Merge branch 'x86/mm' into x86/platform, to pick up TLB flush dependency

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

Documentation/admin-guide/kernel-parameters.txt

@@ -2233,6 +2233,17 @@
 			memory contents and reserves bad memory
 			regions that are detected.
 
+	mem_encrypt=	[X86-64] AMD Secure Memory Encryption (SME) control
+			Valid arguments: on, off
+			Default (depends on kernel configuration option):
+			  on  (CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT=y)
+			  off (CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT=n)
+			mem_encrypt=on:		Activate SME
+			mem_encrypt=off:	Do not activate SME
+
+			Refer to Documentation/x86/amd-memory-encryption.txt
+			for details on when memory encryption can be activated.
+
 	mem_sleep_default=	[SUSPEND] Default system suspend mode:
 			s2idle  - Suspend-To-Idle
 			shallow - Power-On Suspend or equivalent (if supported)
@@ -2696,6 +2707,8 @@
 	nopat		[X86] Disable PAT (page attribute table extension of
 			pagetables) support.
 
+	nopcid		[X86-64] Disable the PCID cpu feature.
+
 	norandmaps	Don't use address space randomization.  Equivalent to
 			echo 0 > /proc/sys/kernel/randomize_va_space
 

Documentation/fb/efifb.txt

@@ -27,5 +27,11 @@ You have to add the following kernel parameters in your elilo.conf:
 	Macbook Pro 17", iMac 20" :
 		video=efifb:i20
 
+Accepted options:
+
+nowc	Don't map the framebuffer write combined. This can be used
+	to workaround side-effects and slowdowns on other CPU cores
+	when large amounts of console data are written.
+
 --
 Edgar Hucek <gimli@dark-green.com>

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

Documentation/x86/amd-memory-encryption.txt

@@ -0,0 +1,68 @@
+Secure Memory Encryption (SME) is a feature found on AMD processors.
+
+SME provides the ability to mark individual pages of memory as encrypted using
+the standard x86 page tables.  A page that is marked encrypted will be
+automatically decrypted when read from DRAM and encrypted when written to
+DRAM.  SME can therefore be used to protect the contents of DRAM from physical
+attacks on the system.
+
+A page is encrypted when a page table entry has the encryption bit set (see
+below on how to determine its position).  The encryption bit can also be
+specified in the cr3 register, allowing the PGD table to be encrypted. Each
+successive level of page tables can also be encrypted by setting the encryption
+bit in the page table entry that points to the next table. This allows the full
+page table hierarchy to be encrypted. Note, this means that just because the
+encryption bit is set in cr3, doesn't imply the full hierarchy is encyrpted.
+Each page table entry in the hierarchy needs to have the encryption bit set to
+achieve that. So, theoretically, you could have the encryption bit set in cr3
+so that the PGD is encrypted, but not set the encryption bit in the PGD entry
+for a PUD which results in the PUD pointed to by that entry to not be
+encrypted.
+
+Support for SME can be determined through the CPUID instruction. The CPUID
+function 0x8000001f reports information related to SME:
+
+	0x8000001f[eax]:
+		Bit[0] indicates support for SME
+	0x8000001f[ebx]:
+		Bits[5:0]  pagetable bit number used to activate memory
+			   encryption
+		Bits[11:6] reduction in physical address space, in bits, when
+			   memory encryption is enabled (this only affects
+			   system physical addresses, not guest physical
+			   addresses)
+
+If support for SME is present, MSR 0xc00100010 (MSR_K8_SYSCFG) can be used to
+determine if SME is enabled and/or to enable memory encryption:
+
+	0xc0010010:
+		Bit[23]   0 = memory encryption features are disabled
+			  1 = memory encryption features are enabled
+
+Linux relies on BIOS to set this bit if BIOS has determined that the reduction
+in the physical address space as a result of enabling memory encryption (see
+CPUID information above) will not conflict with the address space resource
+requirements for the system.  If this bit is not set upon Linux startup then
+Linux itself will not set it and memory encryption will not be possible.
+
+The state of SME in the Linux kernel can be documented as follows:
+	- Supported:
+	  The CPU supports SME (determined through CPUID instruction).
+
+	- Enabled:
+	  Supported and bit 23 of MSR_K8_SYSCFG is set.
+
+	- Active:
+	  Supported, Enabled and the Linux kernel is actively applying
+	  the encryption bit to page table entries (the SME mask in the
+	  kernel is non-zero).
+
+SME can also be enabled and activated in the BIOS. If SME is enabled and
+activated in the BIOS, then all memory accesses will be encrypted and it will
+not be necessary to activate the Linux memory encryption support.  If the BIOS
+merely enables SME (sets bit 23 of the MSR_K8_SYSCFG), then Linux can activate
+memory encryption by default (CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT=y) or
+by supplying mem_encrypt=on on the kernel command line.  However, if BIOS does
+not enable SME, then Linux will not be able to activate memory encryption, even
+if configured to do so by default or the mem_encrypt=on command line parameter
+is specified.

Documentation/x86/protection-keys.txt

@@ -34,7 +34,7 @@ with a key.  In this example WRPKRU is wrapped by a C function
 called pkey_set().
 
 	int real_prot = PROT_READ|PROT_WRITE;
-	pkey = pkey_alloc(0, PKEY_DENY_WRITE);
+	pkey = pkey_alloc(0, PKEY_DISABLE_WRITE);
 	ptr = mmap(NULL, PAGE_SIZE, PROT_NONE, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0);
 	ret = pkey_mprotect(ptr, PAGE_SIZE, real_prot, pkey);
 	... application runs here
@@ -42,9 +42,9 @@ called pkey_set().
 Now, if the application needs to update the data at 'ptr', it can
 gain access, do the update, then remove its write access:
 
-	pkey_set(pkey, 0); // clear PKEY_DENY_WRITE
+	pkey_set(pkey, 0); // clear PKEY_DISABLE_WRITE
 	*ptr = foo; // assign something
-	pkey_set(pkey, PKEY_DENY_WRITE); // set PKEY_DENY_WRITE again
+	pkey_set(pkey, PKEY_DISABLE_WRITE); // set PKEY_DISABLE_WRITE again
 
 Now when it frees the memory, it will also free the pkey since it
 is no longer in use:

Documentation/x86/x86_64/5level-paging.txt

@@ -0,0 +1,64 @@
+== Overview ==
+
+Original x86-64 was limited by 4-level paing to 256 TiB of virtual address
+space and 64 TiB of physical address space. We are already bumping into
+this limit: some vendors offers servers with 64 TiB of memory today.
+
+To overcome the limitation upcoming hardware will introduce support for
+5-level paging. It is a straight-forward extension of the current page
+table structure adding one more layer of translation.
+
+It bumps the limits to 128 PiB of virtual address space and 4 PiB of
+physical address space. This "ought to be enough for anybody" ©.
+
+QEMU 2.9 and later support 5-level paging.
+
+Virtual memory layout for 5-level paging is described in
+Documentation/x86/x86_64/mm.txt
+
+== Enabling 5-level paging ==
+
+CONFIG_X86_5LEVEL=y enables the feature.
+
+So far, a kernel compiled with the option enabled will be able to boot
+only on machines that supports the feature -- see for 'la57' flag in
+/proc/cpuinfo.
+
+The plan is to implement boot-time switching between 4- and 5-level paging
+in the future.
+
+== User-space and large virtual address space ==
+
+On x86, 5-level paging enables 56-bit userspace virtual address space.
+Not all user space is ready to handle wide addresses. It's known that
+at least some JIT compilers use higher bits in pointers to encode their
+information. It collides with valid pointers with 5-level paging and
+leads to crashes.
+
+To mitigate this, we are not going to allocate virtual address space
+above 47-bit by default.
+
+But userspace can ask for allocation from full address space by
+specifying hint address (with or without MAP_FIXED) above 47-bits.
+
+If hint address set above 47-bit, but MAP_FIXED is not specified, we try
+to look for unmapped area by specified address. If it's already
+occupied, we look for unmapped area in *full* address space, rather than
+from 47-bit window.
+
+A high hint address would only affect the allocation in question, but not
+any future mmap()s.
+
+Specifying high hint address on older kernel or on machine without 5-level
+paging support is safe. The hint will be ignored and kernel will fall back
+to allocation from 47-bit address space.
+
+This approach helps to easily make application's memory allocator aware
+about large address space without manually tracking allocated virtual
+address space.
+
+One important case we need to handle here is interaction with MPX.
+MPX (without MAWA extension) cannot handle addresses above 47-bit, so we
+need to make sure that MPX cannot be enabled we already have VMA above
+the boundary and forbid creating such VMAs once MPX is enabled.
+

