Merge tag 'lsk-v4.4-17.07-android' of git://git.linaro.org/kernel/linux-linaro-stable.git

LSK 17.07 v4.4-android * tag 'lsk-v4.4-17.07-android': (402 commits) dt/vendor-prefixes: remove redundant vendor Linux 4.4.77 saa7134: fix warm Medion 7134 EEPROM read x86/mm/pat: Don't report PAT on CPUs that don't support it ext4: check return value of kstrtoull correctly in reserved_clusters_store staging: comedi: fix clean-up of comedi_class in comedi_init() staging: vt6556: vnt_start Fix missing call to vnt_key_init_table. tcp: fix tcp_mark_head_lost to check skb len before fragmenting md: fix super_offset endianness in super_1_rdev_size_change md: fix incorrect use of lexx_to_cpu in does_sb_need_changing perf tools: Use readdir() instead of deprecated readdir_r() again perf tests: Remove wrong semicolon in while loop in CQM test perf trace: Do not process PERF_RECORD_LOST twice perf dwarf: Guard !x86_64 definitions under #ifdef else clause perf pmu: Fix misleadingly indented assignment (whitespace) perf annotate browser: Fix behaviour of Shift-Tab with nothing focussed perf tools: Remove duplicate const qualifier perf script: Use readdir() instead of deprecated readdir_r() perf thread_map: Use readdir() instead of deprecated readdir_r() perf tools: Use readdir() instead of deprecated readdir_r() ... Conflicts: Makefile drivers/Kconfig drivers/Makefile drivers/usb/dwc3/gadget.c Change-Id: Ib4aae2e34ebbf0d7953c748a33f673acb3e744fc
2026-03-24 19:40:21 +09:00 · 2017-07-26 19:32:04 +08:00
parent 8ccefa5de2 16e243013b
commit 6ee6d6d68b
462 changed files with 9493 additions and 1662 deletions
--- a/Documentation/00-INDEX
+++ b/Documentation/00-INDEX
@@ -435,6 +435,8 @@ sysrq.txt
 	- info on the magic SysRq key.
 target/
 	- directory with info on generating TCM v4 fabric .ko modules
+tee.txt
+	- info on the TEE subsystem and drivers
 this_cpu_ops.txt
 	- List rationale behind and the way to use this_cpu operations.
 thermal/
--- a/Documentation/devicetree/bindings/arm/firmware/linaro,optee-tz.txt
+++ b/Documentation/devicetree/bindings/arm/firmware/linaro,optee-tz.txt
@@ -0,0 +1,31 @@
+OP-TEE Device Tree Bindings
+
+OP-TEE is a piece of software using hardware features to provide a Trusted
+Execution Environment. The security can be provided with ARM TrustZone, but
+also by virtualization or a separate chip.
+
+We're using "linaro" as the first part of the compatible property for
+the reference implementation maintained by Linaro.
+
+* OP-TEE based on ARM TrustZone required properties:
+
+- compatible     : should contain "linaro,optee-tz"
+
+- method         : The method of calling the OP-TEE Trusted OS. Permitted
+                   values are:
+
+                   "smc" : SMC #0, with the register assignments specified
+		           in drivers/tee/optee/optee_smc.h
+
+                   "hvc" : HVC #0, with the register assignments specified
+		           in drivers/tee/optee/optee_smc.h
+
+
+
+Example:
+	firmware {
+		optee {
+			compatible = "linaro,optee-tz";
+			method = "smc";
+		};
+	};
--- a/Documentation/devicetree/bindings/chosen.txt
+++ b/Documentation/devicetree/bindings/chosen.txt
@@ -52,3 +52,48 @@ This property is set (currently only on PowerPC, and only needed on
 book3e) by some versions of kexec-tools to tell the new kernel that it
 is being booted by kexec, as the booting environment may differ (e.g.
 a different secondary CPU release mechanism)
+
+linux,usable-memory-range
+-------------------------
+
+This property (arm64 only) holds a base address and size, describing a
+limited region in which memory may be considered available for use by
+the kernel. Memory outside of this range is not available for use.
+
+This property describes a limitation: memory within this range is only
+valid when also described through another mechanism that the kernel
+would otherwise use to determine available memory (e.g. memory nodes
+or the EFI memory map). Valid memory may be sparse within the range.
+e.g.
+
+/ {
+	chosen {
+		linux,usable-memory-range = <0x9 0xf0000000 0x0 0x10000000>;
+	};
+};
+
+The main usage is for crash dump kernel to identify its own usable
+memory and exclude, at its boot time, any other memory areas that are
+part of the panicked kernel's memory.
+
+While this property does not represent a real hardware, the address
+and the size are expressed in #address-cells and #size-cells,
+respectively, of the root node.
+
+linux,elfcorehdr
+----------------
+
+This property (currently used only on arm64) holds the memory range,
+the address and the size, of the elf core header which mainly describes
+the panicked kernel's memory layout as PT_LOAD segments of elf format.
+e.g.
+
+/ {
+	chosen {
+		linux,elfcorehdr = <0x9 0xfffff000 0x0 0x800>;
+	};
+};
+
+While this property does not represent a real hardware, the address
+and the size are expressed in #address-cells and #size-cells,
+respectively, of the root node.
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -128,6 +128,7 @@ lacie	LaCie
 lantiq	Lantiq Semiconductor
 lenovo	Lenovo Group Ltd.
 lg	LG Corporation
+linaro	Linaro Limited
 linux	Linux-specific binding
 lsi	LSI Corp. (LSI Logic)
 lltc	Linear Technology Corporation
--- a/Documentation/ioctl/ioctl-number.txt
+++ b/Documentation/ioctl/ioctl-number.txt
@@ -307,6 +307,7 @@ Code  Seq#(hex)	Include File		Comments
 0xA3	80-8F	Port ACL		in development:
 					<mailto:tlewis@mindspring.com>
 0xA3	90-9F	linux/dtlk.h
+0xA4	00-1F	uapi/linux/tee.h	Generic TEE subsystem
 0xAA	00-3F	linux/uapi/linux/userfaultfd.h
 0xAB	00-1F	linux/nbd.h
 0xAC	00-1F	linux/raw.h
--- a/Documentation/kdump/kdump.txt
+++ b/Documentation/kdump/kdump.txt
@@ -18,7 +18,7 @@ memory image to a dump file on the local disk, or across the network to
 a remote system.

 Kdump and kexec are currently supported on the x86, x86_64, ppc64, ia64,
-s390x and arm architectures.
+s390x, arm and arm64 architectures.

 When the system kernel boots, it reserves a small section of memory for
 the dump-capture kernel. This ensures that ongoing Direct Memory Access
@@ -249,6 +249,13 @@ Dump-capture kernel config options (Arch Dependent, arm)

    AUTO_ZRELADDR=y

+Dump-capture kernel config options (Arch Dependent, arm64)
+----------------------------------------------------------
+
+- Please note that kvm of the dump-capture kernel will not be enabled
+  on non-VHE systems even if it is configured. This is because the CPU
+  will not be reset to EL2 on panic.
+
 Extended crashkernel syntax
 ===========================

@@ -312,6 +319,8 @@ Boot into System Kernel
   any space below the alignment point may be overwritten by the dump-capture kernel,
   which means it is possible that the vmcore is not that precise as expected.

+   On arm64, use "crashkernel=Y[@X]".  Note that the start address of
+   the kernel, X if explicitly specified, must be aligned to 2MiB (0x200000).

 Load the Dump-capture Kernel
 ============================
@@ -334,6 +343,8 @@ For s390x:
 	- Use image or bzImage
 For arm:
 	- Use zImage
+For arm64:
+	- Use vmlinux or Image

 If you are using a uncompressed vmlinux image then use following command
 to load dump-capture kernel.
@@ -377,6 +388,9 @@ For s390x:
 For arm:
 	"1 maxcpus=1 reset_devices"

+For arm64:
+	"1 maxcpus=1 reset_devices"
+
 Notes on loading the dump-capture kernel:

 * By default, the ELF headers are stored in ELF64 format to support
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -3590,6 +3590,13 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	spia_pedr=
 	spia_peddr=

+	stack_guard_gap=	[MM]
+			override the default stack gap protection. The value
+			is in page units and it defines how many pages prior
+			to (for stacks growing down) resp. after (for stacks
+			growing up) the main stack are reserved for no other
+			mapping. Default value is 256 pages.
+
 	stacktrace	[FTRACE]
 			Enabled the stack tracer on boot up.

--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -825,14 +825,13 @@ via the /proc/sys interface:
       Each write syscall must fully contain the sysctl value to be
       written, and multiple writes on the same sysctl file descriptor
       will rewrite the sysctl value, regardless of file position.
-   0 - (default) Same behavior as above, but warn about processes that
-       perform writes to a sysctl file descriptor when the file position
-       is not 0.
-   1 - Respect file position when writing sysctl strings. Multiple writes
-       will append to the sysctl value buffer. Anything past the max length
-       of the sysctl value buffer will be ignored. Writes to numeric sysctl
-       entries must always be at file position 0 and the value must be
-       fully contained in the buffer sent in the write syscall.
+   0 - Same behavior as above, but warn about processes that perform writes
+       to a sysctl file descriptor when the file position is not 0.
+   1 - (default) Respect file position when writing sysctl strings. Multiple
+       writes will append to the sysctl value buffer. Anything past the max
+       length of the sysctl value buffer will be ignored. Writes to numeric
+       sysctl entries must always be at file position 0 and the value must
+       be fully contained in the buffer sent in the write syscall.

