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

Conflicts:

drivers/net/can/dev.c
  commit 03f16c5075b2 ("can: dev: can_restart: fix use after free bug")
  commit 3e77f70e7345 ("can: dev: move driver related infrastructure into separate subdir")

  Code move.

drivers/net/dsa/b53/b53_common.c
 commit 8e4052c32d6b ("net: dsa: b53: fix an off by one in checking "vlan->vid"")
 commit b7a9e0da2d1c ("net: switchdev: remove vid_begin -> vid_end range from VLAN objects")

 Field rename.

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

36 files changed, 219 insertions, 152 deletions

diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 60e901cd0de6..5a957a9a0984 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -371,7 +371,7 @@ static int __init xen_guest_init(void)
 	}
 	gnttab_init();
 	if (!xen_initial_domain())
-		xenbus_probe(NULL);
+		xenbus_probe();
 
 	/*
 	 * Making sure board specific code will not set up ops for
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 05e17351e4f3..f39568b28ec1 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -174,8 +174,6 @@ config ARM64
 	select HAVE_NMI
 	select HAVE_PATA_PLATFORM
 	select HAVE_PERF_EVENTS
-	select HAVE_PERF_EVENTS_NMI if ARM64_PSEUDO_NMI && HW_PERF_EVENTS
-	select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_REGS_AND_STACK_ACCESS_API
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index 015ddffaf6ca..b56a4b2bc248 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -17,7 +17,7 @@
 #include <asm/lse.h>
 
 #define ATOMIC_OP(op)							\
-static inline void arch_##op(int i, atomic_t *v)			\
+static __always_inline void arch_##op(int i, atomic_t *v)		\
 {									\
 	__lse_ll_sc_body(op, i, v);					\
 }
@@ -32,7 +32,7 @@ ATOMIC_OP(atomic_sub)
 #undef ATOMIC_OP
 
 #define ATOMIC_FETCH_OP(name, op)					\
-static inline int arch_##op##name(int i, atomic_t *v)			\
+static __always_inline int arch_##op##name(int i, atomic_t *v)		\
 {									\
 	return __lse_ll_sc_body(op##name, i, v);			\
 }
@@ -56,7 +56,7 @@ ATOMIC_FETCH_OPS(atomic_sub_return)
 #undef ATOMIC_FETCH_OPS
 
 #define ATOMIC64_OP(op)							\
-static inline void arch_##op(long i, atomic64_t *v)			\
+static __always_inline void arch_##op(long i, atomic64_t *v)		\
 {									\
 	__lse_ll_sc_body(op, i, v);					\
 }
@@ -71,7 +71,7 @@ ATOMIC64_OP(atomic64_sub)
 #undef ATOMIC64_OP
 
 #define ATOMIC64_FETCH_OP(name, op)					\
-static inline long arch_##op##name(long i, atomic64_t *v)		\
+static __always_inline long arch_##op##name(long i, atomic64_t *v)	\
 {									\
 	return __lse_ll_sc_body(op##name, i, v);			\
 }
@@ -94,7 +94,7 @@ ATOMIC64_FETCH_OPS(atomic64_sub_return)
 #undef ATOMIC64_FETCH_OP
 #undef ATOMIC64_FETCH_OPS
 
-static inline long arch_atomic64_dec_if_positive(atomic64_t *v)
+static __always_inline long arch_atomic64_dec_if_positive(atomic64_t *v)
 {
 	return __lse_ll_sc_body(atomic64_dec_if_positive, v);
 }
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 69ad25fbeae4..ca2cd75d3286 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -94,8 +94,7 @@
 #endif /* CONFIG_ARM64_FORCE_52BIT */
 
 extern phys_addr_t arm64_dma_phys_limit;
-extern phys_addr_t arm64_dma32_phys_limit;
-#define ARCH_LOW_ADDRESS_LIMIT	((arm64_dma_phys_limit ? : arm64_dma32_phys_limit) - 1)
+#define ARCH_LOW_ADDRESS_LIMIT	(arm64_dma_phys_limit - 1)
 
 struct debug_info {
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index f42fd9e33981..301784463587 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -75,7 +75,7 @@ int main(void)
   DEFINE(S_SDEI_TTBR1,		offsetof(struct pt_regs, sdei_ttbr1));
   DEFINE(S_PMR_SAVE,		offsetof(struct pt_regs, pmr_save));
   DEFINE(S_STACKFRAME,		offsetof(struct pt_regs, stackframe));
-  DEFINE(S_FRAME_SIZE,		sizeof(struct pt_regs));
+  DEFINE(PT_REGS_SIZE,		sizeof(struct pt_regs));
   BLANK();
 #ifdef CONFIG_COMPAT
   DEFINE(COMPAT_SIGFRAME_REGS_OFFSET,		offsetof(struct compat_sigframe, uc.uc_mcontext.arm_r0));
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
index a338f40e64d3..b3e4f9a088b1 100644
--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -35,7 +35,7 @@
  */
 	.macro  ftrace_regs_entry, allregs=0
 	/* Make room for pt_regs, plus a callee frame */
-	sub	sp, sp, #(S_FRAME_SIZE + 16)
+	sub	sp, sp, #(PT_REGS_SIZE + 16)
 
