Merge 4.9.78 into android-4.9

Changes in 4.9.78
	libnvdimm, btt: Fix an incompatibility in the log layout
	scsi: sg: disable SET_FORCE_LOW_DMA
	futex: Prevent overflow by strengthen input validation
	ALSA: seq: Make ioctls race-free
	ALSA: pcm: Remove yet superfluous WARN_ON()
	ALSA: hda - Apply headphone noise quirk for another Dell XPS 13 variant
	ALSA: hda - Apply the existing quirk to iMac 14,1
	timers: Unconditionally check deferrable base
	af_key: fix buffer overread in verify_address_len()
	af_key: fix buffer overread in parse_exthdrs()
	iser-target: Fix possible use-after-free in connection establishment error
	scsi: hpsa: fix volume offline state
	sched/deadline: Zero out positive runtime after throttling constrained tasks
	x86/retpoline: Fill RSB on context switch for affected CPUs
	x86/retpoline: Add LFENCE to the retpoline/RSB filling RSB macros
	objtool: Improve error message for bad file argument
	x86/cpufeature: Move processor tracing out of scattered features
	module: Add retpoline tag to VERMAGIC
	x86/mm/pkeys: Fix fill_sig_info_pkey
	x86/tsc: Fix erroneous TSC rate on Skylake Xeon
	pipe: avoid round_pipe_size() nr_pages overflow on 32-bit
	x86/apic/vector: Fix off by one in error path
	perf tools: Fix build with ARCH=x86_64
	Input: ALPS - fix multi-touch decoding on SS4 plus touchpads
	Input: 88pm860x-ts - fix child-node lookup
	Input: twl6040-vibra - fix child-node lookup
	Input: twl4030-vibra - fix sibling-node lookup
	tracing: Fix converting enum's from the map in trace_event_eval_update()
	phy: work around 'phys' references to usb-nop-xceiv devices
	ARM: sunxi_defconfig: Enable CMA
	ARM: dts: kirkwood: fix pin-muxing of MPP7 on OpenBlocks A7
	can: peak: fix potential bug in packet fragmentation
	scripts/gdb/linux/tasks.py: fix get_thread_info
	proc: fix coredump vs read /proc/*/stat race
	libata: apply MAX_SEC_1024 to all LITEON EP1 series devices
	workqueue: avoid hard lockups in show_workqueue_state()
	dm btree: fix serious bug in btree_split_beneath()
	dm thin metadata: THIN_MAX_CONCURRENT_LOCKS should be 6
	arm64: KVM: Fix SMCCC handling of unimplemented SMC/HVC calls
	x86/cpu, x86/pti: Do not enable PTI on AMD processors
	usbip: fix warning in vhci_hcd_probe/lockdep_init_map
	x86/mce: Make machine check speculation protected
	retpoline: Introduce start/end markers of indirect thunk
	kprobes/x86: Blacklist indirect thunk functions for kprobes
	kprobes/x86: Disable optimizing on the function jumps to indirect thunk
	x86/pti: Document fix wrong index
	x86/retpoline: Optimize inline assembler for vmexit_fill_RSB
	MIPS: AR7: ensure the port type's FCR value is used
	Linux 4.9.78

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
diff --git a/Documentation/x86/pti.txt b/Documentation/x86/pti.txt
index d11eff6..5cd5843 100644
--- a/Documentation/x86/pti.txt
+++ b/Documentation/x86/pti.txt
@@ -78,7 +78,7 @@
      non-PTI SYSCALL entry code, so requires mapping fewer
      things into the userspace page tables.  The downside is
      that stacks must be switched at entry time.
-  d. Global pages are disabled for all kernel structures not
+  c. Global pages are disabled for all kernel structures not
      mapped into both kernel and userspace page tables.  This
      feature of the MMU allows different processes to share TLB
      entries mapping the kernel.  Losing the feature means more
diff --git a/Makefile b/Makefile
index 6637bde..e2a838c 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 9
-SUBLEVEL = 77
+SUBLEVEL = 78
 EXTRAVERSION =
 NAME = Roaring Lionus
 
diff --git a/arch/arm/boot/dts/kirkwood-openblocks_a7.dts b/arch/arm/boot/dts/kirkwood-openblocks_a7.dts
index cf2f524..27cc913 100644
--- a/arch/arm/boot/dts/kirkwood-openblocks_a7.dts
+++ b/arch/arm/boot/dts/kirkwood-openblocks_a7.dts
@@ -53,7 +53,8 @@
 		};
 
 		pinctrl: pin-controller@10000 {
-			pinctrl-0 = <&pmx_dip_switches &pmx_gpio_header>;
+			pinctrl-0 = <&pmx_dip_switches &pmx_gpio_header
+				     &pmx_gpio_header_gpo>;
 			pinctrl-names = "default";
 
 			pmx_uart0: pmx-uart0 {
@@ -85,11 +86,16 @@
 			 * ground.
 			 */
 			pmx_gpio_header: pmx-gpio-header {
-				marvell,pins = "mpp17", "mpp7", "mpp29", "mpp28",
+				marvell,pins = "mpp17", "mpp29", "mpp28",
 					       "mpp35", "mpp34", "mpp40";
 				marvell,function = "gpio";
 			};
 
+			pmx_gpio_header_gpo: pxm-gpio-header-gpo {
+				marvell,pins = "mpp7";
+				marvell,function = "gpo";
+			};
+
 			pmx_gpio_init: pmx-init {
 				marvell,pins = "mpp38";
 				marvell,function = "gpio";
diff --git a/arch/arm/configs/sunxi_defconfig b/arch/arm/configs/sunxi_defconfig
index 714da33..5d49b60 100644
--- a/arch/arm/configs/sunxi_defconfig
+++ b/arch/arm/configs/sunxi_defconfig
@@ -11,6 +11,7 @@
 CONFIG_NR_CPUS=8
 CONFIG_AEABI=y
 CONFIG_HIGHMEM=y
+CONFIG_CMA=y
 CONFIG_ARM_APPENDED_DTB=y
 CONFIG_ARM_ATAG_DTB_COMPAT=y
 CONFIG_CPU_FREQ=y
@@ -35,6 +36,7 @@
 # CONFIG_WIRELESS is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
+CONFIG_DMA_CMA=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_ATA=y
 CONFIG_AHCI_SUNXI=y
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 85baada..2e6e9e9 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -44,7 +44,7 @@
 
 	ret = kvm_psci_call(vcpu);
 	if (ret < 0) {
-		kvm_inject_undefined(vcpu);
+		vcpu_set_reg(vcpu, 0, ~0UL);
 		return 1;
 	}
 
@@ -53,7 +53,7 @@
 
 static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	kvm_inject_undefined(vcpu);
+	vcpu_set_reg(vcpu, 0, ~0UL);
 	return 1;
 }
 
diff --git a/arch/mips/ar7/platform.c b/arch/mips/ar7/platform.c
index 3446b6f..9da4e22 100644
--- a/arch/mips/ar7/platform.c
+++ b/arch/mips/ar7/platform.c
@@ -576,7 +576,7 @@
 	uart_port.type		= PORT_AR7;
 	uart_port.uartclk	= clk_get_rate(bus_clk) / 2;
 	uart_port.iotype	= UPIO_MEM32;
-	uart_port.flags		= UPF_FIXED_TYPE;
+	uart_port.flags		= UPF_FIXED_TYPE | UPF_BOOT_AUTOCONF;
 	uart_port.regshift	= 2;
 
 	uart_port.line		= 0;
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index bdc9aea..a76dc73 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -229,6 +229,17 @@
 	movl	%ebx, PER_CPU_VAR(stack_canary)+stack_canary_offset
 #endif
 
+#ifdef CONFIG_RETPOLINE
+	/*
+	 * When switching from a shallower to a deeper call stack
+	 * the RSB may either underflow or use entries populated
+	 * with userspace addresses. On CPUs where those concerns
+	 * exist, overwrite the RSB with entries which capture
+	 * speculative execution to prevent attack.
+	 */
+	FILL_RETURN_BUFFER %ebx, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
+#endif
+
 	/* restore callee-saved registers */
 	popl	%esi
 	popl	%edi
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index dbe27ce..56297bb 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -427,6 +427,17 @@
 	movq	%rbx, PER_CPU_VAR(irq_stack_union)+stack_canary_offset
 #endif
 
+#ifdef CONFIG_RETPOLINE
+	/*
+	 * When switching from a shallower to a deeper call stack
+	 * the RSB may either underflow or use entries populated
+	 * with userspace addresses. On CPUs where those concerns
+	 * exist, overwrite the RSB with entries which capture
+	 * speculative execution to prevent attack.
+	 */
+	FILL_RETURN_BUFFER %r12, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
+#endif
+
 	/* restore callee-saved registers */
 	popq	%r15
 	popq	%r14
@@ -1048,7 +1059,7 @@
 #endif
 
 #ifdef CONFIG_X86_MCE
-idtentry machine_check					has_error_code=0	paranoid=1 do_sym=*machine_check_vector(%rip)
+idtentry machine_check		do_mce			has_error_code=0	paranoid=1
 #endif
 
 /*
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 4467568..8537a21 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -197,9 +197,9 @@
 #define X86_FEATURE_RETPOLINE	( 7*32+12) /* Generic Retpoline mitigation for Spectre variant 2 */
 #define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* AMD Retpoline mitigation for Spectre variant 2 */
 