 ==============================================================

--- a/Documentation/tee.txt
+++ b/Documentation/tee.txt
@@ -0,0 +1,118 @@
+TEE subsystem
+This document describes the TEE subsystem in Linux.
+
+A TEE (Trusted Execution Environment) is a trusted OS running in some
+secure environment, for example, TrustZone on ARM CPUs, or a separate
+secure co-processor etc. A TEE driver handles the details needed to
+communicate with the TEE.
+
+This subsystem deals with:
+
+- Registration of TEE drivers
+
+- Managing shared memory between Linux and the TEE
+
+- Providing a generic API to the TEE
+
+The TEE interface
+=================
+
+include/uapi/linux/tee.h defines the generic interface to a TEE.
+
+User space (the client) connects to the driver by opening /dev/tee[0-9]* or
+/dev/teepriv[0-9]*.
+
+- TEE_IOC_SHM_ALLOC allocates shared memory and returns a file descriptor
+  which user space can mmap. When user space doesn't need the file
+  descriptor any more, it should be closed. When shared memory isn't needed
+  any longer it should be unmapped with munmap() to allow the reuse of
+  memory.
+
+- TEE_IOC_VERSION lets user space know which TEE this driver handles and
+  the its capabilities.
+
+- TEE_IOC_OPEN_SESSION opens a new session to a Trusted Application.
+
+- TEE_IOC_INVOKE invokes a function in a Trusted Application.
+
+- TEE_IOC_CANCEL may cancel an ongoing TEE_IOC_OPEN_SESSION or TEE_IOC_INVOKE.
+
+- TEE_IOC_CLOSE_SESSION closes a session to a Trusted Application.
+
+There are two classes of clients, normal clients and supplicants. The latter is
+a helper process for the TEE to access resources in Linux, for example file
+system access. A normal client opens /dev/tee[0-9]* and a supplicant opens
+/dev/teepriv[0-9].
+
+Much of the communication between clients and the TEE is opaque to the
+driver. The main job for the driver is to receive requests from the
+clients, forward them to the TEE and send back the results. In the case of
+supplicants the communication goes in the other direction, the TEE sends
+requests to the supplicant which then sends back the result.
+
+OP-TEE driver
+=============
+
+The OP-TEE driver handles OP-TEE [1] based TEEs. Currently it is only the ARM
+TrustZone based OP-TEE solution that is supported.
+
+Lowest level of communication with OP-TEE builds on ARM SMC Calling
+Convention (SMCCC) [2], which is the foundation for OP-TEE's SMC interface
+[3] used internally by the driver. Stacked on top of that is OP-TEE Message
+Protocol [4].
+
+OP-TEE SMC interface provides the basic functions required by SMCCC and some
+additional functions specific for OP-TEE. The most interesting functions are:
+
+- OPTEE_SMC_FUNCID_CALLS_UID (part of SMCCC) returns the version information
+  which is then returned by TEE_IOC_VERSION
+
+- OPTEE_SMC_CALL_GET_OS_UUID returns the particular OP-TEE implementation, used
+  to tell, for instance, a TrustZone OP-TEE apart from an OP-TEE running on a
+  separate secure co-processor.
+
+- OPTEE_SMC_CALL_WITH_ARG drives the OP-TEE message protocol
+
+- OPTEE_SMC_GET_SHM_CONFIG lets the driver and OP-TEE agree on which memory
+  range to used for shared memory between Linux and OP-TEE.
+
+The GlobalPlatform TEE Client API [5] is implemented on top of the generic
+TEE API.
+
+Picture of the relationship between the different components in the
+OP-TEE architecture.
+
+    User space                  Kernel                   Secure world
+    ~~~~~~~~~~                  ~~~~~~                   ~~~~~~~~~~~~
+ +--------+                                             +-------------+
+ | Client |                                             | Trusted     |
+ +--------+                                             | Application |
+    /\                                                  +-------------+
+    || +----------+                                           /\
+    || |tee-      |                                           ||
+    || |supplicant|                                           \/
+    || +----------+                                     +-------------+
+    \/      /\                                          | TEE Internal|
+ +-------+  ||                                          | API         |
+ + TEE   |  ||            +--------+--------+           +-------------+
+ | Client|  ||            | TEE    | OP-TEE |           | OP-TEE      |
+ | API   |  \/            | subsys | driver |           | Trusted OS  |
+ +-------+----------------+----+-------+----+-----------+-------------+
+ |      Generic TEE API        |       |     OP-TEE MSG               |
+ |      IOCTL (TEE_IOC_*)      |       |     SMCCC (OPTEE_SMC_CALL_*) |
+ +-----------------------------+       +------------------------------+
+
+RPC (Remote Procedure Call) are requests from secure world to kernel driver
+or tee-supplicant. An RPC is identified by a special range of SMCCC return
+values from OPTEE_SMC_CALL_WITH_ARG. RPC messages which are intended for the
+kernel are handled by the kernel driver. Other RPC messages will be forwarded to
+tee-supplicant without further involvement of the driver, except switching
+shared memory buffer representation.
+
+References:
+[1] https://github.com/OP-TEE/optee_os
+[2] http://infocenter.arm.com/help/topic/com.arm.doc.den0028a/index.html
+[3] drivers/tee/optee/optee_smc.h
+[4] drivers/tee/optee/optee_msg.h
+[5] http://www.globalplatform.org/specificationsdevice.asp look for
+    "TEE Client API Specification v1.0" and click download.
--- a/13
+++ b/13
@@ -7939,6 +7939,11 @@ F:	arch/*/oprofile/
 F:	drivers/oprofile/
 F:	include/linux/oprofile.h

+OP-TEE DRIVER
+M:	Jens Wiklander <jens.wiklander@linaro.org>
+S:	Maintained
+F:	drivers/tee/optee/
+
 ORACLE CLUSTER FILESYSTEM 2 (OCFS2)
 M:	Mark Fasheh <mfasheh@suse.com>
 M:	Joel Becker <jlbec@evilplan.org>
@@ -9366,6 +9371,14 @@ F:	drivers/hwtracing/stm/
 F:	include/linux/stm.h
 F:	include/uapi/linux/stm.h

+TEE SUBSYSTEM
+M:	Jens Wiklander <jens.wiklander@linaro.org>
+S:	Maintained
+F:	include/linux/tee_drv.h
+F:	include/uapi/linux/tee.h
+F:	drivers/tee/
+F:	Documentation/tee.txt
+
 THUNDERBOLT DRIVER
 M:	Andreas Noever <andreas.noever@gmail.com>
 S:	Maintained
--- a/24
+++ b/24
@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 4
-SUBLEVEL = 71
+SUBLEVEL = 77
 EXTRAVERSION =
 NAME = Blurry Fish Butt

@@ -650,6 +650,17 @@ endif
 # Tell gcc to never replace conditional load with a non-conditional one
 KBUILD_CFLAGS	+= $(call cc-option,--param=allow-store-data-races=0)

+# check for 'asm goto'
+ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC) $(KBUILD_CFLAGS)), y)
+	KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO
+	KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO
+else ifneq ($(findstring aarch64-linux-android, $(CROSS_COMPILE)),)
+# It seems than android gcc can't pass gcc-goto.sh check, but asm goto work.
+# So let's active it.
+	KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO
+	KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO
+endif
+
 ifdef CONFIG_READABLE_ASM
 # Disable optimizations that make assembler listings hard to read.
 # reorder blocks reorders the control in the function
@@ -805,17 +816,6 @@ KBUILD_CFLAGS   += $(call cc-option,-Werror=date-time)
 # use the deterministic mode of AR if available
 KBUILD_ARFLAGS := $(call ar-option,D)

-# check for 'asm goto'
-ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC)), y)
-	KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO
-	KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO
-else ifneq ($(findstring aarch64-linux-android, $(CROSS_COMPILE)),)
-# It seems than android gcc can't pass gcc-goto.sh check, but asm goto work.
-# So let's active it.
-	KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO
-	KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO
-endif
-
 include scripts/Makefile.kasan
 include scripts/Makefile.extrawarn

--- a/arch/arc/mm/mmap.c
+++ b/arch/arc/mm/mmap.c
@@ -64,7 +64,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,

 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}

--- a/arch/arm/boot/dts/bcm5301x.dtsi
+++ b/arch/arm/boot/dts/bcm5301x.dtsi
@@ -54,14 +54,14 @@
 		timer@0200 {
 			compatible = "arm,cortex-a9-global-timer";
 			reg = <0x0200 0x100>;
-			interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_PPI 11 IRQ_TYPE_EDGE_RISING>;
 			clocks = <&clk_periph>;
 		};

 		local-timer@0600 {
 			compatible = "arm,cortex-a9-twd-timer";
 			reg = <0x0600 0x100>;
-			interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_PPI 13 IRQ_TYPE_EDGE_RISING>;
 			clocks = <&clk_periph>;
 		};

--- a/arch/arm/boot/dts/imx6dl.dtsi
+++ b/arch/arm/boot/dts/imx6dl.dtsi
@@ -30,7 +30,7 @@
 				/* kHz    uV */
 				996000  1250000
 				792000  1175000
-				396000  1075000
+				396000  1150000
 			>;
 			fsl,soc-operating-points = <
 				/* ARM kHz  SOC-PU uV */
--- a/arch/arm/kvm/init.S
+++ b/arch/arm/kvm/init.S
@@ -110,7 +110,6 @@ __do_hyp_init:
 	@  - Write permission implies XN: disabled
 	@  - Instruction cache: enabled
 	@  - Data/Unified cache: enabled
-	@  - Memory alignment checks: enabled
 	@  - MMU: enabled (this code must be run from an identity mapping)
 	mrc	p15, 4, r0, c1, c0, 0	@ HSCR
 	ldr	r2, =HSCTLR_MASK
@@ -118,8 +117,8 @@ __do_hyp_init:
 	mrc	p15, 0, r1, c1, c0, 0	@ SCTLR
 	ldr	r2, =(HSCTLR_EE | HSCTLR_FI | HSCTLR_I | HSCTLR_C)
 	and	r1, r1, r2
- ARM(	ldr	r2, =(HSCTLR_M | HSCTLR_A)			)
- THUMB(	ldr	r2, =(HSCTLR_M | HSCTLR_A | HSCTLR_TE)		)
+ ARM(	ldr	r2, =(HSCTLR_M)					)
+ THUMB(	ldr	r2, =(HSCTLR_M | HSCTLR_TE)			)
 	orr	r1, r1, r2
 	orr	r0, r0, r1
 	isb
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -876,6 +876,9 @@ static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache
 	pmd_t *pmd;

 	pud = stage2_get_pud(kvm, cache, addr);
+	if (!pud)
+		return NULL;
+
 	if (pud_none(*pud)) {
 		if (!cache)
 			return NULL;
--- a/arch/arm/mm/mmap.c
+++ b/arch/arm/mm/mmap.c
@@ -89,7 +89,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,

 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}

@@ -140,7 +140,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 			addr = PAGE_ALIGN(addr);
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr &&
-				(!vma || addr + len <= vma->vm_start))
+				(!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}

--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -1184,15 +1184,15 @@ void __init sanity_check_meminfo(void)

 	high_memory = __va(arm_lowmem_limit - 1) + 1;

+	if (!memblock_limit)
+		memblock_limit = arm_lowmem_limit;
+
 	/*
 	 * Round the memblock limit down to a pmd size.  This
 	 * helps to ensure that we will allocate memory from the
 	 * last full pmd, which should be mapped.
 	 */
-	if (memblock_limit)
-		memblock_limit = round_down(memblock_limit, PMD_SIZE);
-	if (!memblock_limit)
-		memblock_limit = arm_lowmem_limit;
+	memblock_limit = round_down(memblock_limit, PMD_SIZE);

 	memblock_set_current_limit(memblock_limit);
 }
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -631,6 +631,27 @@ config SECCOMP
 	  and the task is only allowed to execute a few safe syscalls
 	  defined by each seccomp mode.

+config KEXEC
+	depends on PM_SLEEP_SMP
+	select KEXEC_CORE
+	bool "kexec system call"
+	---help---
+	  kexec is a system call that implements the ability to shutdown your
+	  current kernel, and to start another kernel.  It is like a reboot
+	  but it is independent of the system firmware.   And like a reboot
+	  you can start any kernel with it, not just Linux.
+
+config CRASH_DUMP
+	bool "Build kdump crash kernel"
+	help
+	  Generate crash dump after being started by kexec. This should
+	  be normally only set in special crash dump kernels which are
+	  loaded in the main kernel with kexec-tools into a specially
+	  reserved region and then later executed after a crash by
+	  kdump/kexec.
+
+	  For more details see Documentation/kdump/kdump.txt
+
 config XEN_DOM0
 	def_bool y
 	depends on XEN
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -58,6 +58,8 @@ CONFIG_PREEMPT=y
 CONFIG_KSM=y
 CONFIG_TRANSPARENT_HUGEPAGE=y
 CONFIG_CMA=y
+CONFIG_KEXEC=y
+CONFIG_CRASH_DUMP=y
 CONFIG_CMDLINE="console=ttyAMA0"
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_COMPAT=y
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -22,9 +22,9 @@
 #define ACPI_MADT_GICC_LENGTH	\
 	(acpi_gbl_FADT.header.revision < 6 ? 76 : 80)

-#define BAD_MADT_GICC_ENTRY(entry, end)						\
-	(!(entry) || (unsigned long)(entry) + sizeof(*(entry)) > (end) ||	\
-	 (entry)->header.length != ACPI_MADT_GICC_LENGTH)
+#define BAD_MADT_GICC_ENTRY(entry, end)					\
+	(!(entry) || (entry)->header.length != ACPI_MADT_GICC_LENGTH ||	\
+	(unsigned long)(entry) + ACPI_MADT_GICC_LENGTH > (end))

 /* Basic configuration for ACPI */
 #ifdef	CONFIG_ACPI
--- a/arch/arm64/include/asm/asm-uaccess.h
+++ b/arch/arm64/include/asm/asm-uaccess.h
@@ -0,0 +1,13 @@
+#ifndef __ASM_ASM_UACCESS_H
+#define __ASM_ASM_UACCESS_H
+
+/*
+ * Remove the address tag from a virtual address, if present.
+ */
+	.macro	clear_address_tag, dst, addr
+	tst	\addr, #(1 << 55)
+	bic	\dst, \addr, #(0xff << 56)
+	csel	\dst, \dst, \addr, eq
+	.endm
+
+#endif
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -44,23 +44,33 @@

 #define smp_store_release(p, v)						\
 do {									\
+	union { typeof(*p) __val; char __c[1]; } __u =			\
+		{ .__val = (__force typeof(*p)) (v) }; 			\
 	compiletime_assert_atomic_type(*p);				\
 	switch (sizeof(*p)) {						\
 	case 1:								\
 		asm volatile ("stlrb %w1, %0"				\
-				: "=Q" (*p) : "r" (v) : "memory");	\
+				: "=Q" (*p)				\
+				: "r" (*(__u8 *)__u.__c)		\
+				: "memory");				\
 		break;							\
 	case 2:								\
 		asm volatile ("stlrh %w1, %0"				\
-				: "=Q" (*p) : "r" (v) : "memory");	\
+				: "=Q" (*p)				\
+				: "r" (*(__u16 *)__u.__c)		\
+				: "memory");				\
 		break;							\
 	case 4:								\
 		asm volatile ("stlr %w1, %0"				\
-				: "=Q" (*p) : "r" (v) : "memory");	\
+				: "=Q" (*p)				\
+				: "r" (*(__u32 *)__u.__c)		\
+				: "memory");				\
 		break;							\
 	case 8:								\
 		asm volatile ("stlr %1, %0"				\
-				: "=Q" (*p) : "r" (v) : "memory");	\
+				: "=Q" (*p)				\
+				: "r" (*(__u64 *)__u.__c)		\
+				: "memory");				\
 		break;							\
 	}								\
 } while (0)
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -155,5 +155,6 @@ int set_memory_ro(unsigned long addr, int numpages);
 int set_memory_rw(unsigned long addr, int numpages);
 int set_memory_x(unsigned long addr, int numpages);
 int set_memory_nx(unsigned long addr, int numpages);
+int set_memory_valid(unsigned long addr, unsigned long size, int enable);

 #endif
--- a/arch/arm64/include/asm/hardirq.h
+++ b/arch/arm64/include/asm/hardirq.h
@@ -20,7 +20,7 @@
 #include <linux/threads.h>
 #include <asm/irq.h>

-#define NR_IPI	6
+#define NR_IPI	7

 typedef struct {
 	unsigned int __softirq_pending;
--- a/arch/arm64/include/asm/kexec.h
+++ b/arch/arm64/include/asm/kexec.h
@@ -0,0 +1,98 @@
+/*
+ * kexec for arm64
+ *
+ * Copyright (C) Linaro.
+ * Copyright (C) Huawei Futurewei Technologies.
+ *
+ * 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.
+ */
+
+#ifndef _ARM64_KEXEC_H
+#define _ARM64_KEXEC_H
+
+/* Maximum physical address we can use pages from */
+
+#define KEXEC_SOURCE_MEMORY_LIMIT (-1UL)
+
+/* Maximum address we can reach in physical address mode */
+
+#define KEXEC_DESTINATION_MEMORY_LIMIT (-1UL)
+
+/* Maximum address we can use for the control code buffer */
+
+#define KEXEC_CONTROL_MEMORY_LIMIT (-1UL)
+
+#define KEXEC_CONTROL_PAGE_SIZE 4096
+
+#define KEXEC_ARCH KEXEC_ARCH_AARCH64
+
+#ifndef __ASSEMBLY__
+
+/**
+ * crash_setup_regs() - save registers for the panic kernel
+ *
+ * @newregs: registers are saved here
+ * @oldregs: registers to be saved (may be %NULL)
+ */
+
+static inline void crash_setup_regs(struct pt_regs *newregs,
+				    struct pt_regs *oldregs)
+{
+	if (oldregs) {
+		memcpy(newregs, oldregs, sizeof(*newregs));
+	} else {
+		u64 tmp1, tmp2;
+
+		__asm__ __volatile__ (
+			"stp	 x0,   x1, [%2, #16 *  0]\n"
+			"stp	 x2,   x3, [%2, #16 *  1]\n"
+			"stp	 x4,   x5, [%2, #16 *  2]\n"
+			"stp	 x6,   x7, [%2, #16 *  3]\n"
+			"stp	 x8,   x9, [%2, #16 *  4]\n"