MAINTAINERS

@@ -7111,7 +7111,6 @@ 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/
 
@@ -14005,6 +14004,7 @@ F:	drivers/block/virtio_blk.c
 F:	include/linux/virtio*.h
 F:	include/uapi/linux/virtio_*.h
 F:	drivers/crypto/virtio/
+F:	mm/balloon_compaction.c
 
 VIRTIO CRYPTO DRIVER
 M:	Gonglei <arei.gonglei@huawei.com>

Makefile

@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 13
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc6
 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/include/asm/tlb.h

@@ -148,7 +148,8 @@ static inline void tlb_flush_mmu(struct mmu_gather *tlb)
 }
 
 static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
+arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
+			unsigned long start, unsigned long end)
 {
 	tlb->mm = mm;
 	tlb->fullmm = !(start | (end+1));
@@ -166,8 +167,14 @@ tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start
 }
 
 static inline void
-tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
+arch_tlb_finish_mmu(struct mmu_gather *tlb,
+			unsigned long start, unsigned long end, bool force)
 {
+	if (force) {
+		tlb->range_start = start;
+		tlb->range_end = end;
+	}
+
 	tlb_flush_mmu(tlb);
 
 	/* keep the page table cache within bounds */

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/ia64/include/asm/acpi.h

@@ -112,8 +112,6 @@ static inline void arch_acpi_set_pdc_bits(u32 *buf)
 	buf[2] |= ACPI_PDC_EST_CAPABILITY_SMP;
 }
 
-#define acpi_unlazy_tlb(x)
-
 #ifdef CONFIG_ACPI_NUMA
 extern cpumask_t early_cpu_possible_map;
 #define for_each_possible_early_cpu(cpu)  \

arch/ia64/include/asm/tlb.h

@@ -168,7 +168,8 @@ static inline void __tlb_alloc_page(struct mmu_gather *tlb)
 
 
 static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
+arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
+			unsigned long start, unsigned long end)
 {
 	tlb->mm = mm;
 	tlb->max = ARRAY_SIZE(tlb->local);
@@ -185,8 +186,11 @@ tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start
  * collected.
  */
 static inline void
-tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
+arch_tlb_finish_mmu(struct mmu_gather *tlb,
+			unsigned long start, unsigned long end, bool force)
 {
+	if (force)
+		tlb->need_flush = 1;
 	/*
 	 * Note: tlb->nr may be 0 at this point, so we can't rely on tlb->start_addr and
 	 * tlb->end_addr.

arch/ia64/kernel/efi.c

@@ -757,14 +757,14 @@ efi_memmap_intersects (unsigned long phys_addr, unsigned long size)
 	return 0;
 }
 
-u32
+int
 efi_mem_type (unsigned long phys_addr)
 {
 	efi_memory_desc_t *md = efi_memory_descriptor(phys_addr);
 
 	if (md)
 		return md->type;
-	return 0;
+	return -EINVAL;
 }
 
 u64

arch/mips/Kconfig

@@ -2260,7 +2260,7 @@ config CPU_R4K_CACHE_TLB
 
 config MIPS_MT_SMP
 	bool "MIPS MT SMP support (1 TC on each available VPE)"
-	depends on SYS_SUPPORTS_MULTITHREADING && !CPU_MIPSR6
+	depends on SYS_SUPPORTS_MULTITHREADING && !CPU_MIPSR6 && !CPU_MICROMIPS
 	select CPU_MIPSR2_IRQ_VI
 	select CPU_MIPSR2_IRQ_EI
 	select SYNC_R4K

arch/mips/Makefile

@@ -243,8 +243,21 @@ include arch/mips/Kbuild.platforms
 ifdef CONFIG_PHYSICAL_START
 load-y					= $(CONFIG_PHYSICAL_START)
 endif
-entry-y				= 0x$(shell $(NM) vmlinux 2>/dev/null \
+
+entry-noisa-y				= 0x$(shell $(NM) vmlinux 2>/dev/null \
 					| grep "\bkernel_entry\b" | cut -f1 -d \ )
+ifdef CONFIG_CPU_MICROMIPS
+  #
+  # Set the ISA bit, since the kernel_entry symbol in the ELF will have it
+  # clear which would lead to images containing addresses which bootloaders may
+  # jump to as MIPS32 code.
+  #
+  entry-y = $(patsubst %0,%1,$(patsubst %2,%3,$(patsubst %4,%5, \
+              $(patsubst %6,%7,$(patsubst %8,%9,$(patsubst %a,%b, \
+              $(patsubst %c,%d,$(patsubst %e,%f,$(entry-noisa-y)))))))))
+else
+  entry-y = $(entry-noisa-y)
+endif
 
 cflags-y			+= -I$(srctree)/arch/mips/include/asm/mach-generic
 drivers-$(CONFIG_PCI)		+= arch/mips/pci/

arch/mips/boot/compressed/.gitignore

@@ -0,0 +1,2 @@
+ashldi3.c
+bswapsi.c

arch/mips/cavium-octeon/octeon-usb.c

@@ -13,9 +13,9 @@
 #include <linux/mutex.h>
 #include <linux/delay.h>
 #include <linux/of_platform.h>
+#include <linux/io.h>
 
 #include <asm/octeon/octeon.h>
-#include <asm/octeon/cvmx-gpio-defs.h>
 
 /* USB Control Register */
 union cvm_usbdrd_uctl_ctl {

arch/mips/dec/int-handler.S

@@ -147,23 +147,12 @@
 		 * Find irq with highest priority
 		 */
 		# open coded PTR_LA t1, cpu_mask_nr_tbl
-#if (_MIPS_SZPTR == 32)
+#if defined(CONFIG_32BIT) || defined(KBUILD_64BIT_SYM32)
 		# open coded la t1, cpu_mask_nr_tbl
 		lui	t1, %hi(cpu_mask_nr_tbl)
 		addiu	t1, %lo(cpu_mask_nr_tbl)
-
-#endif
-#if (_MIPS_SZPTR == 64)
-		# open coded dla t1, cpu_mask_nr_tbl
-		.set	push
-		.set	noat
-		lui	t1, %highest(cpu_mask_nr_tbl)
-		lui	AT, %hi(cpu_mask_nr_tbl)
-		daddiu	t1, t1, %higher(cpu_mask_nr_tbl)
-		daddiu	AT, AT, %lo(cpu_mask_nr_tbl)
-		dsll	t1, 32
-		daddu	t1, t1, AT
-		.set	pop
+#else
+#error GCC `-msym32' option required for 64-bit DECstation builds
 #endif
 1:		lw	t2,(t1)
 		nop
@@ -214,23 +203,12 @@
 		 * Find irq with highest priority
 		 */
 		# open coded PTR_LA t1,asic_mask_nr_tbl
-#if (_MIPS_SZPTR == 32)
+#if defined(CONFIG_32BIT) || defined(KBUILD_64BIT_SYM32)
 		# open coded la t1, asic_mask_nr_tbl
 		lui	t1, %hi(asic_mask_nr_tbl)
 		addiu	t1, %lo(asic_mask_nr_tbl)
-
-#endif
-#if (_MIPS_SZPTR == 64)
-		# open coded dla t1, asic_mask_nr_tbl
-		.set	push
-		.set	noat
-		lui	t1, %highest(asic_mask_nr_tbl)
-		lui	AT, %hi(asic_mask_nr_tbl)
-		daddiu	t1, t1, %higher(asic_mask_nr_tbl)
-		daddiu	AT, AT, %lo(asic_mask_nr_tbl)
-		dsll	t1, 32
-		daddu	t1, t1, AT
-		.set	pop
+#else
+#error GCC `-msym32' option required for 64-bit DECstation builds
 #endif
 2:		lw	t2,(t1)
 		nop

