Merge tag 'nand/fixes-for-4.9-rc3' of github.com:linux-nand/linux

From Boris:
"""
Three simple fixes:

- the first one is fixing a non-critical bug in the gpmi driver
- the second one is fixing a bug in the 'automatic NAND timings
  selection' feature introduced in 4.9-rc1
- the last one is fixing a false positive uninitialized-var warning
"""

Acked-by: Marek Vasut <marex@denx.de>

Documentation/ABI/testing/sysfs-class-cxl

@@ -220,8 +220,11 @@ What:           /sys/class/cxl/<card>/reset
 Date:           October 2014
 Contact:        linuxppc-dev@lists.ozlabs.org
 Description:    write only
-                Writing 1 will issue a PERST to card which may cause the card
-                to reload the FPGA depending on load_image_on_perst.
+                Writing 1 will issue a PERST to card provided there are no
+                contexts active on any one of the card AFUs. This may cause
+                the card to reload the FPGA depending on load_image_on_perst.
+                Writing -1 will do a force PERST irrespective of any active
+                contexts on the card AFUs.
 Users:		https://github.com/ibm-capi/libcxl
 
 What:		/sys/class/cxl/<card>/perst_reloads_same_image (not in a guest)

Documentation/devicetree/bindings/ipmi/aspeed,ast2400-bt-bmc.txt

@@ -0,0 +1,23 @@
+* Aspeed BT (Block Transfer) IPMI interface
+
+The Aspeed SOCs (AST2400 and AST2500) are commonly used as BMCs
+(BaseBoard Management Controllers) and the BT interface can be used to
+perform in-band IPMI communication with their host.
+
+Required properties:
+
+- compatible : should be "aspeed,ast2400-bt-bmc"
+- reg: physical address and size of the registers
+
+Optional properties:
+
+- interrupts: interrupt generated by the BT interface. without an
+  interrupt, the driver will operate in poll mode.
+
+Example:
+
+	ibt@1e789140 {
+		compatible = "aspeed,ast2400-bt-bmc";
+		reg = <0x1e789140 0x18>;
+		interrupts = <8>;
+	};

Documentation/devicetree/bindings/pinctrl/pinctrl-aspeed.txt

@@ -43,7 +43,9 @@ aspeed,ast2500-pinctrl, aspeed,g5-pinctrl:
 
 GPID0 GPID2 GPIE0 I2C10 I2C11 I2C12 I2C13 I2C14 I2C3 I2C4 I2C5 I2C6 I2C7 I2C8
 I2C9 MAC1LINK MDIO1 MDIO2 OSCCLK PEWAKE PWM0 PWM1 PWM2 PWM3 PWM4 PWM5 PWM6 PWM7
-RGMII1 RGMII2 RMII1 RMII2 SD1 SPI1 TIMER4 TIMER5 TIMER6 TIMER7 TIMER8
+RGMII1 RGMII2 RMII1 RMII2 SD1 SPI1 SPI1DEBUG SPI1PASSTHRU TIMER4 TIMER5 TIMER6
+TIMER7 TIMER8 VGABIOSROM
+
 
 Examples:
 

Documentation/devicetree/bindings/timer/jcore,pit.txt

@@ -0,0 +1,24 @@
+J-Core Programmable Interval Timer and Clocksource
+
+Required properties:
+
+- compatible: Must be "jcore,pit".
+
+- reg: Memory region(s) for timer/clocksource registers. For SMP,
+  there should be one region per cpu, indexed by the sequential,
+  zero-based hardware cpu number.
+
+- interrupts: An interrupt to assign for the timer. The actual pit
+  core is integrated with the aic and allows the timer interrupt
+  assignment to be programmed by software, but this property is
+  required in order to reserve an interrupt number that doesn't
+  conflict with other devices.
+
+
+Example:
+
+timer@200 {
+	compatible = "jcore,pit";
+	reg = < 0x200 0x30 0x500 0x30 >;
+	interrupts = < 0x48 >;
+};

Documentation/filesystems/proc.txt

@@ -395,32 +395,6 @@ is not associated with a file:
 
  or if empty, the mapping is anonymous.
 
-The /proc/PID/task/TID/maps is a view of the virtual memory from the viewpoint
-of the individual tasks of a process. In this file you will see a mapping marked
-as [stack] if that task sees it as a stack. Hence, for the example above, the
-task-level map, i.e. /proc/PID/task/TID/maps for thread 1001 will look like this:
-
-08048000-08049000 r-xp 00000000 03:00 8312       /opt/test
-08049000-0804a000 rw-p 00001000 03:00 8312       /opt/test
-0804a000-0806b000 rw-p 00000000 00:00 0          [heap]
-a7cb1000-a7cb2000 ---p 00000000 00:00 0
-a7cb2000-a7eb2000 rw-p 00000000 00:00 0
-a7eb2000-a7eb3000 ---p 00000000 00:00 0
-a7eb3000-a7ed5000 rw-p 00000000 00:00 0          [stack]
-a7ed5000-a8008000 r-xp 00000000 03:00 4222       /lib/libc.so.6
-a8008000-a800a000 r--p 00133000 03:00 4222       /lib/libc.so.6
-a800a000-a800b000 rw-p 00135000 03:00 4222       /lib/libc.so.6
-a800b000-a800e000 rw-p 00000000 00:00 0
-a800e000-a8022000 r-xp 00000000 03:00 14462      /lib/libpthread.so.0
-a8022000-a8023000 r--p 00013000 03:00 14462      /lib/libpthread.so.0
-a8023000-a8024000 rw-p 00014000 03:00 14462      /lib/libpthread.so.0
-a8024000-a8027000 rw-p 00000000 00:00 0
-a8027000-a8043000 r-xp 00000000 03:00 8317       /lib/ld-linux.so.2
-a8043000-a8044000 r--p 0001b000 03:00 8317       /lib/ld-linux.so.2
-a8044000-a8045000 rw-p 0001c000 03:00 8317       /lib/ld-linux.so.2
-aff35000-aff4a000 rw-p 00000000 00:00 0
-ffffe000-fffff000 r-xp 00000000 00:00 0          [vdso]
-
 The /proc/PID/smaps is an extension based on maps, showing the memory
 consumption for each of the process's mappings. For each of mappings there
 is a series of lines such as the following:

MAINTAINERS

@@ -4620,8 +4620,9 @@ F:	sound/usb/misc/ua101.c
 
 EXTENSIBLE FIRMWARE INTERFACE (EFI)
 M:	Matt Fleming <matt@codeblueprint.co.uk>
+M:	Ard Biesheuvel <ard.biesheuvel@linaro.org>
 L:	linux-efi@vger.kernel.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mfleming/efi.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/efi/efi.git
 S:	Maintained
 F:	Documentation/efi-stub.txt
 F:	arch/ia64/kernel/efi.c
@@ -8216,7 +8217,7 @@ F:	include/linux/mfd/
 MULTIMEDIA CARD (MMC), SECURE DIGITAL (SD) AND SDIO SUBSYSTEM
 M:	Ulf Hansson <ulf.hansson@linaro.org>
 L:	linux-mmc@vger.kernel.org
-T:	git git://git.linaro.org/people/ulf.hansson/mmc.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/mmc.git
 S:	Maintained
 F:	Documentation/devicetree/bindings/mmc/
 F:	drivers/mmc/
@@ -9303,7 +9304,7 @@ S:	Maintained
 F:	drivers/pci/host/*designware*
 
 PCI DRIVER FOR SYNOPSYS PROTOTYPING DEVICE
-M:	Joao Pinto <jpinto@synopsys.com>
+M:	Jose Abreu <Jose.Abreu@synopsys.com>
 L:	linux-pci@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/pci/designware-pcie.txt

Makefile

@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 9
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
 NAME = Psychotic Stoned Sheep
 
 # *DOCUMENTATION*

arch/alpha/kernel/ptrace.c

@@ -157,14 +157,16 @@ put_reg(struct task_struct *task, unsigned long regno, unsigned long data)
 static inline int
 read_int(struct task_struct *task, unsigned long addr, int * data)
 {
-	int copied = access_process_vm(task, addr, data, sizeof(int), 0);
+	int copied = access_process_vm(task, addr, data, sizeof(int),
+			FOLL_FORCE);
 	return (copied == sizeof(int)) ? 0 : -EIO;
 }
 
 static inline int
 write_int(struct task_struct *task, unsigned long addr, int data)
 {
-	int copied = access_process_vm(task, addr, &data, sizeof(int), 1);
+	int copied = access_process_vm(task, addr, &data, sizeof(int),
+			FOLL_FORCE | FOLL_WRITE);
 	return (copied == sizeof(int)) ? 0 : -EIO;
 }
 
@@ -281,7 +283,8 @@ long arch_ptrace(struct task_struct *child, long request,
 	/* When I and D space are separate, these will need to be fixed.  */
 	case PTRACE_PEEKTEXT: /* read word at location addr. */
 	case PTRACE_PEEKDATA:
-		copied = access_process_vm(child, addr, &tmp, sizeof(tmp), 0);
+		copied = access_process_vm(child, addr, &tmp, sizeof(tmp),
+				FOLL_FORCE);
 		ret = -EIO;
 		if (copied != sizeof(tmp))
 			break;

arch/arm/kvm/arm.c

@@ -1312,6 +1312,13 @@ static int init_hyp_mode(void)
 		goto out_err;
 	}
 
+	err = create_hyp_mappings(kvm_ksym_ref(__bss_start),
+				  kvm_ksym_ref(__bss_stop), PAGE_HYP_RO);
+	if (err) {
+		kvm_err("Cannot map bss section\n");
+		goto out_err;
+	}
+
 	/*
 	 * Map the Hyp stack pages
 	 */

arch/arm64/Kconfig

@@ -915,7 +915,7 @@ config RANDOMIZE_BASE
 
 config RANDOMIZE_MODULE_REGION_FULL
 	bool "Randomize the module region independently from the core kernel"
-	depends on RANDOMIZE_BASE
+	depends on RANDOMIZE_BASE && !DYNAMIC_FTRACE
 	default y
 	help
 	  Randomizes the location of the module region without considering the

arch/arm64/Makefile

@@ -15,7 +15,7 @@ CPPFLAGS_vmlinux.lds = -DTEXT_OFFSET=$(TEXT_OFFSET)
 GZFLAGS		:=-9
 
 ifneq ($(CONFIG_RELOCATABLE),)
-LDFLAGS_vmlinux		+= -pie -Bsymbolic
+LDFLAGS_vmlinux		+= -pie -shared -Bsymbolic
 endif
 
 ifeq ($(CONFIG_ARM64_ERRATUM_843419),y)

arch/arm64/include/asm/cpufeature.h

@@ -94,7 +94,7 @@ struct arm64_cpu_capabilities {
 	u16 capability;
 	int def_scope;			/* default scope */
 	bool (*matches)(const struct arm64_cpu_capabilities *caps, int scope);
-	void (*enable)(void *);		/* Called on all active CPUs */
+	int (*enable)(void *);		/* Called on all active CPUs */
 	union {
 		struct {	/* To be used for erratum handling only */
 			u32 midr_model;

arch/arm64/include/asm/exec.h

@@ -18,6 +18,9 @@
 #ifndef __ASM_EXEC_H
 #define __ASM_EXEC_H
 
+#include <linux/sched.h>
+
 extern unsigned long arch_align_stack(unsigned long sp);
+void uao_thread_switch(struct task_struct *next);
 
 #endif	/* __ASM_EXEC_H */

arch/arm64/include/asm/kvm_emulate.h

@@ -178,11 +178,6 @@ static inline bool kvm_vcpu_dabt_isvalid(const struct kvm_vcpu *vcpu)
 	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_ISV);
 }
 
-static inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu)
-{
-	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WNR);
-}
-
 static inline bool kvm_vcpu_dabt_issext(const struct kvm_vcpu *vcpu)
 {
 	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SSE);
@@ -203,6 +198,12 @@ static inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu)
 	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_S1PTW);
 }
 
+static inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu)
+{
+	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WNR) ||
+		kvm_vcpu_dabt_iss1tw(vcpu); /* AF/DBM update */
+}
+
 static inline bool kvm_vcpu_dabt_is_cm(const struct kvm_vcpu *vcpu)
 {
 	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_CM);

arch/arm64/include/asm/module.h

@@ -17,6 +17,7 @@
 #define __ASM_MODULE_H
 
 #include <asm-generic/module.h>
+#include <asm/memory.h>
 
 #define MODULE_ARCH_VERMAGIC	"aarch64"
 
@@ -32,6 +33,10 @@ u64 module_emit_plt_entry(struct module *mod, const Elf64_Rela *rela,
 			  Elf64_Sym *sym);
 
 #ifdef CONFIG_RANDOMIZE_BASE
+#ifdef CONFIG_MODVERSIONS
+#define ARCH_RELOCATES_KCRCTAB
+#define reloc_start 		(kimage_vaddr - KIMAGE_VADDR)
+#endif
 extern u64 module_alloc_base;
 #else
 #define module_alloc_base	((u64)_etext - MODULES_VSIZE)

arch/arm64/include/asm/percpu.h

@@ -44,48 +44,44 @@ static inline unsigned long __percpu_##op(void *ptr,			\
 									\
 	switch (size) {							\
 	case 1:								\
-		do {							\
-			asm ("//__per_cpu_" #op "_1\n"			\
-			"ldxrb	  %w[ret], %[ptr]\n"			\
+		asm ("//__per_cpu_" #op "_1\n"				\
+		"1:	ldxrb	  %w[ret], %[ptr]\n"			\
 			#asm_op " %w[ret], %w[ret], %w[val]\n"		\
-			"stxrb	  %w[loop], %w[ret], %[ptr]\n"		\
-			: [loop] "=&r" (loop), [ret] "=&r" (ret),	\
-			  [ptr] "+Q"(*(u8 *)ptr)			\
-			: [val] "Ir" (val));				\
-		} while (loop);						\
+		"	stxrb	  %w[loop], %w[ret], %[ptr]\n"		\
+		"	cbnz	  %w[loop], 1b"				\
+		: [loop] "=&r" (loop), [ret] "=&r" (ret),		\
+		  [ptr] "+Q"(*(u8 *)ptr)				\
+		: [val] "Ir" (val));					\
 		break;							\
 	case 2:								\
-		do {							\
-			asm ("//__per_cpu_" #op "_2\n"			\
-			"ldxrh	  %w[ret], %[ptr]\n"			\
+		asm ("//__per_cpu_" #op "_2\n"				\
+		"1:	ldxrh	  %w[ret], %[ptr]\n"			\
 			#asm_op " %w[ret], %w[ret], %w[val]\n"		\
-			"stxrh	  %w[loop], %w[ret], %[ptr]\n"		\
-			: [loop] "=&r" (loop), [ret] "=&r" (ret),	\
-			  [ptr]  "+Q"(*(u16 *)ptr)			\
-			: [val] "Ir" (val));				\
-		} while (loop);						\
+		"	stxrh	  %w[loop], %w[ret], %[ptr]\n"		\
+		"	cbnz	  %w[loop], 1b"				\
+		: [loop] "=&r" (loop), [ret] "=&r" (ret),		\
+		  [ptr]  "+Q"(*(u16 *)ptr)				\
+		: [val] "Ir" (val));					\
 		break;							\
 	case 4:								\
-		do {							\
-			asm ("//__per_cpu_" #op "_4\n"			\
-			"ldxr	  %w[ret], %[ptr]\n"			\
+		asm ("//__per_cpu_" #op "_4\n"				\
+		"1:	ldxr	  %w[ret], %[ptr]\n"			\
 			#asm_op " %w[ret], %w[ret], %w[val]\n"		\
-			"stxr	  %w[loop], %w[ret], %[ptr]\n"		\
-			: [loop] "=&r" (loop), [ret] "=&r" (ret),	\
-			  [ptr] "+Q"(*(u32 *)ptr)			\
-			: [val] "Ir" (val));				\
-		} while (loop);						\
+		"	stxr	  %w[loop], %w[ret], %[ptr]\n"		\
+		"	cbnz	  %w[loop], 1b"				\
+		: [loop] "=&r" (loop), [ret] "=&r" (ret),		\
+		  [ptr] "+Q"(*(u32 *)ptr)				\
+		: [val] "Ir" (val));					\
 		break;							\
 	case 8:								\
-		do {							\
-			asm ("//__per_cpu_" #op "_8\n"			\
-			"ldxr	  %[ret], %[ptr]\n"			\
+		asm ("//__per_cpu_" #op "_8\n"				\
+		"1:	ldxr	  %[ret], %[ptr]\n"			\
 			#asm_op " %[ret], %[ret], %[val]\n"		\
-			"stxr	  %w[loop], %[ret], %[ptr]\n"		\
-			: [loop] "=&r" (loop), [ret] "=&r" (ret),	\
-			  [ptr] "+Q"(*(u64 *)ptr)			\
-			: [val] "Ir" (val));				\
-		} while (loop);						\
+		"	stxr	  %w[loop], %[ret], %[ptr]\n"		\
+		"	cbnz	  %w[loop], 1b"				\
+		: [loop] "=&r" (loop), [ret] "=&r" (ret),		\
+		  [ptr] "+Q"(*(u64 *)ptr)				\
+		: [val] "Ir" (val));					\
 		break;							\
 	default:							\
 		BUILD_BUG();						\
@@ -150,44 +146,40 @@ static inline unsigned long __percpu_xchg(void *ptr, unsigned long val,
 
