Merging upstream version 6.8.11.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

27 files changed, 162 insertions, 103 deletions

diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S
index a86a1d4f34..93afd1005b 100644
--- a/arch/arm/kernel/sleep.S
+++ b/arch/arm/kernel/sleep.S
@@ -127,6 +127,10 @@ cpu_resume_after_mmu:
 	instr_sync
 #endif
 	bl	cpu_init		@ restore the und/abt/irq banked regs
+#if defined(CONFIG_KASAN) && defined(CONFIG_KASAN_STACK)
+	mov	r0, sp
+	bl	kasan_unpoison_task_stack_below
+#endif
 	mov	r0, #0			@ return zero on success
 	ldmfd	sp!, {r4 - r11, pc}
 ENDPROC(cpu_resume_after_mmu)
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 1d672457d0..72b5cd697f 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -871,16 +871,11 @@ static inline void emit_a32_alu_r64(const bool is64, const s8 dst[],
 }
 
 /* dst = src (4 bytes)*/
-static inline void emit_a32_mov_r(const s8 dst, const s8 src, const u8 off,
-				  struct jit_ctx *ctx) {
+static inline void emit_a32_mov_r(const s8 dst, const s8 src, struct jit_ctx *ctx) {
 	const s8 *tmp = bpf2a32[TMP_REG_1];
 	s8 rt;
 
 	rt = arm_bpf_get_reg32(src, tmp[0], ctx);
-	if (off && off != 32) {
-		emit(ARM_LSL_I(rt, rt, 32 - off), ctx);
-		emit(ARM_ASR_I(rt, rt, 32 - off), ctx);
-	}
 	arm_bpf_put_reg32(dst, rt, ctx);
 }
 
@@ -889,15 +884,15 @@ static inline void emit_a32_mov_r64(const bool is64, const s8 dst[],
 				  const s8 src[],
 				  struct jit_ctx *ctx) {
 	if (!is64) {
-		emit_a32_mov_r(dst_lo, src_lo, 0, ctx);
+		emit_a32_mov_r(dst_lo, src_lo, ctx);
 		if (!ctx->prog->aux->verifier_zext)
 			/* Zero out high 4 bytes */
 			emit_a32_mov_i(dst_hi, 0, ctx);
 	} else if (__LINUX_ARM_ARCH__ < 6 &&
 		   ctx->cpu_architecture < CPU_ARCH_ARMv5TE) {
 		/* complete 8 byte move */
-		emit_a32_mov_r(dst_lo, src_lo, 0, ctx);
-		emit_a32_mov_r(dst_hi, src_hi, 0, ctx);
+		emit_a32_mov_r(dst_lo, src_lo, ctx);
+		emit_a32_mov_r(dst_hi, src_hi, ctx);
 	} else if (is_stacked(src_lo) && is_stacked(dst_lo)) {
 		const u8 *tmp = bpf2a32[TMP_REG_1];
 
@@ -917,17 +912,52 @@ static inline void emit_a32_mov_r64(const bool is64, const s8 dst[],
 static inline void emit_a32_movsx_r64(const bool is64, const u8 off, const s8 dst[], const s8 src[],
 				      struct jit_ctx *ctx) {
 	const s8 *tmp = bpf2a32[TMP_REG_1];
-	const s8 *rt;
+	s8 rs;
+	s8 rd;
 
-	rt = arm_bpf_get_reg64(dst, tmp, ctx);
+	if (is_stacked(dst_lo))
+		rd = tmp[1];
+	else
+		rd = dst_lo;
+	rs = arm_bpf_get_reg32(src_lo, rd, ctx);
+	/* rs may be one of src[1], dst[1], or tmp[1] */
+
+	/* Sign extend rs if needed. If off == 32, lower 32-bits of src are moved to dst and sign
+	 * extension only happens in the upper 64 bits.
+	 */
+	if (off != 32) {
+		/* Sign extend rs into rd */
+		emit(ARM_LSL_I(rd, rs, 32 - off), ctx);
+		emit(ARM_ASR_I(rd, rd, 32 - off), ctx);
+	} else {
+		rd = rs;
+	}
+
+	/* Write rd to dst_lo
+	 *
+	 * Optimization:
+	 * Assume:
+	 * 1. dst == src and stacked.
+	 * 2. off == 32
+	 *
+	 * In this case src_lo was loaded into rd(tmp[1]) but rd was not sign extended as off==32.
+	 * So, we don't need to write rd back to dst_lo as they have the same value.
+	 * This saves us one str instruction.
+	 */
+	if (dst_lo != src_lo || off != 32)
+		arm_bpf_put_reg32(dst_lo, rd, ctx);
 
