Merge branch 'perf/urgent' into perf/core, to pick up fixes

Signed-off-by: NIngo Molnar <mingo@kernel.org>

.mailmap

@@ -48,6 +48,9 @@ Felix Kuhling <fxkuehl@gmx.de>
 Felix Moeller <felix@derklecks.de>
 Filipe Lautert <filipe@icewall.org>
 Franck Bui-Huu <vagabon.xyz@gmail.com>
+Frank Rowand <frowand.list@gmail.com> <frowand@mvista.com>
+Frank Rowand <frowand.list@gmail.com> <frank.rowand@am.sony.com>
+Frank Rowand <frowand.list@gmail.com> <frank.rowand@sonymobile.com>
 Frank Zago <fzago@systemfabricworks.com>
 Greg Kroah-Hartman <greg@echidna.(none)>
 Greg Kroah-Hartman <gregkh@suse.de>
@@ -79,6 +82,7 @@ Kay Sievers <kay.sievers@vrfy.org>
 Kenneth W Chen <kenneth.w.chen@intel.com>
 Konstantin Khlebnikov <koct9i@gmail.com> <k.khlebnikov@samsung.com>
 Koushik <raghavendra.koushik@neterion.com>
+Krzysztof Kozlowski <krzk@kernel.org> <k.kozlowski.k@gmail.com>
 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
 Leonid I Ananiev <leonid.i.ananiev@intel.com>
 Linas Vepstas <linas@austin.ibm.com>

Documentation/devicetree/bindings/arc/archs-pct.txt

@@ -2,7 +2,7 @@
 
 The ARC HS can be configured with a pipeline performance monitor for counting
 CPU and cache events like cache misses and hits. Like conventional PCT there
-are 100+ hardware conditions dynamically mapped to upto 32 counters.
+are 100+ hardware conditions dynamically mapped to up to 32 counters.
 It also supports overflow interrupts.
 
 Required properties:

Documentation/devicetree/bindings/arc/pct.txt

@@ -2,7 +2,7 @@
 
 The ARC700 can be configured with a pipeline performance monitor for counting
 CPU and cache events like cache misses and hits. Like conventional PCT there
-are 100+ hardware conditions dynamically mapped to upto 32 counters
+are 100+ hardware conditions dynamically mapped to up to 32 counters
 
 Note that:
  * The ARC 700 PCT does not support interrupts; although HW events may be

Documentation/devicetree/bindings/arm/cpus.txt

@@ -192,7 +192,6 @@ nodes to be present and contain the properties described below.
 			  can be one of:
 			    "allwinner,sun6i-a31"
 			    "allwinner,sun8i-a23"
-			    "arm,psci"
 			    "arm,realview-smp"
 			    "brcm,bcm-nsp-smp"
 			    "brcm,brahma-b15"

Documentation/devicetree/bindings/i2c/i2c-rk3x.txt

@@ -6,8 +6,8 @@ RK3xxx SoCs.
 Required properties :
 
  - reg : Offset and length of the register set for the device
- - compatible : should be "rockchip,rk3066-i2c", "rockchip,rk3188-i2c" or
-		"rockchip,rk3288-i2c".
+ - compatible : should be "rockchip,rk3066-i2c", "rockchip,rk3188-i2c",
+		"rockchip,rk3228-i2c" or "rockchip,rk3288-i2c".
  - interrupts : interrupt number
  - clocks : parent clock
 

Documentation/devicetree/bindings/net/mediatek-net.txt

@@ -9,7 +9,8 @@ have dual GMAC each represented by a child node..
 Required properties:
 - compatible: Should be "mediatek,mt7623-eth"
 - reg: Address and length of the register set for the device
-- interrupts: Should contain the frame engines interrupt
+- interrupts: Should contain the three frame engines interrupts in numeric
+	order. These are fe_int0, fe_int1 and fe_int2.
 - clocks: the clock used by the core
 - clock-names: the names of the clock listed in the clocks property. These are
 	"ethif", "esw", "gp2", "gp1"
@@ -42,7 +43,9 @@ eth: ethernet@1b100000 {
 		 <&ethsys CLK_ETHSYS_GP2>,
 		 <&ethsys CLK_ETHSYS_GP1>;
 	clock-names = "ethif", "esw", "gp2", "gp1";
-	interrupts = <GIC_SPI 200 IRQ_TYPE_LEVEL_LOW>;
+	interrupts = <GIC_SPI 200 IRQ_TYPE_LEVEL_LOW
+		      GIC_SPI 199 IRQ_TYPE_LEVEL_LOW
+		      GIC_SPI 198 IRQ_TYPE_LEVEL_LOW>;
 	power-domains = <&scpsys MT2701_POWER_DOMAIN_ETH>;
 	resets = <&ethsys MT2701_ETHSYS_ETH_RST>;
 	reset-names = "eth";

Documentation/devicetree/bindings/phy/rockchip-dp-phy.txt

@@ -8,15 +8,19 @@ Required properties:
 	of memory mapped region.
 - clock-names: from common clock binding:
 	Required elements: "24m"
-- rockchip,grf: phandle to the syscon managing the "general register files"
 - #phy-cells : from the generic PHY bindings, must be 0;
 
 Example:
 
-edp_phy: edp-phy {
-	compatible = "rockchip,rk3288-dp-phy";
-	rockchip,grf = <&grf>;
-	clocks = <&cru SCLK_EDP_24M>;
-	clock-names = "24m";
-	#phy-cells = <0>;
+grf: syscon@ff770000 {
+	compatible = "rockchip,rk3288-grf", "syscon", "simple-mfd";
+
+...
+
+	edp_phy: edp-phy {
+		compatible = "rockchip,rk3288-dp-phy";
+		clocks = <&cru SCLK_EDP_24M>;
+		clock-names = "24m";
+		#phy-cells = <0>;
+	};
 };

Documentation/devicetree/bindings/phy/rockchip-emmc-phy.txt

@@ -3,17 +3,23 @@ Rockchip EMMC PHY
 
 Required properties:
  - compatible: rockchip,rk3399-emmc-phy
- - rockchip,grf : phandle to the syscon managing the "general
-   register files"
  - #phy-cells: must be 0
- - reg: PHY configure reg address offset in "general
+ - reg: PHY register address offset and length in "general
    register files"
 
 Example:
 
-emmcphy: phy {
-	compatible = "rockchip,rk3399-emmc-phy";
-	rockchip,grf = <&grf>;
-	reg = <0xf780>;
-	#phy-cells = <0>;
+
+grf: syscon@ff770000 {
+	compatible = "rockchip,rk3399-grf", "syscon", "simple-mfd";
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+...
+
+	emmcphy: phy@f780 {
+		compatible = "rockchip,rk3399-emmc-phy";
+		reg = <0xf780 0x20>;
+		#phy-cells = <0>;
+	};
 };

Documentation/devicetree/bindings/rtc/s3c-rtc.txt

@@ -15,9 +15,10 @@ Required properties:
   is the rtc tick interrupt. The number of cells representing a interrupt
   depends on the parent interrupt controller.
 - clocks: Must contain a list of phandle and clock specifier for the rtc
-          and source clocks.
-- clock-names: Must contain "rtc" and "rtc_src" entries sorted in the
-               same order as the clocks property.
+          clock and in the case of a s3c6410 compatible controller, also
+          a source clock.
+- clock-names: Must contain "rtc" and for a s3c6410 compatible controller,
+               a "rtc_src" sorted in the same order as the clocks property.
 
 Example:
 

Documentation/input/event-codes.txt

@@ -173,6 +173,10 @@ A few EV_ABS codes have special meanings:
     proximity of the device and while the value of the BTN_TOUCH code is 0. If
     the input device may be used freely in three dimensions, consider ABS_Z
     instead.
+  - BTN_TOOL_<name> should be set to 1 when the tool comes into detectable
+    proximity and set to 0 when the tool leaves detectable proximity.
+    BTN_TOOL_<name> signals the type of tool that is currently detected by the
+    hardware and is otherwise independent of ABS_DISTANCE and/or BTN_TOUCH.
 
 * ABS_MT_<name>:
   - Used to describe multitouch input events. Please see

Documentation/sysctl/vm.txt

@@ -581,15 +581,16 @@ Specify "[Nn]ode" for node order
 "Zone Order" orders the zonelists by zone type, then by node within each
 zone.  Specify "[Zz]one" for zone order.
 
-Specify "[Dd]efault" to request automatic configuration.  Autoconfiguration
-will select "node" order in following case.
-(1) if the DMA zone does not exist or
-(2) if the DMA zone comprises greater than 50% of the available memory or
-(3) if any node's DMA zone comprises greater than 70% of its local memory and
-    the amount of local memory is big enough.
-
-Otherwise, "zone" order will be selected. Default order is recommended unless
-this is causing problems for your system/application.
+Specify "[Dd]efault" to request automatic configuration.
+
+On 32-bit, the Normal zone needs to be preserved for allocations accessible
+by the kernel, so "zone" order will be selected.
+
+On 64-bit, devices that require DMA32/DMA are relatively rare, so "node"
+order will be selected.
+
+Default order is recommended unless this is causing problems for your
+system/application.
 
 ==============================================================
 

Documentation/x86/x86_64/mm.txt

@@ -19,7 +19,7 @@ ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
 ffffffef00000000 - ffffffff00000000 (=64 GB) EFI region mapping space
 ... unused hole ...
 ffffffff80000000 - ffffffffa0000000 (=512 MB)  kernel text mapping, from phys 0
-ffffffffa0000000 - ffffffffff5fffff (=1525 MB) module mapping space
+ffffffffa0000000 - ffffffffff5fffff (=1526 MB) module mapping space
 ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls
 ffffffffffe00000 - ffffffffffffffff (=2 MB) unused hole
 
@@ -31,8 +31,8 @@ vmalloc space is lazily synchronized into the different PML4 pages of
 the processes using the page fault handler, with init_level4_pgt as
 reference.
 
-Current X86-64 implementations only support 40 bits of address space,
-but we support up to 46 bits. This expands into MBZ space in the page tables.
+Current X86-64 implementations support up to 46 bits of address space (64 TB),
+which is our current limit. This expands into MBZ space in the page tables.
 
 We map EFI runtime services in the 'efi_pgd' PGD in a 64Gb large virtual
 memory window (this size is arbitrary, it can be raised later if needed).

MAINTAINERS

@@ -6027,7 +6027,7 @@ F:	include/scsi/*iscsi*
 
 ISCSI EXTENSIONS FOR RDMA (ISER) INITIATOR
 M:	Or Gerlitz <ogerlitz@mellanox.com>
-M:	Sagi Grimberg <sagig@mellanox.com>
+M:	Sagi Grimberg <sagi@grimberg.me>
 M:	Roi Dayan <roid@mellanox.com>
 L:	linux-rdma@vger.kernel.org
 S:	Supported
@@ -6037,7 +6037,7 @@ Q:	http://patchwork.kernel.org/project/linux-rdma/list/
 F:	drivers/infiniband/ulp/iser/
 
 ISCSI EXTENSIONS FOR RDMA (ISER) TARGET
-M:	Sagi Grimberg <sagig@mellanox.com>
+M:	Sagi Grimberg <sagi@grimberg.me>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending.git master
 L:	linux-rdma@vger.kernel.org
 L:	target-devel@vger.kernel.org
@@ -6400,7 +6400,7 @@ F:	mm/kmemleak.c
 F:	mm/kmemleak-test.c
 
 KPROBES
-M:	Ananth N Mavinakayanahalli <ananth@in.ibm.com>
+M:	Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
 M:	Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
 M:	"David S. Miller" <davem@davemloft.net>
 M:	Masami Hiramatsu <mhiramat@kernel.org>
@@ -11071,6 +11071,15 @@ S:	Maintained
 F:	drivers/clk/ti/
 F:	include/linux/clk/ti.h
 
+TI ETHERNET SWITCH DRIVER (CPSW)
+M:	Mugunthan V N <mugunthanvnm@ti.com>
+R:	Grygorii Strashko <grygorii.strashko@ti.com>
+L:	linux-omap@vger.kernel.org
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	drivers/net/ethernet/ti/cpsw*
+F:	drivers/net/ethernet/ti/davinci*
+
 TI FLASH MEDIA INTERFACE DRIVER
 M:	Alex Dubov <oakad@yahoo.com>
 S:	Maintained

Makefile

 VERSION = 4
 PATCHLEVEL = 6
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
-NAME = Blurry Fish Butt
+EXTRAVERSION = -rc6
+NAME = Charred Weasel
 
 # *DOCUMENTATION*
 # To see a list of typical targets execute "make help"
@@ -1008,7 +1008,8 @@ prepare0: archprepare FORCE
 prepare: prepare0 prepare-objtool
 
 ifdef CONFIG_STACK_VALIDATION
-  has_libelf := $(shell echo "int main() {}" | $(HOSTCC) -xc -o /dev/null -lelf - &> /dev/null && echo 1 || echo 0)
+  has_libelf := $(call try-run,\
+		echo "int main() {}" | $(HOSTCC) -xc -o /dev/null -lelf -,1,0)
   ifeq ($(has_libelf),1)
     objtool_target := tools/objtool FORCE
   else

arch/arc/Kconfig

@@ -35,8 +35,10 @@ config ARC
 	select NO_BOOTMEM
 	select OF
 	select OF_EARLY_FLATTREE
+	select OF_RESERVED_MEM
 	select PERF_USE_VMALLOC
 	select HAVE_DEBUG_STACKOVERFLOW
+	select HAVE_GENERIC_DMA_COHERENT
 
 config MIGHT_HAVE_PCI
 	bool

arch/arc/include/asm/irqflags-arcv2.h

@@ -18,6 +18,12 @@
 #define STATUS_AD_MASK		(1<<STATUS_AD_BIT)
 #define STATUS_IE_MASK		(1<<STATUS_IE_BIT)
 
+/* status32 Bits as encoded/expected by CLRI/SETI */
+#define CLRI_STATUS_IE_BIT	4
+
+#define CLRI_STATUS_E_MASK	0xF
+#define CLRI_STATUS_IE_MASK	(1 << CLRI_STATUS_IE_BIT)
+
 #define AUX_USER_SP		0x00D
 #define AUX_IRQ_CTRL		0x00E
 #define AUX_IRQ_ACT		0x043	/* Active Intr across all levels */
@@ -100,6 +106,13 @@ static inline long arch_local_save_flags(void)
 	:
 	: "memory");
 
+	/* To be compatible with irq_save()/irq_restore()
+	 * encode the irq bits as expected by CLRI/SETI
+	 * (this was needed to make CONFIG_TRACE_IRQFLAGS work)
+	 */
+	temp = (1 << 5) |
+		((!!(temp & STATUS_IE_MASK)) << CLRI_STATUS_IE_BIT) |
+		(temp & CLRI_STATUS_E_MASK);
 	return temp;
 }
 
