[PATCH for v4.9 LTS 01/86] sparc64: Handle PIO & MEM non-resumable errors.

[PATCH for v4.9 LTS 01/86] sparc64: Handle PIO & MEM non-resumable errors.

[Levin, Alexander (Sasha Levin)]

From: "Liam R. Howlett" <Liam.Howlett@Oracle.com>

[ Upstream commit 047487241ff59374fded8c477f21453681f5995c ]

User processes trying to access an invalid memory address via PIO will
receive a SIGBUS signal instead of causing a panic.  Memory errors will
receive a SIGKILL since a SIGBUS may result in a coredump which may
attempt to repeat the faulting access.

Signed-off-by: Liam R. Howlett <Liam.Howlett@Oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 arch/sparc/kernel/traps_64.c | 73 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 73 insertions(+)

diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index 496fa926e1e0..d44fb806bbd7 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -2051,6 +2051,73 @@ void sun4v_resum_overflow(struct pt_regs *regs)
 	atomic_inc(&sun4v_resum_oflow_cnt);
 }
 
+/* Given a set of registers, get the virtual addressi that was being accessed
+ * by the faulting instructions at tpc.
+ */
+static unsigned long sun4v_get_vaddr(struct pt_regs *regs)
+{
+	unsigned int insn;
+
+	if (!copy_from_user(&insn, (void __user *)regs->tpc, 4)) {
+		return compute_effective_address(regs, insn,
+						 (insn >> 25) & 0x1f);
+	}
+	return 0;
+}
+
+/* Attempt to handle non-resumable errors generated from userspace.
+ * Returns true if the signal was handled, false otherwise.
+ */
+bool sun4v_nonresum_error_user_handled(struct pt_regs *regs,
+				  struct sun4v_error_entry *ent) {
+
+	unsigned int attrs = ent->err_attrs;
+
+	if (attrs & SUN4V_ERR_ATTRS_MEMORY) {
+		unsigned long addr = ent->err_raddr;
+		siginfo_t info;
+
+		if (addr == ~(u64)0) {
+			/* This seems highly unlikely to ever occur */
+			pr_emerg("SUN4V NON-RECOVERABLE ERROR: Memory error detected in unknown location!\n");
+		} else {
+			unsigned long page_cnt = DIV_ROUND_UP(ent->err_size,
+							      PAGE_SIZE);
+
+			/* Break the unfortunate news. */
+			pr_emerg("SUN4V NON-RECOVERABLE ERROR: Memory failed at %016lX\n",
+				 addr);
+			pr_emerg("SUN4V NON-RECOVERABLE ERROR:   Claiming %lu ages.\n",
+				 page_cnt);
+
+			while (page_cnt-- > 0) {
+				if (pfn_valid(addr >> PAGE_SHIFT))
+					get_page(pfn_to_page(addr >> PAGE_SHIFT));
+				addr += PAGE_SIZE;
+			}
+		}
+		info.si_signo = SIGKILL;
+		info.si_errno = 0;
+		info.si_trapno = 0;
+		force_sig_info(info.si_signo, &info, current);
+
+		return true;
+	}
+	if (attrs & SUN4V_ERR_ATTRS_PIO) {
+		siginfo_t info;
+
+		info.si_signo = SIGBUS;
+		info.si_code = BUS_ADRERR;
+		info.si_addr = (void __user *)sun4v_get_vaddr(regs);
+		force_sig_info(info.si_signo, &info, current);
+
+		return true;
+	}
+
+	/* Default to doing nothing */
+	return false;
+}
+
 /* We run with %pil set to PIL_NORMAL_MAX and PSTATE_IE enabled in %pstate.
  * Log the event, clear the first word of the entry, and die.
  */
@@ -2075,6 +2142,12 @@ void sun4v_nonresum_error(struct pt_regs *regs, unsigned long offset)
 
 	put_cpu();
 
+	if (!(regs->tstate & TSTATE_PRIV) &&
+	    sun4v_nonresum_error_user_handled(regs, &local_copy)) {
+		/* DON'T PANIC: This userspace error was handled. */
+		return;
+	}
+
 #ifdef CONFIG_PCI
 	/* Check for the special PCI poke sequence. */
 	if (pci_poke_in_progress && pci_poke_cpu == cpu) {
-- 
2.11.0

[PATCH for v4.9 LTS 03/86] net: ethtool: add support for 2500BaseT and 5000BaseT link modes

[Levin, Alexander (Sasha Levin)]

From: Pavel Belous <pavel.s.belous@gmail.com>

[ Upstream commit 94842b4fc4d6b1691cfc86c6f5251f299d27f4ba ]

This patch introduce support for 2500BaseT and 5000BaseT link modes.
These modes are included in the new IEEE 802.3bz standard.

Signed-off-by: Pavel Belous <pavel.s.belous@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 include/uapi/linux/ethtool.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 8e547231c1b7..5c22e8cab24b 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -1368,6 +1368,8 @@ enum ethtool_link_mode_bit_indices {
 	ETHTOOL_LINK_MODE_10000baseLR_Full_BIT	= 44,
 	ETHTOOL_LINK_MODE_10000baseLRM_Full_BIT	= 45,
 	ETHTOOL_LINK_MODE_10000baseER_Full_BIT	= 46,
+	ETHTOOL_LINK_MODE_2500baseT_Full_BIT	= 47,
+	ETHTOOL_LINK_MODE_5000baseT_Full_BIT	= 48,
 
 
 	/* Last allowed bit for __ETHTOOL_LINK_MODE_LEGACY_MASK is bit
@@ -1377,7 +1379,7 @@ enum ethtool_link_mode_bit_indices {
 	 */
 
 	__ETHTOOL_LINK_MODE_LAST
-	  = ETHTOOL_LINK_MODE_10000baseER_Full_BIT,
+	  = ETHTOOL_LINK_MODE_5000baseT_Full_BIT,
 };
 
 #define __ETHTOOL_LINK_MODE_LEGACY_MASK(base_name)	\
-- 
2.11.0

[PATCH for v4.9 LTS 04/86] net: phy: add an option to disable EEE advertisement

[Levin, Alexander (Sasha Levin)]

From: jbrunet <jbrunet@baylibre.com>

[ Upstream commit d853d145ea3e63387a2ac759aa41d5e43876e561 ]

This patch adds an option to disable EEE advertisement in the generic PHY
by providing a mask of prohibited modes corresponding to the value found in
the MDIO_AN_EEE_ADV register.

On some platforms, PHY Low power idle seems to be causing issues, even
breaking the link some cases. The patch provides a convenient way for these
platforms to disable EEE advertisement and work around the issue.

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Tested-by: Yegor Yefremov <yegorslists@googlemail.com>
Tested-by: Andreas Färber <afaerber@suse.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/net/phy/phy.c        |  3 ++
 drivers/net/phy/phy_device.c | 80 +++++++++++++++++++++++++++++++++++++++-----
 include/linux/phy.h          |  3 ++
 3 files changed, 77 insertions(+), 9 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index a9be26f1f677..edd30ebbf275 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -1384,6 +1384,9 @@ int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data)
 {
 	int val = ethtool_adv_to_mmd_eee_adv_t(data->advertised);
 
+	/* Mask prohibited EEE modes */
+	val &= ~phydev->eee_broken_modes;
+
 	phy_write_mmd_indirect(phydev, MDIO_AN_EEE_ADV, MDIO_MMD_AN, val);
 
 	return 0;
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 14d57d0d1c04..b14fcf6e11f6 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1146,6 +1146,43 @@ static int genphy_config_advert(struct phy_device *phydev)
 }
 
 /**
+ * genphy_config_eee_advert - disable unwanted eee mode advertisement
+ * @phydev: target phy_device struct
+ *
+ * Description: Writes MDIO_AN_EEE_ADV after disabling unsupported energy
+ *   efficent ethernet modes. Returns 0 if the PHY's advertisement hasn't
+ *   changed, and 1 if it has changed.
+ */
+static int genphy_config_eee_advert(struct phy_device *phydev)
+{
+	u32 broken = phydev->eee_broken_modes;
+	u32 old_adv, adv;
+
+	/* Nothing to disable */
+	if (!broken)
+		return 0;
+
+	/* If the following call fails, we assume that EEE is not
+	 * supported by the phy. If we read 0, EEE is not advertised
+	 * In both case, we don't need to continue
+	 */
+	adv = phy_read_mmd_indirect(phydev, MDIO_AN_EEE_ADV, MDIO_MMD_AN);
+	if (adv <= 0)
+		return 0;
+
+	old_adv = adv;
+	adv &= ~broken;
+
+	/* Advertising remains unchanged with the broken mask */
+	if (old_adv == adv)
+		return 0;
+
+	phy_write_mmd_indirect(phydev, MDIO_AN_EEE_ADV, MDIO_MMD_AN, adv);
+
+	return 1;
+}
+
+/**
  * genphy_setup_forced - configures/forces speed/duplex from @phydev
  * @phydev: target phy_device struct
  *
@@ -1203,15 +1240,20 @@ EXPORT_SYMBOL(genphy_restart_aneg);
  */
 int genphy_config_aneg(struct phy_device *phydev)
 {
-	int result;
+	int err, changed;
+
+	changed = genphy_config_eee_advert(phydev);
 
 	if (AUTONEG_ENABLE != phydev->autoneg)
 		return genphy_setup_forced(phydev);
 
-	result = genphy_config_advert(phydev);
-	if (result < 0) /* error */
-		return result;
-	if (result == 0) {
+	err = genphy_config_advert(phydev);
+	if (err < 0) /* error */
+		return err;
+
+	changed |= err;
+
+	if (changed == 0) {
 		/* Advertisement hasn't changed, but maybe aneg was never on to
 		 * begin with?  Or maybe phy was isolated?
 		 */
@@ -1221,16 +1263,16 @@ int genphy_config_aneg(struct phy_device *phydev)
 			return ctl;
 
 		if (!(ctl & BMCR_ANENABLE) || (ctl & BMCR_ISOLATE))
-			result = 1; /* do restart aneg */
+			changed = 1; /* do restart aneg */
 	}
 
 	/* Only restart aneg if we are advertising something different
 	 * than we were before.
 	 */
-	if (result > 0)
-		result = genphy_restart_aneg(phydev);
+	if (changed > 0)
+		return genphy_restart_aneg(phydev);
 
-	return result;
+	return 0;
 }
 EXPORT_SYMBOL(genphy_config_aneg);
 
@@ -1588,6 +1630,21 @@ static void of_set_phy_supported(struct phy_device *phydev)
 		__set_phy_supported(phydev, max_speed);
 }
 
+static void of_set_phy_eee_broken(struct phy_device *phydev)
+{
+	struct device_node *node = phydev->mdio.dev.of_node;
+	u32 broken;
+
+	if (!IS_ENABLED(CONFIG_OF_MDIO))
+		return;
+
+	if (!node)
+		return;
+
+	if (!of_property_read_u32(node, "eee-broken-modes", &broken))
+		phydev->eee_broken_modes = broken;
+}
+
 /**
  * phy_probe - probe and init a PHY device
  * @dev: device to probe and init
@@ -1625,6 +1682,11 @@ static int phy_probe(struct device *dev)
 	of_set_phy_supported(phydev);
 	phydev->advertising = phydev->supported;
 
+	/* Get the EEE modes we want to prohibit. We will ask
+	 * the PHY stop advertising these mode later on
+	 */
+	of_set_phy_eee_broken(phydev);
+
 	/* Set the state to READY by default */
 	phydev->state = PHY_READY;
 
diff --git a/include/linux/phy.h b/include/linux/phy.h
index bd22670e2182..6c9b1e0006ee 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -401,6 +401,9 @@ struct phy_device {
 	u32 advertising;
 	u32 lp_advertising;
 
+	/* Energy efficient ethernet modes which should be prohibited */
+	u32 eee_broken_modes;
+
 	int autoneg;
 
 	int link_timeout;
-- 
2.11.0

[PATCH for v4.9 LTS 02/86] sparc64: Zero pages on allocation for mondo and error queues.

[Levin, Alexander (Sasha Levin)]

From: "Liam R. Howlett" <Liam.Howlett@Oracle.com>

[ Upstream commit 7a7dc961a28b965a0d0303c2e989df17b411708b ]

Error queues use a non-zero first word to detect if the queues are full.
Using pages that have not been zeroed may result in false positive
overflow events.  These queues are set up once during boot so zeroing
all mondo and error queue pages is safe.

Note that the false positive overflow does not always occur because the
page allocation for these queues is so early in the boot cycle that
higher number CPUs get fresh pages.  It is only when traps are serviced
with lower number CPUs who were given already used pages that this issue
is exposed.

Signed-off-by: Liam R. Howlett <Liam.Howlett@Oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 arch/sparc/kernel/irq_64.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c
index e1b1ce63a328..5cbf03c14981 100644
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -1021,7 +1021,7 @@ static void __init alloc_one_queue(unsigned long *pa_ptr, unsigned long qmask)
 	unsigned long order = get_order(size);
 	unsigned long p;
 
-	p = __get_free_pages(GFP_KERNEL, order);
+	p = __get_free_pages(GFP_KERNEL | __GFP_ZERO, order);
 	if (!p) {
 		prom_printf("SUN4V: Error, cannot allocate queue.\n");
 		prom_halt();
-- 
2.11.0

[PATCH for v4.9 LTS 05/86] dt-bindings: net: add EEE capability constants

[Levin, Alexander (Sasha Levin)]

From: jbrunet <jbrunet@baylibre.com>

[ Upstream commit 1fc31357ad194fb98691f3d122bcd47e59239e83 ]

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Tested-by: Yegor Yefremov <yegorslists@googlemail.com>
Tested-by: Andreas Färber <afaerber@suse.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 include/dt-bindings/net/mdio.h | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)
 create mode 100644 include/dt-bindings/net/mdio.h

diff --git a/include/dt-bindings/net/mdio.h b/include/dt-bindings/net/mdio.h
new file mode 100644
index 000000000000..99c6d903d439
--- /dev/null
+++ b/include/dt-bindings/net/mdio.h
@@ -0,0 +1,19 @@
+/*
+ * This header provides generic constants for ethernet MDIO bindings
+ */
+
+#ifndef _DT_BINDINGS_NET_MDIO_H
+#define _DT_BINDINGS_NET_MDIO_H
+
+/*
+ * EEE capability Advertisement
+ */
+
+#define MDIO_EEE_100TX		0x0002	/* 100TX EEE cap */
+#define MDIO_EEE_1000T		0x0004	/* 1000T EEE cap */
+#define MDIO_EEE_10GT		0x0008	/* 10GT EEE cap */
+#define MDIO_EEE_1000KX		0x0010	/* 1000KX EEE cap */
+#define MDIO_EEE_10GKX4		0x0020	/* 10G KX4 EEE cap */
+#define MDIO_EEE_10GKR		0x0040	/* 10G KR EEE cap */
+
+#endif
-- 
2.11.0

[PATCH for v4.9 LTS 06/86] net: phy: fix sign type error in genphy_config_eee_advert

[Levin, Alexander (Sasha Levin)]

From: jbrunet <jbrunet@baylibre.com>

[ Upstream commit 3bb9ab63276696988d8224f52db20e87194deb4b ]

In genphy_config_eee_advert, the return value of phy_read_mmd_indirect is
checked to know if the register could be accessed but the result is
assigned to a 'u32'.
Changing to 'int' to correctly get errors from phy_read_mmd_indirect.

Fixes: d853d145ea3e ("net: phy: add an option to disable EEE advertisement")
Reported-by: Julia Lawall <julia.lawall@lip6.fr>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/net/phy/phy_device.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index b14fcf6e11f6..d9ec74895e42 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1155,8 +1155,8 @@ static int genphy_config_advert(struct phy_device *phydev)
  */
 static int genphy_config_eee_advert(struct phy_device *phydev)
 {
-	u32 broken = phydev->eee_broken_modes;
-	u32 old_adv, adv;
+	int broken = phydev->eee_broken_modes;
+	int old_adv, adv;
 
 	/* Nothing to disable */
 	if (!broken)
-- 
2.11.0

[PATCH for v4.9 LTS 09/86] ARM64: dts: amlogic: Add Meson GX dtsi from GXBB

[Levin, Alexander (Sasha Levin)]

From: Neil Armstrong <narmstrong@baylibre.com>

[ Upstream commit c328666d58aac4880bf0934eb915f9c5d1801360 ]

Move all non-gxbb specific nodes to a common GX dtsi.

Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
Signed-off-by: Kevin Hilman <khilman@baylibre.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 arch/arm64/boot/dts/amlogic/meson-gx.dtsi   | 200 +++++++
 arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi | 895 ++++++++++++----------------
 2 files changed, 579 insertions(+), 516 deletions(-)
 create mode 100644 arch/arm64/boot/dts/amlogic/meson-gx.dtsi

diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
new file mode 100644
index 000000000000..0737056b369f
--- /dev/null
+++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
@@ -0,0 +1,200 @@
+/*
+ * Copyright (c) 2016 BayLibre, SAS.
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ *
+ * Copyright (c) 2016 Endless Computers, Inc.
+ * Author: Carlo Caione <carlo@endlessm.com>
+ *
+ * Copyright (c) 2016 Andreas Färber
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This library is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This library is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+
+/ {
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	cpus {
+		#address-cells = <0x2>;
+		#size-cells = <0x0>;
+
+		cpu0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0x0 0x0>;
+			enable-method = "psci";
+		};
+
+		cpu1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0x0 0x1>;
+			enable-method = "psci";
+		};
+
+		cpu2: cpu@2 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0x0 0x2>;
+			enable-method = "psci";
+		};
+
+		cpu3: cpu@3 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0x0 0x3>;
+			enable-method = "psci";
+		};
+	};
+
+	arm-pmu {
+		compatible = "arm,cortex-a53-pmu";
+		interrupts = <GIC_SPI 137 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 153 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 154 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-affinity = <&cpu0>, <&cpu1>, <&cpu2>, <&cpu3>;
+	};
+
+	psci {
+		compatible = "arm,psci-0.2";
+		method = "smc";
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupts = <GIC_PPI 13
+			(GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 14
+			(GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 11
+			(GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 10
+			(GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_LEVEL_LOW)>;
+	};
+
+	xtal: xtal-clk {
+		compatible = "fixed-clock";
+		clock-frequency = <24000000>;
+		clock-output-names = "xtal";
+		#clock-cells = <0>;
+	};
+
+	soc {
+		compatible = "simple-bus";
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		cbus: cbus@c1100000 {
+			compatible = "simple-bus";
+			reg = <0x0 0xc1100000 0x0 0x100000>;
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges = <0x0 0x0 0x0 0xc1100000 0x0 0x100000>;
+
+			uart_A: serial@84c0 {
+				compatible = "amlogic,meson-uart";
+				reg = <0x0 0x84c0 0x0 0x14>;
+				interrupts = <GIC_SPI 26 IRQ_TYPE_EDGE_RISING>;
+				clocks = <&xtal>;
+				status = "disabled";
+			};
+		};
+
+		gic: interrupt-controller@c4301000 {
+			compatible = "arm,gic-400";
+			reg = <0x0 0xc4301000 0 0x1000>,
+			      <0x0 0xc4302000 0 0x2000>,
+			      <0x0 0xc4304000 0 0x2000>,
+			      <0x0 0xc4306000 0 0x2000>;
+			interrupt-controller;
+			interrupts = <GIC_PPI 9
+				(GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_HIGH)>;
+			#interrupt-cells = <3>;
+			#address-cells = <0>;
+		};
+
+		aobus: aobus@c8100000 {
+			compatible = "simple-bus";
+			reg = <0x0 0xc8100000 0x0 0x100000>;
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges = <0x0 0x0 0x0 0xc8100000 0x0 0x100000>;
+
+			uart_AO: serial@4c0 {
+				compatible = "amlogic,meson-uart";
+				reg = <0x0 0x004c0 0x0 0x14>;
+				interrupts = <GIC_SPI 193 IRQ_TYPE_EDGE_RISING>;
+				clocks = <&xtal>;
+				status = "disabled";
+			};
+		};
+
+		periphs: periphs@c8834000 {
+			compatible = "simple-bus";
+			reg = <0x0 0xc8834000 0x0 0x2000>;
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges = <0x0 0x0 0x0 0xc8834000 0x0 0x2000>;
+		};
+
+
+		hiubus: hiubus@c883c000 {
+			compatible = "simple-bus";
+			reg = <0x0 0xc883c000 0x0 0x2000>;
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges = <0x0 0x0 0x0 0xc883c000 0x0 0x2000>;
+		};
+
+		apb: apb@d0000000 {
+			compatible = "simple-bus";
+			reg = <0x0 0xd0000000 0x0 0x200000>;
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges = <0x0 0x0 0x0 0xd0000000 0x0 0x200000>;
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
index 610e0e1c3cee..443811b497de 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
@@ -40,9 +40,7 @@
  *     OTHER DEALINGS IN THE SOFTWARE.
  */
 
-#include <dt-bindings/gpio/gpio.h>
-#include <dt-bindings/interrupt-controller/irq.h>
-#include <dt-bindings/interrupt-controller/arm-gic.h>
+#include "meson-gx.dtsi"
 #include <dt-bindings/gpio/meson-gxbb-gpio.h>
 #include <dt-bindings/reset/amlogic,meson-gxbb-reset.h>
 #include <dt-bindings/clock/gxbb-clkc.h>
@@ -51,56 +49,6 @@
 
 / {
 	compatible = "amlogic,meson-gxbb";
-	interrupt-parent = <&gic>;
-	#address-cells = <2>;
-	#size-cells = <2>;
-
-	cpus {
-		#address-cells = <0x2>;
-		#size-cells = <0x0>;
-
-		cpu0: cpu@0 {
-			device_type = "cpu";
-			compatible = "arm,cortex-a53", "arm,armv8";
-			reg = <0x0 0x0>;
-			enable-method = "psci";
-		};
-
-		cpu1: cpu@1 {
-			device_type = "cpu";
-			compatible = "arm,cortex-a53", "arm,armv8";
-			reg = <0x0 0x1>;
-			enable-method = "psci";
-		};
-
-		cpu2: cpu@2 {
-			device_type = "cpu";
-			compatible = "arm,cortex-a53", "arm,armv8";
-			reg = <0x0 0x2>;
-			enable-method = "psci";
-		};
-
-		cpu3: cpu@3 {
-			device_type = "cpu";
-			compatible = "arm,cortex-a53", "arm,armv8";
-			reg = <0x0 0x3>;
-			enable-method = "psci";
-		};
-	};
-
-	arm-pmu {
-		compatible = "arm,cortex-a53-pmu";
-		interrupts = <GIC_SPI 137 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 153 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 154 IRQ_TYPE_LEVEL_HIGH>;
-		interrupt-affinity = <&cpu0>, <&cpu1>, <&cpu2>, <&cpu3>;
-	};
-
-	psci {
-		compatible = "arm,psci-0.2";
-		method = "smc";
-	};
 
 	firmware {
 		sm: secure-monitor {
@@ -126,31 +74,7 @@
 		};
 	};
 
-	timer {
-		compatible = "arm,armv8-timer";
-		interrupts = <GIC_PPI 13
-			(GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_LEVEL_LOW)>,
-			     <GIC_PPI 14
-			(GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_LEVEL_LOW)>,
-			     <GIC_PPI 11
-			(GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_LEVEL_LOW)>,
-			     <GIC_PPI 10
-			(GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_LEVEL_LOW)>;
-	};
-
-	xtal: xtal-clk {
-		compatible = "fixed-clock";
-		clock-frequency = <24000000>;
-		clock-output-names = "xtal";
-		#clock-cells = <0>;
-	};
-
 	soc {
-		compatible = "simple-bus";
-		#address-cells = <2>;
-		#size-cells = <2>;
-		ranges;
-
 		usb0_phy: phy@c0000000 {
 			compatible = "amlogic,meson-gxbb-usb2-phy";
 			#phy-cells = <0>;
@@ -170,500 +94,439 @@
 			status = "disabled";
 		};
 
-		cbus: cbus@c1100000 {
-			compatible = "simple-bus";
-			reg = <0x0 0xc1100000 0x0 0x100000>;
-			#address-cells = <2>;
-			#size-cells = <2>;
-			ranges = <0x0 0x0 0x0 0xc1100000 0x0 0x100000>;
+		usb0: usb@c9000000 {
+			compatible = "amlogic,meson-gxbb-usb", "snps,dwc2";
+			reg = <0x0 0xc9000000 0x0 0x40000>;
+			interrupts = <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clkc CLKID_USB0_DDR_BRIDGE>;
+			clock-names = "otg";
+			phys = <&usb0_phy>;
+			phy-names = "usb2-phy";
+			dr_mode = "host";
+			status = "disabled";
+		};
 
-			reset: reset-controller@4404 {
-				compatible = "amlogic,meson-gxbb-reset";
-				reg = <0x0 0x04404 0x0 0x20>;
-				#reset-cells = <1>;
-			};
+		usb1: usb@c9100000 {
+			compatible = "amlogic,meson-gxbb-usb", "snps,dwc2";
+			reg = <0x0 0xc9100000 0x0 0x40000>;
+			interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clkc CLKID_USB1_DDR_BRIDGE>;
+			clock-names = "otg";
+			phys = <&usb1_phy>;
+			phy-names = "usb2-phy";
+			dr_mode = "host";
+			status = "disabled";
+		};
 
-			uart_A: serial@84c0 {
-				compatible = "amlogic,meson-uart";
-				reg = <0x0 0x84c0 0x0 0x14>;
-				interrupts = <GIC_SPI 26 IRQ_TYPE_EDGE_RISING>;
-				clocks = <&xtal>;
-				status = "disabled";
-			};
+		ethmac: ethernet@c9410000 {
+			compatible = "amlogic,meson-gxbb-dwmac", "snps,dwmac";
+			reg = <0x0 0xc9410000 0x0 0x10000
+			       0x0 0xc8834540 0x0 0x4>;
+			interrupts = <0 8 1>;
+			interrupt-names = "macirq";
+			clocks = <&clkc CLKID_ETH>,
+				 <&clkc CLKID_FCLK_DIV2>,
+				 <&clkc CLKID_MPLL2>;
+			clock-names = "stmmaceth", "clkin0", "clkin1";
+			phy-mode = "rgmii";
+			status = "disabled";
+		};
+	};
+};
+
+&cbus {
+	reset: reset-controller@4404 {
+		compatible = "amlogic,meson-gxbb-reset";
+		reg = <0x0 0x04404 0x0 0x20>;
+		#reset-cells = <1>;
+	};
+
+	uart_B: serial@84dc {
+		compatible = "amlogic,meson-uart";
+		reg = <0x0 0x84dc 0x0 0x14>;
+		interrupts = <GIC_SPI 75 IRQ_TYPE_EDGE_RISING>;
+		clocks = <&xtal>;
+		status = "disabled";
+	};
+
+	pwm_ab: pwm@8550 {
+		compatible = "amlogic,meson-gxbb-pwm";
+		reg = <0x0 0x08550 0x0 0x10>;
+		#pwm-cells = <3>;
+		status = "disabled";
+	};
+
+	pwm_cd: pwm@8650 {
+		compatible = "amlogic,meson-gxbb-pwm";
+		reg = <0x0 0x08650 0x0 0x10>;
+		#pwm-cells = <3>;
+		status = "disabled";
+	};
+
+	pwm_ef: pwm@86c0 {
+		compatible = "amlogic,meson-gxbb-pwm";
+		reg = <0x0 0x086c0 0x0 0x10>;
+		#pwm-cells = <3>;
+		status = "disabled";
+	};
+
+	uart_C: serial@8700 {
+		compatible = "amlogic,meson-uart";
+		reg = <0x0 0x8700 0x0 0x14>;
+		interrupts = <GIC_SPI 93 IRQ_TYPE_EDGE_RISING>;
+		clocks = <&xtal>;
+		status = "disabled";
+	};
+
+	watchdog@98d0 {
+		compatible = "amlogic,meson-gxbb-wdt";
+		reg = <0x0 0x098d0 0x0 0x10>;
+		clocks = <&xtal>;
+	};
+
+	spifc: spi@8c80 {
+		compatible = "amlogic,meson-gxbb-spifc";
+		reg = <0x0 0x08c80 0x0 0x80>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		clocks = <&clkc CLKID_SPI>;
+		status = "disabled";
+	};
+
+	i2c_A: i2c@8500 {
+		compatible = "amlogic,meson-gxbb-i2c";
+		reg = <0x0 0x08500 0x0 0x20>;
+		interrupts = <GIC_SPI 21 IRQ_TYPE_EDGE_RISING>;
+		clocks = <&clkc CLKID_I2C>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
+	};
+
+	i2c_B: i2c@87c0 {
+		compatible = "amlogic,meson-gxbb-i2c";
+		reg = <0x0 0x087c0 0x0 0x20>;
+		interrupts = <GIC_SPI 214 IRQ_TYPE_EDGE_RISING>;
+		clocks = <&clkc CLKID_I2C>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
+	};
+
+	i2c_C: i2c@87e0 {
+		compatible = "amlogic,meson-gxbb-i2c";
+		reg = <0x0 0x087e0 0x0 0x20>;
+		interrupts = <GIC_SPI 215 IRQ_TYPE_EDGE_RISING>;
+		clocks = <&clkc CLKID_I2C>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
+	};
+};
+
+&aobus {
+	pinctrl_aobus: pinctrl@14 {
+		compatible = "amlogic,meson-gxbb-aobus-pinctrl";
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
 
-			uart_B: serial@84dc {
-				compatible = "amlogic,meson-uart";
-				reg = <0x0 0x84dc 0x0 0x14>;
-				interrupts = <GIC_SPI 75 IRQ_TYPE_EDGE_RISING>;
-				clocks = <&xtal>;
-				status = "disabled";
+		gpio_ao: bank@14 {
+			reg = <0x0 0x00014 0x0 0x8>,
+			      <0x0 0x0002c 0x0 0x4>,
+			      <0x0 0x00024 0x0 0x8>;
+			reg-names = "mux", "pull", "gpio";
+			gpio-controller;
+			#gpio-cells = <2>;
+		};
+
+		uart_ao_a_pins: uart_ao_a {
+			mux {
+				groups = "uart_tx_ao_a", "uart_rx_ao_a";
+				function = "uart_ao";
 			};
+		};
 
-			pwm_ab: pwm@8550 {
-				compatible = "amlogic,meson-gxbb-pwm";
-				reg = <0x0 0x08550 0x0 0x10>;
-				#pwm-cells = <3>;
-				status = "disabled";
+		remote_input_ao_pins: remote_input_ao {
+			mux {
+				groups = "remote_input_ao";
+				function = "remote_input_ao";
 			};
+		};
 
-			pwm_cd: pwm@8650 {
-				compatible = "amlogic,meson-gxbb-pwm";
-				reg = <0x0 0x08650 0x0 0x10>;
-				#pwm-cells = <3>;
-				status = "disabled";
+		i2c_ao_pins: i2c_ao {
+			mux {
+				groups = "i2c_sck_ao",
+				       "i2c_sda_ao";
+				function = "i2c_ao";
 			};
+		};
 
-			pwm_ef: pwm@86c0 {
-				compatible = "amlogic,meson-gxbb-pwm";
-				reg = <0x0 0x086c0 0x0 0x10>;
-				#pwm-cells = <3>;
-				status = "disabled";
+		pwm_ao_a_3_pins: pwm_ao_a_3 {
+			mux {
+				groups = "pwm_ao_a_3";
+				function = "pwm_ao_a_3";
 			};
+		};
 
-			uart_C: serial@8700 {
-				compatible = "amlogic,meson-uart";
-				reg = <0x0 0x8700 0x0 0x14>;
-				interrupts = <GIC_SPI 93 IRQ_TYPE_EDGE_RISING>;
-				clocks = <&xtal>;
-				status = "disabled";
+		pwm_ao_a_6_pins: pwm_ao_a_6 {
+			mux {
+				groups = "pwm_ao_a_6";
+				function = "pwm_ao_a_6";
 			};
+		};
 