-	emit_a32_mov_r(dst_lo, src_lo, off, ctx);
 	if (!is64) {
 		if (!ctx->prog->aux->verifier_zext)
 			/* Zero out high 4 bytes */
 			emit_a32_mov_i(dst_hi, 0, ctx);
 	} else {
-		emit(ARM_ASR_I(rt[0], rt[1], 31), ctx);
+		if (is_stacked(dst_hi)) {
+			emit(ARM_ASR_I(tmp[0], rd, 31), ctx);
+			arm_bpf_put_reg32(dst_hi, tmp[0], ctx);
+		} else {
+			emit(ARM_ASR_I(dst_hi, rd, 31), ctx);
+		}
 	}
 }
 
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-pico6.dts b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-pico6.dts
index a2e74b8293..6a7ae61651 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-pico6.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-pico6.dts
@@ -82,7 +82,8 @@
 };
 
 &mmc1 {
-	bt_reset: bt-reset {
+	bluetooth@2 {
+		reg = <2>;
 		compatible = "mediatek,mt7921s-bluetooth";
 		pinctrl-names = "default";
 		pinctrl-0 = <&bt_pins_reset>;
diff --git a/arch/arm64/boot/dts/qcom/sa8155p-adp.dts b/arch/arm64/boot/dts/qcom/sa8155p-adp.dts
index 5e4287f8c8..b2cf2c9883 100644
--- a/arch/arm64/boot/dts/qcom/sa8155p-adp.dts
+++ b/arch/arm64/boot/dts/qcom/sa8155p-adp.dts
@@ -367,6 +367,16 @@
 	};
 };
 
+&pmm8155au_1_gpios {
+	pmm8155au_1_sdc2_cd: sdc2-cd-default-state {
+		pins = "gpio4";
+		function = "normal";
+		input-enable;
+		bias-pull-up;
+		power-source = <0>;
+	};
+};
+
 &qupv3_id_1 {
 	status = "okay";
 };
@@ -384,10 +394,10 @@
 &sdhc_2 {
 	status = "okay";
 
-	cd-gpios = <&tlmm 4 GPIO_ACTIVE_LOW>;
+	cd-gpios = <&pmm8155au_1_gpios 4 GPIO_ACTIVE_LOW>;
 	pinctrl-names = "default", "sleep";
-	pinctrl-0 = <&sdc2_on>;
-	pinctrl-1 = <&sdc2_off>;
+	pinctrl-0 = <&sdc2_on &pmm8155au_1_sdc2_cd>;
+	pinctrl-1 = <&sdc2_off &pmm8155au_1_sdc2_cd>;
 	vqmmc-supply = <&vreg_l13c_2p96>; /* IO line power */
 	vmmc-supply = <&vreg_l17a_2p96>;  /* Card power line */
 	bus-width = <4>;
@@ -505,13 +515,6 @@
 			bias-pull-up;		/* pull up */
 			drive-strength = <16>;	/* 16 MA */
 		};
-
-		sd-cd-pins {
-			pins = "gpio96";
-			function = "gpio";
-			bias-pull-up;		/* pull up */
-			drive-strength = <2>;	/* 2 MA */
-		};
 	};
 
 	sdc2_off: sdc2-off-state {
@@ -532,13 +535,6 @@
 			bias-pull-up;		/* pull up */
 			drive-strength = <2>;	/* 2 MA */
 		};
-
-		sd-cd-pins {
-			pins = "gpio96";
-			function = "gpio";
-			bias-pull-up;		/* pull up */
-			drive-strength = <2>;	/* 2 MA */
-		};
 	};
 
 	usb2phy_ac_en1_default: usb2phy-ac-en1-default-state {
diff --git a/arch/arm64/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c
index f48b8dab8b..1d26bb5b02 100644
--- a/arch/arm64/kvm/vgic/vgic-kvm-device.c
+++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c
@@ -338,12 +338,12 @@ int kvm_register_vgic_device(unsigned long type)
 int vgic_v2_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr,
 		       struct vgic_reg_attr *reg_attr)
 {
-	int cpuid;
+	int cpuid = FIELD_GET(KVM_DEV_ARM_VGIC_CPUID_MASK, attr->attr);
 
