Merge branch 'linus' into locking/core, to resolve conflict

Conflicts:
	arch/arm/include/asm/percpu.h

As Stephen Rothwell noted, there's a conflict between this commit
in locking/core:

  a21ee6055c30 ("lockdep: Change hardirq{s_enabled,_context} to per-cpu variables")

and this fresh upstream commit:

  aa54ea903abb ("ARM: percpu.h: fix build error")

a21ee6055c30 is a simpler solution to the dependency problem and doesn't
further increase header hell - so this conflict resolution effectively
reverts aa54ea903abb and uses the a21ee6055c30 solution.

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

27 files changed, 110 insertions, 70 deletions

diff --git a/arch/arm/boot/dts/armada-38x.dtsi b/arch/arm/boot/dts/armada-38x.dtsi
index 348116501aa2..9b1a24cc5e91 100644
--- a/arch/arm/boot/dts/armada-38x.dtsi
+++ b/arch/arm/boot/dts/armada-38x.dtsi
@@ -342,7 +342,8 @@
 
 			comphy: phy@18300 {
 				compatible = "marvell,armada-380-comphy";
-				reg = <0x18300 0x100>;
+				reg-names = "comphy", "conf";
+				reg = <0x18300 0x100>, <0x18460 4>;
 				#address-cells = <1>;
 				#size-cells = <0>;
 
diff --git a/arch/arm/boot/dts/imx6qdl-icore.dtsi b/arch/arm/boot/dts/imx6qdl-icore.dtsi
index 756f3a9f1b4f..12997dae35d9 100644
--- a/arch/arm/boot/dts/imx6qdl-icore.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-icore.dtsi
@@ -397,7 +397,7 @@
 
 	pinctrl_usbotg: usbotggrp {
 		fsl,pins = <
-			MX6QDL_PAD_GPIO_1__USB_OTG_ID 0x17059
+			MX6QDL_PAD_ENET_RX_ER__USB_OTG_ID 0x17059
 		>;
 	};
 
@@ -409,6 +409,7 @@
 			MX6QDL_PAD_SD1_DAT1__SD1_DATA1 0x17070
 			MX6QDL_PAD_SD1_DAT2__SD1_DATA2 0x17070
 			MX6QDL_PAD_SD1_DAT3__SD1_DATA3 0x17070
+			MX6QDL_PAD_GPIO_1__GPIO1_IO01  0x1b0b0
 		>;
 	};
 
diff --git a/arch/arm/boot/dts/imx6sx-sabreauto.dts b/arch/arm/boot/dts/imx6sx-sabreauto.dts
index 825924448ab4..14fd1de52a68 100644
--- a/arch/arm/boot/dts/imx6sx-sabreauto.dts
+++ b/arch/arm/boot/dts/imx6sx-sabreauto.dts
@@ -99,7 +99,7 @@
 &fec2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_enet2>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-handle = <&ethphy0>;
 	fsl,magic-packet;
 	status = "okay";
diff --git a/arch/arm/boot/dts/imx6sx-sdb.dtsi b/arch/arm/boot/dts/imx6sx-sdb.dtsi
index 3e5fb72f21fc..c99aa273c296 100644
--- a/arch/arm/boot/dts/imx6sx-sdb.dtsi
+++ b/arch/arm/boot/dts/imx6sx-sdb.dtsi
@@ -213,7 +213,7 @@
 &fec2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_enet2>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-handle = <&ethphy2>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/keystone-k2g-evm.dts b/arch/arm/boot/dts/keystone-k2g-evm.dts
index db640bab8c1d..8b3d64c913d8 100644
--- a/arch/arm/boot/dts/keystone-k2g-evm.dts
+++ b/arch/arm/boot/dts/keystone-k2g-evm.dts
@@ -402,7 +402,7 @@
 