-			watchdog@98d0 {
-				compatible = "amlogic,meson-gxbb-wdt";
-				reg = <0x0 0x098d0 0x0 0x10>;
-				clocks = <&xtal>;
+		pwm_ao_a_12_pins: pwm_ao_a_12 {
+			mux {
+				groups = "pwm_ao_a_12";
+				function = "pwm_ao_a_12";
 			};
+		};
 
-			spifc: spi@8c80 {
-				compatible = "amlogic,meson-gxbb-spifc";
-				reg = <0x0 0x08c80 0x0 0x80>;
-				#address-cells = <1>;
-				#size-cells = <0>;
-				clocks = <&clkc CLKID_SPI>;
-				status = "disabled";
+		pwm_ao_b_pins: pwm_ao_b {
+			mux {
+				groups = "pwm_ao_b";
+				function = "pwm_ao_b";
 			};
+		};
+	};
+
+	clkc_AO: clock-controller@040 {
+		compatible = "amlogic,gxbb-aoclkc";
+		reg = <0x0 0x00040 0x0 0x4>;
+		#clock-cells = <1>;
+		#reset-cells = <1>;
+	};
+
+	ir: ir@580 {
+		compatible = "amlogic,meson-gxbb-ir";
+		reg = <0x0 0x00580 0x0 0x40>;
+		interrupts = <GIC_SPI 196 IRQ_TYPE_EDGE_RISING>;
+		status = "disabled";
+	};
+
+	pwm_ab_AO: pwm@550 {
+		compatible = "amlogic,meson-gxbb-pwm";
+		reg = <0x0 0x0550 0x0 0x10>;
+		#pwm-cells = <3>;
+		status = "disabled";
+	};
+
+	i2c_AO: i2c@500 {
+		compatible = "amlogic,meson-gxbb-i2c";
+		reg = <0x0 0x500 0x0 0x20>;
+		interrupts = <GIC_SPI 195 IRQ_TYPE_EDGE_RISING>;
+		clocks = <&clkc CLKID_AO_I2C>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
+	};
+};
+
+&periphs {
+	rng {
+		compatible = "amlogic,meson-rng";
+		reg = <0x0 0x0 0x0 0x4>;
+	};
+
+	pinctrl_periphs: pinctrl@4b0 {
+		compatible = "amlogic,meson-gxbb-periphs-pinctrl";
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		gpio: bank@4b0 {
+			reg = <0x0 0x004b0 0x0 0x28>,
+			      <0x0 0x004e8 0x0 0x14>,
+			      <0x0 0x00120 0x0 0x14>,
+			      <0x0 0x00430 0x0 0x40>;
+			reg-names = "mux", "pull", "pull-enable", "gpio";
+			gpio-controller;
+			#gpio-cells = <2>;
+		};
 
-			i2c_A: i2c@8500 {
-				compatible = "amlogic,meson-gxbb-i2c";
-				reg = <0x0 0x08500 0x0 0x20>;
-				interrupts = <GIC_SPI 21 IRQ_TYPE_EDGE_RISING>;
-				clocks = <&clkc CLKID_I2C>;
-				#address-cells = <1>;
-				#size-cells = <0>;
-				status = "disabled";
+		emmc_pins: emmc {
+			mux {
+				groups = "emmc_nand_d07",
+				       "emmc_cmd",
+				       "emmc_clk";
+				function = "emmc";
 			};
+		};
 
-			i2c_B: i2c@87c0 {
-				compatible = "amlogic,meson-gxbb-i2c";
-				reg = <0x0 0x087c0 0x0 0x20>;
-				interrupts = <GIC_SPI 214 IRQ_TYPE_EDGE_RISING>;
-				clocks = <&clkc CLKID_I2C>;
-				#address-cells = <1>;
-				#size-cells = <0>;
-				status = "disabled";
+		nor_pins: nor {
+			mux {
+				groups = "nor_d",
+				       "nor_q",
+				       "nor_c",
+				       "nor_cs";
+				function = "nor";
 			};
+		};
 
-			i2c_C: i2c@87e0 {
-				compatible = "amlogic,meson-gxbb-i2c";
-				reg = <0x0 0x087e0 0x0 0x20>;
-				interrupts = <GIC_SPI 215 IRQ_TYPE_EDGE_RISING>;
-				clocks = <&clkc CLKID_I2C>;
-				#address-cells = <1>;
-				#size-cells = <0>;
-				status = "disabled";
+		sdcard_pins: sdcard {
+			mux {
+				groups = "sdcard_d0",
+				       "sdcard_d1",
+				       "sdcard_d2",
+				       "sdcard_d3",
+				       "sdcard_cmd",
+				       "sdcard_clk";
+				function = "sdcard";
 			};
 		};
 
-		gic: interrupt-controller@c4301000 {
-			compatible = "arm,gic-400";
-			reg = <0x0 0xc4301000 0 0x1000>,
-			      <0x0 0xc4302000 0 0x2000>,
-			      <0x0 0xc4304000 0 0x2000>,
-			      <0x0 0xc4306000 0 0x2000>;
-			interrupt-controller;
-			interrupts = <GIC_PPI 9
-				(GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_HIGH)>;
-			#interrupt-cells = <3>;
-			#address-cells = <0>;
-		};
-
-		aobus: aobus@c8100000 {
-			compatible = "simple-bus";
-			reg = <0x0 0xc8100000 0x0 0x100000>;
-			#address-cells = <2>;
-			#size-cells = <2>;
-			ranges = <0x0 0x0 0x0 0xc8100000 0x0 0x100000>;
-
-			pinctrl_aobus: pinctrl@14 {
-				compatible = "amlogic,meson-gxbb-aobus-pinctrl";
-				#address-cells = <2>;
-				#size-cells = <2>;
-				ranges;
-
-				gpio_ao: bank@14 {
-					reg = <0x0 0x00014 0x0 0x8>,
-					      <0x0 0x0002c 0x0 0x4>,
-					      <0x0 0x00024 0x0 0x8>;
-					reg-names = "mux", "pull", "gpio";
-					gpio-controller;
-					#gpio-cells = <2>;
-				};
-
-				uart_ao_a_pins: uart_ao_a {
-					mux {
-						groups = "uart_tx_ao_a", "uart_rx_ao_a";
-						function = "uart_ao";
-					};
-				};
-
-				remote_input_ao_pins: remote_input_ao {
-					mux {
-						groups = "remote_input_ao";
-						function = "remote_input_ao";
-					};
-				};
-
-				i2c_ao_pins: i2c_ao {
-					mux {
-						groups = "i2c_sck_ao",
-						       "i2c_sda_ao";
-						function = "i2c_ao";
-					};
-				};
-
-				pwm_ao_a_3_pins: pwm_ao_a_3 {
-					mux {
-						groups = "pwm_ao_a_3";
-						function = "pwm_ao_a_3";
-					};
-				};
-
-				pwm_ao_a_6_pins: pwm_ao_a_6 {
-					mux {
-						groups = "pwm_ao_a_6";
-						function = "pwm_ao_a_6";
-					};
-				};
-
-				pwm_ao_a_12_pins: pwm_ao_a_12 {
-					mux {
-						groups = "pwm_ao_a_12";
-						function = "pwm_ao_a_12";
-					};
-				};
-
-				pwm_ao_b_pins: pwm_ao_b {
-					mux {
-						groups = "pwm_ao_b";
-						function = "pwm_ao_b";
-					};
-				};
+		sdio_pins: sdio {
+			mux {
+				groups = "sdio_d0",
+				       "sdio_d1",
+				       "sdio_d2",
+				       "sdio_d3",
+				       "sdio_cmd",
+				       "sdio_clk";
+				function = "sdio";
 			};
+		};
 
-			clkc_AO: clock-controller@040 {
-				compatible = "amlogic,gxbb-aoclkc";
-				reg = <0x0 0x00040 0x0 0x4>;
-				#clock-cells = <1>;
-				#reset-cells = <1>;
+		sdio_irq_pins: sdio_irq {
+			mux {
+				groups = "sdio_irq";
+				function = "sdio";
 			};
+		};
 
-			uart_AO: serial@4c0 {
-				compatible = "amlogic,meson-uart";
-				reg = <0x0 0x004c0 0x0 0x14>;
-				interrupts = <GIC_SPI 193 IRQ_TYPE_EDGE_RISING>;
-				clocks = <&xtal>;
-				status = "disabled";
+		uart_a_pins: uart_a {
+			mux {
+				groups = "uart_tx_a",
+				       "uart_rx_a";
+				function = "uart_a";
 			};
+		};
 
-			ir: ir@580 {
-				compatible = "amlogic,meson-gxbb-ir";
-				reg = <0x0 0x00580 0x0 0x40>;
-				interrupts = <GIC_SPI 196 IRQ_TYPE_EDGE_RISING>;
-				status = "disabled";
+		uart_b_pins: uart_b {
+			mux {
+				groups = "uart_tx_b",
+				       "uart_rx_b";
+				function = "uart_b";
 			};
+		};
 
-			pwm_ab_AO: pwm@550 {
-				compatible = "amlogic,meson-gxbb-pwm";
-				reg = <0x0 0x0550 0x0 0x10>;
-				#pwm-cells = <3>;
-				status = "disabled";
+		uart_c_pins: uart_c {
+			mux {
+				groups = "uart_tx_c",
+				       "uart_rx_c";
+				function = "uart_c";
 			};
+		};
 
-			i2c_AO: i2c@500 {
-				compatible = "amlogic,meson-gxbb-i2c";
-				reg = <0x0 0x500 0x0 0x20>;
-				interrupts = <GIC_SPI 195 IRQ_TYPE_EDGE_RISING>;
-				clocks = <&clkc CLKID_AO_I2C>;
-				#address-cells = <1>;
-				#size-cells = <0>;
-				status = "disabled";
+		i2c_a_pins: i2c_a {
+			mux {
+				groups = "i2c_sck_a",
+				       "i2c_sda_a";
+				function = "i2c_a";
 			};
 		};
 
-		periphs: periphs@c8834000 {
-			compatible = "simple-bus";
-			reg = <0x0 0xc8834000 0x0 0x2000>;
-			#address-cells = <2>;
-			#size-cells = <2>;
-			ranges = <0x0 0x0 0x0 0xc8834000 0x0 0x2000>;
+		i2c_b_pins: i2c_b {
+			mux {
+				groups = "i2c_sck_b",
+				       "i2c_sda_b";
+				function = "i2c_b";
+			};
+		};
 
-			rng {
-				compatible = "amlogic,meson-rng";
-				reg = <0x0 0x0 0x0 0x4>;
+		i2c_c_pins: i2c_c {
+			mux {
+				groups = "i2c_sck_c",
+				       "i2c_sda_c";
+				function = "i2c_c";
 			};
+		};
 
-			pinctrl_periphs: pinctrl@4b0 {
-				compatible = "amlogic,meson-gxbb-periphs-pinctrl";
-				#address-cells = <2>;
-				#size-cells = <2>;
-				ranges;
-
-				gpio: bank@4b0 {
-					reg = <0x0 0x004b0 0x0 0x28>,
-					      <0x0 0x004e8 0x0 0x14>,
-					      <0x0 0x00120 0x0 0x14>,
-					      <0x0 0x00430 0x0 0x40>;
-					reg-names = "mux", "pull", "pull-enable", "gpio";
-					gpio-controller;
-					#gpio-cells = <2>;
-				};
-
-				emmc_pins: emmc {
-					mux {
-						groups = "emmc_nand_d07",
-						       "emmc_cmd",
-						       "emmc_clk";
-						function = "emmc";
-					};
-				};
-
-				nor_pins: nor {
-					mux {
-						groups = "nor_d",
-						       "nor_q",
-						       "nor_c",
-						       "nor_cs";
-						function = "nor";
-					};
-				};
-
-				sdcard_pins: sdcard {
-					mux {
-						groups = "sdcard_d0",
-						       "sdcard_d1",
-						       "sdcard_d2",
-						       "sdcard_d3",
-						       "sdcard_cmd",
-						       "sdcard_clk";
-						function = "sdcard";
-					};
-				};
-
-				sdio_pins: sdio {
-					mux {
-						groups = "sdio_d0",
-						       "sdio_d1",
-						       "sdio_d2",
-						       "sdio_d3",
-						       "sdio_cmd",
-						       "sdio_clk";
-						function = "sdio";
-					};
-				};
-
-				sdio_irq_pins: sdio_irq {
-					mux {
-						groups = "sdio_irq";
-						function = "sdio";
-					};
-				};
-
-				uart_a_pins: uart_a {
-					mux {
-						groups = "uart_tx_a",
-						       "uart_rx_a";
-						function = "uart_a";
-					};
-				};
-
-				uart_b_pins: uart_b {
-					mux {
-						groups = "uart_tx_b",
-						       "uart_rx_b";
-						function = "uart_b";
-					};
-				};
-
-				uart_c_pins: uart_c {
-					mux {
-						groups = "uart_tx_c",
-						       "uart_rx_c";
-						function = "uart_c";
-					};
-				};
-
-				i2c_a_pins: i2c_a {
-					mux {
-						groups = "i2c_sck_a",
-						       "i2c_sda_a";
-						function = "i2c_a";
-					};
-				};
-
-				i2c_b_pins: i2c_b {
-					mux {
-						groups = "i2c_sck_b",
-						       "i2c_sda_b";
-						function = "i2c_b";
-					};
-				};
-
-				i2c_c_pins: i2c_c {
-					mux {
-						groups = "i2c_sck_c",
-						       "i2c_sda_c";
-						function = "i2c_c";
-					};
-				};
-
-				eth_pins: eth_c {
-					mux {
-						groups = "eth_mdio",
-						       "eth_mdc",
-						       "eth_clk_rx_clk",
-						       "eth_rx_dv",
-						       "eth_rxd0",
-						       "eth_rxd1",
-						       "eth_rxd2",
-						       "eth_rxd3",
-						       "eth_rgmii_tx_clk",
-						       "eth_tx_en",
-						       "eth_txd0",
-						       "eth_txd1",
-						       "eth_txd2",
-						       "eth_txd3";
-						function = "eth";
-					};
-				};
-
-				pwm_a_x_pins: pwm_a_x {
-					mux {
-						groups = "pwm_a_x";
-						function = "pwm_a_x";
-					};
-				};
-
-				pwm_a_y_pins: pwm_a_y {
-					mux {
-						groups = "pwm_a_y";
-						function = "pwm_a_y";
-					};
-				};
-
-				pwm_b_pins: pwm_b {
-					mux {
-						groups = "pwm_b";
-						function = "pwm_b";
-					};
-				};
-
-				pwm_d_pins: pwm_d {
-					mux {
-						groups = "pwm_d";
-						function = "pwm_d";
-					};
-				};
-
-				pwm_e_pins: pwm_e {
-					mux {
-						groups = "pwm_e";
-						function = "pwm_e";
-					};
-				};
-
-				pwm_f_x_pins: pwm_f_x {
-					mux {
-						groups = "pwm_f_x";
-						function = "pwm_f_x";
-					};
-				};
-
-				pwm_f_y_pins: pwm_f_y {
-					mux {
-						groups = "pwm_f_y";
-						function = "pwm_f_y";
-					};
-				};
+		eth_pins: eth_c {
+			mux {
+				groups = "eth_mdio",
+				       "eth_mdc",
+				       "eth_clk_rx_clk",
+				       "eth_rx_dv",
+				       "eth_rxd0",
+				       "eth_rxd1",
+				       "eth_rxd2",
+				       "eth_rxd3",
+				       "eth_rgmii_tx_clk",
+				       "eth_tx_en",
+				       "eth_txd0",
+				       "eth_txd1",
+				       "eth_txd2",
+				       "eth_txd3";
+				function = "eth";
 			};
 		};
 
-		hiubus: hiubus@c883c000 {
-			compatible = "simple-bus";
-			reg = <0x0 0xc883c000 0x0 0x2000>;
-			#address-cells = <2>;
-			#size-cells = <2>;
-			ranges = <0x0 0x0 0x0 0xc883c000 0x0 0x2000>;
+		pwm_a_x_pins: pwm_a_x {
+			mux {
+				groups = "pwm_a_x";
+				function = "pwm_a_x";
+			};
+		};
 
-			clkc: clock-controller@0 {
-				compatible = "amlogic,gxbb-clkc";
-				#clock-cells = <1>;
-				reg = <0x0 0x0 0x0 0x3db>;
+		pwm_a_y_pins: pwm_a_y {
+			mux {
+				groups = "pwm_a_y";
+				function = "pwm_a_y";
 			};
+		};
 
-			mailbox: mailbox@404 {
-				compatible = "amlogic,meson-gxbb-mhu";
-				reg = <0 0x404 0 0x4c>;
-				interrupts = <0 208 IRQ_TYPE_EDGE_RISING>,
-					     <0 209 IRQ_TYPE_EDGE_RISING>,
-					     <0 210 IRQ_TYPE_EDGE_RISING>;
-				#mbox-cells = <1>;
+		pwm_b_pins: pwm_b {
+			mux {
+				groups = "pwm_b";
+				function = "pwm_b";
 			};
 		};
 
-		apb: apb@d0000000 {
-			compatible = "simple-bus";
-			reg = <0x0 0xd0000000 0x0 0x200000>;
-			#address-cells = <2>;
-			#size-cells = <2>;
-			ranges = <0x0 0x0 0x0 0xd0000000 0x0 0x200000>;
+		pwm_d_pins: pwm_d {
+			mux {
+				groups = "pwm_d";
+				function = "pwm_d";
+			};
 		};
 
-		usb0: usb@c9000000 {
-			compatible = "amlogic,meson-gxbb-usb", "snps,dwc2";
-			reg = <0x0 0xc9000000 0x0 0x40000>;
-			interrupts = <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&clkc CLKID_USB0_DDR_BRIDGE>;
-			clock-names = "otg";
-			phys = <&usb0_phy>;
-			phy-names = "usb2-phy";
-			dr_mode = "host";
-			status = "disabled";
+		pwm_e_pins: pwm_e {
+			mux {
+				groups = "pwm_e";
+				function = "pwm_e";
+			};
 		};
 
-		usb1: usb@c9100000 {
-			compatible = "amlogic,meson-gxbb-usb", "snps,dwc2";
-			reg = <0x0 0xc9100000 0x0 0x40000>;
-			interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&clkc CLKID_USB1_DDR_BRIDGE>;
-			clock-names = "otg";
-			phys = <&usb1_phy>;
-			phy-names = "usb2-phy";
-			dr_mode = "host";
-			status = "disabled";
+		pwm_f_x_pins: pwm_f_x {
+			mux {
+				groups = "pwm_f_x";
+				function = "pwm_f_x";
+			};
 		};
 
-		ethmac: ethernet@c9410000 {
-			compatible = "amlogic,meson-gxbb-dwmac", "snps,dwmac";
-			reg = <0x0 0xc9410000 0x0 0x10000
-			       0x0 0xc8834540 0x0 0x4>;
-			interrupts = <0 8 1>;
-			interrupt-names = "macirq";
-			clocks = <&clkc CLKID_ETH>,
-				 <&clkc CLKID_FCLK_DIV2>,
-				 <&clkc CLKID_MPLL2>;
-			clock-names = "stmmaceth", "clkin0", "clkin1";
-			phy-mode = "rgmii";
-			status = "disabled";
+		pwm_f_y_pins: pwm_f_y {
+			mux {
+				groups = "pwm_f_y";
+				function = "pwm_f_y";
+			};
 		};
 	};
 };
+
+&hiubus {
+	clkc: clock-controller@0 {
+		compatible = "amlogic,gxbb-clkc";
+		#clock-cells = <1>;
+		reg = <0x0 0x0 0x0 0x3db>;
+	};
+
+	mailbox: mailbox@404 {
+		compatible = "amlogic,meson-gxbb-mhu";
+		reg = <0 0x404 0 0x4c>;
+		interrupts = <0 208 IRQ_TYPE_EDGE_RISING>,
+			     <0 209 IRQ_TYPE_EDGE_RISING>,
+			     <0 210 IRQ_TYPE_EDGE_RISING>;
+		#mbox-cells = <1>;
+	};
+};
-- 
2.11.0

[PATCH for v4.9 LTS 07/86] net: phy: use boolean dt properties for eee broken modes

[Levin, Alexander (Sasha Levin)]

From: jbrunet <jbrunet@baylibre.com>

[ Upstream commit 57f3986231bb2c69a55ccab1d2b30a00818027ac ]

The patches regarding eee-broken-modes was merged before all people
involved could find an agreement on the best way to move forward.

While we agreed on having a DT property to mark particular modes as broken,
the value used for eee-broken-modes mapped the phy register in very direct
way. Because of this, the concern is that it could be used to implement
configuration policies instead of describing a broken HW.

In the end, having a boolean property for each mode seems to be preferred
over one bit field value mapping the register (too) directly.

Cc: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/net/phy/phy_device.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index d9ec74895e42..32b555a72e13 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1633,7 +1633,7 @@ static void of_set_phy_supported(struct phy_device *phydev)
 static void of_set_phy_eee_broken(struct phy_device *phydev)
 {
 	struct device_node *node = phydev->mdio.dev.of_node;
-	u32 broken;
+	u32 broken = 0;
 
 	if (!IS_ENABLED(CONFIG_OF_MDIO))
 		return;
@@ -1641,8 +1641,20 @@ static void of_set_phy_eee_broken(struct phy_device *phydev)
 	if (!node)
 		return;
 
-	if (!of_property_read_u32(node, "eee-broken-modes", &broken))
-		phydev->eee_broken_modes = broken;
+	if (of_property_read_bool(node, "eee-broken-100tx"))
+		broken |= MDIO_EEE_100TX;
+	if (of_property_read_bool(node, "eee-broken-1000t"))
+		broken |= MDIO_EEE_1000T;
+	if (of_property_read_bool(node, "eee-broken-10gt"))
+		broken |= MDIO_EEE_10GT;
+	if (of_property_read_bool(node, "eee-broken-1000kx"))
+		broken |= MDIO_EEE_1000KX;
+	if (of_property_read_bool(node, "eee-broken-10gkx4"))
+		broken |= MDIO_EEE_10GKX4;
+	if (of_property_read_bool(node, "eee-broken-10gkr"))
+		broken |= MDIO_EEE_10GKR;
+
+	phydev->eee_broken_modes = broken;
 }
 
 /**
-- 
2.11.0

[PATCH for v4.9 LTS 08/86] dt: bindings: net: use boolean dt properties for eee broken modes

[Levin, Alexander (Sasha Levin)]

From: jbrunet <jbrunet@baylibre.com>

[ Upstream commit 308d3165d8b2b98d3dc3d97d6662062735daea67 ]

The patches regarding eee-broken-modes was merged before all people
involved could find an agreement on the best way to move forward.

While we agreed on having a DT property to mark particular modes as broken,
the value used for eee-broken-modes mapped the phy register in very direct
way. Because of this, the concern is that it could be used to implement
configuration policies instead of describing a broken HW.

In the end, having a boolean property for each mode seems to be preferred
over one bit field value mapping the register (too) directly.

Cc: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 Documentation/devicetree/bindings/net/phy.txt |  9 +++++++++
 include/dt-bindings/net/mdio.h                | 19 -------------------
 2 files changed, 9 insertions(+), 19 deletions(-)
 delete mode 100644 include/dt-bindings/net/mdio.h

diff --git a/Documentation/devicetree/bindings/net/phy.txt b/Documentation/devicetree/bindings/net/phy.txt
index bc1c3c8bf8fa..62bdc5f2bf16 100644
--- a/Documentation/devicetree/bindings/net/phy.txt
+++ b/Documentation/devicetree/bindings/net/phy.txt
@@ -35,6 +35,15 @@ Optional Properties:
 - broken-turn-around: If set, indicates the PHY device does not correctly
   release the turn around line low at the end of a MDIO transaction.
 
+- eee-broken-100tx:
+- eee-broken-1000t:
+- eee-broken-10gt:
+- eee-broken-1000kx:
+- eee-broken-10gkx4:
+- eee-broken-10gkr:
+  Mark the corresponding energy efficient ethernet mode as broken and
+  request the ethernet to stop advertising it.
+
 Example:
 
 ethernet-phy@0 {
diff --git a/include/dt-bindings/net/mdio.h b/include/dt-bindings/net/mdio.h
deleted file mode 100644
index 99c6d903d439..000000000000
--- a/include/dt-bindings/net/mdio.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/*
- * This header provides generic constants for ethernet MDIO bindings
- */
-
-#ifndef _DT_BINDINGS_NET_MDIO_H
-#define _DT_BINDINGS_NET_MDIO_H
-
-/*
- * EEE capability Advertisement
- */
-
-#define MDIO_EEE_100TX		0x0002	/* 100TX EEE cap */
-#define MDIO_EEE_1000T		0x0004	/* 1000T EEE cap */
-#define MDIO_EEE_10GT		0x0008	/* 10GT EEE cap */
-#define MDIO_EEE_1000KX		0x0010	/* 1000KX EEE cap */
-#define MDIO_EEE_10GKX4		0x0020	/* 10G KX4 EEE cap */
-#define MDIO_EEE_10GKR		0x0040	/* 10G KR EEE cap */
-
-#endif
-- 
2.11.0

[PATCH for v4.9 LTS 12/86] perf/x86/intel: Handle exclusive threadid correctly on CPU hotplug

[Levin, Alexander (Sasha Levin)]

From: Zhou Chengming <zhouchengming1@huawei.com>

[ Upstream commit 4e71de7986386d5fd3765458f27d612931f27f5e ]

The CPU hotplug function intel_pmu_cpu_starting() sets
cpu_hw_events.excl_thread_id unconditionally to 1 when the shared exclusive
counters data structure is already availabe for the sibling thread.

This works during the boot process because the first sibling gets threadid
0 assigned and the second sibling which shares the data structure gets 1.

But when the first thread of the core is offlined and onlined again it
shares the data structure with the second thread and gets exclusive thread
id 1 assigned as well.

Prevent this by checking the threadid of the already online thread.

[ tglx: Rewrote changelog ]

Signed-off-by: Zhou Chengming <zhouchengming1@huawei.com>
Cc: NuoHan Qiao <qiaonuohan@huawei.com>
Cc: ak@linux.intel.com
Cc: peterz@infradead.org
Cc: kan.liang@intel.com
Cc: dave.hansen@linux.intel.com
Cc: eranian@google.com
Cc: qiaonuohan@huawei.com
Cc: davidcc@google.com
Cc: guohanjun@huawei.com
Link: http://lkml.kernel.org/r/1484536871-3131-1-git-send-email-zhouchengming1@huawei.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---					---
 arch/x86/events/intel/core.c |    7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 arch/x86/events/intel/core.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index cb8522290e6a..8d7a6a0f7d2f 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3164,13 +3164,16 @@ static void intel_pmu_cpu_starting(int cpu)
 
 	if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) {
 		for_each_cpu(i, topology_sibling_cpumask(cpu)) {
+			struct cpu_hw_events *sibling;
 			struct intel_excl_cntrs *c;
 
-			c = per_cpu(cpu_hw_events, i).excl_cntrs;
+			sibling = &per_cpu(cpu_hw_events, i);
+			c = sibling->excl_cntrs;
 			if (c && c->core_id == core_id) {
 				cpuc->kfree_on_online[1] = cpuc->excl_cntrs;
 				cpuc->excl_cntrs = c;
-				cpuc->excl_thread_id = 1;
+				if (!sibling->excl_thread_id)
+					cpuc->excl_thread_id = 1;
 				break;
 			}
 		}
-- 
2.11.0

[PATCH for v4.9 LTS 11/86] ARM64: dts: meson-gxbb-odroidc2: fix GbE tx link breakage

[Levin, Alexander (Sasha Levin)]

From: Jerome Brunet <jbrunet@baylibre.com>

[ Upstream commit feb3cbea0946c67060e2d5bcb7499b0a6f6700fe ]

OdroidC2 GbE link breaks under heavy tx transfer. This happens even if the
MAC does not enable Energy Efficient Ethernet (No Low Power state Idle on
the Tx path). The problem seems to come from the phy Rx path, entering the
LPI state.

Disabling EEE advertisement on the phy prevent this feature to be
negociated with the link partner and solve the issue.

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Kevin Hilman <khilman@baylibre.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts
index e6e3491d48a5..f150a4c63efe 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts
@@ -85,6 +85,18 @@
 	status = "okay";
 	pinctrl-0 = <&eth_pins>;
 	pinctrl-names = "default";
+	phy-handle = <&eth_phy0>;
+
+	mdio {
+		compatible = "snps,dwmac-mdio";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		eth_phy0: ethernet-phy@0 {
+			reg = <0>;
+			eee-broken-1000t;
+		};
+	};
 };
 
 &ir {
-- 
2.11.0

[PATCH for v4.9 LTS 10/86] ARM64: dts: meson-gx: Add firmware reserved memory zones

[Levin, Alexander (Sasha Levin)]

From: Neil Armstrong <narmstrong@baylibre.com>

[ Upstream commit bba8e3f42736cf7f974968a818e53b128286ad1d ]

The Amlogic Meson GXBB/GXL/GXM secure monitor uses part of the memory space,
this patch adds these reserved zones.

Without such reserved memory zones, running the following stress command :
$ stress-ng --vm 16 --vm-bytes 128M --timeout 10s
multiple times:

Could lead to the following kernel crashes :
[   46.937975] Bad mode in Error handler detected on CPU1, code 0xbf000000 -- SError
...
[   47.058536] Internal error: Attempting to execute userspace memory: 8600000f [#3] PREEMPT SMP
...
Instead of the OOM killer.

Fixes: 4f24eda8401f ("ARM64: dts: Prepare configs for Amlogic Meson GXBaby")
Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
Reviewed-by: Andreas Färber <afaerber@suse.de>
[khilman: added Fixes tag, added _reserved and unit addresses]
Signed-off-by: Kevin Hilman <khilman@baylibre.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>

Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 arch/arm64/boot/dts/amlogic/meson-gx.dtsi | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
index 0737056b369f..88849fe7aa66 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
@@ -55,6 +55,24 @@
 	#address-cells = <2>;
 	#size-cells = <2>;
 
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		/* 16 MiB reserved for Hardware ROM Firmware */
+		hwrom_reserved: hwrom@0 {
+			reg = <0x0 0x0 0x0 0x1000000>;
+			no-map;
+		};
+
+		/* 2 MiB reserved for ARM Trusted Firmware (BL31) */
+		secmon_reserved: secmon@10000000 {
+			reg = <0x0 0x10000000 0x0 0x200000>;
+			no-map;
+		};
+	};
+
 	cpus {
 		#address-cells = <0x2>;
 		#size-cells = <0x0>;
-- 
2.11.0

[PATCH for v4.9 LTS 13/86] ubifs: allow encryption ioctls in compat mode

[Levin, Alexander (Sasha Levin)]

From: Eric Biggers <ebiggers@google.com>

[ Upstream commit a75467d910135905de60b3af3f11b3693625781e ]

The ubifs encryption ioctls did not work when called by a 32-bit program
on a 64-bit kernel.  Since 'struct fscrypt_policy' is not affected by
the word size, ubifs just needs to allow these ioctls through, like what
ext4 and f2fs do.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 fs/ubifs/ioctl.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/ubifs/ioctl.c b/fs/ubifs/ioctl.c
index 3c7b29de0ca7..49d6c0f89c50 100644
--- a/fs/ubifs/ioctl.c
+++ b/fs/ubifs/ioctl.c
@@ -197,6 +197,9 @@ long ubifs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case FS_IOC32_SETFLAGS:
 		cmd = FS_IOC_SETFLAGS;
 		break;
+	case FS_IOC_SET_ENCRYPTION_POLICY:
+	case FS_IOC_GET_ENCRYPTION_POLICY:
+		break;
 	default:
 		return -ENOIOCTLCMD;
 	}
-- 
2.11.0

Re: [PATCH for v4.9 LTS 13/86] ubifs: allow encryption ioctls in compat mode

[Eric Biggers]

On Sat, Jun 17, 2017 at 10:24:31PM +0000, Levin, Alexander (Sasha Levin) wrote:
> From: Eric Biggers <ebiggers@google.com>
> 
> [ Upstream commit a75467d910135905de60b3af3f11b3693625781e ]
> 
> The ubifs encryption ioctls did not work when called by a 32-bit program
> on a 64-bit kernel.  Since 'struct fscrypt_policy' is not affected by
> the word size, ubifs just needs to allow these ioctls through, like what
> ext4 and f2fs do.
> 
> Signed-off-by: Eric Biggers <ebiggers@google.com>
> Signed-off-by: Richard Weinberger <richard@nod.at>
> Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
> ---
>  fs/ubifs/ioctl.c | 3 +++
>  1 file changed, 3 insertions(+)
> 
> diff --git a/fs/ubifs/ioctl.c b/fs/ubifs/ioctl.c
> index 3c7b29de0ca7..49d6c0f89c50 100644
> --- a/fs/ubifs/ioctl.c
> +++ b/fs/ubifs/ioctl.c
> @@ -197,6 +197,9 @@ long ubifs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
>  	case FS_IOC32_SETFLAGS:
>  		cmd = FS_IOC_SETFLAGS;
>  		break;
> +	case FS_IOC_SET_ENCRYPTION_POLICY:
> +	case FS_IOC_GET_ENCRYPTION_POLICY:
> +		break;
>  	default:
>  		return -ENOIOCTLCMD;
>  	}

UBIFS encryption was merged in 4.10, so this isn't needed in 4.9.

