[ Upstream commit 5fe3c0fa0d54877c65e7c9b4442aeeb25cdf469a ]

Since I2C1 and I2C4 have explicit pinmuxing set, let's be on the safe side and set the pin muxing for I2C2 and I2C3.

Signed-off-by: Adam Ford aford173@gmail.com Signed-off-by: Tony Lindgren tony@atomide.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/boot/dts/logicpd-som-lv.dtsi | 16 ++++++++++++++++ 1 file changed, 16 insertions(+)

diff --git a/arch/arm/boot/dts/logicpd-som-lv.dtsi b/arch/arm/boot/dts/logicpd-som-lv.dtsi index 876ed5f2922c4..43035cb71cbee 100644 --- a/arch/arm/boot/dts/logicpd-som-lv.dtsi +++ b/arch/arm/boot/dts/logicpd-som-lv.dtsi @@ -114,10 +114,14 @@ };

&i2c2 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c2_pins>; clock-frequency = <400000>; };

&i2c3 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c3_pins>; clock-frequency = <400000>; };

@@ -239,6 +243,18 @@ OMAP3_WKUP_IOPAD(0x2a0c, PIN_OUTPUT | MUX_MODE4) /* sys_boot1.gpio_3 */ >; }; + i2c2_pins: pinmux_i2c2_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x21be, PIN_INPUT | MUX_MODE0) /* i2c2_scl */ + OMAP3_CORE1_IOPAD(0x21c0, PIN_INPUT | MUX_MODE0) /* i2c2_sda */ + >; + }; + i2c3_pins: pinmux_i2c3_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x21c2, PIN_INPUT | MUX_MODE0) /* i2c3_scl */ + OMAP3_CORE1_IOPAD(0x21c4, PIN_INPUT | MUX_MODE0) /* i2c3_sda */ + >; + }; };

&omap3_pmx_core2 {

[ Upstream commit 95e59fc3c3fa3187a07a75f40b21637deb4bd12d ]

The Audio has worked, but the mute pin has a weak pulldown which alows some of the audio signal to pass very quietly. This patch fixes that so the mute pin is actively driven high for mute or low for normal operation.

Fixes: ab8dd3aed011 ("ARM: DTS: Add minimal Support for Logic PD DM3730 SOM-LV")

Signed-off-by: Adam Ford aford173@gmail.com Signed-off-by: Tony Lindgren tony@atomide.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/boot/dts/logicpd-som-lv.dtsi | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/arch/arm/boot/dts/logicpd-som-lv.dtsi b/arch/arm/boot/dts/logicpd-som-lv.dtsi index 43035cb71cbee..f82f193b88569 100644 --- a/arch/arm/boot/dts/logicpd-som-lv.dtsi +++ b/arch/arm/boot/dts/logicpd-som-lv.dtsi @@ -108,6 +108,7 @@ twl_audio: audio { compatible = "ti,twl4030-audio"; codec { + ti,hs_extmute_gpio = <&gpio2 25 GPIO_ACTIVE_HIGH>; }; }; }; @@ -225,6 +226,7 @@ pinctrl-single,pins = < OMAP3_CORE1_IOPAD(0x21ba, PIN_INPUT | MUX_MODE0) /* i2c1_scl.i2c1_scl */ OMAP3_CORE1_IOPAD(0x21bc, PIN_INPUT | MUX_MODE0) /* i2c1_sda.i2c1_sda */ + OMAP3_CORE1_IOPAD(0x20ba, PIN_OUTPUT | MUX_MODE4) /* gpmc_ncs6.gpio_57 */ >; }; };

commit 147b9635e6347104b91f48ca9dca61eb0fbf2a54 upstream.

If CTR_EL0.{CWG,ERG} are 0b0000 then they must be interpreted to have their architecturally maximum values, which defeats the use of FTR_HIGHER_SAFE when sanitising CPU ID registers on heterogeneous machines.

Introduce FTR_HIGHER_OR_ZERO_SAFE so that these fields effectively saturate at zero.

Fixes: 3c739b571084 ("arm64: Keep track of CPU feature registers") Cc: stable@vger.kernel.org # 4.9.y only Reviewed-by: Suzuki K Poulose suzuki.poulose@arm.com Acked-by: Mark Rutland mark.rutland@arm.com Signed-off-by: Will Deacon will@kernel.org Signed-off-by: Catalin Marinas catalin.marinas@arm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/include/asm/cpufeature.h | 7 ++++--- arch/arm64/kernel/cpufeature.c | 8 ++++++-- 2 files changed, 10 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 15868eca58de0..e7bef3d936d87 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -31,9 +31,10 @@

/* CPU feature register tracking */ enum ftr_type { - FTR_EXACT, /* Use a predefined safe value */ - FTR_LOWER_SAFE, /* Smaller value is safe */ - FTR_HIGHER_SAFE,/* Bigger value is safe */ + FTR_EXACT, /* Use a predefined safe value */ + FTR_LOWER_SAFE, /* Smaller value is safe */ + FTR_HIGHER_SAFE, /* Bigger value is safe */ + FTR_HIGHER_OR_ZERO_SAFE, /* Bigger value is safe, but 0 is biggest */ };

#define FTR_STRICT true /* SANITY check strict matching required */ diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index e2ac72b7e89ca..9a8e45dc36bd0 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -152,8 +152,8 @@ static const struct arm64_ftr_bits ftr_ctr[] = { ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 30, 1, 0), ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 29, 1, 1), /* DIC */ ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 28, 1, 1), /* IDC */ - ARM64_FTR_BITS(FTR_STRICT, FTR_HIGHER_SAFE, 24, 4, 0), /* CWG */ - ARM64_FTR_BITS(FTR_STRICT, FTR_HIGHER_SAFE, 20, 4, 0), /* ERG */ + ARM64_FTR_BITS(FTR_STRICT, FTR_HIGHER_OR_ZERO_SAFE, 24, 4, 0), /* CWG */ + ARM64_FTR_BITS(FTR_STRICT, FTR_HIGHER_OR_ZERO_SAFE, 20, 4, 0), /* ERG */ ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, CTR_DMINLINE_SHIFT, 4, 1), /* * Linux can handle differing I-cache policies. Userspace JITs will @@ -392,6 +392,10 @@ static s64 arm64_ftr_safe_value(const struct arm64_ftr_bits *ftrp, s64 new, case FTR_LOWER_SAFE: ret = new < cur ? new : cur; break; + case FTR_HIGHER_OR_ZERO_SAFE: + if (!cur || !new) + break; + /* Fallthrough */ case FTR_HIGHER_SAFE: ret = new > cur ? new : cur; break;

From: Aaron Armstrong Skomra skomra@gmail.com

commit 693c3dab4e50403f91bca4b52fc6d8562a3180f6 upstream.