@@ -108,7 +121,7 @@ static inline long arch_local_save_flags(void)
  */
 static inline int arch_irqs_disabled_flags(unsigned long flags)
 {
-	return !(flags & (STATUS_IE_MASK));
+	return !(flags & CLRI_STATUS_IE_MASK);
 }
 
 static inline int arch_irqs_disabled(void)
@@ -128,11 +141,32 @@ static inline void arc_softirq_clear(int irq)
 
 #else
 
+#ifdef CONFIG_TRACE_IRQFLAGS
+
+.macro TRACE_ASM_IRQ_DISABLE
+	bl	trace_hardirqs_off
+.endm
+
+.macro TRACE_ASM_IRQ_ENABLE
+	bl	trace_hardirqs_on
+.endm
+
+#else
+
+.macro TRACE_ASM_IRQ_DISABLE
+.endm
+
+.macro TRACE_ASM_IRQ_ENABLE
+.endm
+
+#endif
 .macro IRQ_DISABLE  scratch
 	clri
+	TRACE_ASM_IRQ_DISABLE
 .endm
 
 .macro IRQ_ENABLE  scratch
+	TRACE_ASM_IRQ_ENABLE
 	seti
 .endm
 

arch/arc/kernel/entry-arcv2.S

@@ -69,8 +69,11 @@ ENTRY(handle_interrupt)
 
 	clri		; To make status32.IE agree with CPU internal state
 
-	lr  r0, [ICAUSE]
+#ifdef CONFIG_TRACE_IRQFLAGS
+	TRACE_ASM_IRQ_DISABLE
+#endif
 
+	lr  r0, [ICAUSE]
 	mov   blink, ret_from_exception
 
 	b.d  arch_do_IRQ
@@ -169,6 +172,11 @@ END(EV_TLBProtV)
 
 .Lrestore_regs:
 
+	# Interrpts are actually disabled from this point on, but will get
+	# reenabled after we return from interrupt/exception.
+	# But irq tracer needs to be told now...
+	TRACE_ASM_IRQ_ENABLE
+
 	ld	r0, [sp, PT_status32]	; U/K mode at time of entry
 	lr	r10, [AUX_IRQ_ACT]
 

arch/arc/kernel/entry-compact.S

@@ -341,6 +341,9 @@ END(call_do_page_fault)
 
 .Lrestore_regs:
 
+	# Interrpts are actually disabled from this point on, but will get
+	# reenabled after we return from interrupt/exception.
+	# But irq tracer needs to be told now...
 	TRACE_ASM_IRQ_ENABLE
 
 	lr	r10, [status32]

arch/arc/mm/init.c

@@ -13,6 +13,7 @@
 #ifdef CONFIG_BLK_DEV_INITRD
 #include <linux/initrd.h>
 #endif
+#include <linux/of_fdt.h>
 #include <linux/swap.h>
 #include <linux/module.h>
 #include <linux/highmem.h>
@@ -136,6 +137,9 @@ void __init setup_arch_memory(void)
 		memblock_reserve(__pa(initrd_start), initrd_end - initrd_start);
 #endif
 
+	early_init_fdt_reserve_self();
+	early_init_fdt_scan_reserved_mem();
+
 	memblock_dump_all();
 
 	/*----------------- node/zones setup --------------------------*/

arch/arm/boot/dts/am33xx.dtsi

@@ -860,7 +860,7 @@
 			ti,no-idle-on-init;
 			reg = <0x50000000 0x2000>;
 			interrupts = <100>;
-			dmas = <&edma 52>;
+			dmas = <&edma 52 0>;
 			dma-names = "rxtx";
 			gpmc,num-cs = <7>;
 			gpmc,num-waitpins = <2>;

arch/arm/boot/dts/am4372.dtsi

@@ -884,7 +884,7 @@
 		gpmc: gpmc@50000000 {
 			compatible = "ti,am3352-gpmc";
 			ti,hwmods = "gpmc";
-			dmas = <&edma 52>;
+			dmas = <&edma 52 0>;
 			dma-names = "rxtx";
 			clocks = <&l3s_gclk>;
 			clock-names = "fck";

arch/arm/boot/dts/am57xx-beagle-x15.dts

@@ -99,13 +99,6 @@
 		#cooling-cells = <2>;
 	};
 
-	extcon_usb1: extcon_usb1 {
-		compatible = "linux,extcon-usb-gpio";
-		id-gpio = <&gpio7 25 GPIO_ACTIVE_HIGH>;
-		pinctrl-names = "default";
-		pinctrl-0 = <&extcon_usb1_pins>;
-	};
-
 	hdmi0: connector {
 		compatible = "hdmi-connector";
 		label = "hdmi";
@@ -349,12 +342,6 @@
 		>;
 	};
 
-	extcon_usb1_pins: extcon_usb1_pins {
-		pinctrl-single,pins = <
-			DRA7XX_CORE_IOPAD(0x37ec, PIN_INPUT_PULLUP | MUX_MODE14) /* uart1_rtsn.gpio7_25 */
-		>;
-	};
-
 	tpd12s015_pins: pinmux_tpd12s015_pins {
 		pinctrl-single,pins = <
 			DRA7XX_CORE_IOPAD(0x37b0, PIN_OUTPUT | MUX_MODE14)		/* gpio7_10 CT_CP_HPD */
@@ -706,10 +693,6 @@
 	pinctrl-0 = <&usb1_pins>;
 };
 
-&omap_dwc3_1 {
-	extcon = <&extcon_usb1>;
-};
-
 &omap_dwc3_2 {
 	extcon = <&extcon_usb2>;
 };

arch/arm/boot/dts/dm814x-clocks.dtsi

@@ -4,6 +4,157 @@
  * published by the Free Software Foundation.
  */
 
+&pllss {
+	/*
+	 * See TRM "2.6.10 Connected outputso DPLLS" and
+	 * "2.6.11 Connected Outputs of DPLLJ". Only clkout is
+	 * connected except for hdmi and usb.
+	 */
+	adpll_mpu_ck: adpll@40 {
+		#clock-cells = <1>;
+		compatible = "ti,dm814-adpll-s-clock";
+		reg = <0x40 0x40>;
+		clocks = <&devosc_ck &devosc_ck &devosc_ck>;
+		clock-names = "clkinp", "clkinpulow", "clkinphif";
+		clock-output-names = "481c5040.adpll.dcoclkldo",
+				     "481c5040.adpll.clkout",
+				     "481c5040.adpll.clkoutx2",
+				     "481c5040.adpll.clkouthif";
+	};
+
+	adpll_dsp_ck: adpll@80 {
+		#clock-cells = <1>;
+		compatible = "ti,dm814-adpll-lj-clock";
+		reg = <0x80 0x30>;
+		clocks = <&devosc_ck &devosc_ck>;
+		clock-names = "clkinp", "clkinpulow";
+		clock-output-names = "481c5080.adpll.dcoclkldo",
+				     "481c5080.adpll.clkout",
+				     "481c5080.adpll.clkoutldo";
+	};
+
+	adpll_sgx_ck: adpll@b0 {
+		#clock-cells = <1>;
+		compatible = "ti,dm814-adpll-lj-clock";
+		reg = <0xb0 0x30>;
+		clocks = <&devosc_ck &devosc_ck>;
+		clock-names = "clkinp", "clkinpulow";
+		clock-output-names = "481c50b0.adpll.dcoclkldo",
+				     "481c50b0.adpll.clkout",
+				     "481c50b0.adpll.clkoutldo";
+	};
+
+	adpll_hdvic_ck: adpll@e0 {
+		#clock-cells = <1>;
+		compatible = "ti,dm814-adpll-lj-clock";
+		reg = <0xe0 0x30>;
+		clocks = <&devosc_ck &devosc_ck>;
+		clock-names = "clkinp", "clkinpulow";
+		clock-output-names = "481c50e0.adpll.dcoclkldo",
+				     "481c50e0.adpll.clkout",
+				     "481c50e0.adpll.clkoutldo";
+	};
+
+	adpll_l3_ck: adpll@110 {
+		#clock-cells = <1>;
+		compatible = "ti,dm814-adpll-lj-clock";
+		reg = <0x110 0x30>;
+		clocks = <&devosc_ck &devosc_ck>;
+		clock-names = "clkinp", "clkinpulow";
+		clock-output-names = "481c5110.adpll.dcoclkldo",
+				     "481c5110.adpll.clkout",
+				     "481c5110.adpll.clkoutldo";
+	};
+
+	adpll_isp_ck: adpll@140 {
+		#clock-cells = <1>;
+		compatible = "ti,dm814-adpll-lj-clock";
+		reg = <0x140 0x30>;
+		clocks = <&devosc_ck &devosc_ck>;
+		clock-names = "clkinp", "clkinpulow";
+		clock-output-names = "481c5140.adpll.dcoclkldo",
+				     "481c5140.adpll.clkout",
+				     "481c5140.adpll.clkoutldo";
+	};
+
+	adpll_dss_ck: adpll@170 {
+		#clock-cells = <1>;
+		compatible = "ti,dm814-adpll-lj-clock";
+		reg = <0x170 0x30>;
+		clocks = <&devosc_ck &devosc_ck>;
+		clock-names = "clkinp", "clkinpulow";
+		clock-output-names = "481c5170.adpll.dcoclkldo",
+				     "481c5170.adpll.clkout",
+				     "481c5170.adpll.clkoutldo";
+	};
+
+	adpll_video0_ck: adpll@1a0 {
+		#clock-cells = <1>;
+		compatible = "ti,dm814-adpll-lj-clock";
+		reg = <0x1a0 0x30>;
+		clocks = <&devosc_ck &devosc_ck>;
+		clock-names = "clkinp", "clkinpulow";
+		clock-output-names = "481c51a0.adpll.dcoclkldo",
+				     "481c51a0.adpll.clkout",
+				     "481c51a0.adpll.clkoutldo";
+	};
+
+	adpll_video1_ck: adpll@1d0 {
+		#clock-cells = <1>;
+		compatible = "ti,dm814-adpll-lj-clock";
+		reg = <0x1d0 0x30>;
+		clocks = <&devosc_ck &devosc_ck>;
+		clock-names = "clkinp", "clkinpulow";
+		clock-output-names = "481c51d0.adpll.dcoclkldo",
+				     "481c51d0.adpll.clkout",
+				     "481c51d0.adpll.clkoutldo";
+	};
+
+	adpll_hdmi_ck: adpll@200 {
+		#clock-cells = <1>;
+		compatible = "ti,dm814-adpll-lj-clock";
+		reg = <0x200 0x30>;
+		clocks = <&devosc_ck &devosc_ck>;
+		clock-names = "clkinp", "clkinpulow";
+		clock-output-names = "481c5200.adpll.dcoclkldo",
+				     "481c5200.adpll.clkout",
+				     "481c5200.adpll.clkoutldo";
+	};
+
+	adpll_audio_ck: adpll@230 {
+		#clock-cells = <1>;
+		compatible = "ti,dm814-adpll-lj-clock";
+		reg = <0x230 0x30>;
+		clocks = <&devosc_ck &devosc_ck>;
+		clock-names = "clkinp", "clkinpulow";
+		clock-output-names = "481c5230.adpll.dcoclkldo",
+				     "481c5230.adpll.clkout",
+				     "481c5230.adpll.clkoutldo";
+	};
+
+	adpll_usb_ck: adpll@260 {
+		#clock-cells = <1>;
+		compatible = "ti,dm814-adpll-lj-clock";
+		reg = <0x260 0x30>;
+		clocks = <&devosc_ck &devosc_ck>;
+		clock-names = "clkinp", "clkinpulow";
+		clock-output-names = "481c5260.adpll.dcoclkldo",
+				     "481c5260.adpll.clkout",
+				     "481c5260.adpll.clkoutldo";
+	};
+
+	adpll_ddr_ck: adpll@290 {
+		#clock-cells = <1>;
+		compatible = "ti,dm814-adpll-lj-clock";
+		reg = <0x290 0x30>;
+		clocks = <&devosc_ck &devosc_ck>;
+		clock-names = "clkinp", "clkinpulow";
+		clock-output-names = "481c5290.adpll.dcoclkldo",
+				     "481c5290.adpll.clkout",
+				     "481c5290.adpll.clkoutldo";
+	};
+};
+
 &pllss_clocks {
 	timer1_fck: timer1_fck {
 		#clock-cells = <0>;
@@ -23,6 +174,24 @@
 		reg = <0x2e0>;
 	};
 
+	/* CPTS_RFT_CLK in RMII_REFCLK_SRC, usually sourced from auiod */
+	cpsw_cpts_rft_clk: cpsw_cpts_rft_clk {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&adpll_video0_ck 1
+			  &adpll_video1_ck 1
+			  &adpll_audio_ck 1>;
+		ti,bit-shift = <1>;
+		reg = <0x2e8>;
+	};
+
+	/* REVISIT: Set up with a proper mux using RMII_REFCLK_SRC */
+	cpsw_125mhz_gclk: cpsw_125mhz_gclk {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <125000000>;
+	};
+
 	sysclk18_ck: sysclk18_ck {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
@@ -79,37 +248,6 @@
 		compatible = "fixed-clock";
 		clock-frequency = <1000000000>;
 	};
-
-	sysclk4_ck: sysclk4_ck {
-		#clock-cells = <0>;
-		compatible = "fixed-clock";
-		clock-frequency = <222000000>;
-	};
-
-	sysclk6_ck: sysclk6_ck {
-		#clock-cells = <0>;
-		compatible = "fixed-clock";
-		clock-frequency = <100000000>;
-	};
-
-	sysclk10_ck: sysclk10_ck {
-		#clock-cells = <0>;
-		compatible = "fixed-clock";
-		clock-frequency = <48000000>;
-	};
-
-        cpsw_125mhz_gclk: cpsw_125mhz_gclk {
-		#clock-cells = <0>;
-		compatible = "fixed-clock";
-		clock-frequency = <125000000>;
-	};
-
-	cpsw_cpts_rft_clk: cpsw_cpts_rft_clk {
-		#clock-cells = <0>;
-		compatible = "fixed-clock";
-		clock-frequency = <250000000>;
-	};
-
 };
 
 &prcm_clocks {
@@ -138,6 +276,49 @@
 		clock-div = <78125>;
 	};
 