 	/* Save function arguments (and x9 for simplicity) */
 	stp	x0, x1, [sp, #S_X0]
@@ -61,15 +61,15 @@
 	.endif
 
 	/* Save the callsite's SP and LR */
-	add	x10, sp, #(S_FRAME_SIZE + 16)
+	add	x10, sp, #(PT_REGS_SIZE + 16)
 	stp	x9, x10, [sp, #S_LR]
 
 	/* Save the PC after the ftrace callsite */
 	str	x30, [sp, #S_PC]
 
 	/* Create a frame record for the callsite above pt_regs */
-	stp	x29, x9, [sp, #S_FRAME_SIZE]
-	add	x29, sp, #S_FRAME_SIZE
+	stp	x29, x9, [sp, #PT_REGS_SIZE]
+	add	x29, sp, #PT_REGS_SIZE
 
 	/* Create our frame record within pt_regs. */
 	stp	x29, x30, [sp, #S_STACKFRAME]
@@ -120,7 +120,7 @@ ftrace_common_return:
 	ldr	x9, [sp, #S_PC]
 
 	/* Restore the callsite's SP */
-	add	sp, sp, #S_FRAME_SIZE + 16
+	add	sp, sp, #PT_REGS_SIZE + 16
 
 	ret	x9
 SYM_CODE_END(ftrace_common)
@@ -130,7 +130,7 @@ SYM_CODE_START(ftrace_graph_caller)
 	ldr	x0, [sp, #S_PC]
 	sub	x0, x0, #AARCH64_INSN_SIZE	// ip (callsite's BL insn)
 	add	x1, sp, #S_LR			// parent_ip (callsite's LR)
-	ldr	x2, [sp, #S_FRAME_SIZE]	   	// parent fp (callsite's FP)
+	ldr	x2, [sp, #PT_REGS_SIZE]	   	// parent fp (callsite's FP)
 	bl	prepare_ftrace_return
 	b	ftrace_common_return
 SYM_CODE_END(ftrace_graph_caller)
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index a8c3e7aaca74..c9bae73f2621 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -75,7 +75,7 @@ alternative_else_nop_endif
 	.endif
 #endif
 
-	sub	sp, sp, #S_FRAME_SIZE
+	sub	sp, sp, #PT_REGS_SIZE
 #ifdef CONFIG_VMAP_STACK
 	/*
 	 * Test whether the SP has overflowed, without corrupting a GPR.
@@ -96,7 +96,7 @@ alternative_else_nop_endif
 	 * userspace, and can clobber EL0 registers to free up GPRs.
 	 */
 
-	/* Stash the original SP (minus S_FRAME_SIZE) in tpidr_el0. */
+	/* Stash the original SP (minus PT_REGS_SIZE) in tpidr_el0. */
 	msr	tpidr_el0, x0
 
 	/* Recover the original x0 value and stash it in tpidrro_el0 */
@@ -253,7 +253,7 @@ alternative_else_nop_endif
 
 	scs_load tsk, x20
 	.else
-	add	x21, sp, #S_FRAME_SIZE
+	add	x21, sp, #PT_REGS_SIZE
 	get_current_task tsk
 	.endif /* \el == 0 */
 	mrs	x22, elr_el1
@@ -377,7 +377,7 @@ alternative_else_nop_endif
 	ldp	x26, x27, [sp, #16 * 13]
 	ldp	x28, x29, [sp, #16 * 14]
 	ldr	lr, [sp, #S_LR]
-	add	sp, sp, #S_FRAME_SIZE		// restore sp
+	add	sp, sp, #PT_REGS_SIZE		// restore sp
 
 	.if	\el == 0
 alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0
@@ -580,12 +580,12 @@ __bad_stack:
 
 	/*
 	 * Store the original GPRs to the new stack. The orginal SP (minus
-	 * S_FRAME_SIZE) was stashed in tpidr_el0 by kernel_ventry.
+	 * PT_REGS_SIZE) was stashed in tpidr_el0 by kernel_ventry.
 	 */
-	sub	sp, sp, #S_FRAME_SIZE
+	sub	sp, sp, #PT_REGS_SIZE
 	kernel_entry 1
 	mrs	x0, tpidr_el0
-	add	x0, x0, #S_FRAME_SIZE
+	add	x0, x0, #PT_REGS_SIZE
 	str	x0, [sp, #S_SP]
 