-	cpuid = FIELD_GET(KVM_DEV_ARM_VGIC_CPUID_MASK, attr->attr);
-
-	reg_attr->vcpu = kvm_get_vcpu_by_id(dev->kvm, cpuid);
 	reg_attr->addr = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK;
+	reg_attr->vcpu = kvm_get_vcpu_by_id(dev->kvm, cpuid);
+	if (!reg_attr->vcpu)
+		return -EINVAL;
 
 	return 0;
 }
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 00217d8d03..ceed77c29f 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -1738,15 +1738,15 @@ static void invoke_bpf_prog(struct jit_ctx *ctx, struct bpf_tramp_link *l,
 
 	emit_call(enter_prog, ctx);
 
+	/* save return value to callee saved register x20 */
+	emit(A64_MOV(1, A64_R(20), A64_R(0)), ctx);
+
 	/* if (__bpf_prog_enter(prog) == 0)
 	 *         goto skip_exec_of_prog;
 	 */
 	branch = ctx->image + ctx->idx;
 	emit(A64_NOP, ctx);
 
-	/* save return value to callee saved register x20 */
-	emit(A64_MOV(1, A64_R(20), A64_R(0)), ctx);
-
 	emit(A64_ADD_I(1, A64_R(0), A64_SP, args_off), ctx);
 	if (!p->jited)
 		emit_addr_mov_i64(A64_R(1), (const u64)p->insnsi, ctx);
diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h
index d14d0e37ad..4a2b40ce39 100644
--- a/arch/mips/include/asm/ptrace.h
+++ b/arch/mips/include/asm/ptrace.h
@@ -159,7 +159,7 @@ extern unsigned long exception_ip(struct pt_regs *regs);
 #define exception_ip(regs) exception_ip(regs)
 #define profile_pc(regs) instruction_pointer(regs)
 
-extern asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall);
+extern asmlinkage long syscall_trace_enter(struct pt_regs *regs);
 extern asmlinkage void syscall_trace_leave(struct pt_regs *regs);
 
 extern void die(const char *, struct pt_regs *) __noreturn;
diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c
index d1b11f66f7..cb1045ebab 100644
--- a/arch/mips/kernel/asm-offsets.c
+++ b/arch/mips/kernel/asm-offsets.c
@@ -101,6 +101,7 @@ void output_thread_info_defines(void)
 	OFFSET(TI_CPU, thread_info, cpu);
 	OFFSET(TI_PRE_COUNT, thread_info, preempt_count);
 	OFFSET(TI_REGS, thread_info, regs);
+	OFFSET(TI_SYSCALL, thread_info, syscall);
 	DEFINE(_THREAD_SIZE, THREAD_SIZE);
 	DEFINE(_THREAD_MASK, THREAD_MASK);
 	DEFINE(_IRQ_STACK_SIZE, IRQ_STACK_SIZE);
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index 59288c13b5..61503a3606 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -1317,16 +1317,13 @@ long arch_ptrace(struct task_struct *child, long request,
  * Notification of system call entry/exit
  * - triggered by current->work.syscall_trace
  */
-asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall)
+asmlinkage long syscall_trace_enter(struct pt_regs *regs)
 {
 	user_exit();
 
-	current_thread_info()->syscall = syscall;
-
 	if (test_thread_flag(TIF_SYSCALL_TRACE)) {
 		if (ptrace_report_syscall_entry(regs))
 			return -1;
-		syscall = current_thread_info()->syscall;
 	}
 