arch/mips/include/asm/cache.h

@@ -9,6 +9,8 @@
 #ifndef _ASM_CACHE_H
 #define _ASM_CACHE_H
 
+#include <kmalloc.h>
+
 #define L1_CACHE_SHIFT		CONFIG_MIPS_L1_CACHE_SHIFT
 #define L1_CACHE_BYTES		(1 << L1_CACHE_SHIFT)
 

arch/mips/include/asm/cpu-features.h

@@ -428,6 +428,9 @@
 #ifndef cpu_scache_line_size
 #define cpu_scache_line_size()	cpu_data[0].scache.linesz
 #endif
+#ifndef cpu_tcache_line_size
+#define cpu_tcache_line_size()	cpu_data[0].tcache.linesz
+#endif
 
 #ifndef cpu_hwrena_impl_bits
 #define cpu_hwrena_impl_bits		0

arch/mips/include/asm/octeon/cvmx-l2c-defs.h

@@ -33,6 +33,10 @@
 #define CVMX_L2C_DBG (CVMX_ADD_IO_SEG(0x0001180080000030ull))
 #define CVMX_L2C_CFG (CVMX_ADD_IO_SEG(0x0001180080000000ull))
 #define CVMX_L2C_CTL (CVMX_ADD_IO_SEG(0x0001180080800000ull))
+#define CVMX_L2C_ERR_TDTX(block_id)					       \
+	(CVMX_ADD_IO_SEG(0x0001180080A007E0ull) + ((block_id) & 3) * 0x40000ull)
+#define CVMX_L2C_ERR_TTGX(block_id)					       \
+	(CVMX_ADD_IO_SEG(0x0001180080A007E8ull) + ((block_id) & 3) * 0x40000ull)
 #define CVMX_L2C_LCKBASE (CVMX_ADD_IO_SEG(0x0001180080000058ull))
 #define CVMX_L2C_LCKOFF (CVMX_ADD_IO_SEG(0x0001180080000060ull))
 #define CVMX_L2C_PFCTL (CVMX_ADD_IO_SEG(0x0001180080000090ull))
@@ -66,9 +70,40 @@
 		((offset) & 1) * 8)
 #define CVMX_L2C_WPAR_PPX(offset) (CVMX_ADD_IO_SEG(0x0001180080840000ull)    + \
 		((offset) & 31) * 8)
-#define CVMX_L2D_FUS3 (CVMX_ADD_IO_SEG(0x00011800800007B8ull))
 
 
+union cvmx_l2c_err_tdtx {
+	uint64_t u64;
+	struct cvmx_l2c_err_tdtx_s {
+		__BITFIELD_FIELD(uint64_t dbe:1,
+		__BITFIELD_FIELD(uint64_t sbe:1,
+		__BITFIELD_FIELD(uint64_t vdbe:1,
+		__BITFIELD_FIELD(uint64_t vsbe:1,
+		__BITFIELD_FIELD(uint64_t syn:10,
+		__BITFIELD_FIELD(uint64_t reserved_22_49:28,
+		__BITFIELD_FIELD(uint64_t wayidx:18,
+		__BITFIELD_FIELD(uint64_t reserved_2_3:2,
+		__BITFIELD_FIELD(uint64_t type:2,
+		;)))))))))
+	} s;
+};
+
+union cvmx_l2c_err_ttgx {
+	uint64_t u64;
+	struct cvmx_l2c_err_ttgx_s {
+		__BITFIELD_FIELD(uint64_t dbe:1,
+		__BITFIELD_FIELD(uint64_t sbe:1,
+		__BITFIELD_FIELD(uint64_t noway:1,
+		__BITFIELD_FIELD(uint64_t reserved_56_60:5,
+		__BITFIELD_FIELD(uint64_t syn:6,
+		__BITFIELD_FIELD(uint64_t reserved_22_49:28,
+		__BITFIELD_FIELD(uint64_t wayidx:15,
+		__BITFIELD_FIELD(uint64_t reserved_2_6:5,
+		__BITFIELD_FIELD(uint64_t type:2,
+		;)))))))))
+	} s;
+};
+
 union cvmx_l2c_cfg {
 	uint64_t u64;
 	struct cvmx_l2c_cfg_s {

arch/mips/include/asm/octeon/cvmx-l2d-defs.h

@@ -0,0 +1,60 @@
+/***********************license start***************
+ * Author: Cavium Networks
+ *
+ * Contact: support@caviumnetworks.com
+ * This file is part of the OCTEON SDK
+ *
+ * Copyright (c) 2003-2017 Cavium, Inc.
+ *
+ * This file 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.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this file; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ * or visit http://www.gnu.org/licenses/.
+ *
+ * This file may also be available under a different license from Cavium.
+ * Contact Cavium Networks for more information
+ ***********************license end**************************************/
+
+#ifndef __CVMX_L2D_DEFS_H__
+#define __CVMX_L2D_DEFS_H__
+
+#define CVMX_L2D_ERR	(CVMX_ADD_IO_SEG(0x0001180080000010ull))
+#define CVMX_L2D_FUS3	(CVMX_ADD_IO_SEG(0x00011800800007B8ull))
+
+
+union cvmx_l2d_err {
+	uint64_t u64;
+	struct cvmx_l2d_err_s {
+		__BITFIELD_FIELD(uint64_t reserved_6_63:58,
+		__BITFIELD_FIELD(uint64_t bmhclsel:1,
+		__BITFIELD_FIELD(uint64_t ded_err:1,
+		__BITFIELD_FIELD(uint64_t sec_err:1,
+		__BITFIELD_FIELD(uint64_t ded_intena:1,
+		__BITFIELD_FIELD(uint64_t sec_intena:1,
+		__BITFIELD_FIELD(uint64_t ecc_ena:1,
+		;)))))))
+	} s;
+};
+
+union cvmx_l2d_fus3 {
+	uint64_t u64;
+	struct cvmx_l2d_fus3_s {
+		__BITFIELD_FIELD(uint64_t reserved_40_63:24,
+		__BITFIELD_FIELD(uint64_t ema_ctl:3,
+		__BITFIELD_FIELD(uint64_t reserved_34_36:3,
+		__BITFIELD_FIELD(uint64_t q3fus:34,
+		;))))
+	} s;
+};
+
+#endif

arch/mips/include/asm/octeon/cvmx.h

@@ -62,6 +62,7 @@ enum cvmx_mips_space {
 #include <asm/octeon/cvmx-iob-defs.h>
 #include <asm/octeon/cvmx-ipd-defs.h>
 #include <asm/octeon/cvmx-l2c-defs.h>
+#include <asm/octeon/cvmx-l2d-defs.h>
 #include <asm/octeon/cvmx-l2t-defs.h>
 #include <asm/octeon/cvmx-led-defs.h>
 #include <asm/octeon/cvmx-mio-defs.h>

arch/mips/kernel/smp.c

@@ -376,9 +376,6 @@ asmlinkage void start_secondary(void)
 	cpumask_set_cpu(cpu, &cpu_coherent_mask);
 	notify_cpu_starting(cpu);
 
