cd034a1174dcadb65cd3b294ff8f6 upstream.

`ni_cdio_cmdtest()` validates Comedi asynchronous commands for the DIO subdevice (subdevice 2) of supported National Instruments M-series cards. It is called when handling the `COMEDI_CMD` and `COMEDI_CMDTEST` ioctls for this subdevice. There are two causes for a possible divide-by-zero error when validating that the `stop_arg` member of the passed-in command is not too large.

The first cause for the divide-by-zero is that calls to `comedi_bytes_per_scan()` are only valid once the command has been copied to `s->async->cmd`, but that copy is only done for the `COMEDI_CMD` ioctl. For the `COMEDI_CMDTEST` ioctl, it will use whatever was left there by the previous `COMEDI_CMD` ioctl, if any. (This is very likely, as it is usual for the application to use `COMEDI_CMDTEST` before `COMEDI_CMD`.) If there has been no previous, valid `COMEDI_CMD` for this subdevice, then `comedi_bytes_per_scan()` will return 0, so the subsequent division in `ni_cdio_cmdtest()` of `s->async->prealloc_bufsz / comedi_bytes_per_scan(s)` will be a divide-by-zero error. To fix this error, call a new function `comedi_bytes_per_scan_cmd(s, cmd)`, based on the existing `comedi_bytes_per_scan(s)` but using a specified `struct comedi_cmd` for its calculations. (Also refactor `comedi_bytes_per_scan()` to call the new function.)

Once the first cause for the divide-by-zero has been fixed, the second cause is that `comedi_bytes_per_scan_cmd()` can legitimately return 0 if the `scan_end_arg` member of the `struct comedi_cmd` being tested is 0. Fix it by only performing the division (and validating that `stop_arg` is no more than the maximum value) if `comedi_bytes_per_scan_cmd()` returns a non-zero value.

The problem was reported on the COMEDI mailing list here: https://groups.google.com/forum/#%21topic/comedi_list/4t9WlHzMhKM

Reported-by: Ivan Vasilyev grabesstimme@gmail.com Tested-by: Ivan Vasilyev grabesstimme@gmail.com Fixes: f164cbf98fa8 ("staging: comedi: ni_mio_common: add finite regeneration to dio output") Cc: stable@vger.kernel.org # 4.6+ Cc: Spencer E. Olson olsonse@umich.edu Signed-off-by: Ian Abbott abbotti@mev.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/staging/comedi/comedidev.h | 2 + drivers/staging/comedi/drivers.c | 33 +++++++++++++++++++++---- drivers/staging/comedi/drivers/ni_mio_common.c | 10 +++++-- 3 files changed, 38 insertions(+), 7 deletions(-)

--- a/drivers/staging/comedi/comedidev.h +++ b/drivers/staging/comedi/comedidev.h @@ -992,6 +992,8 @@ int comedi_dio_insn_config(struct comedi unsigned int mask); unsigned int comedi_dio_update_state(struct comedi_subdevice *s, unsigned int *data); +unsigned int comedi_bytes_per_scan_cmd(struct comedi_subdevice *s, + struct comedi_cmd *cmd); unsigned int comedi_bytes_per_scan(struct comedi_subdevice *s); unsigned int comedi_nscans_left(struct comedi_subdevice *s, unsigned int nscans); --- a/drivers/staging/comedi/drivers.c +++ b/drivers/staging/comedi/drivers.c @@ -390,11 +390,13 @@ unsigned int comedi_dio_update_state(str EXPORT_SYMBOL_GPL(comedi_dio_update_state);

/** - * comedi_bytes_per_scan() - Get length of asynchronous command "scan" in bytes + * comedi_bytes_per_scan_cmd() - Get length of asynchronous command "scan" in + * bytes * @s: COMEDI subdevice. + * @cmd: COMEDI command. * * Determines the overall scan length according to the subdevice type and the - * number of channels in the scan. + * number of channels in the scan for the specified command. * * For digital input, output or input/output subdevices, samples for * multiple channels are assumed to be packed into one or more unsigned @@ -404,9 +406,9 @@ EXPORT_SYMBOL_GPL(comedi_dio_update_stat * * Returns the overall scan length in bytes. */ -unsigned int comedi_bytes_per_scan(struct comedi_subdevice *s) +unsigned int comedi_bytes_per_scan_cmd(struct comedi_subdevice *s, + struct comedi_cmd *cmd) { - struct comedi_cmd *cmd = &s->async->cmd; unsigned int num_samples; unsigned int bits_per_sample;