 #ifdef CONFIG_SECCOMP
@@ -1335,7 +1332,7 @@ asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall)
 		struct seccomp_data sd;
 		unsigned long args[6];
 
-		sd.nr = syscall;
+		sd.nr = current_thread_info()->syscall;
 		sd.arch = syscall_get_arch(current);
 		syscall_get_arguments(current, regs, args);
 		for (i = 0; i < 6; i++)
@@ -1345,23 +1342,23 @@ asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall)
 		ret = __secure_computing(&sd);
 		if (ret == -1)
 			return ret;
-		syscall = current_thread_info()->syscall;
 	}
 #endif
 
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
 		trace_sys_enter(regs, regs->regs[2]);
 
-	audit_syscall_entry(syscall, regs->regs[4], regs->regs[5],
+	audit_syscall_entry(current_thread_info()->syscall,
+			    regs->regs[4], regs->regs[5],
 			    regs->regs[6], regs->regs[7]);
 
 	/*
 	 * Negative syscall numbers are mistaken for rejected syscalls, but
 	 * won't have had the return value set appropriately, so we do so now.
 	 */
-	if (syscall < 0)
+	if (current_thread_info()->syscall < 0)
 		syscall_set_return_value(current, regs, -ENOSYS, 0);
-	return syscall;
+	return current_thread_info()->syscall;
 }
 
 /*
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index 18dc9b3450..2c604717e6 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -77,6 +77,18 @@ loads_done:
 	PTR_WD	load_a7, bad_stack_a7
 	.previous
 
+	/*
+	 * syscall number is in v0 unless we called syscall(__NR_###)
+	 * where the real syscall number is in a0
+	 */
+	subu	t2, v0,  __NR_O32_Linux
+	bnez	t2, 1f /* __NR_syscall at offset 0 */
+	LONG_S	a0, TI_SYSCALL($28)	# Save a0 as syscall number
+	b	2f
+1:
+	LONG_S	v0, TI_SYSCALL($28)	# Save v0 as syscall number
+2:
+
 	lw	t0, TI_FLAGS($28)	# syscall tracing enabled?
 	li	t1, _TIF_WORK_SYSCALL_ENTRY
 	and	t0, t1
@@ -114,16 +126,7 @@ syscall_trace_entry:
 	SAVE_STATIC
 	move	a0, sp
 
-	/*
-	 * syscall number is in v0 unless we called syscall(__NR_###)
-	 * where the real syscall number is in a0
-	 */
-	move	a1, v0
-	subu	t2, v0,  __NR_O32_Linux
-	bnez	t2, 1f /* __NR_syscall at offset 0 */
-	lw	a1, PT_R4(sp)
-
-1:	jal	syscall_trace_enter
+	jal	syscall_trace_enter
 
 	bltz	v0, 1f			# seccomp failed? Skip syscall
 
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 97456b2ca7..9778885923 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -44,6 +44,8 @@ NESTED(handle_sysn32, PT_SIZE, sp)
 
 	sd	a3, PT_R26(sp)		# save a3 for syscall restarting
 
+	LONG_S	v0, TI_SYSCALL($28)     # Store syscall number
+
 	li	t1, _TIF_WORK_SYSCALL_ENTRY
 	LONG_L	t0, TI_FLAGS($28)	# syscall tracing enabled?
 	and	t0, t1, t0
@@ -72,7 +74,6 @@ syscall_common:
 n32_syscall_trace_entry:
 	SAVE_STATIC
 	move	a0, sp
-	move	a1, v0
 	jal	syscall_trace_enter
 
 	bltz	v0, 1f			# seccomp failed? Skip syscall
diff --git a/arch/mips/kernel/scall64-n64.S b/arch/mips/kernel/scall64-n64.S
index e6264aa62e..be11ea5cc6 100644
--- a/arch/mips/kernel/scall64-n64.S
+++ b/arch/mips/kernel/scall64-n64.S
@@ -46,6 +46,8 @@ NESTED(handle_sys64, PT_SIZE, sp)
 