The bit indicating BTN_6 on this device is overshifted by 2 bits, resulting in the incorrect button being reported.

Also fix copy-paste mistake in comments.

Signed-off-by: Aaron Armstrong Skomra aaron.skomra@wacom.com Reviewed-by: Ping Cheng ping.cheng@wacom.com Link: https://github.com/linuxwacom/xf86-input-wacom/issues/71 Fixes: c7f0522a1ad1 ("HID: wacom: Slim down wacom_intuos_pad processing") Cc: stable@vger.kernel.org # v4.5+ Signed-off-by: Jiri Kosina jkosina@suse.cz Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/hid/wacom_wac.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-)

--- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -529,14 +529,14 @@ static int wacom_intuos_pad(struct wacom */ buttons = (data[4] << 1) | (data[3] & 0x01); } else if (features->type == CINTIQ_COMPANION_2) { - /* d-pad right -> data[4] & 0x10 - * d-pad up -> data[4] & 0x20 - * d-pad left -> data[4] & 0x40 - * d-pad down -> data[4] & 0x80 - * d-pad center -> data[3] & 0x01 + /* d-pad right -> data[2] & 0x10 + * d-pad up -> data[2] & 0x20 + * d-pad left -> data[2] & 0x40 + * d-pad down -> data[2] & 0x80 + * d-pad center -> data[1] & 0x01 */ buttons = ((data[2] >> 4) << 7) | - ((data[1] & 0x04) << 6) | + ((data[1] & 0x04) << 4) | ((data[2] & 0x0F) << 2) | (data[1] & 0x03); } else if (features->type >= INTUOS5S && features->type <= INTUOSPL) {

From: Jason Gunthorpe jgg@mellanox.com

commit 641114d2af312d39ca9bbc2369d18a5823da51c6 upstream.

gcc 9 now does allocation size tracking and thinks that passing the member of a union and then accessing beyond that member's bounds is an overflow.

Instead of using the union member, use the entire union with a cast to get to the sockaddr. gcc will now know that the memory extends the full size of the union.

Signed-off-by: Jason Gunthorpe jgg@mellanox.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/infiniband/core/addr.c | 15 +++++++-------- drivers/infiniband/hw/ocrdma/ocrdma_ah.c | 5 ++--- drivers/infiniband/hw/ocrdma/ocrdma_hw.c | 5 ++--- 3 files changed, 11 insertions(+), 14 deletions(-)

--- a/drivers/infiniband/core/addr.c +++ b/drivers/infiniband/core/addr.c @@ -735,14 +735,13 @@ int rdma_addr_find_l2_eth_by_grh(const u struct net_device *dev;

union { - struct sockaddr _sockaddr; struct sockaddr_in _sockaddr_in; struct sockaddr_in6 _sockaddr_in6; } sgid_addr, dgid_addr;

- rdma_gid2ip(&sgid_addr._sockaddr, sgid); - rdma_gid2ip(&dgid_addr._sockaddr, dgid); + rdma_gid2ip((struct sockaddr *)&sgid_addr, sgid); + rdma_gid2ip((struct sockaddr *)&dgid_addr, dgid);

memset(&dev_addr, 0, sizeof(dev_addr)); if (if_index) @@ -751,8 +750,9 @@ int rdma_addr_find_l2_eth_by_grh(const u

ctx.addr = &dev_addr; init_completion(&ctx.comp); - ret = rdma_resolve_ip(&self, &sgid_addr._sockaddr, &dgid_addr._sockaddr, - &dev_addr, 1000, resolve_cb, &ctx); + ret = rdma_resolve_ip(&self, (struct sockaddr *)&sgid_addr, + (struct sockaddr *)&dgid_addr, &dev_addr, 1000, + resolve_cb, &ctx); if (ret) return ret;

@@ -782,16 +782,15 @@ int rdma_addr_find_smac_by_sgid(union ib int ret = 0; struct rdma_dev_addr dev_addr; union { - struct sockaddr _sockaddr; struct sockaddr_in _sockaddr_in; struct sockaddr_in6 _sockaddr_in6; } gid_addr;

- rdma_gid2ip(&gid_addr._sockaddr, sgid); + rdma_gid2ip((struct sockaddr *)&gid_addr, sgid);

memset(&dev_addr, 0, sizeof(dev_addr)); dev_addr.net = &init_net; - ret = rdma_translate_ip(&gid_addr._sockaddr, &dev_addr, vlan_id); + ret = rdma_translate_ip((struct sockaddr *)&gid_addr, &dev_addr, vlan_id); if (ret) return ret;

--- a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c @@ -82,7 +82,6 @@ static inline int set_av_attr(struct ocr u8 nxthdr = 0x11; struct iphdr ipv4; union { - struct sockaddr _sockaddr; struct sockaddr_in _sockaddr_in; struct sockaddr_in6 _sockaddr_in6; } sgid_addr, dgid_addr; @@ -131,9 +130,9 @@ static inline int set_av_attr(struct ocr ipv4.tot_len = htons(0); ipv4.ttl = attr->grh.hop_limit; ipv4.protocol = nxthdr; - rdma_gid2ip(&sgid_addr._sockaddr, sgid); + rdma_gid2ip((struct sockaddr *)&sgid_addr, sgid); ipv4.saddr = sgid_addr._sockaddr_in.sin_addr.s_addr; - rdma_gid2ip(&dgid_addr._sockaddr, &attr->grh.dgid); + rdma_gid2ip((struct sockaddr *)&dgid_addr, &attr->grh.dgid); ipv4.daddr = dgid_addr._sockaddr_in.sin_addr.s_addr; memcpy((u8 *)ah->av + eth_sz, &ipv4, sizeof(struct iphdr)); } else { --- a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c @@ -2505,7 +2505,6 @@ static int ocrdma_set_av_params(struct o u32 vlan_id = 0xFFFF; u8 mac_addr[6], hdr_type; union { - struct sockaddr _sockaddr; struct sockaddr_in _sockaddr_in; struct sockaddr_in6 _sockaddr_in6; } sgid_addr, dgid_addr; @@ -2550,8 +2549,8 @@ static int ocrdma_set_av_params(struct o

