4.4.130-stable review

This is the start of the stable review cycle for the 4.4.130 release. There are 50 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Sun Apr 29 13:56:42 UTC 2018. Anything received after that time might be too late.

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

	https://www.kernel.org/pub/linux/kernel/v4.x/stable-review/patch-4.4.130-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-4.4.y
and the diffstat can be found below.

thanks,

greg k-h

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

Greg Kroah-Hartman <[email protected]>

    Linux 4.4.130-rc1

Heiko Carstens <[email protected]>
s390/uprobes: implement arch_uretprobe_is_alive()

Sebastian Ott <[email protected]>
s390/cio: update chpid descriptor after resource accessibility event

Dan Carpenter <[email protected]>
cdrom: information leak in cdrom_ioctl_media_changed()

Martin K. Petersen <[email protected]>
scsi: mptsas: Disable WRITE SAME

Eric Dumazet <[email protected]>
ipv6: add RTA_TABLE and RTA_PREFSRC to rtm_ipv6_policy

Eric Dumazet <[email protected]>
net: af_packet: fix race in PACKET_{R|T}X_RING

Eric Dumazet <[email protected]>
tcp: md5: reject TCP_MD5SIG or TCP_MD5SIG_EXT on established sockets

Wolfgang Bumiller <[email protected]>
net: fix deadlock while clearing neighbor proxy table

Eric Dumazet <[email protected]>
tipc: add policy for TIPC_NLA_NET_ADDR

Cong Wang <[email protected]>
llc: fix NULL pointer deref for SOCK_ZAPPED

Cong Wang <[email protected]>
llc: hold llc_sap before release_sock()

Xin Long <[email protected]>
sctp: do not check port in sctp_inet6_cmp_addr

Toshiaki Makita <[email protected]>

    vlan: Fix reading memory beyond skb->tail in skb_vlan_tagged_multi

Guillaume Nault <[email protected]>
pppoe: check sockaddr length in pppoe_connect()

Willem de Bruijn <[email protected]>
packet: fix bitfield update race

Xin Long <[email protected]>
team: fix netconsole setup over team

Paolo Abeni <[email protected]>
team: avoid adding twice the same option to the event list

Jann Horn <[email protected]>
tcp: don't read out-of-bounds opsize

Cong Wang <[email protected]>
llc: delete timers synchronously in llc_sk_free()

Eric Dumazet <[email protected]>
net: validate attribute sizes in neigh_dump_table()

Guillaume Nault <[email protected]>
l2tp: check sockaddr length in pppol2tp_connect()

Eric Biggers <[email protected]>
KEYS: DNS: limit the length of option strings

Xin Long <[email protected]>
bonding: do not set slave_dev npinfo before slave_enable_netpoll in bond_enslave

Martin Schwidefsky <[email protected]>
s390: correct module section names for expoline code revert

Martin Schwidefsky <[email protected]>
s390: correct nospec auto detection init order

Martin Schwidefsky <[email protected]>
s390: add sysfs attributes for spectre

Martin Schwidefsky <[email protected]>
s390: report spectre mitigation via syslog

Martin Schwidefsky <[email protected]>
s390: add automatic detection of the spectre defense

Martin Schwidefsky <[email protected]>
s390: move nobp parameter functions to nospec-branch.c

Martin Schwidefsky <[email protected]>
s390/entry.S: fix spurious zeroing of r0

Martin Schwidefsky <[email protected]>
s390: do not bypass BPENTER for interrupt system calls

Martin Schwidefsky <[email protected]>
s390: Replace IS_ENABLED(EXPOLINE_*) with IS_ENABLED(CONFIG_EXPOLINE_*)

Martin Schwidefsky <[email protected]>
s390: introduce execute-trampolines for branches

Martin Schwidefsky <[email protected]>
s390: run user space and KVM guests with modified branch prediction

Martin Schwidefsky <[email protected]>
s390: add options to change branch prediction behaviour for the kernel

Martin Schwidefsky <[email protected]>
s390/alternative: use a copy of the facility bit mask

Martin Schwidefsky <[email protected]>
s390: add optimized array_index_mask_nospec

Martin Schwidefsky <[email protected]>
s390: scrub registers on kernel entry and KVM exit

Martin Schwidefsky <[email protected]>
KVM: s390: wire up bpb feature

Martin Schwidefsky <[email protected]>
s390: enable CPU alternatives unconditionally

Martin Schwidefsky <[email protected]>
s390: introduce CPU alternatives

Karthikeyan Periyasamy <[email protected]>
Revert "ath10k: send (re)assoc peer command when NSS changed"

Sahitya Tummala <[email protected]>
jbd2: fix use after free in kjournald2()

Felix Fietkau <[email protected]>
ath9k_hw: check if the chip failed to wake up

Dmitry Torokhov <[email protected]>

    Input: drv260x - fix initializing overdrive voltage

Grant Grundler <[email protected]>
r8152: add Linksys USB3GIGV1 id

Chen Feng <[email protected]>
staging: ion : Donnot wakeup kswapd in ion system alloc

Jiri Olsa <[email protected]>
perf: Return proper values for user stack errors

Xiaoming Gao <[email protected]>
x86/tsc: Prevent 32bit truncation in calc_hpet_ref()

Steve French <[email protected]>
cifs: do not allow creating sockets except with SMB1 posix exensions

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

Diffstat:

 Documentation/kernel-parameters.txt           |   3 +
 Makefile                                      |   4 +-
 arch/s390/Kconfig                             |  47 +++++
 arch/s390/Makefile                            |  10 ++
 arch/s390/include/asm/alternative.h           | 149 +++++++++++++++
 arch/s390/include/asm/barrier.h               |  24 +++
 arch/s390/include/asm/facility.h              |  18 ++
 arch/s390/include/asm/kvm_host.h              |   3 +-
 arch/s390/include/asm/lowcore.h               |   7 +-
 arch/s390/include/asm/nospec-branch.h         |  17 ++
 arch/s390/include/asm/processor.h             |   4 +
 arch/s390/include/asm/thread_info.h           |   4 +
 arch/s390/include/uapi/asm/kvm.h              |   3 +
 arch/s390/kernel/Makefile                     |   5 +-
 arch/s390/kernel/alternative.c                | 112 ++++++++++++
 arch/s390/kernel/early.c                      |   5 +
 arch/s390/kernel/entry.S                      | 250 +++++++++++++++++++++++---
 arch/s390/kernel/ipl.c                        |   1 +
 arch/s390/kernel/module.c                     |  65 ++++++-
 arch/s390/kernel/nospec-branch.c              | 169 +++++++++++++++++
 arch/s390/kernel/processor.c                  |  18 ++
 arch/s390/kernel/setup.c                      |  14 +-
 arch/s390/kernel/smp.c                        |   7 +-
 arch/s390/kernel/uprobes.c                    |   9 +
 arch/s390/kernel/vmlinux.lds.S                |  37 ++++
 arch/s390/kvm/kvm-s390.c                      |  13 +-
 arch/x86/kernel/tsc.c                         |   2 +-
 drivers/cdrom/cdrom.c                         |   2 +-
 drivers/input/misc/drv260x.c                  |   2 +-
 drivers/message/fusion/mptsas.c               |   1 +
 drivers/net/bonding/bond_main.c               |   3 +-
 drivers/net/ppp/pppoe.c                       |   4 +
 drivers/net/team/team.c                       |  38 +++-
 drivers/net/usb/cdc_ether.c                   |  10 ++
 drivers/net/usb/r8152.c                       |   2 +
 drivers/net/wireless/ath/ath10k/mac.c         |   5 +-
 drivers/net/wireless/ath/ath9k/hw.c           |   4 +
 drivers/s390/char/Makefile                    |   2 +
 drivers/s390/cio/chsc.c                       |  14 +-
 drivers/staging/android/ion/ion_system_heap.c |   2 +-
 fs/cifs/dir.c                                 |   9 +-
 fs/jbd2/journal.c                             |   2 +-
 include/linux/if_vlan.h                       |   7 +-
 include/net/llc_conn.h                        |   1 +
 include/uapi/linux/kvm.h                      |   1 +
 kernel/events/core.c                          |   4 +-
 net/core/dev.c                                |   2 +-
 net/core/neighbour.c                          |  40 +++--
 net/dns_resolver/dns_key.c                    |  13 +-
 net/ipv4/tcp.c                                |   6 +-
 net/ipv4/tcp_input.c                          |   7 +-
 net/ipv6/route.c                              |   2 +
 net/l2tp/l2tp_ppp.c                           |   7 +
 net/llc/af_llc.c                              |  14 +-
 net/llc/llc_c_ac.c                            |   9 +-
 net/llc/llc_conn.c                            |  22 ++-
 net/packet/af_packet.c                        |  88 ++++++---
 net/packet/internal.h                         |  10 +-
 net/sctp/ipv6.c                               |  60 +++----
 net/tipc/net.c                                |   3 +-
 60 files changed, 1228 insertions(+), 168 deletions(-)

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

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

From: Steve French <[email protected]>

commit 1d0cffa674cfa7d185a302c8c6850fc50b893bed upstream.

RHBZ: 1453123

Since at least the 3.10 kernel and likely a lot earlier we have not been able to create unix domain sockets in a cifs share when mounted using the SFU mount option (except when mounted with the cifs unix extensions to Samba e.g.)
Trying to create a socket, for example using the af_unix command from xfstests will cause :

BUG: unable to handle kernel NULL pointer dereference at 00000000

00000040

Since no one uses or depends on being able to create unix domains sockets on a cifs share the easiest fix to stop this vulnerability is to simply not allow creation of any other special files than char or block devices when sfu is used.

Added update to Ronnie's patch to handle a tcon link leak, and to address a buf leak noticed by Gustavo and Colin.

---
 fs/cifs/dir.c |    9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

@@ -673,6 +673,9 @@ int cifs_mknod(struct inode *inode, stru
 		goto mknod_out;
 	}
 
+	if (!S_ISCHR(mode) && !S_ISBLK(mode))
+		goto mknod_out;
+
 	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL))
 		goto mknod_out;
 

@@ -681,10 +684,8 @@ int cifs_mknod(struct inode *inode, stru
 
 	buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL);
 	if (buf == NULL) {
-		kfree(full_path);
 		rc = -ENOMEM;
-		free_xid(xid);
-		return rc;
+		goto mknod_out;
 	}
 
 	if (backup_cred(cifs_sb))

@@ -731,7 +732,7 @@ int cifs_mknod(struct inode *inode, stru
 		pdev->minor = cpu_to_le64(MINOR(device_number));
 		rc = tcon->ses->server->ops->sync_write(xid, &fid, &io_parms,
 							&bytes_written, iov, 1);
-	} /* else if (S_ISFIFO) */
+	}
 	tcon->ses->server->ops->close(xid, tcon, &fid);
 	d_drop(direntry);
 

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

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

From: Xiaoming Gao <[email protected]>

commit d3878e164dcd3925a237a20e879432400e369172 upstream.

The TSC calibration code uses HPET as reference. The conversion normalizes the delta of two HPET timestamps:

    hpetref = ((tshpet1 - tshpet2) * HPET_PERIOD) / 1e6

and then divides the normalized delta of the corresponding TSC timestamps by the result to calulate the TSC frequency.

    tscfreq = ((tstsc1 - tstsc2 ) * 1e6) / hpetref

This uses do_div() which takes an u32 as the divisor, which worked so far because the HPET frequency was low enough that 'hpetref' never exceeded 32bit.

On Skylake machines the HPET frequency increased so 'hpetref' can exceed 32bit. do_div() truncates the divisor, which causes the calibration to fail.

Use div64_u64() to avoid the problem.

[ tglx: Fixes whitespace mangled patch and rewrote changelog ]

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

@@ -408,7 +408,7 @@ static unsigned long calc_hpet_ref(u64 d
 	hpet2 -= hpet1;
 	tmp = ((u64)hpet2 * hpet_readl(HPET_PERIOD));
 	do_div(tmp, 1000000);
-	do_div(deltatsc, tmp);
+	deltatsc = div64_u64(deltatsc, tmp);
 
 	return (unsigned long) deltatsc;
 }

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

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

From: Jiri Olsa <[email protected]>

commit 78b562fbfa2cf0a9fcb23c3154756b690f4905c1 upstream.

Return immediately when we find issue in the user stack checks. The error value could get overwritten by following check for PERF_SAMPLE_REGS_INTR.

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

@@ -8133,9 +8133,9 @@ static int perf_copy_attr(struct perf_ev
 		 * __u16 sample size limit.
 		 */
 		if (attr->sample_stack_user >= USHRT_MAX)
-			ret = -EINVAL;
+			return -EINVAL;
 		else if (!IS_ALIGNED(attr->sample_stack_user, sizeof(u64)))
-			ret = -EINVAL;
+			return -EINVAL;
 	}
 
 	if (attr->sample_type & PERF_SAMPLE_REGS_INTR)

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

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

From: Chen Feng <[email protected]>

commit 2ef230531ee171a475fc3ddad5516dd7e09a8a77 upstream.

Since ion alloc can be called by userspace,eg gralloc. When it is called frequently, the efficiency of kswapd is to low. And the reclaimed memory is too lower. In this way, the kswapd can use to much cpu resources.

With 3.5GB DMA Zone and 0.5 Normal Zone.

pgsteal_kswapd_dma 9364140
pgsteal_kswapd_normal 7071043
pgscan_kswapd_dma 10428250
pgscan_kswapd_normal 37840094

With this change the reclaim ratio has greatly improved 18.9% -> 72.5%

---
 drivers/staging/android/ion/ion_system_heap.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -27,7 +27,7 @@
 #include "ion_priv.h"
 
 static gfp_t high_order_gfp_flags = (GFP_HIGHUSER | __GFP_ZERO | __GFP_NOWARN |
-				     __GFP_NORETRY) & ~__GFP_DIRECT_RECLAIM;
+				     __GFP_NORETRY) & ~__GFP_RECLAIM;
 static gfp_t low_order_gfp_flags  = (GFP_HIGHUSER | __GFP_ZERO | __GFP_NOWARN);
 static const unsigned int orders[] = {8, 4, 0};
 static const int num_orders = ARRAY_SIZE(orders);

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

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

From: Grant Grundler <[email protected]>

commit 90841047a01b452cc8c3f9b990698b264143334a upstream.