 &gbe0 {
 	phy-handle = <&ethphy0>;
-	phy-mode = "rgmii-id";
+	phy-mode = "rgmii-rxid";
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi
index bf531efc0610..0f95a6ef8543 100644
--- a/arch/arm/boot/dts/sun4i-a10.dtsi
+++ b/arch/arm/boot/dts/sun4i-a10.dtsi
@@ -198,7 +198,7 @@
 		default-pool {
 			compatible = "shared-dma-pool";
 			size = <0x6000000>;
-			alloc-ranges = <0x4a000000 0x6000000>;
+			alloc-ranges = <0x40000000 0x10000000>;
 			reusable;
 			linux,cma-default;
 		};
diff --git a/arch/arm/boot/dts/sun5i.dtsi b/arch/arm/boot/dts/sun5i.dtsi
index e6b036734a64..c2b4fbf552a3 100644
--- a/arch/arm/boot/dts/sun5i.dtsi
+++ b/arch/arm/boot/dts/sun5i.dtsi
@@ -117,7 +117,7 @@
 		default-pool {
 			compatible = "shared-dma-pool";
 			size = <0x6000000>;
-			alloc-ranges = <0x4a000000 0x6000000>;
+			alloc-ranges = <0x40000000 0x10000000>;
 			reusable;
 			linux,cma-default;
 		};
diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi
index ffe1d10a1a84..6d6a37940db2 100644
--- a/arch/arm/boot/dts/sun7i-a20.dtsi
+++ b/arch/arm/boot/dts/sun7i-a20.dtsi
@@ -181,7 +181,7 @@
 		default-pool {
 			compatible = "shared-dma-pool";
 			size = <0x6000000>;
-			alloc-ranges = <0x4a000000 0x6000000>;
+			alloc-ranges = <0x40000000 0x10000000>;
 			reusable;
 			linux,cma-default;
 		};
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index a0d94d063fa8..70f5905954dd 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -137,7 +137,7 @@ export	TEXT_OFFSET
 
 core-y		+= arch/arm64/
 libs-y		:= arch/arm64/lib/ $(libs-y)
-core-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a
+libs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a
 
 # Default target when executing plain make
 boot		:= arch/arm64/boot
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi
index 78b1361dfbb9..9ce78a7b117d 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi
@@ -161,6 +161,7 @@
 			resets = <&ccu RST_BUS_VE>;
 			interrupts = <GIC_SPI 89 IRQ_TYPE_LEVEL_HIGH>;
 			allwinner,sram = <&ve_sram 1>;
+			iommus = <&iommu 3>;
 		};
 
 		gpu: gpu@1800000 {
diff --git a/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts b/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts
index c8243da71041..eb01cc96ba7a 100644
--- a/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts
+++ b/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts
@@ -454,10 +454,7 @@
 	status = "okay";
 	phy-mode = "2500base-x";
 	phys = <&cp1_comphy5 2>;
-	fixed-link {
-		speed = <2500>;
-		full-duplex;
-	};
+	managed = "in-band-status";
 };
 
 &cp1_spi1 {
diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile
index d88148bef6b0..5139a5f19256 100644
--- a/arch/arm64/kernel/vdso32/Makefile
+++ b/arch/arm64/kernel/vdso32/Makefile
@@ -14,7 +14,7 @@ COMPAT_GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE_COMPAT)elfedit))
 COMPAT_GCC_TOOLCHAIN := $(realpath $(COMPAT_GCC_TOOLCHAIN_DIR)/..)
 
 CC_COMPAT_CLANG_FLAGS := --target=$(notdir $(CROSS_COMPILE_COMPAT:%-=%))
-CC_COMPAT_CLANG_FLAGS += --prefix=$(COMPAT_GCC_TOOLCHAIN_DIR)
+CC_COMPAT_CLANG_FLAGS += --prefix=$(COMPAT_GCC_TOOLCHAIN_DIR)$(notdir $(CROSS_COMPILE_COMPAT))
 CC_COMPAT_CLANG_FLAGS += -no-integrated-as -Qunused-arguments
 ifneq ($(COMPAT_GCC_TOOLCHAIN),)
 CC_COMPAT_CLANG_FLAGS += --gcc-toolchain=$(COMPAT_GCC_TOOLCHAIN)
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index f960e2f32b1b..03862320f779 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -210,6 +210,8 @@ atomic64_set(atomic64_t *v, s64 i)
 	_atomic_spin_unlock_irqrestore(v, flags);
 }
 
+#define atomic64_set_release(v, i)	atomic64_set((v), (i))
+
 static __inline__ s64
 atomic64_read(const atomic64_t *v)
 {
diff --git a/arch/parisc/include/asm/cmpxchg.h b/arch/parisc/include/asm/cmpxchg.h
index ab5c215cf46c..068958575871 100644
--- a/arch/parisc/include/asm/cmpxchg.h
+++ b/arch/parisc/include/asm/cmpxchg.h
@@ -60,6 +60,7 @@ extern void __cmpxchg_called_with_bad_pointer(void);
 extern unsigned long __cmpxchg_u32(volatile unsigned int *m, unsigned int old,
 				   unsigned int new_);
 extern u64 __cmpxchg_u64(volatile u64 *ptr, u64 old, u64 new_);
+extern u8 __cmpxchg_u8(volatile u8 *ptr, u8 old, u8 new_);
 