+			"stp	x10,  x11, [%2, #16 *  5]\n"
+			"stp	x12,  x13, [%2, #16 *  6]\n"
+			"stp	x14,  x15, [%2, #16 *  7]\n"
+			"stp	x16,  x17, [%2, #16 *  8]\n"
+			"stp	x18,  x19, [%2, #16 *  9]\n"
+			"stp	x20,  x21, [%2, #16 * 10]\n"
+			"stp	x22,  x23, [%2, #16 * 11]\n"
+			"stp	x24,  x25, [%2, #16 * 12]\n"
+			"stp	x26,  x27, [%2, #16 * 13]\n"
+			"stp	x28,  x29, [%2, #16 * 14]\n"
+			"mov	 %0,  sp\n"
+			"stp	x30,  %0,  [%2, #16 * 15]\n"
+
+			"/* faked current PSTATE */\n"
+			"mrs	 %0, CurrentEL\n"
+			"mrs	 %1, SPSEL\n"
+			"orr	 %0, %0, %1\n"
+			"mrs	 %1, DAIF\n"
+			"orr	 %0, %0, %1\n"
+			"mrs	 %1, NZCV\n"
+			"orr	 %0, %0, %1\n"
+			/* pc */
+			"adr	 %1, 1f\n"
+		"1:\n"
+			"stp	 %1, %0,   [%2, #16 * 16]\n"
+			: "=&r" (tmp1), "=&r" (tmp2)
+			: "r" (newregs)
+			: "memory"
+		);
+	}
+}
+
+#if defined(CONFIG_KEXEC_CORE) && defined(CONFIG_HIBERNATION)
+extern bool crash_is_nosave(unsigned long pfn);
+extern void crash_prepare_suspend(void);
+extern void crash_post_resume(void);
+#else
+static inline bool crash_is_nosave(unsigned long pfn) {return false; }
+static inline void crash_prepare_suspend(void) {}
+static inline void crash_post_resume(void) {}
+#endif
+
+#endif /* __ASSEMBLY__ */
+
+#endif
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -33,7 +33,7 @@ extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt);
 extern void init_mem_pgprot(void);
 extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
 			       unsigned long virt, phys_addr_t size,
-			       pgprot_t prot);
+			       pgprot_t prot, bool allow_block_mappings);
 extern void *fixmap_remap_fdt(phys_addr_t dt_phys);

 #endif
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -16,6 +16,19 @@
 #ifndef __ASM_SMP_H
 #define __ASM_SMP_H

+/* Values for secondary_data.status */
+
+#define CPU_MMU_OFF		(-1)
+#define CPU_BOOT_SUCCESS	(0)
+/* The cpu invoked ops->cpu_die, synchronise it with cpu_kill */
+#define CPU_KILL_ME		(1)
+/* The cpu couldn't die gracefully and is looping in the kernel */
+#define CPU_STUCK_IN_KERNEL	(2)
+/* Fatal system error detected by secondary CPU, crash the system */
+#define CPU_PANIC_KERNEL	(3)
+
+#ifndef __ASSEMBLY__
+
 #include <linux/threads.h>
 #include <linux/cpumask.h>
 #include <linux/thread_info.h>
@@ -54,11 +67,17 @@ asmlinkage void secondary_start_kernel(void);

 /*
 * Initial data for bringing up a secondary CPU.
+ * @stack  - sp for the secondary CPU
+ * @status - Result passed back from the secondary CPU to
+ *           indicate failure.
 */
 struct secondary_data {
 	void *stack;
+	long status;
 };
+
 extern struct secondary_data secondary_data;
+extern long __early_cpu_boot_status;
 extern void secondary_entry(void);

 extern void arch_send_call_function_single_ipi(int cpu);
@@ -77,5 +96,38 @@ extern int __cpu_disable(void);

 extern void __cpu_die(unsigned int cpu);
 extern void cpu_die(void);
+extern void cpu_die_early(void);
+
+static inline void cpu_park_loop(void)
+{
+	for (;;) {
+		wfe();
+		wfi();
+	}
+}
+
+static inline void update_cpu_boot_status(int val)
+{
+	WRITE_ONCE(secondary_data.status, val);
+	/* Ensure the visibility of the status update */
+	dsb(ishst);
+}
+
+/*
+ * If a secondary CPU enters the kernel but fails to come online,
+ * (e.g. due to mismatched features), and cannot exit the kernel,
+ * we increment cpus_stuck_in_kernel and leave the CPU in a
+ * quiesecent loop within the kernel text. The memory containing
+ * this loop must not be re-used for anything else as the 'stuck'
+ * core is executing it.
+ *
+ * This function is used to inhibit features like kexec and hibernate.
+ */
+bool cpus_are_stuck_in_kernel(void);
+
+extern void smp_send_crash_stop(void);
+extern bool smp_crash_stop_failed(void);
+
+#endif /* ifndef __ASSEMBLY__ */

 #endif /* ifndef __ASM_SMP_H */
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -27,6 +27,7 @@
 /*
 * User space memory access functions
 */
+#include <linux/bitops.h>
 #include <linux/string.h>
 #include <linux/thread_info.h>

@@ -119,6 +120,13 @@ static inline void set_fs(mm_segment_t fs)
 	flag;								\
 })

+/*
+ * When dealing with data aborts, watchpoints, or instruction traps we may end
+ * up with a tagged userland pointer. Clear the tag to get a sane pointer to
+ * pass on to access_ok(), for instance.
+ */
+#define untagged_addr(addr)		sign_extend64(addr, 55)
+
 #define access_ok(type, addr, size)	__range_ok(addr, size)
 #define user_addr_max			get_fs

--- a/arch/arm64/include/asm/virt.h
+++ b/arch/arm64/include/asm/virt.h
@@ -34,6 +34,11 @@
 */
 #define HVC_SET_VECTORS 1

+/*
+ * HVC_SOFT_RESTART - CPU soft reset, used by the cpu_soft_restart routine.
+ */
+#define HVC_SOFT_RESTART 2
+
 #define BOOT_CPU_MODE_EL1	(0xe11)
 #define BOOT_CPU_MODE_EL2	(0xe12)

--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -44,7 +44,9 @@ arm64-obj-$(CONFIG_ACPI)		+= acpi.o
 arm64-obj-$(CONFIG_RANDOMIZE_BASE)	+= kaslr.o
 arm64-obj-$(CONFIG_HIBERNATION)		+= hibernate.o hibernate-asm.o
 arm64-obj-$(CONFIG_ARM64_ACPI_PARKING_PROTOCOL)	+= acpi_parking_protocol.o
-arm64-obj-$(CONFIG_PARAVIRT)		+= paravirt.o
+arm64-obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o	\
+					   cpu-reset.o
+arm64-obj-$(CONFIG_CRASH_DUMP)		+= crash_dump.o

 obj-y					+= $(arm64-obj-y) vdso/ probes/
 obj-m					+= $(arm64-obj-m)
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -299,7 +299,8 @@ do {								\
 	_ASM_EXTABLE(0b, 4b)					\
 	_ASM_EXTABLE(1b, 4b)					\
 	: "=&r" (res), "+r" (data), "=&r" (temp)		\
-	: "r" (addr), "i" (-EAGAIN), "i" (-EFAULT)		\
+	: "r" ((unsigned long)addr), "i" (-EAGAIN),		\
+	  "i" (-EFAULT)						\
 	: "memory");						\
 	uaccess_disable();					\
 } while (0)
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -124,6 +124,8 @@ int main(void)
  DEFINE(TZ_MINWEST,		offsetof(struct timezone, tz_minuteswest));
  DEFINE(TZ_DSTTIME,		offsetof(struct timezone, tz_dsttime));
  BLANK();
+  DEFINE(CPU_BOOT_STACK,	offsetof(struct secondary_data, stack));
+  BLANK();
 #ifdef CONFIG_KVM_ARM_HOST
  DEFINE(VCPU_CONTEXT,		offsetof(struct kvm_vcpu, arch.ctxt));
  DEFINE(CPU_GP_REGS,		offsetof(struct kvm_cpu_context, gp_regs));
--- a/arch/arm64/kernel/cpu-reset.S
+++ b/arch/arm64/kernel/cpu-reset.S
@@ -0,0 +1,54 @@
+/*
+ * CPU reset routines
+ *
+ * Copyright (C) 2001 Deep Blue Solutions Ltd.
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2015 Huawei Futurewei Technologies.
+ *
+ * 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.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/sysreg.h>
+#include <asm/virt.h>
+
+.text
+.pushsection    .idmap.text, "ax"
+
+/*
+ * __cpu_soft_restart(el2_switch, entry, arg0, arg1, arg2) - Helper for
+ * cpu_soft_restart.
+ *
+ * @el2_switch: Flag to indicate a swich to EL2 is needed.
+ * @entry: Location to jump to for soft reset.
+ * arg0: First argument passed to @entry.
+ * arg1: Second argument passed to @entry.
+ * arg2: Third argument passed to @entry.
+ *
+ * Put the CPU into the same state as it would be if it had been reset, and
+ * branch to what would be the reset vector. It must be executed with the
+ * flat identity mapping.
+ */
+ENTRY(__cpu_soft_restart)
+	/* Clear sctlr_el1 flags. */
+	mrs	x12, sctlr_el1
+	ldr	x13, =SCTLR_ELx_FLAGS
+	bic	x12, x12, x13
+	msr	sctlr_el1, x12
+	isb
+
+	cbz	x0, 1f				// el2_switch?
+	mov	x0, #HVC_SOFT_RESTART
+	hvc	#0				// no return
+
+1:	mov	x18, x1				// entry
+	mov	x0, x2				// arg0
+	mov	x1, x3				// arg1
+	mov	x2, x4				// arg2
+	br	x18
+ENDPROC(__cpu_soft_restart)
+
+.popsection
--- a/arch/arm64/kernel/cpu-reset.h
+++ b/arch/arm64/kernel/cpu-reset.h
@@ -0,0 +1,34 @@
+/*
+ * CPU reset routines
+ *
+ * Copyright (C) 2015 Huawei Futurewei Technologies.
+ *
+ * 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.
+ */
+
+#ifndef _ARM64_CPU_RESET_H
+#define _ARM64_CPU_RESET_H
+
+#include <asm/virt.h>
+
+void __cpu_soft_restart(unsigned long el2_switch, unsigned long entry,
+	unsigned long arg0, unsigned long arg1, unsigned long arg2);
+
+static inline void __noreturn cpu_soft_restart(unsigned long el2_switch,
+	unsigned long entry, unsigned long arg0, unsigned long arg1,
+	unsigned long arg2)
+{
+	typeof(__cpu_soft_restart) *restart;
+
+	el2_switch = el2_switch && !is_kernel_in_hyp_mode() &&
+		is_hyp_mode_available();
+	restart = (void *)virt_to_phys(__cpu_soft_restart);
+
+	cpu_install_idmap();
+	restart(el2_switch, entry, arg0, arg1, arg2);
+	unreachable();
+}
+
+#endif
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -894,28 +894,6 @@ static u64 __raw_read_system_reg(u32 sys_id)
 	}
 }

-/*
- * Park the CPU which doesn't have the capability as advertised
- * by the system.
- */
-static void fail_incapable_cpu(char *cap_type,
-				 const struct arm64_cpu_capabilities *cap)
-{
-	int cpu = smp_processor_id();
-
-	pr_crit("CPU%d: missing %s : %s\n", cpu, cap_type, cap->desc);
-	/* Mark this CPU absent */
-	set_cpu_present(cpu, 0);
-
-	/* Check if we can park ourselves */
-	if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_die)
-		cpu_ops[cpu]->cpu_die(cpu);
-	asm(
-	"1:	wfe\n"
-	"	wfi\n"
-	"	b	1b");
-}
-
 /*
 * Run through the enabled system capabilities and enable() it on this CPU.
 * The capabilities were decided based on the available CPUs at the boot time.
@@ -944,8 +922,11 @@ void verify_local_cpu_capabilities(void)
 		 * If the new CPU misses an advertised feature, we cannot proceed
 		 * further, park the cpu.
 		 */
-		if (!feature_matches(__raw_read_system_reg(caps[i].sys_reg), &caps[i]))
-			fail_incapable_cpu("arm64_features", &caps[i]);
+		if (!feature_matches(__raw_read_system_reg(caps[i].sys_reg), &caps[i])) {
+			pr_crit("CPU%d: missing feature: %s\n",
+					smp_processor_id(), caps[i].desc);
+			cpu_die_early();
+		}
 		if (caps[i].enable)
 			caps[i].enable(NULL);
 	}
@@ -953,8 +934,11 @@ void verify_local_cpu_capabilities(void)
 	for (i = 0, caps = arm64_hwcaps; caps[i].matches; i++) {
 		if (!cpus_have_hwcap(&caps[i]))
 			continue;
-		if (!feature_matches(__raw_read_system_reg(caps[i].sys_reg), &caps[i]))
-			fail_incapable_cpu("arm64_hwcaps", &caps[i]);
+		if (!feature_matches(__raw_read_system_reg(caps[i].sys_reg), &caps[i])) {
+			pr_crit("CPU%d: missing HWCAP: %s\n",
+					smp_processor_id(), caps[i].desc);
+			cpu_die_early();
+		}
 	}
 }

--- a/arch/arm64/kernel/crash_dump.c
+++ b/arch/arm64/kernel/crash_dump.c
@@ -0,0 +1,71 @@
+/*
+ * Routines for doing kexec-based kdump
+ *
+ * Copyright (C) 2017 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
+ *
+ * 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.
+ */
+
+#include <linux/crash_dump.h>
+#include <linux/errno.h>
+#include <linux/io.h>
+#include <linux/memblock.h>
+#include <linux/uaccess.h>
+#include <asm/memory.h>
+
+/**
+ * copy_oldmem_page() - copy one page from old kernel memory
+ * @pfn: page frame number to be copied
+ * @buf: buffer where the copied page is placed
+ * @csize: number of bytes to copy
+ * @offset: offset in bytes into the page
+ * @userbuf: if set, @buf is in a user address space
+ *
+ * This function copies one page from old kernel memory into buffer pointed by
+ * @buf. If @buf is in userspace, set @userbuf to %1. Returns number of bytes
+ * copied or negative error in case of failure.
+ */
+ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
+			 size_t csize, unsigned long offset,
+			 int userbuf)
+{
+	void *vaddr;
+
+	if (!csize)
+		return 0;
+
+	vaddr = memremap(__pfn_to_phys(pfn), PAGE_SIZE, MEMREMAP_WB);
+	if (!vaddr)
+		return -ENOMEM;
+
+	if (userbuf) {
+		if (copy_to_user((char __user *)buf, vaddr + offset, csize)) {
+			memunmap(vaddr);
+			return -EFAULT;
+		}
+	} else {
+		memcpy(buf, vaddr + offset, csize);
+	}
+
+	memunmap(vaddr);
+
+	return csize;
+}
+
+/**
+ * elfcorehdr_read - read from ELF core header
+ * @buf: buffer where the data is placed
+ * @csize: number of bytes to read
+ * @ppos: address in the memory
+ *
+ * This function reads @count bytes from elf core header which exists
+ * on crash dump kernel's memory.
+ */
+ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos)
+{
+	memcpy(buf, phys_to_virt((phys_addr_t)*ppos), count);
+	return count;
+}
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -36,7 +36,7 @@ int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md)

 	create_pgd_mapping(mm, md->phys_addr, md->virt_addr,
 			   md->num_pages << EFI_PAGE_SHIFT,
-			   __pgprot(prot_val | PTE_NG));
+			   __pgprot(prot_val | PTE_NG), true);
 	return 0;
 }

--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -32,6 +32,7 @@
 #include <asm/ptrace.h>
 #include <asm/thread_info.h>
 #include <asm/uaccess.h>
+#include <asm/asm-uaccess.h>
 #include <asm/unistd.h>

 /*
@@ -431,12 +432,13 @@ el1_da:
 	/*
 	 * Data abort handling
 	 */
-	mrs	x0, far_el1
+	mrs	x3, far_el1
 	enable_dbg
 	// re-enable interrupts if they were enabled in the aborted context
 	tbnz	x23, #7, 1f			// PSR_I_BIT
 	enable_irq
 1:
+	clear_address_tag x0, x3
 	mov	x2, sp				// struct pt_regs
 	bl	do_mem_abort

@@ -598,7 +600,7 @@ el0_da:
 	// enable interrupts before calling the main handler
 	enable_dbg_and_irq
 	ct_user_exit
-	bic	x0, x26, #(0xff << 56)
+	clear_address_tag x0, x26
 	mov	x1, x25
 	mov	x2, sp
 	bl	do_mem_abort
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -36,6 +36,7 @@
 #include <asm/pgtable-hwdef.h>
 #include <asm/pgtable.h>
 #include <asm/page.h>
+#include <asm/smp.h>
 #include <asm/sysreg.h>
 #include <asm/thread_info.h>
 #include <asm/virt.h>
@@ -601,12 +602,6 @@ ENDPROC(set_cpu_boot_mode_flag)
 ENTRY(__boot_cpu_mode)
 	.long	BOOT_CPU_MODE_EL2
 	.long	BOOT_CPU_MODE_EL1
-/*
- * The booting CPU updates the failed status @__early_cpu_boot_status,
- * with MMU turned off.
- */
-ENTRY(__early_cpu_boot_status)
-	.long 	0

 	.popsection

@@ -655,7 +650,8 @@ __secondary_switched:
 	msr	vbar_el1, x5
 	isb

-	ldr_l	x0, secondary_data		// get secondary_data.stack
+	adr_l	x0, secondary_data
+	ldr	x0, [x0, #CPU_BOOT_STACK]	// get secondary_data.stack
 	mov	sp, x0
 	and	x0, x0, #~(THREAD_SIZE - 1)
 	msr	sp_el0, x0			// save thread_info
@@ -663,6 +659,29 @@ __secondary_switched:
 	b	secondary_start_kernel
 ENDPROC(__secondary_switched)

+/*
+ * The booting CPU updates the failed status @__early_cpu_boot_status,
+ * with MMU turned off.
+ *
+ * update_early_cpu_boot_status tmp, status
+ *  - Corrupts tmp1, tmp2
+ *  - Writes 'status' to __early_cpu_boot_status and makes sure
+ *    it is committed to memory.
+ */
+
+	.macro	update_early_cpu_boot_status status, tmp1, tmp2
+	mov	\tmp2, #\status
+	str_l	\tmp2, __early_cpu_boot_status, \tmp1
+	dmb	sy
+	dc	ivac, \tmp1			// Invalidate potentially stale cache line
+	.endm
+
+	.pushsection	.data..cacheline_aligned
+	.align	L1_CACHE_SHIFT
+ENTRY(__early_cpu_boot_status)
+	.long 	0
+	.popsection
+
 /*
 * Enable the MMU.
 *
@@ -680,6 +699,7 @@ ENTRY(__enable_mmu)
 	ubfx	x2, x1, #ID_AA64MMFR0_TGRAN_SHIFT, 4
 	cmp	x2, #ID_AA64MMFR0_TGRAN_SUPPORTED
 	b.ne	__no_granule_support
+	update_early_cpu_boot_status 0, x1, x2
 	msr	ttbr0_el1, x25			// load TTBR0
 	msr	ttbr1_el1, x26			// load TTBR1
 	isb
@@ -719,8 +739,12 @@ ENTRY(__enable_mmu)
 ENDPROC(__enable_mmu)

 __no_granule_support:
+	/* Indicate that this CPU can't boot and is stuck in the kernel */
+	update_early_cpu_boot_status CPU_STUCK_IN_KERNEL, x1, x2
+1:
 	wfe
-	b __no_granule_support
+	wfi
+	b 1b
 ENDPROC(__no_granule_support)

 __primary_switch:
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -27,6 +27,7 @@
 #include <asm/barrier.h>
 #include <asm/cacheflush.h>
 #include <asm/irqflags.h>
+#include <asm/kexec.h>
 #include <asm/memory.h>
 #include <asm/mmu_context.h>
 #include <asm/pgalloc.h>
@@ -94,7 +95,8 @@ int pfn_is_nosave(unsigned long pfn)
 	unsigned long nosave_begin_pfn = virt_to_pfn(&__nosave_begin);
 	unsigned long nosave_end_pfn = virt_to_pfn(&__nosave_end - 1);

-	return (pfn >= nosave_begin_pfn) && (pfn <= nosave_end_pfn);
+	return ((pfn >= nosave_begin_pfn) && (pfn <= nosave_end_pfn)) ||
+		crash_is_nosave(pfn);
 }

 void notrace save_processor_state(void)
@@ -245,6 +247,9 @@ int swsusp_arch_suspend(void)
 	local_dbg_save(flags);

 	if (__cpu_suspend_enter(&state)) {
+		/* make the crash dump kernel image visible/saveable */
+		crash_prepare_suspend();
+
 		ret = swsusp_save();