-	complete(&cpu_running);
-	synchronise_count_slave(cpu);
-
 	set_cpu_online(cpu, true);
 
 	set_cpu_sibling_map(cpu);
@@ -386,6 +383,9 @@ asmlinkage void start_secondary(void)
 
 	calculate_cpu_foreign_map();
 
+	complete(&cpu_running);
+	synchronise_count_slave(cpu);
+
 	/*
 	 * irq will be enabled in ->smp_finish(), enabling it too early
 	 * is dangerous.

arch/mips/mm/uasm-mips.c

@@ -48,7 +48,7 @@
 
 #include "uasm.c"
 
-static const struct insn const insn_table[insn_invalid] = {
+static const struct insn insn_table[insn_invalid] = {
 	[insn_addiu]	= {M(addiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM},
 	[insn_addu]	= {M(spec_op, 0, 0, 0, 0, addu_op), RS | RT | RD},
 	[insn_and]	= {M(spec_op, 0, 0, 0, 0, and_op), RS | RT | RD},

arch/mips/pci/pci.c

@@ -28,16 +28,15 @@ EXPORT_SYMBOL(PCIBIOS_MIN_MEM);
 
 static int __init pcibios_set_cache_line_size(void)
 {
-	struct cpuinfo_mips *c = &current_cpu_data;
 	unsigned int lsize;
 
 	/*
 	 * Set PCI cacheline size to that of the highest level in the
 	 * cache hierarchy.
 	 */
-	lsize = c->dcache.linesz;
-	lsize = c->scache.linesz ? : lsize;
-	lsize = c->tcache.linesz ? : lsize;
+	lsize = cpu_dcache_line_size();
+	lsize = cpu_scache_line_size() ? : lsize;
+	lsize = cpu_tcache_line_size() ? : lsize;
 
 	BUG_ON(!lsize);
 

arch/mips/vdso/gettimeofday.c

@@ -35,7 +35,8 @@ static __always_inline long gettimeofday_fallback(struct timeval *_tv,
 	"       syscall\n"
 	: "=r" (ret), "=r" (error)
 	: "r" (tv), "r" (tz), "r" (nr)
-	: "memory");
+	: "$1", "$3", "$8", "$9", "$10", "$11", "$12", "$13",
+	  "$14", "$15", "$24", "$25", "hi", "lo", "memory");
 
 	return error ? -ret : ret;
 }
@@ -55,7 +56,8 @@ static __always_inline long clock_gettime_fallback(clockid_t _clkid,
 	"       syscall\n"
 	: "=r" (ret), "=r" (error)
 	: "r" (clkid), "r" (ts), "r" (nr)
-	: "memory");
+	: "$1", "$3", "$8", "$9", "$10", "$11", "$12", "$13",
+	  "$14", "$15", "$24", "$25", "hi", "lo", "memory");
 
 	return error ? -ret : ret;
 }

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/configs/powernv_defconfig

@@ -293,7 +293,8 @@ CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_STACK_USAGE=y
 CONFIG_DEBUG_STACKOVERFLOW=y
-CONFIG_LOCKUP_DETECTOR=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
+CONFIG_HARDLOCKUP_DETECTOR=y
 CONFIG_LATENCYTOP=y
 CONFIG_SCHED_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y

arch/powerpc/configs/ppc64_defconfig

@@ -324,7 +324,8 @@ CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_STACK_USAGE=y
 CONFIG_DEBUG_STACKOVERFLOW=y
-CONFIG_LOCKUP_DETECTOR=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
+CONFIG_HARDLOCKUP_DETECTOR=y
 CONFIG_DEBUG_MUTEXES=y
 CONFIG_LATENCYTOP=y
 CONFIG_SCHED_TRACER=y

arch/powerpc/configs/pseries_defconfig

@@ -291,7 +291,8 @@ CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_STACK_USAGE=y
 CONFIG_DEBUG_STACKOVERFLOW=y
-CONFIG_LOCKUP_DETECTOR=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
+CONFIG_HARDLOCKUP_DETECTOR=y
 CONFIG_LATENCYTOP=y
 CONFIG_SCHED_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y

arch/powerpc/kernel/entry_64.S

@@ -223,17 +223,27 @@ system_call_exit:
 	andi.	r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)
 	bne-	.Lsyscall_exit_work
 
-	/* If MSR_FP and MSR_VEC are set in user msr, then no need to restore */
-	li	r7,MSR_FP
+	andi.	r0,r8,MSR_FP
+	beq 2f
 #ifdef CONFIG_ALTIVEC
-	oris	r7,r7,MSR_VEC@h
+	andis.	r0,r8,MSR_VEC@h
+	bne	3f
 #endif
-	and	r0,r8,r7
-	cmpd	r0,r7
-	bne	.Lsyscall_restore_math
-.Lsyscall_restore_math_cont:
+2:	addi    r3,r1,STACK_FRAME_OVERHEAD
+#ifdef CONFIG_PPC_BOOK3S
+	li	r10,MSR_RI
+	mtmsrd	r10,1		/* Restore RI */
+#endif
+	bl	restore_math
+#ifdef CONFIG_PPC_BOOK3S
+	li	r11,0
+	mtmsrd	r11,1
+#endif
+	ld	r8,_MSR(r1)
+	ld	r3,RESULT(r1)
+	li	r11,-MAX_ERRNO
 
-	cmpld	r3,r11
+3:	cmpld	r3,r11
 	ld	r5,_CCR(r1)
 	bge-	.Lsyscall_error
 .Lsyscall_error_cont:
@@ -267,40 +277,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	std	r5,_CCR(r1)
 	b	.Lsyscall_error_cont
 
-.Lsyscall_restore_math:
-	/*
-	 * Some initial tests from restore_math to avoid the heavyweight
-	 * C code entry and MSR manipulations.
-	 */
-	LOAD_REG_IMMEDIATE(r0, MSR_TS_MASK)
-	and.	r0,r0,r8
-	bne	1f
-
-	ld	r7,PACACURRENT(r13)
-	lbz	r0,THREAD+THREAD_LOAD_FP(r7)
-#ifdef CONFIG_ALTIVEC
-	lbz	r6,THREAD+THREAD_LOAD_VEC(r7)
-	add	r0,r0,r6
-#endif
-	cmpdi	r0,0
-	beq	.Lsyscall_restore_math_cont
-
-1:	addi    r3,r1,STACK_FRAME_OVERHEAD
-#ifdef CONFIG_PPC_BOOK3S
-	li	r10,MSR_RI
-	mtmsrd	r10,1		/* Restore RI */
-#endif
-	bl	restore_math
-#ifdef CONFIG_PPC_BOOK3S
-	li	r11,0
-	mtmsrd	r11,1
-#endif
-	/* Restore volatiles, reload MSR from updated one */
-	ld	r8,_MSR(r1)
-	ld	r3,RESULT(r1)
-	li	r11,-MAX_ERRNO
-	b	.Lsyscall_restore_math_cont
-
 /* Traced system call support */
 .Lsyscall_dotrace:
 	bl	save_nvgprs

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);
 		}
@@ -511,10 +512,6 @@ void restore_math(struct pt_regs *regs)
 {
 	unsigned long msr;
 