@@ -423,6 +425,29 @@ unsigned int comedi_bytes_per_scan(struc } return comedi_samples_to_bytes(s, num_samples); } +EXPORT_SYMBOL_GPL(comedi_bytes_per_scan_cmd); + +/** + * comedi_bytes_per_scan() - Get length of asynchronous command "scan" in bytes + * @s: COMEDI subdevice. + * + * Determines the overall scan length according to the subdevice type and the + * number of channels in the scan for the current command. + * + * For digital input, output or input/output subdevices, samples for + * multiple channels are assumed to be packed into one or more unsigned + * short or unsigned int values according to the subdevice's %SDF_LSAMPL + * flag. For other types of subdevice, samples are assumed to occupy a + * whole unsigned short or unsigned int according to the %SDF_LSAMPL flag. + * + * Returns the overall scan length in bytes. + */ +unsigned int comedi_bytes_per_scan(struct comedi_subdevice *s) +{ + struct comedi_cmd *cmd = &s->async->cmd; + + return comedi_bytes_per_scan_cmd(s, cmd); +} EXPORT_SYMBOL_GPL(comedi_bytes_per_scan);

static unsigned int __comedi_nscans_left(struct comedi_subdevice *s, --- a/drivers/staging/comedi/drivers/ni_mio_common.c +++ b/drivers/staging/comedi/drivers/ni_mio_common.c @@ -3523,6 +3523,7 @@ static int ni_cdio_check_chanlist(struct static int ni_cdio_cmdtest(struct comedi_device *dev, struct comedi_subdevice *s, struct comedi_cmd *cmd) { + unsigned int bytes_per_scan; int err = 0; int tmp;

@@ -3552,9 +3553,12 @@ static int ni_cdio_cmdtest(struct comedi err |= comedi_check_trigger_arg_is(&cmd->convert_arg, 0); err |= comedi_check_trigger_arg_is(&cmd->scan_end_arg, cmd->chanlist_len); - err |= comedi_check_trigger_arg_max(&cmd->stop_arg, - s->async->prealloc_bufsz / - comedi_bytes_per_scan(s)); + bytes_per_scan = comedi_bytes_per_scan_cmd(s, cmd); + if (bytes_per_scan) { + err |= comedi_check_trigger_arg_max(&cmd->stop_arg, + s->async->prealloc_bufsz / + bytes_per_scan); + }

if (err) return 3;

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

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

From: Malcolm Priestley tvboxspy@gmail.com

commit 3b9c2f2e0e99bb67c96abcb659b3465efe3bee1f upstream.

It appears on some slower systems that the driver can find its way out of the workqueue while the interrupt is disabled by continuous polling by it.

Move MACvIntEnable to vnt_interrupt_work so that it is always enabled on all routes out of vnt_interrupt_process.

Move MACvIntDisable so that the device doesn't keep polling the system while the workqueue is being processed.

Signed-off-by: Malcolm Priestley tvboxspy@gmail.com CC: stable@vger.kernel.org # v4.2+ Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/staging/vt6655/device_main.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

--- a/drivers/staging/vt6655/device_main.c +++ b/drivers/staging/vt6655/device_main.c @@ -973,8 +973,6 @@ static void vnt_interrupt_process(struct return; }

- MACvIntDisable(priv->PortOffset); - spin_lock_irqsave(&priv->lock, flags);

/* Read low level stats */ @@ -1062,8 +1060,6 @@ static void vnt_interrupt_process(struct }

spin_unlock_irqrestore(&priv->lock, flags); - - MACvIntEnable(priv->PortOffset, IMR_MASK_VALUE); }

static void vnt_interrupt_work(struct work_struct *work) @@ -1073,6 +1069,8 @@ static void vnt_interrupt_work(struct wo

if (priv->vif) vnt_interrupt_process(priv); + + MACvIntEnable(priv->PortOffset, IMR_MASK_VALUE); }

static irqreturn_t vnt_interrupt(int irq, void *arg) @@ -1081,6 +1079,8 @@ static irqreturn_t vnt_interrupt(int irq

schedule_work(&priv->interrupt_work);

+ MACvIntDisable(priv->PortOffset); + return IRQ_HANDLED; }

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

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

From: Hoan Nguyen An na-hoan@jinso.co.jp

commit 93bcefd4c6bad4c69dbc4edcd3fbf774b24d930d upstream.

We disable transmission interrupt (clear SCSCR_TIE) after all data has been transmitted (if uart_circ_empty(xmit)). While transmitting, if the data is still in the tty buffer, re-enable the SCSCR_TIE bit, which was done at sci_start_tx(). This is unnecessary processing, wasting CPU operation if the data transmission length is large. And further, transmit end, FIFO empty bits disabling have also been performed in the step above.

Signed-off-by: Hoan Nguyen An na-hoan@jinso.co.jp Cc: stable stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/tty/serial/sh-sci.c | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-)

--- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -806,19 +806,9 @@ static void sci_transmit_chars(struct ua

if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS) uart_write_wakeup(port); - if (uart_circ_empty(xmit)) { + if (uart_circ_empty(xmit)) sci_stop_tx(port); - } else { - ctrl = serial_port_in(port, SCSCR);

- if (port->type != PORT_SCI) { - serial_port_in(port, SCxSR); /* Dummy read */ - sci_clear_SCxSR(port, SCxSR_TDxE_CLEAR(port)); - } - - ctrl |= SCSCR_TIE; - serial_port_out(port, SCSCR, ctrl); - } }

/* On SH3, SCIF may read end-of-break as a space->mark char */

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

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

From: George McCollister george.mccollister@gmail.com

commit 422c2537ba9d42320f8ab6573940269f87095320 upstream.

