Merge 4.13-rc7 into staging-next

We want the staging and iio fixes in here to handle the merge issues.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Documentation/networking/switchdev.txt

@@ -228,7 +228,7 @@ Learning on the device port should be enabled, as well as learning_sync:
 	bridge link set dev DEV learning on self
 	bridge link set dev DEV learning_sync on self
 
-Learning_sync attribute enables syncing of the learned/forgotton FDB entry to
+Learning_sync attribute enables syncing of the learned/forgotten FDB entry to
 the bridge's FDB.  It's possible, but not optimal, to enable learning on the
 device port and on the bridge port, and disable learning_sync.
 
@@ -245,7 +245,7 @@ the responsibility of the port driver/device to age out these entries.  If the
 port device supports ageing, when the FDB entry expires, it will notify the
 driver which in turn will notify the bridge with SWITCHDEV_FDB_DEL.  If the
 device does not support ageing, the driver can simulate ageing using a
-garbage collection timer to monitor FBD entries.  Expired entries will be
+garbage collection timer to monitor FDB entries.  Expired entries will be
 notified to the bridge using SWITCHDEV_FDB_DEL.  See rocker driver for
 example of driver running ageing timer.
 

Documentation/printk-formats.txt

@@ -58,20 +58,23 @@ Symbols/Function Pointers
 	%ps	versatile_init
 	%pB	prev_fn_of_versatile_init+0x88/0x88
 
-For printing symbols and function pointers. The ``S`` and ``s`` specifiers
-result in the symbol name with (``S``) or without (``s``) offsets. Where
-this is used on a kernel without KALLSYMS - the symbol address is
-printed instead.
+The ``F`` and ``f`` specifiers are for printing function pointers,
+for example, f->func, &gettimeofday. They have the same result as
+``S`` and ``s`` specifiers. But they do an extra conversion on
+ia64, ppc64 and parisc64 architectures where the function pointers
+are actually function descriptors.
+
+The ``S`` and ``s`` specifiers can be used for printing symbols
+from direct addresses, for example, __builtin_return_address(0),
+(void *)regs->ip. They result in the symbol name with (``S``) or
+without (``s``) offsets. If KALLSYMS are disabled then the symbol
+address is printed instead.
 
 The ``B`` specifier results in the symbol name with offsets and should be
 used when printing stack backtraces. The specifier takes into
 consideration the effect of compiler optimisations which may occur
 when tail-call``s are used and marked with the noreturn GCC attribute.
 
-On ia64, ppc64 and parisc64 architectures function pointers are
-actually function descriptors which must first be resolved. The ``F`` and
-``f`` specifiers perform this resolution and then provide the same
-functionality as the ``S`` and ``s`` specifiers.
 
 Kernel Pointers
 ===============

Documentation/sysctl/net.txt

@@ -35,9 +35,34 @@ Table : Subdirectories in /proc/sys/net
 bpf_jit_enable
 --------------
 
-This enables Berkeley Packet Filter Just in Time compiler.
-Currently supported on x86_64 architecture, bpf_jit provides a framework
-to speed packet filtering, the one used by tcpdump/libpcap for example.
+This enables the BPF Just in Time (JIT) compiler. BPF is a flexible
+and efficient infrastructure allowing to execute bytecode at various
+hook points. It is used in a number of Linux kernel subsystems such
+as networking (e.g. XDP, tc), tracing (e.g. kprobes, uprobes, tracepoints)
+and security (e.g. seccomp). LLVM has a BPF back end that can compile
+restricted C into a sequence of BPF instructions. After program load
+through bpf(2) and passing a verifier in the kernel, a JIT will then
+translate these BPF proglets into native CPU instructions. There are
+two flavors of JITs, the newer eBPF JIT currently supported on:
+  - x86_64
+  - arm64
+  - ppc64
+  - sparc64
+  - mips64
+  - s390x
+
+And the older cBPF JIT supported on the following archs:
+  - arm
+  - mips
+  - ppc
+  - sparc
+
+eBPF JITs are a superset of cBPF JITs, meaning the kernel will
+migrate cBPF instructions into eBPF instructions and then JIT
+compile them transparently. Older cBPF JITs can only translate
+tcpdump filters, seccomp rules, etc, but not mentioned eBPF
+programs loaded through bpf(2).
+
 Values :
 	0 - disable the JIT (default value)
 	1 - enable the JIT
@@ -46,9 +71,9 @@ Values :
 bpf_jit_harden
 --------------
 
-This enables hardening for the Berkeley Packet Filter Just in Time compiler.
-Supported are eBPF JIT backends. Enabling hardening trades off performance,
-but can mitigate JIT spraying.
+This enables hardening for the BPF JIT compiler. Supported are eBPF
+JIT backends. Enabling hardening trades off performance, but can
+mitigate JIT spraying.
 Values :
 	0 - disable JIT hardening (default value)
 	1 - enable JIT hardening for unprivileged users only
@@ -57,11 +82,11 @@ Values :
 bpf_jit_kallsyms
 ----------------
 
-When Berkeley Packet Filter Just in Time compiler is enabled, then compiled
-images are unknown addresses to the kernel, meaning they neither show up in
-traces nor in /proc/kallsyms. This enables export of these addresses, which
-can be used for debugging/tracing. If bpf_jit_harden is enabled, this feature
-is disabled.
+When BPF JIT compiler is enabled, then compiled images are unknown
+addresses to the kernel, meaning they neither show up in traces nor
+in /proc/kallsyms. This enables export of these addresses, which can
+be used for debugging/tracing. If bpf_jit_harden is enabled, this
+feature is disabled.
 Values :
 	0 - disable JIT kallsyms export (default value)
 	1 - enable JIT kallsyms export for privileged users only

MAINTAINERS

@@ -7110,7 +7110,6 @@ M:	Marc Zyngier <marc.zyngier@arm.com>
 L:	linux-kernel@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq/core
-T:	git git://git.infradead.org/users/jcooper/linux.git irqchip/core
 F:	Documentation/devicetree/bindings/interrupt-controller/
 F:	drivers/irqchip/
 

Makefile

@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 13
 SUBLEVEL = 0
-EXTRAVERSION = -rc5
+EXTRAVERSION = -rc7
 NAME = Fearless Coyote
 
 # *DOCUMENTATION*
@@ -396,7 +396,7 @@ LINUXINCLUDE    := \
 KBUILD_CPPFLAGS := -D__KERNEL__
 
 KBUILD_CFLAGS   := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \
-		   -fno-strict-aliasing -fno-common \
+		   -fno-strict-aliasing -fno-common -fshort-wchar \
 		   -Werror-implicit-function-declaration \
 		   -Wno-format-security \
 		   -std=gnu89 $(call cc-option,-fno-PIE)
@@ -442,7 +442,7 @@ export RCS_TAR_IGNORE := --exclude SCCS --exclude BitKeeper --exclude .svn \
 # ===========================================================================
 # Rules shared between *config targets and build targets
 
-# Basic helpers built in scripts/
+# Basic helpers built in scripts/basic/
 PHONY += scripts_basic
 scripts_basic:
 	$(Q)$(MAKE) $(build)=scripts/basic
@@ -505,7 +505,7 @@ ifeq ($(KBUILD_EXTMOD),)
                 endif
         endif
 endif
-# install and module_install need also be processed one by one
+# install and modules_install need also be processed one by one
 ifneq ($(filter install,$(MAKECMDGOALS)),)
         ifneq ($(filter modules_install,$(MAKECMDGOALS)),)
 	        mixed-targets := 1
@@ -964,7 +964,7 @@ export KBUILD_VMLINUX_MAIN := $(core-y) $(libs-y2) $(drivers-y) $(net-y) $(virt-
 export KBUILD_VMLINUX_LIBS := $(libs-y1)
 export KBUILD_LDS          := arch/$(SRCARCH)/kernel/vmlinux.lds
 export LDFLAGS_vmlinux
-# used by scripts/pacmage/Makefile
+# used by scripts/package/Makefile
 export KBUILD_ALLDIRS := $(sort $(filter-out arch/%,$(vmlinux-alldirs)) arch Documentation include samples scripts tools)
 
 vmlinux-deps := $(KBUILD_LDS) $(KBUILD_VMLINUX_INIT) $(KBUILD_VMLINUX_MAIN) $(KBUILD_VMLINUX_LIBS)
@@ -992,8 +992,8 @@ include/generated/autoksyms.h: FORCE
 ARCH_POSTLINK := $(wildcard $(srctree)/arch/$(SRCARCH)/Makefile.postlink)
 
 # Final link of vmlinux with optional arch pass after final link
-    cmd_link-vmlinux =                                                 \
-	$(CONFIG_SHELL) $< $(LD) $(LDFLAGS) $(LDFLAGS_vmlinux) ;       \
+cmd_link-vmlinux =                                                 \
+	$(CONFIG_SHELL) $< $(LD) $(LDFLAGS) $(LDFLAGS_vmlinux) ;    \
 	$(if $(ARCH_POSTLINK), $(MAKE) -f $(ARCH_POSTLINK) $@, true)
 
 vmlinux: scripts/link-vmlinux.sh vmlinux_prereq $(vmlinux-deps) FORCE
@@ -1184,6 +1184,7 @@ PHONY += kselftest
 kselftest:
 	$(Q)$(MAKE) -C tools/testing/selftests run_tests
 
+PHONY += kselftest-clean
 kselftest-clean:
 	$(Q)$(MAKE) -C tools/testing/selftests clean
 

arch/arc/Kconfig

@@ -96,7 +96,6 @@ menu "ARC Architecture Configuration"
 
 menu "ARC Platform/SoC/Board"
 
-source "arch/arc/plat-sim/Kconfig"
 source "arch/arc/plat-tb10x/Kconfig"
 source "arch/arc/plat-axs10x/Kconfig"
 #New platform adds here

arch/arc/Makefile

@@ -107,7 +107,7 @@ core-y		+= arch/arc/
 # w/o this dtb won't embed into kernel binary
 core-y		+= arch/arc/boot/dts/
 
-core-$(CONFIG_ARC_PLAT_SIM)	+= arch/arc/plat-sim/
+core-y				+= arch/arc/plat-sim/
 core-$(CONFIG_ARC_PLAT_TB10X)	+= arch/arc/plat-tb10x/
 core-$(CONFIG_ARC_PLAT_AXS10X)	+= arch/arc/plat-axs10x/
 core-$(CONFIG_ARC_PLAT_EZNPS)	+= arch/arc/plat-eznps/

arch/arc/boot/dts/axc001.dtsi

@@ -15,15 +15,15 @@
 
 / {
 	compatible = "snps,arc";
-	#address-cells = <1>;
-	#size-cells = <1>;
+	#address-cells = <2>;
+	#size-cells = <2>;
 
 	cpu_card {
 		compatible = "simple-bus";
 		#address-cells = <1>;
 		#size-cells = <1>;
 
-		ranges = <0x00000000 0xf0000000 0x10000000>;
+		ranges = <0x00000000 0x0 0xf0000000 0x10000000>;
 
 		core_clk: core_clk {
 			#clock-cells = <0>;
@@ -91,23 +91,21 @@
 	mb_intc: dw-apb-ictl@0xe0012000 {
 		#interrupt-cells = <1>;
 		compatible = "snps,dw-apb-ictl";
-		reg = < 0xe0012000 0x200 >;
+		reg = < 0x0 0xe0012000 0x0 0x200 >;
 		interrupt-controller;
 		interrupt-parent = <&core_intc>;
 		interrupts = < 7 >;
 	};
 
 	memory {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges = <0x00000000 0x80000000 0x20000000>;
 		device_type = "memory";
-		reg = <0x80000000 0x1b000000>;	/* (512 - 32) MiB */
+		/* CONFIG_KERNEL_RAM_BASE_ADDRESS needs to match low mem start */
+		reg = <0x0 0x80000000 0x0 0x1b000000>;	/* (512 - 32) MiB */
 	};
 
 	reserved-memory {
-		#address-cells = <1>;
-		#size-cells = <1>;
+		#address-cells = <2>;
+		#size-cells = <2>;
 		ranges;
 		/*
 		 * We just move frame buffer area to the very end of
@@ -118,7 +116,7 @@
 		 */
 		frame_buffer: frame_buffer@9e000000 {
 			compatible = "shared-dma-pool";
-			reg = <0x9e000000 0x2000000>;
+			reg = <0x0 0x9e000000 0x0 0x2000000>;
 			no-map;
 		};
 	};

arch/arc/boot/dts/axc003.dtsi

@@ -14,15 +14,15 @@
 
 / {
 	compatible = "snps,arc";
-	#address-cells = <1>;
-	#size-cells = <1>;
+	#address-cells = <2>;
+	#size-cells = <2>;
 
 	cpu_card {
 		compatible = "simple-bus";
 		#address-cells = <1>;
 		#size-cells = <1>;
 
-		ranges = <0x00000000 0xf0000000 0x10000000>;
+		ranges = <0x00000000 0x0 0xf0000000 0x10000000>;
 
 		core_clk: core_clk {
 			#clock-cells = <0>;
@@ -94,30 +94,29 @@
 	mb_intc: dw-apb-ictl@0xe0012000 {
 		#interrupt-cells = <1>;
 		compatible = "snps,dw-apb-ictl";
-		reg = < 0xe0012000 0x200 >;
+		reg = < 0x0 0xe0012000 0x0 0x200 >;
 		interrupt-controller;
 		interrupt-parent = <&core_intc>;
 		interrupts = < 24 >;
 	};
 
 	memory {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges = <0x00000000 0x80000000 0x40000000>;
 		device_type = "memory";
-		reg = <0x80000000 0x20000000>;	/* 512MiB */
+		/* CONFIG_KERNEL_RAM_BASE_ADDRESS needs to match low mem start */
+		reg = <0x0 0x80000000 0x0 0x20000000	/* 512 MiB low mem */
+		       0x1 0xc0000000 0x0 0x40000000>;	/* 1 GiB highmem */
 	};
 
 	reserved-memory {
-		#address-cells = <1>;
-		#size-cells = <1>;
+		#address-cells = <2>;
+		#size-cells = <2>;
 		ranges;
 		/*
 		 * Move frame buffer out of IOC aperture (0x8z-0xAz).
 		 */
 		frame_buffer: frame_buffer@be000000 {
 			compatible = "shared-dma-pool";
-			reg = <0xbe000000 0x2000000>;
+			reg = <0x0 0xbe000000 0x0 0x2000000>;
 			no-map;
 		};
 	};

arch/arc/boot/dts/axc003_idu.dtsi

@@ -14,15 +14,15 @@
 
 / {
 	compatible = "snps,arc";
-	#address-cells = <1>;
-	#size-cells = <1>;
+	#address-cells = <2>;
+	#size-cells = <2>;
 
 	cpu_card {
 		compatible = "simple-bus";
 		#address-cells = <1>;
 		#size-cells = <1>;
 