-#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 */
+#define X86_FEATURE_RSB_CTXSW		( 7*32+19) /* Fill RSB on context switches */
 
 /* Because the ALTERNATIVE scheme is for members of the X86_FEATURE club... */
 #define X86_FEATURE_KAISER	( 7*32+31) /* CONFIG_PAGE_TABLE_ISOLATION w/o nokaiser */
@@ -235,6 +235,7 @@
 #define X86_FEATURE_SMAP	( 9*32+20) /* Supervisor Mode Access Prevention */
 #define X86_FEATURE_CLFLUSHOPT	( 9*32+23) /* CLFLUSHOPT instruction */
 #define X86_FEATURE_CLWB	( 9*32+24) /* CLWB instruction */
+#define X86_FEATURE_INTEL_PT	( 9*32+25) /* Intel Processor Trace */
 #define X86_FEATURE_AVX512PF	( 9*32+26) /* AVX-512 Prefetch */
 #define X86_FEATURE_AVX512ER	( 9*32+27) /* AVX-512 Exponential and Reciprocal */
 #define X86_FEATURE_AVX512CD	( 9*32+28) /* AVX-512 Conflict Detection */
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 402a11c..4ad4108 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -11,7 +11,7 @@
  * Fill the CPU return stack buffer.
  *
  * Each entry in the RSB, if used for a speculative 'ret', contains an
- * infinite 'pause; jmp' loop to capture speculative execution.
+ * infinite 'pause; lfence; jmp' loop to capture speculative execution.
  *
  * This is required in various cases for retpoline and IBRS-based
  * mitigations for the Spectre variant 2 vulnerability. Sometimes to
@@ -38,11 +38,13 @@
 	call	772f;				\
 773:	/* speculation trap */			\
 	pause;					\
+	lfence;					\
 	jmp	773b;				\
 772:						\
 	call	774f;				\
 775:	/* speculation trap */			\
 	pause;					\
+	lfence;					\
 	jmp	775b;				\
 774:						\
 	dec	reg;				\
@@ -73,6 +75,7 @@
 	call	.Ldo_rop_\@
 .Lspec_trap_\@:
 	pause
+	lfence
 	jmp	.Lspec_trap_\@
 .Ldo_rop_\@:
 	mov	\reg, (%_ASM_SP)
@@ -165,6 +168,7 @@
 	"       .align 16\n"					\
 	"901:	call   903f;\n"					\
 	"902:	pause;\n"					\
+	"    	lfence;\n"					\
 	"       jmp    902b;\n"					\
 	"       .align 16\n"					\
 	"903:	addl   $4, %%esp;\n"				\
@@ -190,6 +194,9 @@
 	SPECTRE_V2_IBRS,
 };
 
+extern char __indirect_thunk_start[];
+extern char __indirect_thunk_end[];
+
 /*
  * On VMEXIT we must ensure that no RSB predictions learned in the guest
  * can be followed in the host, by overwriting the RSB completely. Both
@@ -199,16 +206,17 @@
 static inline void vmexit_fill_RSB(void)
 {
 #ifdef CONFIG_RETPOLINE
-	unsigned long loops = RSB_CLEAR_LOOPS / 2;
+	unsigned long loops;
 
 	asm volatile (ANNOTATE_NOSPEC_ALTERNATIVE
 		      ALTERNATIVE("jmp 910f",
 				  __stringify(__FILL_RETURN_BUFFER(%0, RSB_CLEAR_LOOPS, %1)),
 				  X86_FEATURE_RETPOLINE)
 		      "910:"
-		      : "=&r" (loops), ASM_CALL_CONSTRAINT
-		      : "r" (loops) : "memory" );
+		      : "=r" (loops), ASM_CALL_CONSTRAINT
+		      : : "memory" );
 #endif
 }
+
 #endif /* __ASSEMBLY__ */
 #endif /* __NOSPEC_BRANCH_H__ */
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 01fd0a7..688315b 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -92,6 +92,7 @@
 #ifdef CONFIG_X86_32
 dotraplinkage void do_iret_error(struct pt_regs *, long);
 #endif
+dotraplinkage void do_mce(struct pt_regs *, long);
 
 static inline int get_si_code(unsigned long condition)
 {
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index f3557a1..b5229ab 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -361,14 +361,17 @@
 		irq_data->chip_data = data;
 		irq_data->hwirq = virq + i;
 		err = assign_irq_vector_policy(virq + i, node, data, info);
-		if (err)
+		if (err) {
+			irq_data->chip_data = NULL;
+			free_apic_chip_data(data);
 			goto error;
+		}
 	}
 
 	return 0;
 
 error:
-	x86_vector_free_irqs(domain, virq, i + 1);
+	x86_vector_free_irqs(domain, virq, i);
 	return err;
 }
 
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 49d25dd..8cacf62 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -22,6 +22,7 @@
 #include <asm/alternative.h>
 #include <asm/pgtable.h>
 #include <asm/cacheflush.h>
+#include <asm/intel-family.h>
 
 static void __init spectre_v2_select_mitigation(void);
 
@@ -154,6 +155,23 @@
 	return SPECTRE_V2_CMD_NONE;
 }
 
+/* Check for Skylake-like CPUs (for RSB handling) */
+static bool __init is_skylake_era(void)
+{
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
+	    boot_cpu_data.x86 == 6) {
+		switch (boot_cpu_data.x86_model) {
+		case INTEL_FAM6_SKYLAKE_MOBILE:
+		case INTEL_FAM6_SKYLAKE_DESKTOP:
+		case INTEL_FAM6_SKYLAKE_X:
+		case INTEL_FAM6_KABYLAKE_MOBILE:
+		case INTEL_FAM6_KABYLAKE_DESKTOP:
+			return true;
+		}
+	}
+	return false;
+}
+
 static void __init spectre_v2_select_mitigation(void)
 {
 	enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline();
@@ -212,6 +230,24 @@
 
 	spectre_v2_enabled = mode;
 	pr_info("%s\n", spectre_v2_strings[mode]);
+
+	/*
+	 * If neither SMEP or KPTI are available, there is a risk of
+	 * hitting userspace addresses in the RSB after a context switch
+	 * from a shallow call stack to a deeper one. To prevent this fill
+	 * the entire RSB, even when using IBRS.
+	 *
+	 * Skylake era CPUs have a separate issue with *underflow* of the
+	 * RSB, when they will predict 'ret' targets from the generic BTB.
+	 * The proper mitigation for this is IBRS. If IBRS is not supported
+	 * or deactivated in favour of retpolines the RSB fill on context
+	 * switch is required.
+	 */
+	if ((!boot_cpu_has(X86_FEATURE_KAISER) &&
+	     !boot_cpu_has(X86_FEATURE_SMEP)) || is_skylake_era()) {
+		setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
+		pr_info("Filling RSB on context switch\n");
+	}
 }
 
 #undef pr_fmt
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 7b9ae04..d198ae0 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -883,8 +883,8 @@
 
 	setup_force_cpu_cap(X86_FEATURE_ALWAYS);
 
-	/* Assume for now that ALL x86 CPUs are insecure */
-	setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
+	if (c->x86_vendor != X86_VENDOR_AMD)
+		setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
 
 	setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
 	setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 8ca5f8a..fe5cd6e 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1754,6 +1754,11 @@
 void (*machine_check_vector)(struct pt_regs *, long error_code) =
 						unexpected_machine_check;
 
+dotraplinkage void do_mce(struct pt_regs *regs, long error_code)
+{
+	machine_check_vector(regs, error_code);
+}
+
 /*
  * Called for each booted CPU to set up machine checks.
  * Must be called with preempt off:
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 1db8dc4..b0dd9ae 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -31,7 +31,6 @@
 	const struct cpuid_bit *cb;
 
 	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 },
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 4d74f73..dc20da1 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -37,6 +37,7 @@
 #include <asm/alternative.h>
 #include <asm/insn.h>
 #include <asm/debugreg.h>
+#include <asm/nospec-branch.h>
 
 #include "common.h"
 
@@ -192,7 +193,7 @@
 }
 
 /* Check whether insn is indirect jump */
-static int insn_is_indirect_jump(struct insn *insn)
+static int __insn_is_indirect_jump(struct insn *insn)
 {
 	return ((insn->opcode.bytes[0] == 0xff &&
 		(X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */
@@ -226,6 +227,26 @@
 	return (start <= target && target <= start + len);
 }
 
+static int insn_is_indirect_jump(struct insn *insn)
+{
+	int ret = __insn_is_indirect_jump(insn);
+
+#ifdef CONFIG_RETPOLINE
+	/*
+	 * Jump to x86_indirect_thunk_* is treated as an indirect jump.
+	 * Note that even with CONFIG_RETPOLINE=y, the kernel compiled with
+	 * older gcc may use indirect jump. So we add this check instead of
+	 * replace indirect-jump check.
+	 */
+	if (!ret)
+		ret = insn_jump_into_range(insn,
+				(unsigned long)__indirect_thunk_start,
+				(unsigned long)__indirect_thunk_end -
+				(unsigned long)__indirect_thunk_start);
+#endif
+	return ret;
+}
+
 /* Decode whole function to ensure any instructions don't jump into target */
 static int can_optimize(unsigned long paddr)
 {
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 44bf5cf..d07a9390 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -693,7 +693,6 @@
 		case INTEL_FAM6_KABYLAKE_DESKTOP:
 			crystal_khz = 24000;	/* 24.0 MHz */
 			break;
-		case INTEL_FAM6_SKYLAKE_X:
 		case INTEL_FAM6_ATOM_DENVERTON:
 			crystal_khz = 25000;	/* 25.0 MHz */
 			break;
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index dbf67f6..c7194e9 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -105,6 +105,13 @@
 		SOFTIRQENTRY_TEXT
 		*(.fixup)
 		*(.gnu.warning)
+
+#ifdef CONFIG_RETPOLINE
+		__indirect_thunk_start = .;
+		*(.text.__x86.indirect_thunk)
+		__indirect_thunk_end = .;
+#endif
+
 		/* End of text section */
 		_etext = .;
 	} :text = 0x9090
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index cb45c6c..dfb2ba9 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -9,7 +9,7 @@
 #include <asm/nospec-branch.h>
 