- Eric

Re: [PATCH for v4.9 LTS 13/86] ubifs: allow encryption ioctls in compat mode

[Richard Weinberger]

Am 19.06.2017 um 19:02 schrieb Eric Biggers:
> On Sat, Jun 17, 2017 at 10:24:31PM +0000, Levin, Alexander (Sasha Levin) wrote:
>> From: Eric Biggers <ebiggers@google.com>
>>
>> [ Upstream commit a75467d910135905de60b3af3f11b3693625781e ]
>>
>> The ubifs encryption ioctls did not work when called by a 32-bit program
>> on a 64-bit kernel.  Since 'struct fscrypt_policy' is not affected by
>> the word size, ubifs just needs to allow these ioctls through, like what
>> ext4 and f2fs do.
>>
>> Signed-off-by: Eric Biggers <ebiggers@google.com>
>> Signed-off-by: Richard Weinberger <richard@nod.at>
>> Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
>> ---
>>  fs/ubifs/ioctl.c | 3 +++
>>  1 file changed, 3 insertions(+)
>>
>> diff --git a/fs/ubifs/ioctl.c b/fs/ubifs/ioctl.c
>> index 3c7b29de0ca7..49d6c0f89c50 100644
>> --- a/fs/ubifs/ioctl.c
>> +++ b/fs/ubifs/ioctl.c
>> @@ -197,6 +197,9 @@ long ubifs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
>>  	case FS_IOC32_SETFLAGS:
>>  		cmd = FS_IOC_SETFLAGS;
>>  		break;
>> +	case FS_IOC_SET_ENCRYPTION_POLICY:
>> +	case FS_IOC_GET_ENCRYPTION_POLICY:
>> +		break;
>>  	default:
>>  		return -ENOIOCTLCMD;
>>  	}
> 
> UBIFS encryption was merged in 4.10, so this isn't needed in 4.9.

Yep. I wonder why this patch made it into the stable queue?

Thanks,
//richard

Re: [PATCH for v4.9 LTS 13/86] ubifs: allow encryption ioctls in compat mode

[Levin, Alexander (Sasha Levin)]

On Mon, Jun 19, 2017 at 09:21:44PM +0200, Richard Weinberger wrote:
>Am 19.06.2017 um 19:02 schrieb Eric Biggers:
>> On Sat, Jun 17, 2017 at 10:24:31PM +0000, Levin, Alexander (Sasha Levin) wrote:
>>> From: Eric Biggers <ebiggers@google.com>
>>>
>>> [ Upstream commit a75467d910135905de60b3af3f11b3693625781e ]
>>>
>>> The ubifs encryption ioctls did not work when called by a 32-bit program
>>> on a 64-bit kernel.  Since 'struct fscrypt_policy' is not affected by
>>> the word size, ubifs just needs to allow these ioctls through, like what
>>> ext4 and f2fs do.
>>>
>>> Signed-off-by: Eric Biggers <ebiggers@google.com>
>>> Signed-off-by: Richard Weinberger <richard@nod.at>
>>> Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
>>> ---
>>>  fs/ubifs/ioctl.c | 3 +++
>>>  1 file changed, 3 insertions(+)
>>>
>>> diff --git a/fs/ubifs/ioctl.c b/fs/ubifs/ioctl.c
>>> index 3c7b29de0ca7..49d6c0f89c50 100644
>>> --- a/fs/ubifs/ioctl.c
>>> +++ b/fs/ubifs/ioctl.c
>>> @@ -197,6 +197,9 @@ long ubifs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
>>>  	case FS_IOC32_SETFLAGS:
>>>  		cmd = FS_IOC_SETFLAGS;
>>>  		break;
>>> +	case FS_IOC_SET_ENCRYPTION_POLICY:
>>> +	case FS_IOC_GET_ENCRYPTION_POLICY:
>>> +		break;
>>>  	default:
>>>  		return -ENOIOCTLCMD;
>>>  	}
>>
>> UBIFS encryption was merged in 4.10, so this isn't needed in 4.9.

Thanks Eric, removed from queue.

>Yep. I wonder why this patch made it into the stable queue?

We're testing out a method of finding commits that aren't tagged for stable
but should be there. There is supposed to be more review for such commits
(I fucked it up in this case) + it's sent out for a review twice before
being shipped.

In general, it seems to have a good hit rate so far.

-- 

Thanks,
Sasha

Re: [PATCH for v4.9 LTS 13/86] ubifs: allow encryption ioctls in compat mode

[Richard Weinberger]

Sasha,

Am 19.06.2017 um 21:41 schrieb Levin, Alexander (Sasha Levin):
>> Yep. I wonder why this patch made it into the stable queue?
> 
> We're testing out a method of finding commits that aren't tagged for stable
> but should be there. There is supposed to be more review for such commits
> (I fucked it up in this case) + it's sent out for a review twice before
> being shipped.
> 
> In general, it seems to have a good hit rate so far.

Oh! Good to know. Usually I don't give much attention to stable mails
since I assume that only patches arrive which I have tagged as stable or asked
for inclusion.

Thanks,
//richard

[PATCH for v4.9 LTS 14/86] KVM: x86: fix fixing of hypercalls

[Levin, Alexander (Sasha Levin)]

From: Dmitry Vyukov <dvyukov@google.com>

[ Upstream commit ce2e852ecc9a42e4b8dabb46025cfef63209234a ]

emulator_fix_hypercall() replaces hypercall with vmcall instruction,
but it does not handle GP exception properly when writes the new instruction.
It can return X86EMUL_PROPAGATE_FAULT without setting exception information.
This leads to incorrect emulation and triggers
WARN_ON(ctxt->exception.vector > 0x1f) in x86_emulate_insn()
as discovered by syzkaller fuzzer:

WARNING: CPU: 2 PID: 18646 at arch/x86/kvm/emulate.c:5558
Call Trace:
 warn_slowpath_null+0x2c/0x40 kernel/panic.c:582
 x86_emulate_insn+0x16a5/0x4090 arch/x86/kvm/emulate.c:5572
 x86_emulate_instruction+0x403/0x1cc0 arch/x86/kvm/x86.c:5618
 emulate_instruction arch/x86/include/asm/kvm_host.h:1127 [inline]
 handle_exception+0x594/0xfd0 arch/x86/kvm/vmx.c:5762
 vmx_handle_exit+0x2b7/0x38b0 arch/x86/kvm/vmx.c:8625
 vcpu_enter_guest arch/x86/kvm/x86.c:6888 [inline]
 vcpu_run arch/x86/kvm/x86.c:6947 [inline]

Set exception information when write in emulator_fix_hypercall() fails.

Signed-off-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Wanpeng Li <wanpeng.li@hotmail.com>
Cc: kvm@vger.kernel.org
Cc: syzkaller@googlegroups.com
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 arch/x86/kvm/x86.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 62cde4f67c72..ab3f00399cbb 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6111,7 +6111,8 @@ static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt)
 
 	kvm_x86_ops->patch_hypercall(vcpu, instruction);
 
-	return emulator_write_emulated(ctxt, rip, instruction, 3, NULL);
+	return emulator_write_emulated(ctxt, rip, instruction, 3,
+		&ctxt->exception);
 }
 
 static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu)
-- 
2.11.0

[PATCH for v4.9 LTS 16/86] stmmac: add missing of_node_put

[Levin, Alexander (Sasha Levin)]

From: Julia Lawall <julia.lawall@lip6.fr>

[ Upstream commit a249708bc2aa1fe3ddf15dfac22bee519d15996b ]

The function stmmac_dt_phy provides several possibilities for initializing
plat->mdio_node, all of which have the effect of increasing the reference
count of the assigned value.  This field is not updated elsewhere, so the
value is live until the end of the lifetime of plat (devm_allocated), just
after the end of stmmac_remove_config_dt.  Thus, add an of_node_put on
plat->mdio_node in stmmac_remove_config_dt.  It is possible that the field
mdio_node is never initialized, but of_node_put is NULL-safe, so it is also
safe to call of_node_put in that case.

Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr>
Acked-by: Alexandre TORGUE <alexandre.torgue@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index ac3d39c69509..890e4b083f4f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -346,6 +346,7 @@ void stmmac_remove_config_dt(struct platform_device *pdev,
 	if (of_phy_is_fixed_link(np))
 		of_phy_deregister_fixed_link(np);
 	of_node_put(plat->phy_node);
+	of_node_put(plat->mdio_node);
 }
 #else
 struct plat_stmmacenet_data *
-- 
2.11.0

[PATCH for v4.9 LTS 15/86] scsi: sd: Fix wrong DPOFUA disable in sd_read_cache_type

[Levin, Alexander (Sasha Levin)]

From: Damien Le Moal <damien.lemoal@wdc.com>

[ Upstream commit 26f2819772af891dee2843e1f8662c58e5129d5f ]

Zoned block devices force the use of READ/WRITE(16) commands by setting
sdkp->use_16_for_rw and clearing sdkp->use_10_for_rw. This result in
DPOFUA always being disabled for these drives as the assumed use of
the deprecated READ/WRITE(6) commands only looks at sdkp->use_10_for_rw.
Strenghten the test by also checking that sdkp->use_16_for_rw is false.

Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/scsi/sd.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 931af0793951..13ac7e57a35d 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -2572,7 +2572,8 @@ sd_read_cache_type(struct scsi_disk *sdkp, unsigned char *buffer)
 		if (sdp->broken_fua) {
 			sd_first_printk(KERN_NOTICE, sdkp, "Disabling FUA\n");
 			sdkp->DPOFUA = 0;
-		} else if (sdkp->DPOFUA && !sdkp->device->use_10_for_rw) {
+		} else if (sdkp->DPOFUA && !sdkp->device->use_10_for_rw &&
+			   !sdkp->device->use_16_for_rw) {
 			sd_first_printk(KERN_NOTICE, sdkp,
 				  "Uses READ/WRITE(6), disabling FUA\n");
 			sdkp->DPOFUA = 0;
-- 
2.11.0

[PATCH for v4.9 LTS 17/86] scsi: lpfc: Set elsiocb contexts to NULL after freeing it

[Levin, Alexander (Sasha Levin)]

From: Johannes Thumshirn <jthumshirn@suse.de>

[ Upstream commit 8667f515952feefebb3c0f8d9a9266c91b101a46 ]

Set the elsiocb contexts to NULL after freeing as others depend on it.

Signed-off-by: Johannes Thumshirn <jthumshirn@suse.de>
Acked-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/scsi/lpfc/lpfc_els.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index b7d54bfb1df9..7b696d108112 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -3590,12 +3590,14 @@ lpfc_els_free_iocb(struct lpfc_hba *phba, struct lpfc_iocbq *elsiocb)
 		} else {
 			buf_ptr1 = (struct lpfc_dmabuf *) elsiocb->context2;
 			lpfc_els_free_data(phba, buf_ptr1);
+			elsiocb->context2 = NULL;
 		}
 	}
 
 	if (elsiocb->context3) {
 		buf_ptr = (struct lpfc_dmabuf *) elsiocb->context3;
 		lpfc_els_free_bpl(phba, buf_ptr);
+		elsiocb->context3 = NULL;
 	}
 	lpfc_sli_release_iocbq(phba, elsiocb);
 	return 0;
-- 
2.11.0

[PATCH for v4.9 LTS 19/86] qla2xxx: Fix erroneous invalid handle message

[Levin, Alexander (Sasha Levin)]

From: Quinn Tran <quinn.tran@cavium.com>

[ Upstream commit 4f060736f29a960aba8e781a88837464756200a8 ]

Termination of Immediate Notify IOCB was using wrong
IOCB handle. IOCB completion code was unable to find
appropriate code path due to wrong handle.

Following message is seen in the logs.

"Error entry - invalid handle/queue (ffff)."

Signed-off-by: Quinn Tran <quinn.tran@cavium.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
[ bvanassche: Fixed word order in patch title ]
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>

Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/scsi/qla2xxx/qla_isr.c    | 4 ++++
 drivers/scsi/qla2xxx/qla_target.c | 2 +-
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 068c4e47fac9..bddaabb288d4 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -2487,6 +2487,10 @@ qla2x00_error_entry(scsi_qla_host_t *vha, struct rsp_que *rsp, sts_entry_t *pkt)
 	if (pkt->entry_status & RF_BUSY)
 		res = DID_BUS_BUSY << 16;
 
+	if (pkt->entry_type == NOTIFY_ACK_TYPE &&
+	    pkt->handle == QLA_TGT_SKIP_HANDLE)
+		return;
+
 	sp = qla2x00_get_sp_from_handle(vha, func, req, pkt);
 	if (sp) {
 		sp->done(ha, sp, res);
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index ee450b6965f3..91f5f55a8a9b 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -3067,7 +3067,7 @@ static int __qlt_send_term_imm_notif(struct scsi_qla_host *vha,
 
 	pkt->entry_type = NOTIFY_ACK_TYPE;
 	pkt->entry_count = 1;
-	pkt->handle = QLA_TGT_SKIP_HANDLE | CTIO_COMPLETION_HANDLE_MARK;
+	pkt->handle = QLA_TGT_SKIP_HANDLE;
 
 	nack = (struct nack_to_isp *)pkt;
 	nack->ox_id = ntfy->ox_id;
-- 
2.11.0

[PATCH for v4.9 LTS 18/86] qla2xxx: Terminate exchange if corrupted

[Levin, Alexander (Sasha Levin)]

From: Quinn Tran <quinn.tran@cavium.com>

[ Upstream commit 5f35509db179ca7ed1feaa4b14f841adb06ed220 ]

Corrupted ATIO is defined as length of fcp_header & fcp_cmd
payload is less than 0x38. It's the minimum size for a frame to
carry 8..16 bytes SCSI CDB. The exchange will be dropped or
terminated if corrupted.

Signed-off-by: Quinn Tran <quinn.tran@cavium.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
[ bvanassche: Fixed spelling in patch title ]
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>

Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/scsi/qla2xxx/qla_def.h    |  3 ++-
 drivers/scsi/qla2xxx/qla_target.c | 23 ++++++++++++++++++++---
 drivers/scsi/qla2xxx/qla_target.h | 22 +++++++++++++++++++++-
 3 files changed, 43 insertions(+), 5 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 8e63a7b90277..91ec0689c714 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -1555,7 +1555,8 @@ typedef struct {
 struct atio {
 	uint8_t		entry_type;		/* Entry type. */
 	uint8_t		entry_count;		/* Entry count. */
-	uint8_t		data[58];
+	__le16		attr_n_length;
+	uint8_t		data[56];
 	uint32_t	signature;
 #define ATIO_PROCESSED 0xDEADDEAD		/* Signature */
 };
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index feab7ea8e823..ee450b6965f3 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -6463,12 +6463,29 @@ qlt_24xx_process_atio_queue(struct scsi_qla_host *vha, uint8_t ha_locked)
 	if (!vha->flags.online)
 		return;
 
-	while (ha->tgt.atio_ring_ptr->signature != ATIO_PROCESSED) {
+	while ((ha->tgt.atio_ring_ptr->signature != ATIO_PROCESSED) ||
+	    fcpcmd_is_corrupted(ha->tgt.atio_ring_ptr)) {
 		pkt = (struct atio_from_isp *)ha->tgt.atio_ring_ptr;
 		cnt = pkt->u.raw.entry_count;
 
-		qlt_24xx_atio_pkt_all_vps(vha, (struct atio_from_isp *)pkt,
-		    ha_locked);
+		if (unlikely(fcpcmd_is_corrupted(ha->tgt.atio_ring_ptr))) {
+			/*
+			 * This packet is corrupted. The header + payload
+			 * can not be trusted. There is no point in passing
+			 * it further up.
+			 */
+			ql_log(ql_log_warn, vha, 0xffff,
+			    "corrupted fcp frame SID[%3phN] OXID[%04x] EXCG[%x] %64phN\n",
+			    pkt->u.isp24.fcp_hdr.s_id,
+			    be16_to_cpu(pkt->u.isp24.fcp_hdr.ox_id),
+			    le32_to_cpu(pkt->u.isp24.exchange_addr), pkt);
+
+			adjust_corrupted_atio(pkt);
+			qlt_send_term_exchange(vha, NULL, pkt, ha_locked, 0);
+		} else {
+			qlt_24xx_atio_pkt_all_vps(vha,
+			    (struct atio_from_isp *)pkt, ha_locked);
+		}
 
 		for (i = 0; i < cnt; i++) {
 			ha->tgt.atio_ring_index++;
diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h
index f26c5f60eedd..0824a8164a24 100644
--- a/drivers/scsi/qla2xxx/qla_target.h
+++ b/drivers/scsi/qla2xxx/qla_target.h
@@ -427,13 +427,33 @@ struct atio_from_isp {
 		struct {
 			uint8_t  entry_type;	/* Entry type. */
 			uint8_t  entry_count;	/* Entry count. */
-			uint8_t  data[58];
+			__le16	 attr_n_length;
+#define FCP_CMD_LENGTH_MASK 0x0fff
+#define FCP_CMD_LENGTH_MIN  0x38
+			uint8_t  data[56];
 			uint32_t signature;
 #define ATIO_PROCESSED 0xDEADDEAD		/* Signature */
 		} raw;
 	} u;
 } __packed;
 
+static inline int fcpcmd_is_corrupted(struct atio *atio)
+{
+	if (atio->entry_type == ATIO_TYPE7 &&
+	    (le16_to_cpu(atio->attr_n_length & FCP_CMD_LENGTH_MASK) <
+	    FCP_CMD_LENGTH_MIN))
+		return 1;
+	else
+		return 0;
+}
+
+/* adjust corrupted atio so we won't trip over the same entry again. */
+static inline void adjust_corrupted_atio(struct atio_from_isp *atio)
+{
+	atio->u.raw.attr_n_length = cpu_to_le16(FCP_CMD_LENGTH_MIN);
+	atio->u.isp24.fcp_cmnd.add_cdb_len = 0;
+}
+
 #define CTIO_TYPE7 0x12 /* Continue target I/O entry (for 24xx) */
 
 /*
-- 
2.11.0

[PATCH for v4.9 LTS 20/86] drm/amdgpu: fix program vce instance logic error.

[Levin, Alexander (Sasha Levin)]

From: Rex Zhu <Rex.Zhu@amd.com>

[ Upstream commit 50a1ebc70a2803deb7811fc73fb55d70e353bc34 ]

need to clear bit31-29 in GRBM_GFX_INDEX,
then the program can be valid.

Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/gpu/drm/amd/amdgpu/vce_v3_0.c | 25 ++++++++++++++++---------
 1 file changed, 16 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index 6feed726e299..50f0cf2788b7 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
@@ -43,9 +43,13 @@
 
 #define GRBM_GFX_INDEX__VCE_INSTANCE__SHIFT	0x04
 #define GRBM_GFX_INDEX__VCE_INSTANCE_MASK	0x10
+#define GRBM_GFX_INDEX__VCE_ALL_PIPE		0x07
+
 #define mmVCE_LMI_VCPU_CACHE_40BIT_BAR0	0x8616
 #define mmVCE_LMI_VCPU_CACHE_40BIT_BAR1	0x8617
 #define mmVCE_LMI_VCPU_CACHE_40BIT_BAR2	0x8618
+#define mmGRBM_GFX_INDEX_DEFAULT 0xE0000000
+
 #define VCE_STATUS_VCPU_REPORT_FW_LOADED_MASK	0x02
 
 #define VCE_V3_0_FW_SIZE	(384 * 1024)
@@ -54,6 +58,9 @@
 
 #define FW_52_8_3	((52 << 24) | (8 << 16) | (3 << 8))
 
+#define GET_VCE_INSTANCE(i)  ((i) << GRBM_GFX_INDEX__VCE_INSTANCE__SHIFT \
+					| GRBM_GFX_INDEX__VCE_ALL_PIPE)
+
 static void vce_v3_0_mc_resume(struct amdgpu_device *adev, int idx);
 static void vce_v3_0_set_ring_funcs(struct amdgpu_device *adev);
 static void vce_v3_0_set_irq_funcs(struct amdgpu_device *adev);
@@ -249,7 +256,7 @@ static int vce_v3_0_start(struct amdgpu_device *adev)
 		if (adev->vce.harvest_config & (1 << idx))
 			continue;
 
-		WREG32_FIELD(GRBM_GFX_INDEX, VCE_INSTANCE, idx);
+		WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(idx));
 		vce_v3_0_mc_resume(adev, idx);
 		WREG32_FIELD(VCE_STATUS, JOB_BUSY, 1);
 
@@ -273,7 +280,7 @@ static int vce_v3_0_start(struct amdgpu_device *adev)
 		}
 	}
 
-	WREG32_FIELD(GRBM_GFX_INDEX, VCE_INSTANCE, 0);
+	WREG32(mmGRBM_GFX_INDEX, mmGRBM_GFX_INDEX_DEFAULT);
 	mutex_unlock(&adev->grbm_idx_mutex);
 
 	return 0;
@@ -288,7 +295,7 @@ static int vce_v3_0_stop(struct amdgpu_device *adev)
 		if (adev->vce.harvest_config & (1 << idx))
 			continue;
 
-		WREG32_FIELD(GRBM_GFX_INDEX, VCE_INSTANCE, idx);
+		WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(idx));
 
 		if (adev->asic_type >= CHIP_STONEY)
 			WREG32_P(mmVCE_VCPU_CNTL, 0, ~0x200001);
@@ -306,7 +313,7 @@ static int vce_v3_0_stop(struct amdgpu_device *adev)
 			vce_v3_0_set_vce_sw_clock_gating(adev, false);
 	}
 
-	WREG32_FIELD(GRBM_GFX_INDEX, VCE_INSTANCE, 0);
+	WREG32(mmGRBM_GFX_INDEX, mmGRBM_GFX_INDEX_DEFAULT);
 	mutex_unlock(&adev->grbm_idx_mutex);
 
 	return 0;
@@ -586,17 +593,17 @@ static bool vce_v3_0_check_soft_reset(void *handle)
 	 * VCE team suggest use bit 3--bit 6 for busy status check
 	 */
 	mutex_lock(&adev->grbm_idx_mutex);
-	WREG32_FIELD(GRBM_GFX_INDEX, INSTANCE_INDEX, 0);
+	WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(0));
 	if (RREG32(mmVCE_STATUS) & AMDGPU_VCE_STATUS_BUSY_MASK) {
 		srbm_soft_reset = REG_SET_FIELD(srbm_soft_reset, SRBM_SOFT_RESET, SOFT_RESET_VCE0, 1);
 		srbm_soft_reset = REG_SET_FIELD(srbm_soft_reset, SRBM_SOFT_RESET, SOFT_RESET_VCE1, 1);
 	}
-	WREG32_FIELD(GRBM_GFX_INDEX, INSTANCE_INDEX, 0x10);
+	WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(1));
 	if (RREG32(mmVCE_STATUS) & AMDGPU_VCE_STATUS_BUSY_MASK) {
 		srbm_soft_reset = REG_SET_FIELD(srbm_soft_reset, SRBM_SOFT_RESET, SOFT_RESET_VCE0, 1);
 		srbm_soft_reset = REG_SET_FIELD(srbm_soft_reset, SRBM_SOFT_RESET, SOFT_RESET_VCE1, 1);
 	}
-	WREG32_FIELD(GRBM_GFX_INDEX, INSTANCE_INDEX, 0);
+	WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(0));
 	mutex_unlock(&adev->grbm_idx_mutex);
 
 	if (srbm_soft_reset) {
@@ -734,7 +741,7 @@ static int vce_v3_0_set_clockgating_state(void *handle,
 		if (adev->vce.harvest_config & (1 << i))
 			continue;
 
-		WREG32_FIELD(GRBM_GFX_INDEX, VCE_INSTANCE, i);
+		WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(i));
 
 		if (enable) {
 			/* initialize VCE_CLOCK_GATING_A: Clock ON/OFF delay */
@@ -753,7 +760,7 @@ static int vce_v3_0_set_clockgating_state(void *handle,
 		vce_v3_0_set_vce_sw_clock_gating(adev, enable);
 	}
 
-	WREG32_FIELD(GRBM_GFX_INDEX, VCE_INSTANCE, 0);
+	WREG32(mmGRBM_GFX_INDEX, mmGRBM_GFX_INDEX_DEFAULT);
 	mutex_unlock(&adev->grbm_idx_mutex);
 
 	return 0;
-- 
2.11.0

[PATCH for v4.9 LTS 21/86] drm/amdgpu: add support for new hainan variants

[Levin, Alexander (Sasha Levin)]

From: Alex Deucher <alexander.deucher@amd.com>

[ Upstream commit 17324b6add82d6c0bf119f1d1944baef392a4e39 ]

New hainan parts require updated smc firmware.

Cc: Sonny Jiang <sonny.jiang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/gpu/drm/amd/amdgpu/si_dpm.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
index 6f3c89178b6a..4cb347e88cf0 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
@@ -64,6 +64,7 @@ MODULE_FIRMWARE("radeon/oland_smc.bin");
 MODULE_FIRMWARE("radeon/oland_k_smc.bin");
 MODULE_FIRMWARE("radeon/hainan_smc.bin");
 MODULE_FIRMWARE("radeon/hainan_k_smc.bin");
+MODULE_FIRMWARE("radeon/banks_k_2_smc.bin");
 
 union power_info {
 	struct _ATOM_POWERPLAY_INFO info;
@@ -7721,10 +7722,11 @@ static int si_dpm_init_microcode(struct amdgpu_device *adev)
 			((adev->pdev->device == 0x6660) ||
 			(adev->pdev->device == 0x6663) ||
 			(adev->pdev->device == 0x6665) ||
-			(adev->pdev->device == 0x6667))) ||
-		    ((adev->pdev->revision == 0xc3) &&
-			(adev->pdev->device == 0x6665)))
+			 (adev->pdev->device == 0x6667))))
 			chip_name = "hainan_k";
+		else if ((adev->pdev->revision == 0xc3) &&
+			 (adev->pdev->device == 0x6665))
+			chip_name = "banks_k_2";
 		else
 			chip_name = "hainan";
 		break;
-- 
2.11.0

[PATCH for v4.9 LTS 22/86] net: phy: dp83848: add DP83620 PHY support

[Levin, Alexander (Sasha Levin)]

From: "Alvaro G. M" <alvaro.gamez@hazent.com>

[ Upstream commit 93b43fd137cd8865adf9978ab9870a344365d3af ]

This PHY with fiber support is register compatible with DP83848,
so add support for it.

Signed-off-by: Alvaro Gamez Machado <alvaro.gamez@hazent.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/net/phy/dp83848.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/phy/dp83848.c b/drivers/net/phy/dp83848.c
index 800b39f06279..a10d0e7fc5f7 100644
--- a/drivers/net/phy/dp83848.c
+++ b/drivers/net/phy/dp83848.c
@@ -17,6 +17,7 @@
 #include <linux/phy.h>
 
 #define TI_DP83848C_PHY_ID		0x20005ca0
+#define TI_DP83620_PHY_ID		0x20005ce0
 #define NS_DP83848C_PHY_ID		0x20005c90
 #define TLK10X_PHY_ID			0x2000a210
 #define TI_DP83822_PHY_ID		0x2000a240
@@ -77,6 +78,7 @@ static int dp83848_config_intr(struct phy_device *phydev)
 static struct mdio_device_id __maybe_unused dp83848_tbl[] = {
 	{ TI_DP83848C_PHY_ID, 0xfffffff0 },
 	{ NS_DP83848C_PHY_ID, 0xfffffff0 },
+	{ TI_DP83620_PHY_ID, 0xfffffff0 },
 	{ TLK10X_PHY_ID, 0xfffffff0 },
 	{ TI_DP83822_PHY_ID, 0xfffffff0 },
 	{ }
@@ -106,6 +108,7 @@ MODULE_DEVICE_TABLE(mdio, dp83848_tbl);
 static struct phy_driver dp83848_driver[] = {
 	DP83848_PHY_DRIVER(TI_DP83848C_PHY_ID, "TI DP83848C 10/100 Mbps PHY"),
 	DP83848_PHY_DRIVER(NS_DP83848C_PHY_ID, "NS DP83848C 10/100 Mbps PHY"),
+	DP83848_PHY_DRIVER(TI_DP83620_PHY_ID, "TI DP83620 10/100 Mbps PHY"),
 	DP83848_PHY_DRIVER(TLK10X_PHY_ID, "TI TLK10X 10/100 Mbps PHY"),
 	DP83848_PHY_DRIVER(TI_DP83822_PHY_ID, "TI DP83822 10/100 Mbps PHY"),
 };
-- 
2.11.0

[PATCH for v4.9 LTS 23/86] powerpc/eeh: Enable IO path on permanent error

[Levin, Alexander (Sasha Levin)]

From: Gavin Shan <gwshan@linux.vnet.ibm.com>

[ Upstream commit 387bbc974f6adf91aa635090f73434ed10edd915 ]

We give up recovery on permanent error, simply shutdown the affected
devices and remove them. If the devices can't be put into quiet state,
they spew more traffic that is likely to cause another unexpected EEH
error. This was observed on "p8dtu2u" machine:

   0002:00:00.0 PCI bridge: IBM Device 03dc
   0002:01:00.0 Ethernet controller: Intel Corporation \
                Ethernet Controller X710/X557-AT 10GBASE-T (rev 02)
   0002:01:00.1 Ethernet controller: Intel Corporation \
                Ethernet Controller X710/X557-AT 10GBASE-T (rev 02)
   0002:01:00.2 Ethernet controller: Intel Corporation \
                Ethernet Controller X710/X557-AT 10GBASE-T (rev 02)
   0002:01:00.3 Ethernet controller: Intel Corporation \
                Ethernet Controller X710/X557-AT 10GBASE-T (rev 02)

On P8 PowerNV platform, the IO path is frozen when shutdowning the
devices, meaning the memory registers are inaccessible. It is why
the devices can't be put into quiet state before removing them.
This fixes the issue by enabling IO path prior to putting the devices
into quiet state.