+	/* L4_HS 220 MHz*/
+	sysclk4_ck: sysclk4_ck {
+		#clock-cells = <0>;
+		compatible = "ti,fixed-factor-clock";
+		clocks = <&adpll_l3_ck 1>;
+		ti,clock-mult = <1>;
+		ti,clock-div = <1>;
+	};
+
+	/* L4_FWCFG */
+	sysclk5_ck: sysclk5_ck {
+		#clock-cells = <0>;
+		compatible = "ti,fixed-factor-clock";
+		clocks = <&adpll_l3_ck 1>;
+		ti,clock-mult = <1>;
+		ti,clock-div = <2>;
+	};
+
+	/* L4_LS 110 MHz */
+	sysclk6_ck: sysclk6_ck {
+		#clock-cells = <0>;
+		compatible = "ti,fixed-factor-clock";
+		clocks = <&adpll_l3_ck 1>;
+		ti,clock-mult = <1>;
+		ti,clock-div = <2>;
+	};
+
+	sysclk8_ck: sysclk8_ck {
+		#clock-cells = <0>;
+		compatible = "ti,fixed-factor-clock";
+		clocks = <&adpll_usb_ck 1>;
+		ti,clock-mult = <1>;
+		ti,clock-div = <1>;
+	};
+
+	sysclk10_ck: sysclk10_ck {
+		compatible = "ti,divider-clock";
+		reg = <0x324>;
+		ti,max-div = <7>;
+		#clock-cells = <0>;
+		clocks = <&adpll_usb_ck 1>;
+	};
+
 	aud_clkin0_ck: aud_clkin0_ck {
 		#clock-cells = <0>;
 		compatible = "fixed-clock";

arch/arm/boot/dts/dra62x-clocks.dtsi

@@ -6,6 +6,32 @@
 
 #include "dm814x-clocks.dtsi"
 
+/* Compared to dm814x, dra62x does not have hdic, l3 or dss PLLs */
+&adpll_hdvic_ck {
+	status = "disabled";
+};
+
+&adpll_l3_ck {
+	status = "disabled";
+};
+
+&adpll_dss_ck {
+	status = "disabled";
+};
+
+/* Compared to dm814x, dra62x has interconnect clocks on isp PLL */
+&sysclk4_ck {
+	clocks = <&adpll_isp_ck 1>;
+};
+
+&sysclk5_ck {
+	clocks = <&adpll_isp_ck 1>;
+};
+
+&sysclk6_ck {
+	clocks = <&adpll_isp_ck 1>;
+};
+
 /*
  * Compared to dm814x, dra62x has different shifts and more mux options.
  * Please add the extra options for ysclk_14 and 16 if really needed.

arch/arm/boot/dts/dra7xx-clocks.dtsi

@@ -98,12 +98,20 @@
 		clock-frequency = <32768>;
 	};
 
-	sys_32k_ck: sys_32k_ck {
+	sys_clk32_crystal_ck: sys_clk32_crystal_ck {
 		#clock-cells = <0>;
 		compatible = "fixed-clock";
 		clock-frequency = <32768>;
 	};
 
+	sys_clk32_pseudo_ck: sys_clk32_pseudo_ck {
+		#clock-cells = <0>;
+		compatible = "fixed-factor-clock";
+		clocks = <&sys_clkin1>;
+		clock-mult = <1>;
+		clock-div = <610>;
+	};
+
 	virt_12000000_ck: virt_12000000_ck {
 		#clock-cells = <0>;
 		compatible = "fixed-clock";
@@ -2170,4 +2178,12 @@
 		ti,bit-shift = <22>;
 		reg = <0x0558>;
 	};
+
+	sys_32k_ck: sys_32k_ck {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sys_clk32_crystal_ck>, <&sys_clk32_pseudo_ck>, <&sys_clk32_pseudo_ck>, <&sys_clk32_pseudo_ck>;
+		ti,bit-shift = <8>;
+		reg = <0x6c4>;
+	};
 };

arch/arm/boot/dts/qcom-msm8974.dtsi

 /dts-v1/;
 
-#include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/interrupt-controller/irq.h>
 #include <dt-bindings/clock/qcom,gcc-msm8974.h>
 #include "skeleton.dtsi"
 
@@ -460,8 +460,6 @@
 			clock-names = "core", "iface";
 			#address-cells = <1>;
 			#size-cells = <0>;
-			dmas = <&blsp2_dma 20>, <&blsp2_dma 21>;
-			dma-names = "tx", "rx";
 		};
 
 		spmi_bus: spmi@fc4cf000 {
@@ -479,16 +477,6 @@
 			interrupt-controller;
 			#interrupt-cells = <4>;
 		};
-
-		blsp2_dma: dma-controller@f9944000 {
-			compatible = "qcom,bam-v1.4.0";
-			reg = <0xf9944000 0x19000>;
-			interrupts = <GIC_SPI 239 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&gcc GCC_BLSP2_AHB_CLK>;
-			clock-names = "bam_clk";
-			#dma-cells = <1>;
-			qcom,ee = <0>;
-		};
 	};
 
 	smd {

arch/arm/boot/dts/r8a7791-koelsch.dts

@@ -661,6 +661,7 @@
 };
 
 &pcie_bus_clk {
+	clock-frequency = <100000000>;
 	status = "okay";
 };
 

arch/arm/boot/dts/r8a7791-porter.dts

@@ -143,19 +143,11 @@
 };
 
 &pfc {
-	pinctrl-0 = <&scif_clk_pins>;
-	pinctrl-names = "default";
-
 	scif0_pins: serial0 {
 		renesas,groups = "scif0_data_d";
 		renesas,function = "scif0";
 	};
 
-	scif_clk_pins: scif_clk {
-		renesas,groups = "scif_clk";
-		renesas,function = "scif_clk";
-	};
-
 	ether_pins: ether {
 		renesas,groups = "eth_link", "eth_mdio", "eth_rmii";
 		renesas,function = "eth";
@@ -229,11 +221,6 @@
 	status = "okay";
 };
 
-&scif_clk {
-	clock-frequency = <14745600>;
-	status = "okay";
-};
-
 &ether {
 	pinctrl-0 = <&ether_pins &phy1_pins>;
 	pinctrl-names = "default";
@@ -414,6 +401,7 @@
 };
 
 &pcie_bus_clk {
+	clock-frequency = <100000000>;
 	status = "okay";
 };
 

arch/arm/boot/dts/r8a7791.dtsi

@@ -1083,9 +1083,8 @@
 		pcie_bus_clk: pcie_bus_clk {
 			compatible = "fixed-clock";
 			#clock-cells = <0>;
-			clock-frequency = <100000000>;
+			clock-frequency = <0>;
 			clock-output-names = "pcie_bus";
-			status = "disabled";
 		};
 
 		/* External SCIF clock */
@@ -1094,7 +1093,6 @@
 			#clock-cells = <0>;
 			/* This value must be overridden by the board. */
 			clock-frequency = <0>;
-			status = "disabled";
 		};
 
 		/* External USB clock - can be overridden by the board */
@@ -1112,7 +1110,6 @@
 			/* This value must be overridden by the board. */
 			clock-frequency = <0>;
 			clock-output-names = "can_clk";
-			status = "disabled";
 		};
 
 		/* Special CPG clocks */

arch/arm/include/asm/cputype.h

@@ -276,7 +276,7 @@ static inline int __attribute_const__ cpuid_feature_extract_field(u32 features,
 	int feature = (features >> field) & 15;
 
 	/* feature registers are signed values */
-	if (feature > 8)
+	if (feature > 7)
 		feature -= 16;
 
 	return feature;

arch/arm/kernel/setup.c

@@ -512,7 +512,7 @@ static void __init elf_hwcap_fixup(void)
 	 */
 	if (cpuid_feature_extract(CPUID_EXT_ISAR3, 12) > 1 ||
 	    (cpuid_feature_extract(CPUID_EXT_ISAR3, 12) == 1 &&
-	     cpuid_feature_extract(CPUID_EXT_ISAR3, 20) >= 3))
+	     cpuid_feature_extract(CPUID_EXT_ISAR4, 20) >= 3))
 		elf_hwcap &= ~HWCAP_SWP;
 }
 

arch/arm/mach-imx/devices/platform-sdhci-esdhc-imx.c

@@ -71,6 +71,7 @@ struct platform_device *__init imx_add_sdhci_esdhc_imx(
 	if (!pdata)
 		pdata = &default_esdhc_pdata;
 
-	return imx_add_platform_device(data->devid, data->id, res,
-			ARRAY_SIZE(res), pdata, sizeof(*pdata));
+	return imx_add_platform_device_dmamask(data->devid, data->id, res,
+			ARRAY_SIZE(res), pdata, sizeof(*pdata),
+			DMA_BIT_MASK(32));
 }

arch/arm/mach-omap2/clockdomains7xx_data.c

@@ -461,7 +461,7 @@ static struct clockdomain ipu_7xx_clkdm = {
 	.cm_inst	  = DRA7XX_CM_CORE_AON_IPU_INST,
 	.clkdm_offs	  = DRA7XX_CM_CORE_AON_IPU_IPU_CDOFFS,
 	.dep_bit	  = DRA7XX_IPU_STATDEP_SHIFT,
-	.flags		  = CLKDM_CAN_HWSUP_SWSUP,
+	.flags		  = CLKDM_CAN_SWSUP,
 };
 
 static struct clockdomain mpu1_7xx_clkdm = {

arch/arm/mach-omap2/io.c

@@ -737,7 +737,8 @@ void __init omap5_init_late(void)
 #ifdef CONFIG_SOC_DRA7XX
 void __init dra7xx_init_early(void)
 {
-	omap2_set_globals_tap(-1, OMAP2_L4_IO_ADDRESS(DRA7XX_TAP_BASE));
+	omap2_set_globals_tap(DRA7XX_CLASS,
+			      OMAP2_L4_IO_ADDRESS(DRA7XX_TAP_BASE));
 	omap2_set_globals_prcm_mpu(OMAP2_L4_IO_ADDRESS(OMAP54XX_PRCM_MPU_BASE));
 	omap2_control_base_init();
 	omap4_pm_init_early();

arch/arm/mach-omap2/omap-wakeupgen.c

@@ -274,6 +274,10 @@ static inline void omap5_irq_save_context(void)
  */
 static void irq_save_context(void)
 {
+	/* DRA7 has no SAR to save */
+	if (soc_is_dra7xx())
+		return;
+
 	if (!sar_base)
 		sar_base = omap4_get_sar_ram_base();
 
@@ -290,6 +294,9 @@ static void irq_sar_clear(void)
 {
 	u32 val;
 	u32 offset = SAR_BACKUP_STATUS_OFFSET;
+	/* DRA7 has no SAR to save */
+	if (soc_is_dra7xx())
+		return;
 
 	if (soc_is_omap54xx())
 		offset = OMAP5_SAR_BACKUP_STATUS_OFFSET;

arch/arm/mach-omap2/pm34xx.c

@@ -198,7 +198,6 @@ void omap_sram_idle(void)
 	int per_next_state = PWRDM_POWER_ON;
 	int core_next_state = PWRDM_POWER_ON;
 	int per_going_off;
-	int core_prev_state;
 	u32 sdrc_pwr = 0;
 
 	mpu_next_state = pwrdm_read_next_pwrst(mpu_pwrdm);
@@ -278,16 +277,20 @@ void omap_sram_idle(void)
 		sdrc_write_reg(sdrc_pwr, SDRC_POWER);
 
 	/* CORE */
-	if (core_next_state < PWRDM_POWER_ON) {
-		core_prev_state = pwrdm_read_prev_pwrst(core_pwrdm);
-		if (core_prev_state == PWRDM_POWER_OFF) {
-			omap3_core_restore_context();
-			omap3_cm_restore_context();
-			omap3_sram_restore_context();
-			omap2_sms_restore_context();
-		}
+	if (core_next_state < PWRDM_POWER_ON &&
+	    pwrdm_read_prev_pwrst(core_pwrdm) == PWRDM_POWER_OFF) {
+		omap3_core_restore_context();
+		omap3_cm_restore_context();
+		omap3_sram_restore_context();
+		omap2_sms_restore_context();
+	} else {
+		/*
+		 * In off-mode resume path above, omap3_core_restore_context
+		 * also handles the INTC autoidle restore done here so limit
+		 * this to non-off mode resume paths so we don't do it twice.
+		 */
+		omap3_intc_resume_idle();
 	}
-	omap3_intc_resume_idle();
 
 	pwrdm_post_transition(NULL);
 

arch/arm/mach-shmobile/timer.c

@@ -40,8 +40,7 @@ static void __init shmobile_setup_delay_hz(unsigned int max_cpu_core_hz,
 void __init shmobile_init_delay(void)
 {
 	struct device_node *np, *cpus;
-	bool is_a7_a8_a9 = false;
-	bool is_a15 = false;
+	unsigned int div = 0;
 	bool has_arch_timer = false;
 	u32 max_freq = 0;
 
@@ -55,27 +54,22 @@ void __init shmobile_init_delay(void)
 		if (!of_property_read_u32(np, "clock-frequency", &freq))
 			max_freq = max(max_freq, freq);
 
-		if (of_device_is_compatible(np, "arm,cortex-a8") ||
-		    of_device_is_compatible(np, "arm,cortex-a9")) {
-			is_a7_a8_a9 = true;
-		} else if (of_device_is_compatible(np, "arm,cortex-a7")) {
-			is_a7_a8_a9 = true;
-			has_arch_timer = true;
-		} else if (of_device_is_compatible(np, "arm,cortex-a15")) {
-			is_a15 = true;
+		if (of_device_is_compatible(np, "arm,cortex-a8")) {
+			div = 2;
+		} else if (of_device_is_compatible(np, "arm,cortex-a9")) {
+			div = 1;
+		} else if (of_device_is_compatible(np, "arm,cortex-a7") ||
+			 of_device_is_compatible(np, "arm,cortex-a15")) {
+			div = 1;
 			has_arch_timer = true;
 		}
 	}
 
 	of_node_put(cpus);
 
-	if (!max_freq)
+	if (!max_freq || !div)
 		return;
 
-	if (!has_arch_timer || !IS_ENABLED(CONFIG_ARM_ARCH_TIMER)) {
-		if (is_a7_a8_a9)
-			shmobile_setup_delay_hz(max_freq, 1, 3);
-		else if (is_a15)
-			shmobile_setup_delay_hz(max_freq, 2, 4);
-	}
+	if (!has_arch_timer || !IS_ENABLED(CONFIG_ARM_ARCH_TIMER))
+		shmobile_setup_delay_hz(max_freq, 1, div);
 }

arch/arm/mm/dma-mapping.c

@@ -762,7 +762,8 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 	if (!mask)
 		return NULL;
 