 	sd	a3, PT_R26(sp)		# save a3 for syscall restarting
 
+	LONG_S	v0, TI_SYSCALL($28)     # Store syscall number
+
 	li	t1, _TIF_WORK_SYSCALL_ENTRY
 	LONG_L	t0, TI_FLAGS($28)	# syscall tracing enabled?
 	and	t0, t1, t0
@@ -82,7 +84,6 @@ n64_syscall_exit:
 syscall_trace_entry:
 	SAVE_STATIC
 	move	a0, sp
-	move	a1, v0
 	jal	syscall_trace_enter
 
 	bltz	v0, 1f			# seccomp failed? Skip syscall
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index d3c2616cba..7a5abb73e5 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -79,6 +79,22 @@ loads_done:
 	PTR_WD	load_a7, bad_stack_a7
 	.previous
 
+	/*
+	 * absolute syscall number is in v0 unless we called syscall(__NR_###)
+	 * where the real syscall number is in a0
+	 * note: NR_syscall is the first O32 syscall but the macro is
+	 * only defined when compiling with -mabi=32 (CONFIG_32BIT)
+	 * therefore __NR_O32_Linux is used (4000)
+	 */
+
+	subu	t2, v0,  __NR_O32_Linux
+	bnez	t2, 1f /* __NR_syscall at offset 0 */
+	LONG_S	a0, TI_SYSCALL($28)	# Save a0 as syscall number
+	b	2f
+1:
+	LONG_S	v0, TI_SYSCALL($28)	# Save v0 as syscall number
+2:
+
 	li	t1, _TIF_WORK_SYSCALL_ENTRY
 	LONG_L	t0, TI_FLAGS($28)	# syscall tracing enabled?
 	and	t0, t1, t0
@@ -113,22 +129,7 @@ trace_a_syscall:
 	sd	a7, PT_R11(sp)		# For indirect syscalls
 
 	move	a0, sp
-	/*
-	 * absolute syscall number is in v0 unless we called syscall(__NR_###)
-	 * where the real syscall number is in a0
-	 * note: NR_syscall is the first O32 syscall but the macro is
-	 * only defined when compiling with -mabi=32 (CONFIG_32BIT)
-	 * therefore __NR_O32_Linux is used (4000)
-	 */
-	.set	push
-	.set	reorder
-	subu	t1, v0,  __NR_O32_Linux
-	move	a1, v0
-	bnez	t1, 1f /* __NR_syscall at offset 0 */
-	ld	a1, PT_R4(sp) /* Arg1 for __NR_syscall case */
-	.set	pop
-
-1:	jal	syscall_trace_enter
+	jal	syscall_trace_enter
 
 	bltz	v0, 1f			# seccomp failed? Skip syscall
 
diff --git a/arch/powerpc/crypto/chacha-p10-glue.c b/arch/powerpc/crypto/chacha-p10-glue.c
index 74fb86b0d2..7c72875585 100644
--- a/arch/powerpc/crypto/chacha-p10-glue.c
+++ b/arch/powerpc/crypto/chacha-p10-glue.c
@@ -197,6 +197,9 @@ static struct skcipher_alg algs[] = {
 
 static int __init chacha_p10_init(void)
 {
+	if (!cpu_has_feature(CPU_FTR_ARCH_31))
+		return 0;
+
 	static_branch_enable(&have_p10);
 
 	return crypto_register_skciphers(algs, ARRAY_SIZE(algs));
@@ -204,10 +207,13 @@ static int __init chacha_p10_init(void)
 
 static void __exit chacha_p10_exit(void)
 {
+	if (!static_branch_likely(&have_p10))
+		return;
+
 	crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
 }
 
-module_cpu_feature_match(PPC_MODULE_FEATURE_P10, chacha_p10_init);
+module_init(chacha_p10_init);
 module_exit(chacha_p10_exit);
 
 MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (P10 accelerated)");
diff --git a/arch/powerpc/include/asm/plpks.h b/arch/powerpc/include/asm/plpks.h
index 23b77027c9..7a84069759 100644
--- a/arch/powerpc/include/asm/plpks.h
+++ b/arch/powerpc/include/asm/plpks.h
@@ -44,9 +44,8 @@
 #define PLPKS_MAX_DATA_SIZE		4000
 
