Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

tools/testing/selftests/net/ioam6.sh
  7b1700e009cc ("selftests: net: modify IOAM tests for undef bits")
  bf77b1400a56 ("selftests: net: Test for the IOAM encapsulation with IPv6")

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

60 files changed, 546 insertions, 223 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index fc196421b2ce..59baf6c132a7 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1989,8 +1989,6 @@ config ARCH_HIBERNATION_POSSIBLE
 
 endmenu
 
-source "drivers/firmware/Kconfig"
-
 if CRYPTO
 source "arch/arm/crypto/Kconfig"
 endif
diff --git a/arch/arm/boot/dts/spear3xx.dtsi b/arch/arm/boot/dts/spear3xx.dtsi
index f266b7b03482..cc88ebe7a60c 100644
--- a/arch/arm/boot/dts/spear3xx.dtsi
+++ b/arch/arm/boot/dts/spear3xx.dtsi
@@ -47,7 +47,7 @@
 		};
 
 		gmac: eth@e0800000 {
-			compatible = "st,spear600-gmac";
+			compatible = "snps,dwmac-3.40a";
 			reg = <0xe0800000 0x8000>;
 			interrupts = <23 22>;
 			interrupt-names = "macirq", "eth_wake_irq";
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 5c7ae4c3954b..fee914c716aa 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1931,8 +1931,6 @@ source "drivers/cpufreq/Kconfig"
 
 endmenu
 
-source "drivers/firmware/Kconfig"
-
 source "drivers/acpi/Kconfig"
 
 source "arch/arm64/kvm/Kconfig"
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 23505fc35324..a8158c948966 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -43,7 +43,7 @@ void __init arm64_hugetlb_cma_reserve(void)
 #ifdef CONFIG_ARM64_4K_PAGES
 	order = PUD_SHIFT - PAGE_SHIFT;
 #else
-	order = CONT_PMD_SHIFT + PMD_SHIFT - PAGE_SHIFT;
+	order = CONT_PMD_SHIFT - PAGE_SHIFT;
 #endif
 	/*
 	 * HugeTLB CMA reservation is required for gigantic
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 045792cde481..1e33666fa679 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -388,8 +388,6 @@ config CRASH_DUMP
 	  help
 	    Generate crash dump after being started by kexec.
 
-source "drivers/firmware/Kconfig"
-
 endmenu
 
 menu "Power management and ACPI options"
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 771ca53af06d..6b8f591c5054 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -3316,8 +3316,6 @@ source "drivers/cpuidle/Kconfig"
 
 endmenu
 
-source "drivers/firmware/Kconfig"
-
 source "arch/mips/kvm/Kconfig"
 
 source "arch/mips/vdso/Kconfig"
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index 4742b6f169b7..27a8b49af11f 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -384,6 +384,4 @@ config KEXEC_FILE
 
 endmenu
 
-source "drivers/firmware/Kconfig"
-
 source "drivers/parisc/Kconfig"
diff --git a/arch/powerpc/include/asm/book3s/32/kup.h b/arch/powerpc/include/asm/book3s/32/kup.h
index d4b145b279f6..9f38040f0641 100644
--- a/arch/powerpc/include/asm/book3s/32/kup.h
+++ b/arch/powerpc/include/asm/book3s/32/kup.h
@@ -136,6 +136,14 @@ static inline void kuap_kernel_restore(struct pt_regs *regs, unsigned long kuap)
 	if (kuap_is_disabled())
 		return;
 
+	if (unlikely(kuap != KUAP_NONE)) {
+		current->thread.kuap = KUAP_NONE;
+		kuap_lock(kuap, false);
+	}
+
+	if (likely(regs->kuap == KUAP_NONE))
+		return;
+
 	current->thread.kuap = regs->kuap;
 
 	kuap_unlock(regs->kuap, false);
diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h
index a95f63788c6b..4ba834599c4d 100644
--- a/arch/powerpc/include/asm/code-patching.h
+++ b/arch/powerpc/include/asm/code-patching.h
@@ -23,6 +23,7 @@
 #define BRANCH_ABSOLUTE	0x2
 
 bool is_offset_in_branch_range(long offset);
+bool is_offset_in_cond_branch_range(long offset);
 int create_branch(struct ppc_inst *instr, const u32 *addr,
 		  unsigned long target, int flags);
 int create_cond_branch(struct ppc_inst *instr, const u32 *addr,
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 6b800d3e2681..a1d238255f07 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -265,13 +265,16 @@ static inline void interrupt_nmi_enter_prepare(struct pt_regs *regs, struct inte
 	local_paca->irq_soft_mask = IRQS_ALL_DISABLED;
 	local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
 
-	if (is_implicit_soft_masked(regs)) {
-		// Adjust regs->softe soft implicit soft-mask, so
-		// arch_irq_disabled_regs(regs) behaves as expected.
+	if (!(regs->msr & MSR_EE) || is_implicit_soft_masked(regs)) {
+		/*
+		 * Adjust regs->softe to be soft-masked if it had not been
+		 * reconcied (e.g., interrupt entry with MSR[EE]=0 but softe
+		 * not yet set disabled), or if it was in an implicit soft
+		 * masked state. This makes arch_irq_disabled_regs(regs)
+		 * behave as expected.
+		 */
 		regs->softe = IRQS_ALL_DISABLED;
 	}
-	if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
-		BUG_ON(!arch_irq_disabled_regs(regs) && !(regs->msr & MSR_EE));
 
 	/* Don't do any per-CPU operations until interrupt state is fixed */
 
@@ -525,10 +528,9 @@ static __always_inline long ____##func(struct pt_regs *regs)
 /* kernel/traps.c */
 DECLARE_INTERRUPT_HANDLER_NMI(system_reset_exception);
 #ifdef CONFIG_PPC_BOOK3S_64
-DECLARE_INTERRUPT_HANDLER_ASYNC(machine_check_exception);
-#else
-DECLARE_INTERRUPT_HANDLER_NMI(machine_check_exception);
+DECLARE_INTERRUPT_HANDLER_ASYNC(machine_check_exception_async);
 #endif
+DECLARE_INTERRUPT_HANDLER_NMI(machine_check_exception);
 DECLARE_INTERRUPT_HANDLER(SMIException);
 DECLARE_INTERRUPT_HANDLER(handle_hmi_exception);
 DECLARE_INTERRUPT_HANDLER(unknown_exception);
diff --git a/arch/powerpc/include/asm/security_features.h b/arch/powerpc/include/asm/security_features.h
index 792eefaf230b..27574f218b37 100644
--- a/arch/powerpc/include/asm/security_features.h
+++ b/arch/powerpc/include/asm/security_features.h
@@ -39,6 +39,11 @@ static inline bool security_ftr_enabled(u64 feature)
 	return !!(powerpc_security_features & feature);
 }
 
+#ifdef CONFIG_PPC_BOOK3S_64
+enum stf_barrier_type stf_barrier_type_get(void);
+#else
+static inline enum stf_barrier_type stf_barrier_type_get(void) { return STF_BARRIER_NONE; }
+#endif
 
 // Features indicating support for Spectre/Meltdown mitigations
 
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index 111249fd619d..038ce8d9061d 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -184,6 +184,15 @@ u64 dma_iommu_get_required_mask(struct device *dev)
 	struct iommu_table *tbl = get_iommu_table_base(dev);
 	u64 mask;
 
+	if (dev_is_pci(dev)) {
+		u64 bypass_mask = dma_direct_get_required_mask(dev);
+
+		if (dma_iommu_dma_supported(dev, bypass_mask)) {
+			dev_info(dev, "%s: returning bypass mask 0x%llx\n", __func__, bypass_mask);
+			return bypass_mask;
+		}
+	}
+
 	if (!tbl)
 		return 0;
 
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 37859e62a8dc..eaf1f72131a1 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1243,7 +1243,7 @@ EXC_COMMON_BEGIN(machine_check_common)
 	li	r10,MSR_RI
 	mtmsrd 	r10,1
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	machine_check_exception
+	bl	machine_check_exception_async
 	b	interrupt_return_srr
 
 
@@ -1303,7 +1303,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
 	subi	r12,r12,1
 	sth	r12,PACA_IN_MCE(r13)
 
-	/* Invoke machine_check_exception to print MCE event and panic. */
+	/*
+	 * Invoke machine_check_exception to print MCE event and panic.
+	 * This is the NMI version of the handler because we are called from
+	 * the early handler which is a true NMI.
+	 */
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	machine_check_exception
 
@@ -1665,27 +1669,30 @@ EXC_COMMON_BEGIN(program_check_common)
 	 */
 
 	andi.	r10,r12,MSR_PR
-	bne	2f			/* If userspace, go normal path */
+	bne	.Lnormal_stack		/* If userspace, go normal path */
 
 	andis.	r10,r12,(SRR1_PROGTM)@h
-	bne	1f			/* If TM, emergency		*/
+	bne	.Lemergency_stack	/* If TM, emergency		*/
 
 	cmpdi	r1,-INT_FRAME_SIZE	/* check if r1 is in userspace	*/
-	blt	2f			/* normal path if not		*/
+	blt	.Lnormal_stack		/* normal path if not		*/
 