 	/* Stash the regs for handle_bad_stack */
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 38bb07eff872..3605f77ad4df 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -23,8 +23,6 @@
 #include <linux/platform_device.h>
 #include <linux/sched_clock.h>
 #include <linux/smp.h>
-#include <linux/nmi.h>
-#include <linux/cpufreq.h>
 
 /* ARMv8 Cortex-A53 specific event types. */
 #define ARMV8_A53_PERFCTR_PREF_LINEFILL				0xC2
@@ -1250,21 +1248,10 @@ static struct platform_driver armv8_pmu_driver = {
 
 static int __init armv8_pmu_driver_init(void)
 {
-	int ret;
-
 	if (acpi_disabled)
-		ret = platform_driver_register(&armv8_pmu_driver);
+		return platform_driver_register(&armv8_pmu_driver);
 	else
-		ret = arm_pmu_acpi_probe(armv8_pmuv3_init);
-
-	/*
-	 * Try to re-initialize lockup detector after PMU init in
-	 * case PMU events are triggered via NMIs.
-	 */
-	if (ret == 0 && arm_pmu_irq_is_nmi())
-		lockup_detector_init();
-
-	return ret;
+		return arm_pmu_acpi_probe(armv8_pmuv3_init);
 }
 device_initcall(armv8_pmu_driver_init)
 
@@ -1322,27 +1309,3 @@ void arch_perf_update_userpage(struct perf_event *event,
 	userpg->cap_user_time_zero = 1;
 	userpg->cap_user_time_short = 1;
 }
-
-#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF
-/*
- * Safe maximum CPU frequency in case a particular platform doesn't implement
- * cpufreq driver. Although, architecture doesn't put any restrictions on
- * maximum frequency but 5 GHz seems to be safe maximum given the available
- * Arm CPUs in the market which are clocked much less than 5 GHz. On the other
- * hand, we can't make it much higher as it would lead to a large hard-lockup
- * detection timeout on parts which are running slower (eg. 1GHz on
- * Developerbox) and doesn't possess a cpufreq driver.
- */
-#define SAFE_MAX_CPU_FREQ	5000000000UL // 5 GHz
-u64 hw_nmi_get_sample_period(int watchdog_thresh)
-{
-	unsigned int cpu = smp_processor_id();
-	unsigned long max_cpu_freq;
-
-	max_cpu_freq = cpufreq_get_hw_max_freq(cpu) * 1000UL;
-	if (!max_cpu_freq)
-		max_cpu_freq = SAFE_MAX_CPU_FREQ;
-
-	return (u64)max_cpu_freq * watchdog_thresh;
-}
-#endif
diff --git a/arch/arm64/kernel/probes/kprobes_trampoline.S b/arch/arm64/kernel/probes/kprobes_trampoline.S
index 890ca72c5a51..288a84e253cc 100644
--- a/arch/arm64/kernel/probes/kprobes_trampoline.S
+++ b/arch/arm64/kernel/probes/kprobes_trampoline.S
@@ -25,7 +25,7 @@
 	stp x24, x25, [sp, #S_X24]
 	stp x26, x27, [sp, #S_X26]
 	stp x28, x29, [sp, #S_X28]
-	add x0, sp, #S_FRAME_SIZE
+	add x0, sp, #PT_REGS_SIZE
 	stp lr, x0, [sp, #S_LR]
 	/*
 	 * Construct a useful saved PSTATE
@@ -62,7 +62,7 @@
 	.endm
 
 SYM_CODE_START(kretprobe_trampoline)
-	sub sp, sp, #S_FRAME_SIZE
+	sub sp, sp, #PT_REGS_SIZE
 
 	save_all_base_regs
 
@@ -76,7 +76,7 @@ SYM_CODE_START(kretprobe_trampoline)
 
 	restore_all_base_regs
 
-	add sp, sp, #S_FRAME_SIZE
+	add sp, sp, #PT_REGS_SIZE
 	ret
 
 SYM_CODE_END(kretprobe_trampoline)
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index f71d6ce4673f..6237486ff6bb 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -914,13 +914,6 @@ static void do_signal(struct pt_regs *regs)
 asmlinkage void do_notify_resume(struct pt_regs *regs,
 				 unsigned long thread_flags)
 {
-	/*
-	 * The assembly code enters us with IRQs off, but it hasn't
-	 * informed the tracing code of that for efficiency reasons.
-	 * Update the trace code with the current status.
-	 */
-	trace_hardirqs_off();
-
 	do {
 		if (thread_flags & _TIF_NEED_RESCHED) {
 			/* Unmask Debug and SError for the next task */
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index f61e9d8cc55a..c2877c332f2d 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -9,6 +9,7 @@
 