 	switch (size) {
 	case 1:
-		do {
-			asm ("//__percpu_xchg_1\n"
-			"ldxrb %w[ret], %[ptr]\n"
-			"stxrb %w[loop], %w[val], %[ptr]\n"
-			: [loop] "=&r"(loop), [ret] "=&r"(ret),
-			  [ptr] "+Q"(*(u8 *)ptr)
-			: [val] "r" (val));
-		} while (loop);
+		asm ("//__percpu_xchg_1\n"
+		"1:	ldxrb	%w[ret], %[ptr]\n"
+		"	stxrb	%w[loop], %w[val], %[ptr]\n"
+		"	cbnz	%w[loop], 1b"
+		: [loop] "=&r"(loop), [ret] "=&r"(ret),
+		  [ptr] "+Q"(*(u8 *)ptr)
+		: [val] "r" (val));
 		break;
 	case 2:
-		do {
-			asm ("//__percpu_xchg_2\n"
-			"ldxrh %w[ret], %[ptr]\n"
-			"stxrh %w[loop], %w[val], %[ptr]\n"
-			: [loop] "=&r"(loop), [ret] "=&r"(ret),
-			  [ptr] "+Q"(*(u16 *)ptr)
-			: [val] "r" (val));
-		} while (loop);
+		asm ("//__percpu_xchg_2\n"
+		"1:	ldxrh	%w[ret], %[ptr]\n"
+		"	stxrh	%w[loop], %w[val], %[ptr]\n"
+		"	cbnz	%w[loop], 1b"
+		: [loop] "=&r"(loop), [ret] "=&r"(ret),
+		  [ptr] "+Q"(*(u16 *)ptr)
+		: [val] "r" (val));
 		break;
 	case 4:
-		do {
-			asm ("//__percpu_xchg_4\n"
-			"ldxr %w[ret], %[ptr]\n"
-			"stxr %w[loop], %w[val], %[ptr]\n"
-			: [loop] "=&r"(loop), [ret] "=&r"(ret),
-			  [ptr] "+Q"(*(u32 *)ptr)
-			: [val] "r" (val));
-		} while (loop);
+		asm ("//__percpu_xchg_4\n"
+		"1:	ldxr	%w[ret], %[ptr]\n"
+		"	stxr	%w[loop], %w[val], %[ptr]\n"
+		"	cbnz	%w[loop], 1b"
+		: [loop] "=&r"(loop), [ret] "=&r"(ret),
+		  [ptr] "+Q"(*(u32 *)ptr)
+		: [val] "r" (val));
 		break;
 	case 8:
-		do {
-			asm ("//__percpu_xchg_8\n"
-			"ldxr %[ret], %[ptr]\n"
-			"stxr %w[loop], %[val], %[ptr]\n"
-			: [loop] "=&r"(loop), [ret] "=&r"(ret),
-			  [ptr] "+Q"(*(u64 *)ptr)
-			: [val] "r" (val));
-		} while (loop);
+		asm ("//__percpu_xchg_8\n"
+		"1:	ldxr	%[ret], %[ptr]\n"
+		"	stxr	%w[loop], %[val], %[ptr]\n"
+		"	cbnz	%w[loop], 1b"
+		: [loop] "=&r"(loop), [ret] "=&r"(ret),
+		  [ptr] "+Q"(*(u64 *)ptr)
+		: [val] "r" (val));
 		break;
 	default:
 		BUILD_BUG();

arch/arm64/include/asm/processor.h

@@ -188,8 +188,8 @@ static inline void spin_lock_prefetch(const void *ptr)
 
 #endif
 
-void cpu_enable_pan(void *__unused);
-void cpu_enable_uao(void *__unused);
-void cpu_enable_cache_maint_trap(void *__unused);
+int cpu_enable_pan(void *__unused);
+int cpu_enable_uao(void *__unused);
+int cpu_enable_cache_maint_trap(void *__unused);
 
 #endif /* __ASM_PROCESSOR_H */

arch/arm64/include/asm/sysreg.h

@@ -286,7 +286,7 @@ asm(
 
 #define write_sysreg_s(v, r) do {					\
 	u64 __val = (u64)v;						\
-	asm volatile("msr_s " __stringify(r) ", %0" : : "rZ" (__val));	\
+	asm volatile("msr_s " __stringify(r) ", %x0" : : "rZ" (__val));	\
 } while (0)
 
 static inline void config_sctlr_el1(u32 clear, u32 set)

arch/arm64/include/asm/uaccess.h

@@ -21,6 +21,7 @@
 /*
  * User space memory access functions
  */
+#include <linux/bitops.h>
 #include <linux/kasan-checks.h>
 #include <linux/string.h>
 #include <linux/thread_info.h>
@@ -102,6 +103,13 @@ static inline void set_fs(mm_segment_t fs)
 	flag;								\
 })
 
+/*
+ * When dealing with data aborts 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
 

arch/arm64/kernel/armv8_deprecated.c

@@ -280,35 +280,43 @@ static void __init register_insn_emulation_sysctl(struct ctl_table *table)
 /*
  * Error-checking SWP macros implemented using ldxr{b}/stxr{b}
  */
-#define __user_swpX_asm(data, addr, res, temp, B)		\
+
+/* Arbitrary constant to ensure forward-progress of the LL/SC loop */
+#define __SWP_LL_SC_LOOPS	4
+
+#define __user_swpX_asm(data, addr, res, temp, temp2, B)	\
 	__asm__ __volatile__(					\
+	"	mov		%w3, %w7\n"			\
 	ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN,	\
 		    CONFIG_ARM64_PAN)				\
-	"0:	ldxr"B"		%w2, [%3]\n"			\
-	"1:	stxr"B"		%w0, %w1, [%3]\n"		\
+	"0:	ldxr"B"		%w2, [%4]\n"			\
+	"1:	stxr"B"		%w0, %w1, [%4]\n"		\
 	"	cbz		%w0, 2f\n"			\
-	"	mov		%w0, %w4\n"			\
+	"	sub		%w3, %w3, #1\n"			\
+	"	cbnz		%w3, 0b\n"			\
+	"	mov		%w0, %w5\n"			\
 	"	b		3f\n"				\
 	"2:\n"							\
 	"	mov		%w1, %w2\n"			\
 	"3:\n"							\
 	"	.pushsection	 .fixup,\"ax\"\n"		\
 	"	.align		2\n"				\
-	"4:	mov		%w0, %w5\n"			\
+	"4:	mov		%w0, %w6\n"			\
 	"	b		3b\n"				\
 	"	.popsection"					\
 	_ASM_EXTABLE(0b, 4b)					\
 	_ASM_EXTABLE(1b, 4b)					\
 	ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,	\
 		CONFIG_ARM64_PAN)				\
-	: "=&r" (res), "+r" (data), "=&r" (temp)		\
-	: "r" (addr), "i" (-EAGAIN), "i" (-EFAULT)		\
+	: "=&r" (res), "+r" (data), "=&r" (temp), "=&r" (temp2)	\
+	: "r" (addr), "i" (-EAGAIN), "i" (-EFAULT),		\
+	  "i" (__SWP_LL_SC_LOOPS)				\
 	: "memory")
 
-#define __user_swp_asm(data, addr, res, temp) \
-	__user_swpX_asm(data, addr, res, temp, "")
-#define __user_swpb_asm(data, addr, res, temp) \
-	__user_swpX_asm(data, addr, res, temp, "b")
+#define __user_swp_asm(data, addr, res, temp, temp2) \
+	__user_swpX_asm(data, addr, res, temp, temp2, "")
+#define __user_swpb_asm(data, addr, res, temp, temp2) \
+	__user_swpX_asm(data, addr, res, temp, temp2, "b")
 
 /*
  * Bit 22 of the instruction encoding distinguishes between
@@ -328,12 +336,12 @@ static int emulate_swpX(unsigned int address, unsigned int *data,
 	}
 
 	while (1) {
-		unsigned long temp;
+		unsigned long temp, temp2;
 
 		if (type == TYPE_SWPB)
-			__user_swpb_asm(*data, address, res, temp);
+			__user_swpb_asm(*data, address, res, temp, temp2);
 		else
-			__user_swp_asm(*data, address, res, temp);
+			__user_swp_asm(*data, address, res, temp, temp2);
 
 		if (likely(res != -EAGAIN) || signal_pending(current))
 			break;

arch/arm64/kernel/cpu_errata.c

@@ -39,10 +39,11 @@ has_mismatched_cache_line_size(const struct arm64_cpu_capabilities *entry,
 		(arm64_ftr_reg_ctrel0.sys_val & arm64_ftr_reg_ctrel0.strict_mask);
 }
 
-static void cpu_enable_trap_ctr_access(void *__unused)
+static int cpu_enable_trap_ctr_access(void *__unused)
 {
 	/* Clear SCTLR_EL1.UCT */
 	config_sctlr_el1(SCTLR_EL1_UCT, 0);
+	return 0;
 }
 
 #define MIDR_RANGE(model, min, max) \

arch/arm64/kernel/cpufeature.c

@@ -19,7 +19,9 @@
 #define pr_fmt(fmt) "CPU features: " fmt
 
 #include <linux/bsearch.h>
+#include <linux/cpumask.h>
 #include <linux/sort.h>
+#include <linux/stop_machine.h>
 #include <linux/types.h>
 #include <asm/cpu.h>
 #include <asm/cpufeature.h>
@@ -941,7 +943,13 @@ void __init enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps)
 {
 	for (; caps->matches; caps++)
 		if (caps->enable && cpus_have_cap(caps->capability))
-			on_each_cpu(caps->enable, NULL, true);
+			/*
+			 * Use stop_machine() as it schedules the work allowing
+			 * us to modify PSTATE, instead of on_each_cpu() which
+			 * uses an IPI, giving us a PSTATE that disappears when
+			 * we return.
+			 */
+			stop_machine(caps->enable, NULL, cpu_online_mask);
 }
 
 /*

arch/arm64/kernel/head.S

@@ -586,8 +586,9 @@ CPU_LE(	movk	x0, #0x30d0, lsl #16	)	// Clear EE and E0E on LE systems
 	b.lt	4f				// Skip if no PMU present
 	mrs	x0, pmcr_el0			// Disable debug access traps
 	ubfx	x0, x0, #11, #5			// to EL2 and allow access to
-	msr	mdcr_el2, x0			// all PMU counters from EL1
 4:
+	csel	x0, xzr, x0, lt			// all PMU counters from EL1
+	msr	mdcr_el2, x0			// (if they exist)
 
 	/* Stage-2 translation */
 	msr	vttbr_el2, xzr

arch/arm64/kernel/process.c

@@ -49,6 +49,7 @@
 #include <asm/alternative.h>
 #include <asm/compat.h>
 #include <asm/cacheflush.h>
+#include <asm/exec.h>
 #include <asm/fpsimd.h>
 #include <asm/mmu_context.h>
 #include <asm/processor.h>
@@ -186,10 +187,19 @@ void __show_regs(struct pt_regs *regs)
 	printk("pc : [<%016llx>] lr : [<%016llx>] pstate: %08llx\n",
 	       regs->pc, lr, regs->pstate);
 	printk("sp : %016llx\n", sp);
-	for (i = top_reg; i >= 0; i--) {
+
+	i = top_reg;
+
+	while (i >= 0) {
 		printk("x%-2d: %016llx ", i, regs->regs[i]);
-		if (i % 2 == 0)
-			printk("\n");
+		i--;
+
+		if (i % 2 == 0) {
+			pr_cont("x%-2d: %016llx ", i, regs->regs[i]);
+			i--;
+		}
+
+		pr_cont("\n");
 	}
 	printk("\n");
 }
@@ -301,7 +311,7 @@ static void tls_thread_switch(struct task_struct *next)
 }
 
 /* Restore the UAO state depending on next's addr_limit */
-static void uao_thread_switch(struct task_struct *next)
+void uao_thread_switch(struct task_struct *next)
 {
 	if (IS_ENABLED(CONFIG_ARM64_UAO)) {
 		if (task_thread_info(next)->addr_limit == KERNEL_DS)

arch/arm64/kernel/sleep.S

@@ -135,7 +135,7 @@ ENTRY(_cpu_resume)
 
 #ifdef CONFIG_KASAN
 	mov	x0, sp
-	bl	kasan_unpoison_remaining_stack
+	bl	kasan_unpoison_task_stack_below
 #endif
 
 	ldp	x19, x20, [x29, #16]

arch/arm64/kernel/smp.c

@@ -544,6 +544,7 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
 			return;
 		}
 		bootcpu_valid = true;
+		early_map_cpu_to_node(0, acpi_numa_get_nid(0, hwid));
 		return;
 	}
 

arch/arm64/kernel/suspend.c

@@ -1,8 +1,11 @@
 #include <linux/ftrace.h>
 #include <linux/percpu.h>
 #include <linux/slab.h>
+#include <asm/alternative.h>
 #include <asm/cacheflush.h>
+#include <asm/cpufeature.h>
 #include <asm/debug-monitors.h>
+#include <asm/exec.h>
 #include <asm/pgtable.h>
 #include <asm/memory.h>
 #include <asm/mmu_context.h>
@@ -49,6 +52,14 @@ void notrace __cpu_suspend_exit(void)
 	 */
 	set_my_cpu_offset(per_cpu_offset(cpu));
 
+	/*
+	 * PSTATE was not saved over suspend/resume, re-enable any detected
+	 * features that might not have been set correctly.
+	 */
+	asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,
+			CONFIG_ARM64_PAN));
+	uao_thread_switch(current);
+
 	/*
 	 * Restore HW breakpoint registers to sane values
 	 * before debug exceptions are possibly reenabled

arch/arm64/kernel/traps.c

@@ -428,24 +428,28 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
 	force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0);
 }
 
-void cpu_enable_cache_maint_trap(void *__unused)
+int cpu_enable_cache_maint_trap(void *__unused)
 {
 	config_sctlr_el1(SCTLR_EL1_UCI, 0);
+	return 0;
 }
 
 #define __user_cache_maint(insn, address, res)			\
-	asm volatile (						\
-		"1:	" insn ", %1\n"				\
-		"	mov	%w0, #0\n"			\
-		"2:\n"						\
-		"	.pushsection .fixup,\"ax\"\n"		\
-		"	.align	2\n"				\
-		"3:	mov	%w0, %w2\n"			\
-		"	b	2b\n"				\
-		"	.popsection\n"				\
-		_ASM_EXTABLE(1b, 3b)				\
-		: "=r" (res)					\
-		: "r" (address), "i" (-EFAULT) )
+	if (untagged_addr(address) >= user_addr_max())		\
+		res = -EFAULT;					\
+	else							\
+		asm volatile (					\
+			"1:	" insn ", %1\n"			\
+			"	mov	%w0, #0\n"		\
+			"2:\n"					\
+			"	.pushsection .fixup,\"ax\"\n"	\
+			"	.align	2\n"			\
+			"3:	mov	%w0, %w2\n"		\
+			"	b	2b\n"			\
+			"	.popsection\n"			\
+			_ASM_EXTABLE(1b, 3b)			\
+			: "=r" (res)				\
+			: "r" (address), "i" (-EFAULT) )
 
 static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs)
 {

arch/arm64/mm/fault.c

@@ -29,7 +29,9 @@
 #include <linux/sched.h>
 #include <linux/highmem.h>
 #include <linux/perf_event.h>
+#include <linux/preempt.h>
 