This linksys dongle by default comes up in cdc_ether mode. This patch allows r8152 to claim the device:
Bus 002 Device 002: ID 13b1:0041 Linksys

---
 drivers/net/usb/cdc_ether.c |   10 ++++++++++
 drivers/net/usb/r8152.c     |    2 ++
 2 files changed, 12 insertions(+)

@@ -461,6 +461,7 @@ static const struct driver_info wwan_inf
 #define REALTEK_VENDOR_ID	0x0bda
 #define SAMSUNG_VENDOR_ID	0x04e8
 #define LENOVO_VENDOR_ID	0x17ef
+#define LINKSYS_VENDOR_ID	0x13b1
 #define NVIDIA_VENDOR_ID	0x0955
 #define HP_VENDOR_ID		0x03f0
 

@@ -650,6 +651,15 @@ static const struct usb_device_id	produc
 	.driver_info = 0,
 },
 
+#if IS_ENABLED(CONFIG_USB_RTL8152)
+/* Linksys USB3GIGV1 Ethernet Adapter */
+{
+	USB_DEVICE_AND_INTERFACE_INFO(LINKSYS_VENDOR_ID, 0x0041, USB_CLASS_COMM,
+			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+	.driver_info = 0,
+},
+#endif
+
 /* Lenovo Thinkpad USB 3.0 Ethernet Adapters (based on Realtek RTL8153) */
 {
 	USB_DEVICE_AND_INTERFACE_INFO(LENOVO_VENDOR_ID, 0x7205, USB_CLASS_COMM,

@@ -506,6 +506,7 @@ enum rtl8152_flags {
 #define VENDOR_ID_REALTEK		0x0bda
 #define VENDOR_ID_SAMSUNG		0x04e8
 #define VENDOR_ID_LENOVO		0x17ef
+#define VENDOR_ID_LINKSYS		0x13b1
 #define VENDOR_ID_NVIDIA		0x0955
 
 #define MCU_TYPE_PLA			0x0100

@@ -4376,6 +4377,7 @@ static struct usb_device_id rtl8152_tabl
 	{REALTEK_USB_DEVICE(VENDOR_ID_SAMSUNG, 0xa101)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x7205)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x304f)},
+	{REALTEK_USB_DEVICE(VENDOR_ID_LINKSYS, 0x0041)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_NVIDIA,  0x09ff)},
 	{}
 };

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

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

From: Dmitry Torokhov <[email protected]>

commit 74c82dae6c474933f2be401976e1530b5f623221 upstream.

We were accidentally initializing haptics->rated_voltage twice, and did not initialize overdrive voltage.

---
 drivers/input/misc/drv260x.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -521,7 +521,7 @@ static int drv260x_probe(struct i2c_clie
 	if (!haptics)
 		return -ENOMEM;
 
-	haptics->rated_voltage = DRV260X_DEF_OD_CLAMP_VOLT;
+	haptics->overdrive_voltage = DRV260X_DEF_OD_CLAMP_VOLT;
 	haptics->rated_voltage = DRV260X_DEF_RATED_VOLT;
 
 	if (pdata) {

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

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

From: Felix Fietkau <[email protected]>

commit a34d0a0da1abae46a5f6ebd06fb0ec484ca099d9 upstream.

In an RFC patch, Sven Eckelmann and Simon Wunderlich reported:

"QCA 802.11n chips (especially AR9330/AR9340) sometimes end up in a state in which a read of AR_CFG always returns 0xdeadbeef. This should not happen when when the power_mode of the device is ATH9K_PM_AWAKE."

Include the check for the default register state in the existing MAC hang check.

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

@@ -1595,6 +1595,10 @@ bool ath9k_hw_check_alive(struct ath_hw
 	int count = 50;
 	u32 reg, last_val;
 
+	/* Check if chip failed to wake up */
+	if (REG_READ(ah, AR_CFG) == 0xdeadbeef)
+		return false;
+
 	if (AR_SREV_9300(ah))
 		return !ath9k_hw_detect_mac_hang(ah);
 

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

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

From: Sahitya Tummala <[email protected]>

commit dbfcef6b0f4012c57bc0b6e0e660d5ed12a5eaed upstream.

Below is the synchronization issue between unmount and kjournald2 contexts, which results into use after free issue in kjournald2(). Fix this issue by using journal->j_state_lock to synchronize the wait_event() done in journal_kill_thread() and the wake_up() done in kjournald2().

TASK 1:
umount cmd:

   |--jbd2_journal_destroy() {
       |--journal_kill_thread() {
            write_lock(&journal->j_state_lock);
	    journal->j_flags |= JBD2_UNMOUNT;
	    ...
	    write_unlock(&journal->j_state_lock);
	    wake_up(&journal->j_wait_commit);	   TASK 2 wakes up here:
	    					   kjournald2() {
						     ...
						     checks JBD2_UNMOUNT flag and calls goto end-loop;
						     ...
						     end_loop:
						       write_unlock(&journal->j_state_lock);
						       journal->j_task = NULL; --> If this thread gets
						       pre-empted here, then TASK 1 wait_event will
						       exit even before this thread is completely
						       done.
	    wait_event(journal->j_wait_done_commit, journal->j_task == NULL);
	    ...
	    write_lock(&journal->j_state_lock);
	    write_unlock(&journal->j_state_lock);
	  }
       |--kfree(journal);
     }
}
						       wake_up(&journal->j_wait_done_commit); --> this step
						       now results into use after free issue.
						   }

---
 fs/jbd2/journal.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -275,11 +275,11 @@ loop:
 	goto loop;
 
 end_loop:
-	write_unlock(&journal->j_state_lock);
 	del_timer_sync(&journal->j_commit_timer);
 	journal->j_task = NULL;
 	wake_up(&journal->j_wait_done_commit);
 	jbd_debug(1, "Journal thread exiting.\n");
+	write_unlock(&journal->j_state_lock);
 	return 0;
 }
 

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

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

From: Karthikeyan Periyasamy <[email protected]>

commit 55cc11da69895a680940c1733caabc37be685f5e upstream.

This reverts commit 55884c045d31a29cf69db8332d1064a1b61dd159.

When Ath10k is in AP mode and an unassociated STA sends a VHT action frame (Operating Mode Notification for the NSS change) periodically to AP this causes ath10k to call ath10k_station_assoc() which sends WMI_PEER_ASSOC_CMDID during NSS update. Over the time (with a certain client it can happen within 15 mins when there are over 500 of these VHT action frames) continuous calls of WMI_PEER_ASSOC_CMDID cause firmware to assert due to resource exhaust.

To my knowledge setting WMI_PEER_NSS peer param itself enough to handle NSS updates and no need to call ath10k_station_assoc(). So revert the original commit from 2014 as it's unclear why the change was really needed. Now the firmware assert doesn't happen anymore.

Issue observed in QCA9984 platform with firmware version:10.4-3.5.3-00053. This Change tested in QCA9984 with firmware version: 10.4-3.5.3-00053 and QCA988x platform with firmware version: 10.2.4-1.0-00036.

Firmware Assert log:

ath10k_pci 0002:01:00.0: firmware crashed! (guid e61f1274-9acd-4c5b-bcca-e032ea6e723c)
ath10k_pci 0002:01:00.0: qca9984/qca9994 hw1.0 target 0x01000000 chip_id 0x00000000 sub 168c:cafe
ath10k_pci 0002:01:00.0: kconfig debug 1 debugfs 1 tracing 0 dfs 1 testmode 1
ath10k_pci 0002:01:00.0: firmware ver 10.4-3.5.3-00053 api 5 features no-p2p,mfp,peer-flow-ctrl,btcoex-param,allows-mesh-bcast crc32 4c56a386 ath10k_pci 0002:01:00.0: board_file api 2 bmi_id 0:4 crc32 c2271344
ath10k_pci 0002:01:00.0: htt-ver 2.2 wmi-op 6 htt-op 4 cal otp max-sta 512 raw 0 hwcrypto 1
ath10k_pci 0002:01:00.0: firmware register dump:
ath10k_pci 0002:01:00.0: [00]: 0x0000000A 0x000015B3 0x00981E5F 0x00975B31
ath10k_pci 0002:01:00.0: [04]: 0x00981E5F 0x00060530 0x00000011 0x00446C60
ath10k_pci 0002:01:00.0: [08]: 0x0042F1FC 0x00458080 0x00000017 0x00000000
ath10k_pci 0002:01:00.0: [12]: 0x00000009 0x00000000 0x00973ABC 0x00973AD2
ath10k_pci 0002:01:00.0: [16]: 0x00973AB0 0x00960E62 0x009606CA 0x00000000
ath10k_pci 0002:01:00.0: [20]: 0x40981E5F 0x004066DC 0x00400000 0x00981E34
ath10k_pci 0002:01:00.0: [24]: 0x80983B48 0x0040673C 0x000000C0 0xC0981E5F
ath10k_pci 0002:01:00.0: [28]: 0x80993DEB 0x0040676C 0x00431AB8 0x0045D0C4
ath10k_pci 0002:01:00.0: [32]: 0x80993E5C 0x004067AC 0x004303C0 0x0045D0C4
ath10k_pci 0002:01:00.0: [36]: 0x80994AAB 0x004067DC 0x00000000 0x0045D0C4
ath10k_pci 0002:01:00.0: [40]: 0x809971A0 0x0040681C 0x004303C0 0x00441B00
ath10k_pci 0002:01:00.0: [44]: 0x80991904 0x0040688C 0x004303C0 0x0045D0C4
ath10k_pci 0002:01:00.0: [48]: 0x80963AD3 0x00406A7C 0x004303C0 0x009918FC
ath10k_pci 0002:01:00.0: [52]: 0x80960E80 0x00406A9C 0x0000001F 0x00400000
ath10k_pci 0002:01:00.0: [56]: 0x80960E51 0x00406ACC 0x00400000 0x00000000
ath10k_pci 0002:01:00.0: Copy Engine register dump:
ath10k_pci 0002:01:00.0: index: addr: sr_wr_idx: sr_r_idx: dst_wr_idx: dst_r_idx:
ath10k_pci 0002:01:00.0: [00]: 0x0004a000 15 15 3 3
ath10k_pci 0002:01:00.0: [01]: 0x0004a400 17 17 212 213
ath10k_pci 0002:01:00.0: [02]: 0x0004a800 21 21 20 21
ath10k_pci 0002:01:00.0: [03]: 0x0004ac00 25 25 27 25
ath10k_pci 0002:01:00.0: [04]: 0x0004b000 515 515 144 104
ath10k_pci 0002:01:00.0: [05]: 0x0004b400 28 28 155 156
ath10k_pci 0002:01:00.0: [06]: 0x0004b800 12 12 12 12
ath10k_pci 0002:01:00.0: [07]: 0x0004bc00 1 1 1 1
ath10k_pci 0002:01:00.0: [08]: 0x0004c000 0 0 127 0
ath10k_pci 0002:01:00.0: [09]: 0x0004c400 1 1 1 1
ath10k_pci 0002:01:00.0: [10]: 0x0004c800 0 0 0 0
ath10k_pci 0002:01:00.0: [11]: 0x0004cc00 0 0 0 0
ath10k_pci 0002:01:00.0: CE[1] write_index 212 sw_index 213 hw_index 0 nentries_mask 0x000001ff
ath10k_pci 0002:01:00.0: CE[2] write_index 20 sw_index 21 hw_index 0 nentries_mask 0x0000007f
ath10k_pci 0002:01:00.0: CE[5] write_index 155 sw_index 156 hw_index 0 nentries_mask 0x000001ff
ath10k_pci 0002:01:00.0: DMA addr: nbytes: meta data: byte swap: gather:
ath10k_pci 0002:01:00.0: [455]: 0x580c0042 0 0 0 0
ath10k_pci 0002:01:00.0: [456]: 0x594a0010 0 0 0 1
ath10k_pci 0002:01:00.0: [457]: 0x580c0042 0 0 0 0
ath10k_pci 0002:01:00.0: [458]: 0x594a0038 0 0 0 1
ath10k_pci 0002:01:00.0: [459]: 0x580c0a42 0 0 0 0
ath10k_pci 0002:01:00.0: [460]: 0x594a0060 0 0 0 1
ath10k_pci 0002:01:00.0: [461]: 0x580c0c42 0 0 0 0
ath10k_pci 0002:01:00.0: [462]: 0x594a0010 0 0 0 1
ath10k_pci 0002:01:00.0: [463]: 0x580c0c42 0 0 0 0
ath10k_pci 0002:01:00.0: [464]: 0x594a0038 0 0 0 1
ath10k_pci 0002:01:00.0: [465]: 0x580c0a42 0 0 0 0
ath10k_pci 0002:01:00.0: [466]: 0x594a0060 0 0 0 1
ath10k_pci 0002:01:00.0: [467]: 0x580c0042 0 0 0 0
ath10k_pci 0002:01:00.0: [468]: 0x594a0010 0 0 0 1
ath10k_pci 0002:01:00.0: [469]: 0x580c1c42 0 0 0 0
ath10k_pci 0002:01:00.0: [470]: 0x594a0010 0 0 0 1
ath10k_pci 0002:01:00.0: [471]: 0x580c1c42 0 0 0 0
ath10k_pci 0002:01:00.0: [472]: 0x594a0010 0 0 0 1
ath10k_pci 0002:01:00.0: [473]: 0x580c1c42 0 0 0 0
ath10k_pci 0002:01:00.0: [474]: 0x594a0010 0 0 0 1
ath10k_pci 0002:01:00.0: [475]: 0x580c0642 0 0 0 0
ath10k_pci 0002:01:00.0: [476]: 0x594a0038 0 0 0 1
ath10k_pci 0002:01:00.0: [477]: 0x580c0842 0 0 0 0
ath10k_pci 0002:01:00.0: [478]: 0x594a0060 0 0 0 1
ath10k_pci 0002:01:00.0: [479]: 0x580c0042 0 0 0 0
ath10k_pci 0002:01:00.0: [480]: 0x594a0010 0 0 0 1
ath10k_pci 0002:01:00.0: [481]: 0x580c0042 0 0 0 0
ath10k_pci 0002:01:00.0: [482]: 0x594a0038 0 0 0 1
ath10k_pci 0002:01:00.0: [483]: 0x580c0842 0 0 0 0
ath10k_pci 0002:01:00.0: [484]: 0x594a0060 0 0 0 1
ath10k_pci 0002:01:00.0: [485]: 0x580c0642 0 0 0 0
ath10k_pci 0002:01:00.0: [486]: 0x594a0010 0 0 0 1
ath10k_pci 0002:01:00.0: [487]: 0x580c0642 0 0 0 0
ath10k_pci 0002:01:00.0: [488]: 0x594a0038 0 0 0 1
ath10k_pci 0002:01:00.0: [489]: 0x580c0842 0 0 0 0
ath10k_pci 0002:01:00.0: [490]: 0x594a0060 0 0 0 1
ath10k_pci 0002:01:00.0: [491]: 0x580c0042 0 0 0 0
ath10k_pci 0002:01:00.0: [492]: 0x58174040 0 1 0 0
ath10k_pci 0002:01:00.0: [493]: 0x5a946040 0 1 0 0
ath10k_pci 0002:01:00.0: [494]: 0x59909040 0 1 0 0
ath10k_pci 0002:01:00.0: [495]: 0x5ae5a040 0 1 0 0
ath10k_pci 0002:01:00.0: [496]: 0x58096040 0 1 0 0
ath10k_pci 0002:01:00.0: [497]: 0x594a0010 0 0 0 1
ath10k_pci 0002:01:00.0: [498]: 0x580c0642 0 0 0 0
ath10k_pci 0002:01:00.0: [499]: 0x5c1e0040 0 1 0 0
ath10k_pci 0002:01:00.0: [500]: 0x58153040 0 1 0 0
ath10k_pci 0002:01:00.0: [501]: 0x58129040 0 1 0 0
ath10k_pci 0002:01:00.0: [502]: 0x5952f040 0 1 0 0
ath10k_pci 0002:01:00.0: [503]: 0x59535040 0 1 0 0
ath10k_pci 0002:01:00.0: [504]: 0x594a0010 0 0 0 1
ath10k_pci 0002:01:00.0: [505]: 0x580c0042 0 0 0 0
ath10k_pci 0002:01:00.0: [506]: 0x594a0010 0 0 0 1
ath10k_pci 0002:01:00.0: [507]: 0x580c0042 0 0 0 0
ath10k_pci 0002:01:00.0: [508]: 0x594a0010 0 0 0 1
ath10k_pci 0002:01:00.0: [509]: 0x580c0042 0 0 0 0
ath10k_pci 0002:01:00.0: [510]: 0x594a0010 0 0 0 1
ath10k_pci 0002:01:00.0: [511]: 0x580c0042 0 0 0 0
ath10k_pci 0002:01:00.0: [512]: 0x5adcc040 0 1 0 0
ath10k_pci 0002:01:00.0: [513]: 0x5cf3d040 0 1 0 0
ath10k_pci 0002:01:00.0: [514]: 0x5c1e9040 64 1 0 0
ath10k_pci 0002:01:00.0: [515]: 0x00000000 0 0 0 0