-	/*
-	 * Syscall exit makes a similar initial check before branching
-	 * to restore_math. Keep them in synch.
-	 */
 	if (!msr_tm_active(regs->msr) &&
 		!current->thread.load_fp && !loadvec(current->thread))
 		return;

arch/powerpc/kernel/smp.c

@@ -351,7 +351,7 @@ static void nmi_ipi_lock_start(unsigned long *flags)
 	hard_irq_disable();
 	while (atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1) {
 		raw_local_irq_restore(*flags);
-		cpu_relax();
+		spin_until_cond(atomic_read(&__nmi_ipi_lock) == 0);
 		raw_local_irq_save(*flags);
 		hard_irq_disable();
 	}
@@ -360,7 +360,7 @@ static void nmi_ipi_lock_start(unsigned long *flags)
 static void nmi_ipi_lock(void)
 {
 	while (atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1)
-		cpu_relax();
+		spin_until_cond(atomic_read(&__nmi_ipi_lock) == 0);
 }
 
 static void nmi_ipi_unlock(void)
@@ -475,7 +475,7 @@ int smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us)
 	nmi_ipi_lock_start(&flags);
 	while (nmi_ipi_busy_count) {
 		nmi_ipi_unlock_end(&flags);
-		cpu_relax();
+		spin_until_cond(nmi_ipi_busy_count == 0);
 		nmi_ipi_lock_start(&flags);
 	}
 

arch/powerpc/kernel/watchdog.c

@@ -71,15 +71,20 @@ static inline void wd_smp_lock(unsigned long *flags)
 	 * This may be called from low level interrupt handlers at some
 	 * point in future.
 	 */
-	local_irq_save(*flags);
-	while (unlikely(test_and_set_bit_lock(0, &__wd_smp_lock)))
-		cpu_relax();
+	raw_local_irq_save(*flags);
+	hard_irq_disable(); /* Make it soft-NMI safe */
+	while (unlikely(test_and_set_bit_lock(0, &__wd_smp_lock))) {
+		raw_local_irq_restore(*flags);
+		spin_until_cond(!test_bit(0, &__wd_smp_lock));
+		raw_local_irq_save(*flags);
+		hard_irq_disable();
+	}
 }
 
 static inline void wd_smp_unlock(unsigned long *flags)
 {
 	clear_bit_unlock(0, &__wd_smp_lock);
-	local_irq_restore(*flags);
+	raw_local_irq_restore(*flags);
 }
 
 static void wd_lockup_ipi(struct pt_regs *regs)
@@ -96,10 +101,10 @@ static void wd_lockup_ipi(struct pt_regs *regs)
 		nmi_panic(regs, "Hard LOCKUP");
 }
 
-static void set_cpu_stuck(int cpu, u64 tb)
+static void set_cpumask_stuck(const struct cpumask *cpumask, u64 tb)
 {
-	cpumask_set_cpu(cpu, &wd_smp_cpus_stuck);
-	cpumask_clear_cpu(cpu, &wd_smp_cpus_pending);
+	cpumask_or(&wd_smp_cpus_stuck, &wd_smp_cpus_stuck, cpumask);
+	cpumask_andnot(&wd_smp_cpus_pending, &wd_smp_cpus_pending, cpumask);
 	if (cpumask_empty(&wd_smp_cpus_pending)) {
 		wd_smp_last_reset_tb = tb;
 		cpumask_andnot(&wd_smp_cpus_pending,
@@ -107,6 +112,10 @@ static void set_cpu_stuck(int cpu, u64 tb)
 				&wd_smp_cpus_stuck);
 	}
 }
+static void set_cpu_stuck(int cpu, u64 tb)
+{
+	set_cpumask_stuck(cpumask_of(cpu), tb);
+}
 
 static void watchdog_smp_panic(int cpu, u64 tb)
 {
@@ -135,11 +144,9 @@ static void watchdog_smp_panic(int cpu, u64 tb)
 	}
 	smp_flush_nmi_ipi(1000000);
 
-	/* Take the stuck CPU out of the watch group */
-	for_each_cpu(c, &wd_smp_cpus_pending)
-		set_cpu_stuck(c, tb);
+	/* Take the stuck CPUs out of the watch group */
+	set_cpumask_stuck(&wd_smp_cpus_pending, tb);
 
-out:
 	wd_smp_unlock(&flags);
 
 	printk_safe_flush();
@@ -152,6 +159,11 @@ out:
 
 	if (hardlockup_panic)
 		nmi_panic(NULL, "Hard LOCKUP");
+
+	return;
+
+out:
+	wd_smp_unlock(&flags);
 }
 
 static void wd_smp_clear_cpu_pending(int cpu, u64 tb)
@@ -258,9 +270,11 @@ static void wd_timer_fn(unsigned long data)
 
 void arch_touch_nmi_watchdog(void)
 {
+	unsigned long ticks = tb_ticks_per_usec * wd_timer_period_ms * 1000;
 	int cpu = smp_processor_id();
 
-	watchdog_timer_interrupt(cpu);
+	if (get_tb() - per_cpu(wd_timer_tb, cpu) >= ticks)
+		watchdog_timer_interrupt(cpu);
 }
 EXPORT_SYMBOL(arch_touch_nmi_watchdog);
 
@@ -283,6 +297,8 @@ static void stop_watchdog_timer_on(unsigned int cpu)
 
 static int start_wd_on_cpu(unsigned int cpu)
 {
+	unsigned long flags;
+
 	if (cpumask_test_cpu(cpu, &wd_cpus_enabled)) {
 		WARN_ON(1);
 		return 0;
@@ -297,12 +313,14 @@ static int start_wd_on_cpu(unsigned int cpu)
 	if (!cpumask_test_cpu(cpu, &watchdog_cpumask))
 		return 0;
 
+	wd_smp_lock(&flags);
 	cpumask_set_cpu(cpu, &wd_cpus_enabled);
 	if (cpumask_weight(&wd_cpus_enabled) == 1) {
 		cpumask_set_cpu(cpu, &wd_smp_cpus_pending);
 		wd_smp_last_reset_tb = get_tb();
 	}
-	smp_wmb();
+	wd_smp_unlock(&flags);
+
 	start_watchdog_timer_on(cpu);
 
 	return 0;
@@ -310,12 +328,17 @@ static int start_wd_on_cpu(unsigned int cpu)
 
 static int stop_wd_on_cpu(unsigned int cpu)
 {
+	unsigned long flags;
+
 	if (!cpumask_test_cpu(cpu, &wd_cpus_enabled))
 		return 0; /* Can happen in CPU unplug case */
 
 	stop_watchdog_timer_on(cpu);
 
+	wd_smp_lock(&flags);
 	cpumask_clear_cpu(cpu, &wd_cpus_enabled);
+	wd_smp_unlock(&flags);
+
 	wd_smp_clear_cpu_pending(cpu, get_tb());
 
 	return 0;

arch/powerpc/platforms/powernv/idle.c

@@ -56,6 +56,7 @@ u64 pnv_first_deep_stop_state = MAX_STOP_STATE;
  */
 static u64 pnv_deepest_stop_psscr_val;
 static u64 pnv_deepest_stop_psscr_mask;
+static u64 pnv_deepest_stop_flag;
 static bool deepest_stop_found;
 
 static int pnv_save_sprs_for_deep_states(void)
@@ -185,8 +186,40 @@ static void pnv_alloc_idle_core_states(void)
 
 	update_subcore_sibling_mask();
 