-	buf = kzalloc(sizeof(*buf), gfp);
+	buf = kzalloc(sizeof(*buf),
+		      gfp & ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM));
 	if (!buf)
 		return NULL;
 

arch/arm64/boot/dts/socionext/uniphier-ph1-ld20-ref.dts

@@ -70,7 +70,6 @@
 		i2c3 = &i2c3;
 		i2c4 = &i2c4;
 		i2c5 = &i2c5;
-		i2c6 = &i2c6;
 	};
 };
 

arch/arm64/boot/dts/socionext/uniphier-ph1-ld20.dtsi

@@ -201,15 +201,12 @@
 
 		i2c2: i2c@58782000 {
 			compatible = "socionext,uniphier-fi2c";
-			status = "disabled";
 			reg = <0x58782000 0x80>;
 			#address-cells = <1>;
 			#size-cells = <0>;
 			interrupts = <0 43 4>;
-			pinctrl-names = "default";
-			pinctrl-0 = <&pinctrl_i2c2>;
 			clocks = <&i2c_clk>;
-			clock-frequency = <100000>;
+			clock-frequency = <400000>;
 		};
 
 		i2c3: i2c@58783000 {
@@ -227,12 +224,15 @@
 
 		i2c4: i2c@58784000 {
 			compatible = "socionext,uniphier-fi2c";
+			status = "disabled";
 			reg = <0x58784000 0x80>;
 			#address-cells = <1>;
 			#size-cells = <0>;
 			interrupts = <0 45 4>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_i2c4>;
 			clocks = <&i2c_clk>;
-			clock-frequency = <400000>;
+			clock-frequency = <100000>;
 		};
 
 		i2c5: i2c@58785000 {
@@ -245,16 +245,6 @@
 			clock-frequency = <400000>;
 		};
 
-		i2c6: i2c@58786000 {
-			compatible = "socionext,uniphier-fi2c";
-			reg = <0x58786000 0x80>;
-			#address-cells = <1>;
-			#size-cells = <0>;
-			interrupts = <0 26 4>;
-			clocks = <&i2c_clk>;
-			clock-frequency = <400000>;
-		};
-
 		system_bus: system-bus@58c00000 {
 			compatible = "socionext,uniphier-system-bus";
 			status = "disabled";

arch/arm64/kernel/head.S

@@ -588,6 +588,15 @@ set_hcr:
 	msr	vpidr_el2, x0
 	msr	vmpidr_el2, x1
 
+	/*
+	 * When VHE is not in use, early init of EL2 and EL1 needs to be
+	 * done here.
+	 * When VHE _is_ in use, EL1 will not be used in the host and
+	 * requires no configuration, and all non-hyp-specific EL2 setup
+	 * will be done via the _EL1 system register aliases in __cpu_setup.
+	 */
+	cbnz	x2, 1f
+
 	/* sctlr_el1 */
 	mov	x0, #0x0800			// Set/clear RES{1,0} bits
 CPU_BE(	movk	x0, #0x33d0, lsl #16	)	// Set EE and E0E on BE systems
@@ -597,6 +606,7 @@ CPU_LE(	movk	x0, #0x30d0, lsl #16	)	// Clear EE and E0E on LE systems
 	/* Coprocessor traps. */
 	mov	x0, #0x33ff
 	msr	cptr_el2, x0			// Disable copro. traps to EL2
+1:
 
 #ifdef CONFIG_COMPAT
 	msr	hstr_el2, xzr			// Disable CP15 traps to EL2
@@ -734,7 +744,8 @@ ENDPROC(__secondary_switched)
 
 	.macro	update_early_cpu_boot_status status, tmp1, tmp2
 	mov	\tmp2, #\status
-	str_l	\tmp2, __early_cpu_boot_status, \tmp1
+	adr_l	\tmp1, __early_cpu_boot_status
+	str	\tmp2, [\tmp1]
 	dmb	sy
 	dc	ivac, \tmp1			// Invalidate potentially stale cache line
 	.endm

arch/arm64/kernel/smp_spin_table.c

@@ -52,6 +52,7 @@ static void write_pen_release(u64 val)
 static int smp_spin_table_cpu_init(unsigned int cpu)
 {
 	struct device_node *dn;
+	int ret;
 
 	dn = of_get_cpu_node(cpu, NULL);
 	if (!dn)
@@ -60,15 +61,15 @@ static int smp_spin_table_cpu_init(unsigned int cpu)
 	/*
 	 * Determine the address from which the CPU is polling.
 	 */
-	if (of_property_read_u64(dn, "cpu-release-addr",
-				 &cpu_release_addr[cpu])) {
+	ret = of_property_read_u64(dn, "cpu-release-addr",
+				   &cpu_release_addr[cpu]);
+	if (ret)
 		pr_err("CPU %d: missing or invalid cpu-release-addr property\n",
 		       cpu);
 
-		return -1;
-	}
+	of_node_put(dn);
 
-	return 0;
+	return ret;
 }
 
 static int smp_spin_table_cpu_prepare(unsigned int cpu)

arch/nios2/lib/memset.c

@@ -68,7 +68,7 @@ void *memset(void *s, int c, size_t count)
 		  "=r" (charcnt),	/* %1  Output */
 		  "=r" (dwordcnt),	/* %2  Output */
 		  "=r" (fill8reg),	/* %3  Output */
-		  "=r" (wrkrega)	/* %4  Output */
+		  "=&r" (wrkrega)	/* %4  Output only */
 		: "r" (c),		/* %5  Input */
 		  "0" (s),		/* %0  Input/Output */
 		  "1" (count)		/* %1  Input/Output */

arch/powerpc/include/asm/systbl.h

@@ -384,3 +384,5 @@ SYSCALL(ni_syscall)
 SYSCALL(ni_syscall)
 SYSCALL(mlock2)
 SYSCALL(copy_file_range)
+COMPAT_SYS_SPU(preadv2)
+COMPAT_SYS_SPU(pwritev2)

arch/powerpc/include/asm/unistd.h

@@ -12,7 +12,7 @@
 #include <uapi/asm/unistd.h>
 
 
-#define NR_syscalls		380
+#define NR_syscalls		382
 
 #define __NR__exit __NR_exit
 

arch/powerpc/include/uapi/asm/cputable.h

@@ -31,6 +31,7 @@
 #define PPC_FEATURE_PSERIES_PERFMON_COMPAT \
 					0x00000040
 
+/* Reserved - do not use		0x00000004 */
 #define PPC_FEATURE_TRUE_LE		0x00000002
 #define PPC_FEATURE_PPC_LE		0x00000001
 

arch/powerpc/include/uapi/asm/unistd.h

@@ -390,5 +390,7 @@
 #define __NR_membarrier		365
 #define __NR_mlock2		378
 #define __NR_copy_file_range	379
+#define __NR_preadv2		380
+#define __NR_pwritev2		381
 
 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */

arch/powerpc/kernel/prom.c

@@ -148,23 +148,25 @@ static struct ibm_pa_feature {
 	unsigned long	cpu_features;	/* CPU_FTR_xxx bit */
 	unsigned long	mmu_features;	/* MMU_FTR_xxx bit */
 	unsigned int	cpu_user_ftrs;	/* PPC_FEATURE_xxx bit */
+	unsigned int	cpu_user_ftrs2;	/* PPC_FEATURE2_xxx bit */
 	unsigned char	pabyte;		/* byte number in ibm,pa-features */
 	unsigned char	pabit;		/* bit number (big-endian) */
 	unsigned char	invert;		/* if 1, pa bit set => clear feature */
 } ibm_pa_features[] __initdata = {
-	{0, 0, PPC_FEATURE_HAS_MMU,	0, 0, 0},
-	{0, 0, PPC_FEATURE_HAS_FPU,	0, 1, 0},
-	{CPU_FTR_CTRL, 0, 0,		0, 3, 0},
-	{CPU_FTR_NOEXECUTE, 0, 0,	0, 6, 0},
-	{CPU_FTR_NODSISRALIGN, 0, 0,	1, 1, 1},
-	{0, MMU_FTR_CI_LARGE_PAGE, 0,	1, 2, 0},
-	{CPU_FTR_REAL_LE, PPC_FEATURE_TRUE_LE, 5, 0, 0},
+	{0, 0, PPC_FEATURE_HAS_MMU, 0,		0, 0, 0},
+	{0, 0, PPC_FEATURE_HAS_FPU, 0,		0, 1, 0},
+	{CPU_FTR_CTRL, 0, 0, 0,			0, 3, 0},
+	{CPU_FTR_NOEXECUTE, 0, 0, 0,		0, 6, 0},
+	{CPU_FTR_NODSISRALIGN, 0, 0, 0,		1, 1, 1},
+	{0, MMU_FTR_CI_LARGE_PAGE, 0, 0,		1, 2, 0},
+	{CPU_FTR_REAL_LE, 0, PPC_FEATURE_TRUE_LE, 0, 5, 0, 0},
 	/*
-	 * If the kernel doesn't support TM (ie. CONFIG_PPC_TRANSACTIONAL_MEM=n),
-	 * we don't want to turn on CPU_FTR_TM here, so we use CPU_FTR_TM_COMP
-	 * which is 0 if the kernel doesn't support TM.
+	 * If the kernel doesn't support TM (ie CONFIG_PPC_TRANSACTIONAL_MEM=n),
+	 * we don't want to turn on TM here, so we use the *_COMP versions
+	 * which are 0 if the kernel doesn't support TM.
 	 */
-	{CPU_FTR_TM_COMP, 0, 0,		22, 0, 0},
+	{CPU_FTR_TM_COMP, 0, 0,
+	 PPC_FEATURE2_HTM_COMP|PPC_FEATURE2_HTM_NOSC_COMP, 22, 0, 0},
 };
 
 static void __init scan_features(unsigned long node, const unsigned char *ftrs,
@@ -195,10 +197,12 @@ static void __init scan_features(unsigned long node, const unsigned char *ftrs,
 		if (bit ^ fp->invert) {
 			cur_cpu_spec->cpu_features |= fp->cpu_features;
 			cur_cpu_spec->cpu_user_features |= fp->cpu_user_ftrs;
+			cur_cpu_spec->cpu_user_features2 |= fp->cpu_user_ftrs2;
 			cur_cpu_spec->mmu_features |= fp->mmu_features;
 		} else {
 			cur_cpu_spec->cpu_features &= ~fp->cpu_features;
 			cur_cpu_spec->cpu_user_features &= ~fp->cpu_user_ftrs;
+			cur_cpu_spec->cpu_user_features2 &= ~fp->cpu_user_ftrs2;
 			cur_cpu_spec->mmu_features &= ~fp->mmu_features;
 		}
 	}

arch/s390/Kconfig

@@ -4,6 +4,9 @@ config MMU
 config ZONE_DMA
 	def_bool y
 
+config CPU_BIG_ENDIAN
+	def_bool y
+
 config LOCKDEP_SUPPORT
 	def_bool y
 

arch/s390/include/asm/mmu.h

@@ -11,7 +11,7 @@ typedef struct {
 	spinlock_t list_lock;
 	struct list_head pgtable_list;
 	struct list_head gmap_list;
-	unsigned long asce_bits;
+	unsigned long asce;
 	unsigned long asce_limit;
 	unsigned long vdso_base;
 	/* The mmu context allocates 4K page tables. */

arch/s390/include/asm/mmu_context.h

@@ -26,12 +26,28 @@ static inline int init_new_context(struct task_struct *tsk,
 	mm->context.has_pgste = 0;
 	mm->context.use_skey = 0;
 #endif
-	if (mm->context.asce_limit == 0) {
+	switch (mm->context.asce_limit) {
+	case 1UL << 42:
+		/*
+		 * forked 3-level task, fall through to set new asce with new
+		 * mm->pgd
+		 */
+	case 0:
 		/* context created by exec, set asce limit to 4TB */
-		mm->context.asce_bits = _ASCE_TABLE_LENGTH |
-			_ASCE_USER_BITS | _ASCE_TYPE_REGION3;
 		mm->context.asce_limit = STACK_TOP_MAX;
-	} else if (mm->context.asce_limit == (1UL << 31)) {
+		mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
+				   _ASCE_USER_BITS | _ASCE_TYPE_REGION3;
+		break;
+	case 1UL << 53:
+		/* forked 4-level task, set new asce with new mm->pgd */
+		mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
+				   _ASCE_USER_BITS | _ASCE_TYPE_REGION2;
+		break;
+	case 1UL << 31:
+		/* forked 2-level compat task, set new asce with new mm->pgd */
+		mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
+				   _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT;
+		/* pgd_alloc() did not increase mm->nr_pmds */
 		mm_inc_nr_pmds(mm);
 	}
 	crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm));
@@ -42,7 +58,7 @@ static inline int init_new_context(struct task_struct *tsk,
 
 static inline void set_user_asce(struct mm_struct *mm)
 {
-	S390_lowcore.user_asce = mm->context.asce_bits | __pa(mm->pgd);
+	S390_lowcore.user_asce = mm->context.asce;
 	if (current->thread.mm_segment.ar4)
 		__ctl_load(S390_lowcore.user_asce, 7, 7);
 	set_cpu_flag(CIF_ASCE);
@@ -71,7 +87,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 {
 	int cpu = smp_processor_id();
 
-	S390_lowcore.user_asce = next->context.asce_bits | __pa(next->pgd);
+	S390_lowcore.user_asce = next->context.asce;
 	if (prev == next)
 		return;
 	if (MACHINE_HAS_TLB_LC)

arch/s390/include/asm/pci.h

@@ -44,7 +44,8 @@ struct zpci_fmb {
 	u64 rpcit_ops;
 	u64 dma_rbytes;
 	u64 dma_wbytes;
-} __packed __aligned(64);
+	u64 pad[2];
+} __packed __aligned(128);
 
 enum zpci_state {
 	ZPCI_FN_STATE_RESERVED,

arch/s390/include/asm/pgalloc.h

@@ -52,8 +52,8 @@ static inline unsigned long pgd_entry_type(struct mm_struct *mm)
 	return _REGION2_ENTRY_EMPTY;
 }
 
-int crst_table_upgrade(struct mm_struct *, unsigned long limit);
-void crst_table_downgrade(struct mm_struct *, unsigned long limit);
+int crst_table_upgrade(struct mm_struct *);
+void crst_table_downgrade(struct mm_struct *);
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
 {

arch/s390/include/asm/processor.h

@@ -175,7 +175,7 @@ extern __vector128 init_task_fpu_regs[__NUM_VXRS];
 	regs->psw.mask	= PSW_USER_BITS | PSW_MASK_BA;			\
 	regs->psw.addr	= new_psw;					\
 	regs->gprs[15]	= new_stackp;					\
-	crst_table_downgrade(current->mm, 1UL << 31);			\
+	crst_table_downgrade(current->mm);				\
 	execve_tail();							\
 } while (0)
 

arch/s390/include/asm/seccomp.h

@@ -13,4 +13,6 @@
 #define __NR_seccomp_exit_32	__NR_exit
 #define __NR_seccomp_sigreturn_32 __NR_sigreturn
 