 	} else {
 		/* Clean kernel core startup/idle code to PoC*/
@@ -255,6 +260,9 @@ int swsusp_arch_suspend(void)
 		if (el2_reset_needed())
 			dcache_clean_range(__hyp_idmap_text_start, __hyp_idmap_text_end);

+		/* make the crash dump kernel image protected again */
+		crash_post_resume();
+
 		/*
 		 * Tell the hibernation core that we've just restored
 		 * the memory
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -36,6 +36,7 @@
 #include <asm/traps.h>
 #include <asm/cputype.h>
 #include <asm/system_misc.h>
+#include <asm/uaccess.h>

 /* Breakpoint currently in use for each BRP. */
 static DEFINE_PER_CPU(struct perf_event *, bp_on_reg[ARM_MAX_BRP]);
--- a/arch/arm64/kernel/hyp-stub.S
+++ b/arch/arm64/kernel/hyp-stub.S
@@ -71,8 +71,16 @@ el1_sync:
 	msr	vbar_el2, x1
 	b	9f

+2:	cmp	x0, #HVC_SOFT_RESTART
+	b.ne	3f
+	mov	x0, x2
+	mov	x2, x4
+	mov	x4, x1
+	mov	x1, x3
+	br	x4				// no return
+
 	/* Someone called kvm_call_hyp() against the hyp-stub... */
-2:	mov     x0, #ARM_EXCEPTION_HYP_GONE
+3:	mov	x0, #ARM_EXCEPTION_HYP_GONE

 9:	eret
 ENDPROC(el1_sync)
--- a/arch/arm64/kernel/machine_kexec.c
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -0,0 +1,364 @@
+/*
+ * kexec for arm64
+ *
+ * Copyright (C) Linaro.
+ * Copyright (C) Huawei Futurewei Technologies.
+ *
+ * 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.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/kexec.h>
+#include <linux/page-flags.h>
+#include <linux/smp.h>
+
+#include <asm/cacheflush.h>
+#include <asm/cpu_ops.h>
+#include <asm/memory.h>
+#include <asm/mmu.h>
+#include <asm/mmu_context.h>
+#include <asm/page.h>
+
+#include "cpu-reset.h"
+
+/* Global variables for the arm64_relocate_new_kernel routine. */
+extern const unsigned char arm64_relocate_new_kernel[];
+extern const unsigned long arm64_relocate_new_kernel_size;
+
+/**
+ * kexec_image_info - For debugging output.
+ */
+#define kexec_image_info(_i) _kexec_image_info(__func__, __LINE__, _i)
+static void _kexec_image_info(const char *func, int line,
+	const struct kimage *kimage)
+{
+	unsigned long i;
+
+	pr_debug("%s:%d:\n", func, line);
+	pr_debug("  kexec kimage info:\n");
+	pr_debug("    type:        %d\n", kimage->type);
+	pr_debug("    start:       %lx\n", kimage->start);
+	pr_debug("    head:        %lx\n", kimage->head);
+	pr_debug("    nr_segments: %lu\n", kimage->nr_segments);
+
+	for (i = 0; i < kimage->nr_segments; i++) {
+		pr_debug("      segment[%lu]: %016lx - %016lx, 0x%lx bytes, %lu pages\n",
+			i,
+			kimage->segment[i].mem,
+			kimage->segment[i].mem + kimage->segment[i].memsz,
+			kimage->segment[i].memsz,
+			kimage->segment[i].memsz /  PAGE_SIZE);
+	}
+}
+
+void machine_kexec_cleanup(struct kimage *kimage)
+{
+	/* Empty routine needed to avoid build errors. */
+}
+
+/**
+ * machine_kexec_prepare - Prepare for a kexec reboot.
+ *
+ * Called from the core kexec code when a kernel image is loaded.
+ * Forbid loading a kexec kernel if we have no way of hotplugging cpus or cpus
+ * are stuck in the kernel. This avoids a panic once we hit machine_kexec().
+ */
+int machine_kexec_prepare(struct kimage *kimage)
+{
+	kexec_image_info(kimage);
+
+	if (kimage->type != KEXEC_TYPE_CRASH && cpus_are_stuck_in_kernel()) {
+		pr_err("Can't kexec: CPUs are stuck in the kernel.\n");
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
+/**
+ * kexec_list_flush - Helper to flush the kimage list and source pages to PoC.
+ */
+static void kexec_list_flush(struct kimage *kimage)
+{
+	kimage_entry_t *entry;
+
+	for (entry = &kimage->head; ; entry++) {
+		unsigned int flag;
+		void *addr;
+
+		/* flush the list entries. */
+		__flush_dcache_area(entry, sizeof(kimage_entry_t));
+
+		flag = *entry & IND_FLAGS;
+		if (flag == IND_DONE)
+			break;
+
+		addr = phys_to_virt(*entry & PAGE_MASK);
+
+		switch (flag) {
+		case IND_INDIRECTION:
+			/* Set entry point just before the new list page. */
+			entry = (kimage_entry_t *)addr - 1;
+			break;
+		case IND_SOURCE:
+			/* flush the source pages. */
+			__flush_dcache_area(addr, PAGE_SIZE);
+			break;
+		case IND_DESTINATION:
+			break;
+		default:
+			BUG();
+		}
+	}
+}
+
+/**
+ * kexec_segment_flush - Helper to flush the kimage segments to PoC.
+ */
+static void kexec_segment_flush(const struct kimage *kimage)
+{
+	unsigned long i;
+
+	pr_debug("%s:\n", __func__);
+
+	for (i = 0; i < kimage->nr_segments; i++) {
+		pr_debug("  segment[%lu]: %016lx - %016lx, 0x%lx bytes, %lu pages\n",
+			i,
+			kimage->segment[i].mem,
+			kimage->segment[i].mem + kimage->segment[i].memsz,
+			kimage->segment[i].memsz,
+			kimage->segment[i].memsz /  PAGE_SIZE);
+
+		__flush_dcache_area(phys_to_virt(kimage->segment[i].mem),
+			kimage->segment[i].memsz);
+	}
+}
+
+/**
+ * machine_kexec - Do the kexec reboot.
+ *
+ * Called from the core kexec code for a sys_reboot with LINUX_REBOOT_CMD_KEXEC.
+ */
+void machine_kexec(struct kimage *kimage)
+{
+	phys_addr_t reboot_code_buffer_phys;
+	void *reboot_code_buffer;
+	bool in_kexec_crash = (kimage == kexec_crash_image);
+	bool stuck_cpus = cpus_are_stuck_in_kernel();
+
+	/*
+	 * New cpus may have become stuck_in_kernel after we loaded the image.
+	 */
+	BUG_ON(!in_kexec_crash && (stuck_cpus || (num_online_cpus() > 1)));
+	WARN(in_kexec_crash && (stuck_cpus || smp_crash_stop_failed()),
+		"Some CPUs may be stale, kdump will be unreliable.\n");
+
+	reboot_code_buffer_phys = page_to_phys(kimage->control_code_page);
+	reboot_code_buffer = phys_to_virt(reboot_code_buffer_phys);
+
+	kexec_image_info(kimage);
+
+	pr_debug("%s:%d: control_code_page:        %p\n", __func__, __LINE__,
+		kimage->control_code_page);
+	pr_debug("%s:%d: reboot_code_buffer_phys:  %pa\n", __func__, __LINE__,
+		&reboot_code_buffer_phys);
+	pr_debug("%s:%d: reboot_code_buffer:       %p\n", __func__, __LINE__,
+		reboot_code_buffer);
+	pr_debug("%s:%d: relocate_new_kernel:      %p\n", __func__, __LINE__,
+		arm64_relocate_new_kernel);
+	pr_debug("%s:%d: relocate_new_kernel_size: 0x%lx(%lu) bytes\n",
+		__func__, __LINE__, arm64_relocate_new_kernel_size,
+		arm64_relocate_new_kernel_size);
+
+	/*
+	 * Copy arm64_relocate_new_kernel to the reboot_code_buffer for use
+	 * after the kernel is shut down.
+	 */
+	memcpy(reboot_code_buffer, arm64_relocate_new_kernel,
+		arm64_relocate_new_kernel_size);
+
+	/* Flush the reboot_code_buffer in preparation for its execution. */
+	__flush_dcache_area(reboot_code_buffer, arm64_relocate_new_kernel_size);
+	flush_icache_range((uintptr_t)reboot_code_buffer,
+		arm64_relocate_new_kernel_size);
+
+	/* Flush the kimage list and its buffers. */
+	kexec_list_flush(kimage);
+
+	/* Flush the new image if already in place. */
+	if ((kimage != kexec_crash_image) && (kimage->head & IND_DONE))
+		kexec_segment_flush(kimage);
+
+	pr_info("Bye!\n");
+
+	/* Disable all DAIF exceptions. */
+	asm volatile ("msr daifset, #0xf" : : : "memory");
+
+	/*
+	 * cpu_soft_restart will shutdown the MMU, disable data caches, then
+	 * transfer control to the reboot_code_buffer which contains a copy of
+	 * the arm64_relocate_new_kernel routine.  arm64_relocate_new_kernel
+	 * uses physical addressing to relocate the new image to its final
+	 * position and transfers control to the image entry point when the
+	 * relocation is complete.
+	 */
+
+	cpu_soft_restart(kimage != kexec_crash_image,
+		reboot_code_buffer_phys, kimage->head, kimage->start, 0);
+
+	BUG(); /* Should never get here. */
+}
+
+static void machine_kexec_mask_interrupts(void)
+{
+	unsigned int i;
+	struct irq_desc *desc;
+
+	for_each_irq_desc(i, desc) {
+		struct irq_chip *chip;
+		int ret;
+
+		chip = irq_desc_get_chip(desc);
+		if (!chip)
+			continue;
+
+		/*
+		 * First try to remove the active state. If this
+		 * fails, try to EOI the interrupt.
+		 */
+		ret = irq_set_irqchip_state(i, IRQCHIP_STATE_ACTIVE, false);
+
+		if (ret && irqd_irq_inprogress(&desc->irq_data) &&
+		    chip->irq_eoi)
+			chip->irq_eoi(&desc->irq_data);
+
+		if (chip->irq_mask)
+			chip->irq_mask(&desc->irq_data);
+
+		if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data))
+			chip->irq_disable(&desc->irq_data);
+	}
+}
+
+/**
+ * machine_crash_shutdown - shutdown non-crashing cpus and save registers
+ */
+void machine_crash_shutdown(struct pt_regs *regs)
+{
+	local_irq_disable();
+
+	/* shutdown non-crashing cpus */
+	smp_send_crash_stop();
+
+	/* for crashing cpu */
+	crash_save_cpu(regs, smp_processor_id());
+	machine_kexec_mask_interrupts();
+
+	pr_info("Starting crashdump kernel...\n");
+}
+
+void arch_kexec_protect_crashkres(void)
+{
+	int i;
+
+	kexec_segment_flush(kexec_crash_image);
+
+	for (i = 0; i < kexec_crash_image->nr_segments; i++)
+		set_memory_valid(
+			__phys_to_virt(kexec_crash_image->segment[i].mem),
+			kexec_crash_image->segment[i].memsz >> PAGE_SHIFT, 0);
+}
+
+void arch_kexec_unprotect_crashkres(void)
+{
+	int i;
+
+	for (i = 0; i < kexec_crash_image->nr_segments; i++)
+		set_memory_valid(
+			__phys_to_virt(kexec_crash_image->segment[i].mem),
+			kexec_crash_image->segment[i].memsz >> PAGE_SHIFT, 1);
+}
+
+#ifdef CONFIG_HIBERNATION
+/*
+ * To preserve the crash dump kernel image, the relevant memory segments
+ * should be mapped again around the hibernation.
+ */
+void crash_prepare_suspend(void)
+{
+	if (kexec_crash_image)
+		arch_kexec_unprotect_crashkres();
+}
+
+void crash_post_resume(void)
+{
+	if (kexec_crash_image)
+		arch_kexec_protect_crashkres();
+}
+
+/*
+ * crash_is_nosave
+ *
+ * Return true only if a page is part of reserved memory for crash dump kernel,
+ * but does not hold any data of loaded kernel image.
+ *
+ * Note that all the pages in crash dump kernel memory have been initially
+ * marked as Reserved in kexec_reserve_crashkres_pages().
+ *
+ * In hibernation, the pages which are Reserved and yet "nosave" are excluded
+ * from the hibernation iamge. crash_is_nosave() does thich check for crash
+ * dump kernel and will reduce the total size of hibernation image.
+ */
+
+bool crash_is_nosave(unsigned long pfn)
+{
+	int i;
+	phys_addr_t addr;
+
+	if (!crashk_res.end)
+		return false;
+
+	/* in reserved memory? */
+	addr = __pfn_to_phys(pfn);
+	if ((addr < crashk_res.start) || (crashk_res.end < addr))
+		return false;
+
+	if (!kexec_crash_image)
+		return true;
+
+	/* not part of loaded kernel image? */
+	for (i = 0; i < kexec_crash_image->nr_segments; i++)
+		if (addr >= kexec_crash_image->segment[i].mem &&
+				addr < (kexec_crash_image->segment[i].mem +
+					kexec_crash_image->segment[i].memsz))
+			return false;
+
+	return true;
+}
+
+void crash_free_reserved_phys_range(unsigned long begin, unsigned long end)
+{
+	unsigned long addr;
+	struct page *page;
+
+	for (addr = begin; addr < end; addr += PAGE_SIZE) {
+		page = phys_to_page(addr);
+		ClearPageReserved(page);
+		free_reserved_page(page);
+	}
+}
+#endif /* CONFIG_HIBERNATION */
+
+void arch_crash_save_vmcoreinfo(void)
+{
+	VMCOREINFO_NUMBER(VA_BITS);
+	/* Please note VMCOREINFO_NUMBER() uses "%d", not "%x" */
+	vmcoreinfo_append_str("NUMBER(kimage_voffset)=0x%llx\n",
+						kimage_voffset);
+	vmcoreinfo_append_str("NUMBER(PHYS_OFFSET)=0x%llx\n",
+						PHYS_OFFSET);
+}
--- a/arch/arm64/kernel/relocate_kernel.S
+++ b/arch/arm64/kernel/relocate_kernel.S
@@ -0,0 +1,130 @@
+/*
+ * kexec for arm64
+ *
+ * Copyright (C) Linaro.
+ * Copyright (C) Huawei Futurewei Technologies.
+ *
+ * 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.
+ */
+
+#include <linux/kexec.h>
+#include <linux/linkage.h>
+
+#include <asm/assembler.h>
+#include <asm/kexec.h>
+#include <asm/page.h>
+#include <asm/sysreg.h>
+
+/*
+ * arm64_relocate_new_kernel - Put a 2nd stage image in place and boot it.
+ *
+ * The memory that the old kernel occupies may be overwritten when coping the
+ * new image to its final location.  To assure that the
+ * arm64_relocate_new_kernel routine which does that copy is not overwritten,
+ * all code and data needed by arm64_relocate_new_kernel must be between the
+ * symbols arm64_relocate_new_kernel and arm64_relocate_new_kernel_end.  The
+ * machine_kexec() routine will copy arm64_relocate_new_kernel to the kexec
+ * control_code_page, a special page which has been set up to be preserved
+ * during the copy operation.
+ */
+ENTRY(arm64_relocate_new_kernel)
+
+	/* Setup the list loop variables. */
+	mov	x17, x1				/* x17 = kimage_start */
+	mov	x16, x0				/* x16 = kimage_head */
+	dcache_line_size x15, x0		/* x15 = dcache line size */
+	mov	x14, xzr			/* x14 = entry ptr */
+	mov	x13, xzr			/* x13 = copy dest */
+
+	/* Clear the sctlr_el2 flags. */
+	mrs	x0, CurrentEL
+	cmp	x0, #CurrentEL_EL2
+	b.ne	1f
+	mrs	x0, sctlr_el2
+	ldr	x1, =SCTLR_ELx_FLAGS
+	bic	x0, x0, x1
+	msr	sctlr_el2, x0
+	isb
+1:
+
+	/* Check if the new image needs relocation. */
+	tbnz	x16, IND_DONE_BIT, .Ldone
+
+.Lloop:
+	and	x12, x16, PAGE_MASK		/* x12 = addr */
+
+	/* Test the entry flags. */
+.Ltest_source:
+	tbz	x16, IND_SOURCE_BIT, .Ltest_indirection
+
+	/* Invalidate dest page to PoC. */
+	mov     x0, x13
+	add     x20, x0, #PAGE_SIZE
+	sub     x1, x15, #1
+	bic     x0, x0, x1
+2:	dc      ivac, x0
+	add     x0, x0, x15
+	cmp     x0, x20
+	b.lo    2b
+	dsb     sy
+
+	mov x20, x13
+	mov x21, x12
+	copy_page x20, x21, x0, x1, x2, x3, x4, x5, x6, x7
+
+	/* dest += PAGE_SIZE */
+	add	x13, x13, PAGE_SIZE
+	b	.Lnext
+
+.Ltest_indirection:
+	tbz	x16, IND_INDIRECTION_BIT, .Ltest_destination
+
+	/* ptr = addr */
+	mov	x14, x12
+	b	.Lnext
+
+.Ltest_destination:
+	tbz	x16, IND_DESTINATION_BIT, .Lnext
+
+	/* dest = addr */
+	mov	x13, x12
+
+.Lnext:
+	/* entry = *ptr++ */
+	ldr	x16, [x14], #8
+
+	/* while (!(entry & DONE)) */
+	tbz	x16, IND_DONE_BIT, .Lloop
+
+.Ldone:
+	/* wait for writes from copy_page to finish */
+	dsb	nsh
+	ic	iallu
+	dsb	nsh
+	isb
+
+	/* Start new image. */
+	mov	x0, xzr
+	mov	x1, xzr
+	mov	x2, xzr
+	mov	x3, xzr
+	br	x17
+
+ENDPROC(arm64_relocate_new_kernel)
+
+.ltorg
+
+.align 3	/* To keep the 64-bit values below naturally aligned. */
+
+.Lcopy_end:
+.org	KEXEC_CONTROL_PAGE_SIZE
+
+/*
+ * arm64_relocate_new_kernel_size - Number of bytes to copy to the
+ * control_code_page.
+ */
+.globl arm64_relocate_new_kernel_size
+arm64_relocate_new_kernel_size:
+	.quad	.Lcopy_end - arm64_relocate_new_kernel
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -31,7 +31,6 @@
 #include <linux/screen_info.h>
 #include <linux/init.h>
 #include <linux/kexec.h>
-#include <linux/crash_dump.h>
 #include <linux/root_dev.h>
 #include <linux/cpu.h>
 #include <linux/interrupt.h>
@@ -220,6 +219,12 @@ static void __init request_standard_resources(void)
 		if (kernel_data.start >= res->start &&
 		    kernel_data.end <= res->end)
 			request_resource(res, &kernel_data);
+#ifdef CONFIG_KEXEC_CORE
+		/* Userspace will find "Crash kernel" region in /proc/iomem. */
+		if (crashk_res.end && crashk_res.start >= res->start &&
+		    crashk_res.end <= res->end)
+			request_resource(res, &crashk_res);
+#endif
 	}
 }

--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -37,6 +37,7 @@
 #include <linux/completion.h>
 #include <linux/of.h>
 #include <linux/irq_work.h>
+#include <linux/kexec.h>

 #include <asm/alternative.h>
 #include <asm/atomic.h>
@@ -63,16 +64,29 @@
 * where to place its SVC stack
 */
 struct secondary_data secondary_data;
+/* Number of CPUs which aren't online, but looping in kernel text. */
+int cpus_stuck_in_kernel;

 enum ipi_msg_type {
 	IPI_RESCHEDULE,
 	IPI_CALL_FUNC,
 	IPI_CPU_STOP,
+	IPI_CPU_CRASH_STOP,
 	IPI_TIMER,
 	IPI_IRQ_WORK,
 	IPI_WAKEUP
 };

+#ifdef CONFIG_HOTPLUG_CPU
+static int op_cpu_kill(unsigned int cpu);
+#else
+static inline int op_cpu_kill(unsigned int cpu)
+{
+	return -ENOSYS;
+}
+#endif
+
+
 /*
 * Boot a secondary CPU, and assign it the specified idle task.
 * This also gives us the initial stack to use for this CPU.
@@ -90,12 +104,14 @@ static DECLARE_COMPLETION(cpu_running);
 int __cpu_up(unsigned int cpu, struct task_struct *idle)
 {
 	int ret;
+	long status;

 	/*
 	 * We need to tell the secondary core where to find its stack and the
 	 * page tables.
 	 */
 	secondary_data.stack = task_stack_page(idle) + THREAD_START_SP;
+	update_cpu_boot_status(CPU_MMU_OFF);
 	__flush_dcache_area(&secondary_data, sizeof(secondary_data));

 	/*