+#include <asm/bug.h>
 #include <asm/cpufeature.h>
 #include <asm/exception.h>
 #include <asm/debug-monitors.h>
@@ -670,9 +672,17 @@ asmlinkage int __exception do_debug_exception(unsigned long addr,
 NOKPROBE_SYMBOL(do_debug_exception);
 
 #ifdef CONFIG_ARM64_PAN
-void cpu_enable_pan(void *__unused)
+int cpu_enable_pan(void *__unused)
 {
+	/*
+	 * We modify PSTATE. This won't work from irq context as the PSTATE
+	 * is discarded once we return from the exception.
+	 */
+	WARN_ON_ONCE(in_interrupt());
+
 	config_sctlr_el1(SCTLR_EL1_SPAN, 0);
+	asm(SET_PSTATE_PAN(1));
+	return 0;
 }
 #endif /* CONFIG_ARM64_PAN */
 
@@ -683,8 +693,9 @@ void cpu_enable_pan(void *__unused)
  * We need to enable the feature at runtime (instead of adding it to
  * PSR_MODE_EL1h) as the feature may not be implemented by the cpu.
  */
-void cpu_enable_uao(void *__unused)
+int cpu_enable_uao(void *__unused)
 {
 	asm(SET_PSTATE_UAO(1));
+	return 0;
 }
 #endif /* CONFIG_ARM64_UAO */

arch/arm64/mm/init.c

@@ -421,35 +421,35 @@ void __init mem_init(void)
 
 	pr_notice("Virtual kernel memory layout:\n");
 #ifdef CONFIG_KASAN
-	pr_cont("    kasan   : 0x%16lx - 0x%16lx   (%6ld GB)\n",
+	pr_notice("    kasan   : 0x%16lx - 0x%16lx   (%6ld GB)\n",
 		MLG(KASAN_SHADOW_START, KASAN_SHADOW_END));
 #endif
-	pr_cont("    modules : 0x%16lx - 0x%16lx   (%6ld MB)\n",
+	pr_notice("    modules : 0x%16lx - 0x%16lx   (%6ld MB)\n",
 		MLM(MODULES_VADDR, MODULES_END));
-	pr_cont("    vmalloc : 0x%16lx - 0x%16lx   (%6ld GB)\n",
+	pr_notice("    vmalloc : 0x%16lx - 0x%16lx   (%6ld GB)\n",
 		MLG(VMALLOC_START, VMALLOC_END));
-	pr_cont("      .text : 0x%p" " - 0x%p" "   (%6ld KB)\n",
+	pr_notice("      .text : 0x%p" " - 0x%p" "   (%6ld KB)\n",
 		MLK_ROUNDUP(_text, _etext));
-	pr_cont("    .rodata : 0x%p" " - 0x%p" "   (%6ld KB)\n",
+	pr_notice("    .rodata : 0x%p" " - 0x%p" "   (%6ld KB)\n",
 		MLK_ROUNDUP(__start_rodata, __init_begin));
-	pr_cont("      .init : 0x%p" " - 0x%p" "   (%6ld KB)\n",
+	pr_notice("      .init : 0x%p" " - 0x%p" "   (%6ld KB)\n",
 		MLK_ROUNDUP(__init_begin, __init_end));
-	pr_cont("      .data : 0x%p" " - 0x%p" "   (%6ld KB)\n",
+	pr_notice("      .data : 0x%p" " - 0x%p" "   (%6ld KB)\n",
 		MLK_ROUNDUP(_sdata, _edata));
-	pr_cont("       .bss : 0x%p" " - 0x%p" "   (%6ld KB)\n",
+	pr_notice("       .bss : 0x%p" " - 0x%p" "   (%6ld KB)\n",
 		MLK_ROUNDUP(__bss_start, __bss_stop));
-	pr_cont("    fixed   : 0x%16lx - 0x%16lx   (%6ld KB)\n",
+	pr_notice("    fixed   : 0x%16lx - 0x%16lx   (%6ld KB)\n",
 		MLK(FIXADDR_START, FIXADDR_TOP));
-	pr_cont("    PCI I/O : 0x%16lx - 0x%16lx   (%6ld MB)\n",
+	pr_notice("    PCI I/O : 0x%16lx - 0x%16lx   (%6ld MB)\n",
 		MLM(PCI_IO_START, PCI_IO_END));
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
-	pr_cont("    vmemmap : 0x%16lx - 0x%16lx   (%6ld GB maximum)\n",
+	pr_notice("    vmemmap : 0x%16lx - 0x%16lx   (%6ld GB maximum)\n",
 		MLG(VMEMMAP_START, VMEMMAP_START + VMEMMAP_SIZE));
-	pr_cont("              0x%16lx - 0x%16lx   (%6ld MB actual)\n",
+	pr_notice("              0x%16lx - 0x%16lx   (%6ld MB actual)\n",
 		MLM((unsigned long)phys_to_page(memblock_start_of_DRAM()),
 		    (unsigned long)virt_to_page(high_memory)));
 #endif
-	pr_cont("    memory  : 0x%16lx - 0x%16lx   (%6ld MB)\n",
+	pr_notice("    memory  : 0x%16lx - 0x%16lx   (%6ld MB)\n",
 		MLM(__phys_to_virt(memblock_start_of_DRAM()),
 		    (unsigned long)high_memory));
 

arch/blackfin/kernel/ptrace.c

@@ -271,7 +271,7 @@ long arch_ptrace(struct task_struct *child, long request,
 			case BFIN_MEM_ACCESS_CORE:
 			case BFIN_MEM_ACCESS_CORE_ONLY:
 				copied = access_process_vm(child, addr, &tmp,
-				                           to_copy, 0);
+							   to_copy, FOLL_FORCE);
 				if (copied)
 					break;
 
@@ -324,7 +324,8 @@ long arch_ptrace(struct task_struct *child, long request,
 			case BFIN_MEM_ACCESS_CORE:
 			case BFIN_MEM_ACCESS_CORE_ONLY:
 				copied = access_process_vm(child, addr, &data,
-				                           to_copy, 1);
+				                           to_copy,
+							   FOLL_FORCE | FOLL_WRITE);
 				break;
 			case BFIN_MEM_ACCESS_DMA:
 				if (safe_dma_memcpy(paddr, &data, to_copy))

arch/cris/arch-v32/drivers/cryptocop.c

@@ -2722,7 +2722,6 @@ static int cryptocop_ioctl_process(struct inode *inode, struct file *filp, unsig
 	err = get_user_pages((unsigned long int)(oper.indata + prev_ix),
 			     noinpages,
 			     0,  /* read access only for in data */
-			     0, /* no force */
 			     inpages,
 			     NULL);
 
@@ -2736,8 +2735,7 @@ static int cryptocop_ioctl_process(struct inode *inode, struct file *filp, unsig
 	if (oper.do_cipher){
 		err = get_user_pages((unsigned long int)oper.cipher_outdata,
 				     nooutpages,
-				     1, /* write access for out data */
-				     0, /* no force */
+				     FOLL_WRITE, /* write access for out data */
 				     outpages,
 				     NULL);
 		up_read(&current->mm->mmap_sem);

arch/cris/arch-v32/kernel/ptrace.c

@@ -147,7 +147,7 @@ long arch_ptrace(struct task_struct *child, long request,
 				/* The trampoline page is globally mapped, no page table to traverse.*/
 				tmp = *(unsigned long*)addr;
 			} else {
-				copied = access_process_vm(child, addr, &tmp, sizeof(tmp), 0);
+				copied = access_process_vm(child, addr, &tmp, sizeof(tmp), FOLL_FORCE);
 
 				if (copied != sizeof(tmp))
 					break;
@@ -279,7 +279,7 @@ static int insn_size(struct task_struct *child, unsigned long pc)
   int opsize = 0;
 
   /* Read the opcode at pc (do what PTRACE_PEEKTEXT would do). */
-  copied = access_process_vm(child, pc, &opcode, sizeof(opcode), 0);
+  copied = access_process_vm(child, pc, &opcode, sizeof(opcode), FOLL_FORCE);
   if (copied != sizeof(opcode))
     return 0;
 

arch/ia64/kernel/err_inject.c

@@ -142,7 +142,7 @@ store_virtual_to_phys(struct device *dev, struct device_attribute *attr,
 	u64 virt_addr=simple_strtoull(buf, NULL, 16);
 	int ret;
 
-	ret = get_user_pages(virt_addr, 1, VM_READ, 0, NULL, NULL);
+	ret = get_user_pages(virt_addr, 1, FOLL_WRITE, NULL, NULL);
 	if (ret<=0) {
 #ifdef ERR_INJ_DEBUG
 		printk("Virtual address %lx is not existing.\n",virt_addr);

arch/ia64/kernel/ptrace.c

@@ -453,7 +453,7 @@ ia64_peek (struct task_struct *child, struct switch_stack *child_stack,
 			return 0;
 		}
 	}
-	copied = access_process_vm(child, addr, &ret, sizeof(ret), 0);
+	copied = access_process_vm(child, addr, &ret, sizeof(ret), FOLL_FORCE);
 	if (copied != sizeof(ret))
 		return -EIO;
 	*val = ret;
@@ -489,7 +489,8 @@ ia64_poke (struct task_struct *child, struct switch_stack *child_stack,
 				*ia64_rse_skip_regs(krbs, regnum) = val;
 			}
 		}
-	} else if (access_process_vm(child, addr, &val, sizeof(val), 1)
+	} else if (access_process_vm(child, addr, &val, sizeof(val),
+				FOLL_FORCE | FOLL_WRITE)
 		   != sizeof(val))
 		return -EIO;
 	return 0;
@@ -543,7 +544,8 @@ ia64_sync_user_rbs (struct task_struct *child, struct switch_stack *sw,
 		ret = ia64_peek(child, sw, user_rbs_end, addr, &val);
 		if (ret < 0)
 			return ret;
-		if (access_process_vm(child, addr, &val, sizeof(val), 1)
+		if (access_process_vm(child, addr, &val, sizeof(val),
+				FOLL_FORCE | FOLL_WRITE)
 		    != sizeof(val))
 			return -EIO;
 	}
@@ -559,7 +561,8 @@ ia64_sync_kernel_rbs (struct task_struct *child, struct switch_stack *sw,
 
 	/* now copy word for word from user rbs to kernel rbs: */
 	for (addr = user_rbs_start; addr < user_rbs_end; addr += 8) {
-		if (access_process_vm(child, addr, &val, sizeof(val), 0)
+		if (access_process_vm(child, addr, &val, sizeof(val),
+				FOLL_FORCE)
 				!= sizeof(val))
 			return -EIO;
 
@@ -1156,7 +1159,8 @@ arch_ptrace (struct task_struct *child, long request,
 	case PTRACE_PEEKTEXT:
 	case PTRACE_PEEKDATA:
 		/* read word at location addr */
-		if (access_process_vm(child, addr, &data, sizeof(data), 0)
+		if (access_process_vm(child, addr, &data, sizeof(data),
+				FOLL_FORCE)
 		    != sizeof(data))
 			return -EIO;
 		/* ensure return value is not mistaken for error code */

arch/m32r/kernel/ptrace.c

@@ -493,7 +493,8 @@ unregister_all_debug_traps(struct task_struct *child)
 	int i;
 
 	for (i = 0; i < p->nr_trap; i++)
-		access_process_vm(child, p->addr[i], &p->insn[i], sizeof(p->insn[i]), 1);
+		access_process_vm(child, p->addr[i], &p->insn[i], sizeof(p->insn[i]),
+				FOLL_FORCE | FOLL_WRITE);
 	p->nr_trap = 0;
 }
 
@@ -537,7 +538,8 @@ embed_debug_trap(struct task_struct *child, unsigned long next_pc)
 	unsigned long next_insn, code;
 	unsigned long addr = next_pc & ~3;
 
-	if (access_process_vm(child, addr, &next_insn, sizeof(next_insn), 0)
+	if (access_process_vm(child, addr, &next_insn, sizeof(next_insn),
+			FOLL_FORCE)
 	    != sizeof(next_insn)) {
 		return -1; /* error */
 	}
@@ -546,7 +548,8 @@ embed_debug_trap(struct task_struct *child, unsigned long next_pc)
 	if (register_debug_trap(child, next_pc, next_insn, &code)) {
 		return -1; /* error */
 	}
-	if (access_process_vm(child, addr, &code, sizeof(code), 1)
+	if (access_process_vm(child, addr, &code, sizeof(code),
+			FOLL_FORCE | FOLL_WRITE)
 	    != sizeof(code)) {
 		return -1; /* error */
 	}
@@ -562,7 +565,8 @@ withdraw_debug_trap(struct pt_regs *regs)
  	addr = (regs->bpc - 2) & ~3;
 	regs->bpc -= 2;
 	if (unregister_debug_trap(current, addr, &code)) {
-	    access_process_vm(current, addr, &code, sizeof(code), 1);
+	    access_process_vm(current, addr, &code, sizeof(code),
+		    FOLL_FORCE | FOLL_WRITE);
 	    invalidate_cache();
 	}
 }
@@ -589,7 +593,8 @@ void user_enable_single_step(struct task_struct *child)
 	/* Compute next pc.  */
 	pc = get_stack_long(child, PT_BPC);
 
-	if (access_process_vm(child, pc&~3, &insn, sizeof(insn), 0)
+	if (access_process_vm(child, pc&~3, &insn, sizeof(insn),
+			FOLL_FORCE)
 	    != sizeof(insn))
 		return;
 

arch/mips/kernel/ptrace32.c

@@ -70,7 +70,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 			break;
 
 		copied = access_process_vm(child, (u64)addrOthers, &tmp,
-				sizeof(tmp), 0);
+				sizeof(tmp), FOLL_FORCE);
 		if (copied != sizeof(tmp))
 			break;
 		ret = put_user(tmp, (u32 __user *) (unsigned long) data);
@@ -179,7 +179,8 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 			break;
 		ret = 0;
 		if (access_process_vm(child, (u64)addrOthers, &data,
-					sizeof(data), 1) == sizeof(data))
+					sizeof(data),
+					FOLL_FORCE | FOLL_WRITE) == sizeof(data))
 			break;
 		ret = -EIO;
 		break;

arch/mips/kvm/mips.c

@@ -14,6 +14,7 @@
 #include <linux/err.h>
 #include <linux/kdebug.h>
 #include <linux/module.h>
+#include <linux/uaccess.h>
 #include <linux/vmalloc.h>
 #include <linux/fs.h>
 #include <linux/bootmem.h>

arch/mips/mm/gup.c

@@ -287,7 +287,7 @@ slow_irqon:
 	pages += nr;
 
 	ret = get_user_pages_unlocked(start, (end - start) >> PAGE_SHIFT,
-				      write, 0, pages);
+				      pages, write ? FOLL_WRITE : 0);
 
 	/* Have to be a bit careful with return values */
 	if (nr > 0) {

arch/powerpc/boot/main.c

@@ -32,9 +32,16 @@ static struct addr_range prep_kernel(void)
 	void *addr = 0;
 	struct elf_info ei;
 	long len;
+	int uncompressed_image = 0;
 
-	partial_decompress(vmlinuz_addr, vmlinuz_size,
+	len = partial_decompress(vmlinuz_addr, vmlinuz_size,
 		elfheader, sizeof(elfheader), 0);
+	/* assume uncompressed data if -1 is returned */
+	if (len == -1) {
+		uncompressed_image = 1;
+		memcpy(elfheader, vmlinuz_addr, sizeof(elfheader));
+		printf("No valid compressed data found, assume uncompressed data\n\r");
+	}
 
 	if (!parse_elf64(elfheader, &ei) && !parse_elf32(elfheader, &ei))
 		fatal("Error: not a valid PPC32 or PPC64 ELF file!\n\r");
@@ -67,6 +74,13 @@ static struct addr_range prep_kernel(void)
 					"device tree\n\r");
 	}
 