 #include <asm/daifflags.h>
 #include <asm/debug-monitors.h>
+#include <asm/exception.h>
 #include <asm/fpsimd.h>
 #include <asm/syscall.h>
 #include <asm/thread_info.h>
@@ -165,15 +166,8 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 	if (!has_syscall_work(flags) && !IS_ENABLED(CONFIG_DEBUG_RSEQ)) {
 		local_daif_mask();
 		flags = current_thread_info()->flags;
-		if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP)) {
-			/*
-			 * We're off to userspace, where interrupts are
-			 * always enabled after we restore the flags from
-			 * the SPSR.
-			 */
-			trace_hardirqs_on();
+		if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP))
 			return;
-		}
 		local_daif_restore(DAIF_PROCCTX);
 	}
 
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 7deddf56f7c3..709d98fea90c 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -53,13 +53,13 @@ s64 memstart_addr __ro_after_init = -1;
 EXPORT_SYMBOL(memstart_addr);
 
 /*
- * We create both ZONE_DMA and ZONE_DMA32. ZONE_DMA covers the first 1G of
- * memory as some devices, namely the Raspberry Pi 4, have peripherals with
- * this limited view of the memory. ZONE_DMA32 will cover the rest of the 32
- * bit addressable memory area.
+ * If the corresponding config options are enabled, we create both ZONE_DMA
+ * and ZONE_DMA32. By default ZONE_DMA covers the 32-bit addressable memory
+ * unless restricted on specific platforms (e.g. 30-bit on Raspberry Pi 4).
+ * In such case, ZONE_DMA32 covers the rest of the 32-bit addressable memory,
+ * otherwise it is empty.
  */
 phys_addr_t arm64_dma_phys_limit __ro_after_init;
-phys_addr_t arm64_dma32_phys_limit __ro_after_init;
 
 #ifdef CONFIG_KEXEC_CORE
 /*
@@ -84,7 +84,7 @@ static void __init reserve_crashkernel(void)
 
 	if (crash_base == 0) {
 		/* Current arm64 boot protocol requires 2MB alignment */
-		crash_base = memblock_find_in_range(0, arm64_dma32_phys_limit,
+		crash_base = memblock_find_in_range(0, arm64_dma_phys_limit,
 				crash_size, SZ_2M);
 		if (crash_base == 0) {
 			pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
@@ -196,6 +196,7 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 	unsigned long max_zone_pfns[MAX_NR_ZONES]  = {0};
 	unsigned int __maybe_unused acpi_zone_dma_bits;
 	unsigned int __maybe_unused dt_zone_dma_bits;
+	phys_addr_t __maybe_unused dma32_phys_limit = max_zone_phys(32);
 
 #ifdef CONFIG_ZONE_DMA
 	acpi_zone_dma_bits = fls64(acpi_iort_dma_get_max_cpu_address());
@@ -205,8 +206,12 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 	max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit);
 #endif
 #ifdef CONFIG_ZONE_DMA32
-	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(arm64_dma32_phys_limit);
+	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(dma32_phys_limit);
+	if (!arm64_dma_phys_limit)
+		arm64_dma_phys_limit = dma32_phys_limit;
 #endif
+	if (!arm64_dma_phys_limit)
+		arm64_dma_phys_limit = PHYS_MASK + 1;
 	max_zone_pfns[ZONE_NORMAL] = max;
 
 	free_area_init(max_zone_pfns);
@@ -394,16 +399,9 @@ void __init arm64_memblock_init(void)
 
 	early_init_fdt_scan_reserved_mem();
 
-	if (IS_ENABLED(CONFIG_ZONE_DMA32))
-		arm64_dma32_phys_limit = max_zone_phys(32);
-	else
-		arm64_dma32_phys_limit = PHYS_MASK + 1;
-
 	reserve_elfcorehdr();
 
 	high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
-
-	dma_contiguous_reserve(arm64_dma32_phys_limit);
 }
 
 void __init bootmem_init(void)
@@ -439,6 +437,11 @@ void __init bootmem_init(void)
 	zone_sizes_init(min, max);
 