 /* don't worry...optimizer will get rid of most of this */
 static inline unsigned long
@@ -71,6 +72,7 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new_, int size)
 #endif
 	case 4: return __cmpxchg_u32((unsigned int *)ptr,
 				     (unsigned int)old, (unsigned int)new_);
+	case 1: return __cmpxchg_u8((u8 *)ptr, (u8)old, (u8)new_);
 	}
 	__cmpxchg_called_with_bad_pointer();
 	return old;
diff --git a/arch/parisc/lib/bitops.c b/arch/parisc/lib/bitops.c
index 70ffbcf889b8..2e4d1f05a926 100644
--- a/arch/parisc/lib/bitops.c
+++ b/arch/parisc/lib/bitops.c
@@ -79,3 +79,15 @@ unsigned long __cmpxchg_u32(volatile unsigned int *ptr, unsigned int old, unsign
 	_atomic_spin_unlock_irqrestore(ptr, flags);
 	return (unsigned long)prev;
 }
+
+u8 __cmpxchg_u8(volatile u8 *ptr, u8 old, u8 new)
+{
+	unsigned long flags;
+	u8 prev;
+
+	_atomic_spin_lock_irqsave(ptr, flags);
+	if ((prev = *ptr) == old)
+		*ptr = new;
+	_atomic_spin_unlock_irqrestore(ptr, flags);
+	return prev;
+}
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index f4adb3684f3d..79e9d55bdf1a 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -95,19 +95,40 @@ void __init mem_init(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 static void __init setup_initrd(void)
 {
+	phys_addr_t start;
 	unsigned long size;
 
-	if (initrd_start >= initrd_end) {
-		pr_info("initrd not found or empty");
+	/* Ignore the virtul address computed during device tree parsing */
+	initrd_start = initrd_end = 0;
+
+	if (!phys_initrd_size)
+		return;
+	/*
+	 * Round the memory region to page boundaries as per free_initrd_mem()
+	 * This allows us to detect whether the pages overlapping the initrd
+	 * are in use, but more importantly, reserves the entire set of pages
+	 * as we don't want these pages allocated for other purposes.
+	 */
+	start = round_down(phys_initrd_start, PAGE_SIZE);
+	size = phys_initrd_size + (phys_initrd_start - start);
+	size = round_up(size, PAGE_SIZE);
+
+	if (!memblock_is_region_memory(start, size)) {
+		pr_err("INITRD: 0x%08llx+0x%08lx is not a memory region",
+		       (u64)start, size);
 		goto disable;
 	}
-	if (__pa_symbol(initrd_end) > PFN_PHYS(max_low_pfn)) {
-		pr_err("initrd extends beyond end of memory");
+
+	if (memblock_is_region_reserved(start, size)) {
+		pr_err("INITRD: 0x%08llx+0x%08lx overlaps in-use memory region\n",
+		       (u64)start, size);
 		goto disable;
 	}
 
-	size = initrd_end - initrd_start;
-	memblock_reserve(__pa_symbol(initrd_start), size);
+	memblock_reserve(start, size);
+	/* Now convert initrd to virtual addresses */
+	initrd_start = (unsigned long)__va(phys_initrd_start);
+	initrd_end = initrd_start + phys_initrd_size;
 	initrd_below_start_ok = 1;
 
 	pr_info("Initial ramdisk at: 0x%p (%lu bytes)\n",
@@ -126,33 +147,36 @@ void __init setup_bootmem(void)
 {
 	struct memblock_region *reg;
 	phys_addr_t mem_size = 0;
+	phys_addr_t total_mem = 0;
+	phys_addr_t mem_start, end = 0;
 	phys_addr_t vmlinux_end = __pa_symbol(&_end);
 	phys_addr_t vmlinux_start = __pa_symbol(&_start);
 