Reported-by: Pridhiviraj Paidipeddi <ppaidipe@linux.vnet.ibm.com>
Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Acked-by: Russell Currey <ruscur@russell.cc>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 arch/powerpc/kernel/eeh.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index f25731627d7f..e5bfbf62827a 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -298,9 +298,17 @@ void eeh_slot_error_detail(struct eeh_pe *pe, int severity)
 	 *
 	 * For pHyp, we have to enable IO for log retrieval. Otherwise,
 	 * 0xFF's is always returned from PCI config space.
+	 *
+	 * When the @severity is EEH_LOG_PERM, the PE is going to be
+	 * removed. Prior to that, the drivers for devices included in
+	 * the PE will be closed. The drivers rely on working IO path
+	 * to bring the devices to quiet state. Otherwise, PCI traffic
+	 * from those devices after they are removed is like to cause
+	 * another unexpected EEH error.
 	 */
 	if (!(pe->type & EEH_PE_PHB)) {
-		if (eeh_has_flag(EEH_ENABLE_IO_FOR_LOG))
+		if (eeh_has_flag(EEH_ENABLE_IO_FOR_LOG) ||
+		    severity == EEH_LOG_PERM)
 			eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
 
 		/*
-- 
2.11.0

[PATCH for v4.9 LTS 24/86] net: ethtool: Initialize buffer when querying device channel settings

[Levin, Alexander (Sasha Levin)]

From: Eran Ben Elisha <eranbe@mellanox.com>

[ Upstream commit 31a86d137219373c3222ca5f4f912e9a4d8065bb ]

Ethtool channels respond struct was uninitialized when querying device
channel boundaries settings. As a result, unreported fields by the driver
hold garbage.  This may cause sending unsupported params to driver.

Fixes: 8bf368620486 ('ethtool: ensure channel counts are within bounds ...')
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
CC: John W. Linville <linville@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 net/core/ethtool.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 072c1f4998c9..e9989b835a66 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1704,7 +1704,7 @@ static noinline_for_stack int ethtool_get_channels(struct net_device *dev,
 static noinline_for_stack int ethtool_set_channels(struct net_device *dev,
 						   void __user *useraddr)
 {
-	struct ethtool_channels channels, max;
+	struct ethtool_channels channels, max = { .cmd = ETHTOOL_GCHANNELS };
 	u32 max_rx_in_use = 0;
 
 	if (!dev->ethtool_ops->set_channels || !dev->ethtool_ops->get_channels)
-- 
2.11.0

[PATCH for v4.9 LTS 25/86] xen-netback: fix memory leaks on XenBus disconnect

[Levin, Alexander (Sasha Levin)]

From: Igor Druzhinin <igor.druzhinin@citrix.com>

[ Upstream commit 9a6cdf52b85ea5fb21d2bb31e4a7bc61b79923a7 ]

Eliminate memory leaks introduced several years ago by cleaning the
queue resources which are allocated on XenBus connection event. Namely, queue
structure array and pages used for IO rings.

Signed-off-by: Igor Druzhinin <igor.druzhinin@citrix.com>
Reviewed-by: Paul Durrant <paul.durrant@citrix.com>
Acked-by: Wei Liu <wei.liu2@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/net/xen-netback/xenbus.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index 8674e188b697..abffdbded5f2 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -493,11 +493,20 @@ static int backend_create_xenvif(struct backend_info *be)
 static void backend_disconnect(struct backend_info *be)
 {
 	if (be->vif) {
+		unsigned int queue_index;
+
 		xen_unregister_watchers(be->vif);
 #ifdef CONFIG_DEBUG_FS
 		xenvif_debugfs_delif(be->vif);
 #endif /* CONFIG_DEBUG_FS */
 		xenvif_disconnect_data(be->vif);
+		for (queue_index = 0; queue_index < be->vif->num_queues; ++queue_index)
+			xenvif_deinit_queue(&be->vif->queues[queue_index]);
+
+		vfree(be->vif->queues);
+		be->vif->num_queues = 0;
+		be->vif->queues = NULL;
+
 		xenvif_disconnect_ctrl(be->vif);
 	}
 }
@@ -1040,6 +1049,8 @@ static void connect(struct backend_info *be)
 err:
 	if (be->vif->num_queues > 0)
 		xenvif_disconnect_data(be->vif); /* Clean up existing queues */
+	for (queue_index = 0; queue_index < be->vif->num_queues; ++queue_index)
+		xenvif_deinit_queue(&be->vif->queues[queue_index]);
 	vfree(be->vif->queues);
 	be->vif->queues = NULL;
 	be->vif->num_queues = 0;
-- 
2.11.0

[PATCH for v4.9 LTS 26/86] xen-netback: protect resource cleaning on XenBus disconnect

[Levin, Alexander (Sasha Levin)]

From: Igor Druzhinin <igor.druzhinin@citrix.com>

[ Upstream commit f16f1df65f1cf139ff9e9f84661e6573d6bb27fc ]

vif->lock is used to protect statistics gathering agents from using the
queue structure during cleaning.

Signed-off-by: Igor Druzhinin <igor.druzhinin@citrix.com>
Acked-by: Wei Liu <wei.liu2@citrix.com>
Reviewed-by: Paul Durrant <paul.durrant@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/net/xen-netback/interface.c | 6 ++++--
 drivers/net/xen-netback/xenbus.c    | 2 ++
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 74dc2bf71428..b009d7966b46 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -221,18 +221,18 @@ static struct net_device_stats *xenvif_get_stats(struct net_device *dev)
 {
 	struct xenvif *vif = netdev_priv(dev);
 	struct xenvif_queue *queue = NULL;
-	unsigned int num_queues = vif->num_queues;
 	unsigned long rx_bytes = 0;
 	unsigned long rx_packets = 0;
 	unsigned long tx_bytes = 0;
 	unsigned long tx_packets = 0;
 	unsigned int index;
 
+	spin_lock(&vif->lock);
 	if (vif->queues == NULL)
 		goto out;
 
 	/* Aggregate tx and rx stats from each queue */
-	for (index = 0; index < num_queues; ++index) {
+	for (index = 0; index < vif->num_queues; ++index) {
 		queue = &vif->queues[index];
 		rx_bytes += queue->stats.rx_bytes;
 		rx_packets += queue->stats.rx_packets;
@@ -241,6 +241,8 @@ static struct net_device_stats *xenvif_get_stats(struct net_device *dev)
 	}
 
 out:
+	spin_unlock(&vif->lock);
+
 	vif->dev->stats.rx_bytes = rx_bytes;
 	vif->dev->stats.rx_packets = rx_packets;
 	vif->dev->stats.tx_bytes = tx_bytes;
diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index abffdbded5f2..b44f37fff890 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -503,9 +503,11 @@ static void backend_disconnect(struct backend_info *be)
 		for (queue_index = 0; queue_index < be->vif->num_queues; ++queue_index)
 			xenvif_deinit_queue(&be->vif->queues[queue_index]);
 
+		spin_lock(&be->vif->lock);
 		vfree(be->vif->queues);
 		be->vif->num_queues = 0;
 		be->vif->queues = NULL;
+		spin_unlock(&be->vif->lock);
 
 		xenvif_disconnect_ctrl(be->vif);
 	}
-- 
2.11.0

[PATCH for v4.9 LTS 27/86] bnxt_en: Fix "uninitialized variable" bug in TPA code path.

[Levin, Alexander (Sasha Levin)]

From: Michael Chan <michael.chan@broadcom.com>

[ Upstream commit 719ca8111402aa6157bd83a3c966d184db0d8956 ]

In the TPA GRO code path, initialize the tcp_opt_len variable to 0 so
that it will be correct for packets without TCP timestamps.  The bug
caused the SKB fields to be incorrectly set up for packets without
TCP timestamps, leading to these packets being rejected by the stack.

Reported-by: Andy Gospodarek <andrew.gospodarek@broadocm.com>
Acked-by: Andy Gospodarek <andrew.gospodarek@broadocm.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 5cc0f8cfec87..20e569bd978a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1097,7 +1097,7 @@ static struct sk_buff *bnxt_gro_func_5730x(struct bnxt_tpa_info *tpa_info,
 {
 #ifdef CONFIG_INET
 	struct tcphdr *th;
-	int len, nw_off, tcp_opt_len;
+	int len, nw_off, tcp_opt_len = 0;
 
 	if (tcp_ts)
 		tcp_opt_len = 12;
-- 
2.11.0

[PATCH for v4.9 LTS 29/86] objtool: Fix IRET's opcode

[Levin, Alexander (Sasha Levin)]

From: Jiri Slaby <jslaby@suse.cz>

[ Upstream commit b5b46c4740aed1538544f0fa849c5b76c7823469 ]

The IRET opcode is 0xcf according to the Intel manual and also to objdump of my
vmlinux:

    1ea8:       48 cf                   iretq

Fix the opcode in arch_decode_instruction().

The previous value (0xc5) seems to correspond to LDS.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Acked-by: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20170118132921.19319-1-jslaby@suse.cz
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 tools/objtool/arch/x86/decode.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 5e0dea2cdc01..039636ffb6c8 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -150,9 +150,9 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
 		*type = INSN_RETURN;
 		break;
 
-	case 0xc5: /* iret */
 	case 0xca: /* retf */
 	case 0xcb: /* retf */
+	case 0xcf: /* iret */
 		*type = INSN_CONTEXT_SWITCH;
 		break;
 
-- 
2.11.0

[PATCH for v4.9 LTS 28/86] bpf: don't trigger OOM killer under pressure with map alloc

[Levin, Alexander (Sasha Levin)]

From: Daniel Borkmann <daniel@iogearbox.net>

[ Upstream commit d407bd25a204bd66b7346dde24bd3d37ef0e0b05 ]

This patch adds two helpers, bpf_map_area_alloc() and bpf_map_area_free(),
that are to be used for map allocations. Using kmalloc() for very large
allocations can cause excessive work within the page allocator, so i) fall
back earlier to vmalloc() when the attempt is considered costly anyway,
and even more importantly ii) don't trigger OOM killer with any of the
allocators.

Since this is based on a user space request, for example, when creating
maps with element pre-allocation, we really want such requests to fail
instead of killing other user space processes.

Also, don't spam the kernel log with warnings should any of the allocations
fail under pressure. Given that, we can make backend selection in
bpf_map_area_alloc() generic, and convert all maps over to use this API
for spots with potentially large allocation requests.

Note, replacing the one kmalloc_array() is fine as overflow checks happen
earlier in htab_map_alloc(), since it must also protect the multiplication
for vmalloc() should kmalloc_array() fail.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 include/linux/bpf.h   |  2 ++
 kernel/bpf/arraymap.c | 18 +++++++-----------
 kernel/bpf/hashtab.c  | 22 +++++++++-------------
 kernel/bpf/stackmap.c | 20 ++++++++------------
 kernel/bpf/syscall.c  | 26 ++++++++++++++++++++++++++
 5 files changed, 52 insertions(+), 36 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index c201017b5730..97498be2ca2e 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -243,6 +243,8 @@ struct bpf_map *bpf_map_inc(struct bpf_map *map, bool uref);
 void bpf_map_put_with_uref(struct bpf_map *map);
 void bpf_map_put(struct bpf_map *map);
 int bpf_map_precharge_memlock(u32 pages);
+void *bpf_map_area_alloc(size_t size);
+void bpf_map_area_free(void *base);
 
 extern int sysctl_unprivileged_bpf_disabled;
 
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index a2ac051c342f..f3721e150d94 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -11,7 +11,6 @@
  */
 #include <linux/bpf.h>
 #include <linux/err.h>
-#include <linux/vmalloc.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/filter.h>
@@ -74,14 +73,10 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 	if (array_size >= U32_MAX - PAGE_SIZE)
 		return ERR_PTR(-ENOMEM);
 
-
 	/* allocate all map elements and zero-initialize them */
-	array = kzalloc(array_size, GFP_USER | __GFP_NOWARN);
-	if (!array) {
-		array = vzalloc(array_size);
-		if (!array)
-			return ERR_PTR(-ENOMEM);
-	}
+	array = bpf_map_area_alloc(array_size);
+	if (!array)
+		return ERR_PTR(-ENOMEM);
 
 	/* copy mandatory map attributes */
 	array->map.map_type = attr->map_type;
@@ -97,7 +92,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 
 	if (array_size >= U32_MAX - PAGE_SIZE ||
 	    elem_size > PCPU_MIN_UNIT_SIZE || bpf_array_alloc_percpu(array)) {
-		kvfree(array);
+		bpf_map_area_free(array);
 		return ERR_PTR(-ENOMEM);
 	}
 out:
@@ -262,7 +257,7 @@ static void array_map_free(struct bpf_map *map)
 	if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
 		bpf_array_free_percpu(array);
 
-	kvfree(array);
+	bpf_map_area_free(array);
 }
 
 static const struct bpf_map_ops array_ops = {
@@ -319,7 +314,8 @@ static void fd_array_map_free(struct bpf_map *map)
 	/* make sure it's empty */
 	for (i = 0; i < array->map.max_entries; i++)
 		BUG_ON(array->ptrs[i] != NULL);
-	kvfree(array);
+
+	bpf_map_area_free(array);
 }
 
 static void *fd_array_map_lookup_elem(struct bpf_map *map, void *key)
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index ad1bc67aff1b..ad2f0ed75471 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -13,7 +13,6 @@
 #include <linux/bpf.h>
 #include <linux/jhash.h>
 #include <linux/filter.h>
-#include <linux/vmalloc.h>
 #include "percpu_freelist.h"
 
 struct bucket {
@@ -84,14 +83,15 @@ static void htab_free_elems(struct bpf_htab *htab)
 		free_percpu(pptr);
 	}
 free_elems:
-	vfree(htab->elems);
+	bpf_map_area_free(htab->elems);
 }
 
 static int prealloc_elems_and_freelist(struct bpf_htab *htab)
 {
 	int err = -ENOMEM, i;
 
-	htab->elems = vzalloc(htab->elem_size * htab->map.max_entries);
+	htab->elems = bpf_map_area_alloc(htab->elem_size *
+					 htab->map.max_entries);
 	if (!htab->elems)
 		return -ENOMEM;
 
@@ -227,14 +227,10 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 		goto free_htab;
 
 	err = -ENOMEM;
-	htab->buckets = kmalloc_array(htab->n_buckets, sizeof(struct bucket),
-				      GFP_USER | __GFP_NOWARN);
-
-	if (!htab->buckets) {
-		htab->buckets = vmalloc(htab->n_buckets * sizeof(struct bucket));
-		if (!htab->buckets)
-			goto free_htab;
-	}
+	htab->buckets = bpf_map_area_alloc(htab->n_buckets *
+					   sizeof(struct bucket));
+	if (!htab->buckets)
+		goto free_htab;
 
 	for (i = 0; i < htab->n_buckets; i++) {
 		INIT_HLIST_HEAD(&htab->buckets[i].head);
@@ -258,7 +254,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 free_extra_elems:
 	free_percpu(htab->extra_elems);
 free_buckets:
-	kvfree(htab->buckets);
+	bpf_map_area_free(htab->buckets);
 free_htab:
 	kfree(htab);
 	return ERR_PTR(err);
@@ -715,7 +711,7 @@ static void htab_map_free(struct bpf_map *map)
 		pcpu_freelist_destroy(&htab->freelist);
 	}
 	free_percpu(htab->extra_elems);
-	kvfree(htab->buckets);
+	bpf_map_area_free(htab->buckets);
 	kfree(htab);
 }
 
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 732ae16d12b7..be8519148c25 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -7,7 +7,6 @@
 #include <linux/bpf.h>
 #include <linux/jhash.h>
 #include <linux/filter.h>
-#include <linux/vmalloc.h>
 #include <linux/stacktrace.h>
 #include <linux/perf_event.h>
 #include "percpu_freelist.h"
@@ -32,7 +31,7 @@ static int prealloc_elems_and_freelist(struct bpf_stack_map *smap)
 	u32 elem_size = sizeof(struct stack_map_bucket) + smap->map.value_size;
 	int err;
 
-	smap->elems = vzalloc(elem_size * smap->map.max_entries);
+	smap->elems = bpf_map_area_alloc(elem_size * smap->map.max_entries);
 	if (!smap->elems)
 		return -ENOMEM;
 
@@ -45,7 +44,7 @@ static int prealloc_elems_and_freelist(struct bpf_stack_map *smap)
 	return 0;
 
 free_elems:
-	vfree(smap->elems);
+	bpf_map_area_free(smap->elems);
 	return err;
 }
 
@@ -76,12 +75,9 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
 	if (cost >= U32_MAX - PAGE_SIZE)
 		return ERR_PTR(-E2BIG);
 
-	smap = kzalloc(cost, GFP_USER | __GFP_NOWARN);
-	if (!smap) {
-		smap = vzalloc(cost);
-		if (!smap)
-			return ERR_PTR(-ENOMEM);
-	}
+	smap = bpf_map_area_alloc(cost);
+	if (!smap)
+		return ERR_PTR(-ENOMEM);
 
 	err = -E2BIG;
 	cost += n_buckets * (value_size + sizeof(struct stack_map_bucket));
@@ -112,7 +108,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
 put_buffers:
 	put_callchain_buffers();
 free_smap:
-	kvfree(smap);
+	bpf_map_area_free(smap);
 	return ERR_PTR(err);
 }
 
@@ -262,9 +258,9 @@ static void stack_map_free(struct bpf_map *map)
 	/* wait for bpf programs to complete before freeing stack map */
 	synchronize_rcu();
 
-	vfree(smap->elems);
+	bpf_map_area_free(smap->elems);
 	pcpu_freelist_destroy(&smap->freelist);
-	kvfree(smap);
+	bpf_map_area_free(smap);
 	put_callchain_buffers();
 }
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 237f3d6a7ddc..72ea91df71c9 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -12,6 +12,8 @@
 #include <linux/bpf.h>
 #include <linux/syscalls.h>
 #include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/mmzone.h>
 #include <linux/anon_inodes.h>
 #include <linux/file.h>
 #include <linux/license.h>
@@ -48,6 +50,30 @@ void bpf_register_map_type(struct bpf_map_type_list *tl)
 	list_add(&tl->list_node, &bpf_map_types);
 }
 
+void *bpf_map_area_alloc(size_t size)
+{
+	/* We definitely need __GFP_NORETRY, so OOM killer doesn't
+	 * trigger under memory pressure as we really just want to
+	 * fail instead.
+	 */
+	const gfp_t flags = __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO;
+	void *area;
+
+	if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
+		area = kmalloc(size, GFP_USER | flags);
+		if (area != NULL)
+			return area;
+	}
+
+	return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | flags,
+			 PAGE_KERNEL);
+}
+
+void bpf_map_area_free(void *area)
+{
+	kvfree(area);
+}
+
 int bpf_map_precharge_memlock(u32 pages)
 {
 	struct user_struct *user = get_current_user();
-- 
2.11.0

[PATCH for v4.9 LTS 30/86] gianfar: Do not reuse pages from emergency reserve

[Levin, Alexander (Sasha Levin)]

From: Eric Dumazet <edumazet@google.com>

[ Upstream commit 69fed99baac186013840ced3524562841296034f ]

A driver using dev_alloc_page() must not reuse a page that had to
use emergency memory reserve.

Otherwise all packets using this page will be immediately dropped,
unless for very specific sockets having SOCK_MEMALLOC bit set.

This issue might be hard to debug, because only a fraction of the RX
ring buffer would suffer from drops.

Fixes: 75354148ce69 ("gianfar: Add paged allocation and Rx S/G")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Claudiu Manoil <claudiu.manoil@freescale.com>
Acked-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/net/ethernet/freescale/gianfar.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index d391beebe591..3f4e71148808 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -2951,7 +2951,7 @@ static bool gfar_add_rx_frag(struct gfar_rx_buff *rxb, u32 lstatus,
 	}
 
 	/* try reuse page */
-	if (unlikely(page_count(page) != 1))
+	if (unlikely(page_count(page) != 1 || page_is_pfmemalloc(page)))
 		return false;
 
 	/* change offset to the other half */
-- 
2.11.0

[PATCH for v4.9 LTS 31/86] Btrfs: Fix deadlock between direct IO and fast fsync

[Levin, Alexander (Sasha Levin)]

From: Chandan Rajendra <chandan@linux.vnet.ibm.com>

[ Upstream commit 97dcdea076ecef41ea4aaa23d4397c2f622e4265 ]

The following deadlock is seen when executing generic/113 test,

 ---------------------------------------------------------+----------------------------------------------------
  Direct I/O task                                           Fast fsync task
 ---------------------------------------------------------+----------------------------------------------------
  btrfs_direct_IO
    __blockdev_direct_IO
     do_blockdev_direct_IO
      do_direct_IO
       btrfs_get_blocks_direct
        while (blocks needs to written)
         get_more_blocks (first iteration)
          btrfs_get_blocks_direct
           btrfs_create_dio_extent
             down_read(&BTRFS_I(inode) >dio_sem)
             Create and add extent map and ordered extent
             up_read(&BTRFS_I(inode) >dio_sem)
                                                            btrfs_sync_file
                                                              btrfs_log_dentry_safe
                                                               btrfs_log_inode_parent
                                                                btrfs_log_inode
                                                                 btrfs_log_changed_extents
                                                                  down_write(&BTRFS_I(inode) >dio_sem)
                                                                   Collect new extent maps and ordered extents
                                                                    wait for ordered extent completion
         get_more_blocks (second iteration)
          btrfs_get_blocks_direct
           btrfs_create_dio_extent
             down_read(&BTRFS_I(inode) >dio_sem)
 --------------------------------------------------------------------------------------------------------------

In the above description, Btrfs direct I/O code path has not yet started
submitting bios for file range covered by the initial ordered
extent. Meanwhile, The fast fsync task obtains the write semaphore and
waits for I/O on the ordered extent to get completed. However, the
Direct I/O task is now blocked on obtaining the read semaphore.

To resolve the deadlock, this commit modifies the Direct I/O code path
to obtain the read semaphore before invoking
__blockdev_direct_IO(). The semaphore is then given up after
__blockdev_direct_IO() returns. This allows the Direct I/O code to
complete I/O on all the ordered extents it creates.

Signed-off-by: Chandan Rajendra <chandan@linux.vnet.ibm.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 fs/btrfs/inode.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index bddbae796941..cada3f977baf 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7235,7 +7235,6 @@ static struct extent_map *btrfs_create_dio_extent(struct inode *inode,
 	struct extent_map *em = NULL;
 	int ret;
 
-	down_read(&BTRFS_I(inode)->dio_sem);
 	if (type != BTRFS_ORDERED_NOCOW) {
 		em = create_pinned_em(inode, start, len, orig_start,
 				      block_start, block_len, orig_block_len,
@@ -7254,7 +7253,6 @@ static struct extent_map *btrfs_create_dio_extent(struct inode *inode,
 		em = ERR_PTR(ret);
 	}
  out:
-	up_read(&BTRFS_I(inode)->dio_sem);
 
 	return em;
 }
@@ -8707,6 +8705,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 		dio_data.unsubmitted_oe_range_start = (u64)offset;
 		dio_data.unsubmitted_oe_range_end = (u64)offset;
 		current->journal_info = &dio_data;
+		down_read(&BTRFS_I(inode)->dio_sem);
 	} else if (test_bit(BTRFS_INODE_READDIO_NEED_LOCK,
 				     &BTRFS_I(inode)->runtime_flags)) {
 		inode_dio_end(inode);
@@ -8719,6 +8718,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 				   iter, btrfs_get_blocks_direct, NULL,
 				   btrfs_submit_direct, flags);
 	if (iov_iter_rw(iter) == WRITE) {
+		up_read(&BTRFS_I(inode)->dio_sem);
 		current->journal_info = NULL;
 		if (ret < 0 && ret != -EIOCBQUEUED) {
 			if (dio_data.reserve)
-- 
2.11.0

[PATCH for v4.9 LTS 32/86] Btrfs: fix truncate down when no_holes feature is enabled

[Levin, Alexander (Sasha Levin)]

From: Liu Bo <bo.li.liu@oracle.com>

[ Upstream commit 91298eec05cd8d4e828cf7ee5d4a6334f70cf69a ]

For such a file mapping,

[0-4k][hole][8k-12k]

In NO_HOLES mode, we don't have the [hole] extent any more.
Commit c1aa45759e90 ("Btrfs: fix shrinking truncate when the no_holes feature is enabled")
 fixed disk isize not being updated in NO_HOLES mode when data is not flushed.

However, even if data has been flushed, we can still have trouble
in updating disk isize since we updated disk isize to 'start' of
the last evicted extent.

Reviewed-by: Chris Mason <clm@fb.com>
Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 fs/btrfs/inode.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index cada3f977baf..a2a014b19f18 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4480,8 +4480,19 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 		if (found_type > min_type) {
 			del_item = 1;
 		} else {
-			if (item_end < new_size)
+			if (item_end < new_size) {
+				/*
+				 * With NO_HOLES mode, for the following mapping
+				 *
+				 * [0-4k][hole][8k-12k]
+				 *
+				 * if truncating isize down to 6k, it ends up
+				 * isize being 8k.
+				 */
+				if (btrfs_fs_incompat(root->fs_info, NO_HOLES))
+					last_size = new_size;
 				break;
+			}
 			if (found_key.offset >= new_size)
 				del_item = 1;
 			else
-- 
2.11.0

[PATCH for v4.9 LTS 33/86] virtio_console: fix a crash in config_work_handler

[Levin, Alexander (Sasha Levin)]

From: "G. Campana" <gcampana@quarkslab.com>

[ Upstream commit 8379cadf71c3ee8173a1c6fc1ea7762a9638c047 ]

Using control_work instead of config_work as the 3rd argument to
container_of results in an invalid portdev pointer. Indeed, the work
structure is initialized as below:

    INIT_WORK(&portdev->config_work, &config_work_handler);

It leads to a crash when portdev->vdev is dereferenced later. This
bug
is triggered when the guest uses a virtio-console without multiport
feature and receives a config_changed virtio interrupt.

Signed-off-by: G. Campana <gcampana@quarkslab.com>
Reviewed-by: Amit Shah <amit.shah@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/char/virtio_console.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 471a301d63e3..8f890c1aca57 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -1870,7 +1870,7 @@ static void config_work_handler(struct work_struct *work)
 {
 	struct ports_device *portdev;
 
-	portdev = container_of(work, struct ports_device, control_work);
+	portdev = container_of(work, struct ports_device, config_work);
 	if (!use_multiport(portdev)) {
 		struct virtio_device *vdev;
 		struct port *port;
-- 
2.11.0

[PATCH for v4.9 LTS 36/86] xen-netfront: Fix Rx stall during network stress and OOM

[Levin, Alexander (Sasha Levin)]

From: Vineeth Remanan Pillai <vineethp@amazon.com>

[ Upstream commit 90c311b0eeead647b708a723dbdde1eda3dcad05 ]

During an OOM scenario, request slots could not be created as skb
allocation fails. So the netback cannot pass in packets and netfront
wrongly assumes that there is no more work to be done and it disables
polling. This causes Rx to stall.

The issue is with the retry logic which schedules the timer if the
created slots are less than NET_RX_SLOTS_MIN. The count of new request
slots to be pushed are calculated as a difference between new req_prod
and rsp_cons which could be more than the actual slots, if there are
unconsumed responses.

The fix is to calculate the count of newly created slots as the
difference between new req_prod and old req_prod.

Signed-off-by: Vineeth Remanan Pillai <vineethp@amazon.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/net/xen-netfront.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 0cdcb2169083..599cf5090030 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -321,7 +321,7 @@ static void xennet_alloc_rx_buffers(struct netfront_queue *queue)
 	queue->rx.req_prod_pvt = req_prod;
 
 	/* Not enough requests? Try again later. */
-	if (req_prod - queue->rx.rsp_cons < NET_RX_SLOTS_MIN) {
+	if (req_prod - queue->rx.sring->req_prod < NET_RX_SLOTS_MIN) {
 		mod_timer(&queue->rx_refill_timer, jiffies + (HZ/10));
 		return;
 	}
-- 
2.11.0

[PATCH for v4.9 LTS 34/86] swiotlb-xen: update dev_addr after swapping pages

[Levin, Alexander (Sasha Levin)]

From: Stefano Stabellini <sstabellini@kernel.org>

[ Upstream commit f1225ee4c8fcf09afaa199b8b1f0450f38b8cd11 ]

In xen_swiotlb_map_page and xen_swiotlb_map_sg_attrs, if the original
page is not suitable, we swap it for another page from the swiotlb
pool.

In these cases, we don't update the previously calculated dma address
for the page before calling xen_dma_map_page. Thus, we end up calling
xen_dma_map_page passing the wrong dev_addr, resulting in
xen_dma_map_page mistakenly assuming that the page is foreign when it is
local.

Fix the bug by updating dev_addr appropriately.

This change has no effect on x86, because xen_dma_map_page is a stub
there.

Signed-off-by: Stefano Stabellini <sstabellini@kernel.org>
Signed-off-by: Pooya Keshavarzi <Pooya.Keshavarzi@de.bosch.com>
Tested-by: Pooya Keshavarzi <Pooya.Keshavarzi@de.bosch.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/xen/swiotlb-xen.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 8e7a3d646531..679f79f68182 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -409,9 +409,9 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	if (map == SWIOTLB_MAP_ERROR)
 		return DMA_ERROR_CODE;
 
+	dev_addr = xen_phys_to_bus(map);
 	xen_dma_map_page(dev, pfn_to_page(map >> PAGE_SHIFT),
 					dev_addr, map & ~PAGE_MASK, size, dir, attrs);
-	dev_addr = xen_phys_to_bus(map);
 
 	/*
 	 * Ensure that the address returned is DMA'ble
@@ -567,13 +567,14 @@ xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
 				sg_dma_len(sgl) = 0;
 				return 0;
 			}
+			dev_addr = xen_phys_to_bus(map);
 			xen_dma_map_page(hwdev, pfn_to_page(map >> PAGE_SHIFT),
 						dev_addr,
 						map & ~PAGE_MASK,
 						sg->length,
 						dir,
 						attrs);
-			sg->dma_address = xen_phys_to_bus(map);
+			sg->dma_address = dev_addr;
 		} else {
 			/* we are not interested in the dma_addr returned by
 			 * xen_dma_map_page, only in the potential cache flushes executed
-- 
2.11.0

[PATCH for v4.9 LTS 35/86] net: sctp: fix array overrun read on sctp_timer_tbl

[Levin, Alexander (Sasha Levin)]

From: Colin Ian King <colin.king@canonical.com>

[ Upstream commit 0e73fc9a56f22f2eec4d2b2910c649f7af67b74d ]

The comparison on the timeout can lead to an array overrun
read on sctp_timer_tbl because of an off-by-one error. Fix
this by using < instead of <= and also compare to the array
size rather than SCTP_EVENT_TIMEOUT_MAX.

Fixes CoverityScan CID#1397639 ("Out-of-bounds read")

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 net/sctp/debug.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sctp/debug.c b/net/sctp/debug.c
index 95d7b15dad21..e371a0d90068 100644
--- a/net/sctp/debug.c
+++ b/net/sctp/debug.c
@@ -166,7 +166,7 @@ static const char *const sctp_timer_tbl[] = {
 /* Lookup timer debug name. */
 const char *sctp_tname(const sctp_subtype_t id)
 {
-	if (id.timeout <= SCTP_EVENT_TIMEOUT_MAX)
+	if (id.timeout < ARRAY_SIZE(sctp_timer_tbl))
 		return sctp_timer_tbl[id.timeout];
 	return "unknown_timer";
 }
-- 
2.11.0

[PATCH for v4.9 LTS 38/86] iwlwifi: fix kernel crash when unregistering thermal zone

[Levin, Alexander (Sasha Levin)]

From: Jens Axboe <axboe@kernel.dk>

[ Upstream commit 92549cdc288f47f3a98cf80ac5890c91f5876a06 ]

A recent firmware change seems to have enabled thermal zones on the
iwlwifi driver. Unfortunately, my device fails when registering the
thermal zone. This doesn't stop the driver from attempting to unregister
the thermal zone at unload time, triggering a NULL pointer deference in
strlen() off the thermal_zone_device_unregister() path.

Don't unregister if name is NULL, for that case we failed registering.
Do the same for the cooling zone.