 	/*
+	 * Reserve the CMA area after arm64_dma_phys_limit was initialised.
+	 */
+	dma_contiguous_reserve(arm64_dma_phys_limit);
+
+	/*
 	 * request_standard_resources() depends on crashkernel's memory being
 	 * reserved, so do it here.
 	 */
@@ -455,7 +458,7 @@ void __init bootmem_init(void)
 void __init mem_init(void)
 {
 	if (swiotlb_force == SWIOTLB_FORCE ||
-	    max_pfn > PFN_DOWN(arm64_dma_phys_limit ? : arm64_dma32_phys_limit))
+	    max_pfn > PFN_DOWN(arm64_dma_phys_limit))
 		swiotlb_init(1);
 	else
 		swiotlb_force = SWIOTLB_NO_FORCE;
diff --git a/arch/ia64/include/asm/sparsemem.h b/arch/ia64/include/asm/sparsemem.h
index dd8c166ffd7b..42ed5248fae9 100644
--- a/arch/ia64/include/asm/sparsemem.h
+++ b/arch/ia64/include/asm/sparsemem.h
@@ -3,6 +3,7 @@
 #define _ASM_IA64_SPARSEMEM_H
 
 #ifdef CONFIG_SPARSEMEM
+#include <asm/page.h>
 /*
  * SECTION_SIZE_BITS            2^N: how big each section will be
  * MAX_PHYSMEM_BITS             2^N: how much memory we can have in that space
diff --git a/arch/mips/boot/compressed/decompress.c b/arch/mips/boot/compressed/decompress.c
index c61c641674e6..e3946b06e840 100644
--- a/arch/mips/boot/compressed/decompress.c
+++ b/arch/mips/boot/compressed/decompress.c
@@ -13,6 +13,7 @@
 #include <linux/libfdt.h>
 
 #include <asm/addrspace.h>
+#include <asm/unaligned.h>
 
 /*
  * These two variables specify the free mem region
@@ -117,7 +118,7 @@ void decompress_kernel(unsigned long boot_heap_start)
 		dtb_size = fdt_totalsize((void *)&__appended_dtb);
 
 		/* last four bytes is always image size in little endian */
-		image_size = le32_to_cpup((void *)&__image_end - 4);
+		image_size = get_unaligned_le32((void *)&__image_end - 4);
 
 		/* copy dtb to where the booted kernel will expect it */
 		memcpy((void *)VMLINUX_LOAD_ADDRESS_ULL + image_size,
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index bd47e15d02c7..be5d4afcd30f 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -1444,7 +1444,7 @@ static void octeon_irq_setup_secondary_ciu2(void)
 static int __init octeon_irq_init_ciu(
 	struct device_node *ciu_node, struct device_node *parent)
 {
-	unsigned int i, r;
+	int i, r;
 	struct irq_chip *chip;
 	struct irq_chip *chip_edge;
 	struct irq_chip *chip_mbox;
diff --git a/arch/mips/kernel/binfmt_elfn32.c b/arch/mips/kernel/binfmt_elfn32.c
index 6ee3f7218c67..c4441416e96b 100644
--- a/arch/mips/kernel/binfmt_elfn32.c
+++ b/arch/mips/kernel/binfmt_elfn32.c
@@ -103,4 +103,11 @@ jiffies_to_old_timeval32(unsigned long jiffies, struct old_timeval32 *value)
 #undef ns_to_kernel_old_timeval
 #define ns_to_kernel_old_timeval ns_to_old_timeval32
 
+/*
+ * Some data types as stored in coredump.
+ */
+#define user_long_t             compat_long_t
+#define user_siginfo_t          compat_siginfo_t
+#define copy_siginfo_to_external        copy_siginfo_to_external32
+
 #include "../../../fs/binfmt_elf.c"
diff --git a/arch/mips/kernel/binfmt_elfo32.c b/arch/mips/kernel/binfmt_elfo32.c
index 6dd103d3cebb..7b2a23f48c1a 100644
--- a/arch/mips/kernel/binfmt_elfo32.c
+++ b/arch/mips/kernel/binfmt_elfo32.c
@@ -106,4 +106,11 @@ jiffies_to_old_timeval32(unsigned long jiffies, struct old_timeval32 *value)
 #undef ns_to_kernel_old_timeval
 #define ns_to_kernel_old_timeval ns_to_old_timeval32
 
+/*
+ * Some data types as stored in coredump.
+ */
+#define user_long_t             compat_long_t
+#define user_siginfo_t          compat_siginfo_t
+#define copy_siginfo_to_external        copy_siginfo_to_external32
+
 #include "../../../fs/binfmt_elf.c"
diff --git a/arch/mips/kernel/relocate.c b/arch/mips/kernel/relocate.c
index 47aeb3350a76..0e365b7c742d 100644
--- a/arch/mips/kernel/relocate.c
+++ b/arch/mips/kernel/relocate.c
@@ -187,8 +187,14 @@ static int __init relocate_exception_table(long offset)
 static inline __init unsigned long rotate_xor(unsigned long hash,
 					      const void *area, size_t size)
 {
-	size_t i;
-	unsigned long *ptr = (unsigned long *)area;
+	const typeof(hash) *ptr = PTR_ALIGN(area, sizeof(hash));
+	size_t diff, i;
+
+	diff = (void *)ptr - area;
+	if (unlikely(size < diff + sizeof(hash)))
+		return hash;
+
+	size = ALIGN_DOWN(size - diff, sizeof(hash));
 