---
 drivers/net/wireless/ath/ath10k/mac.c |    5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

@@ -5285,9 +5285,8 @@ static void ath10k_sta_rc_update_wk(stru
 				    sta->addr, smps, err);
 	}
 
-	if (changed & IEEE80211_RC_SUPP_RATES_CHANGED ||
-	    changed & IEEE80211_RC_NSS_CHANGED) {
-		ath10k_dbg(ar, ATH10K_DBG_MAC, "mac update sta %pM supp rates/nss\n",
+	if (changed & IEEE80211_RC_SUPP_RATES_CHANGED) {
+		ath10k_dbg(ar, ATH10K_DBG_MAC, "mac update sta %pM supp rates\n",
 			   sta->addr);
 
 		err = ath10k_station_assoc(ar, arvif->vif, sta, true);

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

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

From: Martin Schwidefsky <[email protected]>

From: Vasily Gorbik <[email protected]>

[ Upstream commit 686140a1a9c41d85a4212a1c26d671139b76404b ]

Implement CPU alternatives, which allows to optionally patch newer instructions at runtime, based on CPU facilities availability.

A new kernel boot parameter "noaltinstr" disables patching.

Current implementation is derived from x86 alternatives. Although ideal instructions padding (when altinstr is longer then oldinstr) is added at compile time, and no oldinstr nops optimization has to be done at runtime. Also couple of compile time sanity checks are done:
1. oldinstr and altinstr must be <= 254 bytes long,
2. oldinstr and altinstr must not have an odd length.

alternative(oldinstr, altinstr, facility); alternative_2(oldinstr, altinstr1, facility1, altinstr2, facility2);

Both compile time and runtime padding consists of either 6/4/2 bytes nop or a jump (brcl) + 2 bytes nop filler if padding is longer then 6 bytes.

.altinstructions and .altinstr_replacement sections are part of __init_begin : __init_end region and are freed after initialization.

---
 Documentation/kernel-parameters.txt |    3 
 arch/s390/Kconfig                   |   17 +++
 arch/s390/include/asm/alternative.h |  163 ++++++++++++++++++++++++++++++++++++
 arch/s390/kernel/Makefile           |    1 
 arch/s390/kernel/alternative.c      |  110 ++++++++++++++++++++++++
 arch/s390/kernel/module.c           |   17 +++
 arch/s390/kernel/setup.c            |    3 
 arch/s390/kernel/vmlinux.lds.S      |   23 +++++
 8 files changed, 337 insertions(+)
 create mode 100644 arch/s390/include/asm/alternative.h
 create mode 100644 arch/s390/kernel/alternative.c

@@ -2402,6 +2402,9 @@ bytes respectively. Such letter suffixes
 
 	noalign		[KNL,ARM]
 
+	noaltinstr	[S390] Disables alternative instructions patching
+			(CPU alternatives feature).
+
 	noapic		[SMP,APIC] Tells the kernel to not make use of any
 			IOAPICs that may be present in the system.
 

@@ -705,6 +705,22 @@ config SECCOMP
 
 	  If unsure, say Y.
 
+config ALTERNATIVES
+	def_bool y
+	prompt "Patch optimized instructions for running CPU type"
+	help
+	  When enabled the kernel code is compiled with additional
+	  alternative instructions blocks optimized for newer CPU types.
+	  These alternative instructions blocks are patched at kernel boot
+	  time when running CPU supports them. This mechanism is used to
+	  optimize some critical code paths (i.e. spinlocks) for newer CPUs
+	  even if kernel is build to support older machine generations.
+
+	  This mechanism could be disabled by appending "noaltinstr"
+	  option to the kernel command line.
+
+	  If unsure, say Y.
+
 endmenu
 
 menu "Power Management"

@@ -754,6 +770,7 @@ config PFAULT
 config SHARED_KERNEL
 	bool "VM shared kernel support"
 	depends on !JUMP_LABEL
+	depends on !ALTERNATIVES
 	help
 	  Select this option, if you want to share the text segment of the
 	  Linux kernel between different VM guests. This reduces memory

@@ -62,6 +62,7 @@ obj-$(CONFIG_KPROBES)		+= kprobes.o
 obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o ftrace.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
 obj-$(CONFIG_UPROBES)		+= uprobes.o
+obj-$(CONFIG_ALTERNATIVES)	+= alternative.o
 
 obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o perf_cpum_cf.o perf_cpum_sf.o
 obj-$(CONFIG_PERF_EVENTS)	+= perf_cpum_cf_events.o

@@ -31,6 +31,7 @@
 #include <linux/kernel.h>
 #include <linux/moduleloader.h>
 #include <linux/bug.h>
+#include <asm/alternative.h>
 
 #if 0
 #define DEBUGP printk

@@ -424,6 +425,22 @@ int module_finalize(const Elf_Ehdr *hdr,
 		    const Elf_Shdr *sechdrs,
 		    struct module *me)
 {
+	const Elf_Shdr *s;
+	char *secstrings;
+
+	if (IS_ENABLED(CONFIG_ALTERNATIVES)) {
+		secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
+		for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
+			if (!strcmp(".altinstructions",
+				    secstrings + s->sh_name)) {
+				/* patch .altinstructions */
+				void *aseg = (void *)s->sh_addr;
+
+				apply_alternatives(aseg, aseg + s->sh_size);
+			}
+		}
+	}
+
 	jump_label_apply_nops(me);
 	vfree(me->arch.syminfo);
 	me->arch.syminfo = NULL;

@@ -63,6 +63,7 @@
 #include <asm/sclp.h>
 #include <asm/sysinfo.h>
 #include <asm/numa.h>
+#include <asm/alternative.h>
 #include "entry.h"
 
 /*

@@ -893,6 +894,8 @@ void __init setup_arch(char **cmdline_p)
 	conmode_default();
 	set_preferred_console();
 
+	apply_alternative_instructions();
+
 	/* Setup zfcpdump support */
 	setup_zfcpdump();
 

@@ -78,6 +78,29 @@ SECTIONS
 		EXIT_DATA
 	}
 
+	/*
+	 * struct alt_inst entries. From the header (alternative.h):
+	 * "Alternative instructions for different CPU types or capabilities"
+	 * Think locking instructions on spinlocks.
+	 * Note, that it is a part of __init region.
+	 */
+	. = ALIGN(8);
+	.altinstructions : {
+		__alt_instructions = .;
+		*(.altinstructions)
+		__alt_instructions_end = .;
+	}
+
+	/*
+	 * And here are the replacement instructions. The linker sticks
+	 * them as binary blobs. The .altinstructions has enough data to
+	 * get the address and the length of them to patch the kernel safely.
+	 * Note, that it is a part of __init region.
+	 */
+	.altinstr_replacement : {
+		*(.altinstr_replacement)
+	}
+
 	/* early.c uses stsi, which requires page aligned data. */
 	. = ALIGN(PAGE_SIZE);
 	INIT_DATA_SECTION(0x100)

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

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

From: Martin Schwidefsky <[email protected]>

From: Heiko Carstens <[email protected]>

[ Upstream commit 049a2c2d486e8cc82c5cd79fa479c5b105b109e9 ]

Remove the CPU_ALTERNATIVES config option and enable the code unconditionally. The config option was only added to avoid a conflict with the named saved segment support. Since that code is gone there is no reason to keep the CPU_ALTERNATIVES config option.

Just enable it unconditionally to also reduce the number of config options and make it less likely that something breaks.

---
 arch/s390/Kconfig                   |   16 ----------------
 arch/s390/include/asm/alternative.h |   20 +++-----------------
 arch/s390/kernel/Makefile           |    3 +--
 arch/s390/kernel/module.c           |   15 ++++++---------
 4 files changed, 10 insertions(+), 44 deletions(-)

@@ -705,22 +705,6 @@ config SECCOMP
 
 	  If unsure, say Y.
 
-config ALTERNATIVES
-	def_bool y
-	prompt "Patch optimized instructions for running CPU type"
-	help
-	  When enabled the kernel code is compiled with additional
-	  alternative instructions blocks optimized for newer CPU types.
-	  These alternative instructions blocks are patched at kernel boot
-	  time when running CPU supports them. This mechanism is used to
-	  optimize some critical code paths (i.e. spinlocks) for newer CPUs
-	  even if kernel is build to support older machine generations.
-
-	  This mechanism could be disabled by appending "noaltinstr"
-	  option to the kernel command line.
-
-	  If unsure, say Y.
-
 endmenu
 
 menu "Power Management"

@@ -15,14 +15,9 @@ struct alt_instr {
 	u8  replacementlen;	/* length of new instruction */
 } __packed;
 
-#ifdef CONFIG_ALTERNATIVES
-extern void apply_alternative_instructions(void);
-extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
-#else
-static inline void apply_alternative_instructions(void) {};
-static inline void apply_alternatives(struct alt_instr *start,
-				      struct alt_instr *end) {};
-#endif
+void apply_alternative_instructions(void);
+void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
+
 /*
  * |661:       |662:	  |6620      |663:
  * +-----------+---------------------+

@@ -109,7 +104,6 @@ static inline void apply_alternatives(st
 	b_altinstr(num)":\n\t" altinstr "\n" e_altinstr(num) ":\n"	\
 	INSTR_LEN_SANITY_CHECK(altinstr_len(num))
 
-#ifdef CONFIG_ALTERNATIVES
 /* alternative assembly primitive: */
 #define ALTERNATIVE(oldinstr, altinstr, facility) \
 	".pushsection .altinstr_replacement, \"ax\"\n"			\

@@ -130,14 +124,6 @@ static inline void apply_alternatives(st
 	ALTINSTR_ENTRY(facility1, 1)					\
 	ALTINSTR_ENTRY(facility2, 2)					\
 	".popsection\n"
-#else
-/* Alternative instructions are disabled, let's put just oldinstr in */
-#define ALTERNATIVE(oldinstr, altinstr, facility) \
-	oldinstr "\n"
-
-#define ALTERNATIVE_2(oldinstr, altinstr1, facility1, altinstr2, facility2) \
-	oldinstr "\n"
-#endif
 
 /*
  * Alternative instructions for different CPU types or capabilities.

@@ -44,7 +44,7 @@ obj-y	+= processor.o sys_s390.o ptrace.o
 obj-y	+= debug.o irq.o ipl.o dis.o diag.o sclp.o vdso.o
 obj-y	+= sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o pgm_check.o
 obj-y	+= runtime_instr.o cache.o dumpstack.o
-obj-y	+= entry.o reipl.o relocate_kernel.o
+obj-y	+= entry.o reipl.o relocate_kernel.o alternative.o
 
 extra-y				+= head.o head64.o vmlinux.lds
 

@@ -62,7 +62,6 @@ obj-$(CONFIG_KPROBES)		+= kprobes.o
 obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o ftrace.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
 obj-$(CONFIG_UPROBES)		+= uprobes.o
-obj-$(CONFIG_ALTERNATIVES)	+= alternative.o
 
 obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o perf_cpum_cf.o perf_cpum_sf.o
 obj-$(CONFIG_PERF_EVENTS)	+= perf_cpum_cf_events.o

@@ -428,16 +428,13 @@ int module_finalize(const Elf_Ehdr *hdr,
 	const Elf_Shdr *s;
 	char *secstrings;
 
-	if (IS_ENABLED(CONFIG_ALTERNATIVES)) {
-		secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
-		for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
-			if (!strcmp(".altinstructions",
-				    secstrings + s->sh_name)) {
-				/* patch .altinstructions */
-				void *aseg = (void *)s->sh_addr;
+	secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
+	for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
+		if (!strcmp(".altinstructions", secstrings + s->sh_name)) {
+			/* patch .altinstructions */
+			void *aseg = (void *)s->sh_addr;
 
-				apply_alternatives(aseg, aseg + s->sh_size);
-			}
+			apply_alternatives(aseg, aseg + s->sh_size);
 		}
 	}
 

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

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

From: Martin Schwidefsky <[email protected]>

From: Christian Borntraeger <[email protected]>

[ Upstream commit 35b3fde6203b932b2b1a5b53b3d8808abc9c4f60 ]

The new firmware interfaces for branch prediction behaviour changes are transparently available for the guest. Nevertheless, there is new state attached that should be migrated and properly resetted. Provide a mechanism for handling reset, migration and VSIE.