-		ranges = <0x00000000 0xf0000000 0x10000000>;
+		ranges = <0x00000000 0x0 0xf0000000 0x10000000>;
 
 		core_clk: core_clk {
 			#clock-cells = <0>;
@@ -100,30 +100,29 @@
 	mb_intc: dw-apb-ictl@0xe0012000 {
 		#interrupt-cells = <1>;
 		compatible = "snps,dw-apb-ictl";
-		reg = < 0xe0012000 0x200 >;
+		reg = < 0x0 0xe0012000 0x0 0x200 >;
 		interrupt-controller;
 		interrupt-parent = <&idu_intc>;
 		interrupts = <0>;
 	};
 
 	memory {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges = <0x00000000 0x80000000 0x40000000>;
 		device_type = "memory";
-		reg = <0x80000000 0x20000000>;	/* 512MiB */
+		/* CONFIG_KERNEL_RAM_BASE_ADDRESS needs to match low mem start */
+		reg = <0x0 0x80000000 0x0 0x20000000	/* 512 MiB low mem */
+		       0x1 0xc0000000 0x0 0x40000000>;	/* 1 GiB highmem */
 	};
 
 	reserved-memory {
-		#address-cells = <1>;
-		#size-cells = <1>;
+		#address-cells = <2>;
+		#size-cells = <2>;
 		ranges;
 		/*
 		 * Move frame buffer out of IOC aperture (0x8z-0xAz).
 		 */
 		frame_buffer: frame_buffer@be000000 {
 			compatible = "shared-dma-pool";
-			reg = <0xbe000000 0x2000000>;
+			reg = <0x0 0xbe000000 0x0 0x2000000>;
 			no-map;
 		};
 	};

arch/arc/boot/dts/axs10x_mb.dtsi

@@ -13,7 +13,7 @@
 		compatible = "simple-bus";
 		#address-cells = <1>;
 		#size-cells = <1>;
-		ranges = <0x00000000 0xe0000000 0x10000000>;
+		ranges = <0x00000000 0x0 0xe0000000 0x10000000>;
 		interrupt-parent = <&mb_intc>;
 
 		i2sclk: i2sclk@100a0 {

arch/arc/configs/haps_hs_defconfig

@@ -21,7 +21,6 @@ CONFIG_MODULES=y
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
-CONFIG_ARC_PLAT_SIM=y
 CONFIG_ISA_ARCV2=y
 CONFIG_ARC_BUILTIN_DTB_NAME="haps_hs"
 CONFIG_PREEMPT=y

arch/arc/configs/haps_hs_smp_defconfig

@@ -23,7 +23,6 @@ CONFIG_MODULES=y
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
-CONFIG_ARC_PLAT_SIM=y
 CONFIG_ISA_ARCV2=y
 CONFIG_SMP=y
 CONFIG_ARC_BUILTIN_DTB_NAME="haps_hs_idu"

arch/arc/configs/nps_defconfig

@@ -39,7 +39,6 @@ CONFIG_IP_PNP=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_INET_DIAG is not set
 # CONFIG_IPV6 is not set
 # CONFIG_WIRELESS is not set

arch/arc/configs/nsim_700_defconfig

@@ -23,7 +23,6 @@ CONFIG_MODULES=y
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
-CONFIG_ARC_PLAT_SIM=y
 CONFIG_ARC_BUILTIN_DTB_NAME="nsim_700"
 CONFIG_PREEMPT=y
 # CONFIG_COMPACTION is not set

arch/arc/configs/nsim_hs_defconfig

@@ -26,7 +26,6 @@ CONFIG_MODULE_FORCE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
-CONFIG_ARC_PLAT_SIM=y
 CONFIG_ISA_ARCV2=y
 CONFIG_ARC_BUILTIN_DTB_NAME="nsim_hs"
 CONFIG_PREEMPT=y

arch/arc/configs/nsim_hs_smp_defconfig

@@ -24,7 +24,6 @@ CONFIG_MODULE_FORCE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
-CONFIG_ARC_PLAT_SIM=y
 CONFIG_ISA_ARCV2=y
 CONFIG_SMP=y
 CONFIG_ARC_BUILTIN_DTB_NAME="nsim_hs_idu"

arch/arc/configs/nsimosci_defconfig

@@ -23,7 +23,6 @@ CONFIG_MODULES=y
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
-CONFIG_ARC_PLAT_SIM=y
 CONFIG_ARC_BUILTIN_DTB_NAME="nsimosci"
 # CONFIG_COMPACTION is not set
 CONFIG_NET=y

arch/arc/configs/nsimosci_hs_defconfig

@@ -23,7 +23,6 @@ CONFIG_MODULES=y
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
-CONFIG_ARC_PLAT_SIM=y
 CONFIG_ISA_ARCV2=y
 CONFIG_ARC_BUILTIN_DTB_NAME="nsimosci_hs"
 # CONFIG_COMPACTION is not set

arch/arc/configs/nsimosci_hs_smp_defconfig

@@ -18,7 +18,6 @@ CONFIG_MODULES=y
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
-CONFIG_ARC_PLAT_SIM=y
 CONFIG_ISA_ARCV2=y
 CONFIG_SMP=y
 # CONFIG_ARC_TIMERS_64BIT is not set

arch/arc/configs/tb10x_defconfig

@@ -38,7 +38,6 @@ CONFIG_IP_MULTICAST=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_INET_DIAG is not set
 # CONFIG_IPV6 is not set
 # CONFIG_WIRELESS is not set

arch/arc/include/asm/cache.h

@@ -96,7 +96,9 @@ extern unsigned long perip_base, perip_end;
 #define ARC_REG_SLC_FLUSH	0x904
 #define ARC_REG_SLC_INVALIDATE	0x905
 #define ARC_REG_SLC_RGN_START	0x914
+#define ARC_REG_SLC_RGN_START1	0x915
 #define ARC_REG_SLC_RGN_END	0x916
+#define ARC_REG_SLC_RGN_END1	0x917
 
 /* Bit val in SLC_CONTROL */
 #define SLC_CTRL_DIS		0x001

arch/arc/include/asm/mmu.h

@@ -94,6 +94,8 @@ static inline int is_pae40_enabled(void)
 	return IS_ENABLED(CONFIG_ARC_HAS_PAE40);
 }
 
+extern int pae40_exist_but_not_enab(void);
+
 #endif	/* !__ASSEMBLY__ */
 
 #endif

arch/arc/kernel/intc-arcv2.c

@@ -75,10 +75,13 @@ void arc_init_IRQ(void)
 	 * Set a default priority for all available interrupts to prevent
 	 * switching of register banks if Fast IRQ and multiple register banks
 	 * are supported by CPU.
+	 * Also disable all IRQ lines so faulty external hardware won't
+	 * trigger interrupt that kernel is not ready to handle.
 	 */
 	for (i = NR_EXCEPTIONS; i < irq_bcr.irqs + NR_EXCEPTIONS; i++) {
 		write_aux_reg(AUX_IRQ_SELECT, i);
 		write_aux_reg(AUX_IRQ_PRIORITY, ARCV2_IRQ_DEF_PRIO);
+		write_aux_reg(AUX_IRQ_ENABLE, 0);
 	}
 
 	/* setup status32, don't enable intr yet as kernel doesn't want */

arch/arc/kernel/intc-compact.c

@@ -27,7 +27,7 @@
  */
 void arc_init_IRQ(void)
 {
-	int level_mask = 0;
+	int level_mask = 0, i;
 
        /* Is timer high priority Interrupt (Level2 in ARCompact jargon) */
 	level_mask |= IS_ENABLED(CONFIG_ARC_COMPACT_IRQ_LEVELS) << TIMER0_IRQ;
@@ -40,6 +40,18 @@ void arc_init_IRQ(void)
 
 	if (level_mask)
 		pr_info("Level-2 interrupts bitset %x\n", level_mask);
+
+	/*
+	 * Disable all IRQ lines so faulty external hardware won't
+	 * trigger interrupt that kernel is not ready to handle.
+	 */
+	for (i = TIMER0_IRQ; i < NR_CPU_IRQS; i++) {
+		unsigned int ienb;
+
+		ienb = read_aux_reg(AUX_IENABLE);
+		ienb &= ~(1 << i);
+		write_aux_reg(AUX_IENABLE, ienb);
+	}
 }
 
 /*

arch/arc/mm/cache.c

@@ -665,6 +665,7 @@ noinline void slc_op(phys_addr_t paddr, unsigned long sz, const int op)
 	static DEFINE_SPINLOCK(lock);
 	unsigned long flags;
 	unsigned int ctrl;
+	phys_addr_t end;
 
 	spin_lock_irqsave(&lock, flags);
 
@@ -694,8 +695,19 @@ noinline void slc_op(phys_addr_t paddr, unsigned long sz, const int op)
 	 * END needs to be setup before START (latter triggers the operation)
 	 * END can't be same as START, so add (l2_line_sz - 1) to sz
 	 */
-	write_aux_reg(ARC_REG_SLC_RGN_END, (paddr + sz + l2_line_sz - 1));
-	write_aux_reg(ARC_REG_SLC_RGN_START, paddr);
+	end = paddr + sz + l2_line_sz - 1;
+	if (is_pae40_enabled())
+		write_aux_reg(ARC_REG_SLC_RGN_END1, upper_32_bits(end));
+
+	write_aux_reg(ARC_REG_SLC_RGN_END, lower_32_bits(end));
+
+	if (is_pae40_enabled())
+		write_aux_reg(ARC_REG_SLC_RGN_START1, upper_32_bits(paddr));
+
+	write_aux_reg(ARC_REG_SLC_RGN_START, lower_32_bits(paddr));
+
+	/* Make sure "busy" bit reports correct stataus, see STAR 9001165532 */
+	read_aux_reg(ARC_REG_SLC_CTRL);
 
 	while (read_aux_reg(ARC_REG_SLC_CTRL) & SLC_CTRL_BUSY);
 
@@ -1111,6 +1123,13 @@ noinline void __init arc_ioc_setup(void)
 	__dc_enable();
 }
 
+/*
+ * Cache related boot time checks/setups only needed on master CPU:
+ *  - Geometry checks (kernel build and hardware agree: e.g. L1_CACHE_BYTES)
+ *    Assume SMP only, so all cores will have same cache config. A check on
+ *    one core suffices for all
+ *  - IOC setup / dma callbacks only need to be done once
+ */
 void __init arc_cache_init_master(void)
 {
 	unsigned int __maybe_unused cpu = smp_processor_id();
@@ -1190,12 +1209,27 @@ void __ref arc_cache_init(void)
 
 	printk(arc_cache_mumbojumbo(0, str, sizeof(str)));
 
-	/*
-	 * Only master CPU needs to execute rest of function:
-	 *  - Assume SMP so all cores will have same cache config so
-	 *    any geomtry checks will be same for all
-	 *  - IOC setup / dma callbacks only need to be setup once
-	 */
 	if (!cpu)
 		arc_cache_init_master();
+
+	/*
+	 * In PAE regime, TLB and cache maintenance ops take wider addresses
+	 * And even if PAE is not enabled in kernel, the upper 32-bits still need
+	 * to be zeroed to keep the ops sane.
+	 * As an optimization for more common !PAE enabled case, zero them out
+	 * once at init, rather than checking/setting to 0 for every runtime op
+	 */
+	if (is_isa_arcv2() && pae40_exist_but_not_enab()) {
+
+		if (IS_ENABLED(CONFIG_ARC_HAS_ICACHE))
+			write_aux_reg(ARC_REG_IC_PTAG_HI, 0);
+
+		if (IS_ENABLED(CONFIG_ARC_HAS_DCACHE))
+			write_aux_reg(ARC_REG_DC_PTAG_HI, 0);
+
+		if (l2_line_sz) {
+			write_aux_reg(ARC_REG_SLC_RGN_END1, 0);
+			write_aux_reg(ARC_REG_SLC_RGN_START1, 0);
+		}
+	}
 }

arch/arc/mm/dma.c

@@ -153,6 +153,19 @@ static void _dma_cache_sync(phys_addr_t paddr, size_t size,
 	}
 }
 
+/*
+ * arc_dma_map_page - map a portion of a page for streaming DMA
+ *
+ * Ensure that any data held in the cache is appropriately discarded
+ * or written back.
+ *
+ * The device owns this memory once this call has completed.  The CPU
+ * can regain ownership by calling dma_unmap_page().
+ *
+ * Note: while it takes struct page as arg, caller can "abuse" it to pass
+ * a region larger than PAGE_SIZE, provided it is physically contiguous
+ * and this still works correctly
+ */
 static dma_addr_t arc_dma_map_page(struct device *dev, struct page *page,
 		unsigned long offset, size_t size, enum dma_data_direction dir,
 		unsigned long attrs)
@@ -165,6 +178,24 @@ static dma_addr_t arc_dma_map_page(struct device *dev, struct page *page,
 	return plat_phys_to_dma(dev, paddr);
 }
 