Signed-off-by: Jens Axboe <axboe@fb.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/tt.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tt.c b/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
index 63a051be832e..bec7d9c46087 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
@@ -843,8 +843,10 @@ static void iwl_mvm_thermal_zone_unregister(struct iwl_mvm *mvm)
 		return;
 
 	IWL_DEBUG_TEMP(mvm, "Thermal zone device unregister\n");
-	thermal_zone_device_unregister(mvm->tz_device.tzone);
-	mvm->tz_device.tzone = NULL;
+	if (mvm->tz_device.tzone) {
+		thermal_zone_device_unregister(mvm->tz_device.tzone);
+		mvm->tz_device.tzone = NULL;
+	}
 }
 
 static void iwl_mvm_cooling_device_unregister(struct iwl_mvm *mvm)
@@ -853,8 +855,10 @@ static void iwl_mvm_cooling_device_unregister(struct iwl_mvm *mvm)
 		return;
 
 	IWL_DEBUG_TEMP(mvm, "Cooling device unregister\n");
-	thermal_cooling_device_unregister(mvm->cooling_dev.cdev);
-	mvm->cooling_dev.cdev = NULL;
+	if (mvm->cooling_dev.cdev) {
+		thermal_cooling_device_unregister(mvm->cooling_dev.cdev);
+		mvm->cooling_dev.cdev = NULL;
+	}
 }
 #endif /* CONFIG_THERMAL */
 
-- 
2.11.0

[PATCH for v4.9 LTS 39/86] platform/x86: ideapad-laptop: handle ACPI event 1

[Levin, Alexander (Sasha Levin)]

From: Zach Ploskey <zach@ploskey.com>

[ Upstream commit cfee5d63767b2e7997c1f36420d008abbe61565c ]

On Ideapad laptops, ACPI event 1 is currently not handled. Many models
log "ideapad_laptop: Unknown event: 1" every 20 seconds or so while
running on battery power. Some convertible laptops receive this event
when switching in and out of tablet mode.

This adds and additional case for event 1 in ideapad_acpi_notify to call
ideapad_input_report(priv, vpc_bit), so that the event is reported to
userspace and we avoid unnecessary logging.

Fixes bug #107481 (https://bugzilla.kernel.org/show_bug.cgi?id=107481)
Fixes bug #65751 (https://bugzilla.kernel.org/show_bug.cgi?id=65751)

Signed-off-by: Zach Ploskey <zach@ploskey.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/platform/x86/ideapad-laptop.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c
index a7614fc542b5..2f1615e00cb4 100644
--- a/drivers/platform/x86/ideapad-laptop.c
+++ b/drivers/platform/x86/ideapad-laptop.c
@@ -813,6 +813,7 @@ static void ideapad_acpi_notify(acpi_handle handle, u32 event, void *data)
 			case 8:
 			case 7:
 			case 6:
+			case 1:
 				ideapad_input_report(priv, vpc_bit);
 				break;
 			case 5:
-- 
2.11.0

[PATCH for v4.9 LTS 37/86] scsi: virtio_scsi: Reject commands when virtqueue is broken

[Levin, Alexander (Sasha Levin)]

From: Eric Farman <farman@linux.vnet.ibm.com>

[ Upstream commit 773c7220e22d193e5667c352fcbf8d47eefc817f ]

In the case of a graceful set of detaches, where the virtio-scsi-ccw
disk is removed from the guest prior to the controller, the guest
behaves quite normally.  Specifically, the detach gets us into
sd_sync_cache to issue a Synchronize Cache(10) command, which
immediately fails (and is retried a couple of times) because the device
has been removed.  Later, the removal of the controller sees two CRWs
presented, but there's no further indication of the removal from the
guest viewpoint.

 [   17.217458] sd 0:0:0:0: [sda] Synchronizing SCSI cache
 [   17.219257] sd 0:0:0:0: [sda] Synchronize Cache(10) failed: Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK
 [   21.449400] crw_info : CRW reports slct=0, oflw=0, chn=1, rsc=3, anc=0, erc=4, rsid=2
 [   21.449406] crw_info : CRW reports slct=0, oflw=0, chn=0, rsc=3, anc=0, erc=4, rsid=0

However, on s390, the SCSI disks can be removed "by surprise" when an
entire controller (host) is removed and all associated disks are removed
via the loop in scsi_forget_host.  The same call to sd_sync_cache is
made, but because the controller has already been removed, the
Synchronize Cache(10) command is neither issued (and then failed) nor
rejected.

That the I/O isn't returned means the guest cannot have other devices
added nor removed, and other tasks (such as shutdown or reboot) issued
by the guest will not complete either.  The virtio ring has already been
marked as broken (via virtio_break_device in virtio_ccw_remove), but we
still attempt to queue the command only to have it remain there.  The
calling sequence provides a bit of distinction for us:

  virtscsi_queuecommand()
   -> virtscsi_kick_cmd()
    -> virtscsi_add_cmd()
     -> virtqueue_add_sgs()
      -> virtqueue_add()
         if success
           return 0
         elseif vq->broken or vring_mapping_error()
           return -EIO
         else
           return -ENOSPC

A return of ENOSPC is generally a temporary condition, so returning
"host busy" from virtscsi_queuecommand makes sense here, to have it
redriven in a moment or two.  But the EIO return code is more of a
permanent error and so it would be wise to return the I/O itself and
allow the calling thread to finish gracefully.  The result is these four
kernel messages in the guest (the fourth one does not occur prior to
this patch):

 [   22.921562] crw_info : CRW reports slct=0, oflw=0, chn=1, rsc=3, anc=0, erc=4, rsid=2
 [   22.921580] crw_info : CRW reports slct=0, oflw=0, chn=0, rsc=3, anc=0, erc=4, rsid=0
 [   22.921978] sd 0:0:0:0: [sda] Synchronizing SCSI cache
 [   22.921993] sd 0:0:0:0: [sda] Synchronize Cache(10) failed: Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK

I opted to fill in the same response data that is returned from the more
graceful device detach, where the disk device is removed prior to the
controller device.

Signed-off-by: Eric Farman <farman@linux.vnet.ibm.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/scsi/virtio_scsi.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index ec91bd07f00a..c680d7641311 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -534,7 +534,9 @@ static int virtscsi_queuecommand(struct virtio_scsi *vscsi,
 {
 	struct Scsi_Host *shost = virtio_scsi_host(vscsi->vdev);
 	struct virtio_scsi_cmd *cmd = scsi_cmd_priv(sc);
+	unsigned long flags;
 	int req_size;
+	int ret;
 
 	BUG_ON(scsi_sg_count(sc) > shost->sg_tablesize);
 
@@ -562,8 +564,15 @@ static int virtscsi_queuecommand(struct virtio_scsi *vscsi,
 		req_size = sizeof(cmd->req.cmd);
 	}
 
-	if (virtscsi_kick_cmd(req_vq, cmd, req_size, sizeof(cmd->resp.cmd)) != 0)
+	ret = virtscsi_kick_cmd(req_vq, cmd, req_size, sizeof(cmd->resp.cmd));
+	if (ret == -EIO) {
+		cmd->resp.cmd.response = VIRTIO_SCSI_S_BAD_TARGET;
+		spin_lock_irqsave(&req_vq->vq_lock, flags);
+		virtscsi_complete_cmd(vscsi, cmd);
+		spin_unlock_irqrestore(&req_vq->vq_lock, flags);
+	} else if (ret != 0) {
 		return SCSI_MLQUEUE_HOST_BUSY;
+	}
 	return 0;
 }
 
-- 
2.11.0

[PATCH for v4.9 LTS 40/86] amd-xgbe: Check xgbe_init() return code

[Levin, Alexander (Sasha Levin)]

From: "Lendacky, Thomas" <Thomas.Lendacky@amd.com>

[ Upstream commit 738f7f647371ff4cfc9646c99dba5b58ad142db3 ]

The xgbe_init() routine returns a return code indicating success or
failure, but the return code is not checked. Add code to xgbe_init()
to issue a message when failures are seen and add code to check the
xgbe_init() return code.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/net/ethernet/amd/xgbe/xgbe-dev.c | 4 +++-
 drivers/net/ethernet/amd/xgbe/xgbe-drv.c | 4 +++-
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
index ca106d4275cc..3424435a39dd 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -2825,8 +2825,10 @@ static int xgbe_init(struct xgbe_prv_data *pdata)
 
 	/* Flush Tx queues */
 	ret = xgbe_flush_tx_queues(pdata);
-	if (ret)
+	if (ret) {
+		netdev_err(pdata->netdev, "error flushing TX queues\n");
 		return ret;
+	}
 
 	/*
 	 * Initialize DMA related features
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 0f0f30149e5a..1e4e8b245cd5 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -877,7 +877,9 @@ static int xgbe_start(struct xgbe_prv_data *pdata)
 
 	DBGPR("-->xgbe_start\n");
 
-	hw_if->init(pdata);
+	ret = hw_if->init(pdata);
+	if (ret)
+		return ret;
 
 	ret = phy_if->phy_start(pdata);
 	if (ret)
-- 
2.11.0

[PATCH for v4.9 LTS 41/86] net: dsa: Check return value of phy_connect_direct()

[Levin, Alexander (Sasha Levin)]

From: Florian Fainelli <f.fainelli@gmail.com>

[ Upstream commit 4078b76cac68e50ccf1f76a74e7d3d5788aec3fe ]

We need to check the return value of phy_connect_direct() in
dsa_slave_phy_connect() otherwise we may be continuing the
initialization of a slave network device with a PHY that already
attached somewhere else and which will soon be in error because the PHY
device is in error.

The conditions for such an error to occur are that we have a port of our
switch that is not disabled, and has the same port number as a PHY
address (say both 5) that can be probed using the DSA slave MII bus. We
end-up having this slave network device find a PHY at the same address
as our port number, and we try to attach to it.

A slave network (e.g: port 0) has already attached to our PHY device,
and we try to re-attach it with a different network device, but since we
ignore the error we would end-up initializating incorrect device
references by the time the slave network interface is opened.

The code has been (re)organized several times, making it hard to provide
an exact Fixes tag, this is a bugfix nonetheless.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 net/dsa/slave.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 3ff9d97cf56b..079d76bc204c 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1103,10 +1103,8 @@ static int dsa_slave_phy_connect(struct dsa_slave_priv *p,
 	/* Use already configured phy mode */
 	if (p->phy_interface == PHY_INTERFACE_MODE_NA)
 		p->phy_interface = p->phy->interface;
-	phy_connect_direct(slave_dev, p->phy, dsa_slave_adjust_link,
-			   p->phy_interface);
-
-	return 0;
+	return phy_connect_direct(slave_dev, p->phy, dsa_slave_adjust_link,
+				  p->phy_interface);
 }
 
 static int dsa_slave_phy_setup(struct dsa_slave_priv *p,
-- 
2.11.0

[PATCH for v4.9 LTS 44/86] mlxsw: spectrum_router: Correctly reallocate adjacency entries

[Levin, Alexander (Sasha Levin)]

From: Ido Schimmel <idosch@mellanox.com>

[ Upstream commit a59b7e0246774e28193126fe7fdbbd0ae9c67dcc ]

mlxsw_sp_nexthop_group_mac_update() is called in one of two cases:

1) When the MAC of a nexthop needs to be updated
2) When the size of a nexthop group has changed

In the second case the adjacency entries for the nexthop group need to
be reallocated from the adjacency table. In this case we must write to
the entries the MAC addresses of all the nexthops that should be
offloaded and not only those whose MAC changed. Otherwise, these entries
would be filled with garbage data, resulting in packet loss.

Fixes: a7ff87acd995 ("mlxsw: spectrum_router: Implement next-hop routing")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 690563099313..9e31a3390154 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -1178,7 +1178,8 @@ static int mlxsw_sp_nexthop_mac_update(struct mlxsw_sp *mlxsw_sp, u32 adj_index,
 
 static int
 mlxsw_sp_nexthop_group_mac_update(struct mlxsw_sp *mlxsw_sp,
-				  struct mlxsw_sp_nexthop_group *nh_grp)
+				  struct mlxsw_sp_nexthop_group *nh_grp,
+				  bool reallocate)
 {
 	u32 adj_index = nh_grp->adj_index; /* base */
 	struct mlxsw_sp_nexthop *nh;
@@ -1193,7 +1194,7 @@ mlxsw_sp_nexthop_group_mac_update(struct mlxsw_sp *mlxsw_sp,
 			continue;
 		}
 
-		if (nh->update) {
+		if (nh->update || reallocate) {
 			err = mlxsw_sp_nexthop_mac_update(mlxsw_sp,
 							  adj_index, nh);
 			if (err)
@@ -1254,7 +1255,8 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
 		/* Nothing was added or removed, so no need to reallocate. Just
 		 * update MAC on existing adjacency indexes.
 		 */
-		err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp);
+		err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp,
+							false);
 		if (err) {
 			dev_warn(mlxsw_sp->bus_info->dev, "Failed to update neigh MAC in adjacency table.\n");
 			goto set_trap;
@@ -1282,7 +1284,7 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
 	nh_grp->adj_index_valid = 1;
 	nh_grp->adj_index = adj_index;
 	nh_grp->ecmp_size = ecmp_size;
-	err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp);
+	err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp, true);
 	if (err) {
 		dev_warn(mlxsw_sp->bus_info->dev, "Failed to update neigh MAC in adjacency table.\n");
 		goto set_trap;
-- 
2.11.0

[PATCH for v4.9 LTS 42/86] drm/amdgpu: check ring being ready before using

[Levin, Alexander (Sasha Levin)]

From: Ding Pixel <pding@amd.com>

[ Upstream commit c5f21c9f878b8dcd54d0b9739c025ca73cb4c091 ]

Return success when the ring is properly initialized, otherwise return
failure.

Tonga SRIOV VF doesn't have UVD and VCE engines, the initialization of
these IPs is bypassed. The system crashes if application submit IB to
their rings which are not ready to use. It could be a common issue if
IP having ring buffer is disabled for some reason on specific ASIC, so
it should check the ring being ready to use.

Bug: amdgpu_test crashes system on Tonga VF.

Signed-off-by: Ding Pixel <Pixel.Ding@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 82dc8d20e28a..bfb4b91869e7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -83,6 +83,13 @@ int amdgpu_cs_get_ring(struct amdgpu_device *adev, u32 ip_type,
 		}
 		break;
 	}
+
+	if (!(*out_ring && (*out_ring)->adev)) {
+		DRM_ERROR("Ring %d is not initialized on IP %d\n",
+			  ring, ip_type);
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
-- 
2.11.0

[PATCH for v4.9 LTS 43/86] vfio/spapr: fail tce_iommu_attach_group() when iommu_data is null

[Levin, Alexander (Sasha Levin)]

From: Greg Kurz <groug@kaod.org>

[ Upstream commit bd00fdf198e2da475a2f4265a83686ab42d998a8 ]

The recently added mediated VFIO driver doesn't know about powerpc iommu.
It thus doesn't register a struct iommu_table_group in the iommu group
upon device creation. The iommu_data pointer hence remains null.

This causes a kernel oops when userspace tries to set the iommu type of a
container associated with a mediated device to VFIO_SPAPR_TCE_v2_IOMMU.

[   82.585440] mtty mtty: MDEV: Registered
[   87.655522] iommu: Adding device 83b8f4f2-509f-382f-3c1e-e6bfe0fa1001 to group 10
[   87.655527] vfio_mdev 83b8f4f2-509f-382f-3c1e-e6bfe0fa1001: MDEV: group_id = 10
[  116.297184] Unable to handle kernel paging request for data at address 0x00000030
[  116.297389] Faulting instruction address: 0xd000000007870524
[  116.297465] Oops: Kernel access of bad area, sig: 11 [#1]
[  116.297611] SMP NR_CPUS=2048
[  116.297611] NUMA
[  116.297627] PowerNV
...
[  116.297954] CPU: 33 PID: 7067 Comm: qemu-system-ppc Not tainted 4.10.0-rc5-mdev-test #8
[  116.297993] task: c000000e7718b680 task.stack: c000000e77214000
[  116.298025] NIP: d000000007870524 LR: d000000007870518 CTR: 0000000000000000
[  116.298064] REGS: c000000e77217990 TRAP: 0300   Not tainted  (4.10.0-rc5-mdev-test)
[  116.298103] MSR: 9000000000009033 <SF,HV,EE,ME,IR,DR,RI,LE>
[  116.298107]   CR: 84004444  XER: 00000000
[  116.298154] CFAR: c00000000000888c DAR: 0000000000000030 DSISR: 40000000 SOFTE: 1
               GPR00: d000000007870518 c000000e77217c10 d00000000787b0ed c000000eed2103c0
               GPR04: 0000000000000000 0000000000000000 c000000eed2103e0 0000000f24320000
               GPR08: 0000000000000104 0000000000000001 0000000000000000 d0000000078729b0
               GPR12: c00000000025b7e0 c00000000fe08400 0000000000000001 000001002d31d100
               GPR16: 000001002c22c850 00003ffff315c750 0000000043145680 0000000043141bc0
               GPR20: ffffffffffffffed fffffffffffff000 0000000020003b65 d000000007706018
               GPR24: c000000f16cf0d98 d000000007706000 c000000003f42980 c000000003f42980
               GPR28: c000000f1575ac00 c000000003f429c8 0000000000000000 c000000eed2103c0
[  116.298504] NIP [d000000007870524] tce_iommu_attach_group+0x10c/0x360 [vfio_iommu_spapr_tce]
[  116.298555] LR [d000000007870518] tce_iommu_attach_group+0x100/0x360 [vfio_iommu_spapr_tce]
[  116.298601] Call Trace:
[  116.298610] [c000000e77217c10] [d000000007870518] tce_iommu_attach_group+0x100/0x360 [vfio_iommu_spapr_tce] (unreliable)
[  116.298671] [c000000e77217cb0] [d0000000077033a0] vfio_fops_unl_ioctl+0x278/0x3e0 [vfio]
[  116.298713] [c000000e77217d40] [c0000000002a3ebc] do_vfs_ioctl+0xcc/0x8b0
[  116.298745] [c000000e77217de0] [c0000000002a4700] SyS_ioctl+0x60/0xc0
[  116.298782] [c000000e77217e30] [c00000000000b220] system_call+0x38/0xfc
[  116.298812] Instruction dump:
[  116.298828] 7d3f4b78 409effc8 3d220000 e9298020 3c800140 38a00018 608480c0 e8690028
[  116.298869] 4800249d e8410018 7c7f1b79 41820230 <e93e0030> 2fa90000 419e0114 e9090020
[  116.298914] ---[ end trace 1e10b0ced08b9120 ]---

This patch fixes the oops.

Reported-by: Vaibhav Jain <vaibhav@linux.vnet.ibm.com>
Signed-off-by: Greg Kurz <groug@kaod.org>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/vfio/vfio_iommu_spapr_tce.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index 79ddcb05d126..85d3e648bdea 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -1292,6 +1292,10 @@ static int tce_iommu_attach_group(void *iommu_data,
 	/* pr_debug("tce_vfio: Attaching group #%u to iommu %p\n",
 			iommu_group_id(iommu_group), iommu_group); */
 	table_group = iommu_group_get_iommudata(iommu_group);
+	if (!table_group) {
+		ret = -ENODEV;
+		goto unlock_exit;
+	}
 
 	if (tce_groups_attached(container) && (!table_group->ops ||
 			!table_group->ops->take_ownership ||
-- 
2.11.0

[PATCH for v4.9 LTS 47/86] vxlan: do not age static remote mac entries

[Levin, Alexander (Sasha Levin)]

From: Balakrishnan Raman <ramanb@cumulusnetworks.com>

[ Upstream commit efb5f68f32995c146944a9d4257c3cf8eae2c4a1 ]

Mac aging is applicable only for dynamically learnt remote mac
entries. Check for user configured static remote mac entries
and skip aging.

Signed-off-by: Balakrishnan Raman <ramanb@cumulusnetworks.com>
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/net/vxlan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 55c4408892be..963e5339a4d7 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2285,7 +2285,7 @@ static void vxlan_cleanup(unsigned long arg)
 				= container_of(p, struct vxlan_fdb, hlist);
 			unsigned long timeout;
 
-			if (f->state & NUD_PERMANENT)
+			if (f->state & (NUD_PERMANENT | NUD_NOARP))
 				continue;
 
 			timeout = f->used + vxlan->cfg.age_interval * HZ;
-- 
2.11.0

[PATCH for v4.9 LTS 45/86] virtio_net: fix PAGE_SIZE > 64k

[Levin, Alexander (Sasha Levin)]

From: "Michael S. Tsirkin" <mst@redhat.com>

[ Upstream commit d0fa28f00052391b5df328f502fbbdd4444938b7 ]

I don't have any guests with PAGE_SIZE > 64k but the
code seems to be clearly broken in that case
as PAGE_SIZE / MERGEABLE_BUFFER_ALIGN will need
more than 8 bit and so the code in mergeable_ctx_to_buf_address
does not give us the actual true size.

Cc: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/net/virtio_net.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 7ca99899972e..1568aedddfc9 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -47,8 +47,16 @@ module_param(gso, bool, 0444);
  */
 DECLARE_EWMA(pkt_len, 1, 64)
 
+/* With mergeable buffers we align buffer address and use the low bits to
+ * encode its true size. Buffer size is up to 1 page so we need to align to
+ * square root of page size to ensure we reserve enough bits to encode the true
+ * size.
+ */
+#define MERGEABLE_BUFFER_MIN_ALIGN_SHIFT ((PAGE_SHIFT + 1) / 2)
+
 /* Minimum alignment for mergeable packet buffers. */
-#define MERGEABLE_BUFFER_ALIGN max(L1_CACHE_BYTES, 256)
+#define MERGEABLE_BUFFER_ALIGN max(L1_CACHE_BYTES, \
+				   1 << MERGEABLE_BUFFER_MIN_ALIGN_SHIFT)
 
 #define VIRTNET_DRIVER_VERSION "1.0.0"
 
-- 
2.11.0

[PATCH for v4.9 LTS 46/86] ip6_tunnel: must reload ipv6h in ip6ip6_tnl_xmit()

[Levin, Alexander (Sasha Levin)]

From: Eric Dumazet <edumazet@google.com>

[ Upstream commit 21b995a9cb093fff33ec91d7cb3822b882a90a1e ]

Since ip6_tnl_parse_tlv_enc_lim() can call pskb_may_pull(),
we must reload any pointer that was related to skb->head
(or skb->data), or risk use after free.

Fixes: c12b395a4664 ("gre: Support GRE over IPv6")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Dmitry Kozlov <xeb@mail.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 net/ipv6/ip6_gre.c    | 3 +++
 net/ipv6/ip6_tunnel.c | 2 ++
 2 files changed, 5 insertions(+)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 0a5922055da2..a5fdc1aa7a9a 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -582,6 +582,9 @@ static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev)
 		return -1;
 
 	offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb));
+	/* ip6_tnl_parse_tlv_enc_lim() might have reallocated skb->head */
+	ipv6h = ipv6_hdr(skb);
+
 	if (offset > 0) {
 		struct ipv6_tlv_tnl_enc_lim *tel;
 		tel = (struct ipv6_tlv_tnl_enc_lim *)&skb_network_header(skb)[offset];
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 116b4da06820..63fad2467a7e 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1313,6 +1313,8 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 		fl6.flowlabel = key->label;
 	} else {
 		offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb));
+		/* ip6_tnl_parse_tlv_enc_lim() might have reallocated skb->head */
+		ipv6h = ipv6_hdr(skb);
 		if (offset > 0) {
 			struct ipv6_tlv_tnl_enc_lim *tel;
 
-- 
2.11.0

[PATCH for v4.9 LTS 49/86] kernel/panic.c: add missing \n

[Levin, Alexander (Sasha Levin)]

From: Jiri Slaby <jslaby@suse.cz>

[ Upstream commit ff7a28a074ccbea999dadbb58c46212cf90984c6 ]

When a system panics, the "Rebooting in X seconds.." message is never
printed because it lacks a new line.  Fix it.

Link: http://lkml.kernel.org/r/20170119114751.2724-1-jslaby@suse.cz
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 kernel/panic.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/panic.c b/kernel/panic.c
index e6480e20379e..dbec387099b1 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -249,7 +249,7 @@ void panic(const char *fmt, ...)
 		 * Delay timeout seconds before rebooting the machine.
 		 * We can't use the "normal" timers since we just panicked.
 		 */
-		pr_emerg("Rebooting in %d seconds..", panic_timeout);
+		pr_emerg("Rebooting in %d seconds..\n", panic_timeout);
 
 		for (i = 0; i < panic_timeout * 1000; i += PANIC_TIMER_STEP) {
 			touch_nmi_watchdog();
-- 
2.11.0

[PATCH for v4.9 LTS 50/86] Documentation: devicetree: change the mediatek ethernet compatible string

[Levin, Alexander (Sasha Levin)]

From: John Crispin <john@phrozen.org>

[ Upstream commit 61976fff20f92aceecc3670f6168bfc57a79e047 ]

When the binding was defined, I was not aware that mt2701 was an earlier
version of the SoC. For sake of consistency, the ethernet driver should
use mt2701 inside the compat string as this is the earliest SoC with the
ethernet core.

The ethernet driver is currently of no real use until we finish and
upstream the DSA driver. There are no users of this binding yet. It should
be safe to fix this now before it is too late and we need to provide
backward compatibility for the mt7623-eth compat string.

Reported-by: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: John Crispin <john@phrozen.org>
Reviewed-by: Matthias Brugger <matthias.bgg@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 Documentation/devicetree/bindings/net/mediatek-net.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/net/mediatek-net.txt b/Documentation/devicetree/bindings/net/mediatek-net.txt
index c010fafc66a8..c7194e87d5f4 100644
--- a/Documentation/devicetree/bindings/net/mediatek-net.txt
+++ b/Documentation/devicetree/bindings/net/mediatek-net.txt
@@ -7,7 +7,7 @@ have dual GMAC each represented by a child node..
 * Ethernet controller node
 
 Required properties:
-- compatible: Should be "mediatek,mt7623-eth"
+- compatible: Should be "mediatek,mt2701-eth"
 - reg: Address and length of the register set for the device
 - interrupts: Should contain the three frame engines interrupts in numeric
 	order. These are fe_int0, fe_int1 and fe_int2.
-- 
2.11.0

[PATCH for v4.9 LTS 48/86] ibmveth: Add a proper check for the availability of the checksum features

[Levin, Alexander (Sasha Levin)]

From: Thomas Huth <thuth@redhat.com>

[ Upstream commit 23d28a859fb847fd7fcfbd31acb3b160abb5d6ae ]

When using the ibmveth driver in a KVM/QEMU based VM, it currently
always prints out a scary error message like this when it is started:

 ibmveth 71000003 (unregistered net_device): unable to change
 checksum offload settings. 1 rc=-2 ret_attr=71000003

This happens because the driver always tries to enable the checksum
offloading without checking for the availability of this feature first.
QEMU does not support checksum offloading for the spapr-vlan device,
thus we always get the error message here.
According to the LoPAPR specification, the "ibm,illan-options" property
of the corresponding device tree node should be checked first to see
whether the H_ILLAN_ATTRIUBTES hypercall and thus the checksum offloading
feature is available. Thus let's do this in the ibmveth driver, too, so
that the error message is really only limited to cases where something
goes wrong, and does not occur if the feature is just missing.

Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/net/ethernet/ibm/ibmveth.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 03dca732e4c6..b375ae9f98ef 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -1604,8 +1604,11 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	netdev->netdev_ops = &ibmveth_netdev_ops;
 	netdev->ethtool_ops = &netdev_ethtool_ops;
 	SET_NETDEV_DEV(netdev, &dev->dev);
-	netdev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM |
-		NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+	netdev->hw_features = NETIF_F_SG;
+	if (vio_get_attribute(dev, "ibm,illan-options", NULL) != NULL) {
+		netdev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
+				       NETIF_F_RXCSUM;
+	}
 
 	netdev->features |= netdev->hw_features;
 
-- 
2.11.0

[PATCH for v4.9 LTS 51/86] drm/etnaviv: trick drm_mm into giving out a low IOVA

[Levin, Alexander (Sasha Levin)]

From: Lucas Stach <l.stach@pengutronix.de>

[ Upstream commit 3546fb0cdac25a79c89d87020566fab52b92867d ]

After rollover of the IOVA space, we want to get a low IOVA address,
otherwise the the games we play by remembering the last IOVA are
pointless. When we search for a free hole with DRM_MM_SEARCH_DEFAULT,
drm_mm will pop the next entry from the free holes stack, which will
likely be a high IOVA. By using DRM_MM_SEARCH_BELOW we can trick
drm_mm into reversing the search and provide us with a low IOVA.

Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Reviewed-by: Wladimir van der Laan <laanwj@gmail.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/gpu/drm/etnaviv/etnaviv_mmu.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
index 169ac96e8f08..fe0e85b41310 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
@@ -116,9 +116,14 @@ static int etnaviv_iommu_find_iova(struct etnaviv_iommu *mmu,
 		struct list_head list;
 		bool found;
 
+		/*
+		 * XXX: The DRM_MM_SEARCH_BELOW is really a hack to trick
+		 * drm_mm into giving out a low IOVA after address space
+		 * rollover. This needs a proper fix.
+		 */
 		ret = drm_mm_insert_node_in_range(&mmu->mm, node,
 			size, 0, mmu->last_iova, ~0UL,
-			DRM_MM_SEARCH_DEFAULT);
+			mmu->last_iova ? DRM_MM_SEARCH_DEFAULT : DRM_MM_SEARCH_BELOW);
 
 		if (ret != -ENOSPC)
 			break;
-- 
2.11.0

[PATCH for v4.9 LTS 53/86] pinctrl: intel: Set pin direction properly

[Levin, Alexander (Sasha Levin)]

From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>

[ Upstream commit 17fab473693e8357a9aa6fee4fbed6c13a34bd81 ]

There are two bits in the PADCFG0 register to configure direction, one per
TX/RX buffers.

For now we wrongly assume that the GPIO is always requested before it is being
used, which is not true when the GPIO is used through irqchip. In this case the
GPIO is never requested and we never enable RX buffer for it.

Fix this by setting both bits accordingly.

Reported-by: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/pinctrl/intel/pinctrl-intel.c | 30 +++++++++++++++++++-----------
 1 file changed, 19 insertions(+), 11 deletions(-)

diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c
index 01443762e570..b40a074822cf 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.c
+++ b/drivers/pinctrl/intel/pinctrl-intel.c
@@ -353,6 +353,21 @@ static int intel_pinmux_set_mux(struct pinctrl_dev *pctldev, unsigned function,
 	return 0;
 }
 
+static void __intel_gpio_set_direction(void __iomem *padcfg0, bool input)
+{
+	u32 value;
+
+	value = readl(padcfg0);
+	if (input) {
+		value &= ~PADCFG0_GPIORXDIS;
+		value |= PADCFG0_GPIOTXDIS;
+	} else {
+		value &= ~PADCFG0_GPIOTXDIS;
+		value |= PADCFG0_GPIORXDIS;
+	}
+	writel(value, padcfg0);
+}
+
 static int intel_gpio_request_enable(struct pinctrl_dev *pctldev,
 				     struct pinctrl_gpio_range *range,
 				     unsigned pin)
@@ -375,11 +390,11 @@ static int intel_gpio_request_enable(struct pinctrl_dev *pctldev,
 	/* Disable SCI/SMI/NMI generation */
 	value &= ~(PADCFG0_GPIROUTIOXAPIC | PADCFG0_GPIROUTSCI);
 	value &= ~(PADCFG0_GPIROUTSMI | PADCFG0_GPIROUTNMI);
-	/* Disable TX buffer and enable RX (this will be input) */
-	value &= ~PADCFG0_GPIORXDIS;
-	value |= PADCFG0_GPIOTXDIS;
 	writel(value, padcfg0);
 
+	/* Disable TX buffer and enable RX (this will be input) */
+	__intel_gpio_set_direction(padcfg0, true);
+
 	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
 
 	return 0;
@@ -392,18 +407,11 @@ static int intel_gpio_set_direction(struct pinctrl_dev *pctldev,
 	struct intel_pinctrl *pctrl = pinctrl_dev_get_drvdata(pctldev);
 	void __iomem *padcfg0;
 	unsigned long flags;
-	u32 value;
 
 	raw_spin_lock_irqsave(&pctrl->lock, flags);
 
 	padcfg0 = intel_get_padcfg(pctrl, pin, PADCFG0);
-
-	value = readl(padcfg0);
-	if (input)
-		value |= PADCFG0_GPIOTXDIS;
-	else
-		value &= ~PADCFG0_GPIOTXDIS;
-	writel(value, padcfg0);
+	__intel_gpio_set_direction(padcfg0, input);
 
 	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
 
-- 
2.11.0

[PATCH for v4.9 LTS 52/86] perf/x86/intel/uncore: Fix hardcoded socket 0 assumption in the Haswell init code

[Levin, Alexander (Sasha Levin)]

From: Prarit Bhargava <prarit@redhat.com>

[ Upstream commit 6d6daa20945f3f598e56e18d1f926c08754f5801 ]

hswep_uncore_cpu_init() uses a hardcoded physical package id 0 for the boot
cpu. This works as long as the boot CPU is actually on the physical package
0, which is normaly the case after power on / reboot.