-	if (supported_cpuidle_states & OPAL_PM_LOSE_FULL_CONTEXT)
-		pnv_save_sprs_for_deep_states();
+	if (supported_cpuidle_states & OPAL_PM_LOSE_FULL_CONTEXT) {
+		int rc = pnv_save_sprs_for_deep_states();
+
+		if (likely(!rc))
+			return;
+
+		/*
+		 * The stop-api is unable to restore hypervisor
+		 * resources on wakeup from platform idle states which
+		 * lose full context. So disable such states.
+		 */
+		supported_cpuidle_states &= ~OPAL_PM_LOSE_FULL_CONTEXT;
+		pr_warn("cpuidle-powernv: Disabling idle states that lose full context\n");
+		pr_warn("cpuidle-powernv: Idle power-savings, CPU-Hotplug affected\n");
+
+		if (cpu_has_feature(CPU_FTR_ARCH_300) &&
+		    (pnv_deepest_stop_flag & OPAL_PM_LOSE_FULL_CONTEXT)) {
+			/*
+			 * Use the default stop state for CPU-Hotplug
+			 * if available.
+			 */
+			if (default_stop_found) {
+				pnv_deepest_stop_psscr_val =
+					pnv_default_stop_val;
+				pnv_deepest_stop_psscr_mask =
+					pnv_default_stop_mask;
+				pr_warn("cpuidle-powernv: Offlined CPUs will stop with psscr = 0x%016llx\n",
+					pnv_deepest_stop_psscr_val);
+			} else { /* Fallback to snooze loop for CPU-Hotplug */
+				deepest_stop_found = false;
+				pr_warn("cpuidle-powernv: Offlined CPUs will busy wait\n");
+			}
+		}
+	}
 }
 
 u32 pnv_get_supported_cpuidle_states(void)
@@ -375,7 +408,8 @@ unsigned long pnv_cpu_offline(unsigned int cpu)
 						pnv_deepest_stop_psscr_val;
 		srr1 = power9_idle_stop(psscr);
 
-	} else if (idle_states & OPAL_PM_WINKLE_ENABLED) {
+	} else if ((idle_states & OPAL_PM_WINKLE_ENABLED) &&
+		   (idle_states & OPAL_PM_LOSE_FULL_CONTEXT)) {
 		srr1 = power7_idle_insn(PNV_THREAD_WINKLE);
 	} else if ((idle_states & OPAL_PM_SLEEP_ENABLED) ||
 		   (idle_states & OPAL_PM_SLEEP_ENABLED_ER1)) {
@@ -553,6 +587,7 @@ static int __init pnv_power9_idle_init(struct device_node *np, u32 *flags,
 			max_residency_ns = residency_ns[i];
 			pnv_deepest_stop_psscr_val = psscr_val[i];
 			pnv_deepest_stop_psscr_mask = psscr_mask[i];
+			pnv_deepest_stop_flag = flags[i];
 			deepest_stop_found = true;
 		}
 

arch/s390/include/asm/tlb.h

@@ -47,10 +47,9 @@ struct mmu_table_batch {
 extern void tlb_table_flush(struct mmu_gather *tlb);
 extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
 
-static inline void tlb_gather_mmu(struct mmu_gather *tlb,
-				  struct mm_struct *mm,
-				  unsigned long start,
-				  unsigned long end)
+static inline void
+arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
+			unsigned long start, unsigned long end)
 {
 	tlb->mm = mm;
 	tlb->start = start;
@@ -76,9 +75,15 @@ static inline void tlb_flush_mmu(struct mmu_gather *tlb)
 	tlb_flush_mmu_free(tlb);
 }
 
-static inline void tlb_finish_mmu(struct mmu_gather *tlb,
-				  unsigned long start, unsigned long end)
+static inline void
+arch_tlb_finish_mmu(struct mmu_gather *tlb,
+		unsigned long start, unsigned long end, bool force)
 {
+	if (force) {
+		tlb->start = start;
+		tlb->end = end;
+	}
+
 	tlb_flush_mmu(tlb);
 }
 

arch/sh/include/asm/tlb.h

@@ -36,7 +36,8 @@ static inline void init_tlb_gather(struct mmu_gather *tlb)
 }
 
 static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
+arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
+		unsigned long start, unsigned long end)
 {
 	tlb->mm = mm;
 	tlb->start = start;
@@ -47,9 +48,10 @@ tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start
 }
 
 static inline void
-tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
+arch_tlb_finish_mmu(struct mmu_gather *tlb,
+		unsigned long start, unsigned long end, bool force)
 {
-	if (tlb->fullmm)
+	if (tlb->fullmm || force)
 		flush_tlb_mm(tlb->mm);
 
 	/* keep the page table cache within bounds */

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/include/asm/spitfire.h

@@ -47,10 +47,26 @@
 #define SUN4V_CHIP_NIAGARA5	0x05
 #define SUN4V_CHIP_SPARC_M6	0x06
 #define SUN4V_CHIP_SPARC_M7	0x07
+#define SUN4V_CHIP_SPARC_M8	0x08
 #define SUN4V_CHIP_SPARC64X	0x8a
 #define SUN4V_CHIP_SPARC_SN	0x8b
 #define SUN4V_CHIP_UNKNOWN	0xff
 
+/*
+ * The following CPU_ID_xxx constants are used
+ * to identify the CPU type in the setup phase
+ * (see head_64.S)
+ */
+#define CPU_ID_NIAGARA1		('1')
+#define CPU_ID_NIAGARA2		('2')
+#define CPU_ID_NIAGARA3		('3')
+#define CPU_ID_NIAGARA4		('4')
+#define CPU_ID_NIAGARA5		('5')
+#define CPU_ID_M6		('6')
+#define CPU_ID_M7		('7')
+#define CPU_ID_M8		('8')
+#define CPU_ID_SONOMA1		('N')
+
 #ifndef __ASSEMBLY__
 
 enum ultra_tlb_layout {

arch/sparc/kernel/cpu.c

@@ -506,6 +506,12 @@ static void __init sun4v_cpu_probe(void)
 		sparc_pmu_type = "sparc-m7";
 		break;
 
+	case SUN4V_CHIP_SPARC_M8:
+		sparc_cpu_type = "SPARC-M8";
+		sparc_fpu_type = "SPARC-M8 integrated FPU";
+		sparc_pmu_type = "sparc-m8";
+		break;
+
 	case SUN4V_CHIP_SPARC_SN:
 		sparc_cpu_type = "SPARC-SN";
 		sparc_fpu_type = "SPARC-SN integrated FPU";

arch/sparc/kernel/cpumap.c

@@ -328,6 +328,7 @@ static int iterate_cpu(struct cpuinfo_tree *t, unsigned int root_index)
 	case SUN4V_CHIP_NIAGARA5:
 	case SUN4V_CHIP_SPARC_M6:
 	case SUN4V_CHIP_SPARC_M7:
+	case SUN4V_CHIP_SPARC_M8:
 	case SUN4V_CHIP_SPARC_SN:
 	case SUN4V_CHIP_SPARC64X:
 		rover_inc_table = niagara_iterate_method;