+/*
+ * arc_dma_unmap_page - unmap a buffer previously mapped through dma_map_page()
+ *
+ * After this call, reads by the CPU to the buffer are guaranteed to see
+ * whatever the device wrote there.
+ *
+ * Note: historically this routine was not implemented for ARC
+ */
+static void arc_dma_unmap_page(struct device *dev, dma_addr_t handle,
+			       size_t size, enum dma_data_direction dir,
+			       unsigned long attrs)
+{
+	phys_addr_t paddr = plat_dma_to_phys(dev, handle);
+
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		_dma_cache_sync(paddr, size, dir);
+}
+
 static int arc_dma_map_sg(struct device *dev, struct scatterlist *sg,
 	   int nents, enum dma_data_direction dir, unsigned long attrs)
 {
@@ -178,6 +209,18 @@ static int arc_dma_map_sg(struct device *dev, struct scatterlist *sg,
 	return nents;
 }
 
+static void arc_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
+			     int nents, enum dma_data_direction dir,
+			     unsigned long attrs)
+{
+	struct scatterlist *s;
+	int i;
+
+	for_each_sg(sg, s, nents, i)
+		arc_dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir,
+				   attrs);
+}
+
 static void arc_dma_sync_single_for_cpu(struct device *dev,
 		dma_addr_t dma_handle, size_t size, enum dma_data_direction dir)
 {
@@ -223,7 +266,9 @@ const struct dma_map_ops arc_dma_ops = {
 	.free			= arc_dma_free,
 	.mmap			= arc_dma_mmap,
 	.map_page		= arc_dma_map_page,
+	.unmap_page		= arc_dma_unmap_page,
 	.map_sg			= arc_dma_map_sg,
+	.unmap_sg		= arc_dma_unmap_sg,
 	.sync_single_for_device	= arc_dma_sync_single_for_device,
 	.sync_single_for_cpu	= arc_dma_sync_single_for_cpu,
 	.sync_sg_for_cpu	= arc_dma_sync_sg_for_cpu,

arch/arc/mm/tlb.c

@@ -104,6 +104,8 @@
 /* A copy of the ASID from the PID reg is kept in asid_cache */
 DEFINE_PER_CPU(unsigned int, asid_cache) = MM_CTXT_FIRST_CYCLE;
 
+static int __read_mostly pae_exists;
+
 /*
  * Utility Routine to erase a J-TLB entry
  * Caller needs to setup Index Reg (manually or via getIndex)
@@ -784,7 +786,7 @@ void read_decode_mmu_bcr(void)
 		mmu->u_dtlb = mmu4->u_dtlb * 4;
 		mmu->u_itlb = mmu4->u_itlb * 4;
 		mmu->sasid = mmu4->sasid;
-		mmu->pae = mmu4->pae;
+		pae_exists = mmu->pae = mmu4->pae;
 	}
 }
 
@@ -809,6 +811,11 @@ char *arc_mmu_mumbojumbo(int cpu_id, char *buf, int len)
 	return buf;
 }
 
+int pae40_exist_but_not_enab(void)
+{
+	return pae_exists && !is_pae40_enabled();
+}
+
 void arc_mmu_init(void)
 {
 	char str[256];
@@ -859,6 +866,9 @@ void arc_mmu_init(void)
 	/* swapper_pg_dir is the pgd for the kernel, used by vmalloc */
 	write_aux_reg(ARC_REG_SCRATCH_DATA0, swapper_pg_dir);
 #endif
+
+	if (pae40_exist_but_not_enab())
+		write_aux_reg(ARC_REG_TLBPD1HI, 0);
 }
 
 /*

arch/arc/plat-sim/Kconfig

@@ -1,13 +0,0 @@
-#
-# Copyright (C) 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
-#
-# 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
-# published by the Free Software Foundation.
-#
-
-menuconfig ARC_PLAT_SIM
-	bool "ARC nSIM based simulation virtual platforms"
-	help
-	  Support for nSIM based ARC simulation platforms
-	  This includes the standalone nSIM (uart only) vs. System C OSCI VP

arch/arc/plat-sim/platform.c

@@ -20,11 +20,14 @@
  */
 
 static const char *simulation_compat[] __initconst = {
+#ifdef CONFIG_ISA_ARCOMPACT
 	"snps,nsim",
-	"snps,nsim_hs",
 	"snps,nsimosci",
+#else
+	"snps,nsim_hs",
 	"snps,nsimosci_hs",
 	"snps,zebu_hs",
+#endif
 	NULL,
 };
 

arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi

@@ -266,6 +266,7 @@
 
 &hdmicec {
 	status = "okay";
+	needs-hpd;
 };
 
 &hsi2c_4 {

arch/arm/boot/dts/imx25.dtsi

@@ -297,6 +297,7 @@
 				#address-cells = <1>;
 				#size-cells = <1>;
 				status = "disabled";
+				ranges;
 
 				adc: adc@50030800 {
 					compatible = "fsl,imx25-gcq";

arch/arm/boot/dts/imx6qdl-nitrogen6_som2.dtsi

@@ -507,7 +507,7 @@
 	pinctrl_pcie: pciegrp {
 		fsl,pins = <
 			/* PCIe reset */
-			MX6QDL_PAD_EIM_BCLK__GPIO6_IO31	0x030b0
+			MX6QDL_PAD_EIM_DA0__GPIO3_IO00	0x030b0
 			MX6QDL_PAD_EIM_DA4__GPIO3_IO04	0x030b0
 		>;
 	};
@@ -668,7 +668,7 @@
 &pcie {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_pcie>;
-	reset-gpio = <&gpio6 31 GPIO_ACTIVE_LOW>;
+	reset-gpio = <&gpio3 0 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
 

arch/arm/boot/dts/imx7d-sdb.dts

@@ -557,6 +557,14 @@
 			>;
 		};
 
+		pinctrl_spi4: spi4grp {
+			fsl,pins = <
+				MX7D_PAD_GPIO1_IO09__GPIO1_IO9	0x59
+				MX7D_PAD_GPIO1_IO12__GPIO1_IO12	0x59
+				MX7D_PAD_GPIO1_IO13__GPIO1_IO13	0x59
+			>;
+		};
+
 		pinctrl_tsc2046_pendown: tsc2046_pendown {
 			fsl,pins = <
 				MX7D_PAD_EPDC_BDR1__GPIO2_IO29		0x59
@@ -697,13 +705,5 @@
 		fsl,pins = <
 			MX7D_PAD_LPSR_GPIO1_IO01__PWM1_OUT		0x110b0
 		>;
-
-		pinctrl_spi4: spi4grp {
-			fsl,pins = <
-				MX7D_PAD_GPIO1_IO09__GPIO1_IO9	0x59
-				MX7D_PAD_GPIO1_IO12__GPIO1_IO12	0x59
-				MX7D_PAD_GPIO1_IO13__GPIO1_IO13	0x59
-			>;
-		};
 	};
 };

arch/arm/boot/dts/sama5d2.dtsi

@@ -303,7 +303,7 @@
 			#size-cells = <1>;
 			atmel,smc = <&hsmc>;
 			reg = <0x10000000 0x10000000
-			       0x40000000 0x30000000>;
+			       0x60000000 0x30000000>;
 			ranges = <0x0 0x0 0x10000000 0x10000000
 				  0x1 0x0 0x60000000 0x10000000
 				  0x2 0x0 0x70000000 0x10000000
@@ -1048,18 +1048,18 @@
 			};
 
 			hsmc: hsmc@f8014000 {
-				compatible = "atmel,sama5d3-smc", "syscon", "simple-mfd";
+				compatible = "atmel,sama5d2-smc", "syscon", "simple-mfd";
 				reg = <0xf8014000 0x1000>;
-				interrupts = <5 IRQ_TYPE_LEVEL_HIGH 6>;
+				interrupts = <17 IRQ_TYPE_LEVEL_HIGH 6>;
 				clocks = <&hsmc_clk>;
 				#address-cells = <1>;
 				#size-cells = <1>;
 				ranges;
 
-				pmecc: ecc-engine@ffffc070 {
+				pmecc: ecc-engine@f8014070 {
 					compatible = "atmel,sama5d2-pmecc";
-					reg = <0xffffc070 0x490>,
-					      <0xffffc500 0x100>;
+					reg = <0xf8014070 0x490>,
+					      <0xf8014500 0x100>;
 				};
 			};
 

arch/arm/mach-at91/Kconfig

@@ -1,7 +1,7 @@
 menuconfig ARCH_AT91
 	bool "Atmel SoCs"
 	depends on ARCH_MULTI_V4T || ARCH_MULTI_V5 || ARCH_MULTI_V7 || ARM_SINGLE_ARMV7M
-	select ARM_CPU_SUSPEND if PM
+	select ARM_CPU_SUSPEND if PM && ARCH_MULTI_V7
 	select COMMON_CLK_AT91
 	select GPIOLIB
 	select PINCTRL

arch/arm/mach-at91/pm.c

@@ -608,6 +608,9 @@ static void __init at91_pm_init(void (*pm_idle)(void))
 
 void __init at91rm9200_pm_init(void)
 {
+	if (!IS_ENABLED(CONFIG_SOC_AT91RM9200))
+		return;
+
 	at91_dt_ramc();
 
 	/*
@@ -620,18 +623,27 @@ void __init at91rm9200_pm_init(void)
 
 void __init at91sam9_pm_init(void)
 {
+	if (!IS_ENABLED(CONFIG_SOC_AT91SAM9))
+		return;
+
 	at91_dt_ramc();
 	at91_pm_init(at91sam9_idle);
 }
 
 void __init sama5_pm_init(void)
 {
+	if (!IS_ENABLED(CONFIG_SOC_SAMA5))
+		return;
+
 	at91_dt_ramc();
 	at91_pm_init(NULL);
 }
 
 void __init sama5d2_pm_init(void)
 {
+	if (!IS_ENABLED(CONFIG_SOC_SAMA5D2))
+		return;
+
 	at91_pm_backup_init();
 	sama5_pm_init();
 }

arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts

@@ -51,6 +51,7 @@
 	compatible = "sinovoip,bananapi-m64", "allwinner,sun50i-a64";
 
 	aliases {
+		ethernet0 = &emac;
 		serial0 = &uart0;
 		serial1 = &uart1;
 	};

arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts

@@ -51,6 +51,7 @@
 	compatible = "pine64,pine64", "allwinner,sun50i-a64";
 
 	aliases {
+		ethernet0 = &emac;
 		serial0 = &uart0;
 		serial1 = &uart1;
 		serial2 = &uart2;

arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts

@@ -53,6 +53,7 @@
 		     "allwinner,sun50i-a64";
 
 	aliases {
+		ethernet0 = &emac;
 		serial0 = &uart0;
 	};
 

arch/arm64/boot/dts/allwinner/sun50i-h5.dtsi

@@ -120,5 +120,8 @@
 };
 
 &pio {
+	interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>;
 	compatible = "allwinner,sun50i-h5-pinctrl";
 };

arch/arm64/boot/dts/renesas/salvator-common.dtsi

@@ -45,7 +45,7 @@
 		stdout-path = "serial0:115200n8";
 	};
 
-	audio_clkout: audio_clkout {
+	audio_clkout: audio-clkout {
 		/*
 		 * This is same as <&rcar_sound 0>
 		 * but needed to avoid cs2000/rcar_sound probe dead-lock

arch/arm64/include/asm/arch_timer.h

@@ -65,13 +65,13 @@ DECLARE_PER_CPU(const struct arch_timer_erratum_workaround *,
 	u64 _val;							\
 	if (needs_unstable_timer_counter_workaround()) {		\
 		const struct arch_timer_erratum_workaround *wa;		\
-		preempt_disable();					\
+		preempt_disable_notrace();				\
 		wa = __this_cpu_read(timer_unstable_counter_workaround); \
 		if (wa && wa->read_##reg)				\
 			_val = wa->read_##reg();			\
 		else							\
 			_val = read_sysreg(reg);			\
-		preempt_enable();					\
+		preempt_enable_notrace();				\
 	} else {							\
 		_val = read_sysreg(reg);				\
 	}								\

arch/arm64/include/asm/elf.h

@@ -114,10 +114,10 @@
 
 /*
  * This is the base location for PIE (ET_DYN with INTERP) loads. On
- * 64-bit, this is raised to 4GB to leave the entire 32-bit address
+ * 64-bit, this is above 4GB to leave the entire 32-bit address
  * space open for things that want to use the area for 32-bit pointers.
  */
-#define ELF_ET_DYN_BASE		0x100000000UL
+#define ELF_ET_DYN_BASE		(2 * TASK_SIZE_64 / 3)
 
 #ifndef __ASSEMBLY__
 

arch/arm64/kernel/fpsimd.c

@@ -161,9 +161,11 @@ void fpsimd_flush_thread(void)
 {
 	if (!system_supports_fpsimd())
 		return;
+	preempt_disable();
 	memset(&current->thread.fpsimd_state, 0, sizeof(struct fpsimd_state));
 	fpsimd_flush_task_state(current);
 	set_thread_flag(TIF_FOREIGN_FPSTATE);
+	preempt_enable();
 }
 