But it fails with a NULL pointer dereference when a kdump kernel is started
on a secondary socket which has a different physical package id because the
locigal package translation for physical package 0 does not exist.

Use the logical package id of the boot cpu instead of hard coded 0.

[ tglx: Rewrote changelog once more ]

Fixes: cf6d445f6897 ("perf/x86/uncore: Track packages, not per CPU data")
Signed-off-by: Prarit Bhargava <prarit@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Harish Chegondi <harish.chegondi@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: stable@vger.kernel.org
Link: http://lkml.kernel.org/r/1483628965-2890-1-git-send-email-prarit@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 arch/x86/events/intel/uncore_snbep.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 272427700d48..afe8024e9e95 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -2686,7 +2686,7 @@ static struct intel_uncore_type *hswep_msr_uncores[] = {
 
 void hswep_uncore_cpu_init(void)
 {
-	int pkg = topology_phys_to_logical_pkg(0);
+	int pkg = boot_cpu_data.logical_proc_id;
 
 	if (hswep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
 		hswep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
-- 
2.11.0

[PATCH for v4.9 LTS 54/86] net: phy: marvell: fix Marvell 88E1512 used in SGMII mode

[Levin, Alexander (Sasha Levin)]

From: Russell King <rmk+kernel@armlinux.org.uk>

[ Upstream commit a13c06525ab9ff442924e67df9393a5efa914c56 ]

When an Marvell 88E1512 PHY is connected to a nic in SGMII mode, the
fiber page is used for the SGMII host-side connection.  The PHY driver
notices that SUPPORTED_FIBRE is set, so it tries reading the fiber page
for the link status, and ends up reading the MAC-side status instead of
the outgoing (copper) link.  This leads to incorrect results reported
via ethtool.

If the PHY is connected via SGMII to the host, ignore the fiber page.
However, continue to allow the existing power management code to
suspend and resume the fiber page.

Fixes: 6cfb3bcc0641 ("Marvell phy: check link status in case of fiber link.")
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/net/phy/marvell.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index d6a541bde331..d17173214a70 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -1202,7 +1202,8 @@ static int marvell_read_status(struct phy_device *phydev)
 	int err;
 
 	/* Check the fiber mode first */
-	if (phydev->supported & SUPPORTED_FIBRE) {
+	if (phydev->supported & SUPPORTED_FIBRE &&
+	    phydev->interface != PHY_INTERFACE_MODE_SGMII) {
 		err = phy_write(phydev, MII_MARVELL_PHY_PAGE, MII_M1111_FIBER);
 		if (err < 0)
 			goto error;
-- 
2.11.0

[PATCH for v4.9 LTS 55/86] mac80211: recalculate min channel width on VHT opmode changes

[Levin, Alexander (Sasha Levin)]

From: Johannes Berg <johannes.berg@intel.com>

[ Upstream commit d2941df8fbd9708035d66d889ada4d3d160170ce ]

When an associated station changes its VHT operating mode this
can/will affect the bandwidth it's using, and consequently we
must recalculate the minimum bandwidth we need to use. Failure
to do so can lead to one of two scenarios:
 1) we use a too high bandwidth, this is benign
 2) we use a too narrow bandwidth, causing rate control and
    actual PHY configuration to be out of sync, which can in
    turn cause problems/crashes

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 net/mac80211/iface.c | 21 +++++++++++++++++++++
 net/mac80211/rx.c    |  9 +--------
 net/mac80211/vht.c   |  4 +++-
 3 files changed, 25 insertions(+), 9 deletions(-)

diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 8d7747e98fdb..37bec0f864b7 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -6,6 +6,7 @@
  * Copyright (c) 2006 Jiri Benc <jbenc@suse.cz>
  * Copyright 2008, Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
+ * Copyright (c) 2016        Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -1307,6 +1308,26 @@ static void ieee80211_iface_work(struct work_struct *work)
 		} else if (ieee80211_is_action(mgmt->frame_control) &&
 			   mgmt->u.action.category == WLAN_CATEGORY_VHT) {
 			switch (mgmt->u.action.u.vht_group_notif.action_code) {
+			case WLAN_VHT_ACTION_OPMODE_NOTIF: {
+				struct ieee80211_rx_status *status;
+				enum nl80211_band band;
+				u8 opmode;
+
+				status = IEEE80211_SKB_RXCB(skb);
+				band = status->band;
+				opmode = mgmt->u.action.u.vht_opmode_notif.operating_mode;
+
+				mutex_lock(&local->sta_mtx);
+				sta = sta_info_get_bss(sdata, mgmt->sa);
+
+				if (sta)
+					ieee80211_vht_handle_opmode(sdata, sta,
+								    opmode,
+								    band);
+
+				mutex_unlock(&local->sta_mtx);
+				break;
+			}
 			case WLAN_VHT_ACTION_GROUPID_MGMT:
 				ieee80211_process_mu_groups(sdata, mgmt);
 				break;
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index acaaf616da71..c2a028eb7723 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -2918,17 +2918,10 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx)
 
 		switch (mgmt->u.action.u.vht_opmode_notif.action_code) {
 		case WLAN_VHT_ACTION_OPMODE_NOTIF: {
-			u8 opmode;
-
 			/* verify opmode is present */
 			if (len < IEEE80211_MIN_ACTION_SIZE + 2)
 				goto invalid;
-
-			opmode = mgmt->u.action.u.vht_opmode_notif.operating_mode;
-
-			ieee80211_vht_handle_opmode(rx->sdata, rx->sta,
-						    opmode, status->band);
-			goto handled;
+			goto queue;
 		}
 		case WLAN_VHT_ACTION_GROUPID_MGMT: {
 			if (len < IEEE80211_MIN_ACTION_SIZE + 25)
diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c
index 6832bf6ab69f..43e45bb660bc 100644
--- a/net/mac80211/vht.c
+++ b/net/mac80211/vht.c
@@ -527,8 +527,10 @@ void ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata,
 
 	u32 changed = __ieee80211_vht_handle_opmode(sdata, sta, opmode, band);
 
-	if (changed > 0)
+	if (changed > 0) {
+		ieee80211_recalc_min_chandef(sdata);
 		rate_control_rate_update(local, sband, sta, changed);
+	}
 }
 
 void ieee80211_get_vht_mask_from_cap(__le16 vht_cap,
-- 
2.11.0

[PATCH for v4.9 LTS 58/86] scsi: lpfc: avoid double free of resource identifiers

[Levin, Alexander (Sasha Levin)]

From: Roberto Sassu <rsassu@suse.de>

[ Upstream commit cd60be4916ae689387d04b86b6fc15931e4c95ae ]

Set variables initialized in lpfc_sli4_alloc_resource_identifiers() to
NULL if an error occurred. Otherwise, lpfc_sli4_driver_resource_unset()
attempts to free the memory again.

Signed-off-by: Roberto Sassu <rsassu@suse.de>
Signed-off-by: Johannes Thumshirn <jthumshirn@suse.de>
Acked-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/scsi/lpfc/lpfc_sli.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 49b4c798de18..2d4f4b58dcfa 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -5951,18 +5951,25 @@ lpfc_sli4_alloc_resource_identifiers(struct lpfc_hba *phba)
 
  free_vfi_bmask:
 	kfree(phba->sli4_hba.vfi_bmask);
+	phba->sli4_hba.vfi_bmask = NULL;
  free_xri_ids:
 	kfree(phba->sli4_hba.xri_ids);
+	phba->sli4_hba.xri_ids = NULL;
  free_xri_bmask:
 	kfree(phba->sli4_hba.xri_bmask);
+	phba->sli4_hba.xri_bmask = NULL;
  free_vpi_ids:
 	kfree(phba->vpi_ids);
+	phba->vpi_ids = NULL;
  free_vpi_bmask:
 	kfree(phba->vpi_bmask);
+	phba->vpi_bmask = NULL;
  free_rpi_ids:
 	kfree(phba->sli4_hba.rpi_ids);
+	phba->sli4_hba.rpi_ids = NULL;
  free_rpi_bmask:
 	kfree(phba->sli4_hba.rpi_bmask);
+	phba->sli4_hba.rpi_bmask = NULL;
  err_exit:
 	return rc;
 }
-- 
2.11.0

[PATCH for v4.9 LTS 57/86] HID: i2c-hid: Add sleep between POWER ON and RESET

[Levin, Alexander (Sasha Levin)]

From: Brendan McGrath <redmcg@redmandi.dyndns.org>

[ Upstream commit a89af4abdf9b353cdd6f61afc0eaaac403304873 ]

Support for the Asus Touchpad was recently added. It turns out this
device can fail initialisation (and become unusable) when the RESET
command is sent too soon after the POWER ON command.

Unfortunately the i2c-hid specification does not specify the need for
a delay between these two commands. But it was discovered the Windows
driver has a 1ms delay.

As a result, this patch modifies the i2c-hid module to add a sleep
inbetween the POWER ON and RESET commands which lasts between 1ms and 5ms.

See https://github.com/vlasenko/hid-asus-dkms/issues/24 for further
details.

Signed-off-by: Brendan McGrath <redmcg@redmandi.dyndns.org>
Reviewed-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/hid/i2c-hid/i2c-hid.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c
index b1bce804fe97..8008e06b7efe 100644
--- a/drivers/hid/i2c-hid/i2c-hid.c
+++ b/drivers/hid/i2c-hid/i2c-hid.c
@@ -427,6 +427,15 @@ static int i2c_hid_hwreset(struct i2c_client *client)
 	if (ret)
 		goto out_unlock;
 
+	/*
+	 * The HID over I2C specification states that if a DEVICE needs time
+	 * after the PWR_ON request, it should utilise CLOCK stretching.
+	 * However, it has been observered that the Windows driver provides a
+	 * 1ms sleep between the PWR_ON and RESET requests and that some devices
+	 * rely on this.
+	 */
+	usleep_range(1000, 5000);
+
 	i2c_hid_dbg(ihid, "resetting...\n");
 
 	ret = i2c_hid_command(client, &hid_reset_cmd, NULL, 0);
-- 
2.11.0

[PATCH for v4.9 LTS 56/86] perf/x86/intel: Use ULL constant to prevent undefined shift behaviour

[Levin, Alexander (Sasha Levin)]

From: Colin King <colin.king@canonical.com>

[ Upstream commit ad5013d5699d30ded0cdbbc68b93b2aa28222c6e ]

When x86_pmu.num_counters is 32 the shift of the integer constant 1 is
exceeding 32bit and therefor undefined behaviour.

Fix this by shifting 1ULL instead of 1.

Reported-by: CoverityScan CID#1192105 ("Bad bit shift operation")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Link: http://lkml.kernel.org/r/20170111114310.17928-1-colin.king@canonical.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 arch/x86/events/intel/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 8d7a6a0f7d2f..2d60044624b3 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3978,7 +3978,7 @@ __init int intel_pmu_init(void)
 		     x86_pmu.num_counters, INTEL_PMC_MAX_GENERIC);
 		x86_pmu.num_counters = INTEL_PMC_MAX_GENERIC;
 	}
-	x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1;
+	x86_pmu.intel_ctrl = (1ULL << x86_pmu.num_counters) - 1;
 
 	if (x86_pmu.num_counters_fixed > INTEL_PMC_MAX_FIXED) {
 		WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!",
-- 
2.11.0

[PATCH for v4.9 LTS 60/86] usb: dwc3: exynos fix axius clock error path to do cleanup

[Levin, Alexander (Sasha Levin)]

From: Shuah Khan <shuahkh@osg.samsung.com>

[ Upstream commit 8ae584d1951f241efd45499f8774fd7066f22823 ]

Axius clock error path returns without disabling clock and suspend clock.
Fix it to disable them before returning error.

Reviewed-by: Javier Martinez Canillas <javier@osg.samsung.com>
Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
Signed-off-by: Felipe Balbi <felipe.balbi@linux.intel.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/usb/dwc3/dwc3-exynos.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/dwc3/dwc3-exynos.c b/drivers/usb/dwc3/dwc3-exynos.c
index 2f1fb7e7aa54..9eba51b92f72 100644
--- a/drivers/usb/dwc3/dwc3-exynos.c
+++ b/drivers/usb/dwc3/dwc3-exynos.c
@@ -148,7 +148,8 @@ static int dwc3_exynos_probe(struct platform_device *pdev)
 		exynos->axius_clk = devm_clk_get(dev, "usbdrd30_axius_clk");
 		if (IS_ERR(exynos->axius_clk)) {
 			dev_err(dev, "no AXI UpScaler clk specified\n");
-			return -ENODEV;
+			ret = -ENODEV;
+			goto axius_clk_err;
 		}
 		clk_prepare_enable(exynos->axius_clk);
 	} else {
@@ -206,6 +207,7 @@ static int dwc3_exynos_probe(struct platform_device *pdev)
 	regulator_disable(exynos->vdd33);
 err2:
 	clk_disable_unprepare(exynos->axius_clk);
+axius_clk_err:
 	clk_disable_unprepare(exynos->susp_clk);
 	clk_disable_unprepare(exynos->clk);
 	return ret;
-- 
2.11.0

[PATCH for v4.9 LTS 61/86] spi: davinci: use dma_mapping_error()

[Levin, Alexander (Sasha Levin)]

From: Kevin Hilman <khilman@baylibre.com>

[ Upstream commit c5a2a394835f473ae23931eda5066d3771d7b2f8 ]

The correct error checking for dma_map_single() is to use
dma_mapping_error().

Signed-off-by: Kevin Hilman <khilman@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/spi/spi-davinci.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/spi/spi-davinci.c b/drivers/spi/spi-davinci.c
index d36c11b73a35..02fb96797ac8 100644
--- a/drivers/spi/spi-davinci.c
+++ b/drivers/spi/spi-davinci.c
@@ -646,7 +646,7 @@ static int davinci_spi_bufs(struct spi_device *spi, struct spi_transfer *t)
 			buf = t->rx_buf;
 		t->rx_dma = dma_map_single(&spi->dev, buf,
 				t->len, DMA_FROM_DEVICE);
-		if (!t->rx_dma) {
+		if (dma_mapping_error(&spi->dev, !t->rx_dma)) {
 			ret = -EFAULT;
 			goto err_rx_map;
 		}
@@ -660,7 +660,7 @@ static int davinci_spi_bufs(struct spi_device *spi, struct spi_transfer *t)
 			buf = (void *)t->tx_buf;
 		t->tx_dma = dma_map_single(&spi->dev, buf,
 				t->len, DMA_TO_DEVICE);
-		if (!t->tx_dma) {
+		if (dma_mapping_error(&spi->dev, t->tx_dma)) {
 			ret = -EFAULT;
 			goto err_tx_map;
 		}
-- 
2.11.0

[PATCH for v4.9 LTS 59/86] usb: gadget: composite: Fix function used to free memory

[Levin, Alexander (Sasha Levin)]

From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>

[ Upstream commit 990758c53eafe5a220a780ed12e7b4d51b3df032 ]

'cdev->os_desc_req' has been allocated with 'usb_ep_alloc_request()' so
'usb_ep_free_request()' should be used to free it.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Felipe Balbi <felipe.balbi@linux.intel.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/usb/gadget/composite.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index c3c5b87b35b3..baa7cdcc0ebc 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -2147,7 +2147,7 @@ int composite_os_desc_req_prepare(struct usb_composite_dev *cdev,
 	cdev->os_desc_req->buf = kmalloc(4096, GFP_KERNEL);
 	if (!cdev->os_desc_req->buf) {
 		ret = -ENOMEM;
-		kfree(cdev->os_desc_req);
+		usb_ep_free_request(ep0, cdev->os_desc_req);
 		goto end;
 	}
 	cdev->os_desc_req->context = cdev;
-- 
2.11.0

[PATCH for v4.9 LTS 64/86] drm/radeon/si: load special ucode for certain MC configs

[Levin, Alexander (Sasha Levin)]

From: Alex Deucher <alexander.deucher@amd.com>

[ Upstream commit ef736d394e85b1bf1fd65ba5e5257b85f6c82325 ]

Special MC ucode is required for these memory configurations.

Acked-by: Edward O'Callaghan <funfunctor@folklore1984.net>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/gpu/drm/radeon/si.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 3333e8a45933..b75d809c292e 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -115,6 +115,8 @@ MODULE_FIRMWARE("radeon/hainan_rlc.bin");
 MODULE_FIRMWARE("radeon/hainan_smc.bin");
 MODULE_FIRMWARE("radeon/hainan_k_smc.bin");
 
+MODULE_FIRMWARE("radeon/si58_mc.bin");
+
 static u32 si_get_cu_active_bitmap(struct radeon_device *rdev, u32 se, u32 sh);
 static void si_pcie_gen3_enable(struct radeon_device *rdev);
 static void si_program_aspm(struct radeon_device *rdev);
@@ -1650,6 +1652,7 @@ static int si_init_microcode(struct radeon_device *rdev)
 	int err;
 	int new_fw = 0;
 	bool new_smc = false;
+	bool si58_fw = false;
 
 	DRM_DEBUG("\n");
 
@@ -1742,6 +1745,10 @@ static int si_init_microcode(struct radeon_device *rdev)
 	default: BUG();
 	}
 
+	/* this memory configuration requires special firmware */
+	if (((RREG32(MC_SEQ_MISC0) & 0xff000000) >> 24) == 0x58)
+		si58_fw = true;
+
 	DRM_INFO("Loading %s Microcode\n", new_chip_name);
 
 	snprintf(fw_name, sizeof(fw_name), "radeon/%s_pfp.bin", new_chip_name);
@@ -1845,7 +1852,10 @@ static int si_init_microcode(struct radeon_device *rdev)
 		}
 	}
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", new_chip_name);
+	if (si58_fw)
+		snprintf(fw_name, sizeof(fw_name), "radeon/si58_mc.bin");
+	else
+		snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", new_chip_name);
 	err = request_firmware(&rdev->mc_fw, fw_name, rdev->dev);
 	if (err) {
 		snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc2.bin", chip_name);
-- 
2.11.0

[PATCH for v4.9 LTS 62/86] arm64: assembler: make adr_l work in modules under KASLR

[Levin, Alexander (Sasha Levin)]

From: Ard Biesheuvel <ard.biesheuvel@linaro.org>

[ Upstream commit 41c066f2c4d436c535616fe182331766c57838f0 ]

When CONFIG_RANDOMIZE_MODULE_REGION_FULL=y, the offset between loaded
modules and the core kernel may exceed 4 GB, putting symbols exported
by the core kernel out of the reach of the ordinary adrp/add instruction
pairs used to generate relative symbol references. So make the adr_l
macro emit a movz/movk sequence instead when executing in module context.

While at it, remove the pointless special case for the stack pointer.

Acked-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 arch/arm64/include/asm/assembler.h | 36 +++++++++++++++++++++++++++---------
 1 file changed, 27 insertions(+), 9 deletions(-)

diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 28bfe6132eb6..851290d2bfe3 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -155,22 +155,25 @@ lr	.req	x30		// link register
 
 /*
  * Pseudo-ops for PC-relative adr/ldr/str <reg>, <symbol> where
- * <symbol> is within the range +/- 4 GB of the PC.
+ * <symbol> is within the range +/- 4 GB of the PC when running
+ * in core kernel context. In module context, a movz/movk sequence
+ * is used, since modules may be loaded far away from the kernel
+ * when KASLR is in effect.
  */
 	/*
 	 * @dst: destination register (64 bit wide)
 	 * @sym: name of the symbol
-	 * @tmp: optional scratch register to be used if <dst> == sp, which
-	 *       is not allowed in an adrp instruction
 	 */
-	.macro	adr_l, dst, sym, tmp=
-	.ifb	\tmp
+	.macro	adr_l, dst, sym
+#ifndef MODULE
 	adrp	\dst, \sym
 	add	\dst, \dst, :lo12:\sym
-	.else
-	adrp	\tmp, \sym
-	add	\dst, \tmp, :lo12:\sym
-	.endif
+#else
+	movz	\dst, #:abs_g3:\sym
+	movk	\dst, #:abs_g2_nc:\sym
+	movk	\dst, #:abs_g1_nc:\sym
+	movk	\dst, #:abs_g0_nc:\sym
+#endif
 	.endm
 
 	/*
@@ -181,6 +184,7 @@ lr	.req	x30		// link register
 	 *       the address
 	 */
 	.macro	ldr_l, dst, sym, tmp=
+#ifndef MODULE
 	.ifb	\tmp
 	adrp	\dst, \sym
 	ldr	\dst, [\dst, :lo12:\sym]
@@ -188,6 +192,15 @@ lr	.req	x30		// link register
 	adrp	\tmp, \sym
 	ldr	\dst, [\tmp, :lo12:\sym]
 	.endif
+#else
+	.ifb	\tmp
+	adr_l	\dst, \sym
+	ldr	\dst, [\dst]
+	.else
+	adr_l	\tmp, \sym
+	ldr	\dst, [\tmp]
+	.endif
+#endif
 	.endm
 
 	/*
@@ -197,8 +210,13 @@ lr	.req	x30		// link register
 	 *       while <src> needs to be preserved.
 	 */
 	.macro	str_l, src, sym, tmp
+#ifndef MODULE
 	adrp	\tmp, \sym
 	str	\src, [\tmp, :lo12:\sym]
+#else
+	adr_l	\tmp, \sym
+	str	\src, [\tmp]
+#endif
 	.endm
 
 	/*
-- 
2.11.0

[PATCH for v4.9 LTS 63/86] net: thunderx: acpi: fix LMAC initialization

[Levin, Alexander (Sasha Levin)]

From: Vadim Lomovtsev <Vadim.Lomovtsev@caviumnetworks.com>

[ Upstream commit 7aa4865506a26c607e00bd9794a85785b55ebca7 ]

While probing BGX we requesting appropriate QLM for it's configuration
and get LMAC count by that request. Then, while reading configured
MAC values from SSDT table we need to save them in proper mapping:
  BGX[i]->lmac[j].mac = <MAC value>
to later provide for initialization stuff. In order to fill
such mapping properly we need to add lmac index to be used while
acpi initialization since at this moment bgx->lmac_count already contains
actual value.

Signed-off-by: Vadim Lomovtsev <Vadim.Lomovtsev@caviumnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/net/ethernet/cavium/thunder/thunder_bgx.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 679679a4ccb2..e858b1af788d 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -48,8 +48,9 @@ struct lmac {
 struct bgx {
 	u8			bgx_id;
 	struct	lmac		lmac[MAX_LMAC_PER_BGX];
-	int			lmac_count;
+	u8			lmac_count;
 	u8			max_lmac;
+	u8                      acpi_lmac_idx;
 	void __iomem		*reg_base;
 	struct pci_dev		*pdev;
 	bool                    is_dlm;
@@ -1159,13 +1160,13 @@ static acpi_status bgx_acpi_register_phy(acpi_handle handle,
 	if (acpi_bus_get_device(handle, &adev))
 		goto out;
 
-	acpi_get_mac_address(dev, adev, bgx->lmac[bgx->lmac_count].mac);
+	acpi_get_mac_address(dev, adev, bgx->lmac[bgx->acpi_lmac_idx].mac);
 
-	SET_NETDEV_DEV(&bgx->lmac[bgx->lmac_count].netdev, dev);
+	SET_NETDEV_DEV(&bgx->lmac[bgx->acpi_lmac_idx].netdev, dev);
 
-	bgx->lmac[bgx->lmac_count].lmacid = bgx->lmac_count;
+	bgx->lmac[bgx->acpi_lmac_idx].lmacid = bgx->acpi_lmac_idx;
+	bgx->acpi_lmac_idx++; /* move to next LMAC */
 out:
-	bgx->lmac_count++;
 	return AE_OK;
 }
 
-- 
2.11.0

[PATCH for v4.9 LTS 65/86] drm/amd/powerplay: fix vce cg logic error on CZ/St.

[Levin, Alexander (Sasha Levin)]

From: Rex Zhu <Rex.Zhu@amd.com>

[ Upstream commit 3731d12dce83d47b357753ffc450ce03f1b49688 ]

can fix Bug 191281: vce ib test failed.

when vce idle, set vce clock gate, so the clock
in vce domain will be disabled.
when need to encode, disable vce clock gate,
enable the clocks to vce engine.

Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c
index 2028980f1ed4..5b261c1dcc9f 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c
@@ -200,7 +200,7 @@ int cz_dpm_powergate_vce(struct pp_hwmgr *hwmgr, bool bgate)
 				cgs_set_clockgating_state(
 							hwmgr->device,
 							AMD_IP_BLOCK_TYPE_VCE,
-							AMD_CG_STATE_UNGATE);
+							AMD_CG_STATE_GATE);
 				cgs_set_powergating_state(
 							hwmgr->device,
 							AMD_IP_BLOCK_TYPE_VCE,
@@ -218,7 +218,7 @@ int cz_dpm_powergate_vce(struct pp_hwmgr *hwmgr, bool bgate)
 				cgs_set_clockgating_state(
 							hwmgr->device,
 							AMD_IP_BLOCK_TYPE_VCE,
-							AMD_PG_STATE_GATE);
+							AMD_PG_STATE_UNGATE);
 				cz_dpm_update_vce_dpm(hwmgr);
 				cz_enable_disable_vce_dpm(hwmgr, true);
 				return 0;
-- 
2.11.0

[PATCH for v4.9 LTS 66/86] drm/amd/powerplay: refine vce dpm update code on Cz.

[Levin, Alexander (Sasha Levin)]

From: Rex Zhu <Rex.Zhu@amd.com>

[ Upstream commit ab8db87b8256e13a62f10af1d32f5fc233c398cc ]

Program HardMin based on the vce_arbiter.ecclk
if ecclk is 0, disable ECLK DPM 0. Otherwise VCE
could hang if switching SCLK from DPM 0 to 6/7

Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c | 24 ++++++++++++++++--------
 1 file changed, 16 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c
index 960424913496..189ec94c6ff9 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c
@@ -1402,14 +1402,22 @@ int  cz_dpm_update_vce_dpm(struct pp_hwmgr *hwmgr)
 					     cz_hwmgr->vce_dpm.hard_min_clk,
 						PPSMC_MSG_SetEclkHardMin));
 	} else {
-		/*EPR# 419220 -HW limitation to to */
-		cz_hwmgr->vce_dpm.hard_min_clk = hwmgr->vce_arbiter.ecclk;
-		smum_send_msg_to_smc_with_parameter(hwmgr->smumgr,
-					    PPSMC_MSG_SetEclkHardMin,
-					    cz_get_eclk_level(hwmgr,
-				     cz_hwmgr->vce_dpm.hard_min_clk,
-					  PPSMC_MSG_SetEclkHardMin));
-
+		/*Program HardMin based on the vce_arbiter.ecclk */
+		if (hwmgr->vce_arbiter.ecclk == 0) {
+			smum_send_msg_to_smc_with_parameter(hwmgr->smumgr,
+					    PPSMC_MSG_SetEclkHardMin, 0);
+		/* disable ECLK DPM 0. Otherwise VCE could hang if
+		 * switching SCLK from DPM 0 to 6/7 */
+			smum_send_msg_to_smc_with_parameter(hwmgr->smumgr,
+					PPSMC_MSG_SetEclkSoftMin, 1);
+		} else {
+			cz_hwmgr->vce_dpm.hard_min_clk = hwmgr->vce_arbiter.ecclk;
+			smum_send_msg_to_smc_with_parameter(hwmgr->smumgr,
+						PPSMC_MSG_SetEclkHardMin,
+						cz_get_eclk_level(hwmgr,
+						cz_hwmgr->vce_dpm.hard_min_clk,
+						PPSMC_MSG_SetEclkHardMin));
+		}
 	}
 	return 0;
 }
-- 
2.11.0

[PATCH for v4.9 LTS 68/86] mac80211: initialize SMPS field in HT capabilities

[Levin, Alexander (Sasha Levin)]

From: Felix Fietkau <nbd@nbd.name>

[ Upstream commit 43071d8fb3b7f589d72663c496a6880fb097533c ]

ibss and mesh modes copy the ht capabilites from the band without
overriding the SMPS state. Unfortunately the default value 0 for the
SMPS field means static SMPS instead of disabled.

This results in HT ibss and mesh setups using only single-stream rates,
even though SMPS is not supposed to be active.

Initialize SMPS to disabled for all bands on ieee80211_hw_register to
ensure that the value is sane where it is not overriden with the real
SMPS state.

Reported-by: Elektra Wagenrad <onelektra@gmx.net>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
[move VHT TODO comment to a better place]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>

Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 net/mac80211/main.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 1075ac24c8c5..2bb6899854d4 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -908,12 +908,17 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 		supp_ht = supp_ht || sband->ht_cap.ht_supported;
 		supp_vht = supp_vht || sband->vht_cap.vht_supported;
 
-		if (sband->ht_cap.ht_supported)
-			local->rx_chains =
-				max(ieee80211_mcs_to_chains(&sband->ht_cap.mcs),
-				    local->rx_chains);
+		if (!sband->ht_cap.ht_supported)
+			continue;
 
 		/* TODO: consider VHT for RX chains, hopefully it's the same */
+		local->rx_chains =
+			max(ieee80211_mcs_to_chains(&sband->ht_cap.mcs),
+			    local->rx_chains);
+
+		/* no need to mask, SM_PS_DISABLED has all bits set */
+		sband->ht_cap.cap |= WLAN_HT_CAP_SM_PS_DISABLED <<
+			             IEEE80211_HT_CAP_SM_PS_SHIFT;
 	}
 
 	/* if low-level driver supports AP, we also support VLAN */
-- 
2.11.0

[PATCH for v4.9 LTS 69/86] KVM: arm64: Access CNTHCTL_EL2 bit fields correctly on VHE systems

[Levin, Alexander (Sasha Levin)]

From: Jintack Lim <jintack@cs.columbia.edu>

[ Upstream commit 488f94d7212b00a2ec72fb886b155f1b04c5aa98 ]

Current KVM world switch code is unintentionally setting wrong bits to
CNTHCTL_EL2 when E2H == 1, which may allow guest OS to access physical
timer.  Bit positions of CNTHCTL_EL2 are changing depending on
HCR_EL2.E2H bit.  EL1PCEN and EL1PCTEN are 1st and 0th bits when E2H is
not set, but they are 11th and 10th bits respectively when E2H is set.

In fact, on VHE we only need to set those bits once, not for every world
switch. This is because the host kernel runs in EL2 with HCR_EL2.TGE ==
1, which makes those bits have no effect for the host kernel execution.
So we just set those bits once for guests, and that's it.