 .macro THUNK reg
-	.section .text.__x86.indirect_thunk.\reg
+	.section .text.__x86.indirect_thunk
 
 ENTRY(__x86_indirect_thunk_\reg)
 	CFI_STARTPROC
@@ -25,7 +25,8 @@
  * than one per register with the correct names. So we do it
  * the simple and nasty way...
  */
-#define EXPORT_THUNK(reg) EXPORT_SYMBOL(__x86_indirect_thunk_ ## reg)
+#define __EXPORT_THUNK(sym) _ASM_NOKPROBE(sym); EXPORT_SYMBOL(sym)
+#define EXPORT_THUNK(reg) __EXPORT_THUNK(__x86_indirect_thunk_ ## reg)
 #define GENERATE_THUNK(reg) THUNK reg ; EXPORT_THUNK(reg)
 
 GENERATE_THUNK(_ASM_AX)
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index c228ec8..3d7f60f 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -191,14 +191,15 @@
  * 6. T1   : reaches here, sees vma_pkey(vma)=5, when we really
  *	     faulted on a pte with its pkey=4.
  */
-static void fill_sig_info_pkey(int si_code, siginfo_t *info, u32 *pkey)
+static void fill_sig_info_pkey(int si_signo, int si_code, siginfo_t *info,
+		u32 *pkey)
 {
 	/* This is effectively an #ifdef */
 	if (!boot_cpu_has(X86_FEATURE_OSPKE))
 		return;
 
 	/* Fault not from Protection Keys: nothing to do */
-	if (si_code != SEGV_PKUERR)
+	if ((si_code != SEGV_PKUERR) || (si_signo != SIGSEGV))
 		return;
 	/*
 	 * force_sig_info_fault() is called from a number of
@@ -237,7 +238,7 @@
 		lsb = PAGE_SHIFT;
 	info.si_addr_lsb = lsb;
 
-	fill_sig_info_pkey(si_code, &info, pkey);
+	fill_sig_info_pkey(si_signo, si_code, &info, pkey);
 
 	force_sig_info(si_signo, &info, tsk);
 }
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 33e363d..aee3952 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4322,6 +4322,7 @@
 	 * https://bugzilla.kernel.org/show_bug.cgi?id=121671
 	 */
 	{ "LITEON CX1-JB*-HP",	NULL,		ATA_HORKAGE_MAX_SEC_1024 },
+	{ "LITEON EP1-*",	NULL,		ATA_HORKAGE_MAX_SEC_1024 },
 
 	/* Devices we expect to fail diagnostics */
 
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 39d2837..0983470 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -747,6 +747,7 @@
 {
 	struct isert_conn *isert_conn = cma_id->qp->qp_context;
 
+	ib_drain_qp(isert_conn->qp);
 	list_del_init(&isert_conn->node);
 	isert_conn->cm_id = NULL;
 	isert_put_conn(isert_conn);
diff --git a/drivers/input/misc/twl4030-vibra.c b/drivers/input/misc/twl4030-vibra.c
index caa5a62..15929d8 100644
--- a/drivers/input/misc/twl4030-vibra.c
+++ b/drivers/input/misc/twl4030-vibra.c
@@ -178,12 +178,14 @@
 			 twl4030_vibra_suspend, twl4030_vibra_resume);
 
 static bool twl4030_vibra_check_coexist(struct twl4030_vibra_data *pdata,
-			      struct device_node *node)
+			      struct device_node *parent)
 {
+	struct device_node *node;
+
 	if (pdata && pdata->coexist)
 		return true;
 
-	node = of_find_node_by_name(node, "codec");
+	node = of_get_child_by_name(parent, "codec");
 	if (node) {
 		of_node_put(node);
 		return true;
diff --git a/drivers/input/misc/twl6040-vibra.c b/drivers/input/misc/twl6040-vibra.c
index 5690eb7..15e0d35 100644
--- a/drivers/input/misc/twl6040-vibra.c
+++ b/drivers/input/misc/twl6040-vibra.c
@@ -248,8 +248,7 @@
 	int vddvibr_uV = 0;
 	int error;
 
-	of_node_get(twl6040_core_dev->of_node);
-	twl6040_core_node = of_find_node_by_name(twl6040_core_dev->of_node,
+	twl6040_core_node = of_get_child_by_name(twl6040_core_dev->of_node,
 						 "vibra");
 	if (!twl6040_core_node) {
 		dev_err(&pdev->dev, "parent of node is missing?\n");
diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c
index f26807c..af83d2e 100644
--- a/drivers/input/mouse/alps.c
+++ b/drivers/input/mouse/alps.c
@@ -1247,29 +1247,32 @@
 	case SS4_PACKET_ID_MULTI:
 		if (priv->flags & ALPS_BUTTONPAD) {
 			if (IS_SS4PLUS_DEV(priv->dev_id)) {
-				f->mt[0].x = SS4_PLUS_BTL_MF_X_V2(p, 0);
-				f->mt[1].x = SS4_PLUS_BTL_MF_X_V2(p, 1);
+				f->mt[2].x = SS4_PLUS_BTL_MF_X_V2(p, 0);
+				f->mt[3].x = SS4_PLUS_BTL_MF_X_V2(p, 1);
+				no_data_x = SS4_PLUS_MFPACKET_NO_AX_BL;
 			} else {
 				f->mt[2].x = SS4_BTL_MF_X_V2(p, 0);
 				f->mt[3].x = SS4_BTL_MF_X_V2(p, 1);
+				no_data_x = SS4_MFPACKET_NO_AX_BL;
 			}
+			no_data_y = SS4_MFPACKET_NO_AY_BL;
 
 			f->mt[2].y = SS4_BTL_MF_Y_V2(p, 0);
 			f->mt[3].y = SS4_BTL_MF_Y_V2(p, 1);
-			no_data_x = SS4_MFPACKET_NO_AX_BL;
-			no_data_y = SS4_MFPACKET_NO_AY_BL;
 		} else {
 			if (IS_SS4PLUS_DEV(priv->dev_id)) {
-				f->mt[0].x = SS4_PLUS_STD_MF_X_V2(p, 0);
-				f->mt[1].x = SS4_PLUS_STD_MF_X_V2(p, 1);
+				f->mt[2].x = SS4_PLUS_STD_MF_X_V2(p, 0);
+				f->mt[3].x = SS4_PLUS_STD_MF_X_V2(p, 1);
+				no_data_x = SS4_PLUS_MFPACKET_NO_AX;
 			} else {
-				f->mt[0].x = SS4_STD_MF_X_V2(p, 0);
-				f->mt[1].x = SS4_STD_MF_X_V2(p, 1);
+				f->mt[2].x = SS4_STD_MF_X_V2(p, 0);
+				f->mt[3].x = SS4_STD_MF_X_V2(p, 1);
+				no_data_x = SS4_MFPACKET_NO_AX;
 			}
+			no_data_y = SS4_MFPACKET_NO_AY;
+
 			f->mt[2].y = SS4_STD_MF_Y_V2(p, 0);
 			f->mt[3].y = SS4_STD_MF_Y_V2(p, 1);
-			no_data_x = SS4_MFPACKET_NO_AX;
-			no_data_y = SS4_MFPACKET_NO_AY;
 		}
 
 		f->first_mp = 0;
diff --git a/drivers/input/mouse/alps.h b/drivers/input/mouse/alps.h
index 7931237..9bc2bab 100644
--- a/drivers/input/mouse/alps.h
+++ b/drivers/input/mouse/alps.h
@@ -120,10 +120,12 @@
 #define SS4_IS_5F_DETECTED(_b)	((_b[2] & 0x10) == 0x10)
 
 
-#define SS4_MFPACKET_NO_AX	8160	/* X-Coordinate value */
-#define SS4_MFPACKET_NO_AY	4080	/* Y-Coordinate value */
-#define SS4_MFPACKET_NO_AX_BL	8176	/* Buttonless X-Coordinate value */
-#define SS4_MFPACKET_NO_AY_BL	4088	/* Buttonless Y-Coordinate value */
+#define SS4_MFPACKET_NO_AX		8160	/* X-Coordinate value */
+#define SS4_MFPACKET_NO_AY		4080	/* Y-Coordinate value */
+#define SS4_MFPACKET_NO_AX_BL		8176	/* Buttonless X-Coord value */
+#define SS4_MFPACKET_NO_AY_BL		4088	/* Buttonless Y-Coord value */
+#define SS4_PLUS_MFPACKET_NO_AX		4080	/* SS4 PLUS, X */
+#define SS4_PLUS_MFPACKET_NO_AX_BL	4088	/* Buttonless SS4 PLUS, X */
 