hdr_type = ib_gid_to_network_type(sgid_attr.gid_type, &sgid); if (hdr_type == RDMA_NETWORK_IPV4) { - rdma_gid2ip(&sgid_addr._sockaddr, &sgid); - rdma_gid2ip(&dgid_addr._sockaddr, &ah_attr->grh.dgid); + rdma_gid2ip((struct sockaddr *)&sgid_addr, &sgid); + rdma_gid2ip((struct sockaddr *)&dgid_addr, &ah_attr->grh.dgid); memcpy(&cmd->params.dgid[0], &dgid_addr._sockaddr_in.sin_addr.s_addr, 4); memcpy(&cmd->params.sgid[0],

From: Josh Poimboeuf jpoimboe@redhat.com

commit 684fb246578b9e81fc7b4ca5c71eae22edb650b2 upstream.

machine_real_restart() is annotated as '__noreturn", so add it to the objtool noreturn list. This fixes the following warning with clang and CONFIG_CC_OPTIMIZE_FOR_SIZE=y:

arch/x86/kernel/reboot.o: warning: objtool: native_machine_emergency_restart() falls through to next function machine_power_off()

Reported-by: Matthias Kaehlcke mka@chromium.org Signed-off-by: Josh Poimboeuf jpoimboe@redhat.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Tested-by: Matthias Kaehlcke mka@chromium.org Reviewed-by: Matthias Kaehlcke mka@chromium.org Link: https://lkml.kernel.org/r/791712792aa4431bdd55bf1beb33a169ddf3b4a2.152942325... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- tools/objtool/check.c | 1 + 1 file changed, 1 insertion(+)

--- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -165,6 +165,7 @@ static int __dead_end_function(struct ob "__reiserfs_panic", "lbug_with_loc", "fortify_panic", + "machine_real_restart", };

if (func->bind == STB_WEAK)

From: Ilya Dryomov idryomov@gmail.com

commit 6f4dbd149d2a151b89d1a5bbf7530ee5546c7908 upstream.

Signed-off-by: Ilya Dryomov idryomov@gmail.com Reviewed-by: Alex Elder elder@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- include/linux/ceph/ceph_debug.h | 6 +++--- net/ceph/ceph_common.c | 13 ------------- 2 files changed, 3 insertions(+), 16 deletions(-)

--- a/include/linux/ceph/ceph_debug.h +++ b/include/linux/ceph/ceph_debug.h @@ -3,6 +3,8 @@

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

+#include <linux/string.h> + #ifdef CONFIG_CEPH_LIB_PRETTYDEBUG

/* @@ -12,12 +14,10 @@ */

# if defined(DEBUG) || defined(CONFIG_DYNAMIC_DEBUG) -extern const char *ceph_file_part(const char *s, int len); # define dout(fmt, ...) \ pr_debug("%.*s %12.12s:%-4d : " fmt, \ 8 - (int)sizeof(KBUILD_MODNAME), " ", \ - ceph_file_part(__FILE__, sizeof(__FILE__)), \ - __LINE__, ##__VA_ARGS__) + kbasename(__FILE__), __LINE__, ##__VA_ARGS__) # else /* faux printk call just to see any compiler warnings. */ # define dout(fmt, ...) do { \ --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -45,19 +45,6 @@ bool libceph_compatible(void *data) } EXPORT_SYMBOL(libceph_compatible);

-/* - * find filename portion of a path (/foo/bar/baz -> baz) - */ -const char *ceph_file_part(const char *s, int len) -{ - const char *e = s + len; - - while (e != s && *(e-1) != '/') - e--; - return e; -} -EXPORT_SYMBOL(ceph_file_part); - const char *ceph_msg_type_name(int type) { switch (type) {

From: Nikolay Aleksandrov nikolay@cumulusnetworks.com

[ Upstream commit d7bae09fa008c6c9a489580db0a5a12063b97f97 ]

On initialization failure we have to delete the local fdb which was inserted due to the default pvid creation. This problem has been present since the inception of default_pvid. Note that currently there are 2 cases: 1) in br_dev_init() when br_multicast_init() fails 2) if register_netdevice() fails after calling ndo_init()

This patch takes care of both since br_vlan_flush() is called on both occasions. Also the new fdb delete would be a no-op on normal bridge device destruction since the local fdb would've been already flushed by br_dev_delete(). This is not an issue for ports since nbp_vlan_init() is called last when adding a port thus nothing can fail after it.

Reported-by: syzbot+88533dc8b582309bf3ee@syzkaller.appspotmail.com Fixes: 5be5a2df40f0 ("bridge: Add filtering support for default_pvid") Signed-off-by: Nikolay Aleksandrov nikolay@cumulusnetworks.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/bridge/br_vlan.c | 5 +++++ 1 file changed, 5 insertions(+)

--- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -622,6 +622,11 @@ void br_vlan_flush(struct net_bridge *br

ASSERT_RTNL();

+ /* delete auto-added default pvid local fdb before flushing vlans + * otherwise it will be leaked on bridge device init failure + */ + br_fdb_delete_by_port(br, NULL, 0, 1); + vg = br_vlan_group(br); __vlan_flush(vg); RCU_INIT_POINTER(br->vlgrp, NULL);

From: Jiri Pirko jiri@mellanox.com

[ Upstream commit 55b40dbf0e76b4bfb9d8b3a16a0208640a9a45df ]

Commit aca51397d014 ("netns: Fix arbitrary net_device-s corruptions on net_ns stop.") introduced a possibility to hit a BUG in case device is returning back to init_net and two following conditions are met: 1) dev->ifindex value is used in a name of another "dev%d" device in init_net. 2) dev->name is used by another device in init_net.