---
 arch/s390/include/asm/kvm_host.h |    3 ++-
 arch/s390/include/uapi/asm/kvm.h |    3 +++
 arch/s390/kvm/kvm-s390.c         |   13 ++++++++++++-
 include/uapi/linux/kvm.h         |    1 +
 4 files changed, 18 insertions(+), 2 deletions(-)

@@ -136,7 +136,8 @@ struct kvm_s390_sie_block {
 	__u16	ipa;			/* 0x0056 */
 	__u32	ipb;			/* 0x0058 */
 	__u32	scaoh;			/* 0x005c */
-	__u8	reserved60;		/* 0x0060 */
+#define FPF_BPBC 	0x20
+	__u8	fpf;			/* 0x0060 */
 	__u8	ecb;			/* 0x0061 */
 	__u8    ecb2;                   /* 0x0062 */
 #define ECB3_AES 0x04

@@ -151,6 +151,7 @@ struct kvm_guest_debug_arch {
 #define KVM_SYNC_ARCH0  (1UL << 4)
 #define KVM_SYNC_PFAULT (1UL << 5)
 #define KVM_SYNC_VRS    (1UL << 6)
+#define KVM_SYNC_BPBC	(1UL << 10)
 /* definition of registers in kvm_run */
 struct kvm_sync_regs {
 	__u64 prefix;	/* prefix register */

@@ -168,6 +169,8 @@ struct kvm_sync_regs {
 	__u64 vrs[32][2];	/* vector registers */
 	__u8  reserved[512];	/* for future vector expansion */
 	__u32 fpc;	/* only valid with vector registers */
+	__u8 bpbc : 1;		/* bp mode */
+	__u8 reserved2 : 7;
 };
 
 #define KVM_REG_S390_TODPR	(KVM_REG_S390 | KVM_REG_SIZE_U32 | 0x1)

@@ -257,6 +257,9 @@ int kvm_vm_ioctl_check_extension(struct
 	case KVM_CAP_S390_VECTOR_REGISTERS:
 		r = MACHINE_HAS_VX;
 		break;
+	case KVM_CAP_S390_BPB:
+		r = test_facility(82);
+		break;
 	default:
 		r = 0;
 	}

@@ -1262,6 +1265,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *
 				    KVM_SYNC_CRS |
 				    KVM_SYNC_ARCH0 |
 				    KVM_SYNC_PFAULT;
+	if (test_kvm_facility(vcpu->kvm, 82))
+		vcpu->run->kvm_valid_regs |= KVM_SYNC_BPBC;
 	if (test_kvm_facility(vcpu->kvm, 129))
 		vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS;
 

@@ -1286,7 +1291,6 @@ void kvm_arch_vcpu_load(struct kvm_vcpu
 	if (test_fp_ctl(current->thread.fpu.fpc))
 		/* User space provided an invalid FPC, let's clear it */
 		current->thread.fpu.fpc = 0;
-
 	save_access_regs(vcpu->arch.host_acrs);
 	restore_access_regs(vcpu->run->s.regs.acrs);
 	gmap_enable(vcpu->arch.gmap);

@@ -1327,6 +1331,7 @@ static void kvm_s390_vcpu_initial_reset(
 	current->thread.fpu.fpc = 0;
 	vcpu->arch.sie_block->gbea = 1;
 	vcpu->arch.sie_block->pp = 0;
+	vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
 	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
 	kvm_clear_async_pf_completion_queue(vcpu);
 	if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm))

@@ -2162,6 +2167,7 @@ static void store_regs(struct kvm_vcpu *
 	kvm_run->s.regs.pft = vcpu->arch.pfault_token;
 	kvm_run->s.regs.pfs = vcpu->arch.pfault_select;
 	kvm_run->s.regs.pfc = vcpu->arch.pfault_compare;
+	kvm_run->s.regs.bpbc = (vcpu->arch.sie_block->fpf & FPF_BPBC) == FPF_BPBC;
 }
 
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)

@@ -2194,6 +2200,11 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_v
 		kvm_run->exit_reason = KVM_EXIT_INTR;
 		rc = -EINTR;
 	}
+	if ((kvm_run->kvm_dirty_regs & KVM_SYNC_BPBC) &&
+	    test_kvm_facility(vcpu->kvm, 82)) {
+		vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
+		vcpu->arch.sie_block->fpf |= kvm_run->s.regs.bpbc ? FPF_BPBC : 0;
+	}
 
 	if (guestdbg_exit_pending(vcpu) && !rc)  {
 		kvm_s390_prepare_debug_exit(vcpu);

@@ -831,6 +831,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_GUEST_DEBUG_HW_WPS 120
 #define KVM_CAP_SPLIT_IRQCHIP 121
 #define KVM_CAP_IOEVENTFD_ANY_LENGTH 122
+#define KVM_CAP_S390_BPB 152
 
 #ifdef KVM_CAP_IRQ_ROUTING
 

Something went wrong during the backport of this to 4.4

[...]

Ick, that is wrong right there, my scripts messed up, this should not have 2 author lines :(

I'll go look at all of these, odds are it made the same error everywhere...

As for the backport issues, I'll let Martin deal with those :)

thanks,

greg k-h

Yes, I've now fixed that up in the queue.

greg k-h

As this patch backport was also functionally incorrect and Martin is already away do you want me to send an updated version?

Checked my 4.4 backport git branch and indeed the hunk is misplaced. Sometime I wonder about the patch tool and the hickups it can produce.

My take on the replacement patch looks as follows:

---

From: Christian Borntraeger <[email protected]>
Date: Wed, 17 Jan 2018 14:44:34 +0100
Subject: [PATCH 03/18] KVM: s390: wire up bpb feature
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 35b3fde6203b932b2b1a5b53b3d8808abc9c4f60 ]

The new firmware interfaces for branch prediction behaviour changes are transparently available for the guest. Nevertheless, there is new state attached that should be migrated and properly resetted. Provide a mechanism for handling reset, migration and VSIE.

---
 arch/s390/include/asm/kvm_host.h |  3 ++-
 arch/s390/include/uapi/asm/kvm.h |  3 +++
 arch/s390/kvm/kvm-s390.c         | 12 ++++++++++++
 include/uapi/linux/kvm.h         |  1 +
 4 files changed, 18 insertions(+), 1 deletion(-)

index e9a983f40a24..7d9c5917da2b 100644
@@ -136,7 +136,8 @@ struct kvm_s390_sie_block {
 	__u16	ipa;			/* 0x0056 */
 	__u32	ipb;			/* 0x0058 */
 	__u32	scaoh;			/* 0x005c */
-	__u8	reserved60;		/* 0x0060 */
+#define FPF_BPBC 	0x20
+	__u8	fpf;			/* 0x0060 */
 	__u8	ecb;			/* 0x0061 */
 	__u8    ecb2;                   /* 0x0062 */
 #define ECB3_AES 0x04

index ef1a5fcc6c66..3aec52253c04 100644
@@ -151,6 +151,7 @@ struct kvm_guest_debug_arch {
 #define KVM_SYNC_ARCH0  (1UL << 4)
 #define KVM_SYNC_PFAULT (1UL << 5)
 #define KVM_SYNC_VRS    (1UL << 6)
+#define KVM_SYNC_BPBC	(1UL << 10)
 /* definition of registers in kvm_run */
 struct kvm_sync_regs {
 	__u64 prefix;	/* prefix register */

@@ -168,6 +169,8 @@ struct kvm_sync_regs {
 	__u64 vrs[32][2];	/* vector registers */
 	__u8  reserved[512];	/* for future vector expansion */
 	__u32 fpc;	/* only valid with vector registers */
+	__u8 bpbc : 1;		/* bp mode */
+	__u8 reserved2 : 7;
 };
 
 #define KVM_REG_S390_TODPR	(KVM_REG_S390 | KVM_REG_SIZE_U32 | 0x1)

index 23e3f5d77a24..ca03c847127a 100644
@@ -257,6 +257,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_S390_VECTOR_REGISTERS:
 		r = MACHINE_HAS_VX;
 		break;
+	case KVM_CAP_S390_BPB:
+		r = test_facility(82);
+		break;
 	default:
 		r = 0;
 	}

@@ -1262,6 +1265,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 				    KVM_SYNC_CRS |
 				    KVM_SYNC_ARCH0 |
 				    KVM_SYNC_PFAULT;
+	if (test_kvm_facility(vcpu->kvm, 82))
+		vcpu->run->kvm_valid_regs |= KVM_SYNC_BPBC;
 	if (test_kvm_facility(vcpu->kvm, 129))
 		vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS;
 

@@ -1327,6 +1332,7 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
 	current->thread.fpu.fpc = 0;
 	vcpu->arch.sie_block->gbea = 1;
 	vcpu->arch.sie_block->pp = 0;
+	vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
 	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
 	kvm_clear_async_pf_completion_queue(vcpu);
 	if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm))

@@ -2145,6 +2151,11 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		if (vcpu->arch.pfault_token == KVM_S390_PFAULT_TOKEN_INVALID)
 			kvm_clear_async_pf_completion_queue(vcpu);
 	}
+	if ((kvm_run->kvm_dirty_regs & KVM_SYNC_BPBC) &&
+	    test_kvm_facility(vcpu->kvm, 82)) {
+		vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
+		vcpu->arch.sie_block->fpf |= kvm_run->s.regs.bpbc ? FPF_BPBC : 0;
+	}
 	kvm_run->kvm_dirty_regs = 0;
 }
 

@@ -2162,6 +2173,7 @@ static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	kvm_run->s.regs.pft = vcpu->arch.pfault_token;
 	kvm_run->s.regs.pfs = vcpu->arch.pfault_select;
 	kvm_run->s.regs.pfc = vcpu->arch.pfault_compare;
+	kvm_run->s.regs.bpbc = (vcpu->arch.sie_block->fpf & FPF_BPBC) == FPF_BPBC;
 }
 
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)

index 03f3618612aa..376d0ab5b9f2 100644
@@ -831,6 +831,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_GUEST_DEBUG_HW_WPS 120
 #define KVM_CAP_SPLIT_IRQCHIP 121
 #define KVM_CAP_IOEVENTFD_ANY_LENGTH 122
+#define KVM_CAP_S390_BPB 152
 
 #ifdef KVM_CAP_IRQ_ROUTING
 

2.13.5

Martins backport and my backport looks almost identical, so you can keep mine.

From: Christian Borntraeger <[email protected]>

[ Upstream commit 35b3fde6203b932b2b1a5b53b3d8808abc9c4f60 ]

The new firmware interfaces for branch prediction behaviour changes are transparently available for the guest. Nevertheless, there is new state attached that should be migrated and properly resetted. Provide a mechanism for handling reset, migration and VSIE.

---
 arch/s390/include/asm/kvm_host.h |    3 ++-
 arch/s390/include/uapi/asm/kvm.h |    3 +++
 arch/s390/kvm/kvm-s390.c         |   13 ++++++++++++-
 include/uapi/linux/kvm.h         |    1 +
 4 files changed, 18 insertions(+), 2 deletions(-)

Index: linux/arch/s390/include/asm/kvm_host.h
===================================================================
@@ -136,7 +136,8 @@ struct kvm_s390_sie_block {
 	__u16	ipa;			/* 0x0056 */
 	__u32	ipb;			/* 0x0058 */
 	__u32	scaoh;			/* 0x005c */
-	__u8	reserved60;		/* 0x0060 */
+#define FPF_BPBC 	0x20
+	__u8	fpf;			/* 0x0060 */
 	__u8	ecb;			/* 0x0061 */
 	__u8    ecb2;                   /* 0x0062 */
 #define ECB3_AES 0x04

Index: linux/arch/s390/include/uapi/asm/kvm.h
===================================================================
@@ -151,6 +151,7 @@ struct kvm_guest_debug_arch {
 #define KVM_SYNC_ARCH0  (1UL << 4)
 #define KVM_SYNC_PFAULT (1UL << 5)
 #define KVM_SYNC_VRS    (1UL << 6)
+#define KVM_SYNC_BPBC   (1UL << 10)
 /* definition of registers in kvm_run */
 struct kvm_sync_regs {
 	__u64 prefix;	/* prefix register */

@@ -168,6 +169,8 @@ struct kvm_sync_regs {
 	__u64 vrs[32][2];	/* vector registers */
 	__u8  reserved[512];	/* for future vector expansion */
 	__u32 fpc;	/* only valid with vector registers */
+	__u8 bpbc : 1;		/* bp mode */
+	__u8 reserved2 : 7;
 };
 
 #define KVM_REG_S390_TODPR	(KVM_REG_S390 | KVM_REG_SIZE_U32 | 0x1)

Index: linux/arch/s390/kvm/kvm-s390.c
===================================================================
@@ -257,6 +257,9 @@ int kvm_vm_ioctl_check_extension(struct
 	case KVM_CAP_S390_VECTOR_REGISTERS:
 		r = MACHINE_HAS_VX;
 		break;
+	case KVM_CAP_S390_BPB:
+		r = test_facility(82);
+		break;
 	default:
 		r = 0;
 	}

@@ -1264,6 +1267,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *
 				    KVM_SYNC_PFAULT;
 	if (test_kvm_facility(vcpu->kvm, 129))
 		vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS;
+	if (test_kvm_facility(vcpu->kvm, 82))
+		vcpu->run->kvm_valid_regs |= KVM_SYNC_BPBC;
 
 	if (kvm_is_ucontrol(vcpu->kvm))
 		return __kvm_ucontrol_vcpu_init(vcpu);

@@ -1327,6 +1332,7 @@ static void kvm_s390_vcpu_initial_reset(
 	current->thread.fpu.fpc = 0;
 	vcpu->arch.sie_block->gbea = 1;
 	vcpu->arch.sie_block->pp = 0;
+	vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
 	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
 	kvm_clear_async_pf_completion_queue(vcpu);
 	if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm))

@@ -2145,6 +2151,11 @@ static void sync_regs(struct kvm_vcpu *v
 		if (vcpu->arch.pfault_token == KVM_S390_PFAULT_TOKEN_INVALID)
 			kvm_clear_async_pf_completion_queue(vcpu);
 	}
+	if ((kvm_run->kvm_dirty_regs & KVM_SYNC_BPBC) &&
+	    test_kvm_facility(vcpu->kvm, 82)) {
+		vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
+		vcpu->arch.sie_block->fpf |= kvm_run->s.regs.bpbc ? FPF_BPBC : 0;
+	}
 	kvm_run->kvm_dirty_regs = 0;
 }
 

@@ -2162,6 +2173,7 @@ static void store_regs(struct kvm_vcpu *
 	kvm_run->s.regs.pft = vcpu->arch.pfault_token;
 	kvm_run->s.regs.pfs = vcpu->arch.pfault_select;
 	kvm_run->s.regs.pfc = vcpu->arch.pfault_compare;
+	kvm_run->s.regs.bpbc = (vcpu->arch.sie_block->fpf & FPF_BPBC) == FPF_BPBC;
 }
 
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)

Index: linux/include/uapi/linux/kvm.h
===================================================================
@@ -831,6 +831,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_GUEST_DEBUG_HW_WPS 120
 #define KVM_CAP_SPLIT_IRQCHIP 121
 #define KVM_CAP_IOEVENTFD_ANY_LENGTH 122
+#define KVM_CAP_S390_BPB 152
 
 #ifdef KVM_CAP_IRQ_ROUTING
 

Thanks for this, now updated.

greg k-h

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

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

From: Martin Schwidefsky <[email protected]>

[ Upstream commit 7041d28115e91f2144f811ffe8a195c696b1e1d0 ]

Clear all user space registers on entry to the kernel and all KVM guest registers on KVM guest exit if the register does not contain either a parameter or a result value.