arch/sparc/kernel/head_64.S

@@ -424,22 +424,25 @@ EXPORT_SYMBOL(sun4v_chip_type)
 	 nop
 
 70:	ldub	[%g1 + 7], %g2
-	cmp	%g2, '3'
+	cmp	%g2, CPU_ID_NIAGARA3
 	be,pt	%xcc, 5f
 	 mov	SUN4V_CHIP_NIAGARA3, %g4
-	cmp	%g2, '4'
+	cmp	%g2, CPU_ID_NIAGARA4
 	be,pt	%xcc, 5f
 	 mov	SUN4V_CHIP_NIAGARA4, %g4
-	cmp	%g2, '5'
+	cmp	%g2, CPU_ID_NIAGARA5
 	be,pt	%xcc, 5f
 	 mov	SUN4V_CHIP_NIAGARA5, %g4
-	cmp	%g2, '6'
+	cmp	%g2, CPU_ID_M6
 	be,pt	%xcc, 5f
 	 mov	SUN4V_CHIP_SPARC_M6, %g4
-	cmp	%g2, '7'
+	cmp	%g2, CPU_ID_M7
 	be,pt	%xcc, 5f
 	 mov	SUN4V_CHIP_SPARC_M7, %g4
-	cmp	%g2, 'N'
+	cmp	%g2, CPU_ID_M8
+	be,pt	%xcc, 5f
+	 mov	SUN4V_CHIP_SPARC_M8, %g4
+	cmp	%g2, CPU_ID_SONOMA1
 	be,pt	%xcc, 5f
 	 mov	SUN4V_CHIP_SPARC_SN, %g4
 	ba,pt	%xcc, 49f
@@ -448,10 +451,10 @@ EXPORT_SYMBOL(sun4v_chip_type)
 91:	sethi	%hi(prom_cpu_compatible), %g1
 	or	%g1, %lo(prom_cpu_compatible), %g1
 	ldub	[%g1 + 17], %g2
-	cmp	%g2, '1'
+	cmp	%g2, CPU_ID_NIAGARA1
 	be,pt	%xcc, 5f
 	 mov	SUN4V_CHIP_NIAGARA1, %g4
-	cmp	%g2, '2'
+	cmp	%g2, CPU_ID_NIAGARA2
 	be,pt	%xcc, 5f
 	 mov	SUN4V_CHIP_NIAGARA2, %g4
 	
@@ -600,6 +603,9 @@ niagara_tlb_fixup:
 	be,pt	%xcc, niagara4_patch
 	 nop
 	cmp	%g1, SUN4V_CHIP_SPARC_M7
+	be,pt	%xcc, niagara4_patch
+	 nop
+	cmp	%g1, SUN4V_CHIP_SPARC_M8
 	be,pt	%xcc, niagara4_patch
 	 nop
 	cmp	%g1, SUN4V_CHIP_SPARC_SN

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/kernel/setup_64.c

@@ -288,10 +288,17 @@ static void __init sun4v_patch(void)
 
 	sun4v_patch_2insn_range(&__sun4v_2insn_patch,
 				&__sun4v_2insn_patch_end);
-	if (sun4v_chip_type == SUN4V_CHIP_SPARC_M7 ||
-	    sun4v_chip_type == SUN4V_CHIP_SPARC_SN)
+
+	switch (sun4v_chip_type) {
+	case SUN4V_CHIP_SPARC_M7:
+	case SUN4V_CHIP_SPARC_M8:
+	case SUN4V_CHIP_SPARC_SN:
 		sun_m7_patch_2insn_range(&__sun_m7_2insn_patch,
 					 &__sun_m7_2insn_patch_end);
+		break;
+	default:
+		break;
+	}
 
 	sun4v_hvapi_init();
 }
@@ -529,6 +536,7 @@ static void __init init_sparc64_elf_hwcap(void)
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA5 ||
 		    sun4v_chip_type == SUN4V_CHIP_SPARC_M6 ||
 		    sun4v_chip_type == SUN4V_CHIP_SPARC_M7 ||
+		    sun4v_chip_type == SUN4V_CHIP_SPARC_M8 ||
 		    sun4v_chip_type == SUN4V_CHIP_SPARC_SN ||
 		    sun4v_chip_type == SUN4V_CHIP_SPARC64X)
 			cap |= HWCAP_SPARC_BLKINIT;
@@ -538,6 +546,7 @@ static void __init init_sparc64_elf_hwcap(void)
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA5 ||
 		    sun4v_chip_type == SUN4V_CHIP_SPARC_M6 ||
 		    sun4v_chip_type == SUN4V_CHIP_SPARC_M7 ||
+		    sun4v_chip_type == SUN4V_CHIP_SPARC_M8 ||
 		    sun4v_chip_type == SUN4V_CHIP_SPARC_SN ||
 		    sun4v_chip_type == SUN4V_CHIP_SPARC64X)
 			cap |= HWCAP_SPARC_N2;
@@ -568,6 +577,7 @@ static void __init init_sparc64_elf_hwcap(void)
 			    sun4v_chip_type == SUN4V_CHIP_NIAGARA5 ||
 			    sun4v_chip_type == SUN4V_CHIP_SPARC_M6 ||
 			    sun4v_chip_type == SUN4V_CHIP_SPARC_M7 ||
+			    sun4v_chip_type == SUN4V_CHIP_SPARC_M8 ||
 			    sun4v_chip_type == SUN4V_CHIP_SPARC_SN ||
 			    sun4v_chip_type == SUN4V_CHIP_SPARC64X)
 				cap |= (AV_SPARC_VIS | AV_SPARC_VIS2 |
@@ -578,6 +588,7 @@ static void __init init_sparc64_elf_hwcap(void)
 			    sun4v_chip_type == SUN4V_CHIP_NIAGARA5 ||
 			    sun4v_chip_type == SUN4V_CHIP_SPARC_M6 ||
 			    sun4v_chip_type == SUN4V_CHIP_SPARC_M7 ||
+			    sun4v_chip_type == SUN4V_CHIP_SPARC_M8 ||
 			    sun4v_chip_type == SUN4V_CHIP_SPARC_SN ||
 			    sun4v_chip_type == SUN4V_CHIP_SPARC64X)
 				cap |= (AV_SPARC_VIS3 | AV_SPARC_HPC |

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/sparc/mm/init_64.c

@@ -1944,12 +1944,22 @@ static void __init setup_page_offset(void)
 			break;
 		case SUN4V_CHIP_SPARC_M7:
 		case SUN4V_CHIP_SPARC_SN:
-		default:
 			/* M7 and later support 52-bit virtual addresses.  */
 			sparc64_va_hole_top =    0xfff8000000000000UL;
 			sparc64_va_hole_bottom = 0x0008000000000000UL;
 			max_phys_bits = 49;
 			break;
+		case SUN4V_CHIP_SPARC_M8:
+		default:
+			/* M8 and later support 54-bit virtual addresses.
+			 * However, restricting M8 and above VA bits to 53
+			 * as 4-level page table cannot support more than
+			 * 53 VA bits.
+			 */
+			sparc64_va_hole_top =    0xfff0000000000000UL;
+			sparc64_va_hole_bottom = 0x0010000000000000UL;
+			max_phys_bits = 51;
+			break;
 		}
 	}
 
@@ -2161,6 +2171,7 @@ static void __init sun4v_linear_pte_xor_finalize(void)
 	 */
 	switch (sun4v_chip_type) {
 	case SUN4V_CHIP_SPARC_M7:
+	case SUN4V_CHIP_SPARC_M8:
 	case SUN4V_CHIP_SPARC_SN:
 		pagecv_flag = 0x00;
 		break;
@@ -2313,6 +2324,7 @@ void __init paging_init(void)
 	 */
 	switch (sun4v_chip_type) {
 	case SUN4V_CHIP_SPARC_M7:
+	case SUN4V_CHIP_SPARC_M8:
 	case SUN4V_CHIP_SPARC_SN:
 		page_cache4v_flag = _PAGE_CP_4V;
 		break;

arch/um/include/asm/tlb.h

@@ -45,7 +45,8 @@ static inline void init_tlb_gather(struct mmu_gather *tlb)
 }
 
 static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
+arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
+		unsigned long start, unsigned long end)
 {
 	tlb->mm = mm;
 	tlb->start = start;
@@ -80,13 +81,19 @@ tlb_flush_mmu(struct mmu_gather *tlb)
 	tlb_flush_mmu_free(tlb);
 }
 
-/* tlb_finish_mmu
+/* arch_tlb_finish_mmu
  *	Called at the end of the shootdown operation to free up any resources
  *	that were required.
  */
 static inline void
-tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
+arch_tlb_finish_mmu(struct mmu_gather *tlb,
+		unsigned long start, unsigned long end, bool force)
 {
+	if (force) {
+		tlb->start = start;
+		tlb->end = end;
+		tlb->need_flush = 1;
+	}
 	tlb_flush_mmu(tlb);
 
 	/* keep the page table cache within bounds */

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
@@ -163,9 +164,10 @@ 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_RCU_TABLE_FREE
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RELIABLE_STACKTRACE		if X86_64 && FRAME_POINTER && STACK_VALIDATION
 	select HAVE_STACK_VALIDATION		if X86_64
@@ -326,6 +328,7 @@ config FIX_EARLYCON_MEM
 
 config PGTABLE_LEVELS
 	int
+	default 5 if X86_5LEVEL
 	default 4 if X86_64
 	default 3 if X86_PAE
 	default 2
@@ -1398,6 +1401,24 @@ config X86_PAE
 	  has the cost of more pagetable lookup overhead, and also
 	  consumes more pagetable space per process.
 