Add PIDs for the NovaTech OrionLX+ and Orion I/O so they can be automatically detected.

Signed-off-by: George McCollister george.mccollister@gmail.com Cc: stable stable@vger.kernel.org Signed-off-by: Johan Hovold johan@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/usb/serial/ftdi_sio.c | 2 ++ drivers/usb/serial/ftdi_sio_ids.h | 4 +++- 2 files changed, 5 insertions(+), 1 deletion(-)

--- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -604,6 +604,8 @@ static const struct usb_device_id id_tab .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, { USB_DEVICE(FTDI_VID, FTDI_NT_ORIONLXM_PID), .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, + { USB_DEVICE(FTDI_VID, FTDI_NT_ORIONLX_PLUS_PID) }, + { USB_DEVICE(FTDI_VID, FTDI_NT_ORION_IO_PID) }, { USB_DEVICE(FTDI_VID, FTDI_SYNAPSE_SS200_PID) }, { USB_DEVICE(FTDI_VID, FTDI_CUSTOMWARE_MINIPLEX_PID) }, { USB_DEVICE(FTDI_VID, FTDI_CUSTOMWARE_MINIPLEX2_PID) }, --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -567,7 +567,9 @@ /* * NovaTech product ids (FTDI_VID) */ -#define FTDI_NT_ORIONLXM_PID 0x7c90 /* OrionLXm Substation Automation Platform */ +#define FTDI_NT_ORIONLXM_PID 0x7c90 /* OrionLXm Substation Automation Platform */ +#define FTDI_NT_ORIONLX_PLUS_PID 0x7c91 /* OrionLX+ Substation Automation Platform */ +#define FTDI_NT_ORION_IO_PID 0x7c92 /* Orion I/O */

/* * Synapse Wireless product ids (FTDI_VID)

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

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

From: Mans Rullgard mans@mansr.com

commit f8df5c2c3e2df5ffaf9fb5503da93d477a8c7db4 upstream.

The SIMCom SIM5218 and compatible devices have 5 USB interfaces, only 4 of which are serial ports. The fifth is a network interface supported by the qmi-wwan driver. Furthermore, the serial ports do not support modem control signals. Add driver_info flags to reflect this.

Signed-off-by: Mans Rullgard mans@mansr.com Fixes: ec0cd94d881c ("usb: option: add SIMCom SIM5218") Cc: stable stable@vger.kernel.org # 3.2 Signed-off-by: Johan Hovold johan@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

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

--- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1069,7 +1069,8 @@ static const struct usb_device_id option .driver_info = RSVD(3) }, { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6613)}, /* Onda H600/ZTE MF330 */ { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x0023)}, /* ONYX 3G device */ - { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9000)}, /* SIMCom SIM5218 */ + { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9000), /* SIMCom SIM5218 */ + .driver_info = NCTRL(0) | NCTRL(1) | NCTRL(2) | NCTRL(3) | RSVD(4) }, /* Quectel products using Qualcomm vendor ID */ { USB_DEVICE(QUALCOMM_VENDOR_ID, QUECTEL_PRODUCT_UC15)}, { USB_DEVICE(QUALCOMM_VENDOR_ID, QUECTEL_PRODUCT_UC20),

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

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

From: Bjørn Mork bjorn@mork.no

commit 84f3b43f7378b98b7e3096d5499de75183d4347c upstream.

This is a Qualcomm based device with a QMI function on interface 4. It is mode switched from 2020:2030 using a standard eject message.

T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 6 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1 P: Vendor=2020 ProdID=2031 Rev= 2.32 S: Manufacturer=Mobile Connect S: Product=Mobile Connect S: SerialNumber=0123456789ABCDEF C:* #Ifs= 6 Cfg#= 1 Atr=80 MxPwr=500mA I:* If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none) E: Ad=83(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none) E: Ad=85(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none) E: Ad=87(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) E: Ad=89(I) Atr=03(Int.) MxPS= 8 Ivl=32ms E: Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 5 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=(none) E: Ad=8a(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=06(O) Atr=02(Bulk) MxPS= 512 Ivl=125us

Cc: stable@vger.kernel.org Signed-off-by: Bjørn Mork bjorn@mork.no [ johan: use tabs to align comments in adjacent lines ] Signed-off-by: Johan Hovold johan@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/usb/serial/option.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)

--- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1947,10 +1947,12 @@ static const struct usb_device_id option .driver_info = RSVD(4) }, { USB_DEVICE_INTERFACE_CLASS(0x2001, 0x7e35, 0xff), /* D-Link DWM-222 */ .driver_info = RSVD(4) }, - { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e01, 0xff, 0xff, 0xff) }, /* D-Link DWM-152/C1 */ - { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e02, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/C1 */ - { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x7e11, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/A3 */ - { USB_DEVICE_INTERFACE_CLASS(0x2020, 0x4000, 0xff) }, /* OLICARD300 - MT6225 */ + { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e01, 0xff, 0xff, 0xff) }, /* D-Link DWM-152/C1 */ + { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e02, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/C1 */ + { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x7e11, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/A3 */ + { USB_DEVICE_INTERFACE_CLASS(0x2020, 0x2031, 0xff), /* Olicard 600 */ + .driver_info = RSVD(4) }, + { USB_DEVICE_INTERFACE_CLASS(0x2020, 0x4000, 0xff) }, /* OLICARD300 - MT6225 */ { USB_DEVICE(INOVIA_VENDOR_ID, INOVIA_SEW858) }, { USB_DEVICE(VIATELECOM_VENDOR_ID, VIATELECOM_PRODUCT_CDS7) }, { USB_DEVICE_AND_INTERFACE_INFO(WETELECOM_VENDOR_ID, WETELECOM_PRODUCT_WMD200, 0xff, 0xff, 0xff) },

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

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

From: YueHaibing yuehaibing@huawei.com

commit 23da9588037ecdd4901db76a5b79a42b529c4ec3 upstream.

Syzkaller reports:

kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP KASAN PTI CPU: 1 PID: 5373 Comm: syz-executor.0 Not tainted 5.0.0-rc8+ #3 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014 RIP: 0010:put_links+0x101/0x440 fs/proc/proc_sysctl.c:1599 Code: 00 0f 85 3a 03 00 00 48 8b 43 38 48 89 44 24 20 48 83 c0 38 48 89 c2 48 89 44 24 28 48 b8 00 00 00 00 00 fc ff df 48 c1 ea 03 <80> 3c 02 00 0f 85 fe 02 00 00 48 8b 74 24 20 48 c7 c7 60 2a 9d 91 RSP: 0018:ffff8881d828f238 EFLAGS: 00010202 RAX: dffffc0000000000 RBX: ffff8881e01b1140 RCX: ffffffff8ee98267 RDX: 0000000000000007 RSI: ffffc90001479000 RDI: ffff8881e01b1178 RBP: dffffc0000000000 R08: ffffed103ee27259 R09: ffffed103ee27259 R10: 0000000000000001 R11: ffffed103ee27258 R12: fffffffffffffff4 R13: 0000000000000006 R14: ffff8881f59838c0 R15: dffffc0000000000 FS: 00007f072254f700(0000) GS:ffff8881f7100000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fff8b286668 CR3: 00000001f0542002 CR4: 00000000007606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: drop_sysctl_table+0x152/0x9f0 fs/proc/proc_sysctl.c:1629 get_subdir fs/proc/proc_sysctl.c:1022 [inline] __register_sysctl_table+0xd65/0x1090 fs/proc/proc_sysctl.c:1335 br_netfilter_init+0xbc/0x1000 [br_netfilter] do_one_initcall+0xfa/0x5ca init/main.c:887 do_init_module+0x204/0x5f6 kernel/module.c:3460 load_module+0x66b2/0x8570 kernel/module.c:3808 __do_sys_finit_module+0x238/0x2a0 kernel/module.c:3902 do_syscall_64+0x147/0x600 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x462e99 Code: f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f072254ec58 EFLAGS: 00000246 ORIG_RAX: 0000000000000139 RAX: ffffffffffffffda RBX: 000000000073bf00 RCX: 0000000000462e99 RDX: 0000000000000000 RSI: 0000000020000280 RDI: 0000000000000003 RBP: 00007f072254ec70 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f072254f6bc R13: 00000000004bcefa R14: 00000000006f6fb0 R15: 0000000000000004 Modules linked in: br_netfilter(+) dvb_usb_dibusb_mc_common dib3000mc dibx000_common dvb_usb_dibusb_common dvb_usb_dw2102 dvb_usb classmate_laptop palmas_regulator cn videobuf2_v4l2 v4l2_common snd_soc_bd28623 mptbase snd_usb_usx2y snd_usbmidi_lib snd_rawmidi wmi libnvdimm lockd sunrpc grace rc_kworld_pc150u rc_core rtc_da9063 sha1_ssse3 i2c_cros_ec_tunnel adxl34x_spi adxl34x nfnetlink lib80211 i5500_temp dvb_as102 dvb_core videobuf2_common videodev media videobuf2_vmalloc videobuf2_memops udc_core lnbp22 leds_lp3952 hid_roccat_ryos s1d13xxxfb mtd vport_geneve openvswitch nf_conncount nf_nat_ipv6 nsh geneve udp_tunnel ip6_udp_tunnel snd_soc_mt6351 sis_agp phylink snd_soc_adau1761_spi snd_soc_adau1761 snd_soc_adau17x1 snd_soc_core snd_pcm_dmaengine ac97_bus snd_compress snd_soc_adau_utils snd_soc_sigmadsp_regmap snd_soc_sigmadsp raid_class hid_roccat_konepure hid_roccat_common hid_roccat c2port_duramar2150 core mdio_bcm_unimac iptable_security iptable_raw iptable_mangle iptable_nat nf_nat_ipv4 nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 iptable_filter bpfilter ip6_vti ip_vti ip_gre ipip sit tunnel4 ip_tunnel hsr veth netdevsim devlink vxcan batman_adv cfg80211 rfkill chnl_net caif nlmon dummy team bonding vcan bridge stp llc ip6_gre gre ip6_tunnel tunnel6 tun crct10dif_pclmul crc32_pclmul crc32c_intel ghash_clmulni_intel joydev mousedev ide_pci_generic piix aesni_intel aes_x86_64 ide_core crypto_simd atkbd cryptd glue_helper serio_raw ata_generic pata_acpi i2c_piix4 floppy sch_fq_codel ip_tables x_tables ipv6 [last unloaded: lm73] Dumping ftrace buffer: (ftrace buffer empty) ---[ end trace 770020de38961fd0 ]---