 /*

arch/arm64/kernel/head.S

@@ -354,7 +354,6 @@ __primary_switched:
 	tst	x23, ~(MIN_KIMG_ALIGN - 1)	// already running randomized?
 	b.ne	0f
 	mov	x0, x21				// pass FDT address in x0
-	mov	x1, x23				// pass modulo offset in x1
 	bl	kaslr_early_init		// parse FDT for KASLR options
 	cbz	x0, 0f				// KASLR disabled? just proceed
 	orr	x23, x23, x0			// record KASLR offset

arch/arm64/kernel/kaslr.c

@@ -75,7 +75,7 @@ extern void *__init __fixmap_remap_fdt(phys_addr_t dt_phys, int *size,
  * containing function pointers) to be reinitialized, and zero-initialized
  * .bss variables will be reset to 0.
  */
-u64 __init kaslr_early_init(u64 dt_phys, u64 modulo_offset)
+u64 __init kaslr_early_init(u64 dt_phys)
 {
 	void *fdt;
 	u64 seed, offset, mask, module_range;
@@ -131,15 +131,17 @@ u64 __init kaslr_early_init(u64 dt_phys, u64 modulo_offset)
 	/*
 	 * The kernel Image should not extend across a 1GB/32MB/512MB alignment
 	 * boundary (for 4KB/16KB/64KB granule kernels, respectively). If this
-	 * happens, increase the KASLR offset by the size of the kernel image
-	 * rounded up by SWAPPER_BLOCK_SIZE.
+	 * happens, round down the KASLR offset by (1 << SWAPPER_TABLE_SHIFT).
+	 *
+	 * NOTE: The references to _text and _end below will already take the
+	 *       modulo offset (the physical displacement modulo 2 MB) into
+	 *       account, given that the physical placement is controlled by
+	 *       the loader, and will not change as a result of the virtual
+	 *       mapping we choose.
 	 */
-	if ((((u64)_text + offset + modulo_offset) >> SWAPPER_TABLE_SHIFT) !=
-	    (((u64)_end + offset + modulo_offset) >> SWAPPER_TABLE_SHIFT)) {
-		u64 kimg_sz = _end - _text;
-		offset = (offset + round_up(kimg_sz, SWAPPER_BLOCK_SIZE))
-				& mask;
-	}
+	if ((((u64)_text + offset) >> SWAPPER_TABLE_SHIFT) !=
+	    (((u64)_end + offset) >> SWAPPER_TABLE_SHIFT))
+		offset = round_down(offset, 1 << SWAPPER_TABLE_SHIFT);
 
 	if (IS_ENABLED(CONFIG_KASAN))
 		/*

arch/arm64/mm/fault.c

@@ -435,8 +435,11 @@ retry:
 		 * the mmap_sem because it would already be released
 		 * in __lock_page_or_retry in mm/filemap.c.
 		 */
-		if (fatal_signal_pending(current))
+		if (fatal_signal_pending(current)) {
+			if (!user_mode(regs))
+				goto no_context;
 			return 0;
+		}
 
 		/*
 		 * Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk of

arch/powerpc/Kconfig

@@ -199,7 +199,7 @@ config PPC
 	select HAVE_OPTPROBES			if PPC64
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_EVENTS_NMI		if PPC64
-	select HAVE_HARDLOCKUP_DETECTOR_PERF	if HAVE_PERF_EVENTS_NMI && !HAVE_HARDLOCKUP_DETECTOR_ARCH
+	select HAVE_HARDLOCKUP_DETECTOR_PERF	if PERF_EVENTS && HAVE_PERF_EVENTS_NMI && !HAVE_HARDLOCKUP_DETECTOR_ARCH
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_RCU_TABLE_FREE		if SMP

arch/powerpc/include/asm/mmu_context.h

@@ -90,6 +90,24 @@ static inline void switch_mm_irqs_off(struct mm_struct *prev,
 	/* Mark this context has been used on the new CPU */
 	if (!cpumask_test_cpu(smp_processor_id(), mm_cpumask(next))) {
 		cpumask_set_cpu(smp_processor_id(), mm_cpumask(next));
+
+		/*
+		 * This full barrier orders the store to the cpumask above vs
+		 * a subsequent operation which allows this CPU to begin loading
+		 * translations for next.
+		 *
+		 * When using the radix MMU that operation is the load of the
+		 * MMU context id, which is then moved to SPRN_PID.
+		 *
+		 * For the hash MMU it is either the first load from slb_cache
+		 * in switch_slb(), and/or the store of paca->mm_ctx_id in
+		 * copy_mm_to_paca().
+		 *
+		 * On the read side the barrier is in pte_xchg(), which orders
+		 * the store to the PTE vs the load of mm_cpumask.
+		 */
+		smp_mb();
+
 		new_on_cpu = true;
 	}
 

arch/powerpc/include/asm/pgtable-be-types.h

@@ -87,6 +87,7 @@ static inline bool pte_xchg(pte_t *ptep, pte_t old, pte_t new)
 	unsigned long *p = (unsigned long *)ptep;
 	__be64 prev;
 
+	/* See comment in switch_mm_irqs_off() */
 	prev = (__force __be64)__cmpxchg_u64(p, (__force unsigned long)pte_raw(old),
 					     (__force unsigned long)pte_raw(new));
 

arch/powerpc/include/asm/pgtable-types.h

@@ -62,6 +62,7 @@ static inline bool pte_xchg(pte_t *ptep, pte_t old, pte_t new)
 {
 	unsigned long *p = (unsigned long *)ptep;
 
+	/* See comment in switch_mm_irqs_off() */
 	return pte_val(old) == __cmpxchg_u64(p, pte_val(old), pte_val(new));
 }
 #endif

arch/powerpc/kernel/process.c

@@ -362,7 +362,8 @@ void enable_kernel_vsx(void)
 
 	cpumsr = msr_check_and_set(MSR_FP|MSR_VEC|MSR_VSX);
 
-	if (current->thread.regs && (current->thread.regs->msr & MSR_VSX)) {
+	if (current->thread.regs &&
+	    (current->thread.regs->msr & (MSR_VSX|MSR_VEC|MSR_FP))) {
 		check_if_tm_restore_required(current);
 		/*
 		 * If a thread has already been reclaimed then the
@@ -386,7 +387,7 @@ void flush_vsx_to_thread(struct task_struct *tsk)
 {
 	if (tsk->thread.regs) {
 		preempt_disable();
-		if (tsk->thread.regs->msr & MSR_VSX) {
+		if (tsk->thread.regs->msr & (MSR_VSX|MSR_VEC|MSR_FP)) {
 			BUG_ON(tsk != current);
 			giveup_vsx(tsk);
 		}

arch/powerpc/kvm/book3s_64_vio.c

@@ -294,32 +294,26 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 				   struct kvm_create_spapr_tce_64 *args)
 {
 	struct kvmppc_spapr_tce_table *stt = NULL;
+	struct kvmppc_spapr_tce_table *siter;
 	unsigned long npages, size;
 	int ret = -ENOMEM;
 	int i;
+	int fd = -1;
 
 	if (!args->size)
 		return -EINVAL;
 
-	/* Check this LIOBN hasn't been previously allocated */
-	list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) {
-		if (stt->liobn == args->liobn)
-			return -EBUSY;
-	}
-
 	size = _ALIGN_UP(args->size, PAGE_SIZE >> 3);
 	npages = kvmppc_tce_pages(size);
 	ret = kvmppc_account_memlimit(kvmppc_stt_pages(npages), true);
-	if (ret) {
-		stt = NULL;
-		goto fail;
-	}
+	if (ret)
+		return ret;
 
 	ret = -ENOMEM;
 	stt = kzalloc(sizeof(*stt) + npages * sizeof(struct page *),
 		      GFP_KERNEL);
 	if (!stt)
-		goto fail;
+		goto fail_acct;
 
 	stt->liobn = args->liobn;
 	stt->page_shift = args->page_shift;
@@ -334,24 +328,42 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 			goto fail;
 	}
 
-	kvm_get_kvm(kvm);
+	ret = fd = anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops,
+				    stt, O_RDWR | O_CLOEXEC);
+	if (ret < 0)
+		goto fail;
 
 	mutex_lock(&kvm->lock);
-	list_add_rcu(&stt->list, &kvm->arch.spapr_tce_tables);
+
+	/* Check this LIOBN hasn't been previously allocated */
+	ret = 0;
+	list_for_each_entry(siter, &kvm->arch.spapr_tce_tables, list) {
+		if (siter->liobn == args->liobn) {
+			ret = -EBUSY;
+			break;
+		}
+	}
+
+	if (!ret) {
+		list_add_rcu(&stt->list, &kvm->arch.spapr_tce_tables);
+		kvm_get_kvm(kvm);
+	}
 
 	mutex_unlock(&kvm->lock);
 
-	return anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops,
-				stt, O_RDWR | O_CLOEXEC);
+	if (!ret)
+		return fd;
 
-fail:
-	if (stt) {
-		for (i = 0; i < npages; i++)
-			if (stt->pages[i])
-				__free_page(stt->pages[i]);
+	put_unused_fd(fd);
 
-		kfree(stt);
-	}
+ fail:
+	for (i = 0; i < npages; i++)
+		if (stt->pages[i])
+			__free_page(stt->pages[i]);
+
+	kfree(stt);
+ fail_acct:
+	kvmppc_account_memlimit(kvmppc_stt_pages(npages), false);
 	return ret;
 }
 

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -1291,6 +1291,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	/* Hypervisor doorbell - exit only if host IPI flag set */
 	cmpwi	r12, BOOK3S_INTERRUPT_H_DOORBELL
 	bne	3f
+BEGIN_FTR_SECTION
+	PPC_MSGSYNC
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	lbz	r0, HSTATE_HOST_IPI(r13)
 	cmpwi	r0, 0
 	beq	4f

arch/powerpc/kvm/book3s_xive_template.c

@@ -16,7 +16,22 @@ static void GLUE(X_PFX,ack_pending)(struct kvmppc_xive_vcpu *xc)
 	u8 cppr;
 	u16 ack;
 
-	/* XXX DD1 bug workaround: Check PIPR vs. CPPR first ! */
+	/*
+	 * Ensure any previous store to CPPR is ordered vs.
+	 * the subsequent loads from PIPR or ACK.
+	 */
+	eieio();
+
+	/*
+	 * DD1 bug workaround: If PIPR is less favored than CPPR
+	 * ignore the interrupt or we might incorrectly lose an IPB
+	 * bit.
+	 */
+	if (cpu_has_feature(CPU_FTR_POWER9_DD1)) {
+		u8 pipr = __x_readb(__x_tima + TM_QW1_OS + TM_PIPR);
+		if (pipr >= xc->hw_cppr)
+			return;
+	}
 
 	/* Perform the acknowledge OS to register cycle. */
 	ack = be16_to_cpu(__x_readw(__x_tima + TM_SPC_ACK_OS_REG));
@@ -235,6 +250,11 @@ skip_ipi:
 	/*
 	 * If we found an interrupt, adjust what the guest CPPR should
 	 * be as if we had just fetched that interrupt from HW.
+	 *
+	 * Note: This can only make xc->cppr smaller as the previous
+	 * loop will only exit with hirq != 0 if prio is lower than
+	 * the current xc->cppr. Thus we don't need to re-check xc->mfrr
+	 * for pending IPIs.
 	 */
 	if (hirq)
 		xc->cppr = prio;
@@ -380,6 +400,12 @@ X_STATIC int GLUE(X_PFX,h_cppr)(struct kvm_vcpu *vcpu, unsigned long cppr)
 	old_cppr = xc->cppr;
 	xc->cppr = cppr;
 
+	/*
+	 * Order the above update of xc->cppr with the subsequent
+	 * read of xc->mfrr inside push_pending_to_hw()
+	 */
+	smp_mb();
+
 	/*
 	 * We are masking less, we need to look for pending things
 	 * to deliver and set VP pending bits accordingly to trigger
@@ -420,21 +446,37 @@ X_STATIC int GLUE(X_PFX,h_eoi)(struct kvm_vcpu *vcpu, unsigned long xirr)
 	 * used to signal MFRR changes is EOId when fetched from
 	 * the queue.
 	 */
-	if (irq == XICS_IPI || irq == 0)
+	if (irq == XICS_IPI || irq == 0) {
+		/*
+		 * This barrier orders the setting of xc->cppr vs.
+		 * subsquent test of xc->mfrr done inside
+		 * scan_interrupts and push_pending_to_hw
+		 */
+		smp_mb();
 		goto bail;
+	}
 
 	/* Find interrupt source */
 	sb = kvmppc_xive_find_source(xive, irq, &src);
 	if (!sb) {
 		pr_devel(" source not found !\n");
 		rc = H_PARAMETER;
+		/* Same as above */
+		smp_mb();
 		goto bail;
 	}
 	state = &sb->irq_state[src];
 	kvmppc_xive_select_irq(state, &hw_num, &xd);
 
 	state->in_eoi = true;
-	mb();
+
+	/*
+	 * This barrier orders both setting of in_eoi above vs,
+	 * subsequent test of guest_priority, and the setting
+	 * of xc->cppr vs. subsquent test of xc->mfrr done inside
+	 * scan_interrupts and push_pending_to_hw
+	 */
+	smp_mb();
 
 again:
 	if (state->guest_priority == MASKED) {
@@ -461,6 +503,14 @@ again:
 
 	}
 
+	/*
+	 * This barrier orders the above guest_priority check
+	 * and spin_lock/unlock with clearing in_eoi below.
+	 *
+	 * It also has to be a full mb() as it must ensure
+	 * the MMIOs done in source_eoi() are completed before
+	 * state->in_eoi is visible.
+	 */
 	mb();
 	state->in_eoi = false;
 bail:
@@ -495,6 +545,18 @@ X_STATIC int GLUE(X_PFX,h_ipi)(struct kvm_vcpu *vcpu, unsigned long server,
 	/* Locklessly write over MFRR */
 	xc->mfrr = mfrr;
 
+	/*
+	 * The load of xc->cppr below and the subsequent MMIO store
+	 * to the IPI must happen after the above mfrr update is
+	 * globally visible so that:
+	 *
+	 * - Synchronize with another CPU doing an H_EOI or a H_CPPR
+	 *   updating xc->cppr then reading xc->mfrr.
+	 *
+	 * - The target of the IPI sees the xc->mfrr update
+	 */
+	mb();
+
 	/* Shoot the IPI if most favored than target cppr */
 	if (mfrr < xc->cppr)
 		__x_writeq(0, __x_trig_page(&xc->vp_ipi_data));

arch/s390/kvm/sthyi.c

@@ -394,7 +394,7 @@ static int sthyi(u64 vaddr)
 		"srl     %[cc],28\n"
 		: [cc] "=d" (cc)
 		: [code] "d" (code), [addr] "a" (addr)
-		: "memory", "cc");
+		: "3", "memory", "cc");
 	return cc;
 }
 
@@ -425,7 +425,7 @@ int handle_sthyi(struct kvm_vcpu *vcpu)
 	VCPU_EVENT(vcpu, 3, "STHYI: fc: %llu addr: 0x%016llx", code, addr);
 	trace_kvm_s390_handle_sthyi(vcpu, code, addr);
 