 	/* Use the emergency stack					*/
-1:	andi.	r10,r12,MSR_PR		/* Set CR0 correctly for label	*/
+.Lemergency_stack:
+	andi.	r10,r12,MSR_PR		/* Set CR0 correctly for label	*/
 					/* 3 in EXCEPTION_PROLOG_COMMON	*/
 	mr	r10,r1			/* Save r1			*/
 	ld	r1,PACAEMERGSP(r13)	/* Use emergency stack		*/
 	subi	r1,r1,INT_FRAME_SIZE	/* alloc stack frame		*/
 	__ISTACK(program_check)=0
 	__GEN_COMMON_BODY program_check
-	b 3f
-2:
+	b .Ldo_program_check
+
+.Lnormal_stack:
 	__ISTACK(program_check)=1
 	__GEN_COMMON_BODY program_check
-3:
+
+.Ldo_program_check:
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	program_check_exception
 	REST_NVGPRS(r1) /* instruction emulation may change GPRs */
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 551b653228c4..c4f1d6b7d992 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -229,6 +229,9 @@ notrace void arch_local_irq_restore(unsigned long mask)
 		return;
 	}
 
+	if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
+		WARN_ON_ONCE(in_nmi() || in_hardirq());
+
 	/*
 	 * After the stb, interrupts are unmasked and there are no interrupts
 	 * pending replay. The restart sequence makes this atomic with
@@ -321,6 +324,9 @@ notrace void arch_local_irq_restore(unsigned long mask)
 	if (mask)
 		return;
 
+	if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
+		WARN_ON_ONCE(in_nmi() || in_hardirq());
+
 	/*
 	 * From this point onward, we can take interrupts, preempt,
 	 * etc... unless we got hard-disabled. We check if an event
diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c
index 1a998490fe60..15fb5ea1b9ea 100644
--- a/arch/powerpc/kernel/security.c
+++ b/arch/powerpc/kernel/security.c
@@ -263,6 +263,11 @@ static int __init handle_no_stf_barrier(char *p)
 
 early_param("no_stf_barrier", handle_no_stf_barrier);
 
+enum stf_barrier_type stf_barrier_type_get(void)
+{
+	return stf_enabled_flush_types;
+}
+
 /* This is the generic flag used by other architectures */
 static int __init handle_ssbd(char *p)
 {
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index aac8c0412ff9..11741703d26e 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -340,10 +340,16 @@ static bool exception_common(int signr, struct pt_regs *regs, int code,
 		return false;
 	}
 
-	show_signal_msg(signr, regs, code, addr);
+	/*
+	 * Must not enable interrupts even for user-mode exception, because
+	 * this can be called from machine check, which may be a NMI or IRQ
+	 * which don't like interrupts being enabled. Could check for
+	 * in_hardirq || in_nmi perhaps, but there doesn't seem to be a good
+	 * reason why _exception() should enable irqs for an exception handler,
+	 * the handlers themselves do that directly.
+	 */
 
-	if (arch_irqs_disabled())
-		interrupt_cond_local_irq_enable(regs);
+	show_signal_msg(signr, regs, code, addr);
 
 	current->thread.trap_nr = code;
 
@@ -790,24 +796,22 @@ void die_mce(const char *str, struct pt_regs *regs, long err)
 	 * do_exit() checks for in_interrupt() and panics in that case, so
 	 * exit the irq/nmi before calling die.
 	 */
-	if (IS_ENABLED(CONFIG_PPC_BOOK3S_64))
-		irq_exit();
-	else
+	if (in_nmi())
 		nmi_exit();
+	else
+		irq_exit();
 	die(str, regs, err);
 }
 
 /*
- * BOOK3S_64 does not call this handler as a non-maskable interrupt
+ * BOOK3S_64 does not usually call this handler as a non-maskable interrupt
  * (it uses its own early real-mode handler to handle the MCE proper
  * and then raises irq_work to call this handler when interrupts are
- * enabled).
+ * enabled). The only time when this is not true is if the early handler
+ * is unrecoverable, then it does call this directly to try to get a
+ * message out.
  */
-#ifdef CONFIG_PPC_BOOK3S_64
-DEFINE_INTERRUPT_HANDLER_ASYNC(machine_check_exception)
-#else
-DEFINE_INTERRUPT_HANDLER_NMI(machine_check_exception)
-#endif
+static void __machine_check_exception(struct pt_regs *regs)
 {
 	int recover = 0;
 
@@ -841,12 +845,19 @@ bail:
 	/* Must die if the interrupt is not recoverable */
 	if (regs_is_unrecoverable(regs))
 		die_mce("Unrecoverable Machine check", regs, SIGBUS);
+}
 
 #ifdef CONFIG_PPC_BOOK3S_64
-	return;
-#else
-	return 0;
+DEFINE_INTERRUPT_HANDLER_ASYNC(machine_check_exception_async)
+{
+	__machine_check_exception(regs);
+}
 #endif
+DEFINE_INTERRUPT_HANDLER_NMI(machine_check_exception)
+{
+	__machine_check_exception(regs);
+
+	return 0;
 }
 
 DEFINE_INTERRUPT_HANDLER(SMIException) /* async? */
diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c
index f9a3019e37b4..c5ed98823835 100644
--- a/arch/powerpc/lib/code-patching.c
+++ b/arch/powerpc/lib/code-patching.c
@@ -228,6 +228,11 @@ bool is_offset_in_branch_range(long offset)
 	return (offset >= -0x2000000 && offset <= 0x1fffffc && !(offset & 0x3));
 }
 
+bool is_offset_in_cond_branch_range(long offset)
+{
+	return offset >= -0x8000 && offset <= 0x7fff && !(offset & 0x3);
+}
+
 /*
  * Helper to check if a given instruction is a conditional branch
  * Derived from the conditional checks in analyse_instr()
@@ -280,7 +285,7 @@ int create_cond_branch(struct ppc_inst *instr, const u32 *addr,
 		offset = offset - (unsigned long)addr;
 
 	/* Check we can represent the target in the instruction format */
-	if (offset < -0x8000 || offset > 0x7FFF || offset & 0x3)
+	if (!is_offset_in_cond_branch_range(offset))
 		return 1;
 
 	/* Mask out the flags and target, so they don't step on each other. */
diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index 99fad093f43e..7e9b978b768e 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -24,16 +24,30 @@
 #define EMIT(instr)		PLANT_INSTR(image, ctx->idx, instr)
 
 /* Long jump; (unconditional 'branch') */
-#define PPC_JMP(dest)		EMIT(PPC_INST_BRANCH |			      \
-				     (((dest) - (ctx->idx * 4)) & 0x03fffffc))
+#define PPC_JMP(dest)							      \
+	do {								      \
+		long offset = (long)(dest) - (ctx->idx * 4);		      \
+		if (!is_offset_in_branch_range(offset)) {		      \
+			pr_err_ratelimited("Branch offset 0x%lx (@%u) out of range\n", offset, ctx->idx);			\
+			return -ERANGE;					      \
+		}							      \
+		EMIT(PPC_INST_BRANCH | (offset & 0x03fffffc));		      \
+	} while (0)
+
 /* blr; (unconditional 'branch' with link) to absolute address */
 #define PPC_BL_ABS(dest)	EMIT(PPC_INST_BL |			      \
 				     (((dest) - (unsigned long)(image + ctx->idx)) & 0x03fffffc))
 /* "cond" here covers BO:BI fields. */
-#define PPC_BCC_SHORT(cond, dest)	EMIT(PPC_INST_BRANCH_COND |	      \
-					     (((cond) & 0x3ff) << 16) |	      \
-					     (((dest) - (ctx->idx * 4)) &     \
-					      0xfffc))
+#define PPC_BCC_SHORT(cond, dest)					      \
+	do {								      \
+		long offset = (long)(dest) - (ctx->idx * 4);		      \
+		if (!is_offset_in_cond_branch_range(offset)) {		      \
+			pr_err_ratelimited("Conditional branch offset 0x%lx (@%u) out of range\n", offset, ctx->idx);		\
+			return -ERANGE;					      \
+		}							      \
+		EMIT(PPC_INST_BRANCH_COND | (((cond) & 0x3ff) << 16) | (offset & 0xfffc));					\
+	} while (0)
+
 /* Sign-extended 32-bit immediate load */
 #define PPC_LI32(d, i)		do {					      \
 		if ((int)(uintptr_t)(i) >= -32768 &&			      \
@@ -78,11 +92,6 @@
 #define PPC_FUNC_ADDR(d,i) do { PPC_LI32(d, i); } while(0)
 #endif
 
-static inline bool is_nearbranch(int offset)
-{
-	return (offset < 32768) && (offset >= -32768);
-}
-
 /*
  * The fly in the ointment of code size changing from pass to pass is
  * avoided by padding the short branch case with a NOP.	 If code size differs
@@ -91,7 +100,7 @@ static inline bool is_nearbranch(int offset)
  * state.
  */
 #define PPC_BCC(cond, dest)	do {					      \
-		if (is_nearbranch((dest) - (ctx->idx * 4))) {		      \
+		if (is_offset_in_cond_branch_range((long)(dest) - (ctx->idx * 4))) {	\
 			PPC_BCC_SHORT(cond, dest);			      \
 			EMIT(PPC_RAW_NOP());				      \
 		} else {						      \
diff --git a/arch/powerpc/net/bpf_jit64.h b/arch/powerpc/net/bpf_jit64.h
index 7b713edfa7e2..b63b35e45e55 100644
--- a/arch/powerpc/net/bpf_jit64.h
+++ b/arch/powerpc/net/bpf_jit64.h
@@ -16,18 +16,18 @@
  * with our redzone usage.
  *
  *		[	prev sp		] <-------------
- *		[   nv gpr save area	] 6*8		|
+ *		[   nv gpr save area	] 5*8		|
  *		[    tail_call_cnt	] 8		|
- *		[    local_tmp_var	] 8		|
+ *		[    local_tmp_var	] 16		|
  * fp (r31) -->	[   ebpf stack space	] upto 512	|
  *		[     frame header	] 32/112	|
  * sp (r1) --->	[    stack pointer	] --------------
  */
 