A new dir entry can be created in get_subdir and its 'header->parent' is set to NULL. Only after insert_header success, it will be set to 'dir', otherwise 'header->parent' is set to NULL and drop_sysctl_table is called. However in err handling path of get_subdir, drop_sysctl_table also be called on 'new->header' regardless its value of parent pointer. Then put_links is called, which triggers NULL-ptr deref when access member of header->parent.

In fact we have multiple error paths which call drop_sysctl_table() there, upon failure on insert_links() we also call drop_sysctl_table().And even in the successful case on __register_sysctl_table() we still always call drop_sysctl_table().This patch fix it.

Link: http://lkml.kernel.org/r/20190314085527.13244-1-yuehaibing@huawei.com Fixes: 0e47c99d7fe25 ("sysctl: Replace root_list with links between sysctl_table_sets") Signed-off-by: YueHaibing yuehaibing@huawei.com Reported-by: Hulk Robot hulkci@huawei.com Acked-by: Luis Chamberlain mcgrof@kernel.org Cc: Kees Cook keescook@chromium.org Cc: Alexey Dobriyan adobriyan@gmail.com Cc: Alexei Starovoitov ast@kernel.org Cc: Daniel Borkmann daniel@iogearbox.net Cc: Al Viro viro@zeniv.linux.org.uk Cc: Eric W. Biederman ebiederm@xmission.com Cc: stable@vger.kernel.org [3.4+] Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

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

--- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -1620,7 +1620,8 @@ static void drop_sysctl_table(struct ctl if (--header->nreg) return;

- put_links(header); + if (parent) + put_links(header); start_unregistering(header); if (!--header->count) kfree_rcu(header, rcu);

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

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

From: Kangjie Lu kjlu@umn.edu

commit 7ecced0934e574b528a1ba6c237731e682216a74 upstream.

ida_simple_get may fail and return a negative error number. The fix checks its return value; if it fails, go to err_destroy.

Cc: stable@vger.kernel.org Signed-off-by: Kangjie Lu kjlu@umn.edu Signed-off-by: Bartosz Golaszewski bgolaszewski@baylibre.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

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

--- a/drivers/gpio/gpio-exar.c +++ b/drivers/gpio/gpio-exar.c @@ -148,6 +148,8 @@ static int gpio_exar_probe(struct platfo mutex_init(&exar_gpio->lock);

index = ida_simple_get(&ida_index, 0, 0, GFP_KERNEL); + if (index < 0) + goto err_destroy;

sprintf(exar_gpio->name, "exar_gpio%d", index); exar_gpio->gpio_chip.label = exar_gpio->name;

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

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

From: Chen-Yu Tsai wens@csie.org

commit 1396929e8a903db80425343cacca766a18ad6409 upstream.

While only the first PHY supports mode switching, the remaining PHYs work in USB host mode. They should support set_mode with mode=USB_HOST instead of failing. This is especially needed now that the USB core does set_mode for all USB ports, which was added in commit b97a31348379 ("usb: core: comply to PHY framework").

Make set_mode with mode=USB_HOST a no-op instead of failing for the non-OTG USB PHYs.

Fixes: 6ba43c291961 ("phy-sun4i-usb: Add support for phy_set_mode") Signed-off-by: Chen-Yu Tsai wens@csie.org Cc: stable stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/phy/allwinner/phy-sun4i-usb.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

--- a/drivers/phy/allwinner/phy-sun4i-usb.c +++ b/drivers/phy/allwinner/phy-sun4i-usb.c @@ -480,8 +480,11 @@ static int sun4i_usb_phy_set_mode(struct struct sun4i_usb_phy_data *data = to_sun4i_usb_phy_data(phy); int new_mode;

- if (phy->index != 0) + if (phy->index != 0) { + if (mode == PHY_MODE_USB_HOST) + return 0; return -EINVAL; + }

switch (mode) { case PHY_MODE_USB_HOST:

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

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

From: Radoslav Gerganov rgerganov@vmware.com

commit 072684e8c58d17e853f8e8b9f6d9ce2e58d2b036 upstream.