+	if (uncompressed_image) {
+		memcpy(addr, vmlinuz_addr + ei.elfoffset, ei.loadsize);
+		printf("0x%lx bytes of uncompressed data copied\n\r",
+		       ei.loadsize);
+		goto out;
+	}
+
 	/* Finally, decompress the kernel */
 	printf("Decompressing (0x%p <- 0x%p:0x%p)...\n\r", addr,
 	       vmlinuz_addr, vmlinuz_addr+vmlinuz_size);
@@ -82,7 +96,7 @@ static struct addr_range prep_kernel(void)
 			 len, ei.loadsize);
 
 	printf("Done! Decompressed 0x%lx bytes\n\r", len);
-
+out:
 	flush_cache(addr, ei.loadsize);
 
 	return (struct addr_range){addr, ei.memsize};

arch/powerpc/include/asm/unistd.h

@@ -16,6 +16,10 @@
 
 #define __NR__exit __NR_exit
 
+#define __IGNORE_pkey_mprotect
+#define __IGNORE_pkey_alloc
+#define __IGNORE_pkey_free
+
 #ifndef __ASSEMBLY__
 
 #include <linux/types.h>

arch/powerpc/kernel/ptrace32.c

@@ -74,7 +74,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 			break;
 
 		copied = access_process_vm(child, (u64)addrOthers, &tmp,
-				sizeof(tmp), 0);
+				sizeof(tmp), FOLL_FORCE);
 		if (copied != sizeof(tmp))
 			break;
 		ret = put_user(tmp, (u32 __user *)data);
@@ -179,7 +179,8 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 			break;
 		ret = 0;
 		if (access_process_vm(child, (u64)addrOthers, &tmp,
-					sizeof(tmp), 1) == sizeof(tmp))
+					sizeof(tmp),
+					FOLL_FORCE | FOLL_WRITE) == sizeof(tmp))
 			break;
 		ret = -EIO;
 		break;

arch/powerpc/mm/copro_fault.c

@@ -106,6 +106,8 @@ int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb)
 	switch (REGION_ID(ea)) {
 	case USER_REGION_ID:
 		pr_devel("%s: 0x%llx -- USER_REGION_ID\n", __func__, ea);
+		if (mm == NULL)
+			return 1;
 		psize = get_slice_psize(mm, ea);
 		ssize = user_segment_size(ea);
 		vsid = get_vsid(mm->context.id, ea, ssize);

arch/powerpc/mm/numa.c

@@ -845,7 +845,7 @@ void __init dump_numa_cpu_topology(void)
 		return;
 
 	for_each_online_node(node) {
-		printk(KERN_DEBUG "Node %d CPUs:", node);
+		pr_info("Node %d CPUs:", node);
 
 		count = 0;
 		/*
@@ -856,52 +856,18 @@ void __init dump_numa_cpu_topology(void)
 			if (cpumask_test_cpu(cpu,
 					node_to_cpumask_map[node])) {
 				if (count == 0)
-					printk(" %u", cpu);
+					pr_cont(" %u", cpu);
 				++count;
 			} else {
 				if (count > 1)
-					printk("-%u", cpu - 1);
+					pr_cont("-%u", cpu - 1);
 				count = 0;
 			}
 		}
 
 		if (count > 1)
-			printk("-%u", nr_cpu_ids - 1);
-		printk("\n");
-	}
-}
-
-static void __init dump_numa_memory_topology(void)
-{
-	unsigned int node;
-	unsigned int count;
-
-	if (min_common_depth == -1 || !numa_enabled)
-		return;
-
-	for_each_online_node(node) {
-		unsigned long i;
-
-		printk(KERN_DEBUG "Node %d Memory:", node);
-
-		count = 0;
-
-		for (i = 0; i < memblock_end_of_DRAM();
-		     i += (1 << SECTION_SIZE_BITS)) {
-			if (early_pfn_to_nid(i >> PAGE_SHIFT) == node) {
-				if (count == 0)
-					printk(" 0x%lx", i);
-				++count;
-			} else {
-				if (count > 0)
-					printk("-0x%lx", i);
-				count = 0;
-			}
-		}
-
-		if (count > 0)
-			printk("-0x%lx", i);
-		printk("\n");
+			pr_cont("-%u", nr_cpu_ids - 1);
+		pr_cont("\n");
 	}
 }
 
@@ -947,8 +913,6 @@ void __init initmem_init(void)
 
 	if (parse_numa_properties())
 		setup_nonnuma();
-	else
-		dump_numa_memory_topology();
 
 	memblock_dump_all();
 

arch/s390/kvm/intercept.c

@@ -119,8 +119,13 @@ static int handle_validity(struct kvm_vcpu *vcpu)
 
 	vcpu->stat.exit_validity++;
 	trace_kvm_s390_intercept_validity(vcpu, viwhy);
-	WARN_ONCE(true, "kvm: unhandled validity intercept 0x%x\n", viwhy);
-	return -EOPNOTSUPP;
+	KVM_EVENT(3, "validity intercept 0x%x for pid %u (kvm 0x%pK)", viwhy,
+		  current->pid, vcpu->kvm);
+
+	/* do not warn on invalid runtime instrumentation mode */
+	WARN_ONCE(viwhy != 0x44, "kvm: unhandled validity intercept 0x%x\n",
+		  viwhy);
+	return -EINVAL;
 }
 
 static int handle_instruction(struct kvm_vcpu *vcpu)

arch/s390/mm/gup.c

@@ -266,7 +266,8 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 	/* Try to get the remaining pages with get_user_pages */
 	start += nr << PAGE_SHIFT;
 	pages += nr;
-	ret = get_user_pages_unlocked(start, nr_pages - nr, write, 0, pages);
+	ret = get_user_pages_unlocked(start, nr_pages - nr, pages,
+				      write ? FOLL_WRITE : 0);
 	/* Have to be a bit careful with return values */
 	if (nr > 0)
 		ret = (ret < 0) ? nr : ret + nr;

arch/score/kernel/ptrace.c

@@ -131,7 +131,7 @@ read_tsk_long(struct task_struct *child,
 {
 	int copied;
 
-	copied = access_process_vm(child, addr, res, sizeof(*res), 0);
+	copied = access_process_vm(child, addr, res, sizeof(*res), FOLL_FORCE);
 
 	return copied != sizeof(*res) ? -EIO : 0;
 }
@@ -142,7 +142,7 @@ read_tsk_short(struct task_struct *child,
 {
 	int copied;
 
-	copied = access_process_vm(child, addr, res, sizeof(*res), 0);
+	copied = access_process_vm(child, addr, res, sizeof(*res), FOLL_FORCE);
 
 	return copied != sizeof(*res) ? -EIO : 0;
 }
@@ -153,7 +153,8 @@ write_tsk_short(struct task_struct *child,
 {
 	int copied;
 
-	copied = access_process_vm(child, addr, &val, sizeof(val), 1);
+	copied = access_process_vm(child, addr, &val, sizeof(val),
+			FOLL_FORCE | FOLL_WRITE);
 
 	return copied != sizeof(val) ? -EIO : 0;
 }
@@ -164,7 +165,8 @@ write_tsk_long(struct task_struct *child,
 {
 	int copied;
 
-	copied = access_process_vm(child, addr, &val, sizeof(val), 1);
+	copied = access_process_vm(child, addr, &val, sizeof(val),
+			FOLL_FORCE | FOLL_WRITE);
 
 	return copied != sizeof(val) ? -EIO : 0;
 }

arch/sh/Makefile

@@ -31,7 +31,7 @@ isa-y					:= $(isa-y)-up
 endif
 
 cflags-$(CONFIG_CPU_SH2)		:= $(call cc-option,-m2,)
-cflags-$(CONFIG_CPU_J2)			:= $(call cc-option,-mj2,)
+cflags-$(CONFIG_CPU_J2)			+= $(call cc-option,-mj2,)
 cflags-$(CONFIG_CPU_SH2A)		+= $(call cc-option,-m2a,) \
 					   $(call cc-option,-m2a-nofpu,) \
 					   $(call cc-option,-m4-nofpu,)

arch/sh/boards/Kconfig

@@ -22,6 +22,16 @@ config SH_DEVICE_TREE
 	  have sufficient driver coverage to use this option; do not
 	  select it if you are using original SuperH hardware.
 
+config SH_JCORE_SOC
+	bool "J-Core SoC"
+	depends on SH_DEVICE_TREE && (CPU_SH2 || CPU_J2)
+	select CLKSRC_JCORE_PIT
+	select JCORE_AIC
+	default y if CPU_J2
+	help
+	  Select this option to include drivers core components of the
+	  J-Core SoC, including interrupt controllers and timers.
+
 config SH_SOLUTION_ENGINE
 	bool "SolutionEngine"
 	select SOLUTION_ENGINE

arch/sh/configs/j2_defconfig

@@ -8,6 +8,7 @@ CONFIG_MEMORY_START=0x10000000
 CONFIG_MEMORY_SIZE=0x04000000
 CONFIG_CPU_BIG_ENDIAN=y
 CONFIG_SH_DEVICE_TREE=y
+CONFIG_SH_JCORE_SOC=y
 CONFIG_HZ_100=y
 CONFIG_CMDLINE_OVERWRITE=y
 CONFIG_CMDLINE="console=ttyUL0 earlycon"
@@ -20,6 +21,7 @@ CONFIG_INET=y
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_NETDEVICES=y
+CONFIG_SERIAL_EARLYCON=y
 CONFIG_SERIAL_UARTLITE=y
 CONFIG_SERIAL_UARTLITE_CONSOLE=y
 CONFIG_I2C=y

arch/sh/mm/gup.c

@@ -258,7 +258,8 @@ slow_irqon:
 		pages += nr;
 
 		ret = get_user_pages_unlocked(start,
-			(end - start) >> PAGE_SHIFT, write, 0, pages);
+			(end - start) >> PAGE_SHIFT, pages,
+			write ? FOLL_WRITE : 0);
 
 		/* Have to be a bit careful with return values */
 		if (nr > 0) {

arch/sparc/kernel/ptrace_64.c

@@ -127,7 +127,8 @@ static int get_from_target(struct task_struct *target, unsigned long uaddr,
 		if (copy_from_user(kbuf, (void __user *) uaddr, len))
 			return -EFAULT;
 	} else {
-		int len2 = access_process_vm(target, uaddr, kbuf, len, 0);
+		int len2 = access_process_vm(target, uaddr, kbuf, len,
+				FOLL_FORCE);
 		if (len2 != len)
 			return -EFAULT;
 	}
@@ -141,7 +142,8 @@ static int set_to_target(struct task_struct *target, unsigned long uaddr,
 		if (copy_to_user((void __user *) uaddr, kbuf, len))
 			return -EFAULT;
 	} else {
-		int len2 = access_process_vm(target, uaddr, kbuf, len, 1);
+		int len2 = access_process_vm(target, uaddr, kbuf, len,
+				FOLL_FORCE | FOLL_WRITE);
 		if (len2 != len)
 			return -EFAULT;
 	}
@@ -505,7 +507,8 @@ static int genregs32_get(struct task_struct *target,
 				if (access_process_vm(target,
 						      (unsigned long)
 						      &reg_window[pos],
-						      k, sizeof(*k), 0)
+						      k, sizeof(*k),
+						      FOLL_FORCE)
 				    != sizeof(*k))
 					return -EFAULT;
 				k++;
@@ -531,12 +534,14 @@ static int genregs32_get(struct task_struct *target,
 				if (access_process_vm(target,
 						      (unsigned long)
 						      &reg_window[pos],
-						      &reg, sizeof(reg), 0)
+						      &reg, sizeof(reg),
+						      FOLL_FORCE)
 				    != sizeof(reg))
 					return -EFAULT;
 				if (access_process_vm(target,
 						      (unsigned long) u,
-						      &reg, sizeof(reg), 1)
+						      &reg, sizeof(reg),
+						      FOLL_FORCE | FOLL_WRITE)
 				    != sizeof(reg))
 					return -EFAULT;
 				pos++;
@@ -615,7 +620,8 @@ static int genregs32_set(struct task_struct *target,
 						      (unsigned long)
 						      &reg_window[pos],
 						      (void *) k,
-						      sizeof(*k), 1)
+						      sizeof(*k),
+						      FOLL_FORCE | FOLL_WRITE)
 				    != sizeof(*k))
 					return -EFAULT;
 				k++;
@@ -642,13 +648,15 @@ static int genregs32_set(struct task_struct *target,
 				if (access_process_vm(target,
 						      (unsigned long)
 						      u,
-						      &reg, sizeof(reg), 0)
+						      &reg, sizeof(reg),
+						      FOLL_FORCE)
 				    != sizeof(reg))
 					return -EFAULT;
 				if (access_process_vm(target,
 						      (unsigned long)
 						      &reg_window[pos],
-						      &reg, sizeof(reg), 1)
+						      &reg, sizeof(reg),
+						      FOLL_FORCE | FOLL_WRITE)
 				    != sizeof(reg))
 					return -EFAULT;
 				pos++;

arch/sparc/mm/gup.c

@@ -238,7 +238,8 @@ slow:
 		pages += nr;
 
 		ret = get_user_pages_unlocked(start,
-			(end - start) >> PAGE_SHIFT, write, 0, pages);
+			(end - start) >> PAGE_SHIFT, pages,
+			write ? FOLL_WRITE : 0);
 
 		/* Have to be a bit careful with return values */
 		if (nr > 0) {

arch/x86/entry/syscalls/syscall_32.tbl

@@ -389,5 +389,3 @@
 380	i386	pkey_mprotect		sys_pkey_mprotect
 381	i386	pkey_alloc		sys_pkey_alloc
 382	i386	pkey_free		sys_pkey_free
-#383	i386	pkey_get		sys_pkey_get
-#384	i386	pkey_set		sys_pkey_set

arch/x86/entry/syscalls/syscall_64.tbl

@@ -338,8 +338,6 @@
 329	common	pkey_mprotect		sys_pkey_mprotect
 330	common	pkey_alloc		sys_pkey_alloc
 331	common	pkey_free		sys_pkey_free
-#332	common	pkey_get		sys_pkey_get
-#333	common	pkey_set		sys_pkey_set
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact

arch/x86/events/intel/core.c

@@ -3898,6 +3898,7 @@ __init int intel_pmu_init(void)
 		break;
 
 	case INTEL_FAM6_XEON_PHI_KNL:
+	case INTEL_FAM6_XEON_PHI_KNM:
 		memcpy(hw_cache_event_ids,
 		       slm_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs,
@@ -3912,7 +3913,7 @@ __init int intel_pmu_init(void)
 		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
 		x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
 
-		pr_cont("Knights Landing events, ");
+		pr_cont("Knights Landing/Mill events, ");
 		break;
 
 	case INTEL_FAM6_SKYLAKE_MOBILE:

arch/x86/events/intel/lbr.c

@@ -458,8 +458,8 @@ void intel_pmu_lbr_del(struct perf_event *event)
 	if (!x86_pmu.lbr_nr)
 		return;
 
-	if (branch_user_callstack(cpuc->br_sel) && event->ctx &&
-					event->ctx->task_ctx_data) {
+	if (branch_user_callstack(cpuc->br_sel) &&
+	    event->ctx->task_ctx_data) {
 		task_ctx = event->ctx->task_ctx_data;
 		task_ctx->lbr_callstack_users--;
 	}

arch/x86/events/intel/rapl.c

@@ -763,6 +763,7 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, hsw_rapl_init),
 
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL, knl_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNM, knl_rapl_init),
 
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE,  skl_rapl_init),
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP, skl_rapl_init),

arch/x86/events/intel/uncore.c

@@ -1349,6 +1349,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_X,	  bdx_uncore_init),
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, bdx_uncore_init),
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL,	  knl_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNM,	  knl_uncore_init),
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP,skl_uncore_init),
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE, skl_uncore_init),
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X,      skx_uncore_init),

arch/x86/include/asm/cpufeatures.h

@@ -194,6 +194,8 @@
 #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
 
 #define X86_FEATURE_INTEL_PT	( 7*32+15) /* Intel Processor Trace */
+#define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */
+#define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW  ( 8*32+ 0) /* Intel TPR Shadow */

arch/x86/include/asm/intel-family.h

@@ -64,5 +64,6 @@
 /* Xeon Phi */
 
 #define INTEL_FAM6_XEON_PHI_KNL		0x57 /* Knights Landing */
+#define INTEL_FAM6_XEON_PHI_KNM		0x85 /* Knights Mill */
 