 /* for gpr non volatile registers BPG_REG_6 to 10 */
-#define BPF_PPC_STACK_SAVE	(6*8)
+#define BPF_PPC_STACK_SAVE	(5*8)
 /* for bpf JIT code internal usage */
-#define BPF_PPC_STACK_LOCALS	16
+#define BPF_PPC_STACK_LOCALS	24
 /* stack frame excluding BPF stack, ensure this is quadword aligned */
 #define BPF_PPC_STACKFRAME	(STACK_FRAME_MIN_SIZE + \
 				 BPF_PPC_STACK_LOCALS + BPF_PPC_STACK_SAVE)
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 53aefee3fe70..fcbf7a917c56 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -210,7 +210,11 @@ skip_init_ctx:
 		/* Now build the prologue, body code & epilogue for real. */
 		cgctx.idx = 0;
 		bpf_jit_build_prologue(code_base, &cgctx);
-		bpf_jit_build_body(fp, code_base, &cgctx, addrs, extra_pass);
+		if (bpf_jit_build_body(fp, code_base, &cgctx, addrs, extra_pass)) {
+			bpf_jit_binary_free(bpf_hdr);
+			fp = org_fp;
+			goto out_addrs;
+		}
 		bpf_jit_build_epilogue(code_base, &cgctx);
 
 		if (bpf_jit_enable > 1)
diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c
index beb12cbc8c29..0da31d41d413 100644
--- a/arch/powerpc/net/bpf_jit_comp32.c
+++ b/arch/powerpc/net/bpf_jit_comp32.c
@@ -200,7 +200,7 @@ void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 fun
 	}
 }
 
-static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 out)
+static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 out)
 {
 	/*
 	 * By now, the eBPF program has already setup parameters in r3-r6
@@ -261,7 +261,9 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32
 	bpf_jit_emit_common_epilogue(image, ctx);
 
 	EMIT(PPC_RAW_BCTR());
+
 	/* out: */
+	return 0;
 }
 
 /* Assemble the body code between the prologue & epilogue */
@@ -355,7 +357,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 				PPC_LI32(_R0, imm);
 				EMIT(PPC_RAW_ADDC(dst_reg, dst_reg, _R0));
 			}
-			if (imm >= 0)
+			if (imm >= 0 || (BPF_OP(code) == BPF_SUB && imm == 0x80000000))
 				EMIT(PPC_RAW_ADDZE(dst_reg_h, dst_reg_h));
 			else
 				EMIT(PPC_RAW_ADDME(dst_reg_h, dst_reg_h));
@@ -623,7 +625,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 			EMIT(PPC_RAW_LI(dst_reg_h, 0));
 			break;
 		case BPF_ALU | BPF_ARSH | BPF_X: /* (s32) dst >>= src */
-			EMIT(PPC_RAW_SRAW(dst_reg_h, dst_reg, src_reg));
+			EMIT(PPC_RAW_SRAW(dst_reg, dst_reg, src_reg));
 			break;
 		case BPF_ALU64 | BPF_ARSH | BPF_X: /* (s64) dst >>= src */
 			bpf_set_seen_register(ctx, tmp_reg);
@@ -1073,7 +1075,7 @@ cond_branch:
 				break;
 			case BPF_JMP32 | BPF_JSET | BPF_K:
 				/* andi does not sign-extend the immediate */
-				if (imm >= -32768 && imm < 32768) {
+				if (imm >= 0 && imm < 32768) {
 					/* PPC_ANDI is _only/always_ dot-form */
 					EMIT(PPC_RAW_ANDI(_R0, dst_reg, imm));
 				} else {
@@ -1090,7 +1092,9 @@ cond_branch:
 		 */
 		case BPF_JMP | BPF_TAIL_CALL:
 			ctx->seen |= SEEN_TAILCALL;
-			bpf_jit_emit_tail_call(image, ctx, addrs[i + 1]);
+			ret = bpf_jit_emit_tail_call(image, ctx, addrs[i + 1]);
+			if (ret < 0)
+				return ret;
 			break;
 
 		default:
@@ -1103,7 +1107,7 @@ cond_branch:
 			return -EOPNOTSUPP;
 		}
 		if (BPF_CLASS(code) == BPF_ALU && !fp->aux->verifier_zext &&
-		    !insn_is_zext(&insn[i + 1]))
+		    !insn_is_zext(&insn[i + 1]) && !(BPF_OP(code) == BPF_END && imm == 64))
 			EMIT(PPC_RAW_LI(dst_reg_h, 0));
 	}
 
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index b87a63dba9c8..8b5157ccfeba 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -15,6 +15,7 @@
 #include <linux/if_vlan.h>
 #include <asm/kprobes.h>
 #include <linux/bpf.h>
+#include <asm/security_features.h>
 
 #include "bpf_jit64.h"
 
@@ -35,9 +36,9 @@ static inline bool bpf_has_stack_frame(struct codegen_context *ctx)
  *		[	prev sp		] <-------------
  *		[	  ...       	] 		|
  * sp (r1) --->	[    stack pointer	] --------------
- *		[   nv gpr save area	] 6*8
+ *		[   nv gpr save area	] 5*8
  *		[    tail_call_cnt	] 8
- *		[    local_tmp_var	] 8
+ *		[    local_tmp_var	] 16
  *		[   unused red zone	] 208 bytes protected
  */
 static int bpf_jit_stack_local(struct codegen_context *ctx)
@@ -45,12 +46,12 @@ static int bpf_jit_stack_local(struct codegen_context *ctx)
 	if (bpf_has_stack_frame(ctx))
 		return STACK_FRAME_MIN_SIZE + ctx->stack_size;
 	else
-		return -(BPF_PPC_STACK_SAVE + 16);
+		return -(BPF_PPC_STACK_SAVE + 24);
 }
 
 static int bpf_jit_stack_tailcallcnt(struct codegen_context *ctx)
 {
-	return bpf_jit_stack_local(ctx) + 8;
+	return bpf_jit_stack_local(ctx) + 16;
 }
 
 static int bpf_jit_stack_offsetof(struct codegen_context *ctx, int reg)
@@ -206,7 +207,7 @@ void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 fun
 	EMIT(PPC_RAW_BCTRL());
 }
 
-static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 out)
+static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 out)
 {
 	/*
 	 * By now, the eBPF program has already setup parameters in r3, r4 and r5
@@ -267,13 +268,38 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32
 	bpf_jit_emit_common_epilogue(image, ctx);
 
 	EMIT(PPC_RAW_BCTR());
+
 	/* out: */
+	return 0;
 }
 
+/*
+ * We spill into the redzone always, even if the bpf program has its own stackframe.
+ * Offsets hardcoded based on BPF_PPC_STACK_SAVE -- see bpf_jit_stack_local()
+ */
+void bpf_stf_barrier(void);
+
+asm (
+"		.global bpf_stf_barrier		;"
+"	bpf_stf_barrier:			;"
+"		std	21,-64(1)		;"
+"		std	22,-56(1)		;"
+"		sync				;"
+"		ld	21,-64(1)		;"
+"		ld	22,-56(1)		;"
+"		ori	31,31,0			;"
+"		.rept 14			;"
+"		b	1f			;"
+"	1:					;"
+"		.endr				;"
+"		blr				;"
+);
+
 /* Assemble the body code between the prologue & epilogue */
 int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *ctx,
 		       u32 *addrs, bool extra_pass)
 {
+	enum stf_barrier_type stf_barrier = stf_barrier_type_get();
 	const struct bpf_insn *insn = fp->insnsi;
 	int flen = fp->len;
 	int i, ret;
@@ -328,18 +354,25 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 			EMIT(PPC_RAW_SUB(dst_reg, dst_reg, src_reg));
 			goto bpf_alu32_trunc;
 		case BPF_ALU | BPF_ADD | BPF_K: /* (u32) dst += (u32) imm */
-		case BPF_ALU | BPF_SUB | BPF_K: /* (u32) dst -= (u32) imm */
 		case BPF_ALU64 | BPF_ADD | BPF_K: /* dst += imm */
+			if (!imm) {
+				goto bpf_alu32_trunc;
+			} else if (imm >= -32768 && imm < 32768) {
+				EMIT(PPC_RAW_ADDI(dst_reg, dst_reg, IMM_L(imm)));
+			} else {
+				PPC_LI32(b2p[TMP_REG_1], imm);
+				EMIT(PPC_RAW_ADD(dst_reg, dst_reg, b2p[TMP_REG_1]));
+			}
+			goto bpf_alu32_trunc;
+		case BPF_ALU | BPF_SUB | BPF_K: /* (u32) dst -= (u32) imm */
 		case BPF_ALU64 | BPF_SUB | BPF_K: /* dst -= imm */
-			if (BPF_OP(code) == BPF_SUB)
-				imm = -imm;
-			if (imm) {
-				if (imm >= -32768 && imm < 32768)
-					EMIT(PPC_RAW_ADDI(dst_reg, dst_reg, IMM_L(imm)));
-				else {
-					PPC_LI32(b2p[TMP_REG_1], imm);
-					EMIT(PPC_RAW_ADD(dst_reg, dst_reg, b2p[TMP_REG_1]));
-				}
+			if (!imm) {
+				goto bpf_alu32_trunc;
+			} else if (imm > -32768 && imm <= 32768) {
+				EMIT(PPC_RAW_ADDI(dst_reg, dst_reg, IMM_L(-imm)));
+			} else {
+				PPC_LI32(b2p[TMP_REG_1], imm);
+				EMIT(PPC_RAW_SUB(dst_reg, dst_reg, b2p[TMP_REG_1]));
 			}
 			goto bpf_alu32_trunc;
 		case BPF_ALU | BPF_MUL | BPF_X: /* (u32) dst *= (u32) src */
@@ -389,8 +422,14 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 		case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */
 			if (imm == 0)
 				return -EINVAL;
-			else if (imm == 1)
-				goto bpf_alu32_trunc;
+			if (imm == 1) {
+				if (BPF_OP(code) == BPF_DIV) {
+					goto bpf_alu32_trunc;
+				} else {
+					EMIT(PPC_RAW_LI(dst_reg, 0));
+					break;
+				}
+			}
 