Under real life circumstances this is hard to get. Therefore this has been present happily for over 10 years. To reproduce:

$ ip a 1: lo: <LOOPBACK,UP,LOWER_UP> mtu 65536 qdisc noqueue state UNKNOWN group default qlen 1000 link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00 inet 127.0.0.1/8 scope host lo valid_lft forever preferred_lft forever inet6 ::1/128 scope host valid_lft forever preferred_lft forever 2: dummy0: <BROADCAST,NOARP> mtu 1500 qdisc noop state DOWN group default qlen 1000 link/ether 86:89:3f:86:61:29 brd ff:ff:ff:ff:ff:ff 3: enp0s2: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN group default qlen 1000 link/ether 52:54:00:12:34:56 brd ff:ff:ff:ff:ff:ff $ ip netns add ns1 $ ip -n ns1 link add dummy1ns1 type dummy $ ip -n ns1 link add dummy2ns1 type dummy $ ip link set enp0s2 netns ns1 $ ip -n ns1 link set enp0s2 name dummy0 [ 100.858894] virtio_net virtio0 dummy0: renamed from enp0s2 $ ip link add dev4 type dummy $ ip -n ns1 a 1: lo: <LOOPBACK> mtu 65536 qdisc noop state DOWN group default qlen 1000 link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00 2: dummy1ns1: <BROADCAST,NOARP> mtu 1500 qdisc noop state DOWN group default qlen 1000 link/ether 16:63:4c:38:3e:ff brd ff:ff:ff:ff:ff:ff 3: dummy2ns1: <BROADCAST,NOARP> mtu 1500 qdisc noop state DOWN group default qlen 1000 link/ether aa:9e:86:dd:6b:5d brd ff:ff:ff:ff:ff:ff 4: dummy0: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN group default qlen 1000 link/ether 52:54:00:12:34:56 brd ff:ff:ff:ff:ff:ff $ ip a 1: lo: <LOOPBACK,UP,LOWER_UP> mtu 65536 qdisc noqueue state UNKNOWN group default qlen 1000 link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00 inet 127.0.0.1/8 scope host lo valid_lft forever preferred_lft forever inet6 ::1/128 scope host valid_lft forever preferred_lft forever 2: dummy0: <BROADCAST,NOARP> mtu 1500 qdisc noop state DOWN group default qlen 1000 link/ether 86:89:3f:86:61:29 brd ff:ff:ff:ff:ff:ff 4: dev4: <BROADCAST,NOARP> mtu 1500 qdisc noop state DOWN group default qlen 1000 link/ether 5a:e1:4a:b6:ec:f8 brd ff:ff:ff:ff:ff:ff $ ip netns del ns1 [ 158.717795] default_device_exit: failed to move dummy0 to init_net: -17 [ 158.719316] ------------[ cut here ]------------ [ 158.720591] kernel BUG at net/core/dev.c:9824! [ 158.722260] invalid opcode: 0000 [#1] SMP KASAN PTI [ 158.723728] CPU: 0 PID: 56 Comm: kworker/u2:1 Not tainted 5.3.0-rc1+ #18 [ 158.725422] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-2.fc30 04/01/2014 [ 158.727508] Workqueue: netns cleanup_net [ 158.728915] RIP: 0010:default_device_exit.cold+0x1d/0x1f [ 158.730683] Code: 84 e8 18 c9 3e fe 0f 0b e9 70 90 ff ff e8 36 e4 52 fe 89 d9 4c 89 e2 48 c7 c6 80 d6 25 84 48 c7 c7 20 c0 25 84 e8 f4 c8 3e [ 158.736854] RSP: 0018:ffff8880347e7b90 EFLAGS: 00010282 [ 158.738752] RAX: 000000000000003b RBX: 00000000ffffffef RCX: 0000000000000000 [ 158.741369] RDX: 0000000000000000 RSI: ffffffff8128013d RDI: ffffed10068fcf64 [ 158.743418] RBP: ffff888033550170 R08: 000000000000003b R09: fffffbfff0b94b9c [ 158.745626] R10: fffffbfff0b94b9b R11: ffffffff85ca5cdf R12: ffff888032f28000 [ 158.748405] R13: dffffc0000000000 R14: ffff8880335501b8 R15: 1ffff110068fcf72 [ 158.750638] FS: 0000000000000000(0000) GS:ffff888036000000(0000) knlGS:0000000000000000 [ 158.752944] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 158.755245] CR2: 00007fe8b45d21d0 CR3: 00000000340b4005 CR4: 0000000000360ef0 [ 158.757654] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 158.760012] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 158.762758] Call Trace: [ 158.763882] ? dev_change_net_namespace+0xbb0/0xbb0 [ 158.766148] ? devlink_nl_cmd_set_doit+0x520/0x520 [ 158.768034] ? dev_change_net_namespace+0xbb0/0xbb0 [ 158.769870] ops_exit_list.isra.0+0xa8/0x150 [ 158.771544] cleanup_net+0x446/0x8f0 [ 158.772945] ? unregister_pernet_operations+0x4a0/0x4a0 [ 158.775294] process_one_work+0xa1a/0x1740 [ 158.776896] ? pwq_dec_nr_in_flight+0x310/0x310 [ 158.779143] ? do_raw_spin_lock+0x11b/0x280 [ 158.780848] worker_thread+0x9e/0x1060 [ 158.782500] ? process_one_work+0x1740/0x1740 [ 158.784454] kthread+0x31b/0x420 [ 158.786082] ? __kthread_create_on_node+0x3f0/0x3f0 [ 158.788286] ret_from_fork+0x3a/0x50 [ 158.789871] ---[ end trace defd6c657c71f936 ]--- [ 158.792273] RIP: 0010:default_device_exit.cold+0x1d/0x1f [ 158.795478] Code: 84 e8 18 c9 3e fe 0f 0b e9 70 90 ff ff e8 36 e4 52 fe 89 d9 4c 89 e2 48 c7 c6 80 d6 25 84 48 c7 c7 20 c0 25 84 e8 f4 c8 3e [ 158.804854] RSP: 0018:ffff8880347e7b90 EFLAGS: 00010282 [ 158.807865] RAX: 000000000000003b RBX: 00000000ffffffef RCX: 0000000000000000 [ 158.811794] RDX: 0000000000000000 RSI: ffffffff8128013d RDI: ffffed10068fcf64 [ 158.816652] RBP: ffff888033550170 R08: 000000000000003b R09: fffffbfff0b94b9c [ 158.820930] R10: fffffbfff0b94b9b R11: ffffffff85ca5cdf R12: ffff888032f28000 [ 158.825113] R13: dffffc0000000000 R14: ffff8880335501b8 R15: 1ffff110068fcf72 [ 158.829899] FS: 0000000000000000(0000) GS:ffff888036000000(0000) knlGS:0000000000000000 [ 158.834923] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 158.838164] CR2: 00007fe8b45d21d0 CR3: 00000000340b4005 CR4: 0000000000360ef0 [ 158.841917] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 158.845149] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400

Fix this by checking if a device with the same name exists in init_net and fallback to original code - dev%d to allocate name - in case it does.