-	if (reg1 == reg2 || reg1 & 1 || reg2 & 1 || addr & ~PAGE_MASK)
+	if (reg1 == reg2 || reg1 & 1 || reg2 & 1)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
 	if (code & 0xffff) {
@@ -433,6 +433,9 @@ int handle_sthyi(struct kvm_vcpu *vcpu)
 		goto out;
 	}
 
+	if (addr & ~PAGE_MASK)
+		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
 	/*
 	 * If the page has not yet been faulted in, we want to do that
 	 * now and not after all the expensive calculations.

arch/sparc/include/asm/page_32.h

@@ -68,6 +68,7 @@ typedef struct { unsigned long iopgprot; } iopgprot_t;
 #define iopgprot_val(x)	((x).iopgprot)
 
 #define __pte(x)	((pte_t) { (x) } )
+#define __pmd(x)	((pmd_t) { { (x) }, })
 #define __iopte(x)	((iopte_t) { (x) } )
 #define __pgd(x)	((pgd_t) { (x) } )
 #define __ctxd(x)	((ctxd_t) { (x) } )
@@ -95,6 +96,7 @@ typedef unsigned long iopgprot_t;
 #define iopgprot_val(x)	(x)
 
 #define __pte(x)	(x)
+#define __pmd(x)	((pmd_t) { { (x) }, })
 #define __iopte(x)	(x)
 #define __pgd(x)	(x)
 #define __ctxd(x)	(x)

arch/sparc/kernel/pci_sun4v.c

@@ -1266,8 +1266,6 @@ static int pci_sun4v_probe(struct platform_device *op)
 			 * ATU group, but ATU hcalls won't be available.
 			 */
 			hv_atu = false;
-			pr_err(PFX "Could not register hvapi ATU err=%d\n",
-			       err);
 		} else {
 			pr_info(PFX "Registered hvapi ATU major[%lu] minor[%lu]\n",
 				vatu_major, vatu_minor);

arch/sparc/kernel/pcic.c

@@ -602,7 +602,7 @@ void pcibios_fixup_bus(struct pci_bus *bus)
 {
 	struct pci_dev *dev;
 	int i, has_io, has_mem;
-	unsigned int cmd;
+	unsigned int cmd = 0;
 	struct linux_pcic *pcic;
 	/* struct linux_pbm_info* pbm = &pcic->pbm; */
 	int node;

arch/sparc/lib/multi3.S

@@ -5,26 +5,26 @@
 	.align	4
 ENTRY(__multi3) /* %o0 = u, %o1 = v */
 	mov	%o1, %g1
-	srl	%o3, 0, %g4
-	mulx	%g4, %g1, %o1
+	srl	%o3, 0, %o4
+	mulx	%o4, %g1, %o1
 	srlx	%g1, 0x20, %g3
-	mulx	%g3, %g4, %g5
-	sllx	%g5, 0x20, %o5
-	srl	%g1, 0, %g4
+	mulx	%g3, %o4, %g7
+	sllx	%g7, 0x20, %o5
+	srl	%g1, 0, %o4
 	sub	%o1, %o5, %o5
 	srlx	%o5, 0x20, %o5
-	addcc	%g5, %o5, %g5
+	addcc	%g7, %o5, %g7
 	srlx	%o3, 0x20, %o5
-	mulx	%g4, %o5, %g4
+	mulx	%o4, %o5, %o4
 	mulx	%g3, %o5, %o5
 	sethi	%hi(0x80000000), %g3
-	addcc	%g5, %g4, %g5
-	srlx	%g5, 0x20, %g5
+	addcc	%g7, %o4, %g7
+	srlx	%g7, 0x20, %g7
 	add	%g3, %g3, %g3
 	movcc	%xcc, %g0, %g3
-	addcc	%o5, %g5, %o5
-	sllx	%g4, 0x20, %g4
-	add	%o1, %g4, %o1
+	addcc	%o5, %g7, %o5
+	sllx	%o4, 0x20, %o4
+	add	%o1, %o4, %o1
 	add	%o5, %g3, %g2
 	mulx	%g1, %o2, %g1
 	add	%g1, %g2, %g1

arch/x86/Kconfig

@@ -100,6 +100,7 @@ config X86
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
 	select GENERIC_TIME_VSYSCALL
+	select HARDLOCKUP_CHECK_TIMESTAMP	if X86_64
 	select HAVE_ACPI_APEI			if ACPI
 	select HAVE_ACPI_APEI_NMI		if ACPI
 	select HAVE_ALIGNED_STRUCT_PAGE		if SLUB
@@ -163,7 +164,7 @@ config X86
 	select HAVE_PCSPKR_PLATFORM
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_EVENTS_NMI
-	select HAVE_HARDLOCKUP_DETECTOR_PERF	if HAVE_PERF_EVENTS_NMI
+	select HAVE_HARDLOCKUP_DETECTOR_PERF	if PERF_EVENTS && HAVE_PERF_EVENTS_NMI
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_REGS_AND_STACK_ACCESS_API

arch/x86/crypto/sha1_avx2_x86_64_asm.S

@@ -117,11 +117,10 @@
 	.set T1, REG_T1
 .endm
 
-#define K_BASE		%r8
 #define HASH_PTR	%r9
+#define BLOCKS_CTR	%r8
 #define BUFFER_PTR	%r10
 #define BUFFER_PTR2	%r13
-#define BUFFER_END	%r11
 
 #define PRECALC_BUF	%r14
 #define WK_BUF		%r15
@@ -205,14 +204,14 @@
 		 * blended AVX2 and ALU instruction scheduling
 		 * 1 vector iteration per 8 rounds
 		 */
-		vmovdqu ((i * 2) + PRECALC_OFFSET)(BUFFER_PTR), W_TMP
+		vmovdqu (i * 2)(BUFFER_PTR), W_TMP
 	.elseif ((i & 7) == 1)
-		vinsertf128 $1, (((i-1) * 2)+PRECALC_OFFSET)(BUFFER_PTR2),\
+		vinsertf128 $1, ((i-1) * 2)(BUFFER_PTR2),\
 			 WY_TMP, WY_TMP
 	.elseif ((i & 7) == 2)
 		vpshufb YMM_SHUFB_BSWAP, WY_TMP, WY
 	.elseif ((i & 7) == 4)
-		vpaddd  K_XMM(K_BASE), WY, WY_TMP
+		vpaddd  K_XMM + K_XMM_AR(%rip), WY, WY_TMP
 	.elseif ((i & 7) == 7)
 		vmovdqu  WY_TMP, PRECALC_WK(i&~7)
 
@@ -255,7 +254,7 @@
 		vpxor	WY, WY_TMP, WY_TMP
 	.elseif ((i & 7) == 7)
 		vpxor	WY_TMP2, WY_TMP, WY
-		vpaddd	K_XMM(K_BASE), WY, WY_TMP
+		vpaddd  K_XMM + K_XMM_AR(%rip), WY, WY_TMP
 		vmovdqu	WY_TMP, PRECALC_WK(i&~7)
 
 		PRECALC_ROTATE_WY
@@ -291,7 +290,7 @@
 		vpsrld	$30, WY, WY
 		vpor	WY, WY_TMP, WY
 	.elseif ((i & 7) == 7)
-		vpaddd	K_XMM(K_BASE), WY, WY_TMP
+		vpaddd  K_XMM + K_XMM_AR(%rip), WY, WY_TMP
 		vmovdqu	WY_TMP, PRECALC_WK(i&~7)
 
 		PRECALC_ROTATE_WY
@@ -446,6 +445,16 @@
 
 .endm
 
+/* Add constant only if (%2 > %3) condition met (uses RTA as temp)
+ * %1 + %2 >= %3 ? %4 : 0
+ */
+.macro ADD_IF_GE a, b, c, d
+	mov     \a, RTA
+	add     $\d, RTA
+	cmp     $\c, \b
+	cmovge  RTA, \a
+.endm
+
 /*
  * macro implements 80 rounds of SHA-1, for multiple blocks with s/w pipelining
  */
@@ -463,13 +472,16 @@
 	lea	(2*4*80+32)(%rsp), WK_BUF
 
 	# Precalc WK for first 2 blocks
-	PRECALC_OFFSET = 0
+	ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 2, 64
 	.set i, 0
 	.rept    160
 		PRECALC i
 		.set i, i + 1
 	.endr
-	PRECALC_OFFSET = 128
+
+	/* Go to next block if needed */
+	ADD_IF_GE BUFFER_PTR, BLOCKS_CTR, 3, 128
+	ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 4, 128
 	xchg	WK_BUF, PRECALC_BUF
 
 	.align 32
@@ -479,8 +491,8 @@ _loop:
 	 * we use K_BASE value as a signal of a last block,
 	 * it is set below by: cmovae BUFFER_PTR, K_BASE
 	 */
-	cmp	K_BASE, BUFFER_PTR
-	jne	_begin
+	test BLOCKS_CTR, BLOCKS_CTR
+	jnz _begin
 	.align 32
 	jmp	_end
 	.align 32
@@ -512,10 +524,10 @@ _loop0:
 		.set j, j+2
 	.endr
 
-	add	$(2*64), BUFFER_PTR       /* move to next odd-64-byte block */
-	cmp	BUFFER_END, BUFFER_PTR    /* is current block the last one? */
-	cmovae	K_BASE, BUFFER_PTR	/* signal the last iteration smartly */
-
+	/* Update Counter */
+	sub $1, BLOCKS_CTR
+	/* Move to the next block only if needed*/
+	ADD_IF_GE BUFFER_PTR, BLOCKS_CTR, 4, 128
 	/*
 	 * rounds
 	 * 60,62,64,66,68
@@ -532,8 +544,8 @@ _loop0:
 	UPDATE_HASH	12(HASH_PTR), D
 	UPDATE_HASH	16(HASH_PTR), E
 
-	cmp	K_BASE, BUFFER_PTR	/* is current block the last one? */
-	je	_loop
+	test	BLOCKS_CTR, BLOCKS_CTR
+	jz	_loop
 
 	mov	TB, B
 
@@ -575,10 +587,10 @@ _loop2:
 		.set j, j+2
 	.endr
 
-	add	$(2*64), BUFFER_PTR2      /* move to next even-64-byte block */
-
-	cmp	BUFFER_END, BUFFER_PTR2   /* is current block the last one */
-	cmovae	K_BASE, BUFFER_PTR       /* signal the last iteration smartly */
+	/* update counter */
+	sub     $1, BLOCKS_CTR
+	/* Move to the next block only if needed*/
+	ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 4, 128
 
 	jmp	_loop3
 _loop3:
@@ -641,19 +653,12 @@ _loop3:
 
 	avx2_zeroupper
 
-	lea	K_XMM_AR(%rip), K_BASE
-
+	/* Setup initial values */
 	mov	CTX, HASH_PTR
 	mov	BUF, BUFFER_PTR
-	lea	64(BUF), BUFFER_PTR2
-
-	shl	$6, CNT			/* mul by 64 */
-	add	BUF, CNT
-	add	$64, CNT
-	mov	CNT, BUFFER_END
 
-	cmp	BUFFER_END, BUFFER_PTR2
-	cmovae	K_BASE, BUFFER_PTR2
+	mov	BUF, BUFFER_PTR2
+	mov	CNT, BLOCKS_CTR
 
 	xmm_mov	BSWAP_SHUFB_CTL(%rip), YMM_SHUFB_BSWAP
 

arch/x86/crypto/sha1_ssse3_glue.c

@@ -201,7 +201,7 @@ asmlinkage void sha1_transform_avx2(u32 *digest, const char *data,
 
 static bool avx2_usable(void)
 {
-	if (false && avx_usable() && boot_cpu_has(X86_FEATURE_AVX2)
+	if (avx_usable() && boot_cpu_has(X86_FEATURE_AVX2)
 		&& boot_cpu_has(X86_FEATURE_BMI1)
 		&& boot_cpu_has(X86_FEATURE_BMI2))
 		return true;

arch/x86/entry/entry_64.S

@@ -1211,6 +1211,8 @@ ENTRY(nmi)
 	 * other IST entries.
 	 */
 
+	ASM_CLAC
+
 	/* Use %rdx as our temp variable throughout */
 	pushq	%rdx
 

arch/x86/events/core.c

@@ -2114,7 +2114,7 @@ static void refresh_pce(void *ignored)
 	load_mm_cr4(this_cpu_read(cpu_tlbstate.loaded_mm));
 }
 
-static void x86_pmu_event_mapped(struct perf_event *event)
+static void x86_pmu_event_mapped(struct perf_event *event, struct mm_struct *mm)
 {
 	if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED))
 		return;
@@ -2129,22 +2129,20 @@ static void x86_pmu_event_mapped(struct perf_event *event)
 	 * For now, this can't happen because all callers hold mmap_sem
 	 * for write.  If this changes, we'll need a different solution.
 	 */
-	lockdep_assert_held_exclusive(&current->mm->mmap_sem);
+	lockdep_assert_held_exclusive(&mm->mmap_sem);
 
-	if (atomic_inc_return(&current->mm->context.perf_rdpmc_allowed) == 1)
-		on_each_cpu_mask(mm_cpumask(current->mm), refresh_pce, NULL, 1);
+	if (atomic_inc_return(&mm->context.perf_rdpmc_allowed) == 1)
+		on_each_cpu_mask(mm_cpumask(mm), refresh_pce, NULL, 1);
 }
 
-static void x86_pmu_event_unmapped(struct perf_event *event)
+static void x86_pmu_event_unmapped(struct perf_event *event, struct mm_struct *mm)
 {
-	if (!current->mm)
-		return;
 
 	if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED))
 		return;
 
-	if (atomic_dec_and_test(&current->mm->context.perf_rdpmc_allowed))
-		on_each_cpu_mask(mm_cpumask(current->mm), refresh_pce, NULL, 1);
+	if (atomic_dec_and_test(&mm->context.perf_rdpmc_allowed))
+		on_each_cpu_mask(mm_cpumask(mm), refresh_pce, NULL, 1);
 }
 
 static int x86_pmu_event_idx(struct perf_event *event)

arch/x86/events/intel/bts.c

@@ -69,7 +69,7 @@ struct bts_buffer {
 	struct bts_phys	buf[0];
 };
 