 			PPC_LI32(b2p[TMP_REG_1], imm);
 			switch (BPF_CLASS(code)) {
@@ -631,6 +670,29 @@ emit_clear:
 		 * BPF_ST NOSPEC (speculation barrier)
 		 */
 		case BPF_ST | BPF_NOSPEC:
+			if (!security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) ||
+					!security_ftr_enabled(SEC_FTR_STF_BARRIER))
+				break;
+
+			switch (stf_barrier) {
+			case STF_BARRIER_EIEIO:
+				EMIT(PPC_RAW_EIEIO() | 0x02000000);
+				break;
+			case STF_BARRIER_SYNC_ORI:
+				EMIT(PPC_RAW_SYNC());
+				EMIT(PPC_RAW_LD(b2p[TMP_REG_1], _R13, 0));
+				EMIT(PPC_RAW_ORI(_R31, _R31, 0));
+				break;
+			case STF_BARRIER_FALLBACK:
+				EMIT(PPC_RAW_MFLR(b2p[TMP_REG_1]));
+				PPC_LI64(12, dereference_kernel_function_descriptor(bpf_stf_barrier));
+				EMIT(PPC_RAW_MTCTR(12));
+				EMIT(PPC_RAW_BCTRL());
+				EMIT(PPC_RAW_MTLR(b2p[TMP_REG_1]));
+				break;
+			case STF_BARRIER_NONE:
+				break;
+			}
 			break;
 
 		/*
@@ -993,7 +1055,9 @@ cond_branch:
 		 */
 		case BPF_JMP | BPF_TAIL_CALL:
 			ctx->seen |= SEEN_TAILCALL;
-			bpf_jit_emit_tail_call(image, ctx, addrs[i + 1]);
+			ret = bpf_jit_emit_tail_call(image, ctx, addrs[i + 1]);
+			if (ret < 0)
+				return ret;
 			break;
 
 		default:
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index bc15200852b7..09fafcf2d3a0 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -867,6 +867,10 @@ static int __init eeh_pseries_init(void)
 	if (is_kdump_kernel() || reset_devices) {
 		pr_info("Issue PHB reset ...\n");
 		list_for_each_entry(phb, &hose_list, list_node) {
+			// Skip if the slot is empty
+			if (list_empty(&PCI_DN(phb->dn)->child_list))
+				continue;
+
 			pdn = list_first_entry(&PCI_DN(phb->dn)->child_list, struct pci_dn, list);
 			config_addr = pseries_eeh_get_pe_config_addr(pdn);
 
diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c
index 1b305e411862..8627362f613e 100644
--- a/arch/powerpc/platforms/pseries/msi.c
+++ b/arch/powerpc/platforms/pseries/msi.c
@@ -507,12 +507,27 @@ static void pseries_msi_unmask(struct irq_data *d)
 	irq_chip_unmask_parent(d);
 }
 
+static void pseries_msi_write_msg(struct irq_data *data, struct msi_msg *msg)
+{
+	struct msi_desc *entry = irq_data_get_msi_desc(data);
+
+	/*
+	 * Do not update the MSIx vector table. It's not strictly necessary
+	 * because the table is initialized by the underlying hypervisor, PowerVM
+	 * or QEMU/KVM. However, if the MSIx vector entry is cleared, any further
+	 * activation will fail. This can happen in some drivers (eg. IPR) which
+	 * deactivate an IRQ used for testing MSI support.
+	 */
+	entry->msg = *msg;
+}
+
 static struct irq_chip pseries_pci_msi_irq_chip = {
 	.name		= "pSeries-PCI-MSI",
 	.irq_shutdown	= pseries_msi_shutdown,
 	.irq_mask	= pseries_msi_mask,
 	.irq_unmask	= pseries_msi_unmask,
 	.irq_eoi	= irq_chip_eoi_parent,
+	.irq_write_msi_msg	= pseries_msi_write_msg,
 };
 
 static struct msi_domain_info pseries_msi_domain_info = {
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 301a54233c7e..6a6fa9e976d5 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -561,5 +561,3 @@ menu "Power management options"
 source "kernel/power/Kconfig"
 
 endmenu
-
-source "drivers/firmware/Kconfig"
diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h
index b933b1583c9f..34fbb3ea21d5 100644
--- a/arch/riscv/include/asm/syscall.h
+++ b/arch/riscv/include/asm/syscall.h
@@ -82,4 +82,5 @@ static inline int syscall_get_arch(struct task_struct *task)
 #endif
 }
 
+asmlinkage long sys_riscv_flush_icache(uintptr_t, uintptr_t, uintptr_t);
 #endif	/* _ASM_RISCV_SYSCALL_H */
diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h
index 893e47195e30..208e31bc5d1c 100644
--- a/arch/riscv/include/asm/vdso.h
+++ b/arch/riscv/include/asm/vdso.h
@@ -16,18 +16,24 @@
 #ifdef CONFIG_MMU
 
 #include <linux/types.h>
-#include <generated/vdso-offsets.h>
+/*
+ * All systems with an MMU have a VDSO, but systems without an MMU don't
+ * support shared libraries and therefor don't have one.
+ */
+#ifdef CONFIG_MMU
+
+#define __VVAR_PAGES    1
 
-#ifndef CONFIG_GENERIC_TIME_VSYSCALL
-struct vdso_data {
-};
-#endif
+#ifndef __ASSEMBLY__
+#include <generated/vdso-offsets.h>
 
 #define VDSO_SYMBOL(base, name)							\
 	(void __user *)((unsigned long)(base) + __vdso_##name##_offset)
 
 #endif /* CONFIG_MMU */
 
-asmlinkage long sys_riscv_flush_icache(uintptr_t, uintptr_t, uintptr_t);
+#endif /* !__ASSEMBLY__ */
+
+#endif /* CONFIG_MMU */
 
 #endif /* _ASM_RISCV_VDSO_H */
diff --git a/arch/riscv/include/uapi/asm/unistd.h b/arch/riscv/include/uapi/asm/unistd.h
index 4b989ae15d59..8062996c2dfd 100644
--- a/arch/riscv/include/uapi/asm/unistd.h
+++ b/arch/riscv/include/uapi/asm/unistd.h
@@ -18,9 +18,10 @@
 #ifdef __LP64__
 #define __ARCH_WANT_NEW_STAT
 #define __ARCH_WANT_SET_GET_RLIMIT
-#define __ARCH_WANT_SYS_CLONE3
 #endif /* __LP64__ */
 
+#define __ARCH_WANT_SYS_CLONE3
+
 #include <asm-generic/unistd.h>
 
 /*
diff --git a/arch/riscv/kernel/syscall_table.c b/arch/riscv/kernel/syscall_table.c
index a63c667c27b3..44b1420a2270 100644
--- a/arch/riscv/kernel/syscall_table.c
+++ b/arch/riscv/kernel/syscall_table.c
@@ -7,7 +7,6 @@
 #include <linux/linkage.h>
 #include <linux/syscalls.h>
 #include <asm-generic/syscalls.h>
-#include <asm/vdso.h>
 #include <asm/syscall.h>
 
 #undef __SYSCALL
diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c
index 25a3b8849599..b70956d80408 100644
--- a/arch/riscv/kernel/vdso.c
+++ b/arch/riscv/kernel/vdso.c
@@ -12,14 +12,24 @@
 #include <linux/binfmts.h>
 #include <linux/err.h>
 #include <asm/page.h>
+#include <asm/vdso.h>
+
 #ifdef CONFIG_GENERIC_TIME_VSYSCALL
 #include <vdso/datapage.h>
 #else
-#include <asm/vdso.h>
+struct vdso_data {
+};
 #endif
 
 extern char vdso_start[], vdso_end[];
 
+enum vvar_pages {
+	VVAR_DATA_PAGE_OFFSET,
+	VVAR_NR_PAGES,
+};
+
+#define VVAR_SIZE  (VVAR_NR_PAGES << PAGE_SHIFT)
+
 static unsigned int vdso_pages __ro_after_init;
 static struct page **vdso_pagelist __ro_after_init;
 
@@ -38,7 +48,7 @@ static int __init vdso_init(void)
 
 	vdso_pages = (vdso_end - vdso_start) >> PAGE_SHIFT;
 	vdso_pagelist =
-		kcalloc(vdso_pages + 1, sizeof(struct page *), GFP_KERNEL);
+		kcalloc(vdso_pages + VVAR_NR_PAGES, sizeof(struct page *), GFP_KERNEL);
 	if (unlikely(vdso_pagelist == NULL)) {
 		pr_err("vdso: pagelist allocation failed\n");
 		return -ENOMEM;
@@ -63,38 +73,41 @@ int arch_setup_additional_pages(struct linux_binprm *bprm,
 	unsigned long vdso_base, vdso_len;
 	int ret;
 
-	vdso_len = (vdso_pages + 1) << PAGE_SHIFT;
+	BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES);
+
+	vdso_len = (vdso_pages + VVAR_NR_PAGES) << PAGE_SHIFT;
+
+	if (mmap_write_lock_killable(mm))
+		return -EINTR;
 