 #endif /* _ASM_X86_INTEL_FAMILY_H */

arch/x86/include/asm/msr-index.h

@@ -88,7 +88,6 @@
 
 #define MSR_IA32_RTIT_CTL		0x00000570
 #define MSR_IA32_RTIT_STATUS		0x00000571
-#define MSR_IA32_RTIT_STATUS		0x00000571
 #define MSR_IA32_RTIT_ADDR0_A		0x00000580
 #define MSR_IA32_RTIT_ADDR0_B		0x00000581
 #define MSR_IA32_RTIT_ADDR1_A		0x00000582

arch/x86/include/asm/rwsem.h

@@ -103,8 +103,10 @@ static inline bool __down_read_trylock(struct rw_semaphore *sem)
 ({							\
 	long tmp;					\
 	struct rw_semaphore* ret;			\
+	register void *__sp asm(_ASM_SP);		\
+							\
 	asm volatile("# beginning down_write\n\t"	\
-		     LOCK_PREFIX "  xadd      %1,(%3)\n\t"	\
+		     LOCK_PREFIX "  xadd      %1,(%4)\n\t"	\
 		     /* adds 0xffff0001, returns the old value */ \
 		     "  test " __ASM_SEL(%w1,%k1) "," __ASM_SEL(%w1,%k1) "\n\t" \
 		     /* was the active mask 0 before? */\
@@ -112,7 +114,7 @@ static inline bool __down_read_trylock(struct rw_semaphore *sem)
 		     "  call " slow_path "\n"		\
 		     "1:\n"				\
 		     "# ending down_write"		\
-		     : "+m" (sem->count), "=d" (tmp), "=a" (ret)	\
+		     : "+m" (sem->count), "=d" (tmp), "=a" (ret), "+r" (__sp) \
 		     : "a" (sem), "1" (RWSEM_ACTIVE_WRITE_BIAS) \
 		     : "memory", "cc");			\
 	ret;						\

arch/x86/include/asm/thread_info.h

@@ -52,6 +52,15 @@ struct task_struct;
 #include <asm/cpufeature.h>
 #include <linux/atomic.h>
 
+struct thread_info {
+	unsigned long		flags;		/* low level flags */
+};
+
+#define INIT_THREAD_INFO(tsk)			\
+{						\
+	.flags		= 0,			\
+}
+
 #define init_stack		(init_thread_union.stack)
 
 #else /* !__ASSEMBLY__ */

arch/x86/kernel/cpu/scattered.c

@@ -32,6 +32,8 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 
 	static const struct cpuid_bit cpuid_bits[] = {
 		{ X86_FEATURE_INTEL_PT,		CR_EBX,25, 0x00000007, 0 },
+		{ X86_FEATURE_AVX512_4VNNIW,	CR_EDX, 2, 0x00000007, 0 },
+		{ X86_FEATURE_AVX512_4FMAPS,	CR_EDX, 3, 0x00000007, 0 },
 		{ X86_FEATURE_APERFMPERF,	CR_ECX, 0, 0x00000006, 0 },
 		{ X86_FEATURE_EPB,		CR_ECX, 3, 0x00000006, 0 },
 		{ X86_FEATURE_HW_PSTATE,	CR_EDX, 7, 0x80000007, 0 },

arch/x86/kernel/cpu/vmware.c

@@ -27,6 +27,7 @@
 #include <asm/div64.h>
 #include <asm/x86_init.h>
 #include <asm/hypervisor.h>
+#include <asm/timer.h>
 #include <asm/apic.h>
 
 #define CPUID_VMWARE_INFO_LEAF	0x40000000
@@ -94,6 +95,10 @@ static void __init vmware_platform_setup(void)
 	} else {
 		pr_warn("Failed to get TSC freq from the hypervisor\n");
 	}
+
+#ifdef CONFIG_X86_IO_APIC
+	no_timer_check = 1;
+#endif
 }
 
 /*

arch/x86/kernel/e820.c

@@ -350,7 +350,7 @@ int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map,
 		 * continue building up new bios map based on this
 		 * information
 		 */
-		if (current_type != last_type) {
+		if (current_type != last_type || current_type == E820_PRAM) {
 			if (last_type != 0)	 {
 				new_bios[new_bios_entry].size =
 					change_point[chgidx]->addr - last_addr;

arch/x86/kernel/fpu/xstate.c

@@ -74,6 +74,8 @@ void fpu__xstate_clear_all_cpu_caps(void)
 	setup_clear_cpu_cap(X86_FEATURE_MPX);
 	setup_clear_cpu_cap(X86_FEATURE_XGETBV1);
 	setup_clear_cpu_cap(X86_FEATURE_PKU);
+	setup_clear_cpu_cap(X86_FEATURE_AVX512_4VNNIW);
+	setup_clear_cpu_cap(X86_FEATURE_AVX512_4FMAPS);
 }
 
 /*

arch/x86/kernel/kprobes/core.c

@@ -50,6 +50,7 @@
 #include <linux/kallsyms.h>
 #include <linux/ftrace.h>
 #include <linux/frame.h>
+#include <linux/kasan.h>
 
 #include <asm/text-patching.h>
 #include <asm/cacheflush.h>
@@ -1057,9 +1058,10 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 	 * tailcall optimization. So, to be absolutely safe
 	 * we also save and restore enough stack bytes to cover
 	 * the argument area.
+	 * Use __memcpy() to avoid KASAN stack out-of-bounds reports as we copy
+	 * raw stack chunk with redzones:
 	 */
-	memcpy(kcb->jprobes_stack, (kprobe_opcode_t *)addr,
-	       MIN_STACK_SIZE(addr));
+	__memcpy(kcb->jprobes_stack, (kprobe_opcode_t *)addr, MIN_STACK_SIZE(addr));
 	regs->flags &= ~X86_EFLAGS_IF;
 	trace_hardirqs_off();
 	regs->ip = (unsigned long)(jp->entry);
@@ -1080,6 +1082,9 @@ void jprobe_return(void)
 {
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
 
+	/* Unpoison stack redzones in the frames we are going to jump over. */
+	kasan_unpoison_stack_above_sp_to(kcb->jprobe_saved_sp);
+
 	asm volatile (
 #ifdef CONFIG_X86_64
 			"       xchg   %%rbx,%%rsp	\n"
@@ -1118,7 +1123,7 @@ int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 		/* It's OK to start function graph tracing again */
 		unpause_graph_tracing();
 		*regs = kcb->jprobe_saved_regs;
-		memcpy(saved_sp, kcb->jprobes_stack, MIN_STACK_SIZE(saved_sp));
+		__memcpy(saved_sp, kcb->jprobes_stack, MIN_STACK_SIZE(saved_sp));
 		preempt_enable_no_resched();
 		return 1;
 	}

arch/x86/kernel/signal_compat.c

@@ -105,9 +105,6 @@ void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact)
 	/* Don't let flags to be set from userspace */
 	act->sa.sa_flags &= ~(SA_IA32_ABI | SA_X32_ABI);
 
-	if (user_64bit_mode(current_pt_regs()))
-		return;
-
 	if (in_ia32_syscall())
 		act->sa.sa_flags |= SA_IA32_ABI;
 	if (in_x32_syscall())

arch/x86/kernel/smp.c

@@ -261,8 +261,10 @@ static inline void __smp_reschedule_interrupt(void)
 
 __visible void smp_reschedule_interrupt(struct pt_regs *regs)
 {
+	irq_enter();
 	ack_APIC_irq();
 	__smp_reschedule_interrupt();
+	irq_exit();
 	/*
 	 * KVM uses this interrupt to force a cpu out of guest mode
 	 */

arch/x86/kernel/smpboot.c

@@ -1409,15 +1409,17 @@ __init void prefill_possible_map(void)
 
 	/* No boot processor was found in mptable or ACPI MADT */
 	if (!num_processors) {
-		int apicid = boot_cpu_physical_apicid;
-		int cpu = hard_smp_processor_id();
+		if (boot_cpu_has(X86_FEATURE_APIC)) {
+			int apicid = boot_cpu_physical_apicid;
+			int cpu = hard_smp_processor_id();
 
-		pr_warn("Boot CPU (id %d) not listed by BIOS\n", cpu);
+			pr_warn("Boot CPU (id %d) not listed by BIOS\n", cpu);
 
-		/* Make sure boot cpu is enumerated */
-		if (apic->cpu_present_to_apicid(0) == BAD_APICID &&
-		    apic->apic_id_valid(apicid))
-			generic_processor_info(apicid, boot_cpu_apic_version);
+			/* Make sure boot cpu is enumerated */
+			if (apic->cpu_present_to_apicid(0) == BAD_APICID &&
+			    apic->apic_id_valid(apicid))
+				generic_processor_info(apicid, boot_cpu_apic_version);
+		}
 
 		if (!num_processors)
 			num_processors = 1;

arch/x86/kernel/step.c

@@ -57,7 +57,8 @@ static int is_setting_trap_flag(struct task_struct *child, struct pt_regs *regs)
 	unsigned char opcode[15];
 	unsigned long addr = convert_ip_to_linear(child, regs);
 
-	copied = access_process_vm(child, addr, opcode, sizeof(opcode), 0);
+	copied = access_process_vm(child, addr, opcode, sizeof(opcode),
+			FOLL_FORCE);
 	for (i = 0; i < copied; i++) {
 		switch (opcode[i]) {
 		/* popf and iret */

arch/x86/kvm/ioapic.c

@@ -594,7 +594,7 @@ static void kvm_ioapic_reset(struct kvm_ioapic *ioapic)
 	ioapic->irr = 0;
 	ioapic->irr_delivered = 0;
 	ioapic->id = 0;
-	memset(ioapic->irq_eoi, 0x00, IOAPIC_NUM_PINS);
+	memset(ioapic->irq_eoi, 0x00, sizeof(ioapic->irq_eoi));
 	rtc_irq_eoi_tracking_reset(ioapic);
 }
 

arch/x86/kvm/x86.c

@@ -5733,13 +5733,13 @@ static int kvmclock_cpu_online(unsigned int cpu)
 
 static void kvm_timer_init(void)
 {
-	int cpu;
-
 	max_tsc_khz = tsc_khz;
 
 	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
 #ifdef CONFIG_CPU_FREQ
 		struct cpufreq_policy policy;
+		int cpu;
+
 		memset(&policy, 0, sizeof(policy));
 		cpu = get_cpu();
 		cpufreq_get_policy(&policy, cpu);

arch/x86/mm/gup.c

@@ -435,7 +435,7 @@ slow_irqon:
 
 		ret = get_user_pages_unlocked(start,
 					      (end - start) >> PAGE_SHIFT,
-					      write, 0, pages);
+					      pages, write ? FOLL_WRITE : 0);
 
 		/* Have to be a bit careful with return values */
 		if (nr > 0) {

arch/x86/mm/mpx.c

@@ -544,10 +544,9 @@ static int mpx_resolve_fault(long __user *addr, int write)
 {
 	long gup_ret;
 	int nr_pages = 1;
-	int force = 0;
 
-	gup_ret = get_user_pages((unsigned long)addr, nr_pages, write,
-			force, NULL, NULL);
+	gup_ret = get_user_pages((unsigned long)addr, nr_pages,
+			write ? FOLL_WRITE : 0,	NULL, NULL);
 	/*
 	 * get_user_pages() returns number of pages gotten.
 	 * 0 means we failed to fault in and get anything,

arch/x86/platform/uv/bios_uv.c

@@ -40,7 +40,15 @@ s64 uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, u64 a4, u64 a5)
 		 */
 		return BIOS_STATUS_UNIMPLEMENTED;
 
-	ret = efi_call_virt_pointer(tab, function, (u64)which, a1, a2, a3, a4, a5);
+	/*
+	 * If EFI_OLD_MEMMAP is set, we need to fall back to using our old EFI
+	 * callback method, which uses efi_call() directly, with the kernel page tables:
+	 */
+	if (unlikely(test_bit(EFI_OLD_MEMMAP, &efi.flags)))
+		ret = efi_call((void *)__va(tab->function), (u64)which, a1, a2, a3, a4, a5);
+	else
+		ret = efi_call_virt_pointer(tab, function, (u64)which, a1, a2, a3, a4, a5);
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(uv_bios_call);

arch/x86/um/ptrace_32.c

@@ -36,7 +36,8 @@ int is_syscall(unsigned long addr)
 		 * slow, but that doesn't matter, since it will be called only
 		 * in case of singlestepping, if copy_from_user failed.
 		 */
-		n = access_process_vm(current, addr, &instr, sizeof(instr), 0);
+		n = access_process_vm(current, addr, &instr, sizeof(instr),
+				FOLL_FORCE);
 		if (n != sizeof(instr)) {
 			printk(KERN_ERR "is_syscall : failed to read "
 			       "instruction from 0x%lx\n", addr);

arch/x86/um/ptrace_64.c

@@ -212,7 +212,8 @@ int is_syscall(unsigned long addr)
 		 * slow, but that doesn't matter, since it will be called only
 		 * in case of singlestepping, if copy_from_user failed.
 		 */
-		n = access_process_vm(current, addr, &instr, sizeof(instr), 0);
+		n = access_process_vm(current, addr, &instr, sizeof(instr),
+				FOLL_FORCE);
 		if (n != sizeof(instr)) {
 			printk("is_syscall : failed to read instruction from "
 			       "0x%lx\n", addr);

block/badblocks.c

@@ -354,7 +354,8 @@ int badblocks_clear(struct badblocks *bb, sector_t s, int sectors)
 		 * current range.  Earlier ranges could also overlap,
 		 * but only this one can overlap the end of the range.
 		 */
-		if (BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > target) {
+		if ((BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > target) &&
+		    (BB_OFFSET(p[lo]) < target)) {
 			/* Partial overlap, leave the tail of this range */
 			int ack = BB_ACK(p[lo]);
 			sector_t a = BB_OFFSET(p[lo]);
@@ -377,7 +378,8 @@ int badblocks_clear(struct badblocks *bb, sector_t s, int sectors)
 			lo--;
 		}
 		while (lo >= 0 &&
-		       BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > s) {
+		       (BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > s) &&
+		       (BB_OFFSET(p[lo]) < target)) {
 			/* This range does overlap */
 			if (BB_OFFSET(p[lo]) < s) {
 				/* Keep the early parts of this range. */

drivers/Makefile

@@ -21,7 +21,7 @@ obj-y				+= video/
 obj-y				+= idle/
 
 # IPMI must come before ACPI in order to provide IPMI opregion support
-obj-$(CONFIG_IPMI_HANDLER)	+= char/ipmi/
+obj-y				+= char/ipmi/
 
 obj-$(CONFIG_ACPI)		+= acpi/
 obj-$(CONFIG_SFI)		+= sfi/

drivers/block/rbd.c

@@ -415,15 +415,15 @@ struct rbd_device {
 };
 
 /*
- * Flag bits for rbd_dev->flags.  If atomicity is required,
- * rbd_dev->lock is used to protect access.
- *
- * Currently, only the "removing" flag (which is coupled with the
- * "open_count" field) requires atomic access.
+ * Flag bits for rbd_dev->flags:
+ * - REMOVING (which is coupled with rbd_dev->open_count) is protected
+ *   by rbd_dev->lock
+ * - BLACKLISTED is protected by rbd_dev->lock_rwsem
  */
 enum rbd_dev_flags {
 	RBD_DEV_FLAG_EXISTS,	/* mapped snapshot has not been deleted */
 	RBD_DEV_FLAG_REMOVING,	/* this mapping is being removed */
+	RBD_DEV_FLAG_BLACKLISTED, /* our ceph_client is blacklisted */
 };
 
 static DEFINE_MUTEX(client_mutex);	/* Serialize client creation */
@@ -3926,6 +3926,7 @@ static void rbd_reregister_watch(struct work_struct *work)
 	struct rbd_device *rbd_dev = container_of(to_delayed_work(work),
 					    struct rbd_device, watch_dwork);
 	bool was_lock_owner = false;
+	bool need_to_wake = false;
 	int ret;
 
 	dout("%s rbd_dev %p\n", __func__, rbd_dev);
@@ -3935,19 +3936,27 @@ static void rbd_reregister_watch(struct work_struct *work)
 		was_lock_owner = rbd_release_lock(rbd_dev);
 
 	mutex_lock(&rbd_dev->watch_mutex);
-	if (rbd_dev->watch_state != RBD_WATCH_STATE_ERROR)
-		goto fail_unlock;
+	if (rbd_dev->watch_state != RBD_WATCH_STATE_ERROR) {
+		mutex_unlock(&rbd_dev->watch_mutex);
+		goto out;
+	}
 
 	ret = __rbd_register_watch(rbd_dev);
 	if (ret) {
 		rbd_warn(rbd_dev, "failed to reregister watch: %d", ret);
-		if (ret != -EBLACKLISTED)
+		if (ret == -EBLACKLISTED || ret == -ENOENT) {
+			set_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags);
+			need_to_wake = true;
+		} else {
 			queue_delayed_work(rbd_dev->task_wq,
 					   &rbd_dev->watch_dwork,
 					   RBD_RETRY_DELAY);
-		goto fail_unlock;
+		}
+		mutex_unlock(&rbd_dev->watch_mutex);
+		goto out;
 	}
 