---
 arch/s390/kernel/entry.S |   47 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 47 insertions(+)

@@ -244,6 +244,12 @@ ENTRY(sie64a)
 sie_exit:
 	lg	%r14,__SF_EMPTY+8(%r15)		# load guest register save area
 	stmg	%r0,%r13,0(%r14)		# save guest gprs 0-13
+	xgr	%r0,%r0				# clear guest registers to
+	xgr	%r1,%r1				# prevent speculative use
+	xgr	%r2,%r2
+	xgr	%r3,%r3
+	xgr	%r4,%r4
+	xgr	%r5,%r5
 	lmg	%r6,%r14,__SF_GPRS(%r15)	# restore kernel registers
 	lg	%r2,__SF_EMPTY+16(%r15)		# return exit reason code
 	br	%r14

@@ -277,6 +283,8 @@ ENTRY(system_call)
 .Lsysc_vtime:
 	UPDATE_VTIME %r10,%r13,__LC_SYNC_ENTER_TIMER
 	stmg	%r0,%r7,__PT_R0(%r11)
+	# clear user controlled register to prevent speculative use
+	xgr	%r0,%r0
 	mvc	__PT_R8(64,%r11),__LC_SAVE_AREA_SYNC
 	mvc	__PT_PSW(16,%r11),__LC_SVC_OLD_PSW
 	mvc	__PT_INT_CODE(4,%r11),__LC_SVC_ILC

@@ -504,6 +512,15 @@ ENTRY(pgm_check_handler)
 	mvc	__THREAD_trap_tdb(256,%r14),0(%r13)
 3:	la	%r11,STACK_FRAME_OVERHEAD(%r15)
 	stmg	%r0,%r7,__PT_R0(%r11)
+	# clear user controlled registers to prevent speculative use
+	xgr	%r0,%r0
+	xgr	%r1,%r1
+	xgr	%r2,%r2
+	xgr	%r3,%r3
+	xgr	%r4,%r4
+	xgr	%r5,%r5
+	xgr	%r6,%r6
+	xgr	%r7,%r7
 	mvc	__PT_R8(64,%r11),__LC_SAVE_AREA_SYNC
 	stmg	%r8,%r9,__PT_PSW(%r11)
 	mvc	__PT_INT_CODE(4,%r11),__LC_PGM_ILC

@@ -567,6 +584,16 @@ ENTRY(io_int_handler)
 	lmg	%r8,%r9,__LC_IO_OLD_PSW
 	SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_ENTER_TIMER
 	stmg	%r0,%r7,__PT_R0(%r11)
+	# clear user controlled registers to prevent speculative use
+	xgr	%r0,%r0
+	xgr	%r1,%r1
+	xgr	%r2,%r2
+	xgr	%r3,%r3
+	xgr	%r4,%r4
+	xgr	%r5,%r5
+	xgr	%r6,%r6
+	xgr	%r7,%r7
+	xgr	%r10,%r10
 	mvc	__PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC
 	stmg	%r8,%r9,__PT_PSW(%r11)
 	mvc	__PT_INT_CODE(12,%r11),__LC_SUBCHANNEL_ID

@@ -742,6 +769,16 @@ ENTRY(ext_int_handler)
 	lmg	%r8,%r9,__LC_EXT_OLD_PSW
 	SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_ENTER_TIMER
 	stmg	%r0,%r7,__PT_R0(%r11)
+	# clear user controlled registers to prevent speculative use
+	xgr	%r0,%r0
+	xgr	%r1,%r1
+	xgr	%r2,%r2
+	xgr	%r3,%r3
+	xgr	%r4,%r4
+	xgr	%r5,%r5
+	xgr	%r6,%r6
+	xgr	%r7,%r7
+	xgr	%r10,%r10
 	mvc	__PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC
 	stmg	%r8,%r9,__PT_PSW(%r11)
 	lghi	%r1,__LC_EXT_PARAMS2

@@ -908,6 +945,16 @@ ENTRY(mcck_int_handler)
 .Lmcck_skip:
 	lghi	%r14,__LC_GPREGS_SAVE_AREA+64
 	stmg	%r0,%r7,__PT_R0(%r11)
+	# clear user controlled registers to prevent speculative use
+	xgr	%r0,%r0
+	xgr	%r1,%r1
+	xgr	%r2,%r2
+	xgr	%r3,%r3
+	xgr	%r4,%r4
+	xgr	%r5,%r5
+	xgr	%r6,%r6
+	xgr	%r7,%r7
+	xgr	%r10,%r10
 	mvc	__PT_R8(64,%r11),0(%r14)
 	stmg	%r8,%r9,__PT_PSW(%r11)
 	xc	__PT_FLAGS(8,%r11),__PT_FLAGS(%r11)

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

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

From: Martin Schwidefsky <[email protected]>

[ Upstream commit e2dd833389cc4069a96b57bdd24227b5f52288f5 ]

Add an optimized version of the array_index_mask_nospec function for s390 based on a compare and a subtract with borrow.

---
 arch/s390/include/asm/barrier.h |   24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

@@ -53,4 +53,28 @@ do {									\
 	___p1;								\
 })
 
+/**
+ * array_index_mask_nospec - generate a mask for array_idx() that is
+ * ~0UL when the bounds check succeeds and 0 otherwise
+ * @index: array element index
+ * @size: number of elements in array
+ */
+#define array_index_mask_nospec array_index_mask_nospec
+static inline unsigned long array_index_mask_nospec(unsigned long index,
+						    unsigned long size)
+{
+	unsigned long mask;
+
+	if (__builtin_constant_p(size) && size > 0) {
+		asm("	clgr	%2,%1\n"
+		    "	slbgr	%0,%0\n"
+		    :"=d" (mask) : "d" (size-1), "d" (index) :"cc");
+		return mask;
+	}
+	asm("	clgr	%1,%2\n"
+	    "	slbgr	%0,%0\n"
+	    :"=d" (mask) : "d" (size), "d" (index) :"cc");
+	return ~mask;
+}
+
 #endif /* __ASM_BARRIER_H */

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

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

From: Martin Schwidefsky <[email protected]>

[ Upstream commit cf1489984641369611556bf00c48f945c77bcf02 ]

To be able to switch off specific CPU alternatives with kernel parameters make a copy of the facility bit mask provided by STFLE and use the copy for the decision to apply an alternative.

---
 arch/s390/include/asm/facility.h |   18 ++++++++++++++++++
 arch/s390/include/asm/lowcore.h  |    3 ++-
 arch/s390/kernel/alternative.c   |    3 ++-
 arch/s390/kernel/early.c         |    3 +++
 arch/s390/kernel/setup.c         |    4 +++-
 arch/s390/kernel/smp.c           |    4 +++-
 6 files changed, 31 insertions(+), 4 deletions(-)

@@ -13,6 +13,24 @@
 
 #define MAX_FACILITY_BIT (256*8)	/* stfle_fac_list has 256 bytes */
 
+static inline void __set_facility(unsigned long nr, void *facilities)
+{
+	unsigned char *ptr = (unsigned char *) facilities;
+
+	if (nr >= MAX_FACILITY_BIT)
+		return;
+	ptr[nr >> 3] |= 0x80 >> (nr & 7);
+}
+
+static inline void __clear_facility(unsigned long nr, void *facilities)
+{
+	unsigned char *ptr = (unsigned char *) facilities;
+
+	if (nr >= MAX_FACILITY_BIT)
+		return;
+	ptr[nr >> 3] &= ~(0x80 >> (nr & 7));
+}
+
 static inline int __test_facility(unsigned long nr, void *facilities)
 {
 	unsigned char *ptr;

@@ -170,7 +170,8 @@ struct _lowcore {
 	__u8	pad_0x0e20[0x0f00-0x0e20];	/* 0x0e20 */
 
 	/* Extended facility list */
-	__u64	stfle_fac_list[32];		/* 0x0f00 */
+	__u64	stfle_fac_list[16];		/* 0x0f00 */
+	__u64	alt_stfle_fac_list[16];		/* 0x0f80 */
 	__u8	pad_0x1000[0x11b0-0x1000];	/* 0x1000 */
 
 	/* Pointer to vector register save area */

@@ -74,7 +74,8 @@ static void __init_or_module __apply_alt
 		instr = (u8 *)&a->instr_offset + a->instr_offset;
 		replacement = (u8 *)&a->repl_offset + a->repl_offset;
 
-		if (!test_facility(a->facility))
+		if (!__test_facility(a->facility,
+				     S390_lowcore.alt_stfle_fac_list))
 			continue;
 
 		if (unlikely(a->instrlen % 2 || a->replacementlen % 2)) {

@@ -279,6 +279,9 @@ static noinline __init void setup_facili
 {
 	stfle(S390_lowcore.stfle_fac_list,
 	      ARRAY_SIZE(S390_lowcore.stfle_fac_list));
+	memcpy(S390_lowcore.alt_stfle_fac_list,
+	       S390_lowcore.stfle_fac_list,
+	       sizeof(S390_lowcore.alt_stfle_fac_list));
 }
 
 static __init void detect_diag9c(void)

@@ -334,7 +334,9 @@ static void __init setup_lowcore(void)
 	lc->machine_flags = S390_lowcore.machine_flags;
 	lc->stfl_fac_list = S390_lowcore.stfl_fac_list;
 	memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list,
-	       MAX_FACILITY_BIT/8);
+	       sizeof(lc->stfle_fac_list));
+	memcpy(lc->alt_stfle_fac_list, S390_lowcore.alt_stfle_fac_list,
+	       sizeof(lc->alt_stfle_fac_list));
 	if (MACHINE_HAS_VX)
 		lc->vector_save_area_addr =
 			(unsigned long) &lc->vector_save_area;

@@ -250,7 +250,9 @@ static void pcpu_prepare_secondary(struc
 	__ctl_store(lc->cregs_save_area, 0, 15);
 	save_access_regs((unsigned int *) lc->access_regs_save_area);
 	memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list,
-	       MAX_FACILITY_BIT/8);
+	       sizeof(lc->stfle_fac_list));
+	memcpy(lc->alt_stfle_fac_list, S390_lowcore.alt_stfle_fac_list,
+	       sizeof(lc->alt_stfle_fac_list));
 }
 
 static void pcpu_attach_task(struct pcpu *pcpu, struct task_struct *tsk)

...

js
suse labs

IOW, we should include this 4.12-commit in 4.4 too:
commit 6f5165e864d240d15675cc2fb5a369d57e1f60d0

Author: Heiko Carstens <[email protected]>
Date:   Mon Mar 20 14:29:50 2017 +0100

s390/facilites: use stfle_fac_list array size for MAX_FACILITY_BIT

thanks,

js
suse labs

I'm going to defer to Marin here, as he did the backport... Martin?

thanks,

greg k-h

Good catch. With MAX_FACILITY_BIT == 2048 and the patch applied the result for a test_facility/__test_facility call with a facility number >= 1024 would give an incorrect result. Fortunately there are no such calls in the current 4.4 kernel source. And there are no facilities defined with bit numbers this large, so even out-of-tree code would not do this if it is sane.

To correct this the MAX_FACILITY_BIT define needs to be reduced to 1024 which would require the patch pointed out be Heiko:

commit 6f5165e864d240d15675cc2fb5a369d57e1f60d0

Author: Heiko Carstens <[email protected]>
Date:   Mon Mar 20 14:29:50 2017 +0100

s390/facilites: use stfle_fac_list array size for MAX_FACILITY_BIT

I would say yes, it *does* make sense to include this patch even if it does not fix anything.

blue skies,
   Martin.

"Reality continues to ruin my life." - Calvin.

Ok, I've now queued this up for 4.4.y and 4.9.y, thanks!

greg k-h

It breaks the build on 4.4.y, so I'm dropping it :(

If you think it's needed there, a working version would be nice :)

thanks,

greg k-h

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

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

From: Martin Schwidefsky <[email protected]>

[ Upstream commit d768bd892fc8f066cd3aa000eb1867bcf32db0ee ]

Add the PPA instruction to the system entry and exit path to switch the kernel to a different branch prediction behaviour. The instructions are added via CPU alternatives and can be disabled with the "nospec" or the "nobp=0" kernel parameter. If the default behaviour selected with CONFIG_KERNEL_NOBP is set to "n" then the "nobp=1" parameter can be used to enable the changed kernel branch prediction.

---
 arch/s390/Kconfig                 |   17 +++++++++++++
 arch/s390/include/asm/processor.h |    1 
 arch/s390/kernel/alternative.c    |   23 ++++++++++++++++++
 arch/s390/kernel/early.c          |    2 +
 arch/s390/kernel/entry.S          |   48 ++++++++++++++++++++++++++++++++++++++
 arch/s390/kernel/ipl.c            |    1 
 arch/s390/kernel/smp.c            |    2 +
 7 files changed, 94 insertions(+)

@@ -705,6 +705,23 @@ config SECCOMP
 
 	  If unsure, say Y.
 
+config KERNEL_NOBP
+	def_bool n
+	prompt "Enable modified branch prediction for the kernel by default"
+	help
+	  If this option is selected the kernel will switch to a modified
+	  branch prediction mode if the firmware interface is available.
+	  The modified branch prediction mode improves the behaviour in
+	  regard to speculative execution.
+
+	  With the option enabled the kernel parameter "nobp=0" or "nospec"
+	  can be used to run the kernel in the normal branch prediction mode.
+
+	  With the option disabled the modified branch prediction mode is
+	  enabled with the "nobp=1" kernel parameter.
+
+	  If unsure, say N.
+
 endmenu
 
 menu "Power Management"

@@ -69,6 +69,7 @@ extern void s390_adjust_jiffies(void);
 extern const struct seq_operations cpuinfo_op;
 extern int sysctl_ieee_emulation_warnings;
 extern void execve_tail(void);
+extern void __bpon(void);
 
 /*
  * User space process size: 2GB for 31 bit, 4TB or 8PT for 64 bit.