 /*
  * enum V7_PACKET_ID - defines the packet type for V7
diff --git a/drivers/input/touchscreen/88pm860x-ts.c b/drivers/input/touchscreen/88pm860x-ts.c
index 251ff2a..7a0dbce 100644
--- a/drivers/input/touchscreen/88pm860x-ts.c
+++ b/drivers/input/touchscreen/88pm860x-ts.c
@@ -126,7 +126,7 @@
 	int data, n, ret;
 	if (!np)
 		return -ENODEV;
-	np = of_find_node_by_name(np, "touch");
+	np = of_get_child_by_name(np, "touch");
 	if (!np) {
 		dev_err(&pdev->dev, "Can't find touch node\n");
 		return -EINVAL;
@@ -144,13 +144,13 @@
 	if (data) {
 		ret = pm860x_reg_write(i2c, PM8607_GPADC_MISC1, data);
 		if (ret < 0)
-			return -EINVAL;
+			goto err_put_node;
 	}
 	/* set tsi prebias time */
 	if (!of_property_read_u32(np, "marvell,88pm860x-tsi-prebias", &data)) {
 		ret = pm860x_reg_write(i2c, PM8607_TSI_PREBIAS, data);
 		if (ret < 0)
-			return -EINVAL;
+			goto err_put_node;
 	}
 	/* set prebias & prechg time of pen detect */
 	data = 0;
@@ -161,10 +161,18 @@
 	if (data) {
 		ret = pm860x_reg_write(i2c, PM8607_PD_PREBIAS, data);
 		if (ret < 0)
-			return -EINVAL;
+			goto err_put_node;
 	}
 	of_property_read_u32(np, "marvell,88pm860x-resistor-X", res_x);
+
+	of_node_put(np);
+
 	return 0;
+
+err_put_node:
+	of_node_put(np);
+
+	return -EINVAL;
 }
 #else
 #define pm860x_touch_dt_init(x, y, z)	(-1)
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index 4477bf9..e976f4f 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -81,10 +81,14 @@
 #define SECTOR_TO_BLOCK_SHIFT 3
 
 /*
+ * For btree insert:
  *  3 for btree insert +
  *  2 for btree lookup used within space map
+ * For btree remove:
+ *  2 for shadow spine +
+ *  4 for rebalance 3 child node
  */
-#define THIN_MAX_CONCURRENT_LOCKS 5
+#define THIN_MAX_CONCURRENT_LOCKS 6
 
 /* This should be plenty */
 #define SPACE_MAP_ROOT_SIZE 128
diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c
index 7a75b50..e4ececd 100644
--- a/drivers/md/persistent-data/dm-btree.c
+++ b/drivers/md/persistent-data/dm-btree.c
@@ -678,23 +678,8 @@
 	pn->keys[1] = rn->keys[0];
 	memcpy_disk(value_ptr(pn, 1), &val, sizeof(__le64));
 
-	/*
-	 * rejig the spine.  This is ugly, since it knows too
-	 * much about the spine
-	 */
-	if (s->nodes[0] != new_parent) {
-		unlock_block(s->info, s->nodes[0]);
-		s->nodes[0] = new_parent;
-	}
-	if (key < le64_to_cpu(rn->keys[0])) {
-		unlock_block(s->info, right);
-		s->nodes[1] = left;
-	} else {
-		unlock_block(s->info, left);
-		s->nodes[1] = right;
-	}
-	s->count = 2;
-
+	unlock_block(s->info, left);
+	unlock_block(s->info, right);
 	return 0;
 }
 
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
index 3047325..7f5ec40 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
@@ -184,7 +184,7 @@
 	void *cmd_head = pcan_usb_fd_cmd_buffer(dev);
 	int err = 0;
 	u8 *packet_ptr;
-	int i, n = 1, packet_len;
+	int packet_len;
 	ptrdiff_t cmd_len;
 
 	/* usb device unregistered? */
@@ -201,17 +201,13 @@
 	}
 
 	packet_ptr = cmd_head;
+	packet_len = cmd_len;
 
 	/* firmware is not able to re-assemble 512 bytes buffer in full-speed */
-	if ((dev->udev->speed != USB_SPEED_HIGH) &&
-	    (cmd_len > PCAN_UFD_LOSPD_PKT_SIZE)) {
-		packet_len = PCAN_UFD_LOSPD_PKT_SIZE;
-		n += cmd_len / packet_len;
-	} else {
-		packet_len = cmd_len;
-	}
+	if (unlikely(dev->udev->speed != USB_SPEED_HIGH))
+		packet_len = min(packet_len, PCAN_UFD_LOSPD_PKT_SIZE);
 
-	for (i = 0; i < n; i++) {
+	do {
 		err = usb_bulk_msg(dev->udev,
 				   usb_sndbulkpipe(dev->udev,
 						   PCAN_USBPRO_EP_CMDOUT),
@@ -224,7 +220,12 @@
 		}
 
 		packet_ptr += packet_len;
-	}
+		cmd_len -= packet_len;
+
+		if (cmd_len < PCAN_UFD_LOSPD_PKT_SIZE)
+			packet_len = cmd_len;
+
+	} while (packet_len > 0);
 
 	return err;
 }
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index 94733f7..7121453 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -183,13 +183,13 @@
 	return ret;
 }
 
-static int btt_log_read_pair(struct arena_info *arena, u32 lane,
-			struct log_entry *ent)
+static int btt_log_group_read(struct arena_info *arena, u32 lane,
+			struct log_group *log)
 {
-	WARN_ON(!ent);
+	WARN_ON(!log);
 	return arena_read_bytes(arena,
-			arena->logoff + (2 * lane * LOG_ENT_SIZE), ent,
-			2 * LOG_ENT_SIZE);
+			arena->logoff + (lane * LOG_GRP_SIZE), log,
+			LOG_GRP_SIZE);
 }
 
 static struct dentry *debugfs_root;
@@ -229,6 +229,8 @@
 	debugfs_create_x64("logoff", S_IRUGO, d, &a->logoff);
 	debugfs_create_x64("info2off", S_IRUGO, d, &a->info2off);
 	debugfs_create_x32("flags", S_IRUGO, d, &a->flags);
+	debugfs_create_u32("log_index_0", S_IRUGO, d, &a->log_index[0]);
+	debugfs_create_u32("log_index_1", S_IRUGO, d, &a->log_index[1]);
 }
 
 static void btt_debugfs_init(struct btt *btt)
@@ -247,6 +249,11 @@
 	}
 }
 
+static u32 log_seq(struct log_group *log, int log_idx)
+{
+	return le32_to_cpu(log->ent[log_idx].seq);
+}
+
 /*
  * This function accepts two log entries, and uses the
  * sequence number to find the 'older' entry.
@@ -256,8 +263,10 @@
  *
  * TODO The logic feels a bit kludge-y. make it better..
  */
-static int btt_log_get_old(struct log_entry *ent)
+static int btt_log_get_old(struct arena_info *a, struct log_group *log)
 {
+	int idx0 = a->log_index[0];
+	int idx1 = a->log_index[1];
 	int old;
 
 	/*
@@ -265,23 +274,23 @@
 	 * the next time, the following logic works out to put this
 	 * (next) entry into [1]
 	 */
-	if (ent[0].seq == 0) {
-		ent[0].seq = cpu_to_le32(1);
+	if (log_seq(log, idx0) == 0) {
+		log->ent[idx0].seq = cpu_to_le32(1);
 		return 0;
 	}
 
-	if (ent[0].seq == ent[1].seq)
+	if (log_seq(log, idx0) == log_seq(log, idx1))
 		return -EINVAL;
-	if (le32_to_cpu(ent[0].seq) + le32_to_cpu(ent[1].seq) > 5)
+	if (log_seq(log, idx0) + log_seq(log, idx1) > 5)
 		return -EINVAL;
 
-	if (le32_to_cpu(ent[0].seq) < le32_to_cpu(ent[1].seq)) {
-		if (le32_to_cpu(ent[1].seq) - le32_to_cpu(ent[0].seq) == 1)
+	if (log_seq(log, idx0) < log_seq(log, idx1)) {
+		if ((log_seq(log, idx1) - log_seq(log, idx0)) == 1)
 			old = 0;
 		else
 			old = 1;
 	} else {
-		if (le32_to_cpu(ent[0].seq) - le32_to_cpu(ent[1].seq) == 1)
+		if ((log_seq(log, idx0) - log_seq(log, idx1)) == 1)
 			old = 1;
 		else
 			old = 0;
@@ -306,17 +315,18 @@
 {
 	int ret;
 	int old_ent, ret_ent;
-	struct log_entry log[2];
+	struct log_group log;
 
-	ret = btt_log_read_pair(arena, lane, log);
+	ret = btt_log_group_read(arena, lane, &log);
 	if (ret)
 		return -EIO;
 