@@ -119,6 +135,32 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 	}

 	secondary_data.stack = NULL;
+	status = READ_ONCE(secondary_data.status);
+	if (ret && status) {
+
+		if (status == CPU_MMU_OFF)
+			status = READ_ONCE(__early_cpu_boot_status);
+
+		switch (status) {
+		default:
+			pr_err("CPU%u: failed in unknown state : 0x%lx\n",
+					cpu, status);
+			break;
+		case CPU_KILL_ME:
+			if (!op_cpu_kill(cpu)) {
+				pr_crit("CPU%u: died during early boot\n", cpu);
+				break;
+			}
+			/* Fall through */
+			pr_crit("CPU%u: may not have shut down cleanly\n", cpu);
+		case CPU_STUCK_IN_KERNEL:
+			pr_crit("CPU%u: is stuck in kernel\n", cpu);
+			cpus_stuck_in_kernel++;
+			break;
+		case CPU_PANIC_KERNEL:
+			panic("CPU%u detected unsupported configuration\n", cpu);
+		}
+	}

 	return ret;
 }
@@ -184,6 +226,9 @@ asmlinkage void secondary_start_kernel(void)
 	 */
 	pr_info("CPU%u: Booted secondary processor [%08x]\n",
 					 cpu, read_cpuid_id());
+	update_cpu_boot_status(CPU_BOOT_SUCCESS);
+	/* Make sure the status update is visible before we complete */
+	smp_wmb();
 	set_cpu_online(cpu, true);
 	complete(&cpu_running);

@@ -311,6 +356,30 @@ void cpu_die(void)
 }
 #endif

+/*
+ * Kill the calling secondary CPU, early in bringup before it is turned
+ * online.
+ */
+void cpu_die_early(void)
+{
+	int cpu = smp_processor_id();
+
+	pr_crit("CPU%d: will not boot\n", cpu);
+
+	/* Mark this CPU absent */
+	set_cpu_present(cpu, 0);
+
+#ifdef CONFIG_HOTPLUG_CPU
+	update_cpu_boot_status(CPU_KILL_ME);
+	/* Check if we can park ourselves */
+	if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_die)
+		cpu_ops[cpu]->cpu_die(cpu);
+#endif
+	update_cpu_boot_status(CPU_STUCK_IN_KERNEL);
+
+	cpu_park_loop();
+}
+
 static void __init hyp_mode_check(void)
 {
 	if (is_hyp_mode_available())
@@ -634,6 +703,7 @@ static const char *ipi_types[NR_IPI] __tracepoint_string = {
 	S(IPI_RESCHEDULE, "Rescheduling interrupts"),
 	S(IPI_CALL_FUNC, "Function call interrupts"),
 	S(IPI_CPU_STOP, "CPU stop interrupts"),
+	S(IPI_CPU_CRASH_STOP, "CPU stop (for crash dump) interrupts"),
 	S(IPI_TIMER, "Timer broadcast interrupts"),
 	S(IPI_IRQ_WORK, "IRQ work interrupts"),
 	S(IPI_WAKEUP, "CPU wake-up interrupts"),
@@ -718,6 +788,29 @@ static void ipi_cpu_stop(unsigned int cpu)
 		cpu_relax();
 }

+#ifdef CONFIG_KEXEC_CORE
+static atomic_t waiting_for_crash_ipi = ATOMIC_INIT(0);
+#endif
+
+static void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs)
+{
+#ifdef CONFIG_KEXEC_CORE
+	crash_save_cpu(regs, cpu);
+
+	atomic_dec(&waiting_for_crash_ipi);
+
+	local_irq_disable();
+
+#ifdef CONFIG_HOTPLUG_CPU
+	if (cpu_ops[cpu]->cpu_die)
+		cpu_ops[cpu]->cpu_die(cpu);
+#endif
+
+	/* just in case */
+	cpu_park_loop();
+#endif
+}
+
 /*
 * Main handler for inter-processor interrupts
 */
@@ -748,6 +841,15 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 		irq_exit();
 		break;

+	case IPI_CPU_CRASH_STOP:
+		if (IS_ENABLED(CONFIG_KEXEC_CORE)) {
+			irq_enter();
+			ipi_cpu_crash_stop(cpu, regs);
+
+			unreachable();
+		}
+		break;
+
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 	case IPI_TIMER:
 		irq_enter();
@@ -816,6 +918,39 @@ void smp_send_stop(void)
 		pr_warning("SMP: failed to stop secondary CPUs\n");
 }

+#ifdef CONFIG_KEXEC_CORE
+void smp_send_crash_stop(void)
+{
+	cpumask_t mask;
+	unsigned long timeout;
+
+	if (num_online_cpus() == 1)
+		return;
+
+	cpumask_copy(&mask, cpu_online_mask);
+	cpumask_clear_cpu(smp_processor_id(), &mask);
+
+	atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
+
+	pr_crit("SMP: stopping secondary CPUs\n");
+	smp_cross_call(&mask, IPI_CPU_CRASH_STOP);
+
+	/* Wait up to one second for other CPUs to stop */
+	timeout = USEC_PER_SEC;
+	while ((atomic_read(&waiting_for_crash_ipi) > 0) && timeout--)
+		udelay(1);
+
+	if (atomic_read(&waiting_for_crash_ipi) > 0)
+		pr_warning("SMP: failed to stop secondary CPUs %*pbl\n",
+			   cpumask_pr_args(&mask));
+}
+
+bool smp_crash_stop_failed(void)
+{
+	return (atomic_read(&waiting_for_crash_ipi) > 0);
+}
+#endif
+
 /*
 * not supported here
 */
@@ -823,3 +958,21 @@ int setup_profiling_timer(unsigned int multiplier)
 {
 	return -EINVAL;
 }
+
+static bool have_cpu_die(void)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+	int any_cpu = raw_smp_processor_id();
+
+	if (cpu_ops[any_cpu]->cpu_die)
+		return true;
+#endif
+	return false;
+}
+
+bool cpus_are_stuck_in_kernel(void)
+{
+	bool smp_spin_tables = (num_possible_cpus() > 1 && !have_cpu_die());
+
+	return !!cpus_stuck_in_kernel || smp_spin_tables;
+}
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -29,11 +29,14 @@
 #include <linux/gfp.h>
 #include <linux/memblock.h>
 #include <linux/sort.h>
+#include <linux/of.h>
 #include <linux/of_fdt.h>
 #include <linux/dma-mapping.h>
 #include <linux/dma-contiguous.h>
 #include <linux/efi.h>
 #include <linux/swiotlb.h>
+#include <linux/kexec.h>
+#include <linux/crash_dump.h>

 #include <asm/boot.h>
 #include <asm/fixmap.h>
@@ -75,6 +78,142 @@ static int __init early_initrd(char *p)
 early_param("initrd", early_initrd);
 #endif

+#ifdef CONFIG_KEXEC_CORE
+/*
+ * reserve_crashkernel() - reserves memory for crash kernel
+ *
+ * This function reserves memory area given in "crashkernel=" kernel command
+ * line parameter. The memory reserved is used by dump capture kernel when
+ * primary kernel is crashing.
+ */
+static void __init reserve_crashkernel(void)
+{
+	unsigned long long crash_base, crash_size;
+	int ret;
+
+	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
+				&crash_size, &crash_base);
+	/* no crashkernel= or invalid value specified */
+	if (ret || !crash_size)
+		return;
+
+	crash_size = PAGE_ALIGN(crash_size);
+
+	if (crash_base == 0) {
+		/* Current arm64 boot protocol requires 2MB alignment */
+		crash_base = memblock_find_in_range(0, ARCH_LOW_ADDRESS_LIMIT,
+				crash_size, SZ_2M);
+		if (crash_base == 0) {
+			pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
+				crash_size);
+			return;
+		}
+	} else {
+		/* User specifies base address explicitly. */
+		if (!memblock_is_region_memory(crash_base, crash_size)) {
+			pr_warn("cannot reserve crashkernel: region is not memory\n");
+			return;
+		}
+
+		if (memblock_is_region_reserved(crash_base, crash_size)) {
+			pr_warn("cannot reserve crashkernel: region overlaps reserved memory\n");
+			return;
+		}
+
+		if (!IS_ALIGNED(crash_base, SZ_2M)) {
+			pr_warn("cannot reserve crashkernel: base address is not 2MB aligned\n");
+			return;
+		}
+	}
+	memblock_reserve(crash_base, crash_size);
+
+	pr_info("crashkernel reserved: 0x%016llx - 0x%016llx (%lld MB)\n",
+		crash_base, crash_base + crash_size, crash_size >> 20);
+
+	crashk_res.start = crash_base;
+	crashk_res.end = crash_base + crash_size - 1;
+}
+
+static void __init kexec_reserve_crashkres_pages(void)
+{
+#ifdef CONFIG_HIBERNATION
+	phys_addr_t addr;
+	struct page *page;
+
+	if (!crashk_res.end)
+		return;
+
+	/*
+	 * To reduce the size of hibernation image, all the pages are
+	 * marked as Reserved initially.
+	 */
+	for (addr = crashk_res.start; addr < (crashk_res.end + 1);
+			addr += PAGE_SIZE) {
+		page = phys_to_page(addr);
+		SetPageReserved(page);
+	}
+#endif
+}
+#else
+static void __init reserve_crashkernel(void)
+{
+}
+
+static void __init kexec_reserve_crashkres_pages(void)
+{
+}
+#endif /* CONFIG_KEXEC_CORE */
+
+#ifdef CONFIG_CRASH_DUMP
+static int __init early_init_dt_scan_elfcorehdr(unsigned long node,
+		const char *uname, int depth, void *data)
+{
+	const __be32 *reg;
+	int len;
+
+	if (depth != 1 || strcmp(uname, "chosen") != 0)
+		return 0;
+
+	reg = of_get_flat_dt_prop(node, "linux,elfcorehdr", &len);
+	if (!reg || (len < (dt_root_addr_cells + dt_root_size_cells)))
+		return 1;
+
+	elfcorehdr_addr = dt_mem_next_cell(dt_root_addr_cells, &reg);
+	elfcorehdr_size = dt_mem_next_cell(dt_root_size_cells, &reg);
+
+	return 1;
+}
+
+/*
+ * reserve_elfcorehdr() - reserves memory for elf core header
+ *
+ * This function reserves the memory occupied by an elf core header
+ * described in the device tree. This region contains all the
+ * information about primary kernel's core image and is used by a dump
+ * capture kernel to access the system memory on primary kernel.
+ */
+static void __init reserve_elfcorehdr(void)
+{
+	of_scan_flat_dt(early_init_dt_scan_elfcorehdr, NULL);
+
+	if (!elfcorehdr_size)
+		return;
+
+	if (memblock_is_region_reserved(elfcorehdr_addr, elfcorehdr_size)) {
+		pr_warn("elfcorehdr is overlapped\n");
+		return;
+	}
+
+	memblock_reserve(elfcorehdr_addr, elfcorehdr_size);
+
+	pr_info("Reserving %lldKB of memory at 0x%llx for elfcorehdr\n",
+		elfcorehdr_size >> 10, elfcorehdr_addr);
+}
+#else
+static void __init reserve_elfcorehdr(void)
+{
+}
+#endif /* CONFIG_CRASH_DUMP */
 /*
 * Return the maximum physical address for ZONE_DMA (DMA_BIT_MASK(32)). It
 * currently assumes that for memory starting above 4G, 32-bit devices will
@@ -168,10 +307,45 @@ static int __init early_mem(char *p)
 }
 early_param("mem", early_mem);

+static int __init early_init_dt_scan_usablemem(unsigned long node,
+		const char *uname, int depth, void *data)
+{
+	struct memblock_region *usablemem = data;
+	const __be32 *reg;
+	int len;
+
+	if (depth != 1 || strcmp(uname, "chosen") != 0)
+		return 0;
+
+	reg = of_get_flat_dt_prop(node, "linux,usable-memory-range", &len);
+	if (!reg || (len < (dt_root_addr_cells + dt_root_size_cells)))
+		return 1;
+
+	usablemem->base = dt_mem_next_cell(dt_root_addr_cells, &reg);
+	usablemem->size = dt_mem_next_cell(dt_root_size_cells, &reg);
+
+	return 1;
+}
+
+static void __init fdt_enforce_memory_region(void)
+{
+	struct memblock_region reg = {
+		.size = 0,
+	};
+
+	of_scan_flat_dt(early_init_dt_scan_usablemem, &reg);
+
+	if (reg.size)
+		memblock_cap_memory_range(reg.base, reg.size);
+}
+
 void __init arm64_memblock_init(void)
 {
 	const s64 linear_region_size = -(s64)PAGE_OFFSET;

+	/* Handle linux,usable-memory-range property */
+	fdt_enforce_memory_region();
+
 	/*
 	 * Ensure that the linear region takes up exactly half of the kernel
 	 * virtual address space. This way, we can distinguish a linear address
@@ -248,6 +422,11 @@ void __init arm64_memblock_init(void)
 		arm64_dma_phys_limit = max_zone_dma_phys();
 	else
 		arm64_dma_phys_limit = PHYS_MASK + 1;
+
+	reserve_crashkernel();
+
+	reserve_elfcorehdr();
+
 	dma_contiguous_reserve(arm64_dma_phys_limit);

 	memblock_allow_resize();
@@ -361,6 +540,8 @@ void __init mem_init(void)
 	/* this will put all unused low memory onto the freelists */
 	free_all_bootmem();

+	kexec_reserve_crashkres_pages();
+
 	mem_init_print_info(NULL);

 #define MLK(b, t) b, t, ((t) - (b)) >> 10
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -21,6 +21,8 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/init.h>
+#include <linux/ioport.h>
+#include <linux/kexec.h>
 #include <linux/libfdt.h>
 #include <linux/mman.h>
 #include <linux/nodemask.h>
@@ -156,29 +158,10 @@ static void split_pud(pud_t *old_pud, pmd_t *pmd)
 	} while (pmd++, i++, i < PTRS_PER_PMD);
 }

-#ifdef CONFIG_DEBUG_PAGEALLOC
-static bool block_mappings_allowed(phys_addr_t (*pgtable_alloc)(void))
-{
-
-	/*
-	 * If debug_page_alloc is enabled we must map the linear map
-	 * using pages. However, other mappings created by
-	 * create_mapping_noalloc must use sections in some cases. Allow
-	 * sections to be used in those cases, where no pgtable_alloc
-	 * function is provided.
-	 */
-	return !pgtable_alloc || !debug_pagealloc_enabled();
-}
-#else
-static bool block_mappings_allowed(phys_addr_t (*pgtable_alloc)(void))
-{
-	return true;
-}
-#endif
-
 static void alloc_init_pmd(pud_t *pud, unsigned long addr, unsigned long end,
 				  phys_addr_t phys, pgprot_t prot,
-				  phys_addr_t (*pgtable_alloc)(void))
+				  phys_addr_t (*pgtable_alloc)(void),
+				  bool allow_block_mappings)
 {
 	pmd_t *pmd;
 	unsigned long next;
@@ -209,7 +192,7 @@ static void alloc_init_pmd(pud_t *pud, unsigned long addr, unsigned long end,
 		next = pmd_addr_end(addr, end);
 		/* try section mapping first */
 		if (((addr | next | phys) & ~SECTION_MASK) == 0 &&
-		      block_mappings_allowed(pgtable_alloc)) {
+		      (!pgtable_alloc || allow_block_mappings)) {
 			pmd_t old_pmd =*pmd;
 			pmd_set_huge(pmd, phys, prot);
 			/*
@@ -248,7 +231,8 @@ static inline bool use_1G_block(unsigned long addr, unsigned long next,

 static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
 				  phys_addr_t phys, pgprot_t prot,
-				  phys_addr_t (*pgtable_alloc)(void))
+				  phys_addr_t (*pgtable_alloc)(void),
+				  bool allow_block_mappings)
 {
 	pud_t *pud;
 	unsigned long next;
@@ -269,7 +253,7 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
 		 * For 4K granule only, attempt to put down a 1GB block
 		 */
 		if (use_1G_block(addr, next, phys) &&
-		    block_mappings_allowed(pgtable_alloc)) {
+		      (!pgtable_alloc || allow_block_mappings)) {
 			pud_t old_pud = *pud;
 			pud_set_huge(pud, phys, prot);

@@ -290,7 +274,7 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
 			}
 		} else {
 			alloc_init_pmd(pud, addr, next, phys, prot,
-				       pgtable_alloc);
+				       pgtable_alloc, allow_block_mappings);
 		}
 		phys += next - addr;
 	} while (pud++, addr = next, addr != end);
@@ -304,7 +288,8 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
 */
 static void init_pgd(pgd_t *pgd, phys_addr_t phys, unsigned long virt,
 				    phys_addr_t size, pgprot_t prot,
-				    phys_addr_t (*pgtable_alloc)(void))
+				    phys_addr_t (*pgtable_alloc)(void),
+				    bool allow_block_mappings)
 {
 	unsigned long addr, length, end, next;

@@ -322,7 +307,8 @@ static void init_pgd(pgd_t *pgd, phys_addr_t phys, unsigned long virt,
 	end = addr + length;
 	do {
 		next = pgd_addr_end(addr, end);
-		alloc_init_pud(pgd, addr, next, phys, prot, pgtable_alloc);
+		alloc_init_pud(pgd, addr, next, phys, prot, pgtable_alloc,
+			      (!pgtable_alloc || allow_block_mappings));
 		phys += next - addr;
 	} while (pgd++, addr = next, addr != end);
 }
@@ -340,9 +326,11 @@ static phys_addr_t late_pgtable_alloc(void)
 static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
 				 unsigned long virt, phys_addr_t size,
 				 pgprot_t prot,
-				 phys_addr_t (*alloc)(void))
+				 phys_addr_t (*alloc)(void),
+				 bool allow_block_mappings)
 {
-	init_pgd(pgd_offset_raw(pgdir, virt), phys, virt, size, prot, alloc);
+	init_pgd(pgd_offset_raw(pgdir, virt), phys, virt, size, prot, alloc,
+		 allow_block_mappings);
 }

 /*
@@ -358,16 +346,15 @@ static void __init create_mapping_noalloc(phys_addr_t phys, unsigned long virt,
 			&phys, virt);
 		return;
 	}
-	__create_pgd_mapping(init_mm.pgd, phys, virt, size, prot,
-			     NULL);
+	__create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL, true);
 }

 void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
 			       unsigned long virt, phys_addr_t size,
-			       pgprot_t prot)
+			       pgprot_t prot, bool allow_block_mappings)
 {
 	__create_pgd_mapping(mm->pgd, phys, virt, size, prot,
-			     late_pgtable_alloc);
+			     late_pgtable_alloc, allow_block_mappings);
 }

 static void create_mapping_late(phys_addr_t phys, unsigned long virt,
@@ -380,57 +367,36 @@ static void create_mapping_late(phys_addr_t phys, unsigned long virt,
 	}

 	__create_pgd_mapping(init_mm.pgd, phys, virt, size, prot,
-			     late_pgtable_alloc);
+			     late_pgtable_alloc, !debug_pagealloc_enabled());
 }

-static void __init __map_memblock(pgd_t *pgd, phys_addr_t start, phys_addr_t end)
+static void __init __map_memblock(pgd_t *pgd, phys_addr_t start,
+				  phys_addr_t end, pgprot_t prot,
+				  bool allow_block_mappings)
 {
-	unsigned long kernel_start = __pa(_text);
-	unsigned long kernel_end = __pa(__init_begin);
-
-	/*
-	 * Take care not to create a writable alias for the
-	 * read-only text and rodata sections of the kernel image.
-	 */
-
-	/* No overlap with the kernel text/rodata */
-	if (end < kernel_start || start >= kernel_end) {
-		__create_pgd_mapping(pgd, start, __phys_to_virt(start),
-				     end - start, PAGE_KERNEL,
-				     early_pgtable_alloc);
-		return;
-	}
-
-	/*
-	 * This block overlaps the kernel text/rodata mappings.
-	 * Map the portion(s) which don't overlap.