This was found using syzkaller.

Fixes: aca51397d014 ("netns: Fix arbitrary net_device-s corruptions on net_ns stop.") Signed-off-by: Jiri Pirko jiri@mellanox.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/core/dev.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/net/core/dev.c +++ b/net/core/dev.c @@ -8296,6 +8296,8 @@ static void __net_exit default_device_ex

/* Push remaining network devices to init_net */ snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex); + if (__dev_get_by_name(&init_net, fb_name)) + snprintf(fb_name, IFNAMSIZ, "dev%%d"); err = dev_change_net_namespace(dev, &init_net, fb_name); if (err) { pr_emerg("%s: failed to move %s to init_net: %d\n",

From: Jia-Ju Bai baijiaju1990@gmail.com

[ Upstream commit 051c7b39be4a91f6b7d8c4548444e4b850f1f56c ]

In dequeue_func(), there is an if statement on line 74 to check whether skb is NULL: if (skb)

When skb is NULL, it is used on line 77: prefetch(&skb->end);

Thus, a possible null-pointer dereference may occur.

To fix this bug, skb->end is used when skb is not NULL.

This bug is found by a static analysis tool STCheck written by us.

Fixes: 76e3cc126bb2 ("codel: Controlled Delay AQM") Signed-off-by: Jia-Ju Bai baijiaju1990@gmail.com Reviewed-by: Jiri Pirko jiri@mellanox.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/sched/sch_codel.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/net/sched/sch_codel.c +++ b/net/sched/sch_codel.c @@ -71,10 +71,10 @@ static struct sk_buff *dequeue_func(stru struct Qdisc *sch = ctx; struct sk_buff *skb = __qdisc_dequeue_head(&sch->q);

- if (skb) + if (skb) { sch->qstats.backlog -= qdisc_pkt_len(skb); - - prefetch(&skb->end); /* we'll need skb_shinfo() */ + prefetch(&skb->end); /* we'll need skb_shinfo() */ + } return skb; }

From: Arnd Bergmann arnd@arndb.de

[ Upstream commit 055d88242a6046a1ceac3167290f054c72571cd9 ]

Support for handling the PPPOEIOCSFWD ioctl in compat mode was added in linux-2.5.69 along with hundreds of other commands, but was always broken sincen only the structure is compatible, but the command number is not, due to the size being sizeof(size_t), or at first sizeof(sizeof((struct sockaddr_pppox)), which is different on 64-bit architectures.

Guillaume Nault adds:

And the implementation was broken until 2016 (see 29e73269aa4d ("pppoe: fix reference counting in PPPoE proxy")), and nobody ever noticed. I should probably have removed this ioctl entirely instead of fixing it. Clearly, it has never been used.

Fix it by adding a compat_ioctl handler for all pppoe variants that translates the command number and then calls the regular ioctl function.

All other ioctl commands handled by pppoe are compatible between 32-bit and 64-bit, and require compat_ptr() conversion.

This should apply to all stable kernels.

Acked-by: Guillaume Nault g.nault@alphalink.fr Signed-off-by: Arnd Bergmann arnd@arndb.de Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ppp/pppoe.c | 3 +++ drivers/net/ppp/pppox.c | 13 +++++++++++++ drivers/net/ppp/pptp.c | 3 +++ fs/compat_ioctl.c | 3 --- include/linux/if_pppox.h | 3 +++ net/l2tp/l2tp_ppp.c | 3 +++ 6 files changed, 25 insertions(+), 3 deletions(-)

--- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -1134,6 +1134,9 @@ static const struct proto_ops pppoe_ops .recvmsg = pppoe_recvmsg, .mmap = sock_no_mmap, .ioctl = pppox_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = pppox_compat_ioctl, +#endif };

static const struct pppox_proto pppoe_proto = { --- a/drivers/net/ppp/pppox.c +++ b/drivers/net/ppp/pppox.c @@ -22,6 +22,7 @@ #include <linux/string.h> #include <linux/module.h> #include <linux/kernel.h> +#include <linux/compat.h> #include <linux/errno.h> #include <linux/netdevice.h> #include <linux/net.h> @@ -103,6 +104,18 @@ int pppox_ioctl(struct socket *sock, uns

EXPORT_SYMBOL(pppox_ioctl);

+#ifdef CONFIG_COMPAT +int pppox_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) +{ + if (cmd == PPPOEIOCSFWD32) + cmd = PPPOEIOCSFWD; + + return pppox_ioctl(sock, cmd, (unsigned long)compat_ptr(arg)); +} + +EXPORT_SYMBOL(pppox_compat_ioctl); +#endif + static int pppox_create(struct net *net, struct socket *sock, int protocol, int kern) { --- a/drivers/net/ppp/pptp.c +++ b/drivers/net/ppp/pptp.c @@ -638,6 +638,9 @@ static const struct proto_ops pptp_ops = .recvmsg = sock_no_recvmsg, .mmap = sock_no_mmap, .ioctl = pppox_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = pppox_compat_ioctl, +#endif };

static const struct pppox_proto pppox_pptp_proto = { --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -1038,9 +1038,6 @@ COMPATIBLE_IOCTL(PPPIOCDISCONN) COMPATIBLE_IOCTL(PPPIOCATTCHAN) COMPATIBLE_IOCTL(PPPIOCGCHAN) COMPATIBLE_IOCTL(PPPIOCGL2TPSTATS) -/* PPPOX */ -COMPATIBLE_IOCTL(PPPOEIOCSFWD) -COMPATIBLE_IOCTL(PPPOEIOCDFWD) /* Big A */ /* sparc only */ /* Big Q for sound/OSS */ --- a/include/linux/if_pppox.h +++ b/include/linux/if_pppox.h @@ -84,6 +84,9 @@ extern int register_pppox_proto(int prot extern void unregister_pppox_proto(int proto_num); extern void pppox_unbind_sock(struct sock *sk);/* delete ppp-channel binding */ extern int pppox_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); +extern int pppox_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); + +#define PPPOEIOCSFWD32 _IOW(0xB1 ,0, compat_size_t)

/* PPPoX socket states */ enum { --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -1790,6 +1790,9 @@ static const struct proto_ops pppol2tp_o .recvmsg = pppol2tp_recvmsg, .mmap = sock_no_mmap, .ioctl = pppox_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = pppox_compat_ioctl, +#endif };

static const struct pppox_proto pppol2tp_proto = {

From: Cong Wang xiyou.wangcong@gmail.com

[ Upstream commit c8ec4632c6ac9cda0e8c3d51aa41eeab66585bd5 ]

act_ife at least requires TCA_IFE_PARMS, so we have to bail out when there is no attribute passed in.