-	old_ent = btt_log_get_old(log);
+	old_ent = btt_log_get_old(arena, &log);
 	if (old_ent < 0 || old_ent > 1) {
 		dev_info(to_dev(arena),
 				"log corruption (%d): lane %d seq [%d, %d]\n",
-			old_ent, lane, log[0].seq, log[1].seq);
+				old_ent, lane, log.ent[arena->log_index[0]].seq,
+				log.ent[arena->log_index[1]].seq);
 		/* TODO set error state? */
 		return -EIO;
 	}
@@ -324,7 +334,7 @@
 	ret_ent = (old_flag ? old_ent : (1 - old_ent));
 
 	if (ent != NULL)
-		memcpy(ent, &log[ret_ent], LOG_ENT_SIZE);
+		memcpy(ent, &log.ent[arena->log_index[ret_ent]], LOG_ENT_SIZE);
 
 	return ret_ent;
 }
@@ -338,17 +348,13 @@
 			u32 sub, struct log_entry *ent)
 {
 	int ret;
-	/*
-	 * Ignore the padding in log_entry for calculating log_half.
-	 * The entry is 'committed' when we write the sequence number,
-	 * and we want to ensure that that is the last thing written.
-	 * We don't bother writing the padding as that would be extra
-	 * media wear and write amplification
-	 */
-	unsigned int log_half = (LOG_ENT_SIZE - 2 * sizeof(u64)) / 2;
-	u64 ns_off = arena->logoff + (((2 * lane) + sub) * LOG_ENT_SIZE);
+	u32 group_slot = arena->log_index[sub];
+	unsigned int log_half = LOG_ENT_SIZE / 2;
 	void *src = ent;
+	u64 ns_off;
 
+	ns_off = arena->logoff + (lane * LOG_GRP_SIZE) +
+		(group_slot * LOG_ENT_SIZE);
 	/* split the 16B write into atomic, durable halves */
 	ret = arena_write_bytes(arena, ns_off, src, log_half);
 	if (ret)
@@ -419,16 +425,16 @@
 {
 	int ret;
 	u32 i;
-	struct log_entry log, zerolog;
+	struct log_entry ent, zerolog;
 
 	memset(&zerolog, 0, sizeof(zerolog));
 
 	for (i = 0; i < arena->nfree; i++) {
-		log.lba = cpu_to_le32(i);
-		log.old_map = cpu_to_le32(arena->external_nlba + i);
-		log.new_map = cpu_to_le32(arena->external_nlba + i);
-		log.seq = cpu_to_le32(LOG_SEQ_INIT);
-		ret = __btt_log_write(arena, i, 0, &log);
+		ent.lba = cpu_to_le32(i);
+		ent.old_map = cpu_to_le32(arena->external_nlba + i);
+		ent.new_map = cpu_to_le32(arena->external_nlba + i);
+		ent.seq = cpu_to_le32(LOG_SEQ_INIT);
+		ret = __btt_log_write(arena, i, 0, &ent);
 		if (ret)
 			return ret;
 		ret = __btt_log_write(arena, i, 1, &zerolog);
@@ -490,6 +496,123 @@
 	return 0;
 }
 
+static bool ent_is_padding(struct log_entry *ent)
+{
+	return (ent->lba == 0) && (ent->old_map == 0) && (ent->new_map == 0)
+		&& (ent->seq == 0);
+}
+
+/*
+ * Detecting valid log indices: We read a log group (see the comments in btt.h
+ * for a description of a 'log_group' and its 'slots'), and iterate over its
+ * four slots. We expect that a padding slot will be all-zeroes, and use this
+ * to detect a padding slot vs. an actual entry.
+ *
+ * If a log_group is in the initial state, i.e. hasn't been used since the
+ * creation of this BTT layout, it will have three of the four slots with
+ * zeroes. We skip over these log_groups for the detection of log_index. If
+ * all log_groups are in the initial state (i.e. the BTT has never been
+ * written to), it is safe to assume the 'new format' of log entries in slots
+ * (0, 1).
+ */
+static int log_set_indices(struct arena_info *arena)
+{
+	bool idx_set = false, initial_state = true;
+	int ret, log_index[2] = {-1, -1};
+	u32 i, j, next_idx = 0;
+	struct log_group log;
+	u32 pad_count = 0;
+
+	for (i = 0; i < arena->nfree; i++) {
+		ret = btt_log_group_read(arena, i, &log);
+		if (ret < 0)
+			return ret;
+
+		for (j = 0; j < 4; j++) {
+			if (!idx_set) {
+				if (ent_is_padding(&log.ent[j])) {
+					pad_count++;
+					continue;
+				} else {
+					/* Skip if index has been recorded */
+					if ((next_idx == 1) &&
+						(j == log_index[0]))
+						continue;
+					/* valid entry, record index */
+					log_index[next_idx] = j;
+					next_idx++;
+				}
+				if (next_idx == 2) {
+					/* two valid entries found */
+					idx_set = true;
+				} else if (next_idx > 2) {
+					/* too many valid indices */
+					return -ENXIO;
+				}
+			} else {
+				/*
+				 * once the indices have been set, just verify
+				 * that all subsequent log groups are either in
+				 * their initial state or follow the same
+				 * indices.
+				 */
+				if (j == log_index[0]) {
+					/* entry must be 'valid' */
+					if (ent_is_padding(&log.ent[j]))
+						return -ENXIO;
+				} else if (j == log_index[1]) {
+					;
+					/*
+					 * log_index[1] can be padding if the
+					 * lane never got used and it is still
+					 * in the initial state (three 'padding'
+					 * entries)
+					 */
+				} else {
+					/* entry must be invalid (padding) */
+					if (!ent_is_padding(&log.ent[j]))
+						return -ENXIO;
+				}
+			}
+		}
+		/*
+		 * If any of the log_groups have more than one valid,
+		 * non-padding entry, then the we are no longer in the
+		 * initial_state
+		 */
+		if (pad_count < 3)
+			initial_state = false;
+		pad_count = 0;
+	}
+
+	if (!initial_state && !idx_set)
+		return -ENXIO;
+
+	/*
+	 * If all the entries in the log were in the initial state,
+	 * assume new padding scheme
+	 */
+	if (initial_state)
+		log_index[1] = 1;
+
+	/*
+	 * Only allow the known permutations of log/padding indices,
+	 * i.e. (0, 1), and (0, 2)
+	 */
+	if ((log_index[0] == 0) && ((log_index[1] == 1) || (log_index[1] == 2)))
+		; /* known index possibilities */
+	else {
+		dev_err(to_dev(arena), "Found an unknown padding scheme\n");
+		return -ENXIO;
+	}
+
+	arena->log_index[0] = log_index[0];
+	arena->log_index[1] = log_index[1];
+	dev_dbg(to_dev(arena), "log_index_0 = %d\n", log_index[0]);
+	dev_dbg(to_dev(arena), "log_index_1 = %d\n", log_index[1]);
+	return 0;
+}
+
 static int btt_rtt_init(struct arena_info *arena)
 {
 	arena->rtt = kcalloc(arena->nfree, sizeof(u32), GFP_KERNEL);
@@ -545,8 +668,7 @@
 	available -= 2 * BTT_PG_SIZE;
 
 	/* The log takes a fixed amount of space based on nfree */
-	logsize = roundup(2 * arena->nfree * sizeof(struct log_entry),
-				BTT_PG_SIZE);
+	logsize = roundup(arena->nfree * LOG_GRP_SIZE, BTT_PG_SIZE);
 	available -= logsize;
 
 	/* Calculate optimal split between map and data area */
@@ -563,6 +685,10 @@
 	arena->mapoff = arena->dataoff + datasize;
 	arena->logoff = arena->mapoff + mapsize;
 	arena->info2off = arena->logoff + logsize;
+
+	/* Default log indices are (0,1) */
+	arena->log_index[0] = 0;
+	arena->log_index[1] = 1;
 	return arena;
 }
 
@@ -653,6 +779,13 @@
 		arena->external_lba_start = cur_nlba;
 		parse_arena_meta(arena, super, cur_off);
 
+		ret = log_set_indices(arena);
+		if (ret) {
+			dev_err(to_dev(arena),
+				"Unable to deduce log/padding indices\n");
+			goto out;
+		}
+
 		ret = btt_freelist_init(arena);
 		if (ret)
 			goto out;
diff --git a/drivers/nvdimm/btt.h b/drivers/nvdimm/btt.h
index b2f8651..0f80b6b 100644
--- a/drivers/nvdimm/btt.h
+++ b/drivers/nvdimm/btt.h
@@ -26,6 +26,7 @@
 #define MAP_ERR_MASK (1 << MAP_ERR_SHIFT)
 #define MAP_LBA_MASK (~((1 << MAP_TRIM_SHIFT) | (1 << MAP_ERR_SHIFT)))
 #define MAP_ENT_NORMAL 0xC0000000
+#define LOG_GRP_SIZE sizeof(struct log_group)
 #define LOG_ENT_SIZE sizeof(struct log_entry)
 #define ARENA_MIN_SIZE (1UL << 24)	/* 16 MB */
 #define ARENA_MAX_SIZE (1ULL << 39)	/* 512 GB */
@@ -44,12 +45,52 @@
 	INIT_READY
 };
 