-	mmap_write_lock(mm);
 	vdso_base = get_unmapped_area(NULL, 0, vdso_len, 0, 0);
 	if (IS_ERR_VALUE(vdso_base)) {
 		ret = vdso_base;
 		goto end;
 	}
 
-	/*
-	 * Put vDSO base into mm struct. We need to do this before calling
-	 * install_special_mapping or the perf counter mmap tracking code
-	 * will fail to recognise it as a vDSO (since arch_vma_name fails).
-	 */
-	mm->context.vdso = (void *)vdso_base;
+	mm->context.vdso = NULL;
+	ret = install_special_mapping(mm, vdso_base, VVAR_SIZE,
+		(VM_READ | VM_MAYREAD), &vdso_pagelist[vdso_pages]);
+	if (unlikely(ret))
+		goto end;
 
 	ret =
-	   install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT,
+	   install_special_mapping(mm, vdso_base + VVAR_SIZE,
+		vdso_pages << PAGE_SHIFT,
 		(VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC),
 		vdso_pagelist);
 
-	if (unlikely(ret)) {
-		mm->context.vdso = NULL;
+	if (unlikely(ret))
 		goto end;
-	}
 
-	vdso_base += (vdso_pages << PAGE_SHIFT);
-	ret = install_special_mapping(mm, vdso_base, PAGE_SIZE,
-		(VM_READ | VM_MAYREAD), &vdso_pagelist[vdso_pages]);
+	/*
+	 * Put vDSO base into mm struct. We need to do this before calling
+	 * install_special_mapping or the perf counter mmap tracking code
+	 * will fail to recognise it as a vDSO (since arch_vma_name fails).
+	 */
+	mm->context.vdso = (void *)vdso_base + VVAR_SIZE;
 
-	if (unlikely(ret))
-		mm->context.vdso = NULL;
 end:
 	mmap_write_unlock(mm);
 	return ret;
@@ -105,7 +118,7 @@ const char *arch_vma_name(struct vm_area_struct *vma)
 	if (vma->vm_mm && (vma->vm_start == (long)vma->vm_mm->context.vdso))
 		return "[vdso]";
 	if (vma->vm_mm && (vma->vm_start ==
-			   (long)vma->vm_mm->context.vdso + PAGE_SIZE))
+			   (long)vma->vm_mm->context.vdso - VVAR_SIZE))
 		return "[vdso_data]";
 	return NULL;
 }
diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S
index e6f558bca71b..e9111f700af0 100644
--- a/arch/riscv/kernel/vdso/vdso.lds.S
+++ b/arch/riscv/kernel/vdso/vdso.lds.S
@@ -3,12 +3,13 @@
  * Copyright (C) 2012 Regents of the University of California
  */
 #include <asm/page.h>
+#include <asm/vdso.h>
 
 OUTPUT_ARCH(riscv)
 
 SECTIONS
 {
-	PROVIDE(_vdso_data = . + PAGE_SIZE);
+	PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE);
 	. = SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text
diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c
index 094118663285..89f81067e09e 100644
--- a/arch/riscv/mm/cacheflush.c
+++ b/arch/riscv/mm/cacheflush.c
@@ -16,6 +16,8 @@ static void ipi_remote_fence_i(void *info)
 
 void flush_icache_all(void)
 {
+	local_flush_icache_all();
+
 	if (IS_ENABLED(CONFIG_RISCV_SBI))
 		sbi_remote_fence_i(NULL);
 	else
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index e4803ec51110..6b3c366af78e 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -207,6 +207,8 @@ int zpci_enable_device(struct zpci_dev *);
 int zpci_disable_device(struct zpci_dev *);
 int zpci_scan_configured_device(struct zpci_dev *zdev, u32 fh);
 int zpci_deconfigure_device(struct zpci_dev *zdev);
+void zpci_device_reserved(struct zpci_dev *zdev);
+bool zpci_is_device_configured(struct zpci_dev *zdev);
 
 int zpci_register_ioat(struct zpci_dev *, u8, u64, u64, u64);
 int zpci_unregister_ioat(struct zpci_dev *, u8);
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 840d8594437d..1a374d021e25 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -1826,7 +1826,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	jit.addrs = kvcalloc(fp->len + 1, sizeof(*jit.addrs), GFP_KERNEL);
 	if (jit.addrs == NULL) {
 		fp = orig_fp;
-		goto out;
+		goto free_addrs;
 	}
 	/*
 	 * Three initial passes:
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index e7e6788d75a8..b833155ce838 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -92,7 +92,7 @@ void zpci_remove_reserved_devices(void)
 	spin_unlock(&zpci_list_lock);
 
 	list_for_each_entry_safe(zdev, tmp, &remove, entry)
-		zpci_zdev_put(zdev);
+		zpci_device_reserved(zdev);
 }
 
 int pci_domain_nr(struct pci_bus *bus)
@@ -751,6 +751,14 @@ error:
 	return ERR_PTR(rc);
 }
 
+bool zpci_is_device_configured(struct zpci_dev *zdev)
+{
+	enum zpci_state state = zdev->state;
+
+	return state != ZPCI_FN_STATE_RESERVED &&
+		state != ZPCI_FN_STATE_STANDBY;
+}
+
 /**
  * zpci_scan_configured_device() - Scan a freshly configured zpci_dev
  * @zdev: The zpci_dev to be configured
@@ -822,6 +830,31 @@ int zpci_deconfigure_device(struct zpci_dev *zdev)
 	return 0;
 }
 
+/**
+ * zpci_device_reserved() - Mark device as resverved
+ * @zdev: the zpci_dev that was reserved
+ *
+ * Handle the case that a given zPCI function was reserved by another system.
+ * After a call to this function the zpci_dev can not be found via
+ * get_zdev_by_fid() anymore but may still be accessible via existing
+ * references though it will not be functional anymore.
+ */
+void zpci_device_reserved(struct zpci_dev *zdev)
+{
+	if (zdev->has_hp_slot)
+		zpci_exit_slot(zdev);
+	/*
+	 * Remove device from zpci_list as it is going away. This also
+	 * makes sure we ignore subsequent zPCI events for this device.
+	 */
+	spin_lock(&zpci_list_lock);
+	list_del(&zdev->entry);
+	spin_unlock(&zpci_list_lock);
+	zdev->state = ZPCI_FN_STATE_RESERVED;
+	zpci_dbg(3, "rsv fid:%x\n", zdev->fid);
+	zpci_zdev_put(zdev);
+}
+
 void zpci_release_device(struct kref *kref)
 {
 	struct zpci_dev *zdev = container_of(kref, struct zpci_dev, kref);
@@ -843,6 +876,12 @@ void zpci_release_device(struct kref *kref)
 	case ZPCI_FN_STATE_STANDBY:
 		if (zdev->has_hp_slot)
 			zpci_exit_slot(zdev);
+		spin_lock(&zpci_list_lock);
+		list_del(&zdev->entry);
+		spin_unlock(&zpci_list_lock);
+		zpci_dbg(3, "rsv fid:%x\n", zdev->fid);
+		fallthrough;
+	case ZPCI_FN_STATE_RESERVED:
 		if (zdev->has_resources)
 			zpci_cleanup_bus_resources(zdev);
 		zpci_bus_device_unregister(zdev);
@@ -851,10 +890,6 @@ void zpci_release_device(struct kref *kref)
 	default:
 		break;
 	}
-
-	spin_lock(&zpci_list_lock);
-	list_del(&zdev->entry);
-	spin_unlock(&zpci_list_lock);
 	zpci_dbg(3, "rem fid:%x\n", zdev->fid);
 	kfree(zdev);
 }
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index c856f80cb21b..5b8d647523f9 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -140,7 +140,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 			/* The 0x0304 event may immediately reserve the device */
 			if (!clp_get_state(zdev->fid, &state) &&
 			    state == ZPCI_FN_STATE_RESERVED) {
-				zpci_zdev_put(zdev);
+				zpci_device_reserved(zdev);
 			}
 		}
 		break;
@@ -151,7 +151,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 	case 0x0308: /* Standby -> Reserved */
 		if (!zdev)
 			break;
-		zpci_zdev_put(zdev);
+		zpci_device_reserved(zdev);
 		break;
 	default:
 		break;
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index ab83c22d274e..bd70e8a39fbf 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1405,7 +1405,7 @@ config HIGHMEM4G
 
 config HIGHMEM64G
 	bool "64GB"
-	depends on !M486SX && !M486 && !M586 && !M586TSC && !M586MMX && !MGEODE_LX && !MGEODEGX1 && !MCYRIXIII && !MELAN && !MWINCHIPC6 && !WINCHIP3D && !MK6
+	depends on !M486SX && !M486 && !M586 && !M586TSC && !M586MMX && !MGEODE_LX && !MGEODEGX1 && !MCYRIXIII && !MELAN && !MWINCHIPC6 && !MWINCHIP3D && !MK6
 	select X86_PAE
 	help
 	  Select this if you have a 32-bit processor and more than 4
@@ -2832,8 +2832,6 @@ config HAVE_ATOMIC_IOMAP
 	def_bool y
 	depends on X86_32
 
-source "drivers/firmware/Kconfig"
-
 source "arch/x86/kvm/Kconfig"
 
 source "arch/x86/Kconfig.assembler"
diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h
index 14ebd2196569..43184640b579 100644
--- a/arch/x86/include/asm/entry-common.h
+++ b/arch/x86/include/asm/entry-common.h
@@ -25,7 +25,7 @@ static __always_inline void arch_check_user_regs(struct pt_regs *regs)
 		 * For !SMAP hardware we patch out CLAC on entry.
 		 */
 		if (boot_cpu_has(X86_FEATURE_SMAP) ||
-		    (IS_ENABLED(CONFIG_64_BIT) && boot_cpu_has(X86_FEATURE_XENPV)))
+		    (IS_ENABLED(CONFIG_64BIT) && boot_cpu_has(X86_FEATURE_XENPV)))
 			mask |= X86_EFLAGS_AC;
 