+config X86_5LEVEL
+	bool "Enable 5-level page tables support"
+	depends on X86_64
+	---help---
+	  5-level paging enables access to larger address space:
+	  upto 128 PiB of virtual address space and 4 PiB of
+	  physical address space.
+
+	  It will be supported by future Intel CPUs.
+
+	  Note: a kernel with this option enabled can only be booted
+	  on machines that support the feature.
+
+	  See Documentation/x86/x86_64/5level-paging.txt for more
+	  information.
+
+	  Say N if unsure.
+
 config ARCH_PHYS_ADDR_T_64BIT
 	def_bool y
 	depends on X86_64 || X86_PAE
@@ -1415,6 +1436,35 @@ config X86_DIRECT_GBPAGES
 	  supports them), so don't confuse the user by printing
 	  that we have them enabled.
 
+config ARCH_HAS_MEM_ENCRYPT
+	def_bool y
+
+config AMD_MEM_ENCRYPT
+	bool "AMD Secure Memory Encryption (SME) support"
+	depends on X86_64 && CPU_SUP_AMD
+	---help---
+	  Say yes to enable support for the encryption of system memory.
+	  This requires an AMD processor that supports Secure Memory
+	  Encryption (SME).
+
+config AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT
+	bool "Activate AMD Secure Memory Encryption (SME) by default"
+	default y
+	depends on AMD_MEM_ENCRYPT
+	---help---
+	  Say yes to have system memory encrypted by default if running on
+	  an AMD processor that supports Secure Memory Encryption (SME).
+
+	  If set to Y, then the encryption of system memory can be
+	  deactivated with the mem_encrypt=off command line option.
+
+	  If set to N, then the encryption of system memory can be
+	  activated with the mem_encrypt=on command line option.
+
+config ARCH_USE_MEMREMAP_PROT
+	def_bool y
+	depends on AMD_MEM_ENCRYPT
+
 # Common NUMA Features
 config NUMA
 	bool "Numa Memory Allocation and Scheduler Support"

arch/x86/boot/compressed/kaslr.c

@@ -479,35 +479,31 @@ static unsigned long slots_fetch_random(void)
 	return 0;
 }
 
-static void process_e820_entry(struct boot_e820_entry *entry,
+static void process_mem_region(struct mem_vector *entry,
 			       unsigned long minimum,
 			       unsigned long image_size)
 {
 	struct mem_vector region, overlap;
 	struct slot_area slot_area;
 	unsigned long start_orig, end;
-	struct boot_e820_entry cur_entry;
-
-	/* Skip non-RAM entries. */
-	if (entry->type != E820_TYPE_RAM)
-		return;
+	struct mem_vector cur_entry;
 
 	/* On 32-bit, ignore entries entirely above our maximum. */
-	if (IS_ENABLED(CONFIG_X86_32) && entry->addr >= KERNEL_IMAGE_SIZE)
+	if (IS_ENABLED(CONFIG_X86_32) && entry->start >= KERNEL_IMAGE_SIZE)
 		return;
 
 	/* Ignore entries entirely below our minimum. */
-	if (entry->addr + entry->size < minimum)
+	if (entry->start + entry->size < minimum)
 		return;
 
 	/* Ignore entries above memory limit */
-	end = min(entry->size + entry->addr, mem_limit);
-	if (entry->addr >= end)
+	end = min(entry->size + entry->start, mem_limit);
+	if (entry->start >= end)
 		return;
-	cur_entry.addr = entry->addr;
-	cur_entry.size = end - entry->addr;
+	cur_entry.start = entry->start;
+	cur_entry.size = end - entry->start;
 
-	region.start = cur_entry.addr;
+	region.start = cur_entry.start;
 	region.size = cur_entry.size;
 
 	/* Give up if slot area array is full. */
@@ -521,8 +517,8 @@ static void process_e820_entry(struct boot_e820_entry *entry,
 		/* Potentially raise address to meet alignment needs. */
 		region.start = ALIGN(region.start, CONFIG_PHYSICAL_ALIGN);
 
-		/* Did we raise the address above this e820 region? */
-		if (region.start > cur_entry.addr + cur_entry.size)
+		/* Did we raise the address above the passed in memory entry? */
+		if (region.start > cur_entry.start + cur_entry.size)
 			return;
 
 		/* Reduce size by any delta from the original address. */
@@ -562,12 +558,32 @@ static void process_e820_entry(struct boot_e820_entry *entry,
 	}
 }
 
-static unsigned long find_random_phys_addr(unsigned long minimum,
-					   unsigned long image_size)
+static void process_e820_entries(unsigned long minimum,
+				 unsigned long image_size)
 {
 	int i;
-	unsigned long addr;
+	struct mem_vector region;
+	struct boot_e820_entry *entry;
+
+	/* Verify potential e820 positions, appending to slots list. */
+	for (i = 0; i < boot_params->e820_entries; i++) {
+		entry = &boot_params->e820_table[i];
+		/* Skip non-RAM entries. */
+		if (entry->type != E820_TYPE_RAM)
+			continue;
+		region.start = entry->addr;
+		region.size = entry->size;
+		process_mem_region(&region, minimum, image_size);
+		if (slot_area_index == MAX_SLOT_AREA) {
+			debug_putstr("Aborted e820 scan (slot_areas full)!\n");
+			break;
+		}
+	}
+}
 
+static unsigned long find_random_phys_addr(unsigned long minimum,
+					   unsigned long image_size)
+{
 	/* Check if we had too many memmaps. */
 	if (memmap_too_large) {
 		debug_putstr("Aborted e820 scan (more than 4 memmap= args)!\n");
@@ -577,16 +593,7 @@ static unsigned long find_random_phys_addr(unsigned long minimum,
 	/* Make sure minimum is aligned. */
 	minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN);
 
-	/* Verify potential e820 positions, appending to slots list. */
-	for (i = 0; i < boot_params->e820_entries; i++) {
-		process_e820_entry(&boot_params->e820_table[i], minimum,
-				   image_size);
-		if (slot_area_index == MAX_SLOT_AREA) {
-			debug_putstr("Aborted e820 scan (slot_areas full)!\n");
-			break;
-		}
-	}
-
+	process_e820_entries(minimum, image_size);
 	return slots_fetch_random();
 }
 

arch/x86/boot/compressed/pagetable.c

@@ -15,6 +15,13 @@
 #define __pa(x)  ((unsigned long)(x))
 #define __va(x)  ((void *)((unsigned long)(x)))
 
+/*
+ * The pgtable.h and mm/ident_map.c includes make use of the SME related
+ * information which is not used in the compressed image support. Un-define
+ * the SME support to avoid any compile and link errors.
+ */
+#undef CONFIG_AMD_MEM_ENCRYPT
+
 #include "misc.h"
 
 /* These actually do the work of building the kernel identity maps. */

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)