+/*
+ * A log group represents one log 'lane', and consists of four log entries.
+ * Two of the four entries are valid entries, and the remaining two are
+ * padding. Due to an old bug in the padding location, we need to perform a
+ * test to determine the padding scheme being used, and use that scheme
+ * thereafter.
+ *
+ * In kernels prior to 4.15, 'log group' would have actual log entries at
+ * indices (0, 2) and padding at indices (1, 3), where as the correct/updated
+ * format has log entries at indices (0, 1) and padding at indices (2, 3).
+ *
+ * Old (pre 4.15) format:
+ * +-----------------+-----------------+
+ * |      ent[0]     |      ent[1]     |
+ * |       16B       |       16B       |
+ * | lba/old/new/seq |       pad       |
+ * +-----------------------------------+
+ * |      ent[2]     |      ent[3]     |
+ * |       16B       |       16B       |
+ * | lba/old/new/seq |       pad       |
+ * +-----------------+-----------------+
+ *
+ * New format:
+ * +-----------------+-----------------+
+ * |      ent[0]     |      ent[1]     |
+ * |       16B       |       16B       |
+ * | lba/old/new/seq | lba/old/new/seq |
+ * +-----------------------------------+
+ * |      ent[2]     |      ent[3]     |
+ * |       16B       |       16B       |
+ * |       pad       |       pad       |
+ * +-----------------+-----------------+
+ *
+ * We detect during start-up which format is in use, and set
+ * arena->log_index[(0, 1)] with the detected format.
+ */
+
 struct log_entry {
 	__le32 lba;
 	__le32 old_map;
 	__le32 new_map;
 	__le32 seq;
-	__le64 padding[2];
+};
+
+struct log_group {
+	struct log_entry ent[4];
 };
 
 struct btt_sb {
@@ -117,6 +158,7 @@
  * @list:		List head for list of arenas
  * @debugfs_dir:	Debugfs dentry
  * @flags:		Arena flags - may signify error states.
+ * @log_index:		Indices of the valid log entries in a log_group
  *
  * arena_info is a per-arena handle. Once an arena is narrowed down for an
  * IO, this struct is passed around for the duration of the IO.
@@ -147,6 +189,7 @@
 	struct dentry *debugfs_dir;
 	/* Arena flags */
 	u32 flags;
+	int log_index[2];
 };
 
 /**
diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
index a268f4d..48a365e 100644
--- a/drivers/phy/phy-core.c
+++ b/drivers/phy/phy-core.c
@@ -395,6 +395,10 @@
 	if (ret)
 		return ERR_PTR(-ENODEV);
 
+	/* This phy type handled by the usb-phy subsystem for now */
+	if (of_device_is_compatible(args.np, "usb-nop-xceiv"))
+		return ERR_PTR(-ENODEV);
+
 	mutex_lock(&phy_provider_mutex);
 	phy_provider = of_phy_provider_lookup(args.np);
 	if (IS_ERR(phy_provider) || !try_module_get(phy_provider->owner)) {
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index 9962370..0b8db8a 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -3857,6 +3857,7 @@
 		if (h->fw_support & MISC_FW_RAID_OFFLOAD_BASIC)
 			hpsa_get_ioaccel_status(h, scsi3addr, this_device);
 		volume_offline = hpsa_volume_offline(h, scsi3addr);
+		this_device->volume_offline = volume_offline;
 		if (volume_offline == HPSA_LV_FAILED) {
 			rc = HPSA_LV_FAILED;
 			dev_err(&h->pdev->dev,
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 184c7db..cd9537d 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -149,7 +149,6 @@
 	struct list_head rq_list; /* head of request list */
 	struct fasync_struct *async_qp;	/* used by asynchronous notification */
 	Sg_request req_arr[SG_MAX_QUEUE];	/* used as singly-linked list */
-	char low_dma;		/* as in parent but possibly overridden to 1 */
 	char force_packid;	/* 1 -> pack_id input to read(), 0 -> ignored */
 	char cmd_q;		/* 1 -> allow command queuing, 0 -> don't */
 	unsigned char next_cmd_len; /* 0: automatic, >0: use on next write() */
@@ -922,24 +921,14 @@
 				/* strange ..., for backward compatibility */
 		return sfp->timeout_user;
 	case SG_SET_FORCE_LOW_DMA:
-		result = get_user(val, ip);
-		if (result)
-			return result;
-		if (val) {
-			sfp->low_dma = 1;
-			if ((0 == sfp->low_dma) && !sfp->res_in_use) {
-				val = (int) sfp->reserve.bufflen;
-				sg_remove_scat(sfp, &sfp->reserve);
-				sg_build_reserve(sfp, val);
-			}
-		} else {
-			if (atomic_read(&sdp->detaching))
-				return -ENODEV;
-			sfp->low_dma = sdp->device->host->unchecked_isa_dma;
-		}
+		/*
+		 * N.B. This ioctl never worked properly, but failed to
+		 * return an error value. So returning '0' to keep compability
+		 * with legacy applications.
+		 */
 		return 0;
 	case SG_GET_LOW_DMA:
-		return put_user((int) sfp->low_dma, ip);
+		return put_user((int) sdp->device->host->unchecked_isa_dma, ip);
 	case SG_GET_SCSI_ID:
 		if (!access_ok(VERIFY_WRITE, p, sizeof (sg_scsi_id_t)))
 			return -EFAULT;
@@ -1860,6 +1849,7 @@
 	int sg_tablesize = sfp->parentdp->sg_tablesize;
 	int blk_size = buff_size, order;
 	gfp_t gfp_mask = GFP_ATOMIC | __GFP_COMP | __GFP_NOWARN;
+	struct sg_device *sdp = sfp->parentdp;
 
 	if (blk_size < 0)
 		return -EFAULT;
@@ -1885,7 +1875,7 @@
 			scatter_elem_sz_prev = num;
 	}
 
-	if (sfp->low_dma)
+	if (sdp->device->host->unchecked_isa_dma)
 		gfp_mask |= GFP_DMA;
 
 	if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO))
@@ -2148,8 +2138,6 @@
 	sfp->timeout = SG_DEFAULT_TIMEOUT;
 	sfp->timeout_user = SG_DEFAULT_TIMEOUT_USER;
 	sfp->force_packid = SG_DEF_FORCE_PACK_ID;
-	sfp->low_dma = (SG_DEF_FORCE_LOW_DMA == 0) ?
-	    sdp->device->host->unchecked_isa_dma : 1;
 	sfp->cmd_q = SG_DEF_COMMAND_Q;
 	sfp->keep_orphan = SG_DEF_KEEP_ORPHAN;
 	sfp->parentdp = sdp;
@@ -2608,7 +2596,7 @@
 			   jiffies_to_msecs(fp->timeout),
 			   fp->reserve.bufflen,
 			   (int) fp->reserve.k_use_sg,
-			   (int) fp->low_dma);
+			   (int) sdp->device->host->unchecked_isa_dma);
 		seq_printf(s, "   cmd_q=%d f_packid=%d k_orphan=%d closed=0\n",
 			   (int) fp->cmd_q, (int) fp->force_packid,
 			   (int) fp->keep_orphan);
diff --git a/drivers/usb/usbip/vhci_sysfs.c b/drivers/usb/usbip/vhci_sysfs.c
index c404017..b96e5b1 100644
--- a/drivers/usb/usbip/vhci_sysfs.c
+++ b/drivers/usb/usbip/vhci_sysfs.c
@@ -361,6 +361,7 @@
 	status->attr.attr.name = status->name;
 	status->attr.attr.mode = S_IRUGO;
 	status->attr.show = status_show;
+	sysfs_attr_init(&status->attr.attr);
 }
 
 static int init_status_attrs(void)
diff --git a/fs/pipe.c b/fs/pipe.c
index 8e0d9f2..9faecf1 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -1018,13 +1018,19 @@
 
 /*
  * Currently we rely on the pipe array holding a power-of-2 number
- * of pages.
+ * of pages. Returns 0 on error.
  */
 static inline unsigned int round_pipe_size(unsigned int size)
 {
 	unsigned long nr_pages;
 
+	if (size < pipe_min_size)
+		size = pipe_min_size;
+
 	nr_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	if (nr_pages == 0)
+		return 0;
+
 	return roundup_pow_of_two(nr_pages) << PAGE_SHIFT;
 }
 
@@ -1040,6 +1046,8 @@
 	long ret = 0;
 
 	size = round_pipe_size(arg);
+	if (size == 0)
+		return -EINVAL;
 	nr_pages = size >> PAGE_SHIFT;
 
 	if (!nr_pages)
@@ -1123,13 +1131,18 @@
 int pipe_proc_fn(struct ctl_table *table, int write, void __user *buf,
 		 size_t *lenp, loff_t *ppos)
 {
+	unsigned int rounded_pipe_max_size;
 	int ret;
 
 	ret = proc_dointvec_minmax(table, write, buf, lenp, ppos);
 	if (ret < 0 || !write)
 		return ret;
 
-	pipe_max_size = round_pipe_size(pipe_max_size);
+	rounded_pipe_max_size = round_pipe_size(pipe_max_size);
+	if (rounded_pipe_max_size == 0)
+		return -EINVAL;
+
+	pipe_max_size = rounded_pipe_max_size;
 	return ret;
 }
 
diff --git a/fs/proc/array.c b/fs/proc/array.c
index c932ec4..794b52a 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -423,8 +423,11 @@
 		 * safe because the task has stopped executing permanently.
 		 */
 		if (permitted && (task->flags & PF_DUMPCORE)) {
-			eip = KSTK_EIP(task);
-			esp = KSTK_ESP(task);
+			if (try_get_task_stack(task)) {
+				eip = KSTK_EIP(task);
+				esp = KSTK_ESP(task);
+				put_task_stack(task);
+			}
 		}
 	}
 
diff --git a/include/linux/vermagic.h b/include/linux/vermagic.h
index 6f8fbcf..a3d0493 100644
--- a/include/linux/vermagic.h
+++ b/include/linux/vermagic.h
@@ -24,10 +24,16 @@
 #ifndef MODULE_ARCH_VERMAGIC
 #define MODULE_ARCH_VERMAGIC ""
 #endif
+#ifdef RETPOLINE
+#define MODULE_VERMAGIC_RETPOLINE "retpoline "
+#else
+#define MODULE_VERMAGIC_RETPOLINE ""
+#endif
 