 		WARN_ON_ONCE(flags & mask);
diff --git a/arch/x86/include/asm/xen/pci.h b/arch/x86/include/asm/xen/pci.h
index 3506d8c598c1..4557f7cb0fa6 100644
--- a/arch/x86/include/asm/xen/pci.h
+++ b/arch/x86/include/asm/xen/pci.h
@@ -14,16 +14,19 @@ static inline int pci_xen_hvm_init(void)
 	return -1;
 }
 #endif
-#if defined(CONFIG_XEN_DOM0)
+#ifdef CONFIG_XEN_PV_DOM0
 int __init pci_xen_initial_domain(void);
-int xen_find_device_domain_owner(struct pci_dev *dev);
-int xen_register_device_domain_owner(struct pci_dev *dev, uint16_t domain);
-int xen_unregister_device_domain_owner(struct pci_dev *dev);
 #else
 static inline int __init pci_xen_initial_domain(void)
 {
 	return -1;
 }
+#endif
+#ifdef CONFIG_XEN_DOM0
+int xen_find_device_domain_owner(struct pci_dev *dev);
+int xen_register_device_domain_owner(struct pci_dev *dev, uint16_t domain);
+int xen_unregister_device_domain_owner(struct pci_dev *dev);
+#else
 static inline int xen_find_device_domain_owner(struct pci_dev *dev)
 {
 	return -1;
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 0f8885949e8c..b3410f1ac217 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -326,6 +326,7 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c)
 #ifdef CONFIG_X86_SMAP
 		cr4_set_bits(X86_CR4_SMAP);
 #else
+		clear_cpu_cap(c, X86_FEATURE_SMAP);
 		cr4_clear_bits(X86_CR4_SMAP);
 #endif
 	}
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 4b8813bafffd..bb1c3f5f60c8 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -527,12 +527,14 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 	rdt_domain_reconfigure_cdp(r);
 
 	if (r->alloc_capable && domain_setup_ctrlval(r, d)) {
-		kfree(d);
+		kfree(hw_dom);
 		return;
 	}
 
 	if (r->mon_capable && domain_setup_mon_state(r, d)) {
-		kfree(d);
+		kfree(hw_dom->ctrl_val);
+		kfree(hw_dom->mbps_val);
+		kfree(hw_dom);
 		return;
 	}
 
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 38837dad46e6..391a4e2b8604 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -714,12 +714,6 @@ static struct chipset early_qrk[] __initdata = {
 	 */
 	{ PCI_VENDOR_ID_INTEL, 0x0f00,
 		PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
-	{ PCI_VENDOR_ID_INTEL, 0x3e20,
-		PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
-	{ PCI_VENDOR_ID_INTEL, 0x3ec4,
-		PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
-	{ PCI_VENDOR_ID_INTEL, 0x8a12,
-		PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
 	{ PCI_VENDOR_ID_BROADCOM, 0x4331,
 	  PCI_CLASS_NETWORK_OTHER, PCI_ANY_ID, 0, apple_airport_reset},
 	{}
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index 445c57c9c539..fa17a27390ab 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -379,9 +379,14 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx,
 				     sizeof(fpu->state.fxsave)))
 			return -EFAULT;
 
-		/* Reject invalid MXCSR values. */
-		if (fpu->state.fxsave.mxcsr & ~mxcsr_feature_mask)
-			return -EINVAL;
+		if (IS_ENABLED(CONFIG_X86_64)) {
+			/* Reject invalid MXCSR values. */
+			if (fpu->state.fxsave.mxcsr & ~mxcsr_feature_mask)
+				return -EINVAL;
+		} else {
+			/* Mask invalid bits out for historical reasons (broken hardware). */
+			fpu->state.fxsave.mxcsr &= ~mxcsr_feature_mask;
+		}
 
 		/* Enforce XFEATURE_MASK_FPSSE when XSAVE is enabled */
 		if (use_xsave())
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 42fc41dd0e1f..882213df3713 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -10,6 +10,7 @@
 #include <asm/irq_remapping.h>
 #include <asm/hpet.h>
 #include <asm/time.h>
+#include <asm/mwait.h>
 
 #undef  pr_fmt
 #define pr_fmt(fmt) "hpet: " fmt
@@ -916,6 +917,83 @@ static bool __init hpet_counting(void)
 	return false;
 }
 
+static bool __init mwait_pc10_supported(void)
+{
+	unsigned int eax, ebx, ecx, mwait_substates;
+
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+		return false;
+
+	if (!cpu_feature_enabled(X86_FEATURE_MWAIT))
+		return false;
+
+	if (boot_cpu_data.cpuid_level < CPUID_MWAIT_LEAF)
+		return false;
+
+	cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &mwait_substates);
+
+	return (ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED) &&
+	       (ecx & CPUID5_ECX_INTERRUPT_BREAK) &&
+	       (mwait_substates & (0xF << 28));
+}
+
+/*
+ * Check whether the system supports PC10. If so force disable HPET as that
+ * stops counting in PC10. This check is overbroad as it does not take any
+ * of the following into account:
+ *
+ *	- ACPI tables
+ *	- Enablement of intel_idle
+ *	- Command line arguments which limit intel_idle C-state support
+ *
+ * That's perfectly fine. HPET is a piece of hardware designed by committee
+ * and the only reasons why it is still in use on modern systems is the
+ * fact that it is impossible to reliably query TSC and CPU frequency via
+ * CPUID or firmware.
+ *
+ * If HPET is functional it is useful for calibrating TSC, but this can be
+ * done via PMTIMER as well which seems to be the last remaining timer on
+ * X86/INTEL platforms that has not been completely wreckaged by feature
+ * creep.
+ *
+ * In theory HPET support should be removed altogether, but there are older
+ * systems out there which depend on it because TSC and APIC timer are
+ * dysfunctional in deeper C-states.
+ *
+ * It's only 20 years now that hardware people have been asked to provide
+ * reliable and discoverable facilities which can be used for timekeeping
+ * and per CPU timer interrupts.
+ *
+ * The probability that this problem is going to be solved in the
+ * forseeable future is close to zero, so the kernel has to be cluttered
+ * with heuristics to keep up with the ever growing amount of hardware and
+ * firmware trainwrecks. Hopefully some day hardware people will understand
+ * that the approach of "This can be fixed in software" is not sustainable.
+ * Hope dies last...
+ */
+static bool __init hpet_is_pc10_damaged(void)
+{
+	unsigned long long pcfg;
+
+	/* Check whether PC10 substates are supported */
+	if (!mwait_pc10_supported())
+		return false;
+
+	/* Check whether PC10 is enabled in PKG C-state limit */
+	rdmsrl(MSR_PKG_CST_CONFIG_CONTROL, pcfg);
+	if ((pcfg & 0xF) < 8)
+		return false;
+
+	if (hpet_force_user) {
+		pr_warn("HPET force enabled via command line, but dysfunctional in PC10.\n");
+		return false;
+	}
+
+	pr_info("HPET dysfunctional in PC10. Force disabled.\n");
+	boot_hpet_disable = true;
+	return true;
+}
+
 /**
  * hpet_enable - Try to setup the HPET timer. Returns 1 on success.
  */
@@ -929,6 +1007,9 @@ int __init hpet_enable(void)
 	if (!is_hpet_capable())
 		return 0;
 
+	if (hpet_is_pc10_damaged())
+		return 0;
+
 	hpet_set_mapping();
 	if (!hpet_virt_address)
 		return 0;
diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c
index 9f90f460a28c..bf1033a62e48 100644
--- a/arch/x86/kernel/sev-shared.c
+++ b/arch/x86/kernel/sev-shared.c
@@ -130,6 +130,8 @@ static enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb,
 		} else {
 			ret = ES_VMM_ERROR;
 		}
+	} else if (ghcb->save.sw_exit_info_1 & 0xffffffff) {
+		ret = ES_VMM_ERROR;
 	} else {
 		ret = ES_OK;
 	}
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 3d41a09c2c14..5debe4ac6f81 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -113,7 +113,7 @@ static int acpi_register_gsi_xen_hvm(struct device *dev, u32 gsi,
 				 false /* no mapping of GSI to PIRQ */);
 }
 
-#ifdef CONFIG_XEN_DOM0
+#ifdef CONFIG_XEN_PV_DOM0
 static int xen_register_gsi(u32 gsi, int triggering, int polarity)
 {
 	int rc, irq;
@@ -261,7 +261,7 @@ error:
 	return irq;
 }
 
-#ifdef CONFIG_XEN_DOM0
+#ifdef CONFIG_XEN_PV_DOM0
 static bool __read_mostly pci_seg_supported = true;
 
 static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
@@ -375,10 +375,10 @@ static void xen_initdom_restore_msi_irqs(struct pci_dev *dev)
 		WARN(ret && ret != -ENOSYS, "restore_msi -> %d\n", ret);
 	}
 }
-#else /* CONFIG_XEN_DOM0 */
+#else /* CONFIG_XEN_PV_DOM0 */
 #define xen_initdom_setup_msi_irqs	NULL
 #define xen_initdom_restore_msi_irqs	NULL
-#endif /* !CONFIG_XEN_DOM0 */
+#endif /* !CONFIG_XEN_PV_DOM0 */
 
 static void xen_teardown_msi_irqs(struct pci_dev *dev)
 {
@@ -555,7 +555,7 @@ int __init pci_xen_hvm_init(void)
 	return 0;
 }
 