-struct pmu bts_pmu;
+static struct pmu bts_pmu;
 
 static size_t buf_size(struct page *page)
 {

arch/x86/events/intel/p4.c

@@ -587,7 +587,7 @@ static __initconst const u64 p4_hw_cache_event_ids
  * P4_CONFIG_ALIASABLE or bits for P4_PEBS_METRIC, they are
  * either up to date automatically or not applicable at all.
  */
-struct p4_event_alias {
+static struct p4_event_alias {
 	u64 original;
 	u64 alternative;
 } p4_event_aliases[] = {

arch/x86/events/intel/rapl.c

@@ -559,7 +559,7 @@ static struct attribute_group rapl_pmu_format_group = {
 	.attrs = rapl_formats_attr,
 };
 
-const struct attribute_group *rapl_attr_groups[] = {
+static const struct attribute_group *rapl_attr_groups[] = {
 	&rapl_pmu_attr_group,
 	&rapl_pmu_format_group,
 	&rapl_pmu_events_group,

arch/x86/events/intel/uncore.c

@@ -721,7 +721,7 @@ static struct attribute *uncore_pmu_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group uncore_pmu_attr_group = {
+static const struct attribute_group uncore_pmu_attr_group = {
 	.attrs = uncore_pmu_attrs,
 };
 

arch/x86/events/intel/uncore_nhmex.c

@@ -272,7 +272,7 @@ static struct attribute *nhmex_uncore_ubox_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group nhmex_uncore_ubox_format_group = {
+static const struct attribute_group nhmex_uncore_ubox_format_group = {
 	.name		= "format",
 	.attrs		= nhmex_uncore_ubox_formats_attr,
 };
@@ -299,7 +299,7 @@ static struct attribute *nhmex_uncore_cbox_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group nhmex_uncore_cbox_format_group = {
+static const struct attribute_group nhmex_uncore_cbox_format_group = {
 	.name = "format",
 	.attrs = nhmex_uncore_cbox_formats_attr,
 };
@@ -407,7 +407,7 @@ static struct attribute *nhmex_uncore_bbox_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group nhmex_uncore_bbox_format_group = {
+static const struct attribute_group nhmex_uncore_bbox_format_group = {
 	.name = "format",
 	.attrs = nhmex_uncore_bbox_formats_attr,
 };
@@ -484,7 +484,7 @@ static struct attribute *nhmex_uncore_sbox_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group nhmex_uncore_sbox_format_group = {
+static const struct attribute_group nhmex_uncore_sbox_format_group = {
 	.name			= "format",
 	.attrs			= nhmex_uncore_sbox_formats_attr,
 };
@@ -898,7 +898,7 @@ static struct attribute *nhmex_uncore_mbox_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group nhmex_uncore_mbox_format_group = {
+static const struct attribute_group nhmex_uncore_mbox_format_group = {
 	.name		= "format",
 	.attrs		= nhmex_uncore_mbox_formats_attr,
 };
@@ -1163,7 +1163,7 @@ static struct attribute *nhmex_uncore_rbox_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group nhmex_uncore_rbox_format_group = {
+static const struct attribute_group nhmex_uncore_rbox_format_group = {
 	.name = "format",
 	.attrs = nhmex_uncore_rbox_formats_attr,
 };

arch/x86/events/intel/uncore_snb.c

@@ -130,7 +130,7 @@ static struct attribute *snb_uncore_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group snb_uncore_format_group = {
+static const struct attribute_group snb_uncore_format_group = {
 	.name		= "format",
 	.attrs		= snb_uncore_formats_attr,
 };
@@ -289,7 +289,7 @@ static struct attribute *snb_uncore_imc_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group snb_uncore_imc_format_group = {
+static const struct attribute_group snb_uncore_imc_format_group = {
 	.name = "format",
 	.attrs = snb_uncore_imc_formats_attr,
 };
@@ -769,7 +769,7 @@ static struct attribute *nhm_uncore_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group nhm_uncore_format_group = {
+static const struct attribute_group nhm_uncore_format_group = {
 	.name = "format",
 	.attrs = nhm_uncore_formats_attr,
 };

arch/x86/events/intel/uncore_snbep.c

@@ -602,27 +602,27 @@ static struct uncore_event_desc snbep_uncore_qpi_events[] = {
 	{ /* end: all zeroes */ },
 };
 
-static struct attribute_group snbep_uncore_format_group = {
+static const struct attribute_group snbep_uncore_format_group = {
 	.name = "format",
 	.attrs = snbep_uncore_formats_attr,
 };
 
-static struct attribute_group snbep_uncore_ubox_format_group = {
+static const struct attribute_group snbep_uncore_ubox_format_group = {
 	.name = "format",
 	.attrs = snbep_uncore_ubox_formats_attr,
 };
 
-static struct attribute_group snbep_uncore_cbox_format_group = {
+static const struct attribute_group snbep_uncore_cbox_format_group = {
 	.name = "format",
 	.attrs = snbep_uncore_cbox_formats_attr,
 };
 
-static struct attribute_group snbep_uncore_pcu_format_group = {
+static const struct attribute_group snbep_uncore_pcu_format_group = {
 	.name = "format",
 	.attrs = snbep_uncore_pcu_formats_attr,
 };
 
-static struct attribute_group snbep_uncore_qpi_format_group = {
+static const struct attribute_group snbep_uncore_qpi_format_group = {
 	.name = "format",
 	.attrs = snbep_uncore_qpi_formats_attr,
 };
@@ -1431,27 +1431,27 @@ static struct attribute *ivbep_uncore_qpi_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group ivbep_uncore_format_group = {
+static const struct attribute_group ivbep_uncore_format_group = {
 	.name = "format",
 	.attrs = ivbep_uncore_formats_attr,
 };
 
-static struct attribute_group ivbep_uncore_ubox_format_group = {
+static const struct attribute_group ivbep_uncore_ubox_format_group = {
 	.name = "format",
 	.attrs = ivbep_uncore_ubox_formats_attr,
 };
 
-static struct attribute_group ivbep_uncore_cbox_format_group = {
+static const struct attribute_group ivbep_uncore_cbox_format_group = {
 	.name = "format",
 	.attrs = ivbep_uncore_cbox_formats_attr,
 };
 
-static struct attribute_group ivbep_uncore_pcu_format_group = {
+static const struct attribute_group ivbep_uncore_pcu_format_group = {
 	.name = "format",
 	.attrs = ivbep_uncore_pcu_formats_attr,
 };
 
-static struct attribute_group ivbep_uncore_qpi_format_group = {
+static const struct attribute_group ivbep_uncore_qpi_format_group = {
 	.name = "format",
 	.attrs = ivbep_uncore_qpi_formats_attr,
 };
@@ -1887,7 +1887,7 @@ static struct attribute *knl_uncore_ubox_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group knl_uncore_ubox_format_group = {
+static const struct attribute_group knl_uncore_ubox_format_group = {
 	.name = "format",
 	.attrs = knl_uncore_ubox_formats_attr,
 };
@@ -1927,7 +1927,7 @@ static struct attribute *knl_uncore_cha_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group knl_uncore_cha_format_group = {
+static const struct attribute_group knl_uncore_cha_format_group = {
 	.name = "format",
 	.attrs = knl_uncore_cha_formats_attr,
 };
@@ -2037,7 +2037,7 @@ static struct attribute *knl_uncore_pcu_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group knl_uncore_pcu_format_group = {
+static const struct attribute_group knl_uncore_pcu_format_group = {
 	.name = "format",
 	.attrs = knl_uncore_pcu_formats_attr,
 };
@@ -2187,7 +2187,7 @@ static struct attribute *knl_uncore_irp_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group knl_uncore_irp_format_group = {
+static const struct attribute_group knl_uncore_irp_format_group = {
 	.name = "format",
 	.attrs = knl_uncore_irp_formats_attr,
 };
@@ -2385,7 +2385,7 @@ static struct attribute *hswep_uncore_ubox_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group hswep_uncore_ubox_format_group = {
+static const struct attribute_group hswep_uncore_ubox_format_group = {
 	.name = "format",
 	.attrs = hswep_uncore_ubox_formats_attr,
 };
@@ -2439,7 +2439,7 @@ static struct attribute *hswep_uncore_cbox_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group hswep_uncore_cbox_format_group = {
+static const struct attribute_group hswep_uncore_cbox_format_group = {
 	.name = "format",
 	.attrs = hswep_uncore_cbox_formats_attr,
 };
@@ -2621,7 +2621,7 @@ static struct attribute *hswep_uncore_sbox_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group hswep_uncore_sbox_format_group = {
+static const struct attribute_group hswep_uncore_sbox_format_group = {
 	.name = "format",
 	.attrs = hswep_uncore_sbox_formats_attr,
 };
@@ -3314,7 +3314,7 @@ static struct attribute *skx_uncore_cha_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group skx_uncore_chabox_format_group = {
+static const struct attribute_group skx_uncore_chabox_format_group = {
 	.name = "format",
 	.attrs = skx_uncore_cha_formats_attr,
 };
@@ -3427,7 +3427,7 @@ static struct attribute *skx_uncore_iio_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group skx_uncore_iio_format_group = {
+static const struct attribute_group skx_uncore_iio_format_group = {
 	.name = "format",
 	.attrs = skx_uncore_iio_formats_attr,
 };
@@ -3484,7 +3484,7 @@ static struct attribute *skx_uncore_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group skx_uncore_format_group = {
+static const struct attribute_group skx_uncore_format_group = {
 	.name = "format",
 	.attrs = skx_uncore_formats_attr,
 };
@@ -3605,7 +3605,7 @@ static struct attribute *skx_upi_uncore_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group skx_upi_uncore_format_group = {
+static const struct attribute_group skx_upi_uncore_format_group = {
 	.name = "format",
 	.attrs = skx_upi_uncore_formats_attr,
 };

arch/x86/include/asm/cpufeatures.h

@@ -286,7 +286,7 @@
 #define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */
 #define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */
 #define X86_FEATURE_AVIC	(15*32+13) /* Virtual Interrupt Controller */
-#define X86_FEATURE_VIRTUAL_VMLOAD_VMSAVE (15*32+15) /* Virtual VMLOAD VMSAVE */
+#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */
 #define X86_FEATURE_AVX512VBMI  (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/

arch/x86/include/asm/elf.h

@@ -247,11 +247,11 @@ extern int force_personality32;
 
 /*
  * This is the base location for PIE (ET_DYN with INTERP) loads. On
- * 64-bit, this is raised to 4GB to leave the entire 32-bit address
+ * 64-bit, this is above 4GB to leave the entire 32-bit address
  * space open for things that want to use the area for 32-bit pointers.
  */
 #define ELF_ET_DYN_BASE		(mmap_is_ia32() ? 0x000400000UL : \
-						  0x100000000UL)
+						  (TASK_SIZE / 3 * 2))
 
 /* This yields a mask that user programs can use to figure out what
    instruction set this CPU supports.  This could be done in user space,

arch/x86/include/asm/fpu/internal.h

@@ -450,10 +450,10 @@ static inline int copy_fpregs_to_fpstate(struct fpu *fpu)
 	return 0;
 }
 
-static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate)
+static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate, u64 mask)
 {
 	if (use_xsave()) {
-		copy_kernel_to_xregs(&fpstate->xsave, -1);
+		copy_kernel_to_xregs(&fpstate->xsave, mask);
 	} else {
 		if (use_fxsr())
 			copy_kernel_to_fxregs(&fpstate->fxsave);
@@ -477,7 +477,7 @@ static inline void copy_kernel_to_fpregs(union fpregs_state *fpstate)
 			: : [addr] "m" (fpstate));
 	}
 
-	__copy_kernel_to_fpregs(fpstate);
+	__copy_kernel_to_fpregs(fpstate, -1);
 }
 
 extern int copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size);

arch/x86/include/asm/kvm_host.h

@@ -492,6 +492,7 @@ struct kvm_vcpu_arch {
 	unsigned long cr4;
 	unsigned long cr4_guest_owned_bits;
 	unsigned long cr8;
+	u32 pkru;
 	u32 hflags;
 	u64 efer;
 	u64 apic_base;

arch/x86/include/asm/mmu_context.h

@@ -140,9 +140,7 @@ static inline int init_new_context(struct task_struct *tsk,
 		mm->context.execute_only_pkey = -1;
 	}
 	#endif
-	init_new_context_ldt(tsk, mm);
-
-	return 0;
+	return init_new_context_ldt(tsk, mm);
 }
 static inline void destroy_context(struct mm_struct *mm)
 {

arch/x86/kernel/cpu/aperfmperf.c

@@ -40,13 +40,16 @@ static void aperfmperf_snapshot_khz(void *dummy)
 	struct aperfmperf_sample *s = this_cpu_ptr(&samples);
 	ktime_t now = ktime_get();
 	s64 time_delta = ktime_ms_delta(now, s->time);
+	unsigned long flags;
 
 	/* Don't bother re-computing within the cache threshold time. */
 	if (time_delta < APERFMPERF_CACHE_THRESHOLD_MS)
 		return;
 
+	local_irq_save(flags);
 	rdmsrl(MSR_IA32_APERF, aperf);
 	rdmsrl(MSR_IA32_MPERF, mperf);
+	local_irq_restore(flags);
 
 	aperf_delta = aperf - s->aperf;
 	mperf_delta = mperf - s->mperf;

arch/x86/kernel/cpu/mcheck/therm_throt.c

@@ -122,7 +122,7 @@ static struct attribute *thermal_throttle_attrs[] = {
 	NULL
 };
 
-static struct attribute_group thermal_attr_group = {
+static const struct attribute_group thermal_attr_group = {
 	.attrs	= thermal_throttle_attrs,
 	.name	= "thermal_throttle"
 };

arch/x86/kernel/cpu/microcode/core.c

@@ -561,7 +561,7 @@ static struct attribute *mc_default_attrs[] = {
 	NULL
 };
 