 #define VERMAGIC_STRING 						\
 	UTS_RELEASE " "							\
 	MODULE_VERMAGIC_SMP MODULE_VERMAGIC_PREEMPT 			\
 	MODULE_VERMAGIC_MODULE_UNLOAD MODULE_VERMAGIC_MODVERSIONS	\
-	MODULE_ARCH_VERMAGIC
+	MODULE_ARCH_VERMAGIC						\
+	MODULE_VERMAGIC_RETPOLINE
 
diff --git a/include/scsi/sg.h b/include/scsi/sg.h
index 3afec70..20bc71c 100644
--- a/include/scsi/sg.h
+++ b/include/scsi/sg.h
@@ -197,7 +197,6 @@
 #define SG_DEFAULT_RETRIES 0
 
 /* Defaults, commented if they differ from original sg driver */
-#define SG_DEF_FORCE_LOW_DMA 0  /* was 1 -> memory below 16MB on i386 */
 #define SG_DEF_FORCE_PACK_ID 0
 #define SG_DEF_KEEP_ORPHAN 0
 #define SG_DEF_RESERVED_SIZE SG_SCATTER_SZ /* load time option */
diff --git a/kernel/futex.c b/kernel/futex.c
index 88bad86..bb2265a 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1711,6 +1711,9 @@
 	struct futex_q *this, *next;
 	WAKE_Q(wake_q);
 
+	if (nr_wake < 0 || nr_requeue < 0)
+		return -EINVAL;
+
 	if (requeue_pi) {
 		/*
 		 * Requeue PI only works on two distinct uaddrs. This
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 4d89371..49815cc 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -725,6 +725,8 @@
 		if (unlikely(dl_se->dl_boosted || !start_dl_timer(p)))
 			return;
 		dl_se->dl_throttled = 1;
+		if (dl_se->runtime > 0)
+			dl_se->runtime = 0;
 	}
 }
 
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index e872f7f..2d5cc7d 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1696,7 +1696,7 @@
 	hrtimer_run_queues();
 	/* Raise the softirq only if required. */
 	if (time_before(jiffies, base->clk)) {
-		if (!IS_ENABLED(CONFIG_NO_HZ_COMMON) || !base->nohz_active)
+		if (!IS_ENABLED(CONFIG_NO_HZ_COMMON))
 			return;
 		/* CPU is awake, so check the deferrable base. */
 		base++;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 03c0a48..9549ed1 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2200,6 +2200,7 @@
 {
 	struct trace_event_call *call, *p;
 	const char *last_system = NULL;
+	bool first = false;
 	int last_i;
 	int i;
 
@@ -2207,15 +2208,28 @@
 	list_for_each_entry_safe(call, p, &ftrace_events, list) {
 		/* events are usually grouped together with systems */
 		if (!last_system || call->class->system != last_system) {
+			first = true;
 			last_i = 0;
 			last_system = call->class->system;
 		}
 
+		/*
+		 * Since calls are grouped by systems, the likelyhood that the
+		 * next call in the iteration belongs to the same system as the
+		 * previous call is high. As an optimization, we skip seaching
+		 * for a map[] that matches the call's system if the last call
+		 * was from the same system. That's what last_i is for. If the
+		 * call has the same system as the previous call, then last_i
+		 * will be the index of the first map[] that has a matching
+		 * system.
+		 */
 		for (i = last_i; i < len; i++) {
 			if (call->class->system == map[i]->system) {
 				/* Save the first system if need be */
-				if (!last_i)
+				if (first) {
 					last_i = i;
+					first = false;
+				}
 				update_event_printk(call, map[i]);
 			}
 		}
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 181c2ad..ebfea5f 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -48,6 +48,7 @@
 #include <linux/nodemask.h>
 #include <linux/moduleparam.h>
 #include <linux/uaccess.h>
+#include <linux/nmi.h>
 
 #include "workqueue_internal.h"
 
@@ -4424,6 +4425,12 @@
 			if (pwq->nr_active || !list_empty(&pwq->delayed_works))
 				show_pwq(pwq);
 			spin_unlock_irqrestore(&pwq->pool->lock, flags);
+			/*
+			 * We could be printing a lot from atomic context, e.g.
+			 * sysrq-t -> show_workqueue_state(). Avoid triggering
+			 * hard lockup.
+			 */
+			touch_nmi_watchdog();
 		}
 	}
 
@@ -4451,6 +4458,12 @@
 		pr_cont("\n");
 	next_pool:
 		spin_unlock_irqrestore(&pool->lock, flags);
+		/*
+		 * We could be printing a lot from atomic context, e.g.
+		 * sysrq-t -> show_workqueue_state(). Avoid triggering
+		 * hard lockup.
+		 */
+		touch_nmi_watchdog();
 	}
 
 	rcu_read_unlock_sched();
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 94bf810..6482b00 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -401,6 +401,11 @@
 #endif
 	int len;
 
+	if (sp->sadb_address_len <
+	    DIV_ROUND_UP(sizeof(*sp) + offsetofend(typeof(*addr), sa_family),
+			 sizeof(uint64_t)))
+		return -EINVAL;
+
 	switch (addr->sa_family) {
 	case AF_INET:
 		len = DIV_ROUND_UP(sizeof(*sp) + sizeof(*sin), sizeof(uint64_t));
@@ -511,6 +516,9 @@
 		uint16_t ext_type;
 		int ext_len;
 
+		if (len < sizeof(*ehdr))
+			return -EINVAL;
+
 		ext_len  = ehdr->sadb_ext_len;
 		ext_len *= sizeof(uint64_t);
 		ext_type = ehdr->sadb_ext_type;
diff --git a/scripts/gdb/linux/tasks.py b/scripts/gdb/linux/tasks.py
index 1bf949c..f6ab3cc 100644
--- a/scripts/gdb/linux/tasks.py
+++ b/scripts/gdb/linux/tasks.py
@@ -96,6 +96,8 @@
         thread_info_addr = task.address + ia64_task_size
         thread_info = thread_info_addr.cast(thread_info_ptr_type)
     else:
+        if task.type.fields()[0].type == thread_info_type.get_type():
+            return task['thread_info']
         thread_info = task['stack'].cast(thread_info_ptr_type)
     return thread_info.dereference()
 
diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c
index e685e77..9306604 100644
--- a/sound/core/pcm_lib.c
+++ b/sound/core/pcm_lib.c
@@ -578,7 +578,6 @@
 {
 	u_int64_t n = (u_int64_t) a * b;
 	if (c == 0) {
-		snd_BUG_ON(!n);
 		*r = 0;
 		return UINT_MAX;
 	}
diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c
index 45ef591..16580a8 100644
--- a/sound/core/seq/seq_clientmgr.c
+++ b/sound/core/seq/seq_clientmgr.c
@@ -221,6 +221,7 @@
 	rwlock_init(&client->ports_lock);
 	mutex_init(&client->ports_mutex);
 	INIT_LIST_HEAD(&client->ports_list_head);
+	mutex_init(&client->ioctl_mutex);
 
 	/* find free slot in the client table */
 	spin_lock_irqsave(&clients_lock, flags);
@@ -2127,7 +2128,9 @@
 			return -EFAULT;
 	}
 
+	mutex_lock(&client->ioctl_mutex);
 	err = handler->func(client, &buf);
+	mutex_unlock(&client->ioctl_mutex);
 	if (err >= 0) {
 		/* Some commands includes a bug in 'dir' field. */
 		if (handler->cmd == SNDRV_SEQ_IOCTL_SET_QUEUE_CLIENT ||
diff --git a/sound/core/seq/seq_clientmgr.h b/sound/core/seq/seq_clientmgr.h
index c661425..0611e1e 100644
--- a/sound/core/seq/seq_clientmgr.h
+++ b/sound/core/seq/seq_clientmgr.h
@@ -61,6 +61,7 @@
 	struct list_head ports_list_head;
 	rwlock_t ports_lock;
 	struct mutex ports_mutex;
+	struct mutex ioctl_mutex;
 	int convert32;		/* convert 32->64bit */
 
 	/* output pool */
diff --git a/sound/pci/hda/patch_cirrus.c b/sound/pci/hda/patch_cirrus.c
index 80bbadc..d6e079f 100644
--- a/sound/pci/hda/patch_cirrus.c
+++ b/sound/pci/hda/patch_cirrus.c
@@ -408,6 +408,7 @@
 	/*SND_PCI_QUIRK(0x8086, 0x7270, "IMac 27 Inch", CS420X_IMAC27),*/
 
 	/* codec SSID */
+	SND_PCI_QUIRK(0x106b, 0x0600, "iMac 14,1", CS420X_IMAC27_122),
 	SND_PCI_QUIRK(0x106b, 0x1c00, "MacBookPro 8,1", CS420X_MBP81),
 	SND_PCI_QUIRK(0x106b, 0x2000, "iMac 12,2", CS420X_IMAC27_122),
 	SND_PCI_QUIRK(0x106b, 0x2800, "MacBookPro 10,1", CS420X_MBP101),
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 4ef3b00..71a058f 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -5617,6 +5617,7 @@
 	SND_PCI_QUIRK(0x1028, 0x075b, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE),
 	SND_PCI_QUIRK(0x1028, 0x075d, "Dell AIO", ALC298_FIXUP_SPK_VOLUME),
 	SND_PCI_QUIRK(0x1028, 0x0798, "Dell Inspiron 17 7000 Gaming", ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER),
+	SND_PCI_QUIRK(0x1028, 0x082a, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE),
 	SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2),
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index d897702..faacf0c 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -26,6 +26,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
+#include <errno.h>
 