+	need_to_wake = true;
 	rbd_dev->watch_state = RBD_WATCH_STATE_REGISTERED;
 	rbd_dev->watch_cookie = rbd_dev->watch_handle->linger_id;
 	mutex_unlock(&rbd_dev->watch_mutex);
@@ -3963,13 +3972,10 @@ static void rbd_reregister_watch(struct work_struct *work)
 				 ret);
 	}
 
+out:
 	up_write(&rbd_dev->lock_rwsem);
-	wake_requests(rbd_dev, true);
-	return;
-
-fail_unlock:
-	mutex_unlock(&rbd_dev->watch_mutex);
-	up_write(&rbd_dev->lock_rwsem);
+	if (need_to_wake)
+		wake_requests(rbd_dev, true);
 }
 
 /*
@@ -4074,7 +4080,9 @@ static void rbd_wait_state_locked(struct rbd_device *rbd_dev)
 		up_read(&rbd_dev->lock_rwsem);
 		schedule();
 		down_read(&rbd_dev->lock_rwsem);
-	} while (rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED);
+	} while (rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED &&
+		 !test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags));
+
 	finish_wait(&rbd_dev->lock_waitq, &wait);
 }
 
@@ -4166,8 +4174,16 @@ static void rbd_queue_workfn(struct work_struct *work)
 
 	if (must_be_locked) {
 		down_read(&rbd_dev->lock_rwsem);
-		if (rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED)
+		if (rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED &&
+		    !test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags))
 			rbd_wait_state_locked(rbd_dev);
+
+		WARN_ON((rbd_dev->lock_state == RBD_LOCK_STATE_LOCKED) ^
+			!test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags));
+		if (test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags)) {
+			result = -EBLACKLISTED;
+			goto err_unlock;
+		}
 	}
 
 	img_request = rbd_img_request_create(rbd_dev, offset, length, op_type,

drivers/char/ipmi/Kconfig

@@ -76,3 +76,11 @@ config IPMI_POWEROFF
 	 the IPMI management controller is capable of this.
 
 endif # IPMI_HANDLER
+
+config ASPEED_BT_IPMI_BMC
+	depends on ARCH_ASPEED
+	tristate "BT IPMI bmc driver"
+	help
+	  Provides a driver for the BT (Block Transfer) IPMI interface
+	  found on Aspeed SOCs (AST2400 and AST2500). The driver
+	  implements the BMC side of the BT interface.

drivers/char/ipmi/Makefile

@@ -11,3 +11,4 @@ obj-$(CONFIG_IPMI_SSIF) += ipmi_ssif.o
 obj-$(CONFIG_IPMI_POWERNV) += ipmi_powernv.o
 obj-$(CONFIG_IPMI_WATCHDOG) += ipmi_watchdog.o
 obj-$(CONFIG_IPMI_POWEROFF) += ipmi_poweroff.o
+obj-$(CONFIG_ASPEED_BT_IPMI_BMC) += bt-bmc.o

drivers/char/ipmi/bt-bmc.c

@@ -0,0 +1,505 @@
+/*
+ * Copyright (c) 2015-2016, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/atomic.h>
+#include <linux/bt-bmc.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/miscdevice.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/poll.h>
+#include <linux/sched.h>
+#include <linux/timer.h>
+
+/*
+ * This is a BMC device used to communicate to the host
+ */
+#define DEVICE_NAME	"ipmi-bt-host"
+
+#define BT_IO_BASE	0xe4
+#define BT_IRQ		10
+
+#define BT_CR0		0x0
+#define   BT_CR0_IO_BASE		16
+#define   BT_CR0_IRQ			12
+#define   BT_CR0_EN_CLR_SLV_RDP		0x8
+#define   BT_CR0_EN_CLR_SLV_WRP		0x4
+#define   BT_CR0_ENABLE_IBT		0x1
+#define BT_CR1		0x4
+#define   BT_CR1_IRQ_H2B	0x01
+#define   BT_CR1_IRQ_HBUSY	0x40
+#define BT_CR2		0x8
+#define   BT_CR2_IRQ_H2B	0x01
+#define   BT_CR2_IRQ_HBUSY	0x40
+#define BT_CR3		0xc
+#define BT_CTRL		0x10
+#define   BT_CTRL_B_BUSY		0x80
+#define   BT_CTRL_H_BUSY		0x40
+#define   BT_CTRL_OEM0			0x20
+#define   BT_CTRL_SMS_ATN		0x10
+#define   BT_CTRL_B2H_ATN		0x08
+#define   BT_CTRL_H2B_ATN		0x04
+#define   BT_CTRL_CLR_RD_PTR		0x02
+#define   BT_CTRL_CLR_WR_PTR		0x01
+#define BT_BMC2HOST	0x14
+#define BT_INTMASK	0x18
+#define   BT_INTMASK_B2H_IRQEN		0x01
+#define   BT_INTMASK_B2H_IRQ		0x02
+#define   BT_INTMASK_BMC_HWRST		0x80
+
+#define BT_BMC_BUFFER_SIZE 256
+
+struct bt_bmc {
+	struct device		dev;
+	struct miscdevice	miscdev;
+	void __iomem		*base;
+	int			irq;
+	wait_queue_head_t	queue;
+	struct timer_list	poll_timer;
+	struct mutex		mutex;
+};
+
+static atomic_t open_count = ATOMIC_INIT(0);
+
+static u8 bt_inb(struct bt_bmc *bt_bmc, int reg)
+{
+	return ioread8(bt_bmc->base + reg);
+}
+
+static void bt_outb(struct bt_bmc *bt_bmc, u8 data, int reg)
+{
+	iowrite8(data, bt_bmc->base + reg);
+}
+
+static void clr_rd_ptr(struct bt_bmc *bt_bmc)
+{
+	bt_outb(bt_bmc, BT_CTRL_CLR_RD_PTR, BT_CTRL);
+}
+
+static void clr_wr_ptr(struct bt_bmc *bt_bmc)
+{
+	bt_outb(bt_bmc, BT_CTRL_CLR_WR_PTR, BT_CTRL);
+}
+
+static void clr_h2b_atn(struct bt_bmc *bt_bmc)
+{
+	bt_outb(bt_bmc, BT_CTRL_H2B_ATN, BT_CTRL);
+}
+
+static void set_b_busy(struct bt_bmc *bt_bmc)
+{
+	if (!(bt_inb(bt_bmc, BT_CTRL) & BT_CTRL_B_BUSY))
+		bt_outb(bt_bmc, BT_CTRL_B_BUSY, BT_CTRL);
+}
+
+static void clr_b_busy(struct bt_bmc *bt_bmc)
+{
+	if (bt_inb(bt_bmc, BT_CTRL) & BT_CTRL_B_BUSY)
+		bt_outb(bt_bmc, BT_CTRL_B_BUSY, BT_CTRL);
+}
+
+static void set_b2h_atn(struct bt_bmc *bt_bmc)
+{
+	bt_outb(bt_bmc, BT_CTRL_B2H_ATN, BT_CTRL);
+}
+
+static u8 bt_read(struct bt_bmc *bt_bmc)
+{
+	return bt_inb(bt_bmc, BT_BMC2HOST);
+}
+
+static ssize_t bt_readn(struct bt_bmc *bt_bmc, u8 *buf, size_t n)
+{
+	int i;
+
+	for (i = 0; i < n; i++)
+		buf[i] = bt_read(bt_bmc);
+	return n;
+}
+
+static void bt_write(struct bt_bmc *bt_bmc, u8 c)
+{
+	bt_outb(bt_bmc, c, BT_BMC2HOST);
+}
+
+static ssize_t bt_writen(struct bt_bmc *bt_bmc, u8 *buf, size_t n)
+{
+	int i;
+
+	for (i = 0; i < n; i++)
+		bt_write(bt_bmc, buf[i]);
+	return n;
+}
+
+static void set_sms_atn(struct bt_bmc *bt_bmc)
+{
+	bt_outb(bt_bmc, BT_CTRL_SMS_ATN, BT_CTRL);
+}
+
+static struct bt_bmc *file_bt_bmc(struct file *file)
+{
+	return container_of(file->private_data, struct bt_bmc, miscdev);
+}
+
+static int bt_bmc_open(struct inode *inode, struct file *file)
+{
+	struct bt_bmc *bt_bmc = file_bt_bmc(file);
+
+	if (atomic_inc_return(&open_count) == 1) {
+		clr_b_busy(bt_bmc);
+		return 0;
+	}
+
+	atomic_dec(&open_count);
+	return -EBUSY;
+}
+
+/*
+ * The BT (Block Transfer) interface means that entire messages are
+ * buffered by the host before a notification is sent to the BMC that
+ * there is data to be read. The first byte is the length and the
+ * message data follows. The read operation just tries to capture the
+ * whole before returning it to userspace.
+ *
+ * BT Message format :
+ *
+ *    Byte 1  Byte 2     Byte 3  Byte 4  Byte 5:N
+ *    Length  NetFn/LUN  Seq     Cmd     Data
+ *
+ */
+static ssize_t bt_bmc_read(struct file *file, char __user *buf,
+			   size_t count, loff_t *ppos)
+{
+	struct bt_bmc *bt_bmc = file_bt_bmc(file);
+	u8 len;
+	int len_byte = 1;
+	u8 kbuffer[BT_BMC_BUFFER_SIZE];
+	ssize_t ret = 0;
+	ssize_t nread;
+
+	if (!access_ok(VERIFY_WRITE, buf, count))
+		return -EFAULT;
+
+	WARN_ON(*ppos);
+
+	if (wait_event_interruptible(bt_bmc->queue,
+				     bt_inb(bt_bmc, BT_CTRL) & BT_CTRL_H2B_ATN))
+		return -ERESTARTSYS;
+
+	mutex_lock(&bt_bmc->mutex);
+
+	if (unlikely(!(bt_inb(bt_bmc, BT_CTRL) & BT_CTRL_H2B_ATN))) {
+		ret = -EIO;
+		goto out_unlock;
+	}
+
+	set_b_busy(bt_bmc);
+	clr_h2b_atn(bt_bmc);
+	clr_rd_ptr(bt_bmc);
+
+	/*
+	 * The BT frames start with the message length, which does not
+	 * include the length byte.
+	 */
+	kbuffer[0] = bt_read(bt_bmc);
+	len = kbuffer[0];
+
+	/* We pass the length back to userspace as well */
+	if (len + 1 > count)
+		len = count - 1;
+
+	while (len) {
+		nread = min_t(ssize_t, len, sizeof(kbuffer) - len_byte);
+
+		bt_readn(bt_bmc, kbuffer + len_byte, nread);
+
+		if (copy_to_user(buf, kbuffer, nread + len_byte)) {
+			ret = -EFAULT;
+			break;
+		}
+		len -= nread;
+		buf += nread + len_byte;
+		ret += nread + len_byte;
+		len_byte = 0;
+	}
+
+	clr_b_busy(bt_bmc);
+
+out_unlock:
+	mutex_unlock(&bt_bmc->mutex);
+	return ret;
+}
+
+/*
+ * BT Message response format :
+ *
+ *    Byte 1  Byte 2     Byte 3  Byte 4  Byte 5  Byte 6:N
+ *    Length  NetFn/LUN  Seq     Cmd     Code    Data
+ */
+static ssize_t bt_bmc_write(struct file *file, const char __user *buf,
+			    size_t count, loff_t *ppos)
+{
+	struct bt_bmc *bt_bmc = file_bt_bmc(file);
+	u8 kbuffer[BT_BMC_BUFFER_SIZE];
+	ssize_t ret = 0;
+	ssize_t nwritten;
+
+	/*
+	 * send a minimum response size
+	 */
+	if (count < 5)
+		return -EINVAL;
+
+	if (!access_ok(VERIFY_READ, buf, count))
+		return -EFAULT;
+
+	WARN_ON(*ppos);
+
+	/*
+	 * There's no interrupt for clearing bmc busy so we have to
+	 * poll
+	 */
+	if (wait_event_interruptible(bt_bmc->queue,
+				     !(bt_inb(bt_bmc, BT_CTRL) &
+				       (BT_CTRL_H_BUSY | BT_CTRL_B2H_ATN))))
+		return -ERESTARTSYS;
+
+	mutex_lock(&bt_bmc->mutex);
+
+	if (unlikely(bt_inb(bt_bmc, BT_CTRL) &
+		     (BT_CTRL_H_BUSY | BT_CTRL_B2H_ATN))) {
+		ret = -EIO;
+		goto out_unlock;
+	}
+
+	clr_wr_ptr(bt_bmc);
+
+	while (count) {
+		nwritten = min_t(ssize_t, count, sizeof(kbuffer));
+		if (copy_from_user(&kbuffer, buf, nwritten)) {
+			ret = -EFAULT;
+			break;
+		}
+
+		bt_writen(bt_bmc, kbuffer, nwritten);
+
+		count -= nwritten;
+		buf += nwritten;
+		ret += nwritten;
+	}
+
+	set_b2h_atn(bt_bmc);
+
+out_unlock:
+	mutex_unlock(&bt_bmc->mutex);
+	return ret;
+}
+
+static long bt_bmc_ioctl(struct file *file, unsigned int cmd,
+			 unsigned long param)
+{
+	struct bt_bmc *bt_bmc = file_bt_bmc(file);
+
+	switch (cmd) {
+	case BT_BMC_IOCTL_SMS_ATN:
+		set_sms_atn(bt_bmc);
+		return 0;
+	}
+	return -EINVAL;
+}
+
+static int bt_bmc_release(struct inode *inode, struct file *file)
+{
+	struct bt_bmc *bt_bmc = file_bt_bmc(file);
+
+	atomic_dec(&open_count);
+	set_b_busy(bt_bmc);
+	return 0;
+}
+
+static unsigned int bt_bmc_poll(struct file *file, poll_table *wait)
+{
+	struct bt_bmc *bt_bmc = file_bt_bmc(file);
+	unsigned int mask = 0;
+	u8 ctrl;
+
+	poll_wait(file, &bt_bmc->queue, wait);
+
+	ctrl = bt_inb(bt_bmc, BT_CTRL);
+
+	if (ctrl & BT_CTRL_H2B_ATN)
+		mask |= POLLIN;
+
+	if (!(ctrl & (BT_CTRL_H_BUSY | BT_CTRL_B2H_ATN)))
+		mask |= POLLOUT;
+
+	return mask;
+}
+
+static const struct file_operations bt_bmc_fops = {
+	.owner		= THIS_MODULE,
+	.open		= bt_bmc_open,
+	.read		= bt_bmc_read,
+	.write		= bt_bmc_write,
+	.release	= bt_bmc_release,
+	.poll		= bt_bmc_poll,
+	.unlocked_ioctl	= bt_bmc_ioctl,
+};
+
+static void poll_timer(unsigned long data)
+{
+	struct bt_bmc *bt_bmc = (void *)data;
+
+	bt_bmc->poll_timer.expires += msecs_to_jiffies(500);
+	wake_up(&bt_bmc->queue);
+	add_timer(&bt_bmc->poll_timer);
+}
+
+static irqreturn_t bt_bmc_irq(int irq, void *arg)
+{
+	struct bt_bmc *bt_bmc = arg;
+	u32 reg;
+
+	reg = ioread32(bt_bmc->base + BT_CR2);
+	reg &= BT_CR2_IRQ_H2B | BT_CR2_IRQ_HBUSY;
+	if (!reg)
+		return IRQ_NONE;
+
+	/* ack pending IRQs */
+	iowrite32(reg, bt_bmc->base + BT_CR2);
+
+	wake_up(&bt_bmc->queue);
+	return IRQ_HANDLED;
+}
+
+static int bt_bmc_config_irq(struct bt_bmc *bt_bmc,
+			     struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	u32 reg;
+	int rc;
+
+	bt_bmc->irq = platform_get_irq(pdev, 0);
+	if (!bt_bmc->irq)
+		return -ENODEV;
+
+	rc = devm_request_irq(dev, bt_bmc->irq, bt_bmc_irq, IRQF_SHARED,
+			      DEVICE_NAME, bt_bmc);
+	if (rc < 0) {
+		dev_warn(dev, "Unable to request IRQ %d\n", bt_bmc->irq);
+		bt_bmc->irq = 0;
+		return rc;
+	}
+
+	/*
+	 * Configure IRQs on the bmc clearing the H2B and HBUSY bits;
+	 * H2B will be asserted when the bmc has data for us; HBUSY
+	 * will be cleared (along with B2H) when we can write the next
+	 * message to the BT buffer
+	 */
+	reg = ioread32(bt_bmc->base + BT_CR1);
+	reg |= BT_CR1_IRQ_H2B | BT_CR1_IRQ_HBUSY;
+	iowrite32(reg, bt_bmc->base + BT_CR1);
+
+	return 0;
+}
+
+static int bt_bmc_probe(struct platform_device *pdev)
+{
+	struct bt_bmc *bt_bmc;
+	struct device *dev;
+	struct resource *res;
+	int rc;
+
+	if (!pdev || !pdev->dev.of_node)
+		return -ENODEV;
+
+	dev = &pdev->dev;
+	dev_info(dev, "Found bt bmc device\n");
+
+	bt_bmc = devm_kzalloc(dev, sizeof(*bt_bmc), GFP_KERNEL);
+	if (!bt_bmc)
+		return -ENOMEM;
+
+	dev_set_drvdata(&pdev->dev, bt_bmc);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	bt_bmc->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(bt_bmc->base))
+		return PTR_ERR(bt_bmc->base);
+
+	mutex_init(&bt_bmc->mutex);
+	init_waitqueue_head(&bt_bmc->queue);
+
+	bt_bmc->miscdev.minor	= MISC_DYNAMIC_MINOR,
+		bt_bmc->miscdev.name	= DEVICE_NAME,
+		bt_bmc->miscdev.fops	= &bt_bmc_fops,
+		bt_bmc->miscdev.parent = dev;
+	rc = misc_register(&bt_bmc->miscdev);
+	if (rc) {
+		dev_err(dev, "Unable to register misc device\n");
+		return rc;
+	}
+
+	bt_bmc_config_irq(bt_bmc, pdev);
+
+	if (bt_bmc->irq) {
+		dev_info(dev, "Using IRQ %d\n", bt_bmc->irq);
+	} else {
+		dev_info(dev, "No IRQ; using timer\n");
+		setup_timer(&bt_bmc->poll_timer, poll_timer,
+			    (unsigned long)bt_bmc);
+		bt_bmc->poll_timer.expires = jiffies + msecs_to_jiffies(10);
+		add_timer(&bt_bmc->poll_timer);
+	}
+
+	iowrite32((BT_IO_BASE << BT_CR0_IO_BASE) |
+		  (BT_IRQ << BT_CR0_IRQ) |
+		  BT_CR0_EN_CLR_SLV_RDP |
+		  BT_CR0_EN_CLR_SLV_WRP |
+		  BT_CR0_ENABLE_IBT,
+		  bt_bmc->base + BT_CR0);
+
+	clr_b_busy(bt_bmc);
+
+	return 0;
+}
+
+static int bt_bmc_remove(struct platform_device *pdev)
+{
+	struct bt_bmc *bt_bmc = dev_get_drvdata(&pdev->dev);
+
+	misc_deregister(&bt_bmc->miscdev);
+	if (!bt_bmc->irq)
+		del_timer_sync(&bt_bmc->poll_timer);
+	return 0;
+}
+
+static const struct of_device_id bt_bmc_match[] = {
+	{ .compatible = "aspeed,ast2400-bt-bmc" },
+	{ },
+};
+
+static struct platform_driver bt_bmc_driver = {
+	.driver = {
+		.name		= DEVICE_NAME,
+		.of_match_table = bt_bmc_match,
+	},
+	.probe = bt_bmc_probe,
+	.remove = bt_bmc_remove,
+};
+
+module_platform_driver(bt_bmc_driver);
+
+MODULE_DEVICE_TABLE(of, bt_bmc_match);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Alistair Popple <alistair@popple.id.au>");
+MODULE_DESCRIPTION("Linux device interface to the BT interface");