-	 */
-	if (start < kernel_start)
-		__create_pgd_mapping(pgd, start,
-				     __phys_to_virt(start),
-				     kernel_start - start, PAGE_KERNEL,
-				     early_pgtable_alloc);
-	if (kernel_end < end)
-		__create_pgd_mapping(pgd, kernel_end,
-				     __phys_to_virt(kernel_end),
-				     end - kernel_end, PAGE_KERNEL,
-				     early_pgtable_alloc);
-
-	/*
-	 * Map the linear alias of the [_text, __init_begin) interval as
-	 * read-only/non-executable. This makes the contents of the
-	 * region accessible to subsystems such as hibernate, but
-	 * protects it from inadvertent modification or execution.
-	 */
-	__create_pgd_mapping(pgd, kernel_start, __phys_to_virt(kernel_start),
-			     kernel_end - kernel_start, PAGE_KERNEL_RO,
-			     early_pgtable_alloc);
+	__create_pgd_mapping(pgd, start, __phys_to_virt(start), end - start,
+			     prot, early_pgtable_alloc, allow_block_mappings);
 }

 static void __init map_mem(pgd_t *pgd)
 {
+	unsigned long kernel_start = __pa(_text);
+	unsigned long kernel_end = __pa(__init_begin);
 	struct memblock_region *reg;

+	/*
+	 * Take care not to create a writable alias for the
+	 * read-only text and rodata sections of the kernel image.
+	 * So temporarily mark them as NOMAP to skip mappings in
+	 * the following for-loop
+	 */
+	memblock_mark_nomap(kernel_start, kernel_end - kernel_start);
+#ifdef CONFIG_KEXEC_CORE
+	if (crashk_res.end)
+		memblock_mark_nomap(crashk_res.start,
+				    resource_size(&crashk_res));
+#endif
+
 	/* map all the memory banks */
 	for_each_memblock(memory, reg) {
 		phys_addr_t start = reg->base;
@@ -441,8 +407,33 @@ static void __init map_mem(pgd_t *pgd)
 		if (memblock_is_nomap(reg))
 			continue;

-		__map_memblock(pgd, start, end);
+		__map_memblock(pgd, start, end,
+			       PAGE_KERNEL, !debug_pagealloc_enabled());
 	}
+
+	/*
+	 * Map the linear alias of the [_text, __init_begin) interval as
+	 * read-only/non-executable. This makes the contents of the
+	 * region accessible to subsystems such as hibernate, but
+	 * protects it from inadvertent modification or execution.
+	 */
+	__map_memblock(pgd, kernel_start, kernel_end,
+		       PAGE_KERNEL_RO, !debug_pagealloc_enabled());
+	memblock_clear_nomap(kernel_start, kernel_end - kernel_start);
+
+#ifdef CONFIG_KEXEC_CORE
+	/*
+	 * Use page-level mappings here so that we can shrink the region
+	 * in page granularity and put back unused memory to buddy system
+	 * through /sys/kernel/kexec_crash_size interface.
+	 */
+	if (crashk_res.end) {
+		__map_memblock(pgd, crashk_res.start, crashk_res.end + 1,
+			       PAGE_KERNEL, false);
+		memblock_clear_nomap(crashk_res.start,
+				     resource_size(&crashk_res));
+	}
+#endif
 }

 void mark_rodata_ro(void)
@@ -481,7 +472,7 @@ static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end,
 	BUG_ON(!PAGE_ALIGNED(size));

 	__create_pgd_mapping(pgd, pa_start, (unsigned long)va_start, size, prot,
-			     early_pgtable_alloc);
+			     early_pgtable_alloc, !debug_pagealloc_enabled());

 	vma->addr	= va_start;
 	vma->phys_addr	= pa_start;
--- a/arch/arm64/mm/pageattr.c
+++ b/arch/arm64/mm/pageattr.c
@@ -125,6 +125,19 @@ int set_memory_x(unsigned long addr, int numpages)
 }
 EXPORT_SYMBOL_GPL(set_memory_x);

+
+int set_memory_valid(unsigned long addr, int numpages, int enable)
+{
+	if (enable)
+		return __change_memory_common(addr, PAGE_SIZE * numpages,
+					__pgprot(PTE_VALID),
+					__pgprot(0));
+	else
+		return __change_memory_common(addr, PAGE_SIZE * numpages,
+					__pgprot(0),
+					__pgprot(PTE_VALID));
+}
+
 #ifdef CONFIG_DEBUG_PAGEALLOC
 void __kernel_map_pages(struct page *page, int numpages, int enable)
 {
--- a/arch/frv/mm/elf-fdpic.c
+++ b/arch/frv/mm/elf-fdpic.c
@@ -74,7 +74,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi
 		addr = PAGE_ALIGN(addr);
 		vma = find_vma(current->mm, addr);
 		if (TASK_SIZE - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			goto success;
 	}

--- a/arch/mips/ath79/common.c
+++ b/arch/mips/ath79/common.c
@@ -76,14 +76,14 @@ void ath79_ddr_set_pci_windows(void)
 {
 	BUG_ON(!ath79_ddr_pci_win_base);

-	__raw_writel(AR71XX_PCI_WIN0_OFFS, ath79_ddr_pci_win_base + 0);
-	__raw_writel(AR71XX_PCI_WIN1_OFFS, ath79_ddr_pci_win_base + 1);
-	__raw_writel(AR71XX_PCI_WIN2_OFFS, ath79_ddr_pci_win_base + 2);
-	__raw_writel(AR71XX_PCI_WIN3_OFFS, ath79_ddr_pci_win_base + 3);
-	__raw_writel(AR71XX_PCI_WIN4_OFFS, ath79_ddr_pci_win_base + 4);
-	__raw_writel(AR71XX_PCI_WIN5_OFFS, ath79_ddr_pci_win_base + 5);
-	__raw_writel(AR71XX_PCI_WIN6_OFFS, ath79_ddr_pci_win_base + 6);
-	__raw_writel(AR71XX_PCI_WIN7_OFFS, ath79_ddr_pci_win_base + 7);
+	__raw_writel(AR71XX_PCI_WIN0_OFFS, ath79_ddr_pci_win_base + 0x0);
+	__raw_writel(AR71XX_PCI_WIN1_OFFS, ath79_ddr_pci_win_base + 0x4);
+	__raw_writel(AR71XX_PCI_WIN2_OFFS, ath79_ddr_pci_win_base + 0x8);
+	__raw_writel(AR71XX_PCI_WIN3_OFFS, ath79_ddr_pci_win_base + 0xc);
+	__raw_writel(AR71XX_PCI_WIN4_OFFS, ath79_ddr_pci_win_base + 0x10);
+	__raw_writel(AR71XX_PCI_WIN5_OFFS, ath79_ddr_pci_win_base + 0x14);
+	__raw_writel(AR71XX_PCI_WIN6_OFFS, ath79_ddr_pci_win_base + 0x18);
+	__raw_writel(AR71XX_PCI_WIN7_OFFS, ath79_ddr_pci_win_base + 0x1c);
 }
 EXPORT_SYMBOL_GPL(ath79_ddr_set_pci_windows);

--- a/arch/mips/kernel/branch.c
+++ b/arch/mips/kernel/branch.c
@@ -816,8 +816,10 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 			break;
 		}
 		/* Compact branch: BNEZC || JIALC */
-		if (insn.i_format.rs)
+		if (!insn.i_format.rs) {
+			/* JIALC: set $31/ra */
 			regs->regs[31] = epc + 4;
+		}
 		regs->cp0_epc += 8;
 		break;
 #endif
--- a/arch/mips/kernel/entry.S
+++ b/arch/mips/kernel/entry.S
@@ -11,6 +11,7 @@
 #include <asm/asm.h>
 #include <asm/asmmacro.h>
 #include <asm/compiler.h>
+#include <asm/irqflags.h>
 #include <asm/regdef.h>
 #include <asm/mipsregs.h>
 #include <asm/stackframe.h>
@@ -137,6 +138,7 @@ work_pending:
 	andi	t0, a2, _TIF_NEED_RESCHED # a2 is preloaded with TI_FLAGS
 	beqz	t0, work_notifysig
 work_resched:
+	TRACE_IRQS_OFF
 	jal	schedule

 	local_irq_disable		# make sure need_resched and
@@ -173,6 +175,7 @@ syscall_exit_work:
 	beqz	t0, work_pending	# trace bit set?
 	local_irq_enable		# could let syscall_trace_leave()
 					# call schedule() instead
+	TRACE_IRQS_ON
 	move	a0, sp
 	jal	syscall_trace_leave
 	b	resume_userspace
--- a/arch/mips/kernel/pm-cps.c
+++ b/arch/mips/kernel/pm-cps.c
@@ -55,7 +55,6 @@ DECLARE_BITMAP(state_support, CPS_PM_STATE_COUNT);
 * state. Actually per-core rather than per-CPU.
 */
 static DEFINE_PER_CPU_ALIGNED(u32*, ready_count);
-static DEFINE_PER_CPU_ALIGNED(void*, ready_count_alloc);

 /* Indicates online CPUs coupled with the current CPU */
 static DEFINE_PER_CPU_ALIGNED(cpumask_t, online_coupled);
@@ -625,7 +624,6 @@ static int __init cps_gen_core_entries(unsigned cpu)
 {
 	enum cps_pm_state state;
 	unsigned core = cpu_data[cpu].core;
-	unsigned dlinesz = cpu_data[cpu].dcache.linesz;
 	void *entry_fn, *core_rc;

 	for (state = CPS_PM_NC_WAIT; state < CPS_PM_STATE_COUNT; state++) {
@@ -645,16 +643,11 @@ static int __init cps_gen_core_entries(unsigned cpu)
 	}

 	if (!per_cpu(ready_count, core)) {
-		core_rc = kmalloc(dlinesz * 2, GFP_KERNEL);
+		core_rc = kmalloc(sizeof(u32), GFP_KERNEL);
 		if (!core_rc) {
 			pr_err("Failed allocate core %u ready_count\n", core);
 			return -ENOMEM;
 		}
-		per_cpu(ready_count_alloc, core) = core_rc;
-
-		/* Ensure ready_count is aligned to a cacheline boundary */
-		core_rc += dlinesz - 1;
-		core_rc = (void *)((unsigned long)core_rc & ~(dlinesz - 1));
 		per_cpu(ready_count, core) = core_rc;
 	}

--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -194,6 +194,8 @@ void show_stack(struct task_struct *task, unsigned long *sp)
 {
 	struct pt_regs regs;
 	mm_segment_t old_fs = get_fs();
+
+	regs.cp0_status = KSU_KERNEL;
 	if (sp) {
 		regs.regs[29] = (unsigned long)sp;
 		regs.regs[31] = 0;
--- a/arch/mips/mm/mmap.c
+++ b/arch/mips/mm/mmap.c
@@ -92,7 +92,7 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp,

 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}

--- a/arch/mips/ralink/mt7620.c
+++ b/arch/mips/ralink/mt7620.c
@@ -107,31 +107,31 @@ static struct rt2880_pmx_group mt7620a_pinmux_data[] = {
 };

 static struct rt2880_pmx_func pwm1_grp_mt7628[] = {
-	FUNC("sdcx", 3, 19, 1),
+	FUNC("sdxc d6", 3, 19, 1),
 	FUNC("utif", 2, 19, 1),
 	FUNC("gpio", 1, 19, 1),
-	FUNC("pwm", 0, 19, 1),
+	FUNC("pwm1", 0, 19, 1),
 };

 static struct rt2880_pmx_func pwm0_grp_mt7628[] = {
-	FUNC("sdcx", 3, 18, 1),
+	FUNC("sdxc d7", 3, 18, 1),
 	FUNC("utif", 2, 18, 1),
 	FUNC("gpio", 1, 18, 1),
-	FUNC("pwm", 0, 18, 1),
+	FUNC("pwm0", 0, 18, 1),
 };

 static struct rt2880_pmx_func uart2_grp_mt7628[] = {
-	FUNC("sdcx", 3, 20, 2),
+	FUNC("sdxc d5 d4", 3, 20, 2),
 	FUNC("pwm", 2, 20, 2),
 	FUNC("gpio", 1, 20, 2),
-	FUNC("uart", 0, 20, 2),
+	FUNC("uart2", 0, 20, 2),
 };

 static struct rt2880_pmx_func uart1_grp_mt7628[] = {
-	FUNC("sdcx", 3, 45, 2),
+	FUNC("sw_r", 3, 45, 2),
 	FUNC("pwm", 2, 45, 2),
 	FUNC("gpio", 1, 45, 2),
-	FUNC("uart", 0, 45, 2),
+	FUNC("uart1", 0, 45, 2),
 };

 static struct rt2880_pmx_func i2c_grp_mt7628[] = {
@@ -143,21 +143,21 @@ static struct rt2880_pmx_func i2c_grp_mt7628[] = {

 static struct rt2880_pmx_func refclk_grp_mt7628[] = { FUNC("reclk", 0, 36, 1) };
 static struct rt2880_pmx_func perst_grp_mt7628[] = { FUNC("perst", 0, 37, 1) };
-static struct rt2880_pmx_func wdt_grp_mt7628[] = { FUNC("wdt", 0, 15, 38) };
+static struct rt2880_pmx_func wdt_grp_mt7628[] = { FUNC("wdt", 0, 38, 1) };
 static struct rt2880_pmx_func spi_grp_mt7628[] = { FUNC("spi", 0, 7, 4) };

 static struct rt2880_pmx_func sd_mode_grp_mt7628[] = {
 	FUNC("jtag", 3, 22, 8),
 	FUNC("utif", 2, 22, 8),
 	FUNC("gpio", 1, 22, 8),
-	FUNC("sdcx", 0, 22, 8),
+	FUNC("sdxc", 0, 22, 8),
 };

 static struct rt2880_pmx_func uart0_grp_mt7628[] = {
 	FUNC("-", 3, 12, 2),
 	FUNC("-", 2, 12, 2),
 	FUNC("gpio", 1, 12, 2),
-	FUNC("uart", 0, 12, 2),
+	FUNC("uart0", 0, 12, 2),
 };

 static struct rt2880_pmx_func i2s_grp_mt7628[] = {
@@ -171,7 +171,7 @@ static struct rt2880_pmx_func spi_cs1_grp_mt7628[] = {
 	FUNC("-", 3, 6, 1),
 	FUNC("refclk", 2, 6, 1),
 	FUNC("gpio", 1, 6, 1),
-	FUNC("spi", 0, 6, 1),
+	FUNC("spi cs1", 0, 6, 1),
 };

 static struct rt2880_pmx_func spis_grp_mt7628[] = {
@@ -188,28 +188,44 @@ static struct rt2880_pmx_func gpio_grp_mt7628[] = {
 	FUNC("gpio", 0, 11, 1),
 };

-#define MT7628_GPIO_MODE_MASK	0x3
+static struct rt2880_pmx_func wled_kn_grp_mt7628[] = {
+	FUNC("rsvd", 3, 35, 1),
+	FUNC("rsvd", 2, 35, 1),
+	FUNC("gpio", 1, 35, 1),
+	FUNC("wled_kn", 0, 35, 1),
+};

-#define MT7628_GPIO_MODE_PWM1	30
-#define MT7628_GPIO_MODE_PWM0	28
-#define MT7628_GPIO_MODE_UART2	26
-#define MT7628_GPIO_MODE_UART1	24
-#define MT7628_GPIO_MODE_I2C	20
-#define MT7628_GPIO_MODE_REFCLK	18
-#define MT7628_GPIO_MODE_PERST	16
-#define MT7628_GPIO_MODE_WDT	14
-#define MT7628_GPIO_MODE_SPI	12
-#define MT7628_GPIO_MODE_SDMODE	10
-#define MT7628_GPIO_MODE_UART0	8
-#define MT7628_GPIO_MODE_I2S	6
-#define MT7628_GPIO_MODE_CS1	4
-#define MT7628_GPIO_MODE_SPIS	2
-#define MT7628_GPIO_MODE_GPIO	0
+static struct rt2880_pmx_func wled_an_grp_mt7628[] = {
+	FUNC("rsvd", 3, 44, 1),
+	FUNC("rsvd", 2, 44, 1),
+	FUNC("gpio", 1, 44, 1),
+	FUNC("wled_an", 0, 44, 1),
+};
+
+#define MT7628_GPIO_MODE_MASK		0x3
+
+#define MT7628_GPIO_MODE_WLED_KN	48
+#define MT7628_GPIO_MODE_WLED_AN	32
+#define MT7628_GPIO_MODE_PWM1		30
+#define MT7628_GPIO_MODE_PWM0		28
+#define MT7628_GPIO_MODE_UART2		26
+#define MT7628_GPIO_MODE_UART1		24
+#define MT7628_GPIO_MODE_I2C		20
+#define MT7628_GPIO_MODE_REFCLK		18
+#define MT7628_GPIO_MODE_PERST		16
+#define MT7628_GPIO_MODE_WDT		14
+#define MT7628_GPIO_MODE_SPI		12
+#define MT7628_GPIO_MODE_SDMODE		10
+#define MT7628_GPIO_MODE_UART0		8
+#define MT7628_GPIO_MODE_I2S		6
+#define MT7628_GPIO_MODE_CS1		4
+#define MT7628_GPIO_MODE_SPIS		2
+#define MT7628_GPIO_MODE_GPIO		0

 static struct rt2880_pmx_group mt7628an_pinmux_data[] = {
-	GRP_G("pmw1", pwm1_grp_mt7628, MT7628_GPIO_MODE_MASK,
+	GRP_G("pwm1", pwm1_grp_mt7628, MT7628_GPIO_MODE_MASK,
 				1, MT7628_GPIO_MODE_PWM1),
-	GRP_G("pmw1", pwm0_grp_mt7628, MT7628_GPIO_MODE_MASK,
+	GRP_G("pwm0", pwm0_grp_mt7628, MT7628_GPIO_MODE_MASK,
 				1, MT7628_GPIO_MODE_PWM0),
 	GRP_G("uart2", uart2_grp_mt7628, MT7628_GPIO_MODE_MASK,
 				1, MT7628_GPIO_MODE_UART2),
@@ -233,6 +249,10 @@ static struct rt2880_pmx_group mt7628an_pinmux_data[] = {
 				1, MT7628_GPIO_MODE_SPIS),
 	GRP_G("gpio", gpio_grp_mt7628, MT7628_GPIO_MODE_MASK,
 				1, MT7628_GPIO_MODE_GPIO),
+	GRP_G("wled_an", wled_an_grp_mt7628, MT7628_GPIO_MODE_MASK,
+				1, MT7628_GPIO_MODE_WLED_AN),
+	GRP_G("wled_kn", wled_kn_grp_mt7628, MT7628_GPIO_MODE_MASK,
+				1, MT7628_GPIO_MODE_WLED_KN),
 	{ 0 }
 };

@@ -439,7 +459,7 @@ void __init ralink_clk_init(void)
 	ralink_clk_add("10000c00.uartlite", periph_rate);
 	ralink_clk_add("10180000.wmac", xtal_rate);

-	if (IS_ENABLED(CONFIG_USB) && is_mt76x8()) {
+	if (IS_ENABLED(CONFIG_USB) && !is_mt76x8()) {
 		/*
 		 * When the CPU goes into sleep mode, the BUS clock will be
 		 * too low for USB to function properly. Adjust the busses
--- a/arch/mips/ralink/rt288x.c
+++ b/arch/mips/ralink/rt288x.c
@@ -109,5 +109,5 @@ void prom_soc_init(struct ralink_soc_info *soc_info)
 	soc_info->mem_size_max = RT2880_MEM_SIZE_MAX;

 	rt2880_pinmux_data = rt2880_pinmux_data_act;
-	ralink_soc == RT2880_SOC;
+	ralink_soc = RT2880_SOC;
 }
--- a/arch/parisc/kernel/sys_parisc.c
+++ b/arch/parisc/kernel/sys_parisc.c
@@ -88,7 +88,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
 		unsigned long len, unsigned long pgoff, unsigned long flags)
 {
 	struct mm_struct *mm = current->mm;
-	struct vm_area_struct *vma;
+	struct vm_area_struct *vma, *prev;
 	unsigned long task_size = TASK_SIZE;
 	int do_color_align, last_mmap;
 	struct vm_unmapped_area_info info;
@@ -115,9 +115,10 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
 		else
 			addr = PAGE_ALIGN(addr);

-		vma = find_vma(mm, addr);
+		vma = find_vma_prev(mm, addr, &prev);
 		if (task_size - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)) &&
+		    (!prev || addr >= vm_end_gap(prev)))
 			goto found_addr;
 	}

@@ -141,7 +142,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 			  const unsigned long len, const unsigned long pgoff,
 			  const unsigned long flags)
 {
-	struct vm_area_struct *vma;
+	struct vm_area_struct *vma, *prev;
 	struct mm_struct *mm = current->mm;
 	unsigned long addr = addr0;
 	int do_color_align, last_mmap;
@@ -175,9 +176,11 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 			addr = COLOR_ALIGN(addr, last_mmap, pgoff);
 		else
 			addr = PAGE_ALIGN(addr);
-		vma = find_vma(mm, addr);
+
+		vma = find_vma_prev(mm, addr, &prev);
 		if (TASK_SIZE - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)) &&
+		    (!prev || addr >= vm_end_gap(prev)))
 			goto found_addr;
 	}

--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -44,8 +44,22 @@ extern void __init dump_numa_cpu_topology(void);
 extern int sysfs_add_device_to_node(struct device *dev, int nid);
 extern void sysfs_remove_device_from_node(struct device *dev, int nid);

+static inline int early_cpu_to_node(int cpu)
+{
+	int nid;
+
+	nid = numa_cpu_lookup_table[cpu];
+
+	/*
+	 * Fall back to node 0 if nid is unset (it should be, except bugs).
+	 * This allows callers to safely do NODE_DATA(early_cpu_to_node(cpu)).
+	 */
+	return (nid < 0) ? 0 : nid;
+}
 #else

+static inline int early_cpu_to_node(int cpu) { return 0; }
+
 static inline void dump_numa_cpu_topology(void) {}

 static inline int sysfs_add_device_to_node(struct device *dev, int nid)
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -304,9 +304,17 @@ void eeh_slot_error_detail(struct eeh_pe *pe, int severity)
 	 *
 	 * For pHyp, we have to enable IO for log retrieval. Otherwise,
 	 * 0xFF's is always returned from PCI config space.
+	 *
+	 * When the @severity is EEH_LOG_PERM, the PE is going to be
+	 * removed. Prior to that, the drivers for devices included in
+	 * the PE will be closed. The drivers rely on working IO path
+	 * to bring the devices to quiet state. Otherwise, PCI traffic
+	 * from those devices after they are removed is like to cause