Signed-off-by: Jintack Lim <jintack@cs.columbia.edu>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 arch/arm/include/asm/virt.h   |  5 +++++
 arch/arm/kvm/arm.c            |  3 +++
 arch/arm64/include/asm/virt.h |  9 +++++++++
 include/kvm/arm_arch_timer.h  |  1 +
 virt/kvm/arm/arch_timer.c     | 23 +++++++++++++++++++++++
 virt/kvm/arm/hyp/timer-sr.c   | 33 +++++++++++++++++++++------------
 6 files changed, 62 insertions(+), 12 deletions(-)

diff --git a/arch/arm/include/asm/virt.h b/arch/arm/include/asm/virt.h
index a2e75b84e2ae..6dae1956c74d 100644
--- a/arch/arm/include/asm/virt.h
+++ b/arch/arm/include/asm/virt.h
@@ -80,6 +80,11 @@ static inline bool is_kernel_in_hyp_mode(void)
 	return false;
 }
 
+static inline bool has_vhe(void)
+{
+	return false;
+}
+
 /* The section containing the hypervisor idmap text */
 extern char __hyp_idmap_text_start[];
 extern char __hyp_idmap_text_end[];
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 19b5f5c1c0ff..60d031642798 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -1093,6 +1093,9 @@ static void cpu_init_hyp_mode(void *dummy)
 	__cpu_init_hyp_mode(pgd_ptr, hyp_stack_ptr, vector_ptr);
 	__cpu_init_stage2();
 
+	if (is_kernel_in_hyp_mode())
+		kvm_timer_init_vhe();
+
 	kvm_arm_init_debug();
 }
 
diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h
index fea10736b11f..439f6b5d31f6 100644
--- a/arch/arm64/include/asm/virt.h
+++ b/arch/arm64/include/asm/virt.h
@@ -47,6 +47,7 @@
 #include <asm/ptrace.h>
 #include <asm/sections.h>
 #include <asm/sysreg.h>
+#include <asm/cpufeature.h>
 
 /*
  * __boot_cpu_mode records what mode CPUs were booted in.
@@ -80,6 +81,14 @@ static inline bool is_kernel_in_hyp_mode(void)
 	return read_sysreg(CurrentEL) == CurrentEL_EL2;
 }
 
+static inline bool has_vhe(void)
+{
+	if (cpus_have_const_cap(ARM64_HAS_VIRT_HOST_EXTN))
+		return true;
+
+	return false;
+}
+
 #ifdef CONFIG_ARM64_VHE
 extern void verify_cpu_run_el(void);
 #else
diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h
index dda39d8fa189..2d5490375e0d 100644
--- a/include/kvm/arm_arch_timer.h
+++ b/include/kvm/arm_arch_timer.h
@@ -76,4 +76,5 @@ void kvm_timer_unschedule(struct kvm_vcpu *vcpu);
 
 void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu);
 
+void kvm_timer_init_vhe(void);
 #endif
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index 27a1f6341d41..0ebd0dc39cd4 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -24,6 +24,7 @@
 
 #include <clocksource/arm_arch_timer.h>
 #include <asm/arch_timer.h>
+#include <asm/kvm_hyp.h>
 
 #include <kvm/arm_vgic.h>
 #include <kvm/arm_arch_timer.h>
@@ -517,3 +518,25 @@ void kvm_timer_init(struct kvm *kvm)
 {
 	kvm->arch.timer.cntvoff = kvm_phys_timer_read();
 }
+
+/*
+ * On VHE system, we only need to configure trap on physical timer and counter
+ * accesses in EL0 and EL1 once, not for every world switch.
+ * The host kernel runs at EL2 with HCR_EL2.TGE == 1,
+ * and this makes those bits have no effect for the host kernel execution.
+ */
+void kvm_timer_init_vhe(void)
+{
+	/* When HCR_EL2.E2H ==1, EL1PCEN and EL1PCTEN are shifted by 10 */
+	u32 cnthctl_shift = 10;
+	u64 val;
+
+	/*
+	 * Disallow physical timer access for the guest.
+	 * Physical counter access is allowed.
+	 */
+	val = read_sysreg(cnthctl_el2);
+	val &= ~(CNTHCTL_EL1PCEN << cnthctl_shift);
+	val |= (CNTHCTL_EL1PCTEN << cnthctl_shift);
+	write_sysreg(val, cnthctl_el2);
+}
diff --git a/virt/kvm/arm/hyp/timer-sr.c b/virt/kvm/arm/hyp/timer-sr.c
index 798866a8d875..63e28dd18bb0 100644
--- a/virt/kvm/arm/hyp/timer-sr.c
+++ b/virt/kvm/arm/hyp/timer-sr.c
@@ -35,10 +35,16 @@ void __hyp_text __timer_save_state(struct kvm_vcpu *vcpu)
 	/* Disable the virtual timer */
 	write_sysreg_el0(0, cntv_ctl);
 
-	/* Allow physical timer/counter access for the host */
-	val = read_sysreg(cnthctl_el2);
-	val |= CNTHCTL_EL1PCTEN | CNTHCTL_EL1PCEN;
-	write_sysreg(val, cnthctl_el2);
+	/*
+	 * We don't need to do this for VHE since the host kernel runs in EL2
+	 * with HCR_EL2.TGE ==1, which makes those bits have no impact.
+	 */
+	if (!has_vhe()) {
+		/* Allow physical timer/counter access for the host */
+		val = read_sysreg(cnthctl_el2);
+		val |= CNTHCTL_EL1PCTEN | CNTHCTL_EL1PCEN;
+		write_sysreg(val, cnthctl_el2);
+	}
 
 	/* Clear cntvoff for the host */
 	write_sysreg(0, cntvoff_el2);
@@ -50,14 +56,17 @@ void __hyp_text __timer_restore_state(struct kvm_vcpu *vcpu)
 	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
 	u64 val;
 
-	/*
-	 * Disallow physical timer access for the guest
-	 * Physical counter access is allowed
-	 */
-	val = read_sysreg(cnthctl_el2);
-	val &= ~CNTHCTL_EL1PCEN;
-	val |= CNTHCTL_EL1PCTEN;
-	write_sysreg(val, cnthctl_el2);
+	/* Those bits are already configured at boot on VHE-system */
+	if (!has_vhe()) {
+		/*
+		 * Disallow physical timer access for the guest
+		 * Physical counter access is allowed
+		 */
+		val = read_sysreg(cnthctl_el2);
+		val &= ~CNTHCTL_EL1PCEN;
+		val |= CNTHCTL_EL1PCTEN;
+		write_sysreg(val, cnthctl_el2);
+	}
 
 	if (timer->enabled) {
 		write_sysreg(kvm->arch.timer.cntvoff, cntvoff_el2);
-- 
2.11.0

[PATCH for v4.9 LTS 67/86] pmem: return EIO on read_pmem() failure

[Levin, Alexander (Sasha Levin)]

From: Stefan Hajnoczi <stefanha@redhat.com>

[ Upstream commit d47d1d27fd6206c18806440f6ebddf51a806be4f ]

The read_pmem() function uses memcpy_mcsafe() on x86 where an EFAULT
error code indicates a failed read.  Block I/O should use EIO to
indicate failure.  Other pmem code paths (like bad blocks) already use
EIO so let's be consistent.

This fixes compatibility with consumers like btrfs that try to parse the
specific error code rather than treat all errors the same.

Reviewed-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/nvdimm/pmem.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index b4808590870c..3456f532077c 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -87,7 +87,9 @@ static int read_pmem(struct page *page, unsigned int off,
 
 	rc = memcpy_from_pmem(mem + off, pmem_addr, len);
 	kunmap_atomic(mem);
-	return rc;
+	if (rc)
+		return -EIO;
+	return 0;
 }
 
 static int pmem_do_bvec(struct pmem_device *pmem, struct page *page,
-- 
2.11.0

[PATCH for v4.9 LTS 70/86] x86/tsc: Add the Intel Denverton Processor to native_calibrate_tsc()

[Levin, Alexander (Sasha Levin)]

From: Len Brown <len.brown@intel.com>

[ Upstream commit 695085b4bc7603551db0b3da897b8bf9893ca218 ]

The Intel Denverton microserver uses a 25 MHz TSC crystal,
so we can derive its exact [*] TSC frequency
using CPUID and some arithmetic, eg.:

  TSC: 1800 MHz (25000000 Hz * 216 / 3 / 1000000)

[*] 'exact' is only as good as the crystal, which should be +/- 20ppm

Signed-off-by: Len Brown <len.brown@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/306899f94804aece6d8fa8b4223ede3b48dbb59c.1484287748.git.len.brown@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 arch/x86/kernel/tsc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index eea88fe5d969..6e57edf33d75 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -694,6 +694,7 @@ unsigned long native_calibrate_tsc(void)
 			crystal_khz = 24000;	/* 24.0 MHz */
 			break;
 		case INTEL_FAM6_SKYLAKE_X:
+		case INTEL_FAM6_ATOM_DENVERTON:
 			crystal_khz = 25000;	/* 25.0 MHz */
 			break;
 		case INTEL_FAM6_ATOM_GOLDMONT:
-- 
2.11.0

[PATCH for v4.9 LTS 71/86] x86/mpx: Use compatible types in comparison to fix sparse error

[Levin, Alexander (Sasha Levin)]

From: Tobias Klauser <tklauser@distanz.ch>

[ Upstream commit 453828625731d0ba7218242ef6ec88f59408f368 ]

info->si_addr is of type void __user *, so it should be compared against
something from the same address space.

This fixes the following sparse error:

  arch/x86/mm/mpx.c:296:27: error: incompatible types in comparison expression (different address spaces)

Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 arch/x86/mm/mpx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index e4f800999b32..3e7c489e1f55 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -293,7 +293,7 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs)
 	 * We were not able to extract an address from the instruction,
 	 * probably because there was something invalid in it.
 	 */
-	if (info->si_addr == (void *)-1) {
+	if (info->si_addr == (void __user *)-1) {
 		err = -EINVAL;
 		goto err_out;
 	}
-- 
2.11.0

[PATCH for v4.9 LTS 72/86] perf/core: Fix sys_perf_event_open() vs. hotplug

[Levin, Alexander (Sasha Levin)]

From: Peter Zijlstra <peterz@infradead.org>

[ Upstream commit 63cae12bce9861cec309798d34701cf3da20bc71 ]

There is problem with installing an event in a task that is 'stuck' on
an offline CPU.

Blocked tasks are not dis-assosciated from offlined CPUs, after all, a
blocked task doesn't run and doesn't require a CPU etc.. Only on
wakeup do we ammend the situation and place the task on a available
CPU.

If we hit such a task with perf_install_in_context() we'll loop until
either that task wakes up or the CPU comes back online, if the task
waking depends on the event being installed, we're stuck.

While looking into this issue, I also spotted another problem, if we
hit a task with perf_install_in_context() that is in the middle of
being migrated, that is we observe the old CPU before sending the IPI,
but run the IPI (on the old CPU) while the task is already running on
the new CPU, things also go sideways.

Rework things to rely on task_curr() -- outside of rq->lock -- which
is rather tricky. Imagine the following scenario where we're trying to
install the first event into our task 't':

CPU0            CPU1            CPU2

                (current == t)

t->perf_event_ctxp[] = ctx;
smp_mb();
cpu = task_cpu(t);

                switch(t, n);
                                migrate(t, 2);
                                switch(p, t);

                                ctx = t->perf_event_ctxp[]; // must not be NULL

smp_function_call(cpu, ..);

                generic_exec_single()
                  func();
                    spin_lock(ctx->lock);
                    if (task_curr(t)) // false

                    add_event_to_ctx();
                    spin_unlock(ctx->lock);

                                perf_event_context_sched_in();
                                  spin_lock(ctx->lock);
                                  // sees event

So its CPU0's store of t->perf_event_ctxp[] that must not go 'missing'.
Because if CPU2's load of that variable were to observe NULL, it would
not try to schedule the ctx and we'd have a task running without its
counter, which would be 'bad'.

As long as we observe !NULL, we'll acquire ctx->lock. If we acquire it
first and not see the event yet, then CPU0 must observe task_curr()
and retry. If the install happens first, then we must see the event on
sched-in and all is well.

I think we can translate the first part (until the 'must not be NULL')
of the scenario to a litmus test like:

  C C-peterz

  {
  }

  P0(int *x, int *y)
  {
          int r1;

          WRITE_ONCE(*x, 1);
          smp_mb();
          r1 = READ_ONCE(*y);
  }

  P1(int *y, int *z)
  {
          WRITE_ONCE(*y, 1);
          smp_store_release(z, 1);
  }

  P2(int *x, int *z)
  {
          int r1;
          int r2;

          r1 = smp_load_acquire(z);
	  smp_mb();
          r2 = READ_ONCE(*x);
  }

  exists
  (0:r1=0 /\ 2:r1=1 /\ 2:r2=0)

Where:
  x is perf_event_ctxp[],
  y is our tasks's CPU, and
  z is our task being placed on the rq of CPU2.

The P0 smp_mb() is the one added by this patch, ordering the store to
perf_event_ctxp[] from find_get_context() and the load of task_cpu()
in task_function_call().

The smp_store_release/smp_load_acquire model the RCpc locking of the
rq->lock and the smp_mb() of P2 is the context switch switching from
whatever CPU2 was running to our task 't'.

This litmus test evaluates into:

  Test C-peterz Allowed
  States 7
  0:r1=0; 2:r1=0; 2:r2=0;
  0:r1=0; 2:r1=0; 2:r2=1;
  0:r1=0; 2:r1=1; 2:r2=1;
  0:r1=1; 2:r1=0; 2:r2=0;
  0:r1=1; 2:r1=0; 2:r2=1;
  0:r1=1; 2:r1=1; 2:r2=0;
  0:r1=1; 2:r1=1; 2:r2=1;
  No
  Witnesses
  Positive: 0 Negative: 7
  Condition exists (0:r1=0 /\ 2:r1=1 /\ 2:r2=0)
  Observation C-peterz Never 0 7
  Hash=e427f41d9146b2a5445101d3e2fcaa34

And the strong and weak model agree.

Reported-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: Will Deacon <will.deacon@arm.com>
Cc: jeremy.linton@arm.com
Link: http://lkml.kernel.org/r/20161209135900.GU3174@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 kernel/events/core.c | 70 +++++++++++++++++++++++++++++++++++-----------------
 1 file changed, 48 insertions(+), 22 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 11cc1d83c770..30ccc7029d18 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2272,7 +2272,7 @@ static int  __perf_install_in_context(void *info)
 	struct perf_event_context *ctx = event->ctx;
 	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 	struct perf_event_context *task_ctx = cpuctx->task_ctx;
-	bool activate = true;
+	bool reprogram = true;
 	int ret = 0;
 
 	raw_spin_lock(&cpuctx->ctx.lock);
@@ -2280,27 +2280,26 @@ static int  __perf_install_in_context(void *info)
 		raw_spin_lock(&ctx->lock);
 		task_ctx = ctx;
 
-		/* If we're on the wrong CPU, try again */
-		if (task_cpu(ctx->task) != smp_processor_id()) {
-			ret = -ESRCH;
-			goto unlock;
-		}
+		reprogram = (ctx->task == current);
 
 		/*
-		 * If we're on the right CPU, see if the task we target is
-		 * current, if not we don't have to activate the ctx, a future
-		 * context switch will do that for us.
+		 * If the task is running, it must be running on this CPU,
+		 * otherwise we cannot reprogram things.
+		 *
+		 * If its not running, we don't care, ctx->lock will
+		 * serialize against it becoming runnable.
 		 */
-		if (ctx->task != current)
-			activate = false;
-		else
-			WARN_ON_ONCE(cpuctx->task_ctx && cpuctx->task_ctx != ctx);
+		if (task_curr(ctx->task) && !reprogram) {
+			ret = -ESRCH;
+			goto unlock;
+		}
 
+		WARN_ON_ONCE(reprogram && cpuctx->task_ctx && cpuctx->task_ctx != ctx);
 	} else if (task_ctx) {
 		raw_spin_lock(&task_ctx->lock);
 	}
 
-	if (activate) {
+	if (reprogram) {
 		ctx_sched_out(ctx, cpuctx, EVENT_TIME);
 		add_event_to_ctx(event, ctx);
 		ctx_resched(cpuctx, task_ctx);
@@ -2351,13 +2350,36 @@ perf_install_in_context(struct perf_event_context *ctx,
 	/*
 	 * Installing events is tricky because we cannot rely on ctx->is_active
 	 * to be set in case this is the nr_events 0 -> 1 transition.
+	 *
+	 * Instead we use task_curr(), which tells us if the task is running.
+	 * However, since we use task_curr() outside of rq::lock, we can race
+	 * against the actual state. This means the result can be wrong.
+	 *
+	 * If we get a false positive, we retry, this is harmless.
+	 *
+	 * If we get a false negative, things are complicated. If we are after
+	 * perf_event_context_sched_in() ctx::lock will serialize us, and the
+	 * value must be correct. If we're before, it doesn't matter since
+	 * perf_event_context_sched_in() will program the counter.
+	 *
+	 * However, this hinges on the remote context switch having observed
+	 * our task->perf_event_ctxp[] store, such that it will in fact take
+	 * ctx::lock in perf_event_context_sched_in().
+	 *
+	 * We do this by task_function_call(), if the IPI fails to hit the task
+	 * we know any future context switch of task must see the
+	 * perf_event_ctpx[] store.
 	 */
-again:
+
 	/*
-	 * Cannot use task_function_call() because we need to run on the task's
-	 * CPU regardless of whether its current or not.
+	 * This smp_mb() orders the task->perf_event_ctxp[] store with the
+	 * task_cpu() load, such that if the IPI then does not find the task
+	 * running, a future context switch of that task must observe the
+	 * store.
 	 */
-	if (!cpu_function_call(task_cpu(task), __perf_install_in_context, event))
+	smp_mb();
+again:
+	if (!task_function_call(task, __perf_install_in_context, event))
 		return;
 
 	raw_spin_lock_irq(&ctx->lock);
@@ -2371,12 +2393,16 @@ perf_install_in_context(struct perf_event_context *ctx,
 		raw_spin_unlock_irq(&ctx->lock);
 		return;
 	}
-	raw_spin_unlock_irq(&ctx->lock);
 	/*
-	 * Since !ctx->is_active doesn't mean anything, we must IPI
-	 * unconditionally.
+	 * If the task is not running, ctx->lock will avoid it becoming so,
+	 * thus we can safely install the event.
 	 */
-	goto again;
+	if (task_curr(task)) {
+		raw_spin_unlock_irq(&ctx->lock);
+		goto again;
+	}
+	add_event_to_ctx(event, ctx);
+	raw_spin_unlock_irq(&ctx->lock);
 }
 
 /*
-- 
2.11.0

[PATCH for v4.9 LTS 74/86] aio: fix lock dep warning

[Levin, Alexander (Sasha Levin)]

From: Shaohua Li <shli@fb.com>

[ Upstream commit a12f1ae61c489076a9aeb90bddca7722bf330df3 ]

lockdep reports a warnning. file_start_write/file_end_write only
acquire/release the lock for regular files. So checking the files in aio
side too.

[  453.532141] ------------[ cut here ]------------
[  453.533011] WARNING: CPU: 1 PID: 1298 at ../kernel/locking/lockdep.c:3514 lock_release+0x434/0x670
[  453.533011] DEBUG_LOCKS_WARN_ON(depth <= 0)
[  453.533011] Modules linked in:
[  453.533011] CPU: 1 PID: 1298 Comm: fio Not tainted 4.9.0+ #964
[  453.533011] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.9.0-1.fc24 04/01/2014
[  453.533011]  ffff8803a24b7a70 ffffffff8196cffb ffff8803a24b7ae8 0000000000000000
[  453.533011]  ffff8803a24b7ab8 ffffffff81091ee1 ffff8803a5dba700 00000dba00000008
[  453.533011]  ffffed0074496f59 ffff8803a5dbaf54 ffff8803ae0f8488 fffffffffffffdef
[  453.533011] Call Trace:
[  453.533011]  [<ffffffff8196cffb>] dump_stack+0x67/0x9c
[  453.533011]  [<ffffffff81091ee1>] __warn+0x111/0x130
[  453.533011]  [<ffffffff81091f97>] warn_slowpath_fmt+0x97/0xb0
[  453.533011]  [<ffffffff81091f00>] ? __warn+0x130/0x130
[  453.533011]  [<ffffffff8191b789>] ? blk_finish_plug+0x29/0x60
[  453.533011]  [<ffffffff811205d4>] lock_release+0x434/0x670
[  453.533011]  [<ffffffff8198af94>] ? import_single_range+0xd4/0x110
[  453.533011]  [<ffffffff81322195>] ? rw_verify_area+0x65/0x140
[  453.533011]  [<ffffffff813aa696>] ? aio_write+0x1f6/0x280
[  453.533011]  [<ffffffff813aa6c9>] aio_write+0x229/0x280
[  453.533011]  [<ffffffff813aa4a0>] ? aio_complete+0x640/0x640
[  453.533011]  [<ffffffff8111df20>] ? debug_check_no_locks_freed+0x1a0/0x1a0
[  453.533011]  [<ffffffff8114793a>] ? debug_lockdep_rcu_enabled.part.2+0x1a/0x30
[  453.533011]  [<ffffffff81147985>] ? debug_lockdep_rcu_enabled+0x35/0x40
[  453.533011]  [<ffffffff812a92be>] ? __might_fault+0x7e/0xf0
[  453.533011]  [<ffffffff813ac9bc>] do_io_submit+0x94c/0xb10
[  453.533011]  [<ffffffff813ac2ae>] ? do_io_submit+0x23e/0xb10
[  453.533011]  [<ffffffff813ac070>] ? SyS_io_destroy+0x270/0x270
[  453.533011]  [<ffffffff8111d7b3>] ? mark_held_locks+0x23/0xc0
[  453.533011]  [<ffffffff8100201a>] ? trace_hardirqs_on_thunk+0x1a/0x1c
[  453.533011]  [<ffffffff813acb90>] SyS_io_submit+0x10/0x20
[  453.533011]  [<ffffffff824f96aa>] entry_SYSCALL_64_fastpath+0x18/0xad
[  453.533011]  [<ffffffff81119190>] ? trace_hardirqs_off_caller+0xc0/0x110
[  453.533011] ---[ end trace b2fbe664d1cc0082 ]---

Cc: Dmitry Monakhov <dmonakhov@openvz.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 fs/aio.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/fs/aio.c b/fs/aio.c
index 428484f2f841..0fcb49ad67d4 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1085,7 +1085,8 @@ static void aio_complete(struct kiocb *kiocb, long res, long res2)
 		 * Tell lockdep we inherited freeze protection from submission
 		 * thread.
 		 */
-		__sb_writers_acquired(file_inode(file)->i_sb, SB_FREEZE_WRITE);
+		if (S_ISREG(file_inode(file)->i_mode))
+			__sb_writers_acquired(file_inode(file)->i_sb, SB_FREEZE_WRITE);
 		file_end_write(file);
 	}
 
@@ -1492,7 +1493,8 @@ static ssize_t aio_write(struct kiocb *req, struct iocb *iocb, bool vectored,
 		 * by telling it the lock got released so that it doesn't
 		 * complain about held lock when we return to userspace.
 		 */
-		__sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE);
+		if (S_ISREG(file_inode(file)->i_mode))
+			__sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE);
 	}
 	kfree(iovec);
 	return ret;
-- 
2.11.0

[PATCH for v4.9 LTS 73/86] perf/x86: Reject non sampling events with precise_ip

[Levin, Alexander (Sasha Levin)]

From: Jiri Olsa <jolsa@redhat.com>

[ Upstream commit 18e7a45af91acdde99d3aa1372cc40e1f8142f7b ]

As Peter suggested [1] rejecting non sampling PEBS events,
because they dont make any sense and could cause bugs
in the NMI handler [2].

  [1] http://lkml.kernel.org/r/20170103094059.GC3093@worktop
  [2] http://lkml.kernel.org/r/1482931866-6018-3-git-send-email-jolsa@kernel.org

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vince@deater.net>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Link: http://lkml.kernel.org/r/20170103142454.GA26251@krava
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 arch/x86/events/core.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 38623e219816..9604b2574d6c 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -505,6 +505,10 @@ int x86_pmu_hw_config(struct perf_event *event)
 
 		if (event->attr.precise_ip > precise)
 			return -EOPNOTSUPP;
+
+		/* There's no sense in having PEBS for non sampling events: */
+		if (!is_sampling_event(event))
+			return -EINVAL;
 	}
 	/*
 	 * check that PEBS LBR correction does not conflict with
-- 
2.11.0

[PATCH for v4.9 LTS 75/86] coredump: Ensure proper size of sparse core files

[Levin, Alexander (Sasha Levin)]

From: Dave Kleikamp <dave.kleikamp@oracle.com>

[ Upstream commit 4d22c75d4c7b5c5f4bd31054f09103ee490878fd ]

If the last section of a core file ends with an unmapped or zero page,
the size of the file does not correspond with the last dump_skip() call.
gdb complains that the file is truncated and can be confusing to users.

After all of the vma sections are written, make sure that the file size
is no smaller than the current file position.

This problem can be demonstrated with gdb's bigcore testcase on the
sparc architecture.

Signed-off-by: Dave Kleikamp <dave.kleikamp@oracle.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 fs/binfmt_elf.c          |  1 +
 fs/coredump.c            | 18 ++++++++++++++++++
 include/linux/coredump.h |  1 +
 3 files changed, 20 insertions(+)

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 2472af2798c7..cfd724f98332 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -2296,6 +2296,7 @@ static int elf_core_dump(struct coredump_params *cprm)
 				goto end_coredump;
 		}
 	}
+	dump_truncate(cprm);
 
 	if (!elf_core_write_extra_data(cprm))
 		goto end_coredump;
diff --git a/fs/coredump.c b/fs/coredump.c
index eb9c92c9b20f..4407e27beca9 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -833,3 +833,21 @@ int dump_align(struct coredump_params *cprm, int align)
 	return mod ? dump_skip(cprm, align - mod) : 1;
 }
 EXPORT_SYMBOL(dump_align);
+
+/*
+ * Ensures that file size is big enough to contain the current file
+ * postion. This prevents gdb from complaining about a truncated file
+ * if the last "write" to the file was dump_skip.
+ */
+void dump_truncate(struct coredump_params *cprm)
+{
+	struct file *file = cprm->file;
+	loff_t offset;
+
+	if (file->f_op->llseek && file->f_op->llseek != no_llseek) {
+		offset = file->f_op->llseek(file, 0, SEEK_CUR);
+		if (i_size_read(file->f_mapping->host) < offset)
+			do_truncate(file->f_path.dentry, offset, 0, file);
+	}
+}
+EXPORT_SYMBOL(dump_truncate);
diff --git a/include/linux/coredump.h b/include/linux/coredump.h
index d016a121a8c4..28ffa94aed6b 100644
--- a/include/linux/coredump.h
+++ b/include/linux/coredump.h
@@ -14,6 +14,7 @@ struct coredump_params;
 extern int dump_skip(struct coredump_params *cprm, size_t nr);
 extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr);
 extern int dump_align(struct coredump_params *cprm, int align);
+extern void dump_truncate(struct coredump_params *cprm);
 #ifdef CONFIG_COREDUMP
 extern void do_coredump(const siginfo_t *siginfo);
 #else
-- 
2.11.0

[PATCH for v4.9 LTS 77/86] s390/ctl_reg: make __ctl_load a full memory barrier

[Levin, Alexander (Sasha Levin)]

From: Heiko Carstens <heiko.carstens@de.ibm.com>

[ Upstream commit e991c24d68b8c0ba297eeb7af80b1e398e98c33f ]

We have quite a lot of code that depends on the order of the
__ctl_load inline assemby and subsequent memory accesses, like
e.g. disabling lowcore protection and the writing to lowcore.

Since the __ctl_load macro does not have memory barrier semantics, nor
any other dependencies the compiler is, theoretically, free to shuffle
code around. Or in other words: storing to lowcore could happen before
lowcore protection is disabled.

In order to avoid this class of potential bugs simply add a full
memory barrier to the __ctl_load macro.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 arch/s390/include/asm/ctl_reg.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h
index d7697ab802f6..8e136b88cdf4 100644
--- a/arch/s390/include/asm/ctl_reg.h
+++ b/arch/s390/include/asm/ctl_reg.h
@@ -15,7 +15,9 @@
 	BUILD_BUG_ON(sizeof(addrtype) != (high - low + 1) * sizeof(long));\
 	asm volatile(							\
 		"	lctlg	%1,%2,%0\n"				\
-		: : "Q" (*(addrtype *)(&array)), "i" (low), "i" (high));\
+		:							\
+		: "Q" (*(addrtype *)(&array)), "i" (low), "i" (high)	\
+		: "memory");						\
 }
 
 #define __ctl_store(array, low, high) {					\
-- 
2.11.0

[PATCH for v4.9 LTS 76/86] swiotlb: ensure that page-sized mappings are page-aligned

[Levin, Alexander (Sasha Levin)]

From: Nikita Yushchenko <nikita.yoush@cogentembedded.com>

[ Upstream commit 602d9858f07c72eab64f5f00e2fae55f9902cfbe ]

Some drivers do depend on page mappings to be page aligned.

Swiotlb already enforces such alignment for mappings greater than page,
extend that to page-sized mappings as well.

Without this fix, nvme hits BUG() in nvme_setup_prps(), because that routine
assumes page-aligned mappings.

Signed-off-by: Nikita Yushchenko <nikita.yoush@cogentembedded.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Konrad Rzeszutek Wilk <konrad@kernel.org>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 lib/swiotlb.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index ad1d2962d129..b7812df04437 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -456,11 +456,11 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
 		    : 1UL << (BITS_PER_LONG - IO_TLB_SHIFT);
 
 	/*
-	 * For mappings greater than a page, we limit the stride (and
-	 * hence alignment) to a page size.
+	 * For mappings greater than or equal to a page, we limit the stride
+	 * (and hence alignment) to a page size.
 	 */
 	nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
-	if (size > PAGE_SIZE)
+	if (size >= PAGE_SIZE)
 		stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT));
 	else
 		stride = 1;
-- 
2.11.0

[PATCH for v4.9 LTS 80/86] be2net: don't delete MAC on close on unprivileged BE3 VFs

[Levin, Alexander (Sasha Levin)]

From: Ivan Vecera <cera@cera.cz>

[ Upstream commit 6d928ae590c8d58cfd5cca997d54394de139cbb7 ]

BE3 VFs without FILTMGMT privilege are not allowed to modify its MAC,
VLAN table and UC/MC lists. So don't try to delete MAC on such VFs.

Cc: Sathya Perla <sathya.perla@broadcom.com>
Cc: Ajit Khaparde <ajit.khaparde@broadcom.com>
Cc: Sriharsha Basavapatna <sriharsha.basavapatna@broadcom.com>
Cc: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Ivan Vecera <cera@cera.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/net/ethernet/emulex/benet/be_main.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 9711ca4510fa..a25d35a1b03d 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -3630,7 +3630,11 @@ static void be_rx_qs_destroy(struct be_adapter *adapter)
 
 static void be_disable_if_filters(struct be_adapter *adapter)
 {
-	be_dev_mac_del(adapter, adapter->pmac_id[0]);
+	/* Don't delete MAC on BE3 VFs without FILTMGMT privilege  */
+	if (!BEx_chip(adapter) || !be_virtfn(adapter) ||
+	    check_privilege(adapter, BE_PRIV_FILTMGMT))
+		be_dev_mac_del(adapter, adapter->pmac_id[0]);
+
 	be_clear_uc_list(adapter);
 	be_clear_mc_list(adapter);
 
-- 
2.11.0

[PATCH for v4.9 LTS 79/86] be2net: fix status check in be_cmd_pmac_add()

[Levin, Alexander (Sasha Levin)]

From: Ivan Vecera <cera@cera.cz>

[ Upstream commit fe68d8bfe59c561664aa87d827aa4b320eb08895 ]

Return value from be_mcc_notify_wait() contains a base completion status
together with an additional status. The base_status() macro need to be
used to access base status.