-static struct attribute_group mc_attr_group = {
+static const struct attribute_group mc_attr_group = {
 	.attrs			= mc_default_attrs,
 	.name			= "microcode",
 };
@@ -707,7 +707,7 @@ static struct attribute *cpu_root_microcode_attrs[] = {
 	NULL
 };
 
-static struct attribute_group cpu_root_microcode_group = {
+static const struct attribute_group cpu_root_microcode_group = {
 	.name  = "microcode",
 	.attrs = cpu_root_microcode_attrs,
 };

arch/x86/kernel/cpu/mtrr/main.c

@@ -237,6 +237,18 @@ set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type typ
 	stop_machine(mtrr_rendezvous_handler, &data, cpu_online_mask);
 }
 
+static void set_mtrr_cpuslocked(unsigned int reg, unsigned long base,
+				unsigned long size, mtrr_type type)
+{
+	struct set_mtrr_data data = { .smp_reg = reg,
+				      .smp_base = base,
+				      .smp_size = size,
+				      .smp_type = type
+				    };
+
+	stop_machine_cpuslocked(mtrr_rendezvous_handler, &data, cpu_online_mask);
+}
+
 static void set_mtrr_from_inactive_cpu(unsigned int reg, unsigned long base,
 				      unsigned long size, mtrr_type type)
 {
@@ -370,7 +382,7 @@ int mtrr_add_page(unsigned long base, unsigned long size,
 	/* Search for an empty MTRR */
 	i = mtrr_if->get_free_region(base, size, replace);
 	if (i >= 0) {
-		set_mtrr(i, base, size, type);
+		set_mtrr_cpuslocked(i, base, size, type);
 		if (likely(replace < 0)) {
 			mtrr_usage_table[i] = 1;
 		} else {
@@ -378,7 +390,7 @@ int mtrr_add_page(unsigned long base, unsigned long size,
 			if (increment)
 				mtrr_usage_table[i]++;
 			if (unlikely(replace != i)) {
-				set_mtrr(replace, 0, 0, 0);
+				set_mtrr_cpuslocked(replace, 0, 0, 0);
 				mtrr_usage_table[replace] = 0;
 			}
 		}
@@ -506,7 +518,7 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size)
 		goto out;
 	}
 	if (--mtrr_usage_table[reg] < 1)
-		set_mtrr(reg, 0, 0, 0);
+		set_mtrr_cpuslocked(reg, 0, 0, 0);
 	error = reg;
  out:
 	mutex_unlock(&mtrr_mutex);

arch/x86/kernel/head64.c

@@ -53,6 +53,7 @@ void __head __startup_64(unsigned long physaddr)
 	pudval_t *pud;
 	pmdval_t *pmd, pmd_entry;
 	int i;
+	unsigned int *next_pgt_ptr;
 
 	/* Is the address too large? */
 	if (physaddr >> MAX_PHYSMEM_BITS)
@@ -91,9 +92,9 @@ void __head __startup_64(unsigned long physaddr)
 	 * creates a bunch of nonsense entries but that is fine --
 	 * it avoids problems around wraparound.
 	 */
-
-	pud = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr);
-	pmd = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr);
+	next_pgt_ptr = fixup_pointer(&next_early_pgt, physaddr);
+	pud = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], physaddr);
+	pmd = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], physaddr);
 
 	if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
 		p4d = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr);

arch/x86/kernel/ksysfs.c

@@ -55,7 +55,7 @@ static struct bin_attribute *boot_params_data_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group boot_params_attr_group = {
+static const struct attribute_group boot_params_attr_group = {
 	.attrs = boot_params_version_attrs,
 	.bin_attrs = boot_params_data_attrs,
 };
@@ -202,7 +202,7 @@ static struct bin_attribute *setup_data_data_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group setup_data_attr_group = {
+static const struct attribute_group setup_data_attr_group = {
 	.attrs = setup_data_type_attrs,
 	.bin_attrs = setup_data_data_attrs,
 };

arch/x86/kernel/smpboot.c

@@ -971,7 +971,8 @@ void common_cpu_up(unsigned int cpu, struct task_struct *idle)
  * Returns zero if CPU booted OK, else error code from
  * ->wakeup_secondary_cpu.
  */
-static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
+static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
+		       int *cpu0_nmi_registered)
 {
 	volatile u32 *trampoline_status =
 		(volatile u32 *) __va(real_mode_header->trampoline_status);
@@ -979,7 +980,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
 	unsigned long start_ip = real_mode_header->trampoline_start;
 
 	unsigned long boot_error = 0;
-	int cpu0_nmi_registered = 0;
 	unsigned long timeout;
 
 	idle->thread.sp = (unsigned long)task_pt_regs(idle);
@@ -1035,7 +1035,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
 		boot_error = apic->wakeup_secondary_cpu(apicid, start_ip);
 	else
 		boot_error = wakeup_cpu_via_init_nmi(cpu, start_ip, apicid,
-						     &cpu0_nmi_registered);
+						     cpu0_nmi_registered);
 
 	if (!boot_error) {
 		/*
@@ -1080,12 +1080,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
 		 */
 		smpboot_restore_warm_reset_vector();
 	}
-	/*
-	 * Clean up the nmi handler. Do this after the callin and callout sync
-	 * to avoid impact of possible long unregister time.
-	 */
-	if (cpu0_nmi_registered)
-		unregister_nmi_handler(NMI_LOCAL, "wake_cpu0");
 
 	return boot_error;
 }
@@ -1093,8 +1087,9 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
 int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
 {
 	int apicid = apic->cpu_present_to_apicid(cpu);
+	int cpu0_nmi_registered = 0;
 	unsigned long flags;
-	int err;
+	int err, ret = 0;
 
 	WARN_ON(irqs_disabled());
 
@@ -1131,10 +1126,11 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
 
 	common_cpu_up(cpu, tidle);
 
-	err = do_boot_cpu(apicid, cpu, tidle);
+	err = do_boot_cpu(apicid, cpu, tidle, &cpu0_nmi_registered);
 	if (err) {
 		pr_err("do_boot_cpu failed(%d) to wakeup CPU#%u\n", err, cpu);
-		return -EIO;
+		ret = -EIO;
+		goto unreg_nmi;
 	}
 
 	/*
@@ -1150,7 +1146,15 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
 		touch_nmi_watchdog();
 	}
 
-	return 0;
+unreg_nmi:
+	/*
+	 * Clean up the nmi handler. Do this after the callin and callout sync
+	 * to avoid impact of possible long unregister time.
+	 */
+	if (cpu0_nmi_registered)
+		unregister_nmi_handler(NMI_LOCAL, "wake_cpu0");
+
+	return ret;
 }
 
 /**

arch/x86/kvm/cpuid.c

@@ -469,7 +469,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 			entry->ecx &= kvm_cpuid_7_0_ecx_x86_features;
 			cpuid_mask(&entry->ecx, CPUID_7_ECX);
 			/* PKU is not yet implemented for shadow paging. */
-			if (!tdp_enabled)
+			if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE))
 				entry->ecx &= ~F(PKU);
 			entry->edx &= kvm_cpuid_7_0_edx_x86_features;
 			entry->edx &= get_scattered_cpuid_leaf(7, 0, CPUID_EDX);

arch/x86/kvm/kvm_cache_regs.h

@@ -84,11 +84,6 @@ static inline u64 kvm_read_edx_eax(struct kvm_vcpu *vcpu)
 		| ((u64)(kvm_register_read(vcpu, VCPU_REGS_RDX) & -1u) << 32);
 }
 
-static inline u32 kvm_read_pkru(struct kvm_vcpu *vcpu)
-{
-	return kvm_x86_ops->get_pkru(vcpu);
-}
-
 static inline void enter_guest_mode(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.hflags |= HF_GUEST_MASK;

arch/x86/kvm/mmu.h

@@ -185,7 +185,7 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 		* index of the protection domain, so pte_pkey * 2 is
 		* is the index of the first bit for the domain.
 		*/
-		pkru_bits = (kvm_read_pkru(vcpu) >> (pte_pkey * 2)) & 3;
+		pkru_bits = (vcpu->arch.pkru >> (pte_pkey * 2)) & 3;
 
 		/* clear present bit, replace PFEC.RSVD with ACC_USER_MASK. */
 		offset = (pfec & ~1) +

arch/x86/kvm/svm.c

@@ -1100,7 +1100,7 @@ static __init int svm_hardware_setup(void)
 
 	if (vls) {
 		if (!npt_enabled ||
-		    !boot_cpu_has(X86_FEATURE_VIRTUAL_VMLOAD_VMSAVE) ||
+		    !boot_cpu_has(X86_FEATURE_V_VMSAVE_VMLOAD) ||
 		    !IS_ENABLED(CONFIG_X86_64)) {
 			vls = false;
 		} else {
@@ -1777,11 +1777,6 @@ static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 	to_svm(vcpu)->vmcb->save.rflags = rflags;
 }
 
-static u32 svm_get_pkru(struct kvm_vcpu *vcpu)
-{
-	return 0;
-}
-
 static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
 {
 	switch (reg) {
@@ -5413,8 +5408,6 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.get_rflags = svm_get_rflags,
 	.set_rflags = svm_set_rflags,
 
-	.get_pkru = svm_get_pkru,
-
 	.tlb_flush = svm_flush_tlb,
 
 	.run = svm_vcpu_run,

arch/x86/kvm/vmx.c

@@ -636,8 +636,6 @@ struct vcpu_vmx {
 
 	u64 current_tsc_ratio;
 
-	bool guest_pkru_valid;
-	u32 guest_pkru;
 	u32 host_pkru;
 
 	/*
@@ -2383,11 +2381,6 @@ static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 		to_vmx(vcpu)->emulation_required = emulation_required(vcpu);
 }
 
-static u32 vmx_get_pkru(struct kvm_vcpu *vcpu)
-{
-	return to_vmx(vcpu)->guest_pkru;
-}
-
 static u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu)
 {
 	u32 interruptibility = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);
@@ -9020,8 +9013,10 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
 		vmx_set_interrupt_shadow(vcpu, 0);
 
-	if (vmx->guest_pkru_valid)
-		__write_pkru(vmx->guest_pkru);
+	if (static_cpu_has(X86_FEATURE_PKU) &&
+	    kvm_read_cr4_bits(vcpu, X86_CR4_PKE) &&
+	    vcpu->arch.pkru != vmx->host_pkru)
+		__write_pkru(vcpu->arch.pkru);
 
 	atomic_switch_perf_msrs(vmx);
 	debugctlmsr = get_debugctlmsr();
@@ -9169,13 +9164,11 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	 * back on host, so it is safe to read guest PKRU from current
 	 * XSAVE.
 	 */
-	if (boot_cpu_has(X86_FEATURE_OSPKE)) {
-		vmx->guest_pkru = __read_pkru();
-		if (vmx->guest_pkru != vmx->host_pkru) {
-			vmx->guest_pkru_valid = true;
+	if (static_cpu_has(X86_FEATURE_PKU) &&
+	    kvm_read_cr4_bits(vcpu, X86_CR4_PKE)) {
+		vcpu->arch.pkru = __read_pkru();
+		if (vcpu->arch.pkru != vmx->host_pkru)
 			__write_pkru(vmx->host_pkru);
-		} else
-			vmx->guest_pkru_valid = false;
 	}
 
 	/*
@@ -11682,8 +11675,6 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 	.get_rflags = vmx_get_rflags,
 	.set_rflags = vmx_set_rflags,
 
-	.get_pkru = vmx_get_pkru,
-
 	.tlb_flush = vmx_flush_tlb,
 
 	.run = vmx_vcpu_run,

arch/x86/kvm/x86.c

@@ -3245,7 +3245,12 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
 			u32 size, offset, ecx, edx;
 			cpuid_count(XSTATE_CPUID, index,
 				    &size, &offset, &ecx, &edx);
-			memcpy(dest + offset, src, size);
+			if (feature == XFEATURE_MASK_PKRU)
+				memcpy(dest + offset, &vcpu->arch.pkru,
+				       sizeof(vcpu->arch.pkru));
+			else
+				memcpy(dest + offset, src, size);
+
 		}
 
 		valid -= feature;
@@ -3283,7 +3288,11 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
 			u32 size, offset, ecx, edx;
 			cpuid_count(XSTATE_CPUID, index,
 				    &size, &offset, &ecx, &edx);
-			memcpy(dest, src + offset, size);
+			if (feature == XFEATURE_MASK_PKRU)
+				memcpy(&vcpu->arch.pkru, src + offset,
+				       sizeof(vcpu->arch.pkru));
+			else
+				memcpy(dest, src + offset, size);
 		}
 
 		valid -= feature;
@@ -7633,7 +7642,9 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 	 */
 	vcpu->guest_fpu_loaded = 1;
 	__kernel_fpu_begin();
-	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state);
+	/* PKRU is separately restored in kvm_x86_ops->run.  */
+	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state,
+				~XFEATURE_MASK_PKRU);
 	trace_kvm_fpu(1);
 }
 

arch/x86/mm/mmap.c

@@ -50,8 +50,7 @@ unsigned long tasksize_64bit(void)
 static unsigned long stack_maxrandom_size(unsigned long task_size)
 {
 	unsigned long max = 0;
-	if ((current->flags & PF_RANDOMIZE) &&
-		!(current->personality & ADDR_NO_RANDOMIZE)) {
+	if (current->flags & PF_RANDOMIZE) {
 		max = (-1UL) & __STACK_RND_MASK(task_size == tasksize_32bit());
 		max <<= PAGE_SHIFT;
 	}
@@ -79,13 +78,13 @@ static int mmap_is_legacy(void)
 
 static unsigned long arch_rnd(unsigned int rndbits)
 {
+	if (!(current->flags & PF_RANDOMIZE))
+		return 0;
 	return (get_random_long() & ((1UL << rndbits) - 1)) << PAGE_SHIFT;
 }
 
 unsigned long arch_mmap_rnd(void)
 {
-	if (!(current->flags & PF_RANDOMIZE))
-		return 0;
 	return arch_rnd(mmap_is_ia32() ? mmap32_rnd_bits : mmap64_rnd_bits);
 }
 

arch/x86/platform/uv/tlb_uv.c

@@ -26,7 +26,7 @@
 static struct bau_operations ops __ro_after_init;
 