 // Timeouts for PLPKS operations
-#define PLPKS_MAX_TIMEOUT		5000 // msec
-#define PLPKS_FLUSH_SLEEP		10 // msec
-#define PLPKS_FLUSH_SLEEP_RANGE		400
+#define PLPKS_MAX_TIMEOUT		(5 * USEC_PER_SEC)
+#define PLPKS_FLUSH_SLEEP		10000 // usec
 
 struct plpks_var {
 	char *component;
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index e8c4129697..b1e6d275cd 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -786,8 +786,16 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
 	 * parent bus. During reboot, there will be ibm,dma-window property to
 	 * define DMA window. For kdump, there will at least be default window or DDW
 	 * or both.
+	 * There is an exception to the above. In case the PE goes into frozen
+	 * state, firmware may not provide ibm,dma-window property at the time
+	 * of LPAR boot up.
 	 */
 
+	if (!pdn) {
+		pr_debug("  no ibm,dma-window property !\n");
+		return;
+	}
+
 	ppci = PCI_DN(pdn);
 
 	pr_debug("  parent is %pOF, iommu_table: 0x%p\n",
diff --git a/arch/powerpc/platforms/pseries/plpks.c b/arch/powerpc/platforms/pseries/plpks.c
index febe18f251..4a595493d2 100644
--- a/arch/powerpc/platforms/pseries/plpks.c
+++ b/arch/powerpc/platforms/pseries/plpks.c
@@ -415,8 +415,7 @@ static int plpks_confirm_object_flushed(struct label *label,
 			break;
 		}
 
-		usleep_range(PLPKS_FLUSH_SLEEP,
-			     PLPKS_FLUSH_SLEEP + PLPKS_FLUSH_SLEEP_RANGE);
+		fsleep(PLPKS_FLUSH_SLEEP);
 		timeout = timeout + PLPKS_FLUSH_SLEEP;
 	} while (timeout < PLPKS_MAX_TIMEOUT);
 
@@ -464,9 +463,10 @@ int plpks_signed_update_var(struct plpks_var *var, u64 flags)
 
 		continuetoken = retbuf[0];
 		if (pseries_status_to_err(rc) == -EBUSY) {
-			int delay_ms = get_longbusy_msecs(rc);
-			mdelay(delay_ms);
-			timeout += delay_ms;
+			int delay_us = get_longbusy_msecs(rc) * 1000;
+
+			fsleep(delay_us);
+			timeout += delay_us;
 		}
 		rc = pseries_status_to_err(rc);
 	} while (rc == -EBUSY && timeout < PLPKS_MAX_TIMEOUT);
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 719a97e7ed..0bd747d1d0 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -740,6 +740,9 @@ static int invoke_bpf_prog(struct bpf_tramp_link *l, int args_off, int retval_of
 	if (ret)
 		return ret;
 
+	/* store prog start time */
+	emit_mv(RV_REG_S1, RV_REG_A0, ctx);
+
 	/* if (__bpf_prog_enter(prog) == 0)
 	 *	goto skip_exec_of_prog;
 	 */
@@ -747,9 +750,6 @@ static int invoke_bpf_prog(struct bpf_tramp_link *l, int args_off, int retval_of
 	/* nop reserved for conditional jump */
 	emit(rv_nop(), ctx);
 
-	/* store prog start time */
-	emit_mv(RV_REG_S1, RV_REG_A0, ctx);
-
 	/* arg1: &args_off */
 	emit_addi(RV_REG_A0, RV_REG_FP, -args_off, ctx);
 	if (!p->jited)
diff --git a/arch/s390/include/asm/dwarf.h b/arch/s390/include/asm/dwarf.h
index 4f21ae561e..390906b8e3 100644
--- a/arch/s390/include/asm/dwarf.h
+++ b/arch/s390/include/asm/dwarf.h
@@ -9,6 +9,7 @@
 #define CFI_DEF_CFA_OFFSET	.cfi_def_cfa_offset
 #define CFI_ADJUST_CFA_OFFSET	.cfi_adjust_cfa_offset
 #define CFI_RESTORE		.cfi_restore
+#define CFI_REL_OFFSET		.cfi_rel_offset
 