+	 * another unexpected EEH error.
 	 */
 	if (!(pe->type & EEH_PE_PHB)) {
-		if (eeh_has_flag(EEH_ENABLE_IO_FOR_LOG))
+		if (eeh_has_flag(EEH_ENABLE_IO_FOR_LOG) ||
+		    severity == EEH_LOG_PERM)
 			eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);

 		/*
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -655,7 +655,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 */
 #define MAX_WAIT_FOR_RECOVERY 300

-static void eeh_handle_normal_event(struct eeh_pe *pe)
+static bool eeh_handle_normal_event(struct eeh_pe *pe)
 {
 	struct pci_bus *frozen_bus;
 	int rc = 0;
@@ -665,7 +665,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
 	if (!frozen_bus) {
 		pr_err("%s: Cannot find PCI bus for PHB#%d-PE#%x\n",
 			__func__, pe->phb->global_number, pe->addr);
-		return;
+		return false;
 	}

 	eeh_pe_update_time_stamp(pe);
@@ -790,7 +790,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
 	pr_info("EEH: Notify device driver to resume\n");
 	eeh_pe_dev_traverse(pe, eeh_report_resume, NULL);

-	return;
+	return false;

 excess_failures:
 	/*
@@ -831,7 +831,11 @@ perm_error:
 		pci_lock_rescan_remove();
 		pcibios_remove_pci_devices(frozen_bus);
 		pci_unlock_rescan_remove();
+
+		/* The passed PE should no longer be used */
+		return true;
 	}
+	return false;
 }

 static void eeh_handle_special_event(void)
@@ -897,7 +901,14 @@ static void eeh_handle_special_event(void)
 		 */
 		if (rc == EEH_NEXT_ERR_FROZEN_PE ||
 		    rc == EEH_NEXT_ERR_FENCED_PHB) {
-			eeh_handle_normal_event(pe);
+			/*
+			 * eeh_handle_normal_event() can make the PE stale if it
+			 * determines that the PE cannot possibly be recovered.
+			 * Don't modify the PE state if that's the case.
+			 */
+			if (eeh_handle_normal_event(pe))
+				continue;
+
 			eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
 		} else {
 			pci_lock_rescan_remove();
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -514,6 +514,15 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 #endif
 #endif

+	/*
+	 * jprobes use jprobe_return() which skips the normal return
+	 * path of the function, and this messes up the accounting of the
+	 * function graph tracer.
+	 *
+	 * Pause function graph tracing while performing the jprobe function.
+	 */
+	pause_graph_tracing();
+
 	return 1;
 }

@@ -536,6 +545,8 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 	 * saved regs...
 	 */
 	memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs));
+	/* It's OK to start function graph tracing again */
+	unpause_graph_tracing();
 	preempt_enable_no_resched();
 	return 1;
 }
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -751,7 +751,7 @@ void __init setup_arch(char **cmdline_p)

 static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
 {
-	return __alloc_bootmem_node(NODE_DATA(cpu_to_node(cpu)), size, align,
+	return __alloc_bootmem_node(NODE_DATA(early_cpu_to_node(cpu)), size, align,
 				    __pa(MAX_DMA_ADDRESS));
 }

@@ -762,7 +762,7 @@ static void __init pcpu_fc_free(void *ptr, size_t size)

 static int pcpu_cpu_distance(unsigned int from, unsigned int to)
 {
-	if (cpu_to_node(from) == cpu_to_node(to))
+	if (early_cpu_to_node(from) == early_cpu_to_node(to))
 		return LOCAL_DISTANCE;
 	else
 		return REMOTE_DISTANCE;
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2693,6 +2693,27 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		return -EINVAL;
 	}

+	/*
+	 * Don't allow entry with a suspended transaction, because
+	 * the guest entry/exit code will lose it.
+	 * If the guest has TM enabled, save away their TM-related SPRs
+	 * (they will get restored by the TM unavailable interrupt).
+	 */
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	if (cpu_has_feature(CPU_FTR_TM) && current->thread.regs &&
+	    (current->thread.regs->msr & MSR_TM)) {
+		if (MSR_TM_ACTIVE(current->thread.regs->msr)) {
+			run->exit_reason = KVM_EXIT_FAIL_ENTRY;
+			run->fail_entry.hardware_entry_failure_reason = 0;
+			return -EINVAL;
+		}
+		current->thread.tm_tfhar = mfspr(SPRN_TFHAR);
+		current->thread.tm_tfiar = mfspr(SPRN_TFIAR);
+		current->thread.tm_texasr = mfspr(SPRN_TEXASR);
+		current->thread.regs->msr &= ~MSR_TM;
+	}
+#endif
+
 	kvmppc_core_prepare_to_enter(vcpu);

 	/* No need to go into the guest when all we'll do is come back out */
--- a/arch/powerpc/mm/slb_low.S
+++ b/arch/powerpc/mm/slb_low.S
@@ -179,6 +179,16 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 	b	slb_finish_load

 8:	/* invalid EA */
+	/*
+	 * It's possible the bad EA is too large to fit in the SLB cache, which
+	 * would mean we'd fail to invalidate it on context switch. So mark the
+	 * SLB cache as full so we force a full flush. We also set cr7+eq to
+	 * mark the address as a kernel address, so slb_finish_load() skips
+	 * trying to insert it into the SLB cache.
+	 */
+	li	r9,SLB_CACHE_ENTRIES + 1
+	sth	r9,PACASLBCACHEPTR(r13)
+	crset	4*cr7+eq
 	li	r10,0			/* BAD_VSID */
 	li	r9,0			/* BAD_VSID */
 	li	r11,SLB_VSID_USER	/* flags don't much matter */
--- a/arch/powerpc/mm/slice.c
+++ b/arch/powerpc/mm/slice.c
@@ -105,7 +105,7 @@ static int slice_area_is_free(struct mm_struct *mm, unsigned long addr,
 	if ((mm->task_size - len) < addr)
 		return 0;
 	vma = find_vma(mm, addr);
-	return (!vma || (addr + len) <= vma->vm_start);
+	return (!vma || (addr + len) <= vm_start_gap(vma));
 }

 static int slice_low_has_vma(struct mm_struct *mm, unsigned long slice)
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -110,6 +110,7 @@ static struct property *dlpar_clone_drconf_property(struct device_node *dn)
 	for (i = 0; i < num_lmbs; i++) {
 		lmbs[i].base_addr = be64_to_cpu(lmbs[i].base_addr);
 		lmbs[i].drc_index = be32_to_cpu(lmbs[i].drc_index);
+		lmbs[i].aa_index = be32_to_cpu(lmbs[i].aa_index);
 		lmbs[i].flags = be32_to_cpu(lmbs[i].flags);
 	}

@@ -553,6 +554,7 @@ static void dlpar_update_drconf_property(struct device_node *dn,
 	for (i = 0; i < num_lmbs; i++) {
 		lmbs[i].base_addr = cpu_to_be64(lmbs[i].base_addr);
 		lmbs[i].drc_index = cpu_to_be32(lmbs[i].drc_index);
+		lmbs[i].aa_index = cpu_to_be32(lmbs[i].aa_index);
 		lmbs[i].flags = cpu_to_be32(lmbs[i].flags);
 	}

--- a/arch/s390/include/asm/ctl_reg.h
+++ b/arch/s390/include/asm/ctl_reg.h
@@ -15,7 +15,9 @@
 	BUILD_BUG_ON(sizeof(addrtype) != (high - low + 1) * sizeof(long));\
 	asm volatile(							\
 		"	lctlg	%1,%2,%0\n"				\
-		: : "Q" (*(addrtype *)(&array)), "i" (low), "i" (high));\
+		:							\
+		: "Q" (*(addrtype *)(&array)), "i" (low), "i" (high)	\
+		: "memory");						\
 }

 #define __ctl_store(array, low, high) {					\
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -229,12 +229,17 @@ ENTRY(sie64a)
 	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
 .Lsie_done:
 # some program checks are suppressing. C code (e.g. do_protection_exception)
-# will rewind the PSW by the ILC, which is 4 bytes in case of SIE. Other
-# instructions between sie64a and .Lsie_done should not cause program
-# interrupts. So lets use a nop (47 00 00 00) as a landing pad.
+# will rewind the PSW by the ILC, which is often 4 bytes in case of SIE. There
+# are some corner cases (e.g. runtime instrumentation) where ILC is unpredictable.
+# Other instructions between sie64a and .Lsie_done should not cause program
+# interrupts. So lets use 3 nops as a landing pad for all possible rewinds.
 # See also .Lcleanup_sie
-.Lrewind_pad:
-	nop	0
+.Lrewind_pad6:
+	nopr	7
+.Lrewind_pad4:
+	nopr	7
+.Lrewind_pad2:
+	nopr	7
 	.globl sie_exit
 sie_exit:
 	lg	%r14,__SF_EMPTY+8(%r15)		# load guest register save area
@@ -247,7 +252,9 @@ sie_exit:
 	stg	%r14,__SF_EMPTY+16(%r15)	# set exit reason code
 	j	sie_exit

-	EX_TABLE(.Lrewind_pad,.Lsie_fault)
+	EX_TABLE(.Lrewind_pad6,.Lsie_fault)
+	EX_TABLE(.Lrewind_pad4,.Lsie_fault)
+	EX_TABLE(.Lrewind_pad2,.Lsie_fault)
 	EX_TABLE(sie_exit,.Lsie_fault)
 #endif

--- a/arch/s390/mm/mmap.c
+++ b/arch/s390/mm/mmap.c
@@ -97,7 +97,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 		addr = PAGE_ALIGN(addr);
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}

@@ -135,7 +135,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 		addr = PAGE_ALIGN(addr);
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
-				(!vma || addr + len <= vma->vm_start))
+				(!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}

--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -372,7 +372,7 @@ void __init vmem_map_init(void)
 	ro_end = (unsigned long)&_eshared & PAGE_MASK;
 	for_each_memblock(memory, reg) {
 		start = reg->base;
-		end = reg->base + reg->size - 1;
+		end = reg->base + reg->size;
 		if (start >= ro_end || end <= ro_start)
 			vmem_add_mem(start, end - start, 0);
 		else if (start >= ro_start && end <= ro_end)
--- a/arch/sh/mm/mmap.c
+++ b/arch/sh/mm/mmap.c
@@ -63,7 +63,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,

 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}

@@ -113,7 +113,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,

 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}

--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -183,9 +183,9 @@ config NR_CPUS
 	int "Maximum number of CPUs"
 	depends on SMP
 	range 2 32 if SPARC32
-	range 2 1024 if SPARC64
+	range 2 4096 if SPARC64
 	default 32 if SPARC32
-	default 64 if SPARC64
+	default 4096 if SPARC64

 source kernel/Kconfig.hz

--- a/arch/sparc/include/asm/mmu_64.h
+++ b/arch/sparc/include/asm/mmu_64.h
@@ -52,7 +52,7 @@
 #define CTX_NR_MASK		TAG_CONTEXT_BITS
 #define CTX_HW_MASK		(CTX_NR_MASK | CTX_PGSZ_MASK)

-#define CTX_FIRST_VERSION	((_AC(1,UL) << CTX_VERSION_SHIFT) + _AC(1,UL))
+#define CTX_FIRST_VERSION	BIT(CTX_VERSION_SHIFT)
 #define CTX_VALID(__ctx)	\
 	 (!(((__ctx.sparc64_ctx_val) ^ tlb_context_cache) & CTX_VERSION_MASK))
 #define CTX_HWBITS(__ctx)	((__ctx.sparc64_ctx_val) & CTX_HW_MASK)
--- a/arch/sparc/include/asm/mmu_context_64.h
+++ b/arch/sparc/include/asm/mmu_context_64.h
@@ -17,13 +17,8 @@ extern spinlock_t ctx_alloc_lock;
 extern unsigned long tlb_context_cache;
 extern unsigned long mmu_context_bmap[];

+DECLARE_PER_CPU(struct mm_struct *, per_cpu_secondary_mm);
 void get_new_mmu_context(struct mm_struct *mm);
-#ifdef CONFIG_SMP
-void smp_new_mmu_context_version(void);
-#else
-#define smp_new_mmu_context_version() do { } while (0)
-#endif
-
 int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
 void destroy_context(struct mm_struct *mm);

@@ -74,8 +69,9 @@ void __flush_tlb_mm(unsigned long, unsigned long);
 static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, struct task_struct *tsk)
 {
 	unsigned long ctx_valid, flags;
-	int cpu;
+	int cpu = smp_processor_id();

+	per_cpu(per_cpu_secondary_mm, cpu) = mm;
 	if (unlikely(mm == &init_mm))
 		return;

@@ -121,7 +117,6 @@ static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, str
 	 * for the first time, we must flush that context out of the
 	 * local TLB.
 	 */
-	cpu = smp_processor_id();
 	if (!ctx_valid || !cpumask_test_cpu(cpu, mm_cpumask(mm))) {
 		cpumask_set_cpu(cpu, mm_cpumask(mm));
 		__flush_tlb_mm(CTX_HWBITS(mm->context),
@@ -131,26 +126,7 @@ static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, str
 }

 #define deactivate_mm(tsk,mm)	do { } while (0)
-
-/* Activate a new MM instance for the current task. */
-static inline void activate_mm(struct mm_struct *active_mm, struct mm_struct *mm)
-{
-	unsigned long flags;
-	int cpu;
-
-	spin_lock_irqsave(&mm->context.lock, flags);
-	if (!CTX_VALID(mm->context))
-		get_new_mmu_context(mm);
-	cpu = smp_processor_id();
-	if (!cpumask_test_cpu(cpu, mm_cpumask(mm)))
-		cpumask_set_cpu(cpu, mm_cpumask(mm));
-
-	load_secondary_context(mm);
-	__flush_tlb_mm(CTX_HWBITS(mm->context), SECONDARY_CONTEXT);
-	tsb_context_switch(mm);
-	spin_unlock_irqrestore(&mm->context.lock, flags);
-}
-
+#define activate_mm(active_mm, mm) switch_mm(active_mm, mm, NULL)
 #endif /* !(__ASSEMBLY__) */

 #endif /* !(__SPARC64_MMU_CONTEXT_H) */
--- a/arch/sparc/include/asm/pil.h
+++ b/arch/sparc/include/asm/pil.h
@@ -20,7 +20,6 @@
 #define PIL_SMP_CALL_FUNC	1
 #define PIL_SMP_RECEIVE_SIGNAL	2
 #define PIL_SMP_CAPTURE		3
-#define PIL_SMP_CTX_NEW_VERSION	4
 #define PIL_DEVICE_IRQ		5
 #define PIL_SMP_CALL_FUNC_SNGL	6
 #define PIL_DEFERRED_PCR_WORK	7
--- a/arch/sparc/include/asm/vio.h
+++ b/arch/sparc/include/asm/vio.h
@@ -327,6 +327,7 @@ struct vio_dev {
 	int			compat_len;

 	u64			dev_no;
+	u64			id;

 	unsigned long		channel_id;

--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -1034,17 +1034,26 @@ static void __init init_cpu_send_mondo_info(struct trap_per_cpu *tb)
 {
 #ifdef CONFIG_SMP
 	unsigned long page;
+	void *mondo, *p;

-	BUILD_BUG_ON((NR_CPUS * sizeof(u16)) > (PAGE_SIZE - 64));
+	BUILD_BUG_ON((NR_CPUS * sizeof(u16)) > PAGE_SIZE);
+
+	/* Make sure mondo block is 64byte aligned */
+	p = kzalloc(127, GFP_KERNEL);
+	if (!p) {
+		prom_printf("SUN4V: Error, cannot allocate mondo block.\n");
+		prom_halt();
+	}
+	mondo = (void *)(((unsigned long)p + 63) & ~0x3f);
+	tb->cpu_mondo_block_pa = __pa(mondo);

 	page = get_zeroed_page(GFP_KERNEL);
 	if (!page) {
-		prom_printf("SUN4V: Error, cannot allocate cpu mondo page.\n");
+		prom_printf("SUN4V: Error, cannot allocate cpu list page.\n");
 		prom_halt();
 	}

-	tb->cpu_mondo_block_pa = __pa(page);
-	tb->cpu_list_pa = __pa(page + 64);
+	tb->cpu_list_pa = __pa(page);
 #endif
 }

--- a/arch/sparc/kernel/kernel.h
+++ b/arch/sparc/kernel/kernel.h
@@ -37,7 +37,6 @@ void handle_stdfmna(struct pt_regs *regs, unsigned long sfar, unsigned long sfsr
 /* smp_64.c */
 void __irq_entry smp_call_function_client(int irq, struct pt_regs *regs);
 void __irq_entry smp_call_function_single_client(int irq, struct pt_regs *regs);
-void __irq_entry smp_new_mmu_context_version_client(int irq, struct pt_regs *regs);
 void __irq_entry smp_penguin_jailcell(int irq, struct pt_regs *regs);
 void __irq_entry smp_receive_signal_client(int irq, struct pt_regs *regs);

--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -959,37 +959,6 @@ void flush_dcache_page_all(struct mm_struct *mm, struct page *page)
 	preempt_enable();
 }

-void __irq_entry smp_new_mmu_context_version_client(int irq, struct pt_regs *regs)
-{
-	struct mm_struct *mm;
-	unsigned long flags;
-
-	clear_softint(1 << irq);
-
-	/* See if we need to allocate a new TLB context because
-	 * the version of the one we are using is now out of date.
-	 */
-	mm = current->active_mm;
-	if (unlikely(!mm || (mm == &init_mm)))
-		return;
-
-	spin_lock_irqsave(&mm->context.lock, flags);
-
-	if (unlikely(!CTX_VALID(mm->context)))
-		get_new_mmu_context(mm);
-
-	spin_unlock_irqrestore(&mm->context.lock, flags);
-
-	load_secondary_context(mm);
-	__flush_tlb_mm(CTX_HWBITS(mm->context),
-		       SECONDARY_CONTEXT);
-}
-
-void smp_new_mmu_context_version(void)
-{
-	smp_cross_call(&xcall_new_mmu_context_version, 0, 0, 0);
-}
-
 #ifdef CONFIG_KGDB
 void kgdb_roundup_cpus(unsigned long flags)
 {
--- a/arch/sparc/kernel/sys_sparc_64.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
@@ -118,7 +118,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi

 		vma = find_vma(mm, addr);
 		if (task_size - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}

@@ -181,7 +181,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,

 		vma = find_vma(mm, addr);
 		if (task_size - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}

--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -85,7 +85,7 @@ static void dump_tl1_traplog(struct tl1_traplog *p)

 void bad_trap(struct pt_regs *regs, long lvl)
 {
-	char buffer[32];
+	char buffer[36];
 	siginfo_t info;

 	if (notify_die(DIE_TRAP, "bad trap", regs,
@@ -116,7 +116,7 @@ void bad_trap(struct pt_regs *regs, long lvl)

 void bad_trap_tl1(struct pt_regs *regs, long lvl)
 {
-	char buffer[32];
+	char buffer[36];
 	
 	if (notify_die(DIE_TRAP_TL1, "bad trap tl1", regs,
 		       0, lvl, SIGTRAP) == NOTIFY_STOP)
--- a/arch/sparc/kernel/tsb.S
+++ b/arch/sparc/kernel/tsb.S
@@ -470,13 +470,16 @@ __tsb_context_switch:
 	.type	copy_tsb,#function
 copy_tsb:		/* %o0=old_tsb_base, %o1=old_tsb_size
 			 * %o2=new_tsb_base, %o3=new_tsb_size
+			 * %o4=page_size_shift
 			 */
 	sethi		%uhi(TSB_PASS_BITS), %g7
 	srlx		%o3, 4, %o3
-	add		%o0, %o1, %g1	/* end of old tsb */