+#include <asm-generic/seccomp.h>
+
 #endif	/* _ASM_S390_SECCOMP_H */

arch/s390/include/asm/tlbflush.h

@@ -110,8 +110,7 @@ static inline void __tlb_flush_asce(struct mm_struct *mm, unsigned long asce)
 static inline void __tlb_flush_kernel(void)
 {
 	if (MACHINE_HAS_IDTE)
-		__tlb_flush_idte((unsigned long) init_mm.pgd |
-				 init_mm.context.asce_bits);
+		__tlb_flush_idte(init_mm.context.asce);
 	else
 		__tlb_flush_global();
 }
@@ -133,8 +132,7 @@ static inline void __tlb_flush_asce(struct mm_struct *mm, unsigned long asce)
 static inline void __tlb_flush_kernel(void)
 {
 	if (MACHINE_HAS_TLB_LC)
-		__tlb_flush_idte_local((unsigned long) init_mm.pgd |
-				       init_mm.context.asce_bits);
+		__tlb_flush_idte_local(init_mm.context.asce);
 	else
 		__tlb_flush_local();
 }
@@ -148,8 +146,7 @@ static inline void __tlb_flush_mm(struct mm_struct * mm)
 	 * only ran on the local cpu.
 	 */
 	if (MACHINE_HAS_IDTE && list_empty(&mm->context.gmap_list))
-		__tlb_flush_asce(mm, (unsigned long) mm->pgd |
-				 mm->context.asce_bits);
+		__tlb_flush_asce(mm, mm->context.asce);
 	else
 		__tlb_flush_full(mm);
 }

arch/s390/lib/spinlock.c

@@ -105,6 +105,7 @@ void arch_spin_lock_wait_flags(arch_spinlock_t *lp, unsigned long flags)
 			if (_raw_compare_and_swap(&lp->lock, 0, cpu))
 				return;
 			local_irq_restore(flags);
+			continue;
 		}
 		/* Check if the lock owner is running. */
 		if (first_diag && cpu_is_preempted(~owner)) {

arch/s390/mm/init.c

@@ -89,7 +89,8 @@ void __init paging_init(void)
 		asce_bits = _ASCE_TYPE_REGION3 | _ASCE_TABLE_LENGTH;
 		pgd_type = _REGION3_ENTRY_EMPTY;
 	}
-	S390_lowcore.kernel_asce = (__pa(init_mm.pgd) & PAGE_MASK) | asce_bits;
+	init_mm.context.asce = (__pa(init_mm.pgd) & PAGE_MASK) | asce_bits;
+	S390_lowcore.kernel_asce = init_mm.context.asce;
 	clear_table((unsigned long *) init_mm.pgd, pgd_type,
 		    sizeof(unsigned long)*2048);
 	vmem_map_init();

arch/s390/mm/mmap.c

@@ -174,7 +174,7 @@ int s390_mmap_check(unsigned long addr, unsigned long len, unsigned long flags)
 	if (!(flags & MAP_FIXED))
 		addr = 0;
 	if ((addr + len) >= TASK_SIZE)
-		return crst_table_upgrade(current->mm, TASK_MAX_SIZE);
+		return crst_table_upgrade(current->mm);
 	return 0;
 }
 
@@ -191,7 +191,7 @@ s390_get_unmapped_area(struct file *filp, unsigned long addr,
 		return area;
 	if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < TASK_MAX_SIZE) {
 		/* Upgrade the page table to 4 levels and retry. */
-		rc = crst_table_upgrade(mm, TASK_MAX_SIZE);
+		rc = crst_table_upgrade(mm);
 		if (rc)
 			return (unsigned long) rc;
 		area = arch_get_unmapped_area(filp, addr, len, pgoff, flags);
@@ -213,7 +213,7 @@ s390_get_unmapped_area_topdown(struct file *filp, const unsigned long addr,
 		return area;
 	if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < TASK_MAX_SIZE) {
 		/* Upgrade the page table to 4 levels and retry. */
-		rc = crst_table_upgrade(mm, TASK_MAX_SIZE);
+		rc = crst_table_upgrade(mm);
 		if (rc)
 			return (unsigned long) rc;
 		area = arch_get_unmapped_area_topdown(filp, addr, len,

arch/s390/mm/pgalloc.c

@@ -76,81 +76,52 @@ static void __crst_table_upgrade(void *arg)
 	__tlb_flush_local();
 }
 
-int crst_table_upgrade(struct mm_struct *mm, unsigned long limit)
+int crst_table_upgrade(struct mm_struct *mm)
 {
 	unsigned long *table, *pgd;
-	unsigned long entry;
-	int flush;
 
-	BUG_ON(limit > TASK_MAX_SIZE);
-	flush = 0;
-repeat:
+	/* upgrade should only happen from 3 to 4 levels */
+	BUG_ON(mm->context.asce_limit != (1UL << 42));
+
 	table = crst_table_alloc(mm);
 	if (!table)
 		return -ENOMEM;
+
 	spin_lock_bh(&mm->page_table_lock);
-	if (mm->context.asce_limit < limit) {
-		pgd = (unsigned long *) mm->pgd;
-		if (mm->context.asce_limit <= (1UL << 31)) {
-			entry = _REGION3_ENTRY_EMPTY;
-			mm->context.asce_limit = 1UL << 42;
-			mm->context.asce_bits = _ASCE_TABLE_LENGTH |
-						_ASCE_USER_BITS |
-						_ASCE_TYPE_REGION3;
-		} else {
-			entry = _REGION2_ENTRY_EMPTY;
-			mm->context.asce_limit = 1UL << 53;
-			mm->context.asce_bits = _ASCE_TABLE_LENGTH |
-						_ASCE_USER_BITS |
-						_ASCE_TYPE_REGION2;
-		}
-		crst_table_init(table, entry);
-		pgd_populate(mm, (pgd_t *) table, (pud_t *) pgd);
-		mm->pgd = (pgd_t *) table;
-		mm->task_size = mm->context.asce_limit;
-		table = NULL;
-		flush = 1;
-	}
+	pgd = (unsigned long *) mm->pgd;
+	crst_table_init(table, _REGION2_ENTRY_EMPTY);
+	pgd_populate(mm, (pgd_t *) table, (pud_t *) pgd);
+	mm->pgd = (pgd_t *) table;
+	mm->context.asce_limit = 1UL << 53;
+	mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
+			   _ASCE_USER_BITS | _ASCE_TYPE_REGION2;
+	mm->task_size = mm->context.asce_limit;
 	spin_unlock_bh(&mm->page_table_lock);
-	if (table)
-		crst_table_free(mm, table);
-	if (mm->context.asce_limit < limit)
-		goto repeat;
-	if (flush)
-		on_each_cpu(__crst_table_upgrade, mm, 0);
+
+	on_each_cpu(__crst_table_upgrade, mm, 0);
 	return 0;
 }
 
-void crst_table_downgrade(struct mm_struct *mm, unsigned long limit)
+void crst_table_downgrade(struct mm_struct *mm)
 {
 	pgd_t *pgd;
 
+	/* downgrade should only happen from 3 to 2 levels (compat only) */
+	BUG_ON(mm->context.asce_limit != (1UL << 42));
+
 	if (current->active_mm == mm) {
 		clear_user_asce();
 		__tlb_flush_mm(mm);
 	}
-	while (mm->context.asce_limit > limit) {
-		pgd = mm->pgd;
-		switch (pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) {
-		case _REGION_ENTRY_TYPE_R2:
-			mm->context.asce_limit = 1UL << 42;
-			mm->context.asce_bits = _ASCE_TABLE_LENGTH |
-						_ASCE_USER_BITS |
-						_ASCE_TYPE_REGION3;
-			break;
-		case _REGION_ENTRY_TYPE_R3:
-			mm->context.asce_limit = 1UL << 31;
-			mm->context.asce_bits = _ASCE_TABLE_LENGTH |
-						_ASCE_USER_BITS |
-						_ASCE_TYPE_SEGMENT;
-			break;
-		default:
-			BUG();
-		}
-		mm->pgd = (pgd_t *) (pgd_val(*pgd) & _REGION_ENTRY_ORIGIN);
-		mm->task_size = mm->context.asce_limit;
-		crst_table_free(mm, (unsigned long *) pgd);
-	}
+
+	pgd = mm->pgd;
+	mm->pgd = (pgd_t *) (pgd_val(*pgd) & _REGION_ENTRY_ORIGIN);
+	mm->context.asce_limit = 1UL << 31;
+	mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
+			   _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT;
+	mm->task_size = mm->context.asce_limit;
+	crst_table_free(mm, (unsigned long *) pgd);
+
 	if (current->active_mm == mm)
 		set_user_asce(mm);
 }

arch/s390/pci/pci_dma.c

@@ -457,7 +457,7 @@ int zpci_dma_init_device(struct zpci_dev *zdev)
 	zdev->dma_table = dma_alloc_cpu_table();
 	if (!zdev->dma_table) {
 		rc = -ENOMEM;
-		goto out_clean;
+		goto out;
 	}
 
 	/*
@@ -477,18 +477,22 @@ int zpci_dma_init_device(struct zpci_dev *zdev)
 	zdev->iommu_bitmap = vzalloc(zdev->iommu_pages / 8);
 	if (!zdev->iommu_bitmap) {
 		rc = -ENOMEM;
-		goto out_reg;
+		goto free_dma_table;
 	}
 
 	rc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
 				(u64) zdev->dma_table);
 	if (rc)
-		goto out_reg;
-	return 0;
+		goto free_bitmap;
 
-out_reg:
+	return 0;
+free_bitmap:
+	vfree(zdev->iommu_bitmap);
+	zdev->iommu_bitmap = NULL;
+free_dma_table:
 	dma_free_cpu_table(zdev->dma_table);
-out_clean:
+	zdev->dma_table = NULL;
+out:
 	return rc;
 }
 

arch/x86/crypto/sha-mb/sha1_mb.c

@@ -453,10 +453,10 @@ static int sha_complete_job(struct mcryptd_hash_request_ctx *rctx,
 
 			req = cast_mcryptd_ctx_to_req(req_ctx);
 			if (irqs_disabled())
-				rctx->complete(&req->base, ret);
+				req_ctx->complete(&req->base, ret);
 			else {
 				local_bh_disable();
-				rctx->complete(&req->base, ret);
+				req_ctx->complete(&req->base, ret);
 				local_bh_enable();
 			}
 		}

arch/x86/events/amd/iommu.c

@@ -474,6 +474,7 @@ static __init int _init_perf_amd_iommu(
 
 static struct perf_amd_iommu __perf_iommu = {
 	.pmu = {
+		.task_ctx_nr    = perf_invalid_context,
 		.event_init	= perf_iommu_event_init,
 		.add		= perf_iommu_add,
 		.del		= perf_iommu_del,

arch/x86/events/intel/core.c

@@ -3794,6 +3794,8 @@ __init int intel_pmu_init(void)
 		pr_cont("Knights Landing events, ");
 		break;
 
+	case 142: /* 14nm Kabylake Mobile */
+	case 158: /* 14nm Kabylake Desktop */
 	case 78: /* 14nm Skylake Mobile */
 	case 94: /* 14nm Skylake Desktop */
 	case 85: /* 14nm Skylake Server */

arch/x86/include/asm/hugetlb.h

@@ -4,6 +4,7 @@
 #include <asm/page.h>
 #include <asm-generic/hugetlb.h>
 
+#define hugepages_supported() cpu_has_pse
 
 static inline int is_hugepage_only_range(struct mm_struct *mm,
 					 unsigned long addr,

arch/x86/kernel/apic/vector.c

@@ -256,7 +256,8 @@ static void clear_irq_vector(int irq, struct apic_chip_data *data)
 	struct irq_desc *desc;
 	int cpu, vector;
 
-	BUG_ON(!data->cfg.vector);
+	if (!data->cfg.vector)
+		return;
 
 	vector = data->cfg.vector;
 	for_each_cpu_and(cpu, data->domain, cpu_online_mask)

arch/x86/kernel/cpu/mshyperv.c

@@ -152,6 +152,11 @@ static struct clocksource hyperv_cs = {
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
+static unsigned char hv_get_nmi_reason(void)
+{
+	return 0;
+}
+
 static void __init ms_hyperv_init_platform(void)
 {
 	/*
@@ -191,6 +196,13 @@ static void __init ms_hyperv_init_platform(void)
 	machine_ops.crash_shutdown = hv_machine_crash_shutdown;
 #endif
 	mark_tsc_unstable("running on Hyper-V");
+
+	/*
+	 * Generation 2 instances don't support reading the NMI status from
+	 * 0x61 port.
+	 */
+	if (efi_enabled(EFI_BOOT))
+		x86_platform.get_nmi_reason = hv_get_nmi_reason;
 }
 
 const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {

arch/x86/kernel/head_32.S

@@ -389,12 +389,6 @@ default_entry:
 	/* Make changes effective */
 	wrmsr
 
-	/*
-	 * And make sure that all the mappings we set up have NX set from
-	 * the beginning.
-	 */
-	orl $(1 << (_PAGE_BIT_NX - 32)), pa(__supported_pte_mask + 4)
-
 enable_paging:
 
 /*

arch/x86/mm/setup_nx.c

@@ -32,8 +32,9 @@ early_param("noexec", noexec_setup);
 
 void x86_configure_nx(void)
 {
-	/* If disable_nx is set, clear NX on all new mappings going forward. */
-	if (disable_nx)
+	if (boot_cpu_has(X86_FEATURE_NX) && !disable_nx)
+		__supported_pte_mask |= _PAGE_NX;
+	else
 		__supported_pte_mask &= ~_PAGE_NX;
 }
 

arch/x86/xen/spinlock.c

@@ -27,6 +27,12 @@ static bool xen_pvspin = true;
 
 static void xen_qlock_kick(int cpu)
 {
+	int irq = per_cpu(lock_kicker_irq, cpu);
+
+	/* Don't kick if the target's kicker interrupt is not initialized. */
+	if (irq == -1)
+		return;
+
 	xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR);
 }
 

crypto/rsa-pkcs1pad.c

@@ -387,16 +387,16 @@ static int pkcs1pad_decrypt(struct akcipher_request *req)
 	req_ctx->child_req.src = req->src;
 	req_ctx->child_req.src_len = req->src_len;
 	req_ctx->child_req.dst = req_ctx->out_sg;
-	req_ctx->child_req.dst_len = ctx->key_size - 1;
+	req_ctx->child_req.dst_len = ctx->key_size ;
 