In f_hidg_write() the write_spinlock is acquired before calling usb_ep_queue() which causes a deadlock when dummy_hcd is being used. This is because dummy_queue() callbacks into f_hidg_req_complete() which tries to acquire the same spinlock. This is (part of) the backtrace when the deadlock occurs:

0xffffffffc06b1410 in f_hidg_req_complete 0xffffffffc06a590a in usb_gadget_giveback_request 0xffffffffc06cfff2 in dummy_queue 0xffffffffc06a4b96 in usb_ep_queue 0xffffffffc06b1eb6 in f_hidg_write 0xffffffff8127730b in __vfs_write 0xffffffff812774d1 in vfs_write 0xffffffff81277725 in SYSC_write

Fix this by releasing the write_spinlock before calling usb_ep_queue()

Reviewed-by: James Bottomley James.Bottomley@HansenPartnership.com Tested-by: James Bottomley James.Bottomley@HansenPartnership.com Cc: stable@vger.kernel.org # 4.11+ Fixes: 749494b6bdbb ("usb: gadget: f_hid: fix: Move IN request allocation to set_alt()") Signed-off-by: Radoslav Gerganov rgerganov@vmware.com Signed-off-by: Felipe Balbi felipe.balbi@linux.intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/usb/gadget/function/f_hid.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/drivers/usb/gadget/function/f_hid.c +++ b/drivers/usb/gadget/function/f_hid.c @@ -395,20 +395,20 @@ try_again: req->complete = f_hidg_req_complete; req->context = hidg;

+ spin_unlock_irqrestore(&hidg->write_spinlock, flags); + status = usb_ep_queue(hidg->in_ep, req, GFP_ATOMIC); if (status < 0) { ERROR(hidg->func.config->cdev, "usb_ep_queue error on int endpoint %zd\n", status); - goto release_write_pending_unlocked; + goto release_write_pending; } else { status = count; } - spin_unlock_irqrestore(&hidg->write_spinlock, flags);

return status; release_write_pending: spin_lock_irqsave(&hidg->write_spinlock, flags); -release_write_pending_unlocked: hidg->write_pending = 0; spin_unlock_irqrestore(&hidg->write_spinlock, flags);

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

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

From: Yasushi Asano yasano@jp.adit-jv.com

commit 40fc165304f0faaae78b761f8ee30b5d216b1850 upstream.

When plugging BUFFALO LUA4-U3-AGT USB3.0 to Gigabit Ethernet LAN Adapter, warning messages filled up dmesg.

[ 101.098287] xhci-hcd ee000000.usb: WARN Successful completion on short TX for slot 1 ep 4: needs XHCI_TRUST_TX_LENGTH quirk? [ 101.117463] xhci-hcd ee000000.usb: WARN Successful completion on short TX for slot 1 ep 4: needs XHCI_TRUST_TX_LENGTH quirk? [ 101.136513] xhci-hcd ee000000.usb: WARN Successful completion on short TX for slot 1 ep 4: needs XHCI_TRUST_TX_LENGTH quirk?

Adding the XHCI_TRUST_TX_LENGTH quirk resolves the issue.

Signed-off-by: Yasushi Asano yasano@jp.adit-jv.com Signed-off-by: Spyridon Papageorgiou spapageorgiou@de.adit-jv.com Acked-by: Yoshihiro Shimoda yoshihiro.shimoda.uh@renesas.com Cc: stable stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/usb/host/xhci-rcar.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/usb/host/xhci-rcar.c +++ b/drivers/usb/host/xhci-rcar.c @@ -236,6 +236,7 @@ int xhci_rcar_init_quirk(struct usb_hcd xhci_rcar_is_gen3(hcd->self.controller)) xhci->quirks |= XHCI_NO_64BIT_SUPPORT;

+ xhci->quirks |= XHCI_TRUST_TX_LENGTH; return xhci_rcar_download_firmware(hcd); }

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

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

From: Romain Izard romain.izard.pro@gmail.com

commit 93e1c8a638308980309e009cc40b5a57ef87caf1 upstream.

When the kernel is compiled with preemption enabled, the URB completion handler can run in parallel with the work responsible for waking up the tty layer. If the URB handler sets the EVENT_TTY_WAKEUP bit during the call to tty_port_tty_wakeup() to signal that there is room for additional input, it will be cleared at the end of this call. As a result, TX traffic on the upper layer will be blocked.

This can be seen with a kernel configured with CONFIG_PREEMPT, and a fast modem connected with PPP running over a USB CDC-ACM port.

Use test_and_clear_bit() instead, which ensures that each wakeup requested by the URB completion code will trigger a call to tty_port_tty_wakeup().

Fixes: 1aba579f3cf5 cdc-acm: handle read pipe errors Signed-off-by: Romain Izard romain.izard.pro@gmail.com Cc: stable stable@vger.kernel.org Acked-by: Oliver Neukum oneukum@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/usb/class/cdc-acm.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)

--- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -570,10 +570,8 @@ static void acm_softint(struct work_stru clear_bit(EVENT_RX_STALL, &acm->flags); }

- if (test_bit(EVENT_TTY_WAKEUP, &acm->flags)) { + if (test_and_clear_bit(EVENT_TTY_WAKEUP, &acm->flags)) tty_port_tty_wakeup(&acm->port); - clear_bit(EVENT_TTY_WAKEUP, &acm->flags); - } }

/*

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

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

From: Adrian Hunter adrian.hunter@intel.com

commit f3b4e06b3bda759afd042d3d5fa86bea8f1fe278 upstream.