drivers/char/ipmi/ipmi_msghandler.c

@@ -2891,11 +2891,11 @@ int ipmi_register_smi(const struct ipmi_smi_handlers *handlers,
 		intf->curr_channel = IPMI_MAX_CHANNELS;
 	}
 
+	rv = ipmi_bmc_register(intf, i);
+
 	if (rv == 0)
 		rv = add_proc_entries(intf, i);
 
-	rv = ipmi_bmc_register(intf, i);
-
  out:
 	if (rv) {
 		if (intf->proc_dir)
@@ -2982,8 +2982,6 @@ int ipmi_unregister_smi(ipmi_smi_t intf)
 	int intf_num = intf->intf_num;
 	ipmi_user_t user;
 
-	ipmi_bmc_unregister(intf);
-
 	mutex_lock(&smi_watchers_mutex);
 	mutex_lock(&ipmi_interfaces_mutex);
 	intf->intf_num = -1;
@@ -3007,6 +3005,7 @@ int ipmi_unregister_smi(ipmi_smi_t intf)
 	mutex_unlock(&ipmi_interfaces_mutex);
 
 	remove_proc_entries(intf);
+	ipmi_bmc_unregister(intf);
 
 	/*
 	 * Call all the watcher interfaces to tell them that

drivers/clocksource/Kconfig

@@ -417,6 +417,16 @@ config SYS_SUPPORTS_SH_TMU
 config SYS_SUPPORTS_EM_STI
         bool
 
+config CLKSRC_JCORE_PIT
+	bool "J-Core PIT timer driver" if COMPILE_TEST
+	depends on OF
+	depends on GENERIC_CLOCKEVENTS
+	depends on HAS_IOMEM
+	select CLKSRC_MMIO
+	help
+	  This enables build of clocksource and clockevent driver for
+	  the integrated PIT in the J-Core synthesizable, open source SoC.
+
 config SH_TIMER_CMT
 	bool "Renesas CMT timer driver" if COMPILE_TEST
 	depends on GENERIC_CLOCKEVENTS

drivers/clocksource/Makefile

@@ -5,6 +5,7 @@ obj-$(CONFIG_ATMEL_TCB_CLKSRC)	+= tcb_clksrc.o
 obj-$(CONFIG_X86_PM_TIMER)	+= acpi_pm.o
 obj-$(CONFIG_SCx200HR_TIMER)	+= scx200_hrt.o
 obj-$(CONFIG_CS5535_CLOCK_EVENT_SRC)	+= cs5535-clockevt.o
+obj-$(CONFIG_CLKSRC_JCORE_PIT)		+= jcore-pit.o
 obj-$(CONFIG_SH_TIMER_CMT)	+= sh_cmt.o
 obj-$(CONFIG_SH_TIMER_MTU2)	+= sh_mtu2.o
 obj-$(CONFIG_SH_TIMER_TMU)	+= sh_tmu.o

drivers/clocksource/jcore-pit.c

@@ -0,0 +1,249 @@
+/*
+ * J-Core SoC PIT/clocksource driver
+ *
+ * Copyright (C) 2015-2016 Smart Energy Instruments, Inc.
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/clockchips.h>
+#include <linux/clocksource.h>
+#include <linux/sched_clock.h>
+#include <linux/cpu.h>
+#include <linux/cpuhotplug.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+
+#define PIT_IRQ_SHIFT		12
+#define PIT_PRIO_SHIFT		20
+#define PIT_ENABLE_SHIFT	26
+#define PIT_PRIO_MASK		0xf
+
+#define REG_PITEN		0x00
+#define REG_THROT		0x10
+#define REG_COUNT		0x14
+#define REG_BUSPD		0x18
+#define REG_SECHI		0x20
+#define REG_SECLO		0x24
+#define REG_NSEC		0x28
+
+struct jcore_pit {
+	struct clock_event_device	ced;
+	void __iomem			*base;
+	unsigned long			periodic_delta;
+	u32				enable_val;
+};
+
+static void __iomem *jcore_pit_base;
+static struct jcore_pit __percpu *jcore_pit_percpu;
+
+static notrace u64 jcore_sched_clock_read(void)
+{
+	u32 seclo, nsec, seclo0;
+	__iomem void *base = jcore_pit_base;
+
+	seclo = readl(base + REG_SECLO);
+	do {
+		seclo0 = seclo;
+		nsec  = readl(base + REG_NSEC);
+		seclo = readl(base + REG_SECLO);
+	} while (seclo0 != seclo);
+
+	return seclo * NSEC_PER_SEC + nsec;
+}
+
+static cycle_t jcore_clocksource_read(struct clocksource *cs)
+{
+	return jcore_sched_clock_read();
+}
+
+static int jcore_pit_disable(struct jcore_pit *pit)
+{
+	writel(0, pit->base + REG_PITEN);
+	return 0;
+}
+
+static int jcore_pit_set(unsigned long delta, struct jcore_pit *pit)
+{
+	jcore_pit_disable(pit);
+	writel(delta, pit->base + REG_THROT);
+	writel(pit->enable_val, pit->base + REG_PITEN);
+	return 0;
+}
+
+static int jcore_pit_set_state_shutdown(struct clock_event_device *ced)
+{
+	struct jcore_pit *pit = container_of(ced, struct jcore_pit, ced);
+
+	return jcore_pit_disable(pit);
+}
+
+static int jcore_pit_set_state_oneshot(struct clock_event_device *ced)
+{
+	struct jcore_pit *pit = container_of(ced, struct jcore_pit, ced);
+
+	return jcore_pit_disable(pit);
+}
+
+static int jcore_pit_set_state_periodic(struct clock_event_device *ced)
+{
+	struct jcore_pit *pit = container_of(ced, struct jcore_pit, ced);
+
+	return jcore_pit_set(pit->periodic_delta, pit);
+}
+
+static int jcore_pit_set_next_event(unsigned long delta,
+				    struct clock_event_device *ced)
+{
+	struct jcore_pit *pit = container_of(ced, struct jcore_pit, ced);
+
+	return jcore_pit_set(delta, pit);
+}
+
+static int jcore_pit_local_init(unsigned cpu)
+{
+	struct jcore_pit *pit = this_cpu_ptr(jcore_pit_percpu);
+	unsigned buspd, freq;
+
+	pr_info("Local J-Core PIT init on cpu %u\n", cpu);
+
+	buspd = readl(pit->base + REG_BUSPD);
+	freq = DIV_ROUND_CLOSEST(NSEC_PER_SEC, buspd);
+	pit->periodic_delta = DIV_ROUND_CLOSEST(NSEC_PER_SEC, HZ * buspd);
+
+	clockevents_config_and_register(&pit->ced, freq, 1, ULONG_MAX);
+
+	return 0;
+}
+
+static irqreturn_t jcore_timer_interrupt(int irq, void *dev_id)
+{
+	struct jcore_pit *pit = this_cpu_ptr(dev_id);
+
+	if (clockevent_state_oneshot(&pit->ced))
+		jcore_pit_disable(pit);
+
+	pit->ced.event_handler(&pit->ced);
+
+	return IRQ_HANDLED;
+}
+
+static int __init jcore_pit_init(struct device_node *node)
+{
+	int err;
+	unsigned pit_irq, cpu;
+	unsigned long hwirq;
+	u32 irqprio, enable_val;
+
+	jcore_pit_base = of_iomap(node, 0);
+	if (!jcore_pit_base) {
+		pr_err("Error: Cannot map base address for J-Core PIT\n");
+		return -ENXIO;
+	}
+
+	pit_irq = irq_of_parse_and_map(node, 0);
+	if (!pit_irq) {
+		pr_err("Error: J-Core PIT has no IRQ\n");
+		return -ENXIO;
+	}
+
+	pr_info("Initializing J-Core PIT at %p IRQ %d\n",
+		jcore_pit_base, pit_irq);
+
+	err = clocksource_mmio_init(jcore_pit_base, "jcore_pit_cs",
+				    NSEC_PER_SEC, 400, 32,
+				    jcore_clocksource_read);
+	if (err) {
+		pr_err("Error registering clocksource device: %d\n", err);
+		return err;
+	}
+
+	sched_clock_register(jcore_sched_clock_read, 32, NSEC_PER_SEC);
+
+	jcore_pit_percpu = alloc_percpu(struct jcore_pit);
+	if (!jcore_pit_percpu) {
+		pr_err("Failed to allocate memory for clock event device\n");
+		return -ENOMEM;
+	}
+
+	err = request_irq(pit_irq, jcore_timer_interrupt,
+			  IRQF_TIMER | IRQF_PERCPU,
+			  "jcore_pit", jcore_pit_percpu);
+	if (err) {
+		pr_err("pit irq request failed: %d\n", err);
+		free_percpu(jcore_pit_percpu);
+		return err;
+	}
+
+	/*
+	 * The J-Core PIT is not hard-wired to a particular IRQ, but
+	 * integrated with the interrupt controller such that the IRQ it
+	 * generates is programmable, as follows:
+	 *
+	 * The bit layout of the PIT enable register is:
+	 *
+	 *	.....e..ppppiiiiiiii............
+	 *
+	 * where the .'s indicate unrelated/unused bits, e is enable,
+	 * p is priority, and i is hard irq number.
+	 *
+	 * For the PIT included in AIC1 (obsolete but still in use),
+	 * any hard irq (trap number) can be programmed via the 8
+	 * iiiiiiii bits, and a priority (0-15) is programmable
+	 * separately in the pppp bits.
+	 *
+	 * For the PIT included in AIC2 (current), the programming
+	 * interface is equivalent modulo interrupt mapping. This is
+	 * why a different compatible tag was not used. However only
+	 * traps 64-127 (the ones actually intended to be used for
+	 * interrupts, rather than syscalls/exceptions/etc.) can be
+	 * programmed (the high 2 bits of i are ignored) and the
+	 * priority pppp is <<2'd and or'd onto the irq number. This
+	 * choice seems to have been made on the hardware engineering
+	 * side under an assumption that preserving old AIC1 priority
+	 * mappings was important. Future models will likely ignore
+	 * the pppp field.
+	 */
+	hwirq = irq_get_irq_data(pit_irq)->hwirq;
+	irqprio = (hwirq >> 2) & PIT_PRIO_MASK;
+	enable_val = (1U << PIT_ENABLE_SHIFT)
+		   | (hwirq << PIT_IRQ_SHIFT)
+		   | (irqprio << PIT_PRIO_SHIFT);
+
+	for_each_present_cpu(cpu) {
+		struct jcore_pit *pit = per_cpu_ptr(jcore_pit_percpu, cpu);
+
+		pit->base = of_iomap(node, cpu);
+		if (!pit->base) {
+			pr_err("Unable to map PIT for cpu %u\n", cpu);
+			continue;
+		}
+
+		pit->ced.name = "jcore_pit";
+		pit->ced.features = CLOCK_EVT_FEAT_PERIODIC
+				  | CLOCK_EVT_FEAT_ONESHOT
+				  | CLOCK_EVT_FEAT_PERCPU;
+		pit->ced.cpumask = cpumask_of(cpu);
+		pit->ced.rating = 400;
+		pit->ced.irq = pit_irq;
+		pit->ced.set_state_shutdown = jcore_pit_set_state_shutdown;
+		pit->ced.set_state_periodic = jcore_pit_set_state_periodic;
+		pit->ced.set_state_oneshot = jcore_pit_set_state_oneshot;
+		pit->ced.set_next_event = jcore_pit_set_next_event;
+
+		pit->enable_val = enable_val;
+	}
+
+	cpuhp_setup_state(CPUHP_AP_JCORE_TIMER_STARTING,
+			  "AP_JCORE_TIMER_STARTING",
+			  jcore_pit_local_init, NULL);
+
+	return 0;
+}
+
+CLOCKSOURCE_OF_DECLARE(jcore_pit, "jcore,pit", jcore_pit_init);

drivers/clocksource/timer-sun5i.c

@@ -152,6 +152,13 @@ static irqreturn_t sun5i_timer_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+static cycle_t sun5i_clksrc_read(struct clocksource *clksrc)
+{
+	struct sun5i_timer_clksrc *cs = to_sun5i_timer_clksrc(clksrc);
+
+	return ~readl(cs->timer.base + TIMER_CNTVAL_LO_REG(1));
+}
+
 static int sun5i_rate_cb_clksrc(struct notifier_block *nb,
 				unsigned long event, void *data)
 {
@@ -210,8 +217,13 @@ static int __init sun5i_setup_clocksource(struct device_node *node,
 	writel(TIMER_CTL_ENABLE | TIMER_CTL_RELOAD,
 	       base + TIMER_CTL_REG(1));
 