 	for (i = 0; i < size / sizeof(hash); i++) {
 		/* Rotate by odd number of bits and XOR. */
diff --git a/arch/powerpc/include/asm/vdso/gettimeofday.h b/arch/powerpc/include/asm/vdso/gettimeofday.h
index 81671aa365b3..77c635c2c90d 100644
--- a/arch/powerpc/include/asm/vdso/gettimeofday.h
+++ b/arch/powerpc/include/asm/vdso/gettimeofday.h
@@ -103,6 +103,8 @@ int gettimeofday_fallback(struct __kernel_old_timeval *_tv, struct timezone *_tz
 	return do_syscall_2(__NR_gettimeofday, (unsigned long)_tv, (unsigned long)_tz);
 }
 
+#ifdef __powerpc64__
+
 static __always_inline
 int clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
 {
@@ -115,11 +117,23 @@ int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
 	return do_syscall_2(__NR_clock_getres, _clkid, (unsigned long)_ts);
 }
 
-#ifdef CONFIG_VDSO32
+#else
 
 #define BUILD_VDSO32		1
 
 static __always_inline
+int clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+	return do_syscall_2(__NR_clock_gettime64, _clkid, (unsigned long)_ts);
+}
+
+static __always_inline
+int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+	return do_syscall_2(__NR_clock_getres_time64, _clkid, (unsigned long)_ts);
+}
+
+static __always_inline
 int clock_gettime32_fallback(clockid_t _clkid, struct old_timespec32 *_ts)
 {
 	return do_syscall_2(__NR_clock_gettime, _clkid, (unsigned long)_ts);
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 8e0b1298bf19..4ab426b8b0e0 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -187,6 +187,12 @@ SECTIONS
 	.init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
 		_sinittext = .;
 		INIT_TEXT
+
+		/*
+		 *.init.text might be RO so we must ensure this section ends on
+		 * a page boundary.
+		 */
+		. = ALIGN(PAGE_SIZE);
 		_einittext = .;
 #ifdef CONFIG_PPC64
 		*(.tramp.ftrace.init);
@@ -200,6 +206,8 @@ SECTIONS
 		EXIT_TEXT
 	}
 
+	. = ALIGN(PAGE_SIZE);
+
 	INIT_DATA_SECTION(16)
 
 	. = ALIGN(8);
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 81b76d44725d..e9e2c1f0a690 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -137,7 +137,7 @@ config PA_BITS
 
 config PAGE_OFFSET
 	hex
-	default 0xC0000000 if 32BIT && MAXPHYSMEM_2GB
+	default 0xC0000000 if 32BIT && MAXPHYSMEM_1GB
 	default 0x80000000 if 64BIT && !MMU
 	default 0xffffffff80000000 if 64BIT && MAXPHYSMEM_2GB
 	default 0xffffffe000000000 if 64BIT && MAXPHYSMEM_128GB
@@ -247,10 +247,12 @@ config MODULE_SECTIONS
 
 choice
 	prompt "Maximum Physical Memory"
-	default MAXPHYSMEM_2GB if 32BIT
+	default MAXPHYSMEM_1GB if 32BIT
 	default MAXPHYSMEM_2GB if 64BIT && CMODEL_MEDLOW
 	default MAXPHYSMEM_128GB if 64BIT && CMODEL_MEDANY
 
+	config MAXPHYSMEM_1GB
+		bool "1GiB"
 	config MAXPHYSMEM_2GB
 		bool "2GiB"
 	config MAXPHYSMEM_128GB
diff --git a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts
index 4a2729f5ca3f..24d75a146e02 100644
--- a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts
+++ b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts
@@ -88,7 +88,9 @@
 	phy-mode = "gmii";
 	phy-handle = <&phy0>;
 	phy0: ethernet-phy@0 {
+		compatible = "ethernet-phy-id0007.0771";
 		reg = <0>;
+		reset-gpios = <&gpio 12 GPIO_ACTIVE_LOW>;
 	};
 };
 
diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig
index d222d353d86d..8c3d1e451703 100644
--- a/arch/riscv/configs/defconfig
+++ b/arch/riscv/configs/defconfig
@@ -64,6 +64,8 @@ CONFIG_HW_RANDOM=y
 CONFIG_HW_RANDOM_VIRTIO=y
 CONFIG_SPI=y
 CONFIG_SPI_SIFIVE=y
+CONFIG_GPIOLIB=y
+CONFIG_GPIO_SIFIVE=y
 # CONFIG_PTP_1588_CLOCK is not set
 CONFIG_POWER_RESET=y
 CONFIG_DRM=y
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 41a72861987c..251e1db088fa 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -99,7 +99,6 @@
 				| _PAGE_DIRTY)
 