-	req_ctx->out_buf = kmalloc(ctx->key_size - 1,
+	req_ctx->out_buf = kmalloc(ctx->key_size,
 			(req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
 			GFP_KERNEL : GFP_ATOMIC);
 	if (!req_ctx->out_buf)
 		return -ENOMEM;
 
 	pkcs1pad_sg_set_buf(req_ctx->out_sg, req_ctx->out_buf,
-			ctx->key_size - 1, NULL);
+			    ctx->key_size, NULL);
 
 	akcipher_request_set_tfm(&req_ctx->child_req, ctx->child);
 	akcipher_request_set_callback(&req_ctx->child_req, req->base.flags,
@@ -595,16 +595,16 @@ static int pkcs1pad_verify(struct akcipher_request *req)
 	req_ctx->child_req.src = req->src;
 	req_ctx->child_req.src_len = req->src_len;
 	req_ctx->child_req.dst = req_ctx->out_sg;
-	req_ctx->child_req.dst_len = ctx->key_size - 1;
+	req_ctx->child_req.dst_len = ctx->key_size;
 
-	req_ctx->out_buf = kmalloc(ctx->key_size - 1,
+	req_ctx->out_buf = kmalloc(ctx->key_size,
 			(req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
 			GFP_KERNEL : GFP_ATOMIC);
 	if (!req_ctx->out_buf)
 		return -ENOMEM;
 
 	pkcs1pad_sg_set_buf(req_ctx->out_sg, req_ctx->out_buf,
-			ctx->key_size - 1, NULL);
+			    ctx->key_size, NULL);
 
 	akcipher_request_set_tfm(&req_ctx->child_req, ctx->child);
 	akcipher_request_set_callback(&req_ctx->child_req, req->base.flags,

drivers/bcma/main.c

@@ -136,7 +136,6 @@ static bool bcma_is_core_needed_early(u16 core_id)
 	return false;
 }
 
-#if defined(CONFIG_OF) && defined(CONFIG_OF_ADDRESS)
 static struct device_node *bcma_of_find_child_device(struct platform_device *parent,
 						     struct bcma_device *core)
 {
@@ -184,7 +183,7 @@ static unsigned int bcma_of_get_irq(struct platform_device *parent,
 	struct of_phandle_args out_irq;
 	int ret;
 
-	if (!parent || !parent->dev.of_node)
+	if (!IS_ENABLED(CONFIG_OF_IRQ) || !parent || !parent->dev.of_node)
 		return 0;
 
 	ret = bcma_of_irq_parse(parent, core, &out_irq, num);
@@ -202,23 +201,15 @@ static void bcma_of_fill_device(struct platform_device *parent,
 {
 	struct device_node *node;
 
+	if (!IS_ENABLED(CONFIG_OF_IRQ))
+		return;
+
 	node = bcma_of_find_child_device(parent, core);
 	if (node)
 		core->dev.of_node = node;
 
 	core->irq = bcma_of_get_irq(parent, core, 0);
 }
-#else
-static void bcma_of_fill_device(struct platform_device *parent,
-				struct bcma_device *core)
-{
-}
-static inline unsigned int bcma_of_get_irq(struct platform_device *parent,
-					   struct bcma_device *core, int num)
-{
-	return 0;
-}
-#endif /* CONFIG_OF */
 
 unsigned int bcma_core_irq(struct bcma_device *core, int num)
 {

drivers/block/rbd.c

@@ -538,7 +538,6 @@ static int _rbd_dev_v2_snap_size(struct rbd_device *rbd_dev, u64 snap_id,
 				u8 *order, u64 *snap_size);
 static int _rbd_dev_v2_snap_features(struct rbd_device *rbd_dev, u64 snap_id,
 		u64 *snap_features);
-static u64 rbd_snap_id_by_name(struct rbd_device *rbd_dev, const char *name);
 
 static int rbd_open(struct block_device *bdev, fmode_t mode)
 {
@@ -3127,9 +3126,6 @@ static void rbd_watch_cb(u64 ver, u64 notify_id, u8 opcode, void *data)
 	struct rbd_device *rbd_dev = (struct rbd_device *)data;
 	int ret;
 
-	if (!rbd_dev)
-		return;
-
 	dout("%s: \"%s\" notify_id %llu opcode %u\n", __func__,
 		rbd_dev->header_name, (unsigned long long)notify_id,
 		(unsigned int)opcode);
@@ -3263,6 +3259,9 @@ static void rbd_dev_header_unwatch_sync(struct rbd_device *rbd_dev)
 
 	ceph_osdc_cancel_event(rbd_dev->watch_event);
 	rbd_dev->watch_event = NULL;
+
+	dout("%s flushing notifies\n", __func__);
+	ceph_osdc_flush_notifies(&rbd_dev->rbd_client->client->osdc);
 }
 
 /*
@@ -3642,21 +3641,14 @@ static void rbd_exists_validate(struct rbd_device *rbd_dev)
 static void rbd_dev_update_size(struct rbd_device *rbd_dev)
 {
 	sector_t size;
-	bool removing;
 
 	/*
-	 * Don't hold the lock while doing disk operations,
-	 * or lock ordering will conflict with the bdev mutex via:
-	 * rbd_add() -> blkdev_get() -> rbd_open()
+	 * If EXISTS is not set, rbd_dev->disk may be NULL, so don't
+	 * try to update its size.  If REMOVING is set, updating size
+	 * is just useless work since the device can't be opened.
 	 */
-	spin_lock_irq(&rbd_dev->lock);
-	removing = test_bit(RBD_DEV_FLAG_REMOVING, &rbd_dev->flags);
-	spin_unlock_irq(&rbd_dev->lock);
-	/*
-	 * If the device is being removed, rbd_dev->disk has
-	 * been destroyed, so don't try to update its size
-	 */
-	if (!removing) {
+	if (test_bit(RBD_DEV_FLAG_EXISTS, &rbd_dev->flags) &&
+	    !test_bit(RBD_DEV_FLAG_REMOVING, &rbd_dev->flags)) {
 		size = (sector_t)rbd_dev->mapping.size / SECTOR_SIZE;
 		dout("setting size to %llu sectors", (unsigned long long)size);
 		set_capacity(rbd_dev->disk, size);
@@ -4191,7 +4183,7 @@ static int _rbd_dev_v2_snap_features(struct rbd_device *rbd_dev, u64 snap_id,
 		__le64 features;
 		__le64 incompat;
 	} __attribute__ ((packed)) features_buf = { 0 };
-	u64 incompat;
+	u64 unsup;
 	int ret;
 
 	ret = rbd_obj_method_sync(rbd_dev, rbd_dev->header_name,
@@ -4204,9 +4196,12 @@ static int _rbd_dev_v2_snap_features(struct rbd_device *rbd_dev, u64 snap_id,
 	if (ret < sizeof (features_buf))
 		return -ERANGE;
 
-	incompat = le64_to_cpu(features_buf.incompat);
-	if (incompat & ~RBD_FEATURES_SUPPORTED)
+	unsup = le64_to_cpu(features_buf.incompat) & ~RBD_FEATURES_SUPPORTED;
+	if (unsup) {
+		rbd_warn(rbd_dev, "image uses unsupported features: 0x%llx",
+			 unsup);
 		return -ENXIO;
+	}
 
 	*snap_features = le64_to_cpu(features_buf.features);
 
@@ -5187,6 +5182,10 @@ static int rbd_dev_probe_parent(struct rbd_device *rbd_dev, int depth)
 	return ret;
 }
 
+/*
+ * rbd_dev->header_rwsem must be locked for write and will be unlocked
+ * upon return.
+ */
 static int rbd_dev_device_setup(struct rbd_device *rbd_dev)
 {
 	int ret;
@@ -5195,7 +5194,7 @@ static int rbd_dev_device_setup(struct rbd_device *rbd_dev)
 
 	ret = rbd_dev_id_get(rbd_dev);
 	if (ret)
-		return ret;
+		goto err_out_unlock;
 
 	BUILD_BUG_ON(DEV_NAME_LEN
 			< sizeof (RBD_DRV_NAME) + MAX_INT_FORMAT_WIDTH);
@@ -5236,8 +5235,9 @@ static int rbd_dev_device_setup(struct rbd_device *rbd_dev)
 	/* Everything's ready.  Announce the disk to the world. */
 
 	set_bit(RBD_DEV_FLAG_EXISTS, &rbd_dev->flags);
-	add_disk(rbd_dev->disk);
+	up_write(&rbd_dev->header_rwsem);
 
+	add_disk(rbd_dev->disk);
 	pr_info("%s: added with size 0x%llx\n", rbd_dev->disk->disk_name,
 		(unsigned long long) rbd_dev->mapping.size);
 
@@ -5252,6 +5252,8 @@ static int rbd_dev_device_setup(struct rbd_device *rbd_dev)
 		unregister_blkdev(rbd_dev->major, rbd_dev->name);
 err_out_id:
 	rbd_dev_id_put(rbd_dev);
+err_out_unlock:
+	up_write(&rbd_dev->header_rwsem);
 	return ret;
 }
 
@@ -5442,6 +5444,7 @@ static ssize_t do_rbd_add(struct bus_type *bus,
 	spec = NULL;		/* rbd_dev now owns this */
 	rbd_opts = NULL;	/* rbd_dev now owns this */
 
+	down_write(&rbd_dev->header_rwsem);
 	rc = rbd_dev_image_probe(rbd_dev, 0);
 	if (rc < 0)
 		goto err_out_rbd_dev;
@@ -5471,6 +5474,7 @@ static ssize_t do_rbd_add(struct bus_type *bus,
 	return rc;
 
 err_out_rbd_dev:
+	up_write(&rbd_dev->header_rwsem);
 	rbd_dev_destroy(rbd_dev);
 err_out_client:
 	rbd_put_client(rbdc);
@@ -5577,12 +5581,6 @@ static ssize_t do_rbd_remove(struct bus_type *bus,
 		return ret;
 
 	rbd_dev_header_unwatch_sync(rbd_dev);
-	/*
-	 * flush remaining watch callbacks - these must be complete
-	 * before the osd_client is shutdown
-	 */
-	dout("%s: flushing notifies", __func__);
-	ceph_osdc_flush_notifies(&rbd_dev->rbd_client->client->osdc);
 
 	/*
 	 * Don't free anything from rbd_dev->disk until after all

drivers/clocksource/tango_xtal.c

@@ -42,7 +42,7 @@ static void __init tango_clocksource_init(struct device_node *np)
 
 	ret = clocksource_mmio_init(xtal_in_cnt, "tango-xtal", xtal_freq, 350,
 				    32, clocksource_mmio_readl_up);
-	if (!ret) {
+	if (ret) {
 		pr_err("%s: registration failed\n", np->full_name);
 		return;
 	}

drivers/cpufreq/cpufreq.c

@@ -1491,6 +1491,9 @@ static unsigned int cpufreq_update_current_freq(struct cpufreq_policy *policy)
 {
 	unsigned int new_freq;
 
+	if (cpufreq_suspended)
+		return 0;
+
 	new_freq = cpufreq_driver->get(policy->cpu);
 	if (!new_freq)
 		return 0;

drivers/cpufreq/cpufreq_governor.c

@@ -193,12 +193,8 @@ unsigned int dbs_update(struct cpufreq_policy *policy)
 		wall_time = cur_wall_time - j_cdbs->prev_cpu_wall;
 		j_cdbs->prev_cpu_wall = cur_wall_time;
 
-		if (cur_idle_time <= j_cdbs->prev_cpu_idle) {
-			idle_time = 0;
-		} else {
-			idle_time = cur_idle_time - j_cdbs->prev_cpu_idle;
-			j_cdbs->prev_cpu_idle = cur_idle_time;
-		}
+		idle_time = cur_idle_time - j_cdbs->prev_cpu_idle;
+		j_cdbs->prev_cpu_idle = cur_idle_time;
 
 		if (ignore_nice) {
 			u64 cur_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];

drivers/cpufreq/intel_pstate.c

@@ -813,6 +813,11 @@ static int core_get_max_pstate(void)
 			if (err)
 				goto skip_tar;
 
+			/* For level 1 and 2, bits[23:16] contain the ratio */
+			if (tdp_ctrl)
+				tdp_ratio >>= 16;
+
+			tdp_ratio &= 0xff; /* ratios are only 8 bits long */
 			if (tdp_ratio - 1 == tar) {
 				max_pstate = tar;
 				pr_debug("max_pstate=TAC %x\n", max_pstate);
@@ -1130,6 +1135,10 @@ static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu)
 		sample_ratio = div_fp(int_tofp(pid_params.sample_rate_ns),
 				      int_tofp(duration_ns));
 		core_busy = mul_fp(core_busy, sample_ratio);
+	} else {
+		sample_ratio = div_fp(100 * cpu->sample.mperf, cpu->sample.tsc);
+		if (sample_ratio < int_tofp(1))
+			core_busy = 0;
 	}
 
 	cpu->sample.busy_scaled = core_busy;

drivers/crypto/ccp/ccp-crypto-aes-cmac.c

@@ -225,6 +225,9 @@ static int ccp_aes_cmac_export(struct ahash_request *req, void *out)
 	struct ccp_aes_cmac_req_ctx *rctx = ahash_request_ctx(req);
 	struct ccp_aes_cmac_exp_ctx state;
 
+	/* Don't let anything leak to 'out' */
+	memset(&state, 0, sizeof(state));
+
 	state.null_msg = rctx->null_msg;
 	memcpy(state.iv, rctx->iv, sizeof(state.iv));
 	state.buf_count = rctx->buf_count;

drivers/crypto/ccp/ccp-crypto-sha.c

@@ -212,6 +212,9 @@ static int ccp_sha_export(struct ahash_request *req, void *out)
 	struct ccp_sha_req_ctx *rctx = ahash_request_ctx(req);
 	struct ccp_sha_exp_ctx state;
 
+	/* Don't let anything leak to 'out' */
+	memset(&state, 0, sizeof(state));
+
 	state.type = rctx->type;
 	state.msg_bits = rctx->msg_bits;
 	state.first = rctx->first;

drivers/crypto/talitos.c

@@ -63,6 +63,14 @@ static void to_talitos_ptr(struct talitos_ptr *ptr, dma_addr_t dma_addr,
 		ptr->eptr = upper_32_bits(dma_addr);
 }
 