-	ret = clocksource_mmio_init(base + TIMER_CNTVAL_LO_REG(1), node->name,
-				    rate, 340, 32, clocksource_mmio_readl_down);
+	cs->clksrc.name = node->name;
+	cs->clksrc.rating = 340;
+	cs->clksrc.read = sun5i_clksrc_read;
+	cs->clksrc.mask = CLOCKSOURCE_MASK(32);
+	cs->clksrc.flags = CLOCK_SOURCE_IS_CONTINUOUS;
+
+	ret = clocksource_register_hz(&cs->clksrc, rate);
 	if (ret) {
 		pr_err("Couldn't register clock source.\n");
 		goto err_remove_notifier;

drivers/firewire/nosy.c

@@ -566,6 +566,11 @@ add_card(struct pci_dev *dev, const struct pci_device_id *unused)
 
 	lynx->registers = ioremap_nocache(pci_resource_start(dev, 0),
 					  PCILYNX_MAX_REGISTER);
+	if (lynx->registers == NULL) {
+		dev_err(&dev->dev, "Failed to map registers\n");
+		ret = -ENOMEM;
+		goto fail_deallocate_lynx;
+	}
 
 	lynx->rcv_start_pcl = pci_alloc_consistent(lynx->pci_device,
 				sizeof(struct pcl), &lynx->rcv_start_pcl_bus);
@@ -578,7 +583,7 @@ add_card(struct pci_dev *dev, const struct pci_device_id *unused)
 	    lynx->rcv_buffer == NULL) {
 		dev_err(&dev->dev, "Failed to allocate receive buffer\n");
 		ret = -ENOMEM;
-		goto fail_deallocate;
+		goto fail_deallocate_buffers;
 	}
 	lynx->rcv_start_pcl->next	= cpu_to_le32(lynx->rcv_pcl_bus);
 	lynx->rcv_pcl->next		= cpu_to_le32(PCL_NEXT_INVALID);
@@ -641,7 +646,7 @@ add_card(struct pci_dev *dev, const struct pci_device_id *unused)
 		dev_err(&dev->dev,
 			"Failed to allocate shared interrupt %d\n", dev->irq);
 		ret = -EIO;
-		goto fail_deallocate;
+		goto fail_deallocate_buffers;
 	}
 
 	lynx->misc.parent = &dev->dev;
@@ -668,7 +673,7 @@ fail_free_irq:
 	reg_write(lynx, PCI_INT_ENABLE, 0);
 	free_irq(lynx->pci_device->irq, lynx);
 
-fail_deallocate:
+fail_deallocate_buffers:
 	if (lynx->rcv_start_pcl)
 		pci_free_consistent(lynx->pci_device, sizeof(struct pcl),
 				lynx->rcv_start_pcl, lynx->rcv_start_pcl_bus);
@@ -679,6 +684,8 @@ fail_deallocate:
 		pci_free_consistent(lynx->pci_device, PAGE_SIZE,
 				lynx->rcv_buffer, lynx->rcv_buffer_bus);
 	iounmap(lynx->registers);
+
+fail_deallocate_lynx:
 	kfree(lynx);
 
 fail_disable:

drivers/firmware/efi/libstub/Makefile

@@ -11,7 +11,7 @@ cflags-$(CONFIG_X86)		+= -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2 \
 				   -mno-mmx -mno-sse
 
 cflags-$(CONFIG_ARM64)		:= $(subst -pg,,$(KBUILD_CFLAGS))
-cflags-$(CONFIG_ARM)		:= $(subst -pg,,$(KBUILD_CFLAGS)) \
+cflags-$(CONFIG_ARM)		:= $(subst -pg,,$(KBUILD_CFLAGS)) -g0 \
 				   -fno-builtin -fpic -mno-single-pic-base
 
 cflags-$(CONFIG_EFI_ARMSTUB)	+= -I$(srctree)/scripts/dtc/libfdt
@@ -79,5 +79,6 @@ quiet_cmd_stubcopy = STUBCPY $@
 # decompressor. So move our .data to .data.efistub, which is preserved
 # explicitly by the decompressor linker script.
 #
-STUBCOPY_FLAGS-$(CONFIG_ARM)	+= --rename-section .data=.data.efistub
+STUBCOPY_FLAGS-$(CONFIG_ARM)	+= --rename-section .data=.data.efistub \
+				   -R ___ksymtab+sort -R ___kcrctab+sort
 STUBCOPY_RELOC-$(CONFIG_ARM)	:= R_ARM_ABS

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

@@ -765,7 +765,7 @@ amdgpu_connector_lvds_detect(struct drm_connector *connector, bool force)
 	return ret;
 }
 
-static void amdgpu_connector_destroy(struct drm_connector *connector)
+static void amdgpu_connector_unregister(struct drm_connector *connector)
 {
 	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 
@@ -773,6 +773,12 @@ static void amdgpu_connector_destroy(struct drm_connector *connector)
 		drm_dp_aux_unregister(&amdgpu_connector->ddc_bus->aux);
 		amdgpu_connector->ddc_bus->has_aux = false;
 	}
+}
+
+static void amdgpu_connector_destroy(struct drm_connector *connector)
+{
+	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
+
 	amdgpu_connector_free_edid(connector);
 	kfree(amdgpu_connector->con_priv);
 	drm_connector_unregister(connector);
@@ -826,6 +832,7 @@ static const struct drm_connector_funcs amdgpu_connector_lvds_funcs = {
 	.dpms = drm_helper_connector_dpms,
 	.detect = amdgpu_connector_lvds_detect,
 	.fill_modes = drm_helper_probe_single_connector_modes,
+	.early_unregister = amdgpu_connector_unregister,
 	.destroy = amdgpu_connector_destroy,
 	.set_property = amdgpu_connector_set_lcd_property,
 };
@@ -936,6 +943,7 @@ static const struct drm_connector_funcs amdgpu_connector_vga_funcs = {
 	.dpms = drm_helper_connector_dpms,
 	.detect = amdgpu_connector_vga_detect,
 	.fill_modes = drm_helper_probe_single_connector_modes,
+	.early_unregister = amdgpu_connector_unregister,
 	.destroy = amdgpu_connector_destroy,
 	.set_property = amdgpu_connector_set_property,
 };
@@ -1203,6 +1211,7 @@ static const struct drm_connector_funcs amdgpu_connector_dvi_funcs = {
 	.detect = amdgpu_connector_dvi_detect,
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.set_property = amdgpu_connector_set_property,
+	.early_unregister = amdgpu_connector_unregister,
 	.destroy = amdgpu_connector_destroy,
 	.force = amdgpu_connector_dvi_force,
 };
@@ -1493,6 +1502,7 @@ static const struct drm_connector_funcs amdgpu_connector_dp_funcs = {
 	.detect = amdgpu_connector_dp_detect,
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.set_property = amdgpu_connector_set_property,
+	.early_unregister = amdgpu_connector_unregister,
 	.destroy = amdgpu_connector_destroy,
 	.force = amdgpu_connector_dvi_force,
 };
@@ -1502,6 +1512,7 @@ static const struct drm_connector_funcs amdgpu_connector_edp_funcs = {
 	.detect = amdgpu_connector_dp_detect,
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.set_property = amdgpu_connector_set_lcd_property,
+	.early_unregister = amdgpu_connector_unregister,
 	.destroy = amdgpu_connector_destroy,
 	.force = amdgpu_connector_dvi_force,
 };

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

@@ -43,6 +43,9 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev, struct amdgpu_ctx *ctx)
 		ctx->rings[i].sequence = 1;
 		ctx->rings[i].fences = &ctx->fences[amdgpu_sched_jobs * i];
 	}
+
+	ctx->reset_counter = atomic_read(&adev->gpu_reset_counter);
+
 	/* create context entity for each ring */
 	for (i = 0; i < adev->num_rings; i++) {
 		struct amdgpu_ring *ring = adev->rings[i];

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

@@ -1408,16 +1408,6 @@ static int amdgpu_late_init(struct amdgpu_device *adev)
 	for (i = 0; i < adev->num_ip_blocks; i++) {
 		if (!adev->ip_block_status[i].valid)
 			continue;
-		if (adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_UVD ||
-			adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_VCE)
-			continue;
-		/* enable clockgating to save power */
-		r = adev->ip_blocks[i].funcs->set_clockgating_state((void *)adev,
-								    AMD_CG_STATE_GATE);
-		if (r) {
-			DRM_ERROR("set_clockgating_state(gate) of IP block <%s> failed %d\n", adev->ip_blocks[i].funcs->name, r);
-			return r;
-		}
 		if (adev->ip_blocks[i].funcs->late_init) {
 			r = adev->ip_blocks[i].funcs->late_init((void *)adev);
 			if (r) {
@@ -1426,6 +1416,18 @@ static int amdgpu_late_init(struct amdgpu_device *adev)
 			}
 			adev->ip_block_status[i].late_initialized = true;
 		}
+		/* skip CG for VCE/UVD, it's handled specially */
+		if (adev->ip_blocks[i].type != AMD_IP_BLOCK_TYPE_UVD &&
+		    adev->ip_blocks[i].type != AMD_IP_BLOCK_TYPE_VCE) {
+			/* enable clockgating to save power */
+			r = adev->ip_blocks[i].funcs->set_clockgating_state((void *)adev,
+									    AMD_CG_STATE_GATE);
+			if (r) {
+				DRM_ERROR("set_clockgating_state(gate) of IP block <%s> failed %d\n",
+					  adev->ip_blocks[i].funcs->name, r);
+				return r;
+			}
+		}
 	}
 
 	return 0;
@@ -1435,6 +1437,30 @@ static int amdgpu_fini(struct amdgpu_device *adev)
 {
 	int i, r;
 
+	/* need to disable SMC first */
+	for (i = 0; i < adev->num_ip_blocks; i++) {
+		if (!adev->ip_block_status[i].hw)
+			continue;
+		if (adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_SMC) {
+			/* ungate blocks before hw fini so that we can shutdown the blocks safely */
+			r = adev->ip_blocks[i].funcs->set_clockgating_state((void *)adev,
+									    AMD_CG_STATE_UNGATE);
+			if (r) {
+				DRM_ERROR("set_clockgating_state(ungate) of IP block <%s> failed %d\n",
+					  adev->ip_blocks[i].funcs->name, r);
+				return r;
+			}
+			r = adev->ip_blocks[i].funcs->hw_fini((void *)adev);
+			/* XXX handle errors */
+			if (r) {
+				DRM_DEBUG("hw_fini of IP block <%s> failed %d\n",
+					  adev->ip_blocks[i].funcs->name, r);
+			}
+			adev->ip_block_status[i].hw = false;
+			break;
+		}
+	}
+
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
 		if (!adev->ip_block_status[i].hw)
 			continue;
@@ -2073,7 +2099,8 @@ static bool amdgpu_check_soft_reset(struct amdgpu_device *adev)
 		if (!adev->ip_block_status[i].valid)
 			continue;
 		if (adev->ip_blocks[i].funcs->check_soft_reset)
-			adev->ip_blocks[i].funcs->check_soft_reset(adev);
+			adev->ip_block_status[i].hang =
+				adev->ip_blocks[i].funcs->check_soft_reset(adev);
 		if (adev->ip_block_status[i].hang) {
 			DRM_INFO("IP block:%d is hang!\n", i);
 			asic_hang = true;
@@ -2102,12 +2129,20 @@ static int amdgpu_pre_soft_reset(struct amdgpu_device *adev)
 
 static bool amdgpu_need_full_reset(struct amdgpu_device *adev)
 {
-	if (adev->ip_block_status[AMD_IP_BLOCK_TYPE_GMC].hang ||
-	    adev->ip_block_status[AMD_IP_BLOCK_TYPE_SMC].hang ||
-	    adev->ip_block_status[AMD_IP_BLOCK_TYPE_ACP].hang ||
-	    adev->ip_block_status[AMD_IP_BLOCK_TYPE_DCE].hang) {
-		DRM_INFO("Some block need full reset!\n");
-		return true;
+	int i;
+
+	for (i = 0; i < adev->num_ip_blocks; i++) {
+		if (!adev->ip_block_status[i].valid)
+			continue;
+		if ((adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_GMC) ||
+		    (adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_SMC) ||
+		    (adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_ACP) ||
+		    (adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_DCE)) {
+			if (adev->ip_block_status[i].hang) {
+				DRM_INFO("Some block need full reset!\n");
+				return true;
+			}
+		}
 	}
 	return false;
 }

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

@@ -113,24 +113,26 @@ void amdgpu_dpm_print_ps_status(struct amdgpu_device *adev,
 	printk("\n");
 }
 
+
 u32 amdgpu_dpm_get_vblank_time(struct amdgpu_device *adev)
 {
 	struct drm_device *dev = adev->ddev;
 	struct drm_crtc *crtc;
 	struct amdgpu_crtc *amdgpu_crtc;
-	u32 line_time_us, vblank_lines;
+	u32 vblank_in_pixels;
 	u32 vblank_time_us = 0xffffffff; /* if the displays are off, vblank time is max */
 
 	if (adev->mode_info.num_crtc && adev->mode_info.mode_config_initialized) {
 		list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
 			amdgpu_crtc = to_amdgpu_crtc(crtc);
 			if (crtc->enabled && amdgpu_crtc->enabled && amdgpu_crtc->hw_mode.clock) {
-				line_time_us = (amdgpu_crtc->hw_mode.crtc_htotal * 1000) /
-					amdgpu_crtc->hw_mode.clock;
-				vblank_lines = amdgpu_crtc->hw_mode.crtc_vblank_end -
+				vblank_in_pixels =
+					amdgpu_crtc->hw_mode.crtc_htotal *
+					(amdgpu_crtc->hw_mode.crtc_vblank_end -
 					amdgpu_crtc->hw_mode.crtc_vdisplay +
-					(amdgpu_crtc->v_border * 2);
-				vblank_time_us = vblank_lines * line_time_us;
+					(amdgpu_crtc->v_border * 2));
+
+				vblank_time_us = vblank_in_pixels * 1000 / amdgpu_crtc->hw_mode.clock;
 				break;
 			}
 		}

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

@@ -345,8 +345,8 @@ static int amdgpu_debugfs_ring_init(struct amdgpu_device *adev,
 	ent = debugfs_create_file(name,
 				  S_IFREG | S_IRUGO, root,
 				  ring, &amdgpu_debugfs_ring_fops);
-	if (IS_ERR(ent))
-		return PTR_ERR(ent);
+	if (!ent)
+		return -ENOMEM;
 
 	i_size_write(ent->d_inode, ring->ring_size + 12);
 	ring->ent = ent;

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

@@ -555,10 +555,13 @@ struct amdgpu_ttm_tt {
 int amdgpu_ttm_tt_get_user_pages(struct ttm_tt *ttm, struct page **pages)
 {
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
-	int write = !(gtt->userflags & AMDGPU_GEM_USERPTR_READONLY);
+	unsigned int flags = 0;
 	unsigned pinned = 0;
 	int r;
 
+	if (!(gtt->userflags & AMDGPU_GEM_USERPTR_READONLY))
+		flags |= FOLL_WRITE;
+
 	if (gtt->userflags & AMDGPU_GEM_USERPTR_ANONONLY) {
 		/* check that we only use anonymous memory
 		   to prevent problems with writeback */
@@ -581,7 +584,7 @@ int amdgpu_ttm_tt_get_user_pages(struct ttm_tt *ttm, struct page **pages)
 		list_add(&guptask.list, &gtt->guptasks);
 		spin_unlock(&gtt->guptasklock);
 
-		r = get_user_pages(userptr, num_pages, write, 0, p, NULL);
+		r = get_user_pages(userptr, num_pages, flags, p, NULL);
 
 		spin_lock(&gtt->guptasklock);
 		list_del(&guptask.list);