 #define PAGE_KERNEL		__pgprot(_PAGE_KERNEL)
-#define PAGE_KERNEL_EXEC	__pgprot(_PAGE_KERNEL | _PAGE_EXEC)
 #define PAGE_KERNEL_READ	__pgprot(_PAGE_KERNEL & ~_PAGE_WRITE)
 #define PAGE_KERNEL_EXEC	__pgprot(_PAGE_KERNEL | _PAGE_EXEC)
 #define PAGE_KERNEL_READ_EXEC	__pgprot((_PAGE_KERNEL & ~_PAGE_WRITE) \
diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h
index 8454f746bbfd..1453a2f563bc 100644
--- a/arch/riscv/include/asm/vdso.h
+++ b/arch/riscv/include/asm/vdso.h
@@ -10,7 +10,7 @@
 
 #include <linux/types.h>
 
-#ifndef GENERIC_TIME_VSYSCALL
+#ifndef CONFIG_GENERIC_TIME_VSYSCALL
 struct vdso_data {
 };
 #endif
diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c
index de59dd457b41..d86781357044 100644
--- a/arch/riscv/kernel/cacheinfo.c
+++ b/arch/riscv/kernel/cacheinfo.c
@@ -26,7 +26,16 @@ cache_get_priv_group(struct cacheinfo *this_leaf)
 
 static struct cacheinfo *get_cacheinfo(u32 level, enum cache_type type)
 {
-	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(smp_processor_id());
+	/*
+	 * Using raw_smp_processor_id() elides a preemptability check, but this
+	 * is really indicative of a larger problem: the cacheinfo UABI assumes
+	 * that cores have a homonogenous view of the cache hierarchy.  That
+	 * happens to be the case for the current set of RISC-V systems, but
+	 * likely won't be true in general.  Since there's no way to provide
+	 * correct information for these systems via the current UABI we're
+	 * just eliding the check for now.
+	 */
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(raw_smp_processor_id());
 	struct cacheinfo *this_leaf;
 	int index;
 
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 524d918f3601..744f3209c48d 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -124,15 +124,15 @@ skip_context_tracking:
 	REG_L a1, (a1)
 	jr a1
 1:
-#ifdef CONFIG_TRACE_IRQFLAGS
-	call trace_hardirqs_on
-#endif
 	/*
 	 * Exceptions run with interrupts enabled or disabled depending on the
 	 * state of SR_PIE in m/sstatus.
 	 */
 	andi t0, s1, SR_PIE
 	beqz t0, 1f
+#ifdef CONFIG_TRACE_IRQFLAGS
+	call trace_hardirqs_on
+#endif
 	csrs CSR_STATUS, SR_IE
 
 1:
@@ -155,6 +155,15 @@ skip_context_tracking:
 	tail do_trap_unknown
 
 handle_syscall:
+#ifdef CONFIG_RISCV_M_MODE
+	/*
+	 * When running is M-Mode (no MMU config), MPIE does not get set.
+	 * As a result, we need to force enable interrupts here because
+	 * handle_exception did not do set SR_IE as it always sees SR_PIE
+	 * being cleared.
+	 */
+	csrs CSR_STATUS, SR_IE
+#endif
 #if defined(CONFIG_TRACE_IRQFLAGS) || defined(CONFIG_CONTEXT_TRACKING)
 	/* Recover a0 - a7 for system calls */
 	REG_L a0, PT_A0(sp)
@@ -186,14 +195,7 @@ check_syscall_nr:
 	 * Syscall number held in a7.
 	 * If syscall number is above allowed value, redirect to ni_syscall.
 	 */
-	bge a7, t0, 1f
-	/*
-	 * Check if syscall is rejected by tracer, i.e., a7 == -1.
-	 * If yes, we pretend it was executed.
-	 */
-	li t1, -1
-	beq a7, t1, ret_from_syscall_rejected
-	blt a7, t1, 1f
+	bgeu a7, t0, 1f
 	/* Call syscall */
 	la s0, sys_call_table
 	slli t0, a7, RISCV_LGPTR
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 1d85e9bf783c..3fa3f26dde85 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -127,7 +127,9 @@ static void __init init_resources(void)
 {
 	struct memblock_region *region = NULL;
 	struct resource *res = NULL;
-	int ret = 0;
+	struct resource *mem_res = NULL;
+	size_t mem_res_sz = 0;
+	int ret = 0, i = 0;
 
 	code_res.start = __pa_symbol(_text);
 	code_res.end = __pa_symbol(_etext) - 1;
@@ -145,16 +147,17 @@ static void __init init_resources(void)
 	bss_res.end = __pa_symbol(__bss_stop) - 1;
 	bss_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
 