Reported-by: syzbot+fbb5b288c9cb6a2eeac4@syzkaller.appspotmail.com Fixes: ef6980b6becb ("introduce IFE action") Cc: Jamal Hadi Salim jhs@mojatatu.com Cc: Jiri Pirko jiri@resnulli.us Signed-off-by: Cong Wang xiyou.wangcong@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/sched/act_ife.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -477,6 +477,9 @@ static int tcf_ife_init(struct net *net, int ret = 0; int err;

+ if (!nla) + return -EINVAL; + err = nla_parse_nested(tb, TCA_IFE_MAX, nla, ife_policy); if (err < 0) return err;

From: xiao jin jin.xiao@intel.com

commit 54648cf1ec2d7f4b6a71767799c45676a138ca24 upstream.

We find the memory use-after-free issue in __blk_drain_queue() on the kernel 4.14. After read the latest kernel 4.18-rc6 we think it has the same problem.

Memory is allocated for q->fq in the blk_init_allocated_queue(). If the elevator init function called with error return, it will run into the fail case to free the q->fq.

Then the __blk_drain_queue() uses the same memory after the free of the q->fq, it will lead to the unpredictable event.

The patch is to set q->fq as NULL in the fail case of blk_init_allocated_queue().

Fixes: commit 7c94e1c157a2 ("block: introduce blk_flush_queue to drive flush machinery") Cc: stable@vger.kernel.org Reviewed-by: Ming Lei ming.lei@redhat.com Reviewed-by: Bart Van Assche bart.vanassche@wdc.com Signed-off-by: xiao jin jin.xiao@intel.com Signed-off-by: Jens Axboe axboe@kernel.dk [groeck: backport to v4.4.y/v4.9.y (context change)] Signed-off-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Alessio Balsini balsini@android.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- block/blk-core.c | 1 + 1 file changed, 1 insertion(+)

--- a/block/blk-core.c +++ b/block/blk-core.c @@ -881,6 +881,7 @@ blk_init_allocated_queue(struct request_

fail: blk_free_flush_queue(q->fq); + q->fq = NULL; return NULL; } EXPORT_SYMBOL(blk_init_allocated_queue);

From: Ben Hutchings ben@decadent.org.uk

This will make it clearer which bits are allocated, in case we need to assign more feature bits for later backports.

Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/cpufeatures.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)

--- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -201,9 +201,6 @@

#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */

-/* Because the ALTERNATIVE scheme is for members of the X86_FEATURE club... */ -#define X86_FEATURE_KAISER ( 7*32+31) /* CONFIG_PAGE_TABLE_ISOLATION w/o nokaiser */ - #define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ #define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */ #define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* "" Disable Speculative Store Bypass. */ @@ -214,6 +211,7 @@ #define X86_FEATURE_ZEN ( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */ #define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* "" L1TF workaround PTE inversion */ #define X86_FEATURE_IBRS_ENHANCED ( 7*32+30) /* Enhanced IBRS */ +#define X86_FEATURE_KAISER ( 7*32+31) /* CONFIG_PAGE_TABLE_ISOLATION w/o nokaiser */

/* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */

From: Josh Poimboeuf jpoimboe@redhat.com

commit a2059825986a1c8143fd6698774fa9d83733bb11 upstream.

The previous commit added macro calls in the entry code which mitigate the Spectre v1 swapgs issue if the X86_FEATURE_FENCE_SWAPGS_* features are enabled. Enable those features where applicable.

The mitigations may be disabled with "nospectre_v1" or "mitigations=off".

There are different features which can affect the risk of attack:

- When FSGSBASE is enabled, unprivileged users are able to place any value in GS, using the wrgsbase instruction. This means they can write a GS value which points to any value in kernel space, which can be useful with the following gadget in an interrupt/exception/NMI handler:

if (coming from user space) swapgs mov %gs:<percpu_offset>, %reg1 // dependent load or store based on the value of %reg // for example: mov %(reg1), %reg2

If an interrupt is coming from user space, and the entry code speculatively skips the swapgs (due to user branch mistraining), it may speculatively execute the GS-based load and a subsequent dependent load or store, exposing the kernel data to an L1 side channel leak.

Note that, on Intel, a similar attack exists in the above gadget when coming from kernel space, if the swapgs gets speculatively executed to switch back to the user GS. On AMD, this variant isn't possible because swapgs is serializing with respect to future GS-based accesses.

NOTE: The FSGSBASE patch set hasn't been merged yet, so the above case doesn't exist quite yet.

- When FSGSBASE is disabled, the issue is mitigated somewhat because unprivileged users must use prctl(ARCH_SET_GS) to set GS, which restricts GS values to user space addresses only. That means the gadget would need an additional step, since the target kernel address needs to be read from user space first. Something like:

if (coming from user space) swapgs mov %gs:<percpu_offset>, %reg1 mov (%reg1), %reg2 // dependent load or store based on the value of %reg2 // for example: mov %(reg2), %reg3

It's difficult to audit for this gadget in all the handlers, so while there are no known instances of it, it's entirely possible that it exists somewhere (or could be introduced in the future). Without tooling to analyze all such code paths, consider it vulnerable.

Effects of SMAP on the !FSGSBASE case:

- If SMAP is enabled, and the CPU reports RDCL_NO (i.e., not susceptible to Meltdown), the kernel is prevented from speculatively reading user space memory, even L1 cached values. This effectively disables the !FSGSBASE attack vector.

- If SMAP is enabled, but the CPU *is* susceptible to Meltdown, SMAP still prevents the kernel from speculatively reading user space memory. But it does *not* prevent the kernel from reading the user value from L1, if it has already been cached. This is probably only a small hurdle for an attacker to overcome.