 #include "elf.h"
 #include "warn.h"
@@ -370,7 +371,8 @@
 
 	elf->fd = open(name, O_RDONLY);
 	if (elf->fd == -1) {
-		perror("open");
+		fprintf(stderr, "objtool: Can't open '%s': %s\n",
+			name, strerror(errno));
 		goto err;
 	}
 
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index cffdd9c..ff37531 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -19,18 +19,18 @@
 
 include $(srctree)/tools/scripts/Makefile.arch
 
-$(call detected_var,ARCH)
+$(call detected_var,SRCARCH)
 
 NO_PERF_REGS := 1
 
 # Additional ARCH settings for ppc
-ifeq ($(ARCH),powerpc)
+ifeq ($(SRCARCH),powerpc)
   NO_PERF_REGS := 0
   LIBUNWIND_LIBS := -lunwind -lunwind-ppc64
 endif
 
 # Additional ARCH settings for x86
-ifeq ($(ARCH),x86)
+ifeq ($(SRCARCH),x86)
   $(call detected,CONFIG_X86)
   ifeq (${IS_64_BIT}, 1)
     CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT -DHAVE_SYSCALL_TABLE -I$(OUTPUT)arch/x86/include/generated
@@ -43,12 +43,12 @@
   NO_PERF_REGS := 0
 endif
 
-ifeq ($(ARCH),arm)
+ifeq ($(SRCARCH),arm)
   NO_PERF_REGS := 0
   LIBUNWIND_LIBS = -lunwind -lunwind-arm
 endif
 
-ifeq ($(ARCH),arm64)
+ifeq ($(SRCARCH),arm64)
   NO_PERF_REGS := 0
   LIBUNWIND_LIBS = -lunwind -lunwind-aarch64
 endif
@@ -61,7 +61,7 @@
 # Disable it on all other architectures in case libdw unwind
 # support is detected in system. Add supported architectures
 # to the check.
-ifneq ($(ARCH),$(filter $(ARCH),x86 arm))
+ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm))
   NO_LIBDW_DWARF_UNWIND := 1
 endif
 
@@ -115,9 +115,9 @@
 FEATURE_CHECK_CFLAGS-libbabeltrace := $(LIBBABELTRACE_CFLAGS)
 FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf
 
-FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi
+FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(SRCARCH)/include/uapi -I$(srctree)/tools/include/uapi
 # include ARCH specific config
--include $(src-perf)/arch/$(ARCH)/Makefile
+-include $(src-perf)/arch/$(SRCARCH)/Makefile
 
 ifdef PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET
   CFLAGS += -DHAVE_ARCH_REGS_QUERY_REGISTER_OFFSET
@@ -205,12 +205,12 @@
 endif
 
 CFLAGS += -I$(src-perf)/util/include
-CFLAGS += -I$(src-perf)/arch/$(ARCH)/include
+CFLAGS += -I$(src-perf)/arch/$(SRCARCH)/include
 CFLAGS += -I$(srctree)/tools/include/uapi
 CFLAGS += -I$(srctree)/tools/include/
-CFLAGS += -I$(srctree)/tools/arch/$(ARCH)/include/uapi
-CFLAGS += -I$(srctree)/tools/arch/$(ARCH)/include/
-CFLAGS += -I$(srctree)/tools/arch/$(ARCH)/
+CFLAGS += -I$(srctree)/tools/arch/$(SRCARCH)/include/uapi
+CFLAGS += -I$(srctree)/tools/arch/$(SRCARCH)/include/
+CFLAGS += -I$(srctree)/tools/arch/$(SRCARCH)/
 
 # $(obj-perf)      for generated common-cmds.h
 # $(obj-perf)/util for generated bison/flex headers
@@ -321,7 +321,7 @@
 
   ifndef NO_DWARF
     ifeq ($(origin PERF_HAVE_DWARF_REGS), undefined)
-      msg := $(warning DWARF register mappings have not been defined for architecture $(ARCH), DWARF support disabled);
+      msg := $(warning DWARF register mappings have not been defined for architecture $(SRCARCH), DWARF support disabled);
       NO_DWARF := 1
     else
       CFLAGS += -DHAVE_DWARF_SUPPORT $(LIBDW_CFLAGS)
@@ -346,7 +346,7 @@
         CFLAGS += -DHAVE_BPF_PROLOGUE
         $(call detected,CONFIG_BPF_PROLOGUE)
       else
-        msg := $(warning BPF prologue is not supported by architecture $(ARCH), missing regs_query_register_offset());
+        msg := $(warning BPF prologue is not supported by architecture $(SRCARCH), missing regs_query_register_offset());
       endif
     else
       msg := $(warning DWARF support is off, BPF prologue is disabled);
@@ -372,7 +372,7 @@
   endif
 endif
 
-ifeq ($(ARCH),powerpc)
+ifeq ($(SRCARCH),powerpc)
   ifndef NO_DWARF
     CFLAGS += -DHAVE_SKIP_CALLCHAIN_IDX
   endif
@@ -453,7 +453,7 @@
 endif
 
 ifndef NO_LOCAL_LIBUNWIND
-  ifeq ($(ARCH),$(filter $(ARCH),arm arm64))
+  ifeq ($(SRCARCH),$(filter $(SRCARCH),arm arm64))
     $(call feature_check,libunwind-debug-frame)
     ifneq ($(feature-libunwind-debug-frame), 1)
       msg := $(warning No debug_frame support found in libunwind);
@@ -717,7 +717,7 @@
       NO_PERF_READ_VDSO32 := 1
     endif
   endif
-  ifneq ($(ARCH), x86)
+  ifneq ($(SRCARCH), x86)
     NO_PERF_READ_VDSOX32 := 1
   endif
   ifndef NO_PERF_READ_VDSOX32
@@ -746,7 +746,7 @@
 endif
 
 ifndef NO_AUXTRACE
-  ifeq ($(ARCH),x86)
+  ifeq ($(SRCARCH),x86)
     ifeq ($(feature-get_cpuid), 0)
       msg := $(warning Your gcc lacks the __get_cpuid() builtin, disables support for auxtrace/Intel PT, please install a newer gcc);
       NO_AUXTRACE := 1
@@ -793,7 +793,7 @@
 ETC_PERFCONFIG = etc/perfconfig
 endif
 ifndef lib
-ifeq ($(ARCH)$(IS_64_BIT), x861)
+ifeq ($(SRCARCH)$(IS_64_BIT), x861)
 lib = lib64
 else
 lib = lib
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index ef52d1e..2b92ffe 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -192,7 +192,7 @@
 
 ifeq ($(config),0)
 include $(srctree)/tools/scripts/Makefile.arch
--include arch/$(ARCH)/Makefile
+-include arch/$(SRCARCH)/Makefile
 endif
 
 # The FEATURE_DUMP_EXPORT holds location of the actual
diff --git a/tools/perf/arch/Build b/tools/perf/arch/Build
index 109eb75..d9b6af8 100644
--- a/tools/perf/arch/Build
+++ b/tools/perf/arch/Build
@@ -1,2 +1,2 @@
 libperf-y += common.o
-libperf-y += $(ARCH)/
+libperf-y += $(SRCARCH)/
diff --git a/tools/perf/pmu-events/Build b/tools/perf/pmu-events/Build
index 9213a12..999a4e8 100644
--- a/tools/perf/pmu-events/Build
+++ b/tools/perf/pmu-events/Build
@@ -2,7 +2,7 @@
 
 jevents-y	+= json.o jsmn.o jevents.o
 pmu-events-y	+= pmu-events.o
-JDIR		=  pmu-events/arch/$(ARCH)
+JDIR		=  pmu-events/arch/$(SRCARCH)
 JSON		=  $(shell [ -d $(JDIR) ] &&				\
 			find $(JDIR) -name '*.json' -o -name 'mapfile.csv')
 #
@@ -10,4 +10,4 @@
 # directory and create tables in pmu-events.c.
 #
 $(OUTPUT)pmu-events/pmu-events.c: $(JSON) $(JEVENTS)
-	$(Q)$(call echo-cmd,gen)$(JEVENTS) $(ARCH) pmu-events/arch $(OUTPUT)pmu-events/pmu-events.c $(V)
+	$(Q)$(call echo-cmd,gen)$(JEVENTS) $(SRCARCH) pmu-events/arch $(OUTPUT)pmu-events/pmu-events.c $(V)
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 8a4ce49..546250a 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -71,7 +71,7 @@
 	$(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@
 	$(Q)echo ';' >> $@
 
-ifeq ($(ARCH),$(filter $(ARCH),x86 arm arm64 powerpc))
+ifeq ($(SRCARCH),$(filter $(SRCARCH),x86 arm arm64 powerpc))
 perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
 endif
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 5337f49..28bdb48 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -826,7 +826,7 @@
 
 /*
  * default get_cpuid(): nothing gets recorded
- * actual implementation must be in arch/$(ARCH)/util/header.c
+ * actual implementation must be in arch/$(SRCARCH)/util/header.c
  */
 int __weak get_cpuid(char *buffer __maybe_unused, size_t sz __maybe_unused)
 {