A TSC packet can slip past MTC packets so that the timestamp appears to go backwards. One estimate is that can be up to about 40 CPU cycles, which is certainly less than 0x1000 TSC ticks, but accept slippage an order of magnitude more to be on the safe side.

Signed-off-by: Adrian Hunter adrian.hunter@intel.com Cc: Jiri Olsa jolsa@redhat.com Cc: stable@vger.kernel.org Fixes: 79b58424b821c ("perf tools: Add Intel PT support for decoding MTC packets") Link: http://lkml.kernel.org/r/20190325135135.18348-1-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- tools/perf/util/intel-pt-decoder/intel-pt-decoder.c | 20 ++++++++------------ 1 file changed, 8 insertions(+), 12 deletions(-)

--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -251,19 +251,15 @@ struct intel_pt_decoder *intel_pt_decode if (!(decoder->tsc_ctc_ratio_n % decoder->tsc_ctc_ratio_d)) decoder->tsc_ctc_mult = decoder->tsc_ctc_ratio_n / decoder->tsc_ctc_ratio_d; - - /* - * Allow for timestamps appearing to backwards because a TSC - * packet has slipped past a MTC packet, so allow 2 MTC ticks - * or ... - */ - decoder->tsc_slip = multdiv(2 << decoder->mtc_shift, - decoder->tsc_ctc_ratio_n, - decoder->tsc_ctc_ratio_d); } - /* ... or 0x100 paranoia */ - if (decoder->tsc_slip < 0x100) - decoder->tsc_slip = 0x100; + + /* + * A TSC packet can slip past MTC packets so that the timestamp appears + * to go backwards. One estimate is that can be up to about 40 CPU + * cycles, which is certainly less than 0x1000 TSC ticks, but accept + * slippage an order of magnitude more to be on the safe side. + */ + decoder->tsc_slip = 0x10000;

intel_pt_log("timestamp: mtc_shift %u\n", decoder->mtc_shift); intel_pt_log("timestamp: tsc_ctc_ratio_n %u\n", decoder->tsc_ctc_ratio_n);

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

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

From: Thomas Gleixner tglx@linutronix.de

commit bebd024e4815b1a170fcd21ead9c2222b23ce9e6 upstream.

The SMT disable 'nosmt' command line argument is not working properly when CONFIG_HOTPLUG_CPU is disabled. The teardown of the sibling CPUs which are required to be brought up due to the MCE issues, cannot work. The CPUs are then kept in a half dead state.

As the 'nosmt' functionality has become popular due to the speculative hardware vulnerabilities, the half torn down state is not a proper solution to the problem.

Enforce CONFIG_HOTPLUG_CPU=y when SMP is enabled so the full operation is possible.

Reported-by: Tianyu Lan Tianyu.Lan@microsoft.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Acked-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Cc: Konrad Wilk konrad.wilk@oracle.com Cc: Josh Poimboeuf jpoimboe@redhat.com Cc: Mukesh Ojha mojha@codeaurora.org Cc: Peter Zijlstra peterz@infradead.org Cc: Jiri Kosina jkosina@suse.cz Cc: Rik van Riel riel@surriel.com Cc: Andy Lutomirski luto@kernel.org Cc: Micheal Kelley michael.h.kelley@microsoft.com Cc: "K. Y. Srinivasan" kys@microsoft.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Borislav Petkov bp@alien8.de Cc: K. Y. Srinivasan kys@microsoft.com Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20190326163811.598166056@linutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/Kconfig | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-)

--- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2139,14 +2139,8 @@ config RANDOMIZE_MEMORY_PHYSICAL_PADDING If unsure, leave at the default value.

config HOTPLUG_CPU - bool "Support for hot-pluggable CPUs" + def_bool y depends on SMP - ---help--- - Say Y here to allow turning CPUs off and on. CPUs can be - controlled through /sys/devices/system/cpu. - ( Note: power management support will enable this option - automatically on SMP systems. ) - Say N if you want to disable CPU hotplug.

config BOOTPARAM_HOTPLUG_CPU0 bool "Set default setting of cpu0_hotpluggable"

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

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

From: Sean Christopherson sean.j.christopherson@intel.com

commit 0cf9135b773bf32fba9dd8e6699c1b331ee4b749 upstream.

The CPUID flag ARCH_CAPABILITIES is unconditioinally exposed to host userspace for all x86 hosts, i.e. KVM advertises ARCH_CAPABILITIES regardless of hardware support under the pretense that KVM fully emulates MSR_IA32_ARCH_CAPABILITIES. Unfortunately, only VMX hosts handle accesses to MSR_IA32_ARCH_CAPABILITIES (despite KVM_GET_MSRS also reporting MSR_IA32_ARCH_CAPABILITIES for all hosts).

Move the MSR_IA32_ARCH_CAPABILITIES handling to common x86 code so that it's emulated on AMD hosts.