+	add		%o0, %o1, %o1	/* end of old tsb */
 	sllx		%g7, 32, %g7
 	sub		%o3, 1, %o3	/* %o3 == new tsb hash mask */

+	mov		%o4, %g1	/* page_size_shift */
+
 661:	prefetcha	[%o0] ASI_N, #one_read
 	.section	.tsb_phys_patch, "ax"
 	.word		661b
@@ -501,9 +504,9 @@ copy_tsb:		/* %o0=old_tsb_base, %o1=old_tsb_size
 	/* This can definitely be computed faster... */
 	srlx		%o0, 4, %o5	/* Build index */
 	and		%o5, 511, %o5	/* Mask index */
-	sllx		%o5, PAGE_SHIFT, %o5 /* Put into vaddr position */
+	sllx		%o5, %g1, %o5	/* Put into vaddr position */
 	or		%o4, %o5, %o4	/* Full VADDR. */
-	srlx		%o4, PAGE_SHIFT, %o4 /* Shift down to create index */
+	srlx		%o4, %g1, %o4	/* Shift down to create index */
 	and		%o4, %o3, %o4	/* Mask with new_tsb_nents-1 */
 	sllx		%o4, 4, %o4	/* Shift back up into tsb ent offset */
 	TSB_STORE(%o2 + %o4, %g2)	/* Store TAG */
@@ -511,7 +514,7 @@ copy_tsb:		/* %o0=old_tsb_base, %o1=old_tsb_size
 	TSB_STORE(%o2 + %o4, %g3)	/* Store TTE */

 80:	add		%o0, 16, %o0
-	cmp		%o0, %g1
+	cmp		%o0, %o1
 	bne,pt		%xcc, 90b
 	 nop

--- a/arch/sparc/kernel/ttable_64.S
+++ b/arch/sparc/kernel/ttable_64.S
@@ -50,7 +50,7 @@ tl0_resv03e:	BTRAP(0x3e) BTRAP(0x3f) BTRAP(0x40)
 tl0_irq1:	TRAP_IRQ(smp_call_function_client, 1)
 tl0_irq2:	TRAP_IRQ(smp_receive_signal_client, 2)
 tl0_irq3:	TRAP_IRQ(smp_penguin_jailcell, 3)
-tl0_irq4:	TRAP_IRQ(smp_new_mmu_context_version_client, 4)
+tl0_irq4:       BTRAP(0x44)
 #else
 tl0_irq1:	BTRAP(0x41)
 tl0_irq2:	BTRAP(0x42)
--- a/arch/sparc/kernel/vio.c
+++ b/arch/sparc/kernel/vio.c
@@ -284,13 +284,16 @@ static struct vio_dev *vio_create_one(struct mdesc_handle *hp, u64 mp,
 	if (!id) {
 		dev_set_name(&vdev->dev, "%s", bus_id_name);
 		vdev->dev_no = ~(u64)0;
+		vdev->id = ~(u64)0;
 	} else if (!cfg_handle) {
 		dev_set_name(&vdev->dev, "%s-%llu", bus_id_name, *id);
 		vdev->dev_no = *id;
+		vdev->id = ~(u64)0;
 	} else {
 		dev_set_name(&vdev->dev, "%s-%llu-%llu", bus_id_name,
 			     *cfg_handle, *id);
 		vdev->dev_no = *cfg_handle;
+		vdev->id = *id;
 	}

 	vdev->dev.parent = parent;
@@ -333,27 +336,84 @@ static void vio_add(struct mdesc_handle *hp, u64 node)
 	(void) vio_create_one(hp, node, &root_vdev->dev);
 }

+struct vio_md_node_query {
+	const char *type;
+	u64 dev_no;
+	u64 id;
+};
+
 static int vio_md_node_match(struct device *dev, void *arg)
 {
+	struct vio_md_node_query *query = (struct vio_md_node_query *) arg;
 	struct vio_dev *vdev = to_vio_dev(dev);

-	if (vdev->mp == (u64) arg)
-		return 1;
+	if (vdev->dev_no != query->dev_no)
+		return 0;
+	if (vdev->id != query->id)
+		return 0;
+	if (strcmp(vdev->type, query->type))
+		return 0;

-	return 0;
+	return 1;
 }

 static void vio_remove(struct mdesc_handle *hp, u64 node)
 {
+	const char *type;
+	const u64 *id, *cfg_handle;
+	u64 a;
+	struct vio_md_node_query query;
 	struct device *dev;

-	dev = device_find_child(&root_vdev->dev, (void *) node,
+	type = mdesc_get_property(hp, node, "device-type", NULL);
+	if (!type) {
+		type = mdesc_get_property(hp, node, "name", NULL);
+		if (!type)
+			type = mdesc_node_name(hp, node);
+	}
+
+	query.type = type;
+
+	id = mdesc_get_property(hp, node, "id", NULL);
+	cfg_handle = NULL;
+	mdesc_for_each_arc(a, hp, node, MDESC_ARC_TYPE_BACK) {
+		u64 target;
+
+		target = mdesc_arc_target(hp, a);
+		cfg_handle = mdesc_get_property(hp, target,
+						"cfg-handle", NULL);
+		if (cfg_handle)
+			break;
+	}
+
+	if (!id) {
+		query.dev_no = ~(u64)0;
+		query.id = ~(u64)0;
+	} else if (!cfg_handle) {
+		query.dev_no = *id;
+		query.id = ~(u64)0;
+	} else {
+		query.dev_no = *cfg_handle;
+		query.id = *id;
+	}
+
+	dev = device_find_child(&root_vdev->dev, &query,
 				vio_md_node_match);
 	if (dev) {
 		printk(KERN_INFO "VIO: Removing device %s\n", dev_name(dev));

 		device_unregister(dev);
 		put_device(dev);
+	} else {
+		if (!id)
+			printk(KERN_ERR "VIO: Removed unknown %s node.\n",
+			       type);
+		else if (!cfg_handle)
+			printk(KERN_ERR "VIO: Removed unknown %s node %llu.\n",
+			       type, *id);
+		else
+			printk(KERN_ERR "VIO: Removed unknown %s node %llu-%llu.\n",
+			       type, *cfg_handle, *id);
 	}
 }

--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -115,7 +115,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 		addr = ALIGN(addr, HPAGE_SIZE);
 		vma = find_vma(mm, addr);
 		if (task_size - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 	if (mm->get_unmapped_area == arch_get_unmapped_area)
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -656,10 +656,58 @@ EXPORT_SYMBOL(__flush_dcache_range);

 /* get_new_mmu_context() uses "cache + 1".  */
 DEFINE_SPINLOCK(ctx_alloc_lock);
-unsigned long tlb_context_cache = CTX_FIRST_VERSION - 1;
+unsigned long tlb_context_cache = CTX_FIRST_VERSION;
 #define MAX_CTX_NR	(1UL << CTX_NR_BITS)
 #define CTX_BMAP_SLOTS	BITS_TO_LONGS(MAX_CTX_NR)
 DECLARE_BITMAP(mmu_context_bmap, MAX_CTX_NR);
+DEFINE_PER_CPU(struct mm_struct *, per_cpu_secondary_mm) = {0};
+
+static void mmu_context_wrap(void)
+{
+	unsigned long old_ver = tlb_context_cache & CTX_VERSION_MASK;
+	unsigned long new_ver, new_ctx, old_ctx;
+	struct mm_struct *mm;
+	int cpu;
+
+	bitmap_zero(mmu_context_bmap, 1 << CTX_NR_BITS);
+
+	/* Reserve kernel context */
+	set_bit(0, mmu_context_bmap);
+
+	new_ver = (tlb_context_cache & CTX_VERSION_MASK) + CTX_FIRST_VERSION;
+	if (unlikely(new_ver == 0))
+		new_ver = CTX_FIRST_VERSION;
+	tlb_context_cache = new_ver;
+
+	/*
+	 * Make sure that any new mm that are added into per_cpu_secondary_mm,
+	 * are going to go through get_new_mmu_context() path.
+	 */
+	mb();
+
+	/*
+	 * Updated versions to current on those CPUs that had valid secondary
+	 * contexts
+	 */
+	for_each_online_cpu(cpu) {
+		/*
+		 * If a new mm is stored after we took this mm from the array,
+		 * it will go into get_new_mmu_context() path, because we
+		 * already bumped the version in tlb_context_cache.
+		 */
+		mm = per_cpu(per_cpu_secondary_mm, cpu);
+
+		if (unlikely(!mm || mm == &init_mm))
+			continue;
+
+		old_ctx = mm->context.sparc64_ctx_val;
+		if (likely((old_ctx & CTX_VERSION_MASK) == old_ver)) {
+			new_ctx = (old_ctx & ~CTX_VERSION_MASK) | new_ver;
+			set_bit(new_ctx & CTX_NR_MASK, mmu_context_bmap);
+			mm->context.sparc64_ctx_val = new_ctx;
+		}
+	}
+}

 /* Caller does TLB context flushing on local CPU if necessary.
 * The caller also ensures that CTX_VALID(mm->context) is false.
@@ -675,48 +723,30 @@ void get_new_mmu_context(struct mm_struct *mm)
 {
 	unsigned long ctx, new_ctx;
 	unsigned long orig_pgsz_bits;
-	int new_version;

 	spin_lock(&ctx_alloc_lock);
+retry:
+	/* wrap might have happened, test again if our context became valid */
+	if (unlikely(CTX_VALID(mm->context)))
+		goto out;
 	orig_pgsz_bits = (mm->context.sparc64_ctx_val & CTX_PGSZ_MASK);
 	ctx = (tlb_context_cache + 1) & CTX_NR_MASK;
 	new_ctx = find_next_zero_bit(mmu_context_bmap, 1 << CTX_NR_BITS, ctx);
-	new_version = 0;
 	if (new_ctx >= (1 << CTX_NR_BITS)) {
 		new_ctx = find_next_zero_bit(mmu_context_bmap, ctx, 1);
 		if (new_ctx >= ctx) {
-			int i;
-			new_ctx = (tlb_context_cache & CTX_VERSION_MASK) +
-				CTX_FIRST_VERSION;
-			if (new_ctx == 1)
-				new_ctx = CTX_FIRST_VERSION;
-
-			/* Don't call memset, for 16 entries that's just
-			 * plain silly...
-			 */
-			mmu_context_bmap[0] = 3;
-			mmu_context_bmap[1] = 0;
-			mmu_context_bmap[2] = 0;
-			mmu_context_bmap[3] = 0;
-			for (i = 4; i < CTX_BMAP_SLOTS; i += 4) {
-				mmu_context_bmap[i + 0] = 0;
-				mmu_context_bmap[i + 1] = 0;
-				mmu_context_bmap[i + 2] = 0;
-				mmu_context_bmap[i + 3] = 0;
-			}
-			new_version = 1;
-			goto out;
+			mmu_context_wrap();
+			goto retry;
 		}
 	}
+	if (mm->context.sparc64_ctx_val)
+		cpumask_clear(mm_cpumask(mm));
 	mmu_context_bmap[new_ctx>>6] |= (1UL << (new_ctx & 63));
 	new_ctx |= (tlb_context_cache & CTX_VERSION_MASK);
-out:
 	tlb_context_cache = new_ctx;
 	mm->context.sparc64_ctx_val = new_ctx | orig_pgsz_bits;
+out:
 	spin_unlock(&ctx_alloc_lock);
-
-	if (unlikely(new_version))
-		smp_new_mmu_context_version();
 }

 static int numa_enabled = 1;
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -451,7 +451,8 @@ retry_tsb_alloc:
 		extern void copy_tsb(unsigned long old_tsb_base,
 				     unsigned long old_tsb_size,
 				     unsigned long new_tsb_base,
-				     unsigned long new_tsb_size);
+				     unsigned long new_tsb_size,
+				     unsigned long page_size_shift);
 		unsigned long old_tsb_base = (unsigned long) old_tsb;
 		unsigned long new_tsb_base = (unsigned long) new_tsb;

@@ -459,7 +460,9 @@ retry_tsb_alloc:
 			old_tsb_base = __pa(old_tsb_base);
 			new_tsb_base = __pa(new_tsb_base);
 		}
-		copy_tsb(old_tsb_base, old_size, new_tsb_base, new_size);
+		copy_tsb(old_tsb_base, old_size, new_tsb_base, new_size,
+			tsb_index == MM_TSB_BASE ?
+			PAGE_SHIFT : REAL_HPAGE_SHIFT);
 	}

 	mm->context.tsb_block[tsb_index].tsb = new_tsb;
--- a/arch/sparc/mm/ultra.S
+++ b/arch/sparc/mm/ultra.S
@@ -971,11 +971,6 @@ xcall_capture:
 	wr		%g0, (1 << PIL_SMP_CAPTURE), %set_softint
 	retry

-	.globl		xcall_new_mmu_context_version
-xcall_new_mmu_context_version:
-	wr		%g0, (1 << PIL_SMP_CTX_NEW_VERSION), %set_softint
-	retry
-
 #ifdef CONFIG_KGDB
 	.globl		xcall_kgdb_capture
 xcall_kgdb_capture:
--- a/arch/tile/mm/hugetlbpage.c
+++ b/arch/tile/mm/hugetlbpage.c
@@ -232,7 +232,7 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 		addr = ALIGN(addr, huge_page_size(h));
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 	if (current->mm->get_unmapped_area == arch_get_unmapped_area)
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -221,6 +221,9 @@ struct x86_emulate_ops {
 	void (*get_cpuid)(struct x86_emulate_ctxt *ctxt,
 			  u32 *eax, u32 *ebx, u32 *ecx, u32 *edx);
 	void (*set_nmi_mask)(struct x86_emulate_ctxt *ctxt, bool masked);
+
+	unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt);
+	void (*set_hflags)(struct x86_emulate_ctxt *ctxt, unsigned hflags);
 };

 typedef u32 __attribute__((vector_size(16))) sse128_t;
@@ -290,7 +293,6 @@ struct x86_emulate_ctxt {

 	/* interruptibility state, as a result of execution of STI or MOV SS */
 	int interruptibility;
-	int emul_flags;

 	bool perm_ok; /* do not check permissions if true */
 	bool ud;	/* inject an #UD if host doesn't support insn */
--- a/arch/x86/include/asm/pat.h
+++ b/arch/x86/include/asm/pat.h
@@ -7,6 +7,7 @@
 bool pat_enabled(void);
 void pat_disable(const char *reason);
 extern void pat_init(void);
+extern void init_cache_modes(void);

 extern int reserve_memtype(u64 start, u64 end,
 		enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm);
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -161,8 +161,8 @@ void kvm_async_pf_task_wait(u32 token)
 			 */
 			rcu_irq_exit();
 			native_safe_halt();
-			rcu_irq_enter();
 			local_irq_disable();
+			rcu_irq_enter();
 		}
 	}
 	if (!n.halted)
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1048,6 +1048,13 @@ void __init setup_arch(char **cmdline_p)
 	if (mtrr_trim_uncached_memory(max_pfn))
 		max_pfn = e820_end_of_ram_pfn();

+	/*
+	 * This call is required when the CPU does not support PAT. If
+	 * mtrr_bp_init() invoked it already via pat_init() the call has no
+	 * effect.
+	 */
+	init_cache_modes();
+
 #ifdef CONFIG_X86_32
 	/* max_low_pfn get updated here */
 	find_low_pfn_range();
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -143,7 +143,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 		addr = PAGE_ALIGN(addr);
 		vma = find_vma(mm, addr);
 		if (end - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}

@@ -186,7 +186,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 		addr = PAGE_ALIGN(addr);
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr &&
-				(!vma || addr + len <= vma->vm_start))
+				(!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}

--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -737,18 +737,20 @@ out:
 static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i)
 {
 	struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i];
-	int j, nent = vcpu->arch.cpuid_nent;
+	struct kvm_cpuid_entry2 *ej;
+	int j = i;
+	int nent = vcpu->arch.cpuid_nent;

 	e->flags &= ~KVM_CPUID_FLAG_STATE_READ_NEXT;
 	/* when no next entry is found, the current entry[i] is reselected */
-	for (j = i + 1; ; j = (j + 1) % nent) {
-		struct kvm_cpuid_entry2 *ej = &vcpu->arch.cpuid_entries[j];
-		if (ej->function == e->function) {
-			ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
-			return j;
-		}
-	}
-	return 0; /* silence gcc, even though control never reaches here */
+	do {
+		j = (j + 1) % nent;
+		ej = &vcpu->arch.cpuid_entries[j];
+	} while (ej->function != e->function);
+
+	ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
+
+	return j;
 }

 /* find an entry with matching function, matching index (if needed), and that
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2531,7 +2531,7 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt)
 	u64 smbase;
 	int ret;

-	if ((ctxt->emul_flags & X86EMUL_SMM_MASK) == 0)
+	if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_MASK) == 0)
 		return emulate_ud(ctxt);

 	/*
@@ -2580,11 +2580,11 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt)
 		return X86EMUL_UNHANDLEABLE;
 	}

-	if ((ctxt->emul_flags & X86EMUL_SMM_INSIDE_NMI_MASK) == 0)
+	if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_INSIDE_NMI_MASK) == 0)
 		ctxt->ops->set_nmi_mask(ctxt, false);

-	ctxt->emul_flags &= ~X86EMUL_SMM_INSIDE_NMI_MASK;
-	ctxt->emul_flags &= ~X86EMUL_SMM_MASK;
+	ctxt->ops->set_hflags(ctxt, ctxt->ops->get_hflags(ctxt) &
+		~(X86EMUL_SMM_INSIDE_NMI_MASK | X86EMUL_SMM_MASK));
 	return X86EMUL_CONTINUE;
 }

@@ -5296,6 +5296,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 	const struct x86_emulate_ops *ops = ctxt->ops;
 	int rc = X86EMUL_CONTINUE;
 	int saved_dst_type = ctxt->dst.type;
+	unsigned emul_flags;

 	ctxt->mem_read.pos = 0;

@@ -5310,6 +5311,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 		goto done;
 	}

+	emul_flags = ctxt->ops->get_hflags(ctxt);
 	if (unlikely(ctxt->d &
 		     (No64|Undefined|Sse|Mmx|Intercept|CheckPerm|Priv|Prot|String))) {
 		if ((ctxt->mode == X86EMUL_MODE_PROT64 && (ctxt->d & No64)) ||
@@ -5343,7 +5345,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 				fetch_possible_mmx_operand(ctxt, &ctxt->dst);
 		}

-		if (unlikely(ctxt->emul_flags & X86EMUL_GUEST_MASK) && ctxt->intercept) {
+		if (unlikely(emul_flags & X86EMUL_GUEST_MASK) && ctxt->intercept) {
 			rc = emulator_check_intercept(ctxt, ctxt->intercept,
 						      X86_ICPT_PRE_EXCEPT);
 			if (rc != X86EMUL_CONTINUE)
@@ -5372,7 +5374,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 				goto done;
 		}

-		if (unlikely(ctxt->emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) {
+		if (unlikely(emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) {
 			rc = emulator_check_intercept(ctxt, ctxt->intercept,
 						      X86_ICPT_POST_EXCEPT);
 			if (rc != X86EMUL_CONTINUE)
@@ -5426,7 +5428,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)

 special_insn:

-	if (unlikely(ctxt->emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) {
+	if (unlikely(emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) {
 		rc = emulator_check_intercept(ctxt, ctxt->intercept,
 					      X86_ICPT_POST_MEMACCESS);
 		if (rc != X86EMUL_CONTINUE)
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3433,12 +3433,15 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
 	return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
 }

-static bool can_do_async_pf(struct kvm_vcpu *vcpu)
+bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu)
 {
 	if (unlikely(!lapic_in_kernel(vcpu) ||
 		     kvm_event_needs_reinjection(vcpu)))
 		return false;

+	if (is_guest_mode(vcpu))
+		return false;
+
 	return kvm_x86_ops->interrupt_allowed(vcpu);
 }

@@ -3454,7 +3457,7 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
 	if (!async)
 		return false; /* *pfn has correct page already */

-	if (!prefault && can_do_async_pf(vcpu)) {
+	if (!prefault && kvm_can_do_async_pf(vcpu)) {
 		trace_kvm_try_async_get_page(gva, gfn);
 		if (kvm_find_async_pf_gfn(vcpu, gfn)) {
 			trace_kvm_async_pf_doublefault(gva, gfn);
--- a/Show More
+++ b/Show More