Thanks to Dave Hansen for contributing the speculative_smap() function.

Thanks to Andrew Cooper for providing the inside scoop on whether swapgs is serializing on AMD.

[ tglx: Fixed the USER fence decision and polished the comment as suggested by Dave Hansen ]

Signed-off-by: Josh Poimboeuf jpoimboe@redhat.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Dave Hansen dave.hansen@intel.com [bwh: Backported to 4.9: - Check for X86_FEATURE_KAISER instead of X86_FEATURE_PTI - mitigations= parameter is x86-only here - Adjust filename, context] Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- Documentation/kernel-parameters.txt | 9 +- arch/x86/kernel/cpu/bugs.c | 115 +++++++++++++++++++++++++++++++++--- 2 files changed, 111 insertions(+), 13 deletions(-)

--- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2484,6 +2484,7 @@ bytes respectively. Such letter suffixes improves system performance, but it may also expose users to several CPU vulnerabilities. Equivalent to: nopti [X86] + nospectre_v1 [X86] nospectre_v2 [X86] spectre_v2_user=off [X86] spec_store_bypass_disable=off [X86] @@ -2819,10 +2820,6 @@ bytes respectively. Such letter suffixes

nohugeiomap [KNL,x86] Disable kernel huge I/O mappings.

- nospectre_v1 [PPC] Disable mitigations for Spectre Variant 1 (bounds - check bypass). With this option data leaks are possible - in the system. - nosmt [KNL,S390] Disable symmetric multithreading (SMT). Equivalent to smt=1.

@@ -2830,6 +2827,10 @@ bytes respectively. Such letter suffixes nosmt=force: Force disable SMT, cannot be undone via the sysfs control file.

+ nospectre_v1 [X86,PPC] Disable mitigations for Spectre Variant 1 + (bounds check bypass). With this option data leaks are + possible in the system. + nospectre_v2 [X86,PPC_FSL_BOOK3E] Disable all mitigations for the Spectre variant 2 (indirect branch prediction) vulnerability. System may allow data leaks with this option, which is equivalent --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -31,6 +31,7 @@ #include <asm/intel-family.h> #include <asm/e820.h>

+static void __init spectre_v1_select_mitigation(void); static void __init spectre_v2_select_mitigation(void); static void __init ssb_select_mitigation(void); static void __init l1tf_select_mitigation(void); @@ -95,17 +96,11 @@ void __init check_bugs(void) if (boot_cpu_has(X86_FEATURE_STIBP)) x86_spec_ctrl_mask |= SPEC_CTRL_STIBP;

- /* Select the proper spectre mitigation before patching alternatives */ + /* Select the proper CPU mitigations before patching alternatives: */ + spectre_v1_select_mitigation(); spectre_v2_select_mitigation(); - - /* - * Select proper mitigation for any exposure to the Speculative Store - * Bypass vulnerability. - */ ssb_select_mitigation(); - l1tf_select_mitigation(); - mds_select_mitigation();

arch_smt_update(); @@ -271,6 +266,108 @@ static int __init mds_cmdline(char *str) early_param("mds", mds_cmdline);

#undef pr_fmt +#define pr_fmt(fmt) "Spectre V1 : " fmt + +enum spectre_v1_mitigation { + SPECTRE_V1_MITIGATION_NONE, + SPECTRE_V1_MITIGATION_AUTO, +}; + +static enum spectre_v1_mitigation spectre_v1_mitigation __ro_after_init = + SPECTRE_V1_MITIGATION_AUTO; + +static const char * const spectre_v1_strings[] = { + [SPECTRE_V1_MITIGATION_NONE] = "Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers", + [SPECTRE_V1_MITIGATION_AUTO] = "Mitigation: usercopy/swapgs barriers and __user pointer sanitization", +}; + +static bool is_swapgs_serializing(void) +{ + /* + * Technically, swapgs isn't serializing on AMD (despite it previously + * being documented as such in the APM). But according to AMD, %gs is + * updated non-speculatively, and the issuing of %gs-relative memory + * operands will be blocked until the %gs update completes, which is + * good enough for our purposes. + */ + return boot_cpu_data.x86_vendor == X86_VENDOR_AMD; +} + +/* + * Does SMAP provide full mitigation against speculative kernel access to + * userspace? + */ +static bool smap_works_speculatively(void) +{ + if (!boot_cpu_has(X86_FEATURE_SMAP)) + return false; + + /* + * On CPUs which are vulnerable to Meltdown, SMAP does not + * prevent speculative access to user data in the L1 cache. + * Consider SMAP to be non-functional as a mitigation on these + * CPUs. + */ + if (boot_cpu_has(X86_BUG_CPU_MELTDOWN)) + return false; + + return true; +} + +static void __init spectre_v1_select_mitigation(void) +{ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1) || cpu_mitigations_off()) { + spectre_v1_mitigation = SPECTRE_V1_MITIGATION_NONE; + return; + } + + if (spectre_v1_mitigation == SPECTRE_V1_MITIGATION_AUTO) { + /* + * With Spectre v1, a user can speculatively control either + * path of a conditional swapgs with a user-controlled GS + * value. The mitigation is to add lfences to both code paths. + * + * If FSGSBASE is enabled, the user can put a kernel address in + * GS, in which case SMAP provides no protection. + * + * [ NOTE: Don't check for X86_FEATURE_FSGSBASE until the + * FSGSBASE enablement patches have been merged. ] + * + * If FSGSBASE is disabled, the user can only put a user space + * address in GS. That makes an attack harder, but still + * possible if there's no SMAP protection. + */ + if (!smap_works_speculatively()) { + /* + * Mitigation can be provided from SWAPGS itself or + * PTI as the CR3 write in the Meltdown mitigation + * is serializing. + * + * If neither is there, mitigate with an LFENCE. + */ + if (!is_swapgs_serializing() && !boot_cpu_has(X86_FEATURE_KAISER)) + setup_force_cpu_cap(X86_FEATURE_FENCE_SWAPGS_USER); + + /* + * Enable lfences in the kernel entry (non-swapgs) + * paths, to prevent user entry from speculatively + * skipping swapgs. + */ + setup_force_cpu_cap(X86_FEATURE_FENCE_SWAPGS_KERNEL); + } + } + + pr_info("%s\n", spectre_v1_strings[spectre_v1_mitigation]); +} + +static int __init nospectre_v1_cmdline(char *str) +{ + spectre_v1_mitigation = SPECTRE_V1_MITIGATION_NONE; + return 0; +} +early_param("nospectre_v1", nospectre_v1_cmdline); + +#undef pr_fmt #define pr_fmt(fmt) "Spectre V2 : " fmt

static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init = @@ -1265,7 +1362,7 @@ static ssize_t cpu_show_common(struct de break;

case X86_BUG_SPECTRE_V1: - return sprintf(buf, "Mitigation: __user pointer sanitization\n"); + return sprintf(buf, "%s\n", spectre_v1_strings[spectre_v1_mitigation]);

case X86_BUG_SPECTRE_V2: return sprintf(buf, "%s%s%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],