 #ifdef CONFIG_AS_CFI_VAL_OFFSET
 #define CFI_VAL_OFFSET		.cfi_val_offset
diff --git a/arch/s390/kernel/vdso64/vdso_user_wrapper.S b/arch/s390/kernel/vdso64/vdso_user_wrapper.S
index 57f62596e5..85247ef5a4 100644
--- a/arch/s390/kernel/vdso64/vdso_user_wrapper.S
+++ b/arch/s390/kernel/vdso64/vdso_user_wrapper.S
@@ -24,8 +24,10 @@ __kernel_\func:
 	CFI_DEF_CFA_OFFSET (STACK_FRAME_OVERHEAD + WRAPPER_FRAME_SIZE)
 	CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD
 	stg	%r14,STACK_FRAME_OVERHEAD(%r15)
+	CFI_REL_OFFSET 14, STACK_FRAME_OVERHEAD
 	brasl	%r14,__s390_vdso_\func
 	lg	%r14,STACK_FRAME_OVERHEAD(%r15)
+	CFI_RESTORE 14
 	aghi	%r15,WRAPPER_FRAME_SIZE
 	CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD
 	CFI_RESTORE 15
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 08a7eca03d..41a4a60c5e 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -2659,7 +2659,7 @@ static int __s390_enable_skey_hugetlb(pte_t *pte, unsigned long addr,
 		return 0;
 
 	start = pmd_val(*pmd) & HPAGE_MASK;
-	end = start + HPAGE_SIZE - 1;
+	end = start + HPAGE_SIZE;
 	__storage_key_init_range(start, end);
 	set_bit(PG_arch_1, &page->flags);
 	cond_resched();
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index 5f64f3d0fa..763469e518 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -139,7 +139,7 @@ static void clear_huge_pte_skeys(struct mm_struct *mm, unsigned long rste)
 	}
 
 	if (!test_and_set_bit(PG_arch_1, &page->flags))
-		__storage_key_init_range(paddr, paddr + size - 1);
+		__storage_key_init_range(paddr, paddr + size);
 }
 
 void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 75bd5ac7ac..a04a5163e5 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1808,7 +1808,7 @@ void x2apic_setup(void)
 	__x2apic_enable();
 }
 
-static __init void apic_set_fixmap(void);
+static __init void apic_set_fixmap(bool read_apic);
 
 static __init void x2apic_disable(void)
 {
@@ -1830,7 +1830,12 @@ static __init void x2apic_disable(void)
 	}
 
 	__x2apic_disable();
-	apic_set_fixmap();
+	/*
+	 * Don't reread the APIC ID as it was already done from
+	 * check_x2apic() and the APIC driver still is a x2APIC variant,
+	 * which fails to do the read after x2APIC was disabled.
+	 */
+	apic_set_fixmap(false);
 }
 
 static __init void x2apic_enable(void)
@@ -2095,13 +2100,14 @@ void __init init_apic_mappings(void)
 	}
 }
 
-static __init void apic_set_fixmap(void)
+static __init void apic_set_fixmap(bool read_apic)
 {
 	set_fixmap_nocache(FIX_APIC_BASE, mp_lapic_addr);
 	apic_mmio_base = APIC_BASE;
 	apic_printk(APIC_VERBOSE, "mapped APIC to %16lx (%16lx)\n",
 		    apic_mmio_base, mp_lapic_addr);
-	apic_read_boot_cpu_id(false);
+	if (read_apic)
+		apic_read_boot_cpu_id(false);
 }
 
 void __init register_lapic_address(unsigned long address)
@@ -2111,7 +2117,7 @@ void __init register_lapic_address(unsigned long address)
 	mp_lapic_addr = address;
 
 	if (!x2apic_mode)
-		apic_set_fixmap();
+		apic_set_fixmap(true);
 }
 
 /*
diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h
index d008a153a2..7ed1a2085b 100644
--- a/arch/xtensa/include/asm/processor.h
+++ b/arch/xtensa/include/asm/processor.h
@@ -115,9 +115,9 @@
 #define MAKE_RA_FOR_CALL(ra,ws)   (((ra) & 0x3fffffff) | (ws) << 30)
 