 	/* Find the memory region containing the kernel */
 	for_each_memblock(memory, reg) {
-		phys_addr_t end = reg->base + reg->size;
-
-		if (reg->base <= vmlinux_start && vmlinux_end <= end) {
-			mem_size = min(reg->size, (phys_addr_t)-PAGE_OFFSET);
-
-			/*
-			 * Remove memblock from the end of usable area to the
-			 * end of region
-			 */
-			if (reg->base + mem_size < end)
-				memblock_remove(reg->base + mem_size,
-						end - reg->base - mem_size);
-		}
+		end = reg->base + reg->size;
+		if (!total_mem)
+			mem_start = reg->base;
+		if (reg->base <= vmlinux_start && vmlinux_end <= end)
+			BUG_ON(reg->size == 0);
+		total_mem = total_mem + reg->size;
 	}
-	BUG_ON(mem_size == 0);
+
+	/*
+	 * Remove memblock from the end of usable area to the
+	 * end of region
+	 */
+	mem_size = min(total_mem, (phys_addr_t)-PAGE_OFFSET);
+	if (mem_start + mem_size < end)
+		memblock_remove(mem_start + mem_size,
+				end - mem_start - mem_size);
 
 	/* Reserve from the start of the kernel to the end of the kernel */
 	memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start);
 
-	set_max_mapnr(PFN_DOWN(mem_size));
 	max_pfn = PFN_DOWN(memblock_end_of_DRAM());
 	max_low_pfn = max_pfn;
+	set_max_mapnr(max_low_pfn);
 
 #ifdef CONFIG_BLK_DEV_INITRD
 	setup_initrd();
diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c
index 4a8b61806633..87b4ab3d3c77 100644
--- a/arch/riscv/mm/kasan_init.c
+++ b/arch/riscv/mm/kasan_init.c
@@ -44,7 +44,7 @@ asmlinkage void __init kasan_early_init(void)
 				(__pa(((uintptr_t) kasan_early_shadow_pmd))),
 				__pgprot(_PAGE_TABLE)));
 
-	flush_tlb_all();
+	local_flush_tlb_all();
 }
 
 static void __init populate(void *start, void *end)
@@ -79,7 +79,7 @@ static void __init populate(void *start, void *end)
 			pfn_pgd(PFN_DOWN(__pa(&pmd[offset])),
 				__pgprot(_PAGE_TABLE)));
 
-	flush_tlb_all();
+	local_flush_tlb_all();
 	memset(start, 0, end - start);
 }
 
diff --git a/arch/s390/kernel/perf_cpum_cf_events.c b/arch/s390/kernel/perf_cpum_cf_events.c
index 1e3df52b2b65..37265f551a11 100644
--- a/arch/s390/kernel/perf_cpum_cf_events.c
+++ b/arch/s390/kernel/perf_cpum_cf_events.c
@@ -292,7 +292,7 @@ CPUMF_EVENT_ATTR(cf_z15, TX_C_TABORT_SPECIAL, 0x00f5);
 CPUMF_EVENT_ATTR(cf_z15, DFLT_ACCESS, 0x00f7);
 CPUMF_EVENT_ATTR(cf_z15, DFLT_CYCLES, 0x00fc);
 CPUMF_EVENT_ATTR(cf_z15, DFLT_CC, 0x00108);
-CPUMF_EVENT_ATTR(cf_z15, DFLT_CCERROR, 0x00109);
+CPUMF_EVENT_ATTR(cf_z15, DFLT_CCFINISH, 0x00109);
 CPUMF_EVENT_ATTR(cf_z15, MT_DIAG_CYCLES_ONE_THR_ACTIVE, 0x01c0);
 CPUMF_EVENT_ATTR(cf_z15, MT_DIAG_CYCLES_TWO_THR_ACTIVE, 0x01c1);
 
@@ -629,7 +629,7 @@ static struct attribute *cpumcf_z15_pmu_event_attr[] __initdata = {
 	CPUMF_EVENT_PTR(cf_z15, DFLT_ACCESS),
 	CPUMF_EVENT_PTR(cf_z15, DFLT_CYCLES),
 	CPUMF_EVENT_PTR(cf_z15, DFLT_CC),
-	CPUMF_EVENT_PTR(cf_z15, DFLT_CCERROR),
+	CPUMF_EVENT_PTR(cf_z15, DFLT_CCFINISH),
 	CPUMF_EVENT_PTR(cf_z15, MT_DIAG_CYCLES_ONE_THR_ACTIVE),
 	CPUMF_EVENT_PTR(cf_z15, MT_DIAG_CYCLES_TWO_THR_ACTIVE),
 	NULL,
diff --git a/arch/sh/include/asm/pgalloc.h b/arch/sh/include/asm/pgalloc.h
index 22d968bfe9bb..d770da3f8b6f 100644
--- a/arch/sh/include/asm/pgalloc.h
+++ b/arch/sh/include/asm/pgalloc.h
@@ -12,6 +12,7 @@ extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
 extern void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd);
 extern pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address);
 extern void pmd_free(struct mm_struct *mm, pmd_t *pmd);
+#define __pmd_free_tlb(tlb, pmdp, addr)		pmd_free((tlb)->mm, (pmdp))
 #endif
 
 static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
@@ -33,13 +34,4 @@ do {							\
 	tlb_remove_page((tlb), (pte));			\
 } while (0)
 