@@ -14,6 +14,29 @@ static int __init disable_alternative_in
 
 early_param("noaltinstr", disable_alternative_instructions);
 
+static int __init nobp_setup_early(char *str)
+{
+	bool enabled;
+	int rc;
+
+	rc = kstrtobool(str, &enabled);
+	if (rc)
+		return rc;
+	if (enabled && test_facility(82))
+		__set_facility(82, S390_lowcore.alt_stfle_fac_list);
+	else
+		__clear_facility(82, S390_lowcore.alt_stfle_fac_list);
+	return 0;
+}
+early_param("nobp", nobp_setup_early);
+
+static int __init nospec_setup_early(char *str)
+{
+	__clear_facility(82, S390_lowcore.alt_stfle_fac_list);
+	return 0;
+}
+early_param("nospec", nospec_setup_early);
+
 struct brcl_insn {
 	u16 opc;
 	s32 disp;

@@ -282,6 +282,8 @@ static noinline __init void setup_facili
 	memcpy(S390_lowcore.alt_stfle_fac_list,
 	       S390_lowcore.stfle_fac_list,
 	       sizeof(S390_lowcore.alt_stfle_fac_list));
+	if (!IS_ENABLED(CONFIG_KERNEL_NOBP))
+		__clear_facility(82, S390_lowcore.alt_stfle_fac_list);
 }
 
 static __init void detect_diag9c(void)

@@ -563,6 +563,7 @@ static struct kset *ipl_kset;
 
 static void __ipl_run(void *unused)
 {
+	__bpon();
 	diag308(DIAG308_IPL, NULL);
 	if (MACHINE_IS_VM)
 		__cpcmd("IPL", NULL, 0, NULL);

@@ -301,6 +301,7 @@ static void pcpu_delegate(struct pcpu *p
 	mem_assign_absolute(lc->restart_fn, (unsigned long) func);
 	mem_assign_absolute(lc->restart_data, (unsigned long) data);
 	mem_assign_absolute(lc->restart_source, source_cpu);
+	__bpon();
 	asm volatile(
 		"0:	sigp	0,%0,%2	# sigp restart to target cpu\n"
 		"	brc	2,0b	# busy, try again\n"

@@ -890,6 +891,7 @@ void __cpu_die(unsigned int cpu)
 void __noreturn cpu_die(void)
 {
 	idle_task_exit();
+	__bpon();
 	pcpu_sigp_retry(pcpu_devices + smp_processor_id(), SIGP_STOP, 0);
 	for (;;) ;
 }

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

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

From: Martin Schwidefsky <[email protected]>

[ Upstream commit 6b73044b2b0081ee3dd1cd6eaab7dee552601efb ]

Define TIF_ISOLATE_BP and TIF_ISOLATE_BP_GUEST and add the necessary plumbing in entry.S to be able to run user space and KVM guests with limited branch prediction.

To switch a user space process to limited branch prediction the s390_isolate_bp() function has to be call, and to run a vCPU of a KVM guest associated with the current task with limited branch prediction call s390_isolate_bp_guest().

---
 arch/s390/include/asm/processor.h   |    3 ++
 arch/s390/include/asm/thread_info.h |    4 ++
 arch/s390/kernel/entry.S            |   49 +++++++++++++++++++++++++++++++++---
 arch/s390/kernel/processor.c        |   18 +++++++++++++
 4 files changed, 70 insertions(+), 4 deletions(-)

@@ -316,6 +316,9 @@ extern void memcpy_absolute(void *, void
 	memcpy_absolute(&(dest), &__tmp, sizeof(__tmp));	\
 }
 
+extern int s390_isolate_bp(void);
+extern int s390_isolate_bp_guest(void);
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* __ASM_S390_PROCESSOR_H */

@@ -78,6 +78,8 @@ void arch_release_task_struct(struct tas
 #define TIF_SECCOMP		5	/* secure computing */
 #define TIF_SYSCALL_TRACEPOINT	6	/* syscall tracepoint instrumentation */
 #define TIF_UPROBE		7	/* breakpointed or single-stepping */
+#define TIF_ISOLATE_BP		8	/* Run process with isolated BP */
+#define TIF_ISOLATE_BP_GUEST	9	/* Run KVM guests with isolated BP */
 #define TIF_31BIT		16	/* 32bit process */
 #define TIF_MEMDIE		17	/* is terminating due to OOM killer */
 #define TIF_RESTORE_SIGMASK	18	/* restore signal mask in do_signal() */

@@ -93,6 +95,8 @@ void arch_release_task_struct(struct tas
 #define _TIF_SECCOMP		_BITUL(TIF_SECCOMP)
 #define _TIF_SYSCALL_TRACEPOINT	_BITUL(TIF_SYSCALL_TRACEPOINT)
 #define _TIF_UPROBE		_BITUL(TIF_UPROBE)
+#define _TIF_ISOLATE_BP		_BITUL(TIF_ISOLATE_BP)
+#define _TIF_ISOLATE_BP_GUEST	_BITUL(TIF_ISOLATE_BP_GUEST)
 #define _TIF_31BIT		_BITUL(TIF_31BIT)
 #define _TIF_SINGLE_STEP	_BITUL(TIF_SINGLE_STEP)
 

@@ -13,6 +13,7 @@
 #include <linux/cpu.h>
 #include <asm/diag.h>
 #include <asm/elf.h>
+#include <asm/facility.h>
 #include <asm/lowcore.h>
 #include <asm/param.h>
 #include <asm/smp.h>

@@ -113,3 +114,20 @@ const struct seq_operations cpuinfo_op =
 	.show	= show_cpuinfo,
 };
 
+int s390_isolate_bp(void)
+{
+	if (!test_facility(82))
+		return -EOPNOTSUPP;
+	set_thread_flag(TIF_ISOLATE_BP);
+	return 0;
+}
+EXPORT_SYMBOL(s390_isolate_bp);
+
+int s390_isolate_bp_guest(void)
+{
+	if (!test_facility(82))
+		return -EOPNOTSUPP;
+	set_thread_flag(TIF_ISOLATE_BP_GUEST);
+	return 0;
+}
+EXPORT_SYMBOL(s390_isolate_bp_guest);

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

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

From: Martin Schwidefsky <[email protected]>

[ Upstream commit f19fbd5ed642dc31c809596412dab1ed56f2f156 ]

Add CONFIG_EXPOLINE to enable the use of the new -mindirect-branch= and -mfunction_return= compiler options to create a kernel fortified against the specte v2 attack.

With CONFIG_EXPOLINE=y all indirect branches will be issued with an execute type instruction. For z10 or newer the EXRL instruction will be used, for older machines the EX instruction. The typical indirect call

	basr	%r14,%r1

is replaced with a PC relative call to a new thunk

	brasl	%r14,__s390x_indirect_jump_r1

The thunk contains the EXRL/EX instruction to the indirect branch

__s390x_indirect_jump_r1:

	exrl	0,0f
	j	.

0: br %r1

The detour via the execute type instruction has a performance impact. To get rid of the detour the new kernel parameter "nospectre_v2" and "spectre_v2=[on,off,auto]" can be used. If the parameter is specified the kernel and module code will be patched at runtime.

---
 arch/s390/Kconfig                     |   28 ++++++++
 arch/s390/Makefile                    |   10 +++
 arch/s390/include/asm/lowcore.h       |    4 -
 arch/s390/include/asm/nospec-branch.h |   18 +++++
 arch/s390/kernel/Makefile             |    3 
 arch/s390/kernel/entry.S              |  113 ++++++++++++++++++++++++++--------
 arch/s390/kernel/module.c             |   62 +++++++++++++++---
 arch/s390/kernel/nospec-branch.c      |  101 ++++++++++++++++++++++++++++++
 arch/s390/kernel/setup.c              |    4 +
 arch/s390/kernel/smp.c                |    1 
 arch/s390/kernel/vmlinux.lds.S        |   14 ++++
 drivers/s390/char/Makefile            |    2 
 12 files changed, 325 insertions(+), 35 deletions(-)
 create mode 100644 arch/s390/include/asm/nospec-branch.h
 create mode 100644 arch/s390/kernel/nospec-branch.c

@@ -722,6 +722,34 @@ config KERNEL_NOBP
 
 	  If unsure, say N.
 
+config EXPOLINE
+	def_bool n
+	prompt "Avoid speculative indirect branches in the kernel"
+	help
+	  Compile the kernel with the expoline compiler options to guard
+	  against kernel-to-user data leaks by avoiding speculative indirect
+	  branches.
+	  Requires a compiler with -mindirect-branch=thunk support for full
+	  protection. The kernel may run slower.
+
+	  If unsure, say N.
+
+choice
+	prompt "Expoline default"
+	depends on EXPOLINE
+	default EXPOLINE_FULL
+
+config EXPOLINE_OFF
+	bool "spectre_v2=off"
+
+config EXPOLINE_MEDIUM
+	bool "spectre_v2=auto"
+
+config EXPOLINE_FULL
+	bool "spectre_v2=on"
+
+endchoice
+
 endmenu
 
 menu "Power Management"

@@ -77,6 +77,16 @@ ifeq ($(call cc-option-yn,-mwarn-dynamic
 cflags-$(CONFIG_WARN_DYNAMIC_STACK) += -mwarn-dynamicstack
 endif
 
+ifdef CONFIG_EXPOLINE
+  ifeq ($(call cc-option-yn,$(CC_FLAGS_MARCH) -mindirect-branch=thunk),y)
+    CC_FLAGS_EXPOLINE := -mindirect-branch=thunk
+    CC_FLAGS_EXPOLINE += -mfunction-return=thunk
+    CC_FLAGS_EXPOLINE += -mindirect-branch-table
+    export CC_FLAGS_EXPOLINE
+    cflags-y += $(CC_FLAGS_EXPOLINE)
+  endif
+endif
+
 ifdef CONFIG_FUNCTION_TRACER
 # make use of hotpatch feature if the compiler supports it
 cc_hotpatch	:= -mhotpatch=0,3

@@ -155,7 +155,9 @@ struct _lowcore {
 	/* Per cpu primary space access list */
 	__u32	paste[16];			/* 0x0400 */
 
-	__u8	pad_0x04c0[0x0e00-0x0440];	/* 0x0440 */
+	/* br %r1 trampoline */
+	__u16	br_r1_trampoline;		/* 0x0440 */
+	__u8	pad_0x0442[0x0e00-0x0442];	/* 0x0442 */
 
 	/*
 	 * 0xe00 contains the address of the IPL Parameter Information

@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_S390_EXPOLINE_H
+#define _ASM_S390_EXPOLINE_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+
+extern int nospec_call_disable;
+extern int nospec_return_disable;
+
+void nospec_init_branches(void);
+void nospec_call_revert(s32 *start, s32 *end);
+void nospec_return_revert(s32 *start, s32 *end);
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_S390_EXPOLINE_H */

@@ -48,6 +48,9 @@ obj-y	+= entry.o reipl.o relocate_kernel
 
 extra-y				+= head.o head64.o vmlinux.lds
 
+obj-$(CONFIG_EXPOLINE)		+= nospec-branch.o
+CFLAGS_REMOVE_expoline.o	+= $(CC_FLAGS_EXPOLINE)
+
 obj-$(CONFIG_MODULES)		+= s390_ksyms.o module.o
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_SCHED_BOOK)	+= topology.o

@@ -64,6 +64,7 @@
 #include <asm/sysinfo.h>
 #include <asm/numa.h>
 #include <asm/alternative.h>
+#include <asm/nospec-branch.h>
 #include "entry.h"
 
 /*

@@ -373,6 +374,7 @@ static void __init setup_lowcore(void)
 #ifdef CONFIG_SMP
 	lc->spinlock_lockval = arch_spin_lockval(0);
 #endif
+	lc->br_r1_trampoline = 0x07f1;	/* br %r1 */
 
 	set_prefix((u32)(unsigned long) lc);
 	lowcore_ptr[0] = lc;

@@ -897,6 +899,8 @@ void __init setup_arch(char **cmdline_p)
 	set_preferred_console();
 
 	apply_alternative_instructions();
+	if (IS_ENABLED(CONFIG_EXPOLINE))
+		nospec_init_branches();
 
 	/* Setup zfcpdump support */
 	setup_zfcpdump();

@@ -200,6 +200,7 @@ static int pcpu_alloc_lowcore(struct pcp
 	lc->panic_stack = panic_stack + PANIC_FRAME_OFFSET;
 	lc->cpu_nr = cpu;
 	lc->spinlock_lockval = arch_spin_lockval(cpu);
+	lc->br_r1_trampoline = 0x07f1;	/* br %r1 */
 	if (MACHINE_HAS_VX)
 		lc->vector_save_area_addr =
 			(unsigned long) &lc->vector_save_area;

@@ -101,6 +101,20 @@ SECTIONS
 		*(.altinstr_replacement)
 	}
 
+	/*
+	 * Table with the patch locations to undo expolines
+	*/
+	.nospec_call_table : {
+		__nospec_call_start = . ;
+		*(.s390_indirect*)
+		__nospec_call_end = . ;
+	}
+	.nospec_return_table : {
+		__nospec_return_start = . ;
+		*(.s390_return*)
+		__nospec_return_end = . ;
+	}
+
 	/* early.c uses stsi, which requires page aligned data. */
 	. = ALIGN(PAGE_SIZE);
 	INIT_DATA_SECTION(0x100)

@@ -2,6 +2,8 @@
 # S/390 character devices
 #
 
+CFLAGS_REMOVE_sclp_early_core.o	+= $(CC_FLAGS_EXPOLINE)
+
 obj-y += ctrlchar.o keyboard.o defkeymap.o sclp.o sclp_rw.o sclp_quiesce.o \
 	 sclp_cmd.o sclp_config.o sclp_cpi_sys.o sclp_ocf.o sclp_ctl.o \
 	 sclp_early.o

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

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

From: Martin Schwidefsky <[email protected]>

From: Eugeniu Rosca <[email protected]>

[ Upstream commit 2cb370d615e9fbed9e95ed222c2c8f337181aa90 ]

I've accidentally stumbled upon the IS_ENABLED(EXPOLINE_*) lines, which obviously always evaluate to false. Fix this.

---
 arch/s390/kernel/nospec-branch.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -3,8 +3,8 @@
 #include <asm/facility.h>
 #include <asm/nospec-branch.h>
 
-int nospec_call_disable = IS_ENABLED(EXPOLINE_OFF);
-int nospec_return_disable = !IS_ENABLED(EXPOLINE_FULL);
+int nospec_call_disable = IS_ENABLED(CONFIG_EXPOLINE_OFF);
+int nospec_return_disable = !IS_ENABLED(CONFIG_EXPOLINE_FULL);
 
 static int __init nospectre_v2_setup_early(char *str)
 {

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

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

From: Martin Schwidefsky <[email protected]>

[ Upstream commit d5feec04fe578c8dbd9e2e1439afc2f0af761ed4 ]

The system call path can be interrupted before the switch back to the standard branch prediction with BPENTER has been done. The critical section cleanup code skips forward to .Lsysc_do_svc and bypasses the BPENTER. In this case the kernel and all subsequent code will run with the limited branch prediction.