From: Thomas Gleixner tglx@linutronix.de

commit f36cf386e3fec258a341d446915862eded3e13d8 upstream.

Intel provided the following information:

On all current Atom processors, instructions that use a segment register value (e.g. a load or store) will not speculatively execute before the last writer of that segment retires. Thus they will not use a speculatively written segment value.

That means on ATOMs there is no speculation through SWAPGS, so the SWAPGS entry paths can be excluded from the extra LFENCE if PTI is disabled.

Create a separate bug flag for the through SWAPGS speculation and mark all out-of-order ATOMs and AMD/HYGON CPUs as not affected. The in-order ATOMs are excluded from the whole mitigation mess anyway.

Reported-by: Andrew Cooper andrew.cooper3@citrix.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Tyler Hicks tyhicks@canonical.com Reviewed-by: Josh Poimboeuf jpoimboe@redhat.com [bwh: Backported to 4.4: - There's no whitelist entry (or any support) for Hygon CPUs - Adjust context, indentation] Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/cpufeatures.h | 1 arch/x86/kernel/cpu/bugs.c | 18 +++------------ arch/x86/kernel/cpu/common.c | 42 +++++++++++++++++++++++-------------- 3 files changed, 32 insertions(+), 29 deletions(-)

--- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -356,5 +356,6 @@ #define X86_BUG_L1TF X86_BUG(18) /* CPU is affected by L1 Terminal Fault */ #define X86_BUG_MDS X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */ #define X86_BUG_MSBDS_ONLY X86_BUG(20) /* CPU is only affected by the MSDBS variant of BUG_MDS */ +#define X86_BUG_SWAPGS X86_BUG(21) /* CPU is affected by speculation through SWAPGS */

#endif /* _ASM_X86_CPUFEATURES_H */ --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -281,18 +281,6 @@ static const char * const spectre_v1_str [SPECTRE_V1_MITIGATION_AUTO] = "Mitigation: usercopy/swapgs barriers and __user pointer sanitization", };

-static bool is_swapgs_serializing(void) -{ - /* - * Technically, swapgs isn't serializing on AMD (despite it previously - * being documented as such in the APM). But according to AMD, %gs is - * updated non-speculatively, and the issuing of %gs-relative memory - * operands will be blocked until the %gs update completes, which is - * good enough for our purposes. - */ - return boot_cpu_data.x86_vendor == X86_VENDOR_AMD; -} - /* * Does SMAP provide full mitigation against speculative kernel access to * userspace? @@ -343,9 +331,11 @@ static void __init spectre_v1_select_mit * PTI as the CR3 write in the Meltdown mitigation * is serializing. * - * If neither is there, mitigate with an LFENCE. + * If neither is there, mitigate with an LFENCE to + * stop speculation through swapgs. */ - if (!is_swapgs_serializing() && !boot_cpu_has(X86_FEATURE_KAISER)) + if (boot_cpu_has_bug(X86_BUG_SWAPGS) && + !boot_cpu_has(X86_FEATURE_KAISER)) setup_force_cpu_cap(X86_FEATURE_FENCE_SWAPGS_USER);

/* --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -897,6 +897,7 @@ static void identify_cpu_without_cpuid(s #define NO_L1TF BIT(3) #define NO_MDS BIT(4) #define MSBDS_ONLY BIT(5) +#define NO_SWAPGS BIT(6)

#define VULNWL(_vendor, _family, _model, _whitelist) \ { X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist } @@ -920,29 +921,37 @@ static const __initconst struct x86_cpu_ VULNWL_INTEL(ATOM_BONNELL, NO_SPECULATION), VULNWL_INTEL(ATOM_BONNELL_MID, NO_SPECULATION),

- VULNWL_INTEL(ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY), - VULNWL_INTEL(ATOM_SILVERMONT_X, NO_SSB | NO_L1TF | MSBDS_ONLY), - VULNWL_INTEL(ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY), - VULNWL_INTEL(ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY), - VULNWL_INTEL(XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY), - VULNWL_INTEL(XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY), + VULNWL_INTEL(ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), + VULNWL_INTEL(ATOM_SILVERMONT_X, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), + VULNWL_INTEL(ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), + VULNWL_INTEL(ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), + VULNWL_INTEL(XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), + VULNWL_INTEL(XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),

VULNWL_INTEL(CORE_YONAH, NO_SSB),

- VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY), + VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY | NO_SWAPGS),

- VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF), - VULNWL_INTEL(ATOM_GOLDMONT_X, NO_MDS | NO_L1TF), - VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF), + VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS), + VULNWL_INTEL(ATOM_GOLDMONT_X, NO_MDS | NO_L1TF | NO_SWAPGS), + VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS), + + /* + * Technically, swapgs isn't serializing on AMD (despite it previously + * being documented as such in the APM). But according to AMD, %gs is + * updated non-speculatively, and the issuing of %gs-relative memory + * operands will be blocked until the %gs update completes, which is + * good enough for our purposes. + */

/* AMD Family 0xf - 0x12 */ - VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS), - VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS), - VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS), - VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS), + VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS), + VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS), + VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS), + VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS),

/* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */ - VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS), + VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS), {} };

@@ -979,6 +988,9 @@ static void __init cpu_set_bug_bits(stru setup_force_cpu_bug(X86_BUG_MSBDS_ONLY); }

+ if (!cpu_matches(NO_SWAPGS)) + setup_force_cpu_bug(X86_BUG_SWAPGS); + if (cpu_matches(NO_MELTDOWN)) return;