 /* timeouts in nanoseconds (indexed by UVH_AGING_PRESCALE_SEL urgency7 30:28) */
-static int timeout_base_ns[] = {
+static const int timeout_base_ns[] = {
 		20,
 		160,
 		1280,
@@ -1216,7 +1216,7 @@ static struct bau_pq_entry *find_another_by_swack(struct bau_pq_entry *msg,
  * set a bit in the UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE register.
  * Such a message must be ignored.
  */
-void process_uv2_message(struct msg_desc *mdp, struct bau_control *bcp)
+static void process_uv2_message(struct msg_desc *mdp, struct bau_control *bcp)
 {
 	unsigned long mmr_image;
 	unsigned char swack_vec;

block/blk-mq-debugfs.c

@@ -75,6 +75,8 @@ static const char *const blk_queue_flag_name[] = {
 	QUEUE_FLAG_NAME(STATS),
 	QUEUE_FLAG_NAME(POLL_STATS),
 	QUEUE_FLAG_NAME(REGISTERED),
+	QUEUE_FLAG_NAME(SCSI_PASSTHROUGH),
+	QUEUE_FLAG_NAME(QUIESCED),
 };
 #undef QUEUE_FLAG_NAME
 
@@ -265,6 +267,7 @@ static const char *const cmd_flag_name[] = {
 	CMD_FLAG_NAME(RAHEAD),
 	CMD_FLAG_NAME(BACKGROUND),
 	CMD_FLAG_NAME(NOUNMAP),
+	CMD_FLAG_NAME(NOWAIT),
 };
 #undef CMD_FLAG_NAME
 

block/blk-mq-pci.c

@@ -36,12 +36,18 @@ int blk_mq_pci_map_queues(struct blk_mq_tag_set *set, struct pci_dev *pdev)
 	for (queue = 0; queue < set->nr_hw_queues; queue++) {
 		mask = pci_irq_get_affinity(pdev, queue);
 		if (!mask)
-			return -EINVAL;
+			goto fallback;
 
 		for_each_cpu(cpu, mask)
 			set->mq_map[cpu] = queue;
 	}
 
 	return 0;
+
+fallback:
+	WARN_ON_ONCE(set->nr_hw_queues > 1);
+	for_each_possible_cpu(cpu)
+		set->mq_map[cpu] = 0;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(blk_mq_pci_map_queues);

block/blk-mq.c

@@ -360,12 +360,12 @@ struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
 		return ERR_PTR(ret);
 
 	rq = blk_mq_get_request(q, NULL, op, &alloc_data);
+	blk_queue_exit(q);
 
 	if (!rq)
 		return ERR_PTR(-EWOULDBLOCK);
 
 	blk_mq_put_ctx(alloc_data.ctx);
-	blk_queue_exit(q);
 
 	rq->__data_len = 0;
 	rq->__sector = (sector_t) -1;
@@ -411,12 +411,11 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 	alloc_data.ctx = __blk_mq_get_ctx(q, cpu);
 
 	rq = blk_mq_get_request(q, NULL, op, &alloc_data);
+	blk_queue_exit(q);
 
 	if (!rq)
 		return ERR_PTR(-EWOULDBLOCK);
 
-	blk_queue_exit(q);
-
 	return rq;
 }
 EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx);

block/blk-throttle.c

@@ -382,6 +382,14 @@ static unsigned int tg_iops_limit(struct throtl_grp *tg, int rw)
 	}								\
 } while (0)
 
+static inline unsigned int throtl_bio_data_size(struct bio *bio)
+{
+	/* assume it's one sector */
+	if (unlikely(bio_op(bio) == REQ_OP_DISCARD))
+		return 512;
+	return bio->bi_iter.bi_size;
+}
+
 static void throtl_qnode_init(struct throtl_qnode *qn, struct throtl_grp *tg)
 {
 	INIT_LIST_HEAD(&qn->node);
@@ -934,6 +942,7 @@ static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio,
 	bool rw = bio_data_dir(bio);
 	u64 bytes_allowed, extra_bytes, tmp;
 	unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd;
+	unsigned int bio_size = throtl_bio_data_size(bio);
 
 	jiffy_elapsed = jiffy_elapsed_rnd = jiffies - tg->slice_start[rw];
 
@@ -947,14 +956,14 @@ static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio,
 	do_div(tmp, HZ);
 	bytes_allowed = tmp;
 
-	if (tg->bytes_disp[rw] + bio->bi_iter.bi_size <= bytes_allowed) {
+	if (tg->bytes_disp[rw] + bio_size <= bytes_allowed) {
 		if (wait)
 			*wait = 0;
 		return true;
 	}
 
 	/* Calc approx time to dispatch */
-	extra_bytes = tg->bytes_disp[rw] + bio->bi_iter.bi_size - bytes_allowed;
+	extra_bytes = tg->bytes_disp[rw] + bio_size - bytes_allowed;
 	jiffy_wait = div64_u64(extra_bytes * HZ, tg_bps_limit(tg, rw));
 
 	if (!jiffy_wait)
@@ -1034,11 +1043,12 @@ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio,
 static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio)
 {
 	bool rw = bio_data_dir(bio);
+	unsigned int bio_size = throtl_bio_data_size(bio);
 
 	/* Charge the bio to the group */
-	tg->bytes_disp[rw] += bio->bi_iter.bi_size;
+	tg->bytes_disp[rw] += bio_size;
 	tg->io_disp[rw]++;
-	tg->last_bytes_disp[rw] += bio->bi_iter.bi_size;
+	tg->last_bytes_disp[rw] += bio_size;
 	tg->last_io_disp[rw]++;
 
 	/*

block/bsg-lib.c

@@ -29,26 +29,25 @@
 #include <scsi/scsi_cmnd.h>
 
 /**
- * bsg_destroy_job - routine to teardown/delete a bsg job
+ * bsg_teardown_job - routine to teardown a bsg job
  * @job: bsg_job that is to be torn down
  */
-static void bsg_destroy_job(struct kref *kref)
+static void bsg_teardown_job(struct kref *kref)
 {
 	struct bsg_job *job = container_of(kref, struct bsg_job, kref);
 	struct request *rq = job->req;
 
-	blk_end_request_all(rq, BLK_STS_OK);
-
 	put_device(job->dev);	/* release reference for the request */
 
 	kfree(job->request_payload.sg_list);
 	kfree(job->reply_payload.sg_list);
-	kfree(job);
+
+	blk_end_request_all(rq, BLK_STS_OK);
 }
 
 void bsg_job_put(struct bsg_job *job)
 {
-	kref_put(&job->kref, bsg_destroy_job);
+	kref_put(&job->kref, bsg_teardown_job);
 }
 EXPORT_SYMBOL_GPL(bsg_job_put);
 
@@ -100,7 +99,7 @@ EXPORT_SYMBOL_GPL(bsg_job_done);
  */
 static void bsg_softirq_done(struct request *rq)
 {
-	struct bsg_job *job = rq->special;
+	struct bsg_job *job = blk_mq_rq_to_pdu(rq);
 
 	bsg_job_put(job);
 }
@@ -122,33 +121,20 @@ static int bsg_map_buffer(struct bsg_buffer *buf, struct request *req)
 }
 
 /**
- * bsg_create_job - create the bsg_job structure for the bsg request
+ * bsg_prepare_job - create the bsg_job structure for the bsg request
  * @dev: device that is being sent the bsg request
  * @req: BSG request that needs a job structure
  */
-static int bsg_create_job(struct device *dev, struct request *req)
+static int bsg_prepare_job(struct device *dev, struct request *req)
 {
 	struct request *rsp = req->next_rq;
-	struct request_queue *q = req->q;
 	struct scsi_request *rq = scsi_req(req);
-	struct bsg_job *job;
+	struct bsg_job *job = blk_mq_rq_to_pdu(req);
 	int ret;
 
-	BUG_ON(req->special);
-
-	job = kzalloc(sizeof(struct bsg_job) + q->bsg_job_size, GFP_KERNEL);
-	if (!job)
-		return -ENOMEM;
-
-	req->special = job;
-	job->req = req;
-	if (q->bsg_job_size)
-		job->dd_data = (void *)&job[1];
 	job->request = rq->cmd;
 	job->request_len = rq->cmd_len;
-	job->reply = rq->sense;
-	job->reply_len = SCSI_SENSE_BUFFERSIZE;	/* Size of sense buffer
-						 * allocated */
+
 	if (req->bio) {
 		ret = bsg_map_buffer(&job->request_payload, req);
 		if (ret)
@@ -187,7 +173,6 @@ static void bsg_request_fn(struct request_queue *q)
 {
 	struct device *dev = q->queuedata;
 	struct request *req;
-	struct bsg_job *job;
 	int ret;
 
 	if (!get_device(dev))
@@ -199,7 +184,7 @@ static void bsg_request_fn(struct request_queue *q)
 			break;
 		spin_unlock_irq(q->queue_lock);
 
-		ret = bsg_create_job(dev, req);
+		ret = bsg_prepare_job(dev, req);
 		if (ret) {
 			scsi_req(req)->result = ret;
 			blk_end_request_all(req, BLK_STS_OK);
@@ -207,8 +192,7 @@ static void bsg_request_fn(struct request_queue *q)
 			continue;
 		}
 
-		job = req->special;
-		ret = q->bsg_job_fn(job);
+		ret = q->bsg_job_fn(blk_mq_rq_to_pdu(req));
 		spin_lock_irq(q->queue_lock);
 		if (ret)
 			break;
@@ -219,6 +203,35 @@ static void bsg_request_fn(struct request_queue *q)
 	spin_lock_irq(q->queue_lock);
 }
 
+static int bsg_init_rq(struct request_queue *q, struct request *req, gfp_t gfp)
+{
+	struct bsg_job *job = blk_mq_rq_to_pdu(req);
+	struct scsi_request *sreq = &job->sreq;
+
+	memset(job, 0, sizeof(*job));
+
+	scsi_req_init(sreq);
+	sreq->sense_len = SCSI_SENSE_BUFFERSIZE;
+	sreq->sense = kzalloc(sreq->sense_len, gfp);
+	if (!sreq->sense)
+		return -ENOMEM;
+
+	job->req = req;
+	job->reply = sreq->sense;
+	job->reply_len = sreq->sense_len;
+	job->dd_data = job + 1;
+
+	return 0;
+}
+
+static void bsg_exit_rq(struct request_queue *q, struct request *req)
+{
+	struct bsg_job *job = blk_mq_rq_to_pdu(req);
+	struct scsi_request *sreq = &job->sreq;
+
+	kfree(sreq->sense);
+}
+
 /**
  * bsg_setup_queue - Create and add the bsg hooks so we can receive requests
  * @dev: device to attach bsg device to
@@ -235,7 +248,9 @@ struct request_queue *bsg_setup_queue(struct device *dev, char *name,
 	q = blk_alloc_queue(GFP_KERNEL);
 	if (!q)
 		return ERR_PTR(-ENOMEM);
-	q->cmd_size = sizeof(struct scsi_request);
+	q->cmd_size = sizeof(struct bsg_job) + dd_job_size;
+	q->init_rq_fn = bsg_init_rq;
+	q->exit_rq_fn = bsg_exit_rq;
 	q->request_fn = bsg_request_fn;
 
 	ret = blk_init_allocated_queue(q);
@@ -243,7 +258,6 @@ struct request_queue *bsg_setup_queue(struct device *dev, char *name,
 		goto out_cleanup_queue;
 
 	q->queuedata = dev;
-	q->bsg_job_size = dd_job_size;
 	q->bsg_job_fn = job_fn;
 	queue_flag_set_unlocked(QUEUE_FLAG_BIDI, q);
 	queue_flag_set_unlocked(QUEUE_FLAG_SCSI_PASSTHROUGH, q);

drivers/acpi/acpica/nsxfeval.c

@@ -100,9 +100,13 @@ acpi_evaluate_object_typed(acpi_handle handle,
 		free_buffer_on_error = TRUE;
 	}
 
-	status = acpi_get_handle(handle, pathname, &target_handle);
-	if (ACPI_FAILURE(status)) {
-		return_ACPI_STATUS(status);
+	if (pathname) {
+		status = acpi_get_handle(handle, pathname, &target_handle);
+		if (ACPI_FAILURE(status)) {
+			return_ACPI_STATUS(status);
+		}
+	} else {
+		target_handle = handle;
 	}
 
 	full_pathname = acpi_ns_get_external_pathname(target_handle);

drivers/acpi/ec.c

@@ -1741,7 +1741,7 @@ error:
  * functioning ECDT EC first in order to handle the events.
  * https://bugzilla.kernel.org/show_bug.cgi?id=115021
  */
-int __init acpi_ec_ecdt_start(void)
+static int __init acpi_ec_ecdt_start(void)
 {
 	acpi_handle handle;
 
@@ -2003,20 +2003,17 @@ static inline void acpi_ec_query_exit(void)
 int __init acpi_ec_init(void)
 {
 	int result;
+	int ecdt_fail, dsdt_fail;
 
 	/* register workqueue for _Qxx evaluations */
 	result = acpi_ec_query_init();
 	if (result)
-		goto err_exit;
-	/* Now register the driver for the EC */
-	result = acpi_bus_register_driver(&acpi_ec_driver);
-	if (result)
-		goto err_exit;
+		return result;
 
-err_exit:
-	if (result)
-		acpi_ec_query_exit();
-	return result;
+	/* Drivers must be started after acpi_ec_query_init() */
+	ecdt_fail = acpi_ec_ecdt_start();
+	dsdt_fail = acpi_bus_register_driver(&acpi_ec_driver);
+	return ecdt_fail && dsdt_fail ? -ENODEV : 0;
 }
 
 /* EC driver currently not unloadable */