---
 arch/s390/kernel/entry.S |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -1299,7 +1299,8 @@ cleanup_critical:
 	srag	%r9,%r9,23
 	jz	0f
 	mvc	__TI_last_break(8,%r12),16(%r11)
-0:	# set up saved register r11
+0:	BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP
+	# set up saved register r11
 	lg	%r15,__LC_KERNEL_STACK
 	la	%r9,STACK_FRAME_OVERHEAD(%r15)
 	stg	%r9,24(%r11)		# r11 pt_regs pointer

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

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

From: Martin Schwidefsky <[email protected]>

From: Christian Borntraeger <[email protected]>

[ Upstream commit d3f468963cd6fd6d2aa5e26aed8b24232096d0e1 ]

when a system call is interrupted we might call the critical section cleanup handler that re-does some of the operations. When we are between .Lsysc_vtime and .Lsysc_do_svc we might also redo the saving of the problem state registers r0-r7:

.Lcleanup_system_call:
[...]
0: # update accounting time stamp

        mvc     __LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER
        # set up saved register r11
        lg      %r15,__LC_KERNEL_STACK
        la      %r9,STACK_FRAME_OVERHEAD(%r15)
        stg     %r9,24(%r11)            # r11 pt_regs pointer
        # fill pt_regs
        mvc     __PT_R8(64,%r9),__LC_SAVE_AREA_SYNC

---> stmg %r0,%r7,__PT_R0(%r9)

The problem is now, that we might have already zeroed out r0. The fix is to move the zeroing of r0 after sysc_do_svc.

---
 arch/s390/kernel/entry.S |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -421,13 +421,13 @@ ENTRY(system_call)
 	UPDATE_VTIME %r10,%r13,__LC_SYNC_ENTER_TIMER
 	BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP
 	stmg	%r0,%r7,__PT_R0(%r11)
-	# clear user controlled register to prevent speculative use
-	xgr	%r0,%r0
 	mvc	__PT_R8(64,%r11),__LC_SAVE_AREA_SYNC
 	mvc	__PT_PSW(16,%r11),__LC_SVC_OLD_PSW
 	mvc	__PT_INT_CODE(4,%r11),__LC_SVC_ILC
 	stg	%r14,__PT_FLAGS(%r11)
 .Lsysc_do_svc:
+	# clear user controlled register to prevent speculative use
+	xgr	%r0,%r0
 	lg	%r10,__TI_sysc_table(%r12)	# address of system call table
 	llgh	%r8,__PT_INT_CODE+2(%r11)
 	slag	%r8,%r8,2			# shift and test for svc 0

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

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

From: Martin Schwidefsky <[email protected]>

[ Upstream commit b2e2f43a01bace1a25bdbae04c9f9846882b727a ]

Keep the code for the nobp parameter handling with the code for expolines. Both are related to the spectre v2 mitigation.

---
 arch/s390/kernel/Makefile        |    4 ++--
 arch/s390/kernel/alternative.c   |   23 -----------------------
 arch/s390/kernel/nospec-branch.c |   27 +++++++++++++++++++++++++++
 3 files changed, 29 insertions(+), 25 deletions(-)

@@ -45,11 +45,11 @@ obj-y	+= debug.o irq.o ipl.o dis.o diag.
 obj-y	+= sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o pgm_check.o
 obj-y	+= runtime_instr.o cache.o dumpstack.o
 obj-y	+= entry.o reipl.o relocate_kernel.o alternative.o
+obj-y	+= nospec-branch.o
 
 extra-y				+= head.o head64.o vmlinux.lds
 
-obj-$(CONFIG_EXPOLINE)		+= nospec-branch.o
-CFLAGS_REMOVE_expoline.o	+= $(CC_FLAGS_EXPOLINE)
+CFLAGS_REMOVE_nospec-branch.o	+= $(CC_FLAGS_EXPOLINE)
 
 obj-$(CONFIG_MODULES)		+= s390_ksyms.o module.o
 obj-$(CONFIG_SMP)		+= smp.o

@@ -14,29 +14,6 @@ static int __init disable_alternative_in
 
 early_param("noaltinstr", disable_alternative_instructions);
 
-static int __init nobp_setup_early(char *str)
-{
-	bool enabled;
-	int rc;
-
-	rc = kstrtobool(str, &enabled);
-	if (rc)
-		return rc;
-	if (enabled && test_facility(82))
-		__set_facility(82, S390_lowcore.alt_stfle_fac_list);
-	else
-		__clear_facility(82, S390_lowcore.alt_stfle_fac_list);
-	return 0;
-}
-early_param("nobp", nobp_setup_early);
-
-static int __init nospec_setup_early(char *str)
-{
-	__clear_facility(82, S390_lowcore.alt_stfle_fac_list);
-	return 0;
-}
-early_param("nospec", nospec_setup_early);
-
 struct brcl_insn {
 	u16 opc;
 	s32 disp;

@@ -3,6 +3,31 @@
 #include <asm/facility.h>
 #include <asm/nospec-branch.h>
 
+static int __init nobp_setup_early(char *str)
+{
+	bool enabled;
+	int rc;
+
+	rc = kstrtobool(str, &enabled);
+	if (rc)
+		return rc;
+	if (enabled && test_facility(82))
+		__set_facility(82, S390_lowcore.alt_stfle_fac_list);
+	else
+		__clear_facility(82, S390_lowcore.alt_stfle_fac_list);
+	return 0;
+}
+early_param("nobp", nobp_setup_early);
+
+static int __init nospec_setup_early(char *str)
+{
+	__clear_facility(82, S390_lowcore.alt_stfle_fac_list);
+	return 0;
+}
+early_param("nospec", nospec_setup_early);
+
+#ifdef CONFIG_EXPOLINE
+
 int nospec_call_disable = IS_ENABLED(CONFIG_EXPOLINE_OFF);
 int nospec_return_disable = !IS_ENABLED(CONFIG_EXPOLINE_FULL);
 

@@ -99,3 +124,5 @@ void __init nospec_init_branches(void)
 	nospec_call_revert(__nospec_call_start, __nospec_call_end);
 	nospec_return_revert(__nospec_return_start, __nospec_return_end);
 }
+
+#endif /* CONFIG_EXPOLINE */

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

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

From: Martin Schwidefsky <[email protected]>

[ Upstream commit 6e179d64126b909f0b288fa63cdbf07c531e9b1d ]

Automatically decide between nobp vs. expolines if the spectre_v2=auto kernel parameter is specified or CONFIG_EXPOLINE_AUTO=y is set.

The decision made at boot time due to CONFIG_EXPOLINE_AUTO=y being set can be overruled with the nobp, nospec and spectre_v2 kernel parameters.

---
 arch/s390/Kconfig                     |    2 -
 arch/s390/Makefile                    |    2 -
 arch/s390/include/asm/nospec-branch.h |    6 +--
 arch/s390/kernel/alternative.c        |    1 
 arch/s390/kernel/module.c             |   11 ++---
 arch/s390/kernel/nospec-branch.c      |   68 +++++++++++++++++++++-------------
 6 files changed, 52 insertions(+), 38 deletions(-)

@@ -742,7 +742,7 @@ choice
 config EXPOLINE_OFF
 	bool "spectre_v2=off"
 
-config EXPOLINE_MEDIUM
+config EXPOLINE_AUTO
 	bool "spectre_v2=auto"
 
 config EXPOLINE_FULL

@@ -83,7 +83,7 @@ ifdef CONFIG_EXPOLINE
     CC_FLAGS_EXPOLINE += -mfunction-return=thunk
     CC_FLAGS_EXPOLINE += -mindirect-branch-table
     export CC_FLAGS_EXPOLINE
-    cflags-y += $(CC_FLAGS_EXPOLINE)
+    cflags-y += $(CC_FLAGS_EXPOLINE) -DCC_USING_EXPOLINE
   endif
 endif
 

@@ -6,12 +6,10 @@
 
 #include <linux/types.h>
 
-extern int nospec_call_disable;
-extern int nospec_return_disable;
+extern int nospec_disable;
 
 void nospec_init_branches(void);
-void nospec_call_revert(s32 *start, s32 *end);
-void nospec_return_revert(s32 *start, s32 *end);
+void nospec_revert(s32 *start, s32 *end);
 
 #endif /* __ASSEMBLY__ */
 

@@ -1,6 +1,7 @@
 #include <linux/module.h>
 #include <asm/alternative.h>
 #include <asm/facility.h>
+#include <asm/nospec-branch.h>
 
 #define MAX_PATCH_LEN (255 - 1)
 

@@ -167,7 +167,7 @@ int module_frob_arch_sections(Elf_Ehdr *
 	me->core_size += me->arch.got_size;
 	me->arch.plt_offset = me->core_size;
 	if (me->arch.plt_size) {
-		if (IS_ENABLED(CONFIG_EXPOLINE) && !nospec_call_disable)
+		if (IS_ENABLED(CONFIG_EXPOLINE) && !nospec_disable)
 			me->arch.plt_size += PLT_ENTRY_SIZE;
 		me->core_size += me->arch.plt_size;
 	}

@@ -326,8 +326,7 @@ static int apply_rela(Elf_Rela *rela, El
 				info->plt_offset;
 			ip[0] = 0x0d10e310;	/* basr 1,0  */
 			ip[1] = 0x100a0004;	/* lg	1,10(1) */
-			if (IS_ENABLED(CONFIG_EXPOLINE) &&
-			    !nospec_call_disable) {
+			if (IS_ENABLED(CONFIG_EXPOLINE) && !nospec_disable) {
 				unsigned int *ij;
 				ij = me->module_core +
 					me->arch.plt_offset +

@@ -448,7 +447,7 @@ int module_finalize(const Elf_Ehdr *hdr,
 	void *aseg;
 
 	if (IS_ENABLED(CONFIG_EXPOLINE) &&
-	    !nospec_call_disable && me->arch.plt_size) {
+	    !nospec_disable && me->arch.plt_size) {
 		unsigned int *ij;
 
 		ij = me->module_core + me->arch.plt_offset +

@@ -475,11 +474,11 @@ int module_finalize(const Elf_Ehdr *hdr,
 
 		if (IS_ENABLED(CONFIG_EXPOLINE) &&
 		    (!strcmp(".nospec_call_table", secname)))
-			nospec_call_revert(aseg, aseg + s->sh_size);
+			nospec_revert(aseg, aseg + s->sh_size);
 
 		if (IS_ENABLED(CONFIG_EXPOLINE) &&
 		    (!strcmp(".nospec_return_table", secname)))
-			nospec_return_revert(aseg, aseg + s->sh_size);
+			nospec_revert(aseg, aseg + s->sh_size);
 	}
 
 	jump_label_apply_nops(me);

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

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

From: Martin Schwidefsky <[email protected]>

[ Upstream commit bc035599718412cfba9249aa713f90ef13f13ee9 ]

Add a boot message if either of the spectre defenses is active. The message is
"Spectre V2 mitigation: execute trampolines."
or "Spectre V2 mitigation: limited branch prediction."

---
 arch/s390/kernel/nospec-branch.c |   10 ++++++++++
 1 file changed, 10 insertions(+)

@@ -33,6 +33,16 @@ static int __init nospec_setup_early(cha
 }
 early_param("nospec", nospec_setup_early);
 
+static int __init nospec_report(void)
+{
+	if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable)
+		pr_info("Spectre V2 mitigation: execute trampolines.\n");
+	if (__test_facility(82, S390_lowcore.alt_stfle_fac_list))
+		pr_info("Spectre V2 mitigation: limited branch prediction.\n");
+	return 0;
+}
+arch_initcall(nospec_report);
+
 #ifdef CONFIG_EXPOLINE
 
 int nospec_disable = IS_ENABLED(CONFIG_EXPOLINE_OFF);

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

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

From: Martin Schwidefsky <[email protected]>

[ Upstream commit d424986f1d6b16079b3231db0314923f4f8deed1 ]

Set CONFIG_GENERIC_CPU_VULNERABILITIES and provide the two functions cpu_show_spectre_v1 and cpu_show_spectre_v2 to report the spectre mitigations.

---
 arch/s390/Kconfig                |    1 +
 arch/s390/kernel/nospec-branch.c |   19 +++++++++++++++++++
 2 files changed, 20 insertions(+)

@@ -111,6 +111,7 @@ config S390
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CPU_AUTOPROBE
 	select GENERIC_CPU_DEVICES if !SMP
+	select GENERIC_CPU_VULNERABILITIES
 	select GENERIC_FIND_FIRST_BIT
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_TIME_VSYSCALL

@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/module.h>
+#include <linux/device.h>
 #include <asm/facility.h>
 #include <asm/nospec-branch.h>
 

@@ -43,6 +44,24 @@ static int __init nospec_report(void)
 }
 arch_initcall(nospec_report);
 
+#ifdef CONFIG_SYSFS
+ssize_t cpu_show_spectre_v1(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "Mitigation: __user pointer sanitization\n");
+}
+
+ssize_t cpu_show_spectre_v2(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable)
+		return sprintf(buf, "Mitigation: execute trampolines\n");
+	if (__test_facility(82, S390_lowcore.alt_stfle_fac_list))
+		return sprintf(buf, "Mitigation: limited branch prediction.\n");
+	return sprintf(buf, "Vulnerable\n");
+}
+#endif
+
 #ifdef CONFIG_EXPOLINE
 
 int nospec_disable = IS_ENABLED(CONFIG_EXPOLINE_OFF);

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

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

From: Martin Schwidefsky <[email protected]>

[ Upstream commit 6a3d1e81a434fc311f224b8be77258bafc18ccc6 ]

With CONFIG_EXPOLINE_AUTO=y the call of spectre_v2_auto_early() via early_initcall is done *after* the early_param functions. This overwrites any settings done with the nobp/no_spectre_v2/spectre_v2 parameters. The code patching for the kernel is done after the evaluation of the early parameters but before the early_initcall is done. The end result is a kernel image that is patched correctly but the kernel modules are not.

Make sure that the nospec auto detection function is called before the early parameters are evaluated and before the code patching is done.

---
 arch/s390/include/asm/nospec-branch.h |    1 +
 arch/s390/kernel/nospec-branch.c      |    8 ++------
 arch/s390/kernel/setup.c              |    3 +++
 3 files changed, 6 insertions(+), 6 deletions(-)

@@ -9,6 +9,7 @@
 extern int nospec_disable;
 
 void nospec_init_branches(void);
+void nospec_auto_detect(void);
 void nospec_revert(s32 *start, s32 *end);
 
 #endif /* __ASSEMBLY__ */

@@ -73,7 +73,7 @@ static int __init nospectre_v2_setup_ear
 }
 early_param("nospectre_v2", nospectre_v2_setup_early);
 
-static int __init spectre_v2_auto_early(void)
+void __init nospec_auto_detect(void)
 {
 	if (IS_ENABLED(CC_USING_EXPOLINE)) {
 		/*

@@ -88,11 +88,7 @@ static int __init spectre_v2_auto_early(
 	 * nobp setting decides what is done, this depends on the
 	 * CONFIG_KERNEL_NP option and the nobp/nospec parameters.
 	 */
-	return 0;
 }
-#ifdef CONFIG_EXPOLINE_AUTO
-early_initcall(spectre_v2_auto_early);
-#endif
 
 static int __init spectre_v2_setup_early(char *str)
 {

@@ -103,7 +99,7 @@ static int __init spectre_v2_setup_early
 	if (str && !strncmp(str, "off", 3))
 		nospec_disable = 1;
 	if (str && !strncmp(str, "auto", 4))
-		spectre_v2_auto_early();
+		nospec_auto_detect();
 	return 0;
 }
 early_param("spectre_v2", spectre_v2_setup_early);

@@ -846,6 +846,9 @@ void __init setup_arch(char **cmdline_p)
 	init_mm.end_data = (unsigned long) &_edata;
 	init_mm.brk = (unsigned long) &_end;
 
+	if (IS_ENABLED(CONFIG_EXPOLINE_AUTO))
+		nospec_auto_detect();
+
 	parse_early_param();
 	os_info_init();
 	setup_ipl();

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

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

From: Martin Schwidefsky <[email protected]>

[ Upstream commit 6cf09958f32b9667bb3ebadf74367c791112771b ]

The main linker script vmlinux.lds.S for the kernel image merges the expoline code patch tables into two section ".nospec_call_table" and ".nospec_return_table". This is *not* done for the modules, there the sections retain their original names as generated by gcc:
".s390_indirect_call", ".s390_return_mem" and ".s390_return_reg".