-#ifdef CONFIG_XEN_DOM0
+#ifdef CONFIG_XEN_PV_DOM0
 int __init pci_xen_initial_domain(void)
 {
 	int irq;
@@ -583,6 +583,9 @@ int __init pci_xen_initial_domain(void)
 	}
 	return 0;
 }
+#endif
+
+#ifdef CONFIG_XEN_DOM0
 
 struct xen_device_domain_owner {
 	domid_t domain;
@@ -656,4 +659,4 @@ int xen_unregister_device_domain_owner(struct pci_dev *dev)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(xen_unregister_device_domain_owner);
-#endif
+#endif /* CONFIG_XEN_DOM0 */
diff --git a/arch/x86/platform/olpc/olpc.c b/arch/x86/platform/olpc/olpc.c
index ee2beda590d0..1d4a00e767ec 100644
--- a/arch/x86/platform/olpc/olpc.c
+++ b/arch/x86/platform/olpc/olpc.c
@@ -274,7 +274,7 @@ static struct olpc_ec_driver ec_xo1_driver = {
 
 static struct olpc_ec_driver ec_xo1_5_driver = {
 	.ec_cmd = olpc_xo1_ec_cmd,
-#ifdef CONFIG_OLPC_XO1_5_SCI
+#ifdef CONFIG_OLPC_XO15_SCI
 	/*
 	 * XO-1.5 EC wakeups are available when olpc-xo15-sci driver is
 	 * compiled in
diff --git a/arch/x86/platform/pvh/enlighten.c b/arch/x86/platform/pvh/enlighten.c
index 9ac7457f52a3..ed0442e35434 100644
--- a/arch/x86/platform/pvh/enlighten.c
+++ b/arch/x86/platform/pvh/enlighten.c
@@ -16,15 +16,15 @@
 /*
  * PVH variables.
  *
- * pvh_bootparams and pvh_start_info need to live in the data segment since
+ * pvh_bootparams and pvh_start_info need to live in a data segment since
  * they are used after startup_{32|64}, which clear .bss, are invoked.
  */
-struct boot_params pvh_bootparams __section(".data");
-struct hvm_start_info pvh_start_info __section(".data");
+struct boot_params __initdata pvh_bootparams;
+struct hvm_start_info __initdata pvh_start_info;
 
-unsigned int pvh_start_info_sz = sizeof(pvh_start_info);
+const unsigned int __initconst pvh_start_info_sz = sizeof(pvh_start_info);
 
-static u64 pvh_get_root_pointer(void)
+static u64 __init pvh_get_root_pointer(void)
 {
 	return pvh_start_info.rsdp_paddr;
 }
@@ -107,7 +107,7 @@ void __init __weak xen_pvh_init(struct boot_params *boot_params)
 	BUG();
 }
 
-static void hypervisor_specific_init(bool xen_guest)
+static void __init hypervisor_specific_init(bool xen_guest)
 {
 	if (xen_guest)
 		xen_pvh_init(&pvh_bootparams);
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index afc1da68b06d..6bcd3d8ca6ac 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -43,13 +43,9 @@ config XEN_PV_SMP
 	def_bool y
 	depends on XEN_PV && SMP
 
-config XEN_DOM0
-	bool "Xen PV Dom0 support"
-	default y
-	depends on XEN_PV && PCI_XEN && SWIOTLB_XEN
-	depends on X86_IO_APIC && ACPI && PCI
-	help
-	  Support running as a Xen PV Dom0 guest.
+config XEN_PV_DOM0
+	def_bool y
+	depends on XEN_PV && XEN_DOM0
 
 config XEN_PVHVM
 	def_bool y
@@ -86,3 +82,12 @@ config XEN_PVH
 	def_bool n
 	help
 	  Support for running as a Xen PVH guest.
+
+config XEN_DOM0
+	bool "Xen Dom0 support"
+	default XEN_PV
+	depends on (XEN_PV && SWIOTLB_XEN) || (XEN_PVH && X86_64)
+	depends on X86_IO_APIC && ACPI && PCI
+	select X86_X2APIC if XEN_PVH && X86_64
+	help
+	  Support running as a Xen Dom0 guest.
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index 40b5779fce21..4953260e281c 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -45,7 +45,7 @@ obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o
 
 obj-$(CONFIG_XEN_DEBUG_FS)	+= debugfs.o
 
-obj-$(CONFIG_XEN_DOM0)		+= vga.o
+obj-$(CONFIG_XEN_PV_DOM0)	+= vga.o
 
 obj-$(CONFIG_SWIOTLB_XEN)	+= pci-swiotlb-xen.o
 
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index c79bd0af2e8c..95d970359e17 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -3,6 +3,7 @@
 #ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
 #include <linux/memblock.h>
 #endif
+#include <linux/console.h>
 #include <linux/cpu.h>
 #include <linux/kexec.h>
 #include <linux/slab.h>
@@ -10,12 +11,15 @@
 
 #include <xen/xen.h>
 #include <xen/features.h>
+#include <xen/interface/sched.h>
+#include <xen/interface/version.h>
 #include <xen/page.h>
 
 #include <asm/xen/hypercall.h>
 #include <asm/xen/hypervisor.h>
 #include <asm/cpu.h>
 #include <asm/e820/api.h> 
+#include <asm/setup.h>
 
 #include "xen-ops.h"
 #include "smp.h"
@@ -52,9 +56,6 @@ DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info);
 DEFINE_PER_CPU(uint32_t, xen_vcpu_id);
 EXPORT_PER_CPU_SYMBOL(xen_vcpu_id);
 
-enum xen_domain_type xen_domain_type = XEN_NATIVE;
-EXPORT_SYMBOL_GPL(xen_domain_type);
-
 unsigned long *machine_to_phys_mapping = (void *)MACH2PHYS_VIRT_START;
 EXPORT_SYMBOL(machine_to_phys_mapping);
 unsigned long  machine_to_phys_nr;
@@ -69,10 +70,12 @@ __read_mostly int xen_have_vector_callback;
 EXPORT_SYMBOL_GPL(xen_have_vector_callback);
 
 /*
- * NB: needs to live in .data because it's used by xen_prepare_pvh which runs
- * before clearing the bss.
+ * NB: These need to live in .data or alike because they're used by
+ * xen_prepare_pvh() which runs before clearing the bss.
  */
-uint32_t xen_start_flags __section(".data") = 0;
+enum xen_domain_type __ro_after_init xen_domain_type = XEN_NATIVE;
+EXPORT_SYMBOL_GPL(xen_domain_type);
+uint32_t __ro_after_init xen_start_flags;
 EXPORT_SYMBOL(xen_start_flags);
 
 /*
@@ -258,6 +261,45 @@ int xen_vcpu_setup(int cpu)
 	return ((per_cpu(xen_vcpu, cpu) == NULL) ? -ENODEV : 0);
 }
 
+void __init xen_banner(void)
+{
+	unsigned version = HYPERVISOR_xen_version(XENVER_version, NULL);
+	struct xen_extraversion extra;
+
+	HYPERVISOR_xen_version(XENVER_extraversion, &extra);
+
+	pr_info("Booting kernel on %s\n", pv_info.name);
+	pr_info("Xen version: %u.%u%s%s\n",
+		version >> 16, version & 0xffff, extra.extraversion,
+		xen_feature(XENFEAT_mmu_pt_update_preserve_ad)
+		? " (preserve-AD)" : "");
+}
+
+/* Check if running on Xen version (major, minor) or later */
+bool xen_running_on_version_or_later(unsigned int major, unsigned int minor)
+{
+	unsigned int version;
+
+	if (!xen_domain())
+		return false;
+
+	version = HYPERVISOR_xen_version(XENVER_version, NULL);
+	if ((((version >> 16) == major) && ((version & 0xffff) >= minor)) ||
+		((version >> 16) > major))
+		return true;
+	return false;
+}
+
+void __init xen_add_preferred_consoles(void)
+{
+	add_preferred_console("xenboot", 0, NULL);
+	if (!boot_params.screen_info.orig_video_isVGA)
+		add_preferred_console("tty", 0, NULL);
+	add_preferred_console("hvc", 0, NULL);
+	if (boot_params.screen_info.orig_video_isVGA)
+		add_preferred_console("tty", 0, NULL);
+}
+
 void xen_reboot(int reason)
 {
 	struct sched_shutdown r = { .reason = reason };
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 6e0d0754f94f..a7b7d674f500 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -28,7 +28,6 @@
 #include <linux/mm.h>
 #include <linux/page-flags.h>
 #include <linux/highmem.h>
-#include <linux/console.h>
 #include <linux/pci.h>
 #include <linux/gfp.h>
 #include <linux/edd.h>
@@ -109,17 +108,6 @@ struct tls_descs {
  */
 static DEFINE_PER_CPU(struct tls_descs, shadow_tls_desc);
 
-static void __init xen_banner(void)
-{
-	unsigned version = HYPERVISOR_xen_version(XENVER_version, NULL);
-	struct xen_extraversion extra;
-	HYPERVISOR_xen_version(XENVER_extraversion, &extra);
-
-	pr_info("Booting paravirtualized kernel on %s\n", pv_info.name);
-	pr_info("Xen version: %d.%d%s (preserve-AD)\n",
-		version >> 16, version & 0xffff, extra.extraversion);
-}
-
 static void __init xen_pv_init_platform(void)
 {
 	populate_extra_pte(fix_to_virt(FIX_PARAVIRT_BOOTMAP));
@@ -142,22 +130,6 @@ static void __init xen_pv_guest_late_init(void)
 #endif
 }
 