Fixes: 1eaafe91a0df4 ("kvm: x86: IA32_ARCH_CAPABILITIES is always supported") Cc: stable@vger.kernel.org Reported-by: Xiaoyao Li xiaoyao.li@linux.intel.com Cc: Jim Mattson jmattson@google.com Signed-off-by: Sean Christopherson sean.j.christopherson@intel.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/vmx.c | 14 -------------- arch/x86/kvm/x86.c | 12 ++++++++++++ 3 files changed, 13 insertions(+), 14 deletions(-)

--- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -509,6 +509,7 @@ struct kvm_vcpu_arch { bool tpr_access_reporting; u64 ia32_xss; u64 microcode_version; + u64 arch_capabilities;

/* * Paging state of the vcpu --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -740,7 +740,6 @@ struct vcpu_vmx { u64 msr_guest_kernel_gs_base; #endif

- u64 arch_capabilities; u64 spec_ctrl;

u32 vm_entry_controls_shadow; @@ -3493,12 +3492,6 @@ static int vmx_get_msr(struct kvm_vcpu *

msr_info->data = to_vmx(vcpu)->spec_ctrl; break; - case MSR_IA32_ARCH_CAPABILITIES: - if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES)) - return 1; - msr_info->data = to_vmx(vcpu)->arch_capabilities; - break; case MSR_IA32_SYSENTER_CS: msr_info->data = vmcs_read32(GUEST_SYSENTER_CS); break; @@ -3663,11 +3656,6 @@ static int vmx_set_msr(struct kvm_vcpu * vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, MSR_IA32_PRED_CMD, MSR_TYPE_W); break; - case MSR_IA32_ARCH_CAPABILITIES: - if (!msr_info->host_initiated) - return 1; - vmx->arch_capabilities = data; - break; case MSR_IA32_CR_PAT: if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) { if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data)) @@ -5929,8 +5917,6 @@ static int vmx_vcpu_setup(struct vcpu_vm ++vmx->nmsrs; }

- vmx->arch_capabilities = kvm_get_arch_capabilities(); - vm_exit_controls_init(vmx, vmcs_config.vmexit_ctrl);

/* 22.2.1, 20.8.1 */ --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2234,6 +2234,11 @@ int kvm_set_msr_common(struct kvm_vcpu * if (msr_info->host_initiated) vcpu->arch.microcode_version = data; break; + case MSR_IA32_ARCH_CAPABILITIES: + if (!msr_info->host_initiated) + return 1; + vcpu->arch.arch_capabilities = data; + break; case MSR_EFER: return set_efer(vcpu, data); case MSR_K7_HWCR: @@ -2523,6 +2528,12 @@ int kvm_get_msr_common(struct kvm_vcpu * case MSR_IA32_UCODE_REV: msr_info->data = vcpu->arch.microcode_version; break; + case MSR_IA32_ARCH_CAPABILITIES: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES)) + return 1; + msr_info->data = vcpu->arch.arch_capabilities; + break; case MSR_MTRRcap: case 0x200 ... 0x2ff: return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data); @@ -7918,6 +7929,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu { int r;

+ vcpu->arch.arch_capabilities = kvm_get_arch_capabilities(); kvm_vcpu_mtrr_init(vcpu); r = vcpu_load(vcpu); if (r)

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

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

From: Cornelia Huck cohuck@redhat.com

commit 50b7f1b7236bab08ebbbecf90521e84b068d7a17 upstream.

When we get an interrupt for a channel program, it is not necessarily the final interrupt; for example, the issuing guest may request an intermediate interrupt by specifying the program-controlled-interrupt flag on a ccw.

We must not switch the state to idle if the interrupt is not yet final; even more importantly, we must not free the translated channel program if the interrupt is not yet final, or the host can crash during cp rewind.

Fixes: e5f84dbaea59 ("vfio: ccw: return I/O results asynchronously") Cc: stable@vger.kernel.org # v4.12+ Reviewed-by: Eric Farman farman@linux.ibm.com Signed-off-by: Cornelia Huck cohuck@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/s390/cio/vfio_ccw_drv.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

--- a/drivers/s390/cio/vfio_ccw_drv.c +++ b/drivers/s390/cio/vfio_ccw_drv.c @@ -70,20 +70,24 @@ static void vfio_ccw_sch_io_todo(struct { struct vfio_ccw_private *private; struct irb *irb; + bool is_final;

private = container_of(work, struct vfio_ccw_private, io_work); irb = &private->irb;

+ is_final = !(scsw_actl(&irb->scsw) & + (SCSW_ACTL_DEVACT | SCSW_ACTL_SCHACT)); if (scsw_is_solicited(&irb->scsw)) { cp_update_scsw(&private->cp, &irb->scsw); - cp_free(&private->cp); + if (is_final) + cp_free(&private->cp); } memcpy(private->io_region.irb_area, irb, sizeof(*irb));

if (private->io_trigger) eventfd_signal(private->io_trigger, 1);

- if (private->mdev) + if (private->mdev && is_final) private->state = VFIO_CCW_STATE_IDLE; }