+static void copy_talitos_ptr(struct talitos_ptr *dst_ptr,
+			     struct talitos_ptr *src_ptr, bool is_sec1)
+{
+	dst_ptr->ptr = src_ptr->ptr;
+	if (!is_sec1)
+		dst_ptr->eptr = src_ptr->eptr;
+}
+
 static void to_talitos_ptr_len(struct talitos_ptr *ptr, unsigned int len,
 			       bool is_sec1)
 {
@@ -1083,21 +1091,20 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 	sg_count = dma_map_sg(dev, areq->src, edesc->src_nents ?: 1,
 			      (areq->src == areq->dst) ? DMA_BIDIRECTIONAL
 							   : DMA_TO_DEVICE);
-
 	/* hmac data */
 	desc->ptr[1].len = cpu_to_be16(areq->assoclen);
 	if (sg_count > 1 &&
 	    (ret = sg_to_link_tbl_offset(areq->src, sg_count, 0,
 					 areq->assoclen,
 					 &edesc->link_tbl[tbl_off])) > 1) {
-		tbl_off += ret;
-
 		to_talitos_ptr(&desc->ptr[1], edesc->dma_link_tbl + tbl_off *
 			       sizeof(struct talitos_ptr), 0);
 		desc->ptr[1].j_extent = DESC_PTR_LNKTBL_JUMP;
 
 		dma_sync_single_for_device(dev, edesc->dma_link_tbl,
 					   edesc->dma_len, DMA_BIDIRECTIONAL);
+
+		tbl_off += ret;
 	} else {
 		to_talitos_ptr(&desc->ptr[1], sg_dma_address(areq->src), 0);
 		desc->ptr[1].j_extent = 0;
@@ -1126,11 +1133,13 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 	if (edesc->desc.hdr & DESC_HDR_MODE1_MDEU_CICV)
 		sg_link_tbl_len += authsize;
 
-	if (sg_count > 1 &&
-	    (ret = sg_to_link_tbl_offset(areq->src, sg_count, areq->assoclen,
-					 sg_link_tbl_len,
-					 &edesc->link_tbl[tbl_off])) > 1) {
-		tbl_off += ret;
+	if (sg_count == 1) {
+		to_talitos_ptr(&desc->ptr[4], sg_dma_address(areq->src) +
+			       areq->assoclen, 0);
+	} else if ((ret = sg_to_link_tbl_offset(areq->src, sg_count,
+						areq->assoclen, sg_link_tbl_len,
+						&edesc->link_tbl[tbl_off])) >
+		   1) {
 		desc->ptr[4].j_extent |= DESC_PTR_LNKTBL_JUMP;
 		to_talitos_ptr(&desc->ptr[4], edesc->dma_link_tbl +
 					      tbl_off *
@@ -1138,8 +1147,10 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 		dma_sync_single_for_device(dev, edesc->dma_link_tbl,
 					   edesc->dma_len,
 					   DMA_BIDIRECTIONAL);
-	} else
-		to_talitos_ptr(&desc->ptr[4], sg_dma_address(areq->src), 0);
+		tbl_off += ret;
+	} else {
+		copy_talitos_ptr(&desc->ptr[4], &edesc->link_tbl[tbl_off], 0);
+	}
 
 	/* cipher out */
 	desc->ptr[5].len = cpu_to_be16(cryptlen);
@@ -1151,11 +1162,13 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 
 	edesc->icv_ool = false;
 
-	if (sg_count > 1 &&
-	    (sg_count = sg_to_link_tbl_offset(areq->dst, sg_count,
+	if (sg_count == 1) {
+		to_talitos_ptr(&desc->ptr[5], sg_dma_address(areq->dst) +
+			       areq->assoclen, 0);
+	} else if ((sg_count =
+			sg_to_link_tbl_offset(areq->dst, sg_count,
 					      areq->assoclen, cryptlen,
-					      &edesc->link_tbl[tbl_off])) >
-	    1) {
+					      &edesc->link_tbl[tbl_off])) > 1) {
 		struct talitos_ptr *tbl_ptr = &edesc->link_tbl[tbl_off];
 
 		to_talitos_ptr(&desc->ptr[5], edesc->dma_link_tbl +
@@ -1178,8 +1191,9 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 					   edesc->dma_len, DMA_BIDIRECTIONAL);
 
 		edesc->icv_ool = true;
-	} else
-		to_talitos_ptr(&desc->ptr[5], sg_dma_address(areq->dst), 0);
+	} else {
+		copy_talitos_ptr(&desc->ptr[5], &edesc->link_tbl[tbl_off], 0);
+	}
 
 	/* iv out */
 	map_single_talitos_ptr(dev, &desc->ptr[6], ivsize, ctx->iv,
@@ -2629,21 +2643,11 @@ struct talitos_crypto_alg {
 	struct talitos_alg_template algt;
 };
 
-static int talitos_cra_init(struct crypto_tfm *tfm)
+static int talitos_init_common(struct talitos_ctx *ctx,
+			       struct talitos_crypto_alg *talitos_alg)
 {
-	struct crypto_alg *alg = tfm->__crt_alg;
-	struct talitos_crypto_alg *talitos_alg;
-	struct talitos_ctx *ctx = crypto_tfm_ctx(tfm);
 	struct talitos_private *priv;
 
-	if ((alg->cra_flags & CRYPTO_ALG_TYPE_MASK) == CRYPTO_ALG_TYPE_AHASH)
-		talitos_alg = container_of(__crypto_ahash_alg(alg),
-					   struct talitos_crypto_alg,
-					   algt.alg.hash);
-	else
-		talitos_alg = container_of(alg, struct talitos_crypto_alg,
-					   algt.alg.crypto);
-
 	/* update context with ptr to dev */
 	ctx->dev = talitos_alg->dev;
 
@@ -2661,10 +2665,33 @@ static int talitos_cra_init(struct crypto_tfm *tfm)
 	return 0;
 }
 
+static int talitos_cra_init(struct crypto_tfm *tfm)
+{
+	struct crypto_alg *alg = tfm->__crt_alg;
+	struct talitos_crypto_alg *talitos_alg;
+	struct talitos_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if ((alg->cra_flags & CRYPTO_ALG_TYPE_MASK) == CRYPTO_ALG_TYPE_AHASH)
+		talitos_alg = container_of(__crypto_ahash_alg(alg),
+					   struct talitos_crypto_alg,
+					   algt.alg.hash);
+	else
+		talitos_alg = container_of(alg, struct talitos_crypto_alg,
+					   algt.alg.crypto);
+
+	return talitos_init_common(ctx, talitos_alg);
+}
+
 static int talitos_cra_init_aead(struct crypto_aead *tfm)
 {
-	talitos_cra_init(crypto_aead_tfm(tfm));
-	return 0;
+	struct aead_alg *alg = crypto_aead_alg(tfm);
+	struct talitos_crypto_alg *talitos_alg;
+	struct talitos_ctx *ctx = crypto_aead_ctx(tfm);
+
+	talitos_alg = container_of(alg, struct talitos_crypto_alg,
+				   algt.alg.aead);
+
+	return talitos_init_common(ctx, talitos_alg);
 }
 
 static int talitos_cra_init_ahash(struct crypto_tfm *tfm)

drivers/edac/i7core_edac.c

@@ -1866,7 +1866,7 @@ static int i7core_mce_check_error(struct notifier_block *nb, unsigned long val,
 
 	i7_dev = get_i7core_dev(mce->socketid);
 	if (!i7_dev)
-		return NOTIFY_BAD;
+		return NOTIFY_DONE;
 
 	mci = i7_dev->mci;
 	pvt = mci->pvt_info;

drivers/edac/sb_edac.c

@@ -362,6 +362,7 @@ struct sbridge_pvt {
 
 	/* Memory type detection */
 	bool			is_mirrored, is_lockstep, is_close_pg;
+	bool			is_chan_hash;
 
 	/* Fifo double buffers */
 	struct mce		mce_entry[MCE_LOG_LEN];
@@ -1060,6 +1061,20 @@ static inline u8 sad_pkg_ha(u8 pkg)
 	return (pkg >> 2) & 0x1;
 }
 
+static int haswell_chan_hash(int idx, u64 addr)
+{
+	int i;
+
+	/*
+	 * XOR even bits from 12:26 to bit0 of idx,
+	 *     odd bits from 13:27 to bit1
+	 */
+	for (i = 12; i < 28; i += 2)
+		idx ^= (addr >> i) & 3;
+
+	return idx;
+}
+
 /****************************************************************************
 			Memory check routines
  ****************************************************************************/
@@ -1616,6 +1631,10 @@ static int get_dimm_config(struct mem_ctl_info *mci)
 		KNL_MAX_CHANNELS : NUM_CHANNELS;
 	u64 knl_mc_sizes[KNL_MAX_CHANNELS];
 
+	if (pvt->info.type == HASWELL || pvt->info.type == BROADWELL) {
+		pci_read_config_dword(pvt->pci_ha0, HASWELL_HASYSDEFEATURE2, &reg);
+		pvt->is_chan_hash = GET_BITFIELD(reg, 21, 21);
+	}
 	if (pvt->info.type == HASWELL || pvt->info.type == BROADWELL ||
 			pvt->info.type == KNIGHTS_LANDING)
 		pci_read_config_dword(pvt->pci_sad1, SAD_TARGET, &reg);
@@ -2118,12 +2137,15 @@ static int get_memory_error_data(struct mem_ctl_info *mci,
 	}
 
 	ch_way = TAD_CH(reg) + 1;
-	sck_way = 1 << TAD_SOCK(reg);
+	sck_way = TAD_SOCK(reg);
 
 	if (ch_way == 3)
 		idx = addr >> 6;
-	else
+	else {
 		idx = (addr >> (6 + sck_way + shiftup)) & 0x3;
+		if (pvt->is_chan_hash)
+			idx = haswell_chan_hash(idx, addr);
+	}
 	idx = idx % ch_way;
 
 	/*
@@ -2157,7 +2179,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci,
 		switch(ch_way) {
 		case 2:
 		case 4:
-			sck_xch = 1 << sck_way * (ch_way >> 1);
+			sck_xch = (1 << sck_way) * (ch_way >> 1);
 			break;
 		default:
 			sprintf(msg, "Invalid mirror set. Can't decode addr");
@@ -2193,7 +2215,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci,
 
 	ch_addr = addr - offset;
 	ch_addr >>= (6 + shiftup);
-	ch_addr /= ch_way * sck_way;
+	ch_addr /= sck_xch;
 	ch_addr <<= (6 + shiftup);
 	ch_addr |= addr & ((1 << (6 + shiftup)) - 1);
 
@@ -3146,7 +3168,7 @@ static int sbridge_mce_check_error(struct notifier_block *nb, unsigned long val,
 
 	mci = get_mci_for_node_id(mce->socketid);
 	if (!mci)
-		return NOTIFY_BAD;
+		return NOTIFY_DONE;
 	pvt = mci->pvt_info;
 
 	/*

drivers/firmware/efi/vars.c

@@ -202,29 +202,44 @@ static const struct variable_validate variable_validate[] = {
 	{ NULL_GUID, "", NULL },
 };
 
+/*
+ * Check if @var_name matches the pattern given in @match_name.
+ *
+ * @var_name: an array of @len non-NUL characters.
+ * @match_name: a NUL-terminated pattern string, optionally ending in "*". A
+ *              final "*" character matches any trailing characters @var_name,
+ *              including the case when there are none left in @var_name.
+ * @match: on output, the number of non-wildcard characters in @match_name
+ *         that @var_name matches, regardless of the return value.
+ * @return: whether @var_name fully matches @match_name.
+ */
 static bool
 variable_matches(const char *var_name, size_t len, const char *match_name,
 		 int *match)
 {
 	for (*match = 0; ; (*match)++) {
 		char c = match_name[*match];
-		char u = var_name[*match];
 
-		/* Wildcard in the matching name means we've matched */
-		if (c == '*')
+		switch (c) {
+		case '*':
+			/* Wildcard in @match_name means we've matched. */
 			return true;
 
-		/* Case sensitive match */
-		if (!c && *match == len)
-			return true;
+		case '\0':
+			/* @match_name has ended. Has @var_name too? */
+			return (*match == len);
 
-		if (c != u)
+		default:
+			/*
+			 * We've reached a non-wildcard char in @match_name.
+			 * Continue only if there's an identical character in
+			 * @var_name.
+			 */
+			if (*match < len && c == var_name[*match])
+				continue;
 			return false;
-
-		if (!c)
-			return true;
+		}
 	}
-	return true;
 }
 
 bool

drivers/firmware/psci.c

@@ -360,7 +360,7 @@ static struct cpuidle_ops psci_cpuidle_ops __initdata = {
 	.init = psci_dt_cpu_init_idle,
 };
 
-CPUIDLE_METHOD_OF_DECLARE(psci, "arm,psci", &psci_cpuidle_ops);
+CPUIDLE_METHOD_OF_DECLARE(psci, "psci", &psci_cpuidle_ops);
 #endif
 #endif
 

drivers/gpu/drm/amd/amdgpu/amdgpu.h

@@ -1591,6 +1591,7 @@ struct amdgpu_uvd {
 	struct amdgpu_bo	*vcpu_bo;
 	void			*cpu_addr;
 	uint64_t		gpu_addr;
+	unsigned		fw_version;
 	void			*saved_bo;
 	atomic_t		handles[AMDGPU_MAX_UVD_HANDLES];
 	struct drm_file		*filp[AMDGPU_MAX_UVD_HANDLES];

drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c

@@ -425,6 +425,10 @@ static int acp_resume(void *handle)
 	struct acp_pm_domain *apd;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	/* return early if no ACP */
+	if (!adev->acp.acp_genpd)
+		return 0;
+
 	/* SMU block will power on ACP irrespective of ACP runtime status.
 	 * Power off explicitly based on genpd ACP runtime status so that ACP
 	 * hw and ACP-genpd status are in sync.

drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c

@@ -63,10 +63,6 @@ bool amdgpu_has_atpx(void) {
 	return amdgpu_atpx_priv.atpx_detected;
 }
 
-bool amdgpu_has_atpx_dgpu_power_cntl(void) {
-	return amdgpu_atpx_priv.atpx.functions.power_cntl;
-}
-
 /**
  * amdgpu_atpx_call - call an ATPX method
  *
@@ -146,6 +142,13 @@ static void amdgpu_atpx_parse_functions(struct amdgpu_atpx_functions *f, u32 mas
  */
 static int amdgpu_atpx_validate(struct amdgpu_atpx *atpx)
 {
+	/* make sure required functions are enabled */
+	/* dGPU power control is required */
+	if (atpx->functions.power_cntl == false) {
+		printk("ATPX dGPU power cntl not present, forcing\n");
+		atpx->functions.power_cntl = true;
+	}
+
 	if (atpx->functions.px_params) {
 		union acpi_object *info;
 		struct atpx_px_params output;

drivers/gpu/drm/amd/amdgpu/amdgpu_device.c

@@ -62,12 +62,6 @@ static const char *amdgpu_asic_name[] = {
 	"LAST",
 };
 