 /* Convert return address to a valid pc
- * Note: We assume that the stack pointer is in the same 1GB ranges as the ra
+ * Note: 'text' is the address within the same 1GB range as the ra
  */
-#define MAKE_PC_FROM_RA(ra,sp)    (((ra) & 0x3fffffff) | ((sp) & 0xc0000000))
+#define MAKE_PC_FROM_RA(ra, text) (((ra) & 0x3fffffff) | ((unsigned long)(text) & 0xc0000000))
 
 #elif defined(__XTENSA_CALL0_ABI__)
 
@@ -127,9 +127,9 @@
 #define MAKE_RA_FOR_CALL(ra, ws)   (ra)
 
 /* Convert return address to a valid pc
- * Note: We assume that the stack pointer is in the same 1GB ranges as the ra
+ * Note: 'text' is not used as 'ra' is always the full address
  */
-#define MAKE_PC_FROM_RA(ra, sp)    (ra)
+#define MAKE_PC_FROM_RA(ra, text)  (ra)
 
 #else
 #error Unsupported Xtensa ABI
diff --git a/arch/xtensa/include/asm/ptrace.h b/arch/xtensa/include/asm/ptrace.h
index a270467556..86c7011737 100644
--- a/arch/xtensa/include/asm/ptrace.h
+++ b/arch/xtensa/include/asm/ptrace.h
@@ -87,7 +87,7 @@ struct pt_regs {
 # define user_mode(regs) (((regs)->ps & 0x00000020)!=0)
 # define instruction_pointer(regs) ((regs)->pc)
 # define return_pointer(regs) (MAKE_PC_FROM_RA((regs)->areg[0], \
-					       (regs)->areg[1]))
+					       (regs)->pc))
 
 # ifndef CONFIG_SMP
 #  define profile_pc(regs) instruction_pointer(regs)
diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c
index a815577d25..7bd66677f7 100644
--- a/arch/xtensa/kernel/process.c
+++ b/arch/xtensa/kernel/process.c
@@ -47,6 +47,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/regs.h>
 #include <asm/hw_breakpoint.h>
+#include <asm/sections.h>
 #include <asm/traps.h>
 
 extern void ret_from_fork(void);
@@ -380,7 +381,7 @@ unsigned long __get_wchan(struct task_struct *p)
 	int count = 0;
 
 	sp = p->thread.sp;
-	pc = MAKE_PC_FROM_RA(p->thread.ra, p->thread.sp);
+	pc = MAKE_PC_FROM_RA(p->thread.ra, _text);
 
 	do {
 		if (sp < stack_page + sizeof(struct task_struct) ||
@@ -392,7 +393,7 @@ unsigned long __get_wchan(struct task_struct *p)
 
 		/* Stack layout: sp-4: ra, sp-3: sp' */
 
-		pc = MAKE_PC_FROM_RA(SPILL_SLOT(sp, 0), sp);
+		pc = MAKE_PC_FROM_RA(SPILL_SLOT(sp, 0), _text);
 		sp = SPILL_SLOT(sp, 1);
 	} while (count++ < 16);
 	return 0;
diff --git a/arch/xtensa/kernel/stacktrace.c b/arch/xtensa/kernel/stacktrace.c
index 831ffb648b..ed324fdf2a 100644
--- a/arch/xtensa/kernel/stacktrace.c
+++ b/arch/xtensa/kernel/stacktrace.c
@@ -13,6 +13,7 @@
 #include <linux/stacktrace.h>
 
 #include <asm/ftrace.h>
+#include <asm/sections.h>
 #include <asm/stacktrace.h>
 #include <asm/traps.h>
 #include <linux/uaccess.h>
@@ -189,7 +190,7 @@ void walk_stackframe(unsigned long *sp,
 		if (a1 <= (unsigned long)sp)
 			break;
 
-		frame.pc = MAKE_PC_FROM_RA(a0, a1);
+		frame.pc = MAKE_PC_FROM_RA(a0, _text);
 		frame.sp = a1;
 
 		if (fn(&frame, data))