-/* Check if running on Xen version (major, minor) or later */
-bool
-xen_running_on_version_or_later(unsigned int major, unsigned int minor)
-{
-	unsigned int version;
-
-	if (!xen_domain())
-		return false;
-
-	version = HYPERVISOR_xen_version(XENVER_version, NULL);
-	if ((((version >> 16) == major) && ((version & 0xffff) >= minor)) ||
-		((version >> 16) > major))
-		return true;
-	return false;
-}
-
 static __read_mostly unsigned int cpuid_leaf5_ecx_val;
 static __read_mostly unsigned int cpuid_leaf5_edx_val;
 
@@ -1364,7 +1336,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	boot_params.hdr.hardware_subarch = X86_SUBARCH_XEN;
 
 	if (!xen_initial_domain()) {
-		add_preferred_console("xenboot", 0, NULL);
 		if (pci_xen)
 			x86_init.pci.arch_init = pci_xen_init;
 		x86_platform.set_legacy_features =
@@ -1409,11 +1380,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
 #endif
 	}
 
-	if (!boot_params.screen_info.orig_video_isVGA)
-		add_preferred_console("tty", 0, NULL);
-	add_preferred_console("hvc", 0, NULL);
-	if (boot_params.screen_info.orig_video_isVGA)
-		add_preferred_console("tty", 0, NULL);
+	xen_add_preferred_consoles();
 
 #ifdef CONFIG_PCI
 	/* PCI BIOS service won't work from a PV guest. */
diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c
index 0d5e34b9e6f9..bcae606bbc5c 100644
--- a/arch/x86/xen/enlighten_pvh.c
+++ b/arch/x86/xen/enlighten_pvh.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/acpi.h>
+#include <linux/export.h>
 
 #include <xen/hvc-console.h>
 
@@ -18,10 +19,11 @@
 /*
  * PVH variables.
  *
- * The variable xen_pvh needs to live in the data segment since it is used
+ * The variable xen_pvh needs to live in a data segment since it is used
  * after startup_{32|64} is invoked, which will clear the .bss segment.
  */
-bool xen_pvh __section(".data") = 0;
+bool __ro_after_init xen_pvh;
+EXPORT_SYMBOL_GPL(xen_pvh);
 
 void __init xen_pvh_init(struct boot_params *boot_params)
 {
@@ -36,6 +38,10 @@ void __init xen_pvh_init(struct boot_params *boot_params)
 	pfn = __pa(hypercall_page);
 	wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32));
 
+	if (xen_initial_domain())
+		x86_init.oem.arch_setup = xen_add_preferred_consoles;
+	x86_init.oem.banner = xen_banner;
+
 	xen_efi_init(boot_params);
 }
 
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 8d751939c6f3..3359c23573c5 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -2398,7 +2398,7 @@ static int remap_area_pfn_pte_fn(pte_t *ptep, unsigned long addr, void *data)
 
 int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr,
 		  xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot,
-		  unsigned int domid, bool no_translate, struct page **pages)
+		  unsigned int domid, bool no_translate)
 {
 	int err = 0;
 	struct remap_data rmd;
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 8d7ec49a35fb..8bc8b72a205d 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -51,6 +51,7 @@ void __init xen_remap_memory(void);
 phys_addr_t __init xen_find_free_area(phys_addr_t size);
 char * __init xen_memory_setup(void);
 void __init xen_arch_setup(void);
+void xen_banner(void);
 void xen_enable_sysenter(void);
 void xen_enable_syscall(void);
 void xen_vcpu_restore(void);
@@ -109,7 +110,7 @@ static inline void xen_uninit_lock_cpu(int cpu)
 
 struct dom0_vga_console_info;
 
-#ifdef CONFIG_XEN_DOM0
+#ifdef CONFIG_XEN_PV_DOM0
 void __init xen_init_vga(const struct dom0_vga_console_info *, size_t size);
 #else
 static inline void __init xen_init_vga(const struct dom0_vga_console_info *info,
@@ -118,6 +119,8 @@ static inline void __init xen_init_vga(const struct dom0_vga_console_info *info,
 }
 #endif
 
+void xen_add_preferred_consoles(void);
+
 void __init xen_init_apic(void);
 
 #ifdef CONFIG_XEN_EFI
diff --git a/arch/xtensa/include/asm/kmem_layout.h b/arch/xtensa/include/asm/kmem_layout.h
index 7cbf68ca7106..6fc05cba61a2 100644
--- a/arch/xtensa/include/asm/kmem_layout.h
+++ b/arch/xtensa/include/asm/kmem_layout.h
@@ -78,7 +78,7 @@
 #endif
 #define XCHAL_KIO_SIZE			0x10000000
 
-#if (!XCHAL_HAVE_PTP_MMU || XCHAL_HAVE_SPANNING_WAY) && defined(CONFIG_OF)
+#if (!XCHAL_HAVE_PTP_MMU || XCHAL_HAVE_SPANNING_WAY) && defined(CONFIG_USE_OF)
 #define XCHAL_KIO_PADDR			xtensa_get_kio_paddr()
 #ifndef __ASSEMBLY__
 extern unsigned long xtensa_kio_paddr;
diff --git a/arch/xtensa/kernel/irq.c b/arch/xtensa/kernel/irq.c
index 764b54bef701..15051a8a1539 100644
--- a/arch/xtensa/kernel/irq.c
+++ b/arch/xtensa/kernel/irq.c
@@ -143,7 +143,7 @@ unsigned xtensa_get_ext_irq_no(unsigned irq)
 
 void __init init_IRQ(void)
 {
-#ifdef CONFIG_OF
+#ifdef CONFIG_USE_OF
 	irqchip_init();
 #else
 #ifdef CONFIG_HAVE_SMP
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index ed184106e4cf..ee9082a142fe 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -63,7 +63,7 @@ extern unsigned long initrd_end;
 extern int initrd_below_start_ok;
 #endif
 
-#ifdef CONFIG_OF
+#ifdef CONFIG_USE_OF
 void *dtb_start = __dtb_start;
 #endif
 
@@ -125,7 +125,7 @@ __tagtable(BP_TAG_INITRD, parse_tag_initrd);
 
 #endif /* CONFIG_BLK_DEV_INITRD */
 
-#ifdef CONFIG_OF
+#ifdef CONFIG_USE_OF
 
 static int __init parse_tag_fdt(const bp_tag_t *tag)
 {
@@ -135,7 +135,7 @@ static int __init parse_tag_fdt(const bp_tag_t *tag)
 
 __tagtable(BP_TAG_FDT, parse_tag_fdt);
 
-#endif /* CONFIG_OF */
+#endif /* CONFIG_USE_OF */
 
 static int __init parse_tag_cmdline(const bp_tag_t* tag)
 {
@@ -183,7 +183,7 @@ static int __init parse_bootparam(const bp_tag_t *tag)
 }
 #endif
 
-#ifdef CONFIG_OF
+#ifdef CONFIG_USE_OF
 
 #if !XCHAL_HAVE_PTP_MMU || XCHAL_HAVE_SPANNING_WAY
 unsigned long xtensa_kio_paddr = XCHAL_KIO_DEFAULT_PADDR;
@@ -232,7 +232,7 @@ void __init early_init_devtree(void *params)
 		strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
 }
 
-#endif /* CONFIG_OF */
+#endif /* CONFIG_USE_OF */
 
 /*
  * Initialize architecture. (Early stage)
@@ -253,7 +253,7 @@ void __init init_arch(bp_tag_t *bp_start)
 	if (bp_start)
 		parse_bootparam(bp_start);
 
-#ifdef CONFIG_OF
+#ifdef CONFIG_USE_OF
 	early_init_devtree(dtb_start);
 #endif
 
diff --git a/arch/xtensa/mm/mmu.c b/arch/xtensa/mm/mmu.c
index 7e4d97dc8bd8..38acda4f04e8 100644
--- a/arch/xtensa/mm/mmu.c
+++ b/arch/xtensa/mm/mmu.c
@@ -101,7 +101,7 @@ void init_mmu(void)
 
 void init_kio(void)
 {
-#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && defined(CONFIG_OF)
+#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && defined(CONFIG_USE_OF)
 	/*
 	 * Update the IO area mapping in case xtensa_kio_paddr has changed
 	 */
diff --git a/arch/xtensa/platforms/xtfpga/setup.c b/arch/xtensa/platforms/xtfpga/setup.c
index 4f7d6142d41f..538e6748e85a 100644
--- a/arch/xtensa/platforms/xtfpga/setup.c
+++ b/arch/xtensa/platforms/xtfpga/setup.c
@@ -51,8 +51,12 @@ void platform_power_off(void)
 
 void platform_restart(void)
 {
-	/* Flush and reset the mmu, simulate a processor reset, and
-	 * jump to the reset vector. */
+	/* Try software reset first. */
+	WRITE_ONCE(*(u32 *)XTFPGA_SWRST_VADDR, 0xdead);
+
+	/* If software reset did not work, flush and reset the mmu,
+	 * simulate a processor reset, and jump to the reset vector.
+	 */
 	cpu_reset();
 	/* control never gets here */
 }
@@ -66,7 +70,7 @@ void __init platform_calibrate_ccount(void)
 
 #endif
 
-#ifdef CONFIG_OF
+#ifdef CONFIG_USE_OF
 
 static void __init xtfpga_clk_setup(struct device_node *np)
 {
@@ -284,4 +288,4 @@ static int __init xtavnet_init(void)
  */
 arch_initcall(xtavnet_init);
 
-#endif /* CONFIG_OF */
+#endif /* CONFIG_USE_OF */