-#if CONFIG_PGTABLE_LEVELS > 2
-#define __pmd_free_tlb(tlb, pmdp, addr)			\
-do {							\
-	struct page *page = virt_to_page(pmdp);		\
-	pgtable_pmd_page_dtor(page);			\
-	tlb_remove_page((tlb), page);			\
-} while (0);
-#endif
-
 #endif /* __ASM_SH_PGALLOC_H */
diff --git a/arch/sh/kernel/entry-common.S b/arch/sh/kernel/entry-common.S
index 956a7a03b0c8..9bac5bbb67f3 100644
--- a/arch/sh/kernel/entry-common.S
+++ b/arch/sh/kernel/entry-common.S
@@ -199,7 +199,7 @@ syscall_trace_entry:
 	mov.l	@(OFF_R7,r15), r7   ! arg3
 	mov.l	@(OFF_R3,r15), r3   ! syscall_nr
 	!
-	mov.l	2f, r10			! Number of syscalls
+	mov.l	6f, r10			! Number of syscalls
 	cmp/hs	r10, r3
 	bf	syscall_call
 	mov	#-ENOSYS, r0
@@ -353,7 +353,7 @@ ENTRY(system_call)
 	tst	r9, r8
 	bf	syscall_trace_entry
 	!
-	mov.l	2f, r8			! Number of syscalls
+	mov.l	6f, r8			! Number of syscalls
 	cmp/hs	r8, r3
 	bt	syscall_badsys
 	!
@@ -392,7 +392,7 @@ syscall_exit:
 #if !defined(CONFIG_CPU_SH2)
 1:	.long	TRA
 #endif
-2:	.long	NR_syscalls
+6:	.long	NR_syscalls
 3:	.long	sys_call_table
 7:	.long	do_syscall_trace_enter
 8:	.long	do_syscall_trace_leave
diff --git a/arch/x86/include/asm/iosf_mbi.h b/arch/x86/include/asm/iosf_mbi.h
index 5270ff39b9af..a1911fea8739 100644
--- a/arch/x86/include/asm/iosf_mbi.h
+++ b/arch/x86/include/asm/iosf_mbi.h
@@ -39,6 +39,7 @@
 #define BT_MBI_UNIT_PMC		0x04
 #define BT_MBI_UNIT_GFX		0x06
 #define BT_MBI_UNIT_SMI		0x0C
+#define BT_MBI_UNIT_CCK		0x14
 #define BT_MBI_UNIT_USB		0x43
 #define BT_MBI_UNIT_SATA	0xA3
 #define BT_MBI_UNIT_PCIE	0xA6
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index b037cfa7c0c5..7401cc12c3cc 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -71,6 +71,22 @@ static void printk_stack_address(unsigned long address, int reliable,
 	printk("%s %s%pB\n", log_lvl, reliable ? "" : "? ", (void *)address);
 }
 
+static int copy_code(struct pt_regs *regs, u8 *buf, unsigned long src,
+		     unsigned int nbytes)
+{
+	if (!user_mode(regs))
+		return copy_from_kernel_nofault(buf, (u8 *)src, nbytes);
+
+	/*
+	 * Make sure userspace isn't trying to trick us into dumping kernel
+	 * memory by pointing the userspace instruction pointer at it.
+	 */
+	if (__chk_range_not_ok(src, nbytes, TASK_SIZE_MAX))
+		return -EINVAL;
+
+	return copy_from_user_nmi(buf, (void __user *)src, nbytes);
+}
+
 /*
  * There are a couple of reasons for the 2/3rd prologue, courtesy of Linus:
  *
@@ -97,17 +113,8 @@ void show_opcodes(struct pt_regs *regs, const char *loglvl)
 #define OPCODE_BUFSIZE (PROLOGUE_SIZE + 1 + EPILOGUE_SIZE)
 	u8 opcodes[OPCODE_BUFSIZE];
 	unsigned long prologue = regs->ip - PROLOGUE_SIZE;
-	bool bad_ip;
-
-	/*
-	 * Make sure userspace isn't trying to trick us into dumping kernel
-	 * memory by pointing the userspace instruction pointer at it.
-	 */
-	bad_ip = user_mode(regs) &&
-		__chk_range_not_ok(prologue, OPCODE_BUFSIZE, TASK_SIZE_MAX);
 