-#if defined(CONFIG_VGA_SWITCHEROO)
-bool amdgpu_has_atpx_dgpu_power_cntl(void);
-#else
-static inline bool amdgpu_has_atpx_dgpu_power_cntl(void) { return false; }
-#endif
-
 bool amdgpu_device_is_px(struct drm_device *dev)
 {
 	struct amdgpu_device *adev = dev->dev_private;
@@ -1485,7 +1479,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 
 	if (amdgpu_runtime_pm == 1)
 		runtime = true;
-	if (amdgpu_device_is_px(ddev) && amdgpu_has_atpx_dgpu_power_cntl())
+	if (amdgpu_device_is_px(ddev))
 		runtime = true;
 	vga_switcheroo_register_client(adev->pdev, &amdgpu_switcheroo_ops, runtime);
 	if (runtime)

drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c

@@ -303,7 +303,7 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 			fw_info.feature = adev->vce.fb_version;
 			break;
 		case AMDGPU_INFO_FW_UVD:
-			fw_info.ver = 0;
+			fw_info.ver = adev->uvd.fw_version;
 			fw_info.feature = 0;
 			break;
 		case AMDGPU_INFO_FW_GMC:

drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h

@@ -53,7 +53,7 @@ struct amdgpu_hpd;
 
 #define AMDGPU_MAX_HPD_PINS 6
 #define AMDGPU_MAX_CRTCS 6
-#define AMDGPU_MAX_AFMT_BLOCKS 7
+#define AMDGPU_MAX_AFMT_BLOCKS 9
 
 enum amdgpu_rmx_type {
 	RMX_OFF,
@@ -309,8 +309,8 @@ struct amdgpu_mode_info {
 	struct atom_context *atom_context;
 	struct card_info *atom_card_info;
 	bool mode_config_initialized;
-	struct amdgpu_crtc *crtcs[6];
-	struct amdgpu_afmt *afmt[7];
+	struct amdgpu_crtc *crtcs[AMDGPU_MAX_CRTCS];
+	struct amdgpu_afmt *afmt[AMDGPU_MAX_AFMT_BLOCKS];
 	/* DVI-I properties */
 	struct drm_property *coherent_mode_property;
 	/* DAC enable load detect */

drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c

@@ -223,6 +223,8 @@ static int amdgpu_verify_access(struct ttm_buffer_object *bo, struct file *filp)
 {
 	struct amdgpu_bo *rbo = container_of(bo, struct amdgpu_bo, tbo);
 
+	if (amdgpu_ttm_tt_get_usermm(bo->ttm))
+		return -EPERM;
 	return drm_vma_node_verify_access(&rbo->gem_base.vma_node, filp);
 }
 

drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c

@@ -158,6 +158,9 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
 	DRM_INFO("Found UVD firmware Version: %hu.%hu Family ID: %hu\n",
 		version_major, version_minor, family_id);
 
+	adev->uvd.fw_version = ((version_major << 24) | (version_minor << 16) |
+				(family_id << 8));
+
 	bo_size = AMDGPU_GPU_PAGE_ALIGN(le32_to_cpu(hdr->ucode_size_bytes) + 8)
 		 +  AMDGPU_UVD_STACK_SIZE + AMDGPU_UVD_HEAP_SIZE;
 	r = amdgpu_bo_create(adev, bo_size, PAGE_SIZE, true,
@@ -255,6 +258,8 @@ int amdgpu_uvd_suspend(struct amdgpu_device *adev)
 	if (i == AMDGPU_MAX_UVD_HANDLES)
 		return 0;
 
+	cancel_delayed_work_sync(&adev->uvd.idle_work);
+
 	size = amdgpu_bo_size(adev->uvd.vcpu_bo);
 	ptr = adev->uvd.cpu_addr;
 

drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c

@@ -234,6 +234,7 @@ int amdgpu_vce_suspend(struct amdgpu_device *adev)
 	if (i == AMDGPU_MAX_VCE_HANDLES)
 		return 0;
 
+	cancel_delayed_work_sync(&adev->vce.idle_work);
 	/* TODO: suspending running encoding sessions isn't supported */
 	return -EINVAL;
 }

drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c

@@ -910,7 +910,10 @@ static int gmc_v7_0_late_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	return amdgpu_irq_get(adev, &adev->mc.vm_fault, 0);
+	if (amdgpu_vm_fault_stop != AMDGPU_VM_FAULT_STOP_ALWAYS)
+		return amdgpu_irq_get(adev, &adev->mc.vm_fault, 0);
+	else
+		return 0;
 }
 
 static int gmc_v7_0_sw_init(void *handle)

drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c

@@ -870,7 +870,10 @@ static int gmc_v8_0_late_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	return amdgpu_irq_get(adev, &adev->mc.vm_fault, 0);
+	if (amdgpu_vm_fault_stop != AMDGPU_VM_FAULT_STOP_ALWAYS)
+		return amdgpu_irq_get(adev, &adev->mc.vm_fault, 0);
+	else
+		return 0;
 }
 
 #define mmMC_SEQ_MISC0_FIJI 0xA71

drivers/gpu/drm/drm_dp_mst_topology.c

@@ -1672,13 +1672,19 @@ static int drm_dp_payload_send_msg(struct drm_dp_mst_topology_mgr *mgr,
 	u8 sinks[DRM_DP_MAX_SDP_STREAMS];
 	int i;
 
+	port = drm_dp_get_validated_port_ref(mgr, port);
+	if (!port)
+		return -EINVAL;
+
 	port_num = port->port_num;
 	mstb = drm_dp_get_validated_mstb_ref(mgr, port->parent);
 	if (!mstb) {
 		mstb = drm_dp_get_last_connected_port_and_mstb(mgr, port->parent, &port_num);
 
-		if (!mstb)
+		if (!mstb) {
+			drm_dp_put_port(port);
 			return -EINVAL;
+		}
 	}
 
 	txmsg = kzalloc(sizeof(*txmsg), GFP_KERNEL);
@@ -1707,6 +1713,7 @@ static int drm_dp_payload_send_msg(struct drm_dp_mst_topology_mgr *mgr,
 	kfree(txmsg);
 fail_put:
 	drm_dp_put_mst_branch_device(mstb);
+	drm_dp_put_port(port);
 	return ret;
 }
 
@@ -1789,6 +1796,11 @@ int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr)
 		req_payload.start_slot = cur_slots;
 		if (mgr->proposed_vcpis[i]) {
 			port = container_of(mgr->proposed_vcpis[i], struct drm_dp_mst_port, vcpi);
+			port = drm_dp_get_validated_port_ref(mgr, port);
+			if (!port) {
+				mutex_unlock(&mgr->payload_lock);
+				return -EINVAL;
+			}
 			req_payload.num_slots = mgr->proposed_vcpis[i]->num_slots;
 			req_payload.vcpi = mgr->proposed_vcpis[i]->vcpi;
 		} else {
@@ -1816,6 +1828,9 @@ int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr)
 			mgr->payloads[i].payload_state = req_payload.payload_state;
 		}
 		cur_slots += req_payload.num_slots;
+
+		if (port)
+			drm_dp_put_port(port);
 	}
 
 	for (i = 0; i < mgr->max_payloads; i++) {
@@ -2121,6 +2136,8 @@ int drm_dp_mst_topology_mgr_resume(struct drm_dp_mst_topology_mgr *mgr)
 
 	if (mgr->mst_primary) {
 		int sret;
+		u8 guid[16];
+
 		sret = drm_dp_dpcd_read(mgr->aux, DP_DPCD_REV, mgr->dpcd, DP_RECEIVER_CAP_SIZE);
 		if (sret != DP_RECEIVER_CAP_SIZE) {
 			DRM_DEBUG_KMS("dpcd read failed - undocked during suspend?\n");
@@ -2135,6 +2152,16 @@ int drm_dp_mst_topology_mgr_resume(struct drm_dp_mst_topology_mgr *mgr)
 			ret = -1;
 			goto out_unlock;
 		}
+
+		/* Some hubs forget their guids after they resume */
+		sret = drm_dp_dpcd_read(mgr->aux, DP_GUID, guid, 16);
+		if (sret != 16) {
+			DRM_DEBUG_KMS("dpcd read failed - undocked during suspend?\n");
+			ret = -1;
+			goto out_unlock;
+		}
+		drm_dp_check_mstb_guid(mgr->mst_primary, guid);
+
 		ret = 0;
 	} else
 		ret = -1;

drivers/gpu/drm/etnaviv/etnaviv_gpu.c

@@ -572,6 +572,24 @@ int etnaviv_gpu_init(struct etnaviv_gpu *gpu)
 		goto fail;
 	}
 
+	/*
+	 * Set the GPU linear window to be at the end of the DMA window, where
+	 * the CMA area is likely to reside. This ensures that we are able to
+	 * map the command buffers while having the linear window overlap as
+	 * much RAM as possible, so we can optimize mappings for other buffers.
+	 *
+	 * For 3D cores only do this if MC2.0 is present, as with MC1.0 it leads
+	 * to different views of the memory on the individual engines.
+	 */
+	if (!(gpu->identity.features & chipFeatures_PIPE_3D) ||
+	    (gpu->identity.minor_features0 & chipMinorFeatures0_MC20)) {
+		u32 dma_mask = (u32)dma_get_required_mask(gpu->dev);
+		if (dma_mask < PHYS_OFFSET + SZ_2G)
+			gpu->memory_base = PHYS_OFFSET;
+		else
+			gpu->memory_base = dma_mask - SZ_2G + 1;
+	}
+
 	ret = etnaviv_hw_reset(gpu);
 	if (ret)
 		goto fail;
@@ -1566,7 +1584,6 @@ static int etnaviv_gpu_platform_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct etnaviv_gpu *gpu;
-	u32 dma_mask;
 	int err = 0;
 
 	gpu = devm_kzalloc(dev, sizeof(*gpu), GFP_KERNEL);
@@ -1576,18 +1593,6 @@ static int etnaviv_gpu_platform_probe(struct platform_device *pdev)
 	gpu->dev = &pdev->dev;
 	mutex_init(&gpu->lock);
 
-	/*
-	 * Set the GPU linear window to be at the end of the DMA window, where
-	 * the CMA area is likely to reside. This ensures that we are able to
-	 * map the command buffers while having the linear window overlap as
-	 * much RAM as possible, so we can optimize mappings for other buffers.
-	 */
-	dma_mask = (u32)dma_get_required_mask(dev);
-	if (dma_mask < PHYS_OFFSET + SZ_2G)
-		gpu->memory_base = PHYS_OFFSET;
-	else
-		gpu->memory_base = dma_mask - SZ_2G + 1;
-
 	/* Map registers: */
 	gpu->mmio = etnaviv_ioremap(pdev, NULL, dev_name(gpu->dev));
 	if (IS_ERR(gpu->mmio))

drivers/gpu/drm/i915/i915_drv.h

@@ -2634,8 +2634,9 @@ struct drm_i915_cmd_table {
 
 /* WaRsDisableCoarsePowerGating:skl,bxt */
 #define NEEDS_WaRsDisableCoarsePowerGating(dev) (IS_BXT_REVID(dev, 0, BXT_REVID_A1) || \
-						 ((IS_SKL_GT3(dev) || IS_SKL_GT4(dev)) && \
-						  IS_SKL_REVID(dev, 0, SKL_REVID_F0)))
+						 IS_SKL_GT3(dev) || \
+						 IS_SKL_GT4(dev))
+
 /*
  * dp aux and gmbus irq on gen4 seems to be able to generate legacy interrupts
  * even when in MSI mode. This results in spurious interrupt warnings if the

drivers/gpu/drm/i915/i915_gem_userptr.c

@@ -501,19 +501,24 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
 	if (pvec != NULL) {
 		struct mm_struct *mm = obj->userptr.mm->mm;
 
-		down_read(&mm->mmap_sem);
-		while (pinned < npages) {
-			ret = get_user_pages_remote(work->task, mm,
-					obj->userptr.ptr + pinned * PAGE_SIZE,
-					npages - pinned,
-					!obj->userptr.read_only, 0,
-					pvec + pinned, NULL);
-			if (ret < 0)
-				break;
-
-			pinned += ret;
+		ret = -EFAULT;
+		if (atomic_inc_not_zero(&mm->mm_users)) {
+			down_read(&mm->mmap_sem);
+			while (pinned < npages) {
+				ret = get_user_pages_remote
+					(work->task, mm,
+					 obj->userptr.ptr + pinned * PAGE_SIZE,
+					 npages - pinned,
+					 !obj->userptr.read_only, 0,
+					 pvec + pinned, NULL);
+				if (ret < 0)
+					break;
+
+				pinned += ret;
+			}
+			up_read(&mm->mmap_sem);
+			mmput(mm);
 		}
-		up_read(&mm->mmap_sem);
 	}
 
 	mutex_lock(&dev->struct_mutex);

drivers/gpu/drm/i915/intel_lrc.c

@@ -841,11 +841,11 @@ static int logical_ring_prepare(struct drm_i915_gem_request *req, int bytes)
 		if (unlikely(total_bytes > remain_usable)) {
 			/*
 			 * The base request will fit but the reserved space
-			 * falls off the end. So only need to to wait for the
-			 * reserved size after flushing out the remainder.
+			 * falls off the end. So don't need an immediate wrap
+			 * and only need to effectively wait for the reserved
+			 * size space from the start of ringbuffer.
 			 */
 			wait_bytes = remain_actual + ringbuf->reserved_size;
-			need_wrap = true;
 		} else if (total_bytes > ringbuf->space) {
 			/* No wrapping required, just waiting. */
 			wait_bytes = total_bytes;
@@ -1913,15 +1913,18 @@ static int gen8_emit_request_render(struct drm_i915_gem_request *request)
 	struct intel_ringbuffer *ringbuf = request->ringbuf;
 	int ret;
 
-	ret = intel_logical_ring_begin(request, 6 + WA_TAIL_DWORDS);
+	ret = intel_logical_ring_begin(request, 8 + WA_TAIL_DWORDS);
 	if (ret)
 		return ret;
 
+	/* We're using qword write, seqno should be aligned to 8 bytes. */
+	BUILD_BUG_ON(I915_GEM_HWS_INDEX & 1);
+
 	/* w/a for post sync ops following a GPGPU operation we
 	 * need a prior CS_STALL, which is emitted by the flush
 	 * following the batch.
 	 */
-	intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(5));
+	intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(6));
 	intel_logical_ring_emit(ringbuf,
 				(PIPE_CONTROL_GLOBAL_GTT_IVB |
 				 PIPE_CONTROL_CS_STALL |
@@ -1929,7 +1932,10 @@ static int gen8_emit_request_render(struct drm_i915_gem_request *request)
 	intel_logical_ring_emit(ringbuf, hws_seqno_address(request->ring));
 	intel_logical_ring_emit(ringbuf, 0);
 	intel_logical_ring_emit(ringbuf, i915_gem_request_get_seqno(request));
+	/* We're thrashing one dword of HWS. */
+	intel_logical_ring_emit(ringbuf, 0);
 	intel_logical_ring_emit(ringbuf, MI_USER_INTERRUPT);
+	intel_logical_ring_emit(ringbuf, MI_NOOP);
 	return intel_logical_ring_advance_and_submit(request);
 }