Fixes: e3a7ae2 be2net: Changing MAC Address of a VF was broken
Cc: Sathya Perla <sathya.perla@broadcom.com>
Cc: Ajit Khaparde <ajit.khaparde@broadcom.com>
Cc: Sriharsha Basavapatna <sriharsha.basavapatna@broadcom.com>
Cc: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Ivan Vecera <cera@cera.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/net/ethernet/emulex/benet/be_cmds.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 0e74529a4209..30e855004c57 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -1118,7 +1118,7 @@ int be_cmd_pmac_add(struct be_adapter *adapter, u8 *mac_addr,
 err:
 	mutex_unlock(&adapter->mcc_lock);
 
-	 if (status == MCC_STATUS_UNAUTHORIZED_REQUEST)
+	 if (base_status(status) == MCC_STATUS_UNAUTHORIZED_REQUEST)
 		status = -EPERM;
 
 	return status;
-- 
2.11.0

[PATCH for v4.9 LTS 78/86] usb: dwc2: gadget: Fix GUSBCFG.USBTRDTIM value

[Levin, Alexander (Sasha Levin)]

From: Amelie Delaunay <amelie.delaunay@st.com>

[ Upstream commit ca02954ada711b08e5b0d84590a631fd63ed39f9 ]

USBTrdTim must be programmed to 0x5 when phy has a UTMI+ 16-bit wide
interface or 0x9 when it has a 8-bit wide interface.
GUSBCFG reset value (Value After Reset: 0x1400) sets USBTrdTim to 0x5.
In case of 8-bit UTMI+, without clearing GUSBCFG.USBTRDTIM mask, USBTrdTim
results in 0xD (0x5 | 0x9).
That's why we need to clear GUSBCFG.USBTRDTIM mask before setting USBTrdTim
value, to ensure USBTrdTim is correctly set in case of 8-bit UTMI+.

Signed-off-by: Amelie Delaunay <amelie.delaunay@st.com>
Signed-off-by: Felipe Balbi <felipe.balbi@linux.intel.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/usb/dwc2/gadget.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c
index 24fbebc9b409..cfdd5c3da236 100644
--- a/drivers/usb/dwc2/gadget.c
+++ b/drivers/usb/dwc2/gadget.c
@@ -2532,7 +2532,7 @@ void dwc2_hsotg_core_init_disconnected(struct dwc2_hsotg *hsotg,
 	/* keep other bits untouched (so e.g. forced modes are not lost) */
 	usbcfg = dwc2_readl(hsotg->regs + GUSBCFG);
 	usbcfg &= ~(GUSBCFG_TOUTCAL_MASK | GUSBCFG_PHYIF16 | GUSBCFG_SRPCAP |
-		GUSBCFG_HNPCAP);
+		GUSBCFG_HNPCAP | GUSBCFG_USBTRDTIM_MASK);
 
 	/* set the PLL on, remove the HNP/SRP and set the PHY */
 	val = (hsotg->phyif == GUSBCFG_PHYIF8) ? 9 : 5;
@@ -3403,7 +3403,7 @@ static void dwc2_hsotg_init(struct dwc2_hsotg *hsotg)
 	/* keep other bits untouched (so e.g. forced modes are not lost) */
 	usbcfg = dwc2_readl(hsotg->regs + GUSBCFG);
 	usbcfg &= ~(GUSBCFG_TOUTCAL_MASK | GUSBCFG_PHYIF16 | GUSBCFG_SRPCAP |
-		GUSBCFG_HNPCAP);
+		GUSBCFG_HNPCAP | GUSBCFG_USBTRDTIM_MASK);
 
 	/* set the PLL on, remove the HNP/SRP and set the PHY */
 	trdtim = (hsotg->phyif == GUSBCFG_PHYIF8) ? 9 : 5;
-- 
2.11.0

[PATCH for v4.9 LTS 83/86] net: phy: dp83867: allow RGMII_TXID/RGMII_RXID interface types

[Levin, Alexander (Sasha Levin)]

From: "Karicheri, Muralidharan" <m-karicheri2@ti.com>

[ Upstream commit 34c55cf2fc75f8bf6ba87df321038c064cf2d426 ]

Currently dp83867 driver returns error if phy interface type
PHY_INTERFACE_MODE_RGMII_RXID is used to set the rx only internal
delay. Similarly issue happens for PHY_INTERFACE_MODE_RGMII_TXID.
Fix this by checking also the interface type if a particular delay
value is missing in the phy dt bindings. Also update the DT document
accordingly.

Signed-off-by: Murali Karicheri <m-karicheri2@ti.com>
Signed-off-by: Sekhar Nori <nsekhar@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 Documentation/devicetree/bindings/net/ti,dp83867.txt | 6 ++++--
 drivers/net/phy/dp83867.c                            | 8 ++++++--
 2 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/ti,dp83867.txt b/Documentation/devicetree/bindings/net/ti,dp83867.txt
index 5d21141a68b5..75bcaa355880 100644
--- a/Documentation/devicetree/bindings/net/ti,dp83867.txt
+++ b/Documentation/devicetree/bindings/net/ti,dp83867.txt
@@ -3,9 +3,11 @@
 Required properties:
 	- reg - The ID number for the phy, usually a small integer
 	- ti,rx-internal-delay - RGMII Receive Clock Delay - see dt-bindings/net/ti-dp83867.h
-		for applicable values
+		for applicable values. Required only if interface type is
+		PHY_INTERFACE_MODE_RGMII_ID or PHY_INTERFACE_MODE_RGMII_RXID
 	- ti,tx-internal-delay - RGMII Transmit Clock Delay - see dt-bindings/net/ti-dp83867.h
-		for applicable values
+		for applicable values. Required only if interface type is
+		PHY_INTERFACE_MODE_RGMII_ID or PHY_INTERFACE_MODE_RGMII_TXID
 	- ti,fifo-depth - Transmitt FIFO depth- see dt-bindings/net/ti-dp83867.h
 		for applicable values
 
diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c
index 91177a4a32ad..4cad95552cf1 100644
--- a/drivers/net/phy/dp83867.c
+++ b/drivers/net/phy/dp83867.c
@@ -113,12 +113,16 @@ static int dp83867_of_init(struct phy_device *phydev)
 
 	ret = of_property_read_u32(of_node, "ti,rx-internal-delay",
 				   &dp83867->rx_id_delay);
-	if (ret)
+	if (ret &&
+	    (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID ||
+	     phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID))
 		return ret;
 
 	ret = of_property_read_u32(of_node, "ti,tx-internal-delay",
 				   &dp83867->tx_id_delay);
-	if (ret)
+	if (ret &&
+	    (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID ||
+	     phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID))
 		return ret;
 
 	return of_property_read_u32(of_node, "ti,fifo-depth",
-- 
2.11.0

[PATCH for v4.9 LTS 81/86] be2net: fix MAC addr setting on privileged BE3 VFs

[Levin, Alexander (Sasha Levin)]

From: Ivan Vecera <cera@cera.cz>

[ Upstream commit 34393529163af7163ef8459808e3cf2af7db7f16 ]

During interface opening MAC address stored in netdev->dev_addr is
programmed in the HW with exception of BE3 VFs where the initial
MAC is programmed by parent PF. This is OK when MAC address is not
changed when an interfaces is down. In this case the requested MAC is
stored to netdev->dev_addr and later is stored into HW during opening.
But this is not done for all BE3 VFs so the NIC HW does not know
anything about this change and all traffic is filtered.

This is the case of bonding if fail_over_mac == 0 where the MACs of
the slaves are changed while they are down.

The be2net behavior is too restrictive because if a BE3 VF has
the FILTMGMT privilege then it is able to modify its MAC without
any restriction.

To solve the described problem the driver should take care about these
privileged BE3 VFs so the MAC is programmed during opening. And by
contrast unpriviled BE3 VFs should not be allowed to change its MAC
in any case.

Cc: Sathya Perla <sathya.perla@broadcom.com>
Cc: Ajit Khaparde <ajit.khaparde@broadcom.com>
Cc: Sriharsha Basavapatna <sriharsha.basavapatna@broadcom.com>
Cc: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Ivan Vecera <cera@cera.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/net/ethernet/emulex/benet/be_main.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index a25d35a1b03d..b3c9cbef766e 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -319,6 +319,13 @@ static int be_mac_addr_set(struct net_device *netdev, void *p)
 	if (ether_addr_equal(addr->sa_data, adapter->dev_mac))
 		return 0;
 
+	/* BE3 VFs without FILTMGMT privilege are not allowed to set its MAC
+	 * address
+	 */
+	if (BEx_chip(adapter) && be_virtfn(adapter) &&
+	    !check_privilege(adapter, BE_PRIV_FILTMGMT))
+		return -EPERM;
+
 	/* if device is not running, copy MAC to netdev->dev_addr */
 	if (!netif_running(netdev))
 		goto done;
@@ -3787,8 +3794,9 @@ static int be_enable_if_filters(struct be_adapter *adapter)
 	if (status)
 		return status;
 
-	/* For BE3 VFs, the PF programs the initial MAC address */
-	if (!(BEx_chip(adapter) && be_virtfn(adapter))) {
+	/* Don't add MAC on BE3 VFs without FILTMGMT privilege */
+	if (!BEx_chip(adapter) || !be_virtfn(adapter) ||
+	    check_privilege(adapter, BE_PRIV_FILTMGMT)) {
 		status = be_dev_mac_add(adapter, adapter->netdev->dev_addr);
 		if (status)
 			return status;
-- 
2.11.0

[PATCH for v4.9 LTS 82/86] perf probe: Fix to show correct locations for events on modules

[Levin, Alexander (Sasha Levin)]

From: Masami Hiramatsu <mhiramat@kernel.org>

[ Upstream commit d2d4edbebe07ddb77980656abe7b9bc7a9e0cdf7 ]

Fix to show correct locations for events on modules by relocating given
address instead of retrying after failure.

This happens when the module text size is big enough, bigger than
sh_addr, because the original code retries with given address + sh_addr
if it failed to find CU DIE at the given address.

Any address smaller than sh_addr always fails and it retries with the
correct address, but addresses bigger than sh_addr will get a CU DIE
which is on the given address (not adjusted by sh_addr).

In my environment(x86-64), the sh_addr of ".text" section is 0x10030.
Since i915 is a huge kernel module, we can see this issue as below.

  $ grep "[Tt] .*\[i915\]" /proc/kallsyms | sort | head -n1
  ffffffffc0270000 t i915_switcheroo_can_switch	[i915]

ffffffffc0270000 + 0x10030 = ffffffffc0280030, so we'll check
symbols cross this boundary.

  $ grep "[Tt] .*\[i915\]" /proc/kallsyms | grep -B1 ^ffffffffc028\
  | head -n 2
  ffffffffc027ff80 t haswell_init_clock_gating	[i915]
  ffffffffc0280110 t valleyview_init_clock_gating	[i915]

So setup probes on both function and see what happen.

  $ sudo ./perf probe -m i915 -a haswell_init_clock_gating \
        -a valleyview_init_clock_gating
  Added new events:
    probe:haswell_init_clock_gating (on haswell_init_clock_gating in i915)
    probe:valleyview_init_clock_gating (on valleyview_init_clock_gating in i915)

  You can now use it in all perf tools, such as:

  	perf record -e probe:valleyview_init_clock_gating -aR sleep 1

  $ sudo ./perf probe -l
    probe:haswell_init_clock_gating (on haswell_init_clock_gating@gpu/drm/i915/intel_pm.c in i915)
    probe:valleyview_init_clock_gating (on i915_vga_set_decode:4@gpu/drm/i915/i915_drv.c in i915)

As you can see, haswell_init_clock_gating is correctly shown,
but valleyview_init_clock_gating is not.

With this patch, both events are shown correctly.

  $ sudo ./perf probe -l
    probe:haswell_init_clock_gating (on haswell_init_clock_gating@gpu/drm/i915/intel_pm.c in i915)
    probe:valleyview_init_clock_gating (on valleyview_init_clock_gating@gpu/drm/i915/intel_pm.c in i915)

Committer notes:

In my case:

  # perf probe -m i915 -a haswell_init_clock_gating -a valleyview_init_clock_gating
  Added new events:
    probe:haswell_init_clock_gating (on haswell_init_clock_gating in i915)
    probe:valleyview_init_clock_gating (on valleyview_init_clock_gating in i915)

  You can now use it in all perf tools, such as:

	  perf record -e probe:valleyview_init_clock_gating -aR sleep 1

  # perf probe -l
    probe:haswell_init_clock_gating (on i915_getparam+432@gpu/drm/i915/i915_drv.c in i915)
    probe:valleyview_init_clock_gating (on __i915_printk+240@gpu/drm/i915/i915_drv.c in i915)
  #

  # readelf -SW /lib/modules/4.9.0+/build/vmlinux | egrep -w '.text|Name'
   [Nr] Name   Type      Address          Off    Size   ES Flg Lk Inf Al
   [ 1] .text  PROGBITS  ffffffff81000000 200000 822fd3 00  AX  0   0 4096
  #

  So both are b0rked, now with the fix:

  # perf probe -m i915 -a haswell_init_clock_gating -a valleyview_init_clock_gating
  Added new events:
    probe:haswell_init_clock_gating (on haswell_init_clock_gating in i915)
    probe:valleyview_init_clock_gating (on valleyview_init_clock_gating in i915)

  You can now use it in all perf tools, such as:

	perf record -e probe:valleyview_init_clock_gating -aR sleep 1

  # perf probe -l
    probe:haswell_init_clock_gating (on haswell_init_clock_gating@gpu/drm/i915/intel_pm.c in i915)
    probe:valleyview_init_clock_gating (on valleyview_init_clock_gating@gpu/drm/i915/intel_pm.c in i915)
  #

Both looks correct.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/148411436777.9978.1440275861947194930.stgit@devbox
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 tools/perf/util/probe-finder.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index df4debe564da..0278fe1a4cc6 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -1543,16 +1543,12 @@ int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr,
 	Dwarf_Addr _addr = 0, baseaddr = 0;
 	const char *fname = NULL, *func = NULL, *basefunc = NULL, *tmp;
 	int baseline = 0, lineno = 0, ret = 0;
-	bool reloc = false;
 
-retry:
+	/* We always need to relocate the address for aranges */
+	if (debuginfo__get_text_offset(dbg, &baseaddr) == 0)
+		addr += baseaddr;
 	/* Find cu die */
 	if (!dwarf_addrdie(dbg->dbg, (Dwarf_Addr)addr, &cudie)) {
-		if (!reloc && debuginfo__get_text_offset(dbg, &baseaddr) == 0) {
-			addr += baseaddr;
-			reloc = true;
-			goto retry;
-		}
 		pr_warning("Failed to find debug information for address %lx\n",
 			   addr);
 		ret = -EINVAL;
-- 
2.11.0

[PATCH for v4.9 LTS 85/86] perf probe: Fix to probe on gcc generated functions in modules

[Levin, Alexander (Sasha Levin)]

From: Masami Hiramatsu <mhiramat@kernel.org>

[ Upstream commit 613f050d68a8ed3c0b18b9568698908ef7bbc1f7 ]

Fix to probe on gcc generated functions on modules. Since
probing on a module is based on its symbol name, it should
be adjusted on actual symbols.

E.g. without this fix, perf probe shows probe definition
on non-exist symbol as below.

  $ perf probe -m build-x86_64/net/netfilter/nf_nat.ko -F in_range*
  in_range.isra.12
  $ perf probe -m build-x86_64/net/netfilter/nf_nat.ko -D in_range
  p:probe/in_range nf_nat:in_range+0

With this fix, perf probe correctly shows a probe on
gcc-generated symbol.

  $ perf probe -m build-x86_64/net/netfilter/nf_nat.ko -D in_range
  p:probe/in_range nf_nat:in_range.isra.12+0

This also fixes same problem on online module as below.

  $ perf probe -m i915 -D assert_plane
  p:probe/assert_plane i915:assert_plane.constprop.134+0

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/148411450673.9978.14905987549651656075.stgit@devbox
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 tools/perf/util/probe-event.c  | 45 +++++++++++++++++++++++++++---------------
 tools/perf/util/probe-finder.c |  7 +++++--
 tools/perf/util/probe-finder.h |  3 +++
 3 files changed, 37 insertions(+), 18 deletions(-)

diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index d281ae2b54e8..1d9c02bc00f1 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -645,18 +645,31 @@ static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs,
 	return ret;
 }
 
-static int add_module_to_probe_trace_events(struct probe_trace_event *tevs,
-					    int ntevs, const char *module)
+static int
+post_process_module_probe_trace_events(struct probe_trace_event *tevs,
+				       int ntevs, const char *module,
+				       struct debuginfo *dinfo)
 {
+	Dwarf_Addr text_offs = 0;
 	int i, ret = 0;
 	char *mod_name = NULL;
+	struct map *map;
 
 	if (!module)
 		return 0;
 
-	mod_name = find_module_name(module);
+	map = get_target_map(module, false);
+	if (!map || debuginfo__get_text_offset(dinfo, &text_offs, true) < 0) {
+		pr_warning("Failed to get ELF symbols for %s\n", module);
+		return -EINVAL;
+	}
 
+	mod_name = find_module_name(module);
 	for (i = 0; i < ntevs; i++) {
+		ret = post_process_probe_trace_point(&tevs[i].point,
+						map, (unsigned long)text_offs);
+		if (ret < 0)
+			break;
 		tevs[i].point.module =
 			strdup(mod_name ? mod_name : module);
 		if (!tevs[i].point.module) {
@@ -666,6 +679,8 @@ static int add_module_to_probe_trace_events(struct probe_trace_event *tevs,
 	}
 
 	free(mod_name);
+	map__put(map);
+
 	return ret;
 }
 
@@ -722,7 +737,7 @@ arch__post_process_probe_trace_events(struct perf_probe_event *pev __maybe_unuse
 static int post_process_probe_trace_events(struct perf_probe_event *pev,
 					   struct probe_trace_event *tevs,
 					   int ntevs, const char *module,
-					   bool uprobe)
+					   bool uprobe, struct debuginfo *dinfo)
 {
 	int ret;
 
@@ -730,7 +745,8 @@ static int post_process_probe_trace_events(struct perf_probe_event *pev,
 		ret = add_exec_to_probe_trace_events(tevs, ntevs, module);
 	else if (module)
 		/* Currently ref_reloc_sym based probe is not for drivers */
-		ret = add_module_to_probe_trace_events(tevs, ntevs, module);
+		ret = post_process_module_probe_trace_events(tevs, ntevs,
+							     module, dinfo);
 	else
 		ret = post_process_kernel_probe_trace_events(tevs, ntevs);
 
@@ -774,30 +790,27 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 		}
 	}
 
-	debuginfo__delete(dinfo);
-
 	if (ntevs > 0) {	/* Succeeded to find trace events */
 		pr_debug("Found %d probe_trace_events.\n", ntevs);
 		ret = post_process_probe_trace_events(pev, *tevs, ntevs,
-						pev->target, pev->uprobes);
+					pev->target, pev->uprobes, dinfo);
 		if (ret < 0 || ret == ntevs) {
+			pr_debug("Post processing failed or all events are skipped. (%d)\n", ret);
 			clear_probe_trace_events(*tevs, ntevs);
 			zfree(tevs);
+			ntevs = 0;
 		}
-		if (ret != ntevs)
-			return ret < 0 ? ret : ntevs;
-		ntevs = 0;
-		/* Fall through */
 	}
 
+	debuginfo__delete(dinfo);
+
 	if (ntevs == 0)	{	/* No error but failed to find probe point. */
 		pr_warning("Probe point '%s' not found.\n",
 			   synthesize_perf_probe_point(&pev->point));
 		return -ENOENT;
-	}
-	/* Error path : ntevs < 0 */
-	pr_debug("An error occurred in debuginfo analysis (%d).\n", ntevs);
-	if (ntevs < 0) {
+	} else if (ntevs < 0) {
+		/* Error path : ntevs < 0 */
+		pr_debug("An error occurred in debuginfo analysis (%d).\n", ntevs);
 		if (ntevs == -EBADF)
 			pr_warning("Warning: No dwarf info found in the vmlinux - "
 				"please rebuild kernel with CONFIG_DEBUG_INFO=y.\n");
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 0278fe1a4cc6..0d9d6e0803b8 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -1501,7 +1501,8 @@ int debuginfo__find_available_vars_at(struct debuginfo *dbg,
 }
 
 /* For the kernel module, we need a special code to get a DIE */
-static int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs)
+int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs,
+				bool adjust_offset)
 {
 	int n, i;
 	Elf32_Word shndx;
@@ -1530,6 +1531,8 @@ static int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs)
 			if (!shdr)
 				return -ENOENT;
 			*offs = shdr->sh_addr;
+			if (adjust_offset)
+				*offs -= shdr->sh_offset;
 		}
 	}
 	return 0;
@@ -1545,7 +1548,7 @@ int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr,
 	int baseline = 0, lineno = 0, ret = 0;
 
 	/* We always need to relocate the address for aranges */
-	if (debuginfo__get_text_offset(dbg, &baseaddr) == 0)
+	if (debuginfo__get_text_offset(dbg, &baseaddr, false) == 0)
 		addr += baseaddr;
 	/* Find cu die */
 	if (!dwarf_addrdie(dbg->dbg, (Dwarf_Addr)addr, &cudie)) {
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index f1d8558f498e..2956c5198652 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -46,6 +46,9 @@ int debuginfo__find_trace_events(struct debuginfo *dbg,
 int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr,
 				struct perf_probe_point *ppt);
 
+int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs,
+			       bool adjust_offset);
+
 /* Find a line range */
 int debuginfo__find_line_range(struct debuginfo *dbg, struct line_range *lr);
 
-- 
2.11.0

[PATCH for v4.9 LTS 84/86] tipc: allocate user memory with GFP_KERNEL flag

[Levin, Alexander (Sasha Levin)]

From: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>

[ Upstream commit 57d5f64d83ab5b5a5118b1597386dd76eaf4340d ]

Until now, we allocate memory always with GFP_ATOMIC flag.
When the system is under memory pressure and a user tries to send,
the send fails due to low memory. However, the user application
can wait for free memory if we allocate it using GFP_KERNEL flag.

In this commit, we use allocate memory with GFP_KERNEL for all user
allocation.

Reported-by: Rune Torgersen <runet@innovsys.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 net/tipc/discover.c   |  4 ++--
 net/tipc/link.c       |  2 +-
 net/tipc/msg.c        | 16 ++++++++--------
 net/tipc/msg.h        |  2 +-
 net/tipc/name_distr.c |  2 +-
 5 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/net/tipc/discover.c b/net/tipc/discover.c
index 6b109a808d4c..02462d67d191 100644
--- a/net/tipc/discover.c
+++ b/net/tipc/discover.c
@@ -169,7 +169,7 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *skb,
 
 	/* Send response, if necessary */
 	if (respond && (mtyp == DSC_REQ_MSG)) {
-		rskb = tipc_buf_acquire(MAX_H_SIZE);
+		rskb = tipc_buf_acquire(MAX_H_SIZE, GFP_ATOMIC);
 		if (!rskb)
 			return;
 		tipc_disc_init_msg(net, rskb, DSC_RESP_MSG, bearer);
@@ -278,7 +278,7 @@ int tipc_disc_create(struct net *net, struct tipc_bearer *b,
 	req = kmalloc(sizeof(*req), GFP_ATOMIC);
 	if (!req)
 		return -ENOMEM;
-	req->buf = tipc_buf_acquire(MAX_H_SIZE);
+	req->buf = tipc_buf_acquire(MAX_H_SIZE, GFP_ATOMIC);
 	if (!req->buf) {
 		kfree(req);
 		return -ENOMEM;
diff --git a/net/tipc/link.c b/net/tipc/link.c
index bda89bf9f4ff..4e8647aef01c 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1395,7 +1395,7 @@ void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl,
 			msg_set_seqno(hdr, seqno++);
 		pktlen = msg_size(hdr);
 		msg_set_size(&tnlhdr, pktlen + INT_H_SIZE);
-		tnlskb = tipc_buf_acquire(pktlen + INT_H_SIZE);
+		tnlskb = tipc_buf_acquire(pktlen + INT_H_SIZE, GFP_ATOMIC);
 		if (!tnlskb) {
 			pr_warn("%sunable to send packet\n", link_co_err);
 			return;
diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index 17201aa8423d..a53fbe120f35 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -58,12 +58,12 @@ static unsigned int align(unsigned int i)
  * NOTE: Headroom is reserved to allow prepending of a data link header.
  *       There may also be unrequested tailroom present at the buffer's end.
  */
-struct sk_buff *tipc_buf_acquire(u32 size)
+struct sk_buff *tipc_buf_acquire(u32 size, gfp_t gfp)
 {
 	struct sk_buff *skb;
 	unsigned int buf_size = (BUF_HEADROOM + size + 3) & ~3u;
 
-	skb = alloc_skb_fclone(buf_size, GFP_ATOMIC);
+	skb = alloc_skb_fclone(buf_size, gfp);
 	if (skb) {
 		skb_reserve(skb, BUF_HEADROOM);
 		skb_put(skb, size);
@@ -95,7 +95,7 @@ struct sk_buff *tipc_msg_create(uint user, uint type,
 	struct tipc_msg *msg;
 	struct sk_buff *buf;
 
-	buf = tipc_buf_acquire(hdr_sz + data_sz);
+	buf = tipc_buf_acquire(hdr_sz + data_sz, GFP_ATOMIC);
 	if (unlikely(!buf))
 		return NULL;
 
@@ -261,7 +261,7 @@ int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m,
 
 	/* No fragmentation needed? */
 	if (likely(msz <= pktmax)) {
-		skb = tipc_buf_acquire(msz);
+		skb = tipc_buf_acquire(msz, GFP_KERNEL);
 		if (unlikely(!skb))
 			return -ENOMEM;
 		skb_orphan(skb);
@@ -282,7 +282,7 @@ int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m,
 	msg_set_importance(&pkthdr, msg_importance(mhdr));
 
 	/* Prepare first fragment */
-	skb = tipc_buf_acquire(pktmax);
+	skb = tipc_buf_acquire(pktmax, GFP_KERNEL);
 	if (!skb)
 		return -ENOMEM;
 	skb_orphan(skb);
@@ -313,7 +313,7 @@ int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m,
 			pktsz = drem + INT_H_SIZE;
 		else
 			pktsz = pktmax;
-		skb = tipc_buf_acquire(pktsz);
+		skb = tipc_buf_acquire(pktsz, GFP_KERNEL);
 		if (!skb) {
 			rc = -ENOMEM;
 			goto error;
@@ -448,7 +448,7 @@ bool tipc_msg_make_bundle(struct sk_buff **skb,  struct tipc_msg *msg,
 	if (msz > (max / 2))
 		return false;
 
-	_skb = tipc_buf_acquire(max);
+	_skb = tipc_buf_acquire(max, GFP_ATOMIC);
 	if (!_skb)
 		return false;
 
@@ -496,7 +496,7 @@ bool tipc_msg_reverse(u32 own_node,  struct sk_buff **skb, int err)
 
 	/* Never return SHORT header; expand by replacing buffer if necessary */
 	if (msg_short(hdr)) {
-		*skb = tipc_buf_acquire(BASIC_H_SIZE + dlen);
+		*skb = tipc_buf_acquire(BASIC_H_SIZE + dlen, GFP_ATOMIC);
 		if (!*skb)
 			goto exit;
 		memcpy((*skb)->data + BASIC_H_SIZE, msg_data(hdr), dlen);
diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index 50a739860d37..6c0455caf302 100644
--- a/net/tipc/msg.h
+++ b/net/tipc/msg.h
@@ -820,7 +820,7 @@ static inline bool msg_is_reset(struct tipc_msg *hdr)
 	return (msg_user(hdr) == LINK_PROTOCOL) && (msg_type(hdr) == RESET_MSG);
 }
 
-struct sk_buff *tipc_buf_acquire(u32 size);
+struct sk_buff *tipc_buf_acquire(u32 size, gfp_t gfp);
 bool tipc_msg_validate(struct sk_buff *skb);
 bool tipc_msg_reverse(u32 own_addr, struct sk_buff **skb, int err);
 void tipc_msg_init(u32 own_addr, struct tipc_msg *m, u32 user, u32 type,
diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c
index c1cfd92de17a..23f8899e0f8c 100644
--- a/net/tipc/name_distr.c
+++ b/net/tipc/name_distr.c
@@ -69,7 +69,7 @@ static struct sk_buff *named_prepare_buf(struct net *net, u32 type, u32 size,
 					 u32 dest)
 {
 	struct tipc_net *tn = net_generic(net, tipc_net_id);
-	struct sk_buff *buf = tipc_buf_acquire(INT_H_SIZE + size);
+	struct sk_buff *buf = tipc_buf_acquire(INT_H_SIZE + size, GFP_ATOMIC);
 	struct tipc_msg *msg;
 
 	if (buf != NULL) {
-- 
2.11.0

[PATCH for v4.9 LTS 86/86] net/mlx4_core: Eliminate warning messages for SRQ_LIMIT under SRIOV

[Levin, Alexander (Sasha Levin)]

From: Jack Morgenstein <jackm@dev.mellanox.co.il>

[ Upstream commit 9577b174cd0323d287c994ef0891db71666d0765 ]

When running SRIOV, warnings for SRQ LIMIT events flood the Hypervisor's
message log when (correct, normally operating) apps use SRQ LIMIT events
as a trigger to post WQEs to SRQs.

Add more information to the existing debug printout for SRQ_LIMIT, and
output the warning messages only for the SRQ CATAS ERROR event.

Fixes: acba2420f9d2 ("mlx4_core: Add wrapper functions and comm channel and slave event support to EQs")
Fixes: e0debf9cb50d ("mlx4_core: Reduce warning message for SRQ_LIMIT event to debug level")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
---
 drivers/net/ethernet/mellanox/mlx4/eq.c | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index cd3638e6fe25..0509996957d9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -554,8 +554,9 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 			break;
 
 		case MLX4_EVENT_TYPE_SRQ_LIMIT:
-			mlx4_dbg(dev, "%s: MLX4_EVENT_TYPE_SRQ_LIMIT\n",
-				 __func__);
+			mlx4_dbg(dev, "%s: MLX4_EVENT_TYPE_SRQ_LIMIT. srq_no=0x%x, eq 0x%x\n",
+				 __func__, be32_to_cpu(eqe->event.srq.srqn),
+				 eq->eqn);
 		case MLX4_EVENT_TYPE_SRQ_CATAS_ERROR:
 			if (mlx4_is_master(dev)) {
 				/* forward only to slave owning the SRQ */
@@ -570,15 +571,19 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 						  eq->eqn, eq->cons_index, ret);
 					break;
 				}
-				mlx4_warn(dev, "%s: slave:%d, srq_no:0x%x, event: %02x(%02x)\n",
-					  __func__, slave,
-					  be32_to_cpu(eqe->event.srq.srqn),
-					  eqe->type, eqe->subtype);
+				if (eqe->type ==
+				    MLX4_EVENT_TYPE_SRQ_CATAS_ERROR)
+					mlx4_warn(dev, "%s: slave:%d, srq_no:0x%x, event: %02x(%02x)\n",
+						  __func__, slave,
+						  be32_to_cpu(eqe->event.srq.srqn),
+						  eqe->type, eqe->subtype);
 
 				if (!ret && slave != dev->caps.function) {
-					mlx4_warn(dev, "%s: sending event %02x(%02x) to slave:%d\n",
-						  __func__, eqe->type,
-						  eqe->subtype, slave);
+					if (eqe->type ==
+					    MLX4_EVENT_TYPE_SRQ_CATAS_ERROR)
+						mlx4_warn(dev, "%s: sending event %02x(%02x) to slave:%d\n",
+							  __func__, eqe->type,
+							  eqe->subtype, slave);
 					mlx4_slave_event(dev, slave, eqe);
 					break;
 				}
-- 
2.11.0