-	if (bad_ip || copy_from_kernel_nofault(opcodes, (u8 *)prologue,
-					OPCODE_BUFSIZE)) {
+	if (copy_code(regs, opcodes, prologue, sizeof(opcodes))) {
 		printk("%sCode: Bad RIP value.\n", loglvl);
 	} else {
 		printk("%sCode: %" __stringify(PROLOGUE_SIZE) "ph <%02x> %"
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index bda2e5eaca0e..ad3a2b37927d 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -1074,7 +1074,7 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int of
 		copy_part(offsetof(struct fxregs_state, st_space), 128,
 			  &xsave->i387.st_space, &kbuf, &offset_start, &count);
 	if (header.xfeatures & XFEATURE_MASK_SSE)
-		copy_part(xstate_offsets[XFEATURE_MASK_SSE], 256,
+		copy_part(xstate_offsets[XFEATURE_SSE], 256,
 			  &xsave->i387.xmm_space, &kbuf, &offset_start, &count);
 	/*
 	 * Fill xsave->i387.sw_reserved value for ptrace frame:
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 6ad43fc44556..2fd698e28e4d 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -58,7 +58,6 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry,
 			 * or a page fault), which can make frame pointers
 			 * unreliable.
 			 */
-
 			if (IS_ENABLED(CONFIG_FRAME_POINTER))
 				return -EINVAL;
 		}
@@ -81,10 +80,6 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry,
 	if (unwind_error(&state))
 		return -EINVAL;
 
-	/* Success path for non-user tasks, i.e. kthreads and idle tasks */
-	if (!(task->flags & (PF_KTHREAD | PF_IDLE)))
-		return -EINVAL;
-
 	return 0;
 }
 
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 7f969b2d240f..ec88bbe08a32 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -440,8 +440,11 @@ bool unwind_next_frame(struct unwind_state *state)
 	/*
 	 * Find the orc_entry associated with the text address.
 	 *
-	 * Decrement call return addresses by one so they work for sibling
-	 * calls and calls to noreturn functions.
+	 * For a call frame (as opposed to a signal frame), state->ip points to
+	 * the instruction after the call.  That instruction's stack layout
+	 * could be different from the call instruction's layout, for example
+	 * if the call was to a noreturn function.  So get the ORC data for the
+	 * call instruction itself.
 	 */
 	orc = orc_find(state->signal ? state->ip : state->ip - 1);
 	if (!orc) {
@@ -662,6 +665,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 		state->sp = task->thread.sp;
 		state->bp = READ_ONCE_NOCHECK(frame->bp);
 		state->ip = READ_ONCE_NOCHECK(frame->ret_addr);
+		state->signal = (void *)state->ip == ret_from_fork;
 	}
 
 	if (get_stack_info((unsigned long *)state->sp, state->task,
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 3bfc8dd8a43d..9a03e5b23135 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -358,6 +358,7 @@ SECTIONS
 	.bss : AT(ADDR(.bss) - LOAD_OFFSET) {
 		__bss_start = .;
 		*(.bss..page_aligned)
+		. = ALIGN(PAGE_SIZE);
 		*(BSS_MAIN)
 		BSS_DECRYPTED
 		. = ALIGN(PAGE_SIZE);
diff --git a/arch/xtensa/include/asm/checksum.h b/arch/xtensa/include/asm/checksum.h
index d8292cc9ebdf..243a5fe79d3c 100644
--- a/arch/xtensa/include/asm/checksum.h
+++ b/arch/xtensa/include/asm/checksum.h
@@ -57,7 +57,7 @@ static inline
 __wsum csum_and_copy_from_user(const void __user *src, void *dst,
 				   int len, __wsum sum, int *err_ptr)
 {
-	if (access_ok(dst, len))
+	if (access_ok(src, len))
 		return csum_partial_copy_generic((__force const void *)src, dst,
 					len, sum, err_ptr, NULL);
 	if (len)