The module_finalize code has to check for the compiler generated section names, otherwise no code patching is done. This slows down the module code in case of "spectre_v2=off".

---
 arch/s390/kernel/module.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -473,11 +473,11 @@ int module_finalize(const Elf_Ehdr *hdr,
 			apply_alternatives(aseg, aseg + s->sh_size);
 
 		if (IS_ENABLED(CONFIG_EXPOLINE) &&
-		    (!strcmp(".nospec_call_table", secname)))
+		    (!strncmp(".s390_indirect", secname, 14)))
 			nospec_revert(aseg, aseg + s->sh_size);
 
 		if (IS_ENABLED(CONFIG_EXPOLINE) &&
-		    (!strcmp(".nospec_return_table", secname)))
+		    (!strncmp(".s390_return", secname, 12)))
 			nospec_revert(aseg, aseg + s->sh_size);
 	}
 

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

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

From: Xin Long <[email protected]>

[ Upstream commit ddea788c63094f7c483783265563dd5b50052e28 ]

After Commit 8a8efa22f51b ("bonding: sync netpoll code with bridge"), it would set slave_dev npinfo in slave_enable_netpoll when enslaving a dev if bond->dev->npinfo was set.

However now slave_dev npinfo is set with bond->dev->npinfo before calling slave_enable_netpoll. With slave_dev npinfo set, __netpoll_setup called in slave_enable_netpoll will not call slave dev's .ndo_netpoll_setup(). It causes that the lower dev of this slave dev can't set its npinfo.

One way to reproduce it:

  # modprobe bonding
  # brctl addbr br0
  # brctl addif br0 eth1
  # ifconfig bond0 192.168.122.1/24 up
  # ifenslave bond0 eth2
  # systemctl restart netconsole
  # ifenslave bond0 br0
  # ifconfig eth2 down
  # systemctl restart netconsole

The netpoll won't really work.

This patch is to remove that slave_dev npinfo setting in bond_enslave().

---
 drivers/net/bonding/bond_main.c |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

@@ -1614,8 +1614,7 @@ int bond_enslave(struct net_device *bond
 	} /* switch(bond_mode) */
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
-	slave_dev->npinfo = bond->dev->npinfo;
-	if (slave_dev->npinfo) {
+	if (bond->dev->npinfo) {
 		if (slave_enable_netpoll(new_slave)) {
 			netdev_info(bond_dev, "master_dev is using netpoll, but new slave device does not support netpoll\n");
 			res = -EBUSY;

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

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

From: Eric Biggers <[email protected]>

[ Upstream commit 9c438d7a3a52dcc2b9ed095cb87d3a5e83cf7e60 ]

Adding a dns_resolver key whose payload contains a very long option name resulted in that string being printed in full. This hit the WARN_ONCE() in set_precision() during the printk(), because printk() only supports a precision of up to 32767 bytes:

    precision 1000000 too large
    WARNING: CPU: 0 PID: 752 at lib/vsprintf.c:2189 vsnprintf+0x4bc/0x5b0

Fix it by limiting option strings (combined name + value) to a much more reasonable 128 bytes. The exact limit is arbitrary, but currently the only recognized option is formatted as "dnserror=%lu" which fits well within this limit.

Also ratelimit the printks.

Reproducer:

    perl -e 'print "#", "A" x 1000000, "\x00"' | keyctl padd dns_resolver desc @s

This bug was found using syzkaller.

---
 net/dns_resolver/dns_key.c |   13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

@@ -25,6 +25,7 @@
 #include <linux/moduleparam.h>
 #include <linux/slab.h>
 #include <linux/string.h>
+#include <linux/ratelimit.h>
 #include <linux/kernel.h>
 #include <linux/keyctl.h>
 #include <linux/err.h>

@@ -91,9 +92,9 @@ dns_resolver_preparse(struct key_prepars
 
 			next_opt = memchr(opt, '#', end - opt) ?: end;
 			opt_len = next_opt - opt;
-			if (!opt_len) {
-				printk(KERN_WARNING
-				       "Empty option to dns_resolver key\n");
+			if (opt_len <= 0 || opt_len > 128) {
+				pr_warn_ratelimited("Invalid option length (%d) for dns_resolver key\n",
+						    opt_len);
 				return -EINVAL;
 			}
 

@@ -127,10 +128,8 @@ dns_resolver_preparse(struct key_prepars
 			}
 
 		bad_option_value:
-			printk(KERN_WARNING
-			       "Option '%*.*s' to dns_resolver key:"
-			       " bad/missing value\n",
-			       opt_nlen, opt_nlen, opt);
+			pr_warn_ratelimited("Option '%*.*s' to dns_resolver key: bad/missing value\n",
+					    opt_nlen, opt_nlen, opt);
 			return -EINVAL;
 		} while (opt = next_opt + 1, opt < end);
 	}

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

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

From: Guillaume Nault <[email protected]>

[ Upstream commit eb1c28c05894a4b1f6b56c5bf072205e64cfa280 ]

Check sockaddr_len before dereferencing sp->sa_protocol, to ensure that it actually points to valid data.

---
 net/l2tp/l2tp_ppp.c |    7 +++++++
 1 file changed, 7 insertions(+)

@@ -606,6 +606,13 @@ static int pppol2tp_connect(struct socke
 	lock_sock(sk);
 
 	error = -EINVAL;
+
+	if (sockaddr_len != sizeof(struct sockaddr_pppol2tp) &&
+	    sockaddr_len != sizeof(struct sockaddr_pppol2tpv3) &&
+	    sockaddr_len != sizeof(struct sockaddr_pppol2tpin6) &&
+	    sockaddr_len != sizeof(struct sockaddr_pppol2tpv3in6))
+		goto end;
+
 	if (sp->sa_protocol != PX_PROTO_OL2TP)
 		goto end;
 

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

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

From: Eric Dumazet <[email protected]>

[ Upstream commit 7dd07c143a4b54d050e748bee4b4b9e94a7b1744 ]

Since neigh_dump_table() calls nlmsg_parse() without giving policy constraints, attributes can have arbirary size that we must validate

Reported by syzbot/KMSAN :

BUG: KMSAN: uninit-value in neigh_master_filtered net/core/neighbour.c:2292 [inline]
BUG: KMSAN: uninit-value in neigh_dump_table net/core/neighbour.c:2348 [inline]
BUG: KMSAN: uninit-value in neigh_dump_info+0x1af0/0x2250 net/core/neighbour.c:2438
CPU: 1 PID: 3575 Comm: syzkaller268891 Not tainted 4.16.0+ #83
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x185/0x1d0 lib/dump_stack.c:53
 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067
 __msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:676
 neigh_master_filtered net/core/neighbour.c:2292 [inline]
 neigh_dump_table net/core/neighbour.c:2348 [inline]
 neigh_dump_info+0x1af0/0x2250 net/core/neighbour.c:2438
 netlink_dump+0x9ad/0x1540 net/netlink/af_netlink.c:2225
 __netlink_dump_start+0x1167/0x12a0 net/netlink/af_netlink.c:2322
 netlink_dump_start include/linux/netlink.h:214 [inline]
 rtnetlink_rcv_msg+0x1435/0x1560 net/core/rtnetlink.c:4598
 netlink_rcv_skb+0x355/0x5f0 net/netlink/af_netlink.c:2447
 rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:4653
 netlink_unicast_kernel net/netlink/af_netlink.c:1311 [inline]
 netlink_unicast+0x1672/0x1750 net/netlink/af_netlink.c:1337
 netlink_sendmsg+0x1048/0x1310 net/netlink/af_netlink.c:1900
 sock_sendmsg_nosec net/socket.c:630 [inline]
 sock_sendmsg net/socket.c:640 [inline]
 ___sys_sendmsg+0xec0/0x1310 net/socket.c:2046
 __sys_sendmsg net/socket.c:2080 [inline]
 SYSC_sendmsg+0x2a3/0x3d0 net/socket.c:2091
 SyS_sendmsg+0x54/0x80 net/socket.c:2087
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2
RIP: 0033:0x43fed9
RSP: 002b:00007ffddbee2798 EFLAGS: 00000213 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 000000000043fed9
RDX: 0000000000000000 RSI: 0000000020005000 RDI: 0000000000000003
RBP: 00000000006ca018 R08: 00000000004002c8 R09: 00000000004002c8
R10: 00000000004002c8 R11: 0000000000000213 R12: 0000000000401800
R13: 0000000000401890 R14: 0000000000000000 R15: 0000000000000000

Uninit was created at:

 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline]
 kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:188
 kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:314
 kmsan_slab_alloc+0x11/0x20 mm/kmsan/kmsan.c:321
 slab_post_alloc_hook mm/slab.h:445 [inline]
 slab_alloc_node mm/slub.c:2737 [inline]
 __kmalloc_node_track_caller+0xaed/0x11c0 mm/slub.c:4369
 __kmalloc_reserve net/core/skbuff.c:138 [inline]
 __alloc_skb+0x2cf/0x9f0 net/core/skbuff.c:206
 alloc_skb include/linux/skbuff.h:984 [inline]
 netlink_alloc_large_skb net/netlink/af_netlink.c:1183 [inline]
 netlink_sendmsg+0x9a6/0x1310 net/netlink/af_netlink.c:1875
 sock_sendmsg_nosec net/socket.c:630 [inline]
 sock_sendmsg net/socket.c:640 [inline]
 ___sys_sendmsg+0xec0/0x1310 net/socket.c:2046
 __sys_sendmsg net/socket.c:2080 [inline]
 SYSC_sendmsg+0x2a3/0x3d0 net/socket.c:2091
 SyS_sendmsg+0x54/0x80 net/socket.c:2087
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2

---
 net/core/neighbour.c |   12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

@@ -2280,12 +2280,16 @@ static int neigh_dump_table(struct neigh
 
 	err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX, NULL);
 	if (!err) {
-		if (tb[NDA_IFINDEX])
+		if (tb[NDA_IFINDEX]) {
+			if (nla_len(tb[NDA_IFINDEX]) != sizeof(u32))
+				return -EINVAL;
 			filter_idx = nla_get_u32(tb[NDA_IFINDEX]);
-
-		if (tb[NDA_MASTER])
+		}
+		if (tb[NDA_MASTER]) {
+			if (nla_len(tb[NDA_MASTER]) != sizeof(u32))
+				return -EINVAL;
 			filter_master_idx = nla_get_u32(tb[NDA_MASTER]);
-
+		}
 		if (filter_idx || filter_master_idx)
 			flags |= NLM_F_DUMP_FILTERED;
 	}

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

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

From: Cong Wang <[email protected]>

[ Upstream commit b905ef9ab90115d001c1658259af4b1c65088779 ]

The connection timers of an llc sock could be still flying after we delete them in llc_sk_free(), and even possibly after we free the sock. We could just wait synchronously here in case of troubles.

Note, I leave other call paths as they are, since they may not have to wait, at least we can change them to synchronously when needed.

Also, move the code to net/llc/llc_conn.c, which is apparently a better place.

---
 include/net/llc_conn.h |    1 +
 net/llc/llc_c_ac.c     |    9 +--------
 net/llc/llc_conn.c     |   22 +++++++++++++++++++++-
 3 files changed, 23 insertions(+), 9 deletions(-)

@@ -97,6 +97,7 @@ static __inline__ char llc_backlog_type(
 
 struct sock *llc_sk_alloc(struct net *net, int family, gfp_t priority,
 			  struct proto *prot, int kern);
+void llc_sk_stop_all_timers(struct sock *sk, bool sync);
 void llc_sk_free(struct sock *sk);
 
 void llc_sk_reset(struct sock *sk);

@@ -1096,14 +1096,7 @@ int llc_conn_ac_inc_tx_win_size(struct s
 
 int llc_conn_ac_stop_all_timers(struct sock *sk, struct sk_buff *skb)
 {
-	struct llc_sock *llc = llc_sk(sk);
-
-	del_timer(&llc->pf_cycle_timer.timer);
-	del_timer(&llc->ack_timer.timer);
-	del_timer(&llc->rej_sent_timer.timer);
-	del_timer(&llc->busy_state_timer.timer);
-	llc->ack_must_be_send = 0;
-	llc->ack_pf = 0;
+	llc_sk_stop_all_timers(sk, false);
 	return 0;
 }
 

@@ -951,6 +951,26 @@ out:
 	return sk;
 }
 
+void llc_sk_stop_all_timers(struct sock *sk, bool sync)
+{
+	struct llc_sock *llc = llc_sk(sk);
+
+	if (sync) {
+		del_timer_sync(&llc->pf_cycle_timer.timer);
+		del_timer_sync(&llc->ack_timer.timer);
+		del_timer_sync(&llc->rej_sent_timer.timer);
+		del_timer_sync(&llc->busy_state_timer.timer);
+	} else {
+		del_timer(&llc->pf_cycle_timer.timer);
+		del_timer(&llc->ack_timer.timer);
+		del_timer(&llc->rej_sent_timer.timer);
+		del_timer(&llc->busy_state_timer.timer);
+	}
+
+	llc->ack_must_be_send = 0;
+	llc->ack_pf = 0;
+}
+
 /**
  *	llc_sk_free - Frees a LLC socket
  *	@sk - socket to free

@@ -963,7 +983,7 @@ void llc_sk_free(struct sock *sk)
 
 	llc->state = LLC_CONN_OUT_OF_SVC;
 	/* Stop all (possibly) running timers */
-	llc_conn_ac_stop_all_timers(sk, NULL);
+	llc_sk_stop_all_timers(sk, true);
 #ifdef DEBUG_LLC_CONN_ALLOC
 	printk(KERN_INFO "%s: unackq=%d, txq=%d\n", __func__,
 		skb_queue_len(&llc->pdu_unack_q),