+	mem_res_sz = (memblock.memory.cnt + memblock.reserved.cnt) * sizeof(*mem_res);
+	mem_res = memblock_alloc(mem_res_sz, SMP_CACHE_BYTES);
+	if (!mem_res)
+		panic("%s: Failed to allocate %zu bytes\n", __func__, mem_res_sz);
 	/*
 	 * Start by adding the reserved regions, if they overlap
 	 * with /memory regions, insert_resource later on will take
 	 * care of it.
 	 */
 	for_each_reserved_mem_region(region) {
-		res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES);
-		if (!res)
-			panic("%s: Failed to allocate %zu bytes\n", __func__,
-			      sizeof(struct resource));
+		res = &mem_res[i++];
 
 		res->name = "Reserved";
 		res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
@@ -171,8 +174,10 @@ static void __init init_resources(void)
 		 * Ignore any other reserved regions within
 		 * system memory.
 		 */
-		if (memblock_is_memory(res->start))
+		if (memblock_is_memory(res->start)) {
+			memblock_free((phys_addr_t) res, sizeof(struct resource));
 			continue;
+		}
 
 		ret = add_resource(&iomem_resource, res);
 		if (ret < 0)
@@ -181,10 +186,7 @@ static void __init init_resources(void)
 
 	/* Add /memory regions to the resource tree */
 	for_each_mem_region(region) {
-		res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES);
-		if (!res)
-			panic("%s: Failed to allocate %zu bytes\n", __func__,
-			      sizeof(struct resource));
+		res = &mem_res[i++];
 
 		if (unlikely(memblock_is_nomap(region))) {
 			res->name = "Reserved";
@@ -205,9 +207,9 @@ static void __init init_resources(void)
 	return;
 
  error:
-	memblock_free((phys_addr_t) res, sizeof(struct resource));
 	/* Better an empty resource tree than an inconsistent one */
 	release_child_resources(&iomem_resource);
+	memblock_free((phys_addr_t) mem_res, mem_res_sz);
 }
 
 
diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c
index 48b870a685b3..df5d2da7c40b 100644
--- a/arch/riscv/kernel/stacktrace.c
+++ b/arch/riscv/kernel/stacktrace.c
@@ -14,7 +14,7 @@
 
 #include <asm/stacktrace.h>
 
-register unsigned long sp_in_global __asm__("sp");
+register const unsigned long sp_in_global __asm__("sp");
 
 #ifdef CONFIG_FRAME_POINTER
 
@@ -28,9 +28,8 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs,
 		sp = user_stack_pointer(regs);
 		pc = instruction_pointer(regs);
 	} else if (task == NULL || task == current) {
-		const register unsigned long current_sp = sp_in_global;
 		fp = (unsigned long)__builtin_frame_address(0);
-		sp = current_sp;
+		sp = sp_in_global;
 		pc = (unsigned long)walk_stackframe;
 	} else {
 		/* task blocked in __switch_to */
diff --git a/arch/riscv/kernel/time.c b/arch/riscv/kernel/time.c
index 4d3a1048ad8b..8a5cf99c0776 100644
--- a/arch/riscv/kernel/time.c
+++ b/arch/riscv/kernel/time.c
@@ -4,6 +4,7 @@
  * Copyright (C) 2017 SiFive
  */
 
+#include <linux/of_clk.h>
 #include <linux/clocksource.h>
 #include <linux/delay.h>
 #include <asm/sbi.h>
@@ -24,6 +25,8 @@ void __init time_init(void)
 	riscv_timebase = prop;
 
 	lpj_fine = riscv_timebase / HZ;
+
+	of_clk_init(NULL);
 	timer_probe();
 }
 
diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c
index 678204231700..3f1d35e7c98a 100644
--- a/arch/riscv/kernel/vdso.c
+++ b/arch/riscv/kernel/vdso.c
@@ -12,7 +12,7 @@
 #include <linux/binfmts.h>
 #include <linux/err.h>
 #include <asm/page.h>
-#ifdef GENERIC_TIME_VSYSCALL
+#ifdef CONFIG_GENERIC_TIME_VSYSCALL
 #include <vdso/datapage.h>
 #else
 #include <asm/vdso.h>
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index bf5379135e39..7cd4993f4ff2 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -157,9 +157,10 @@ disable:
 void __init setup_bootmem(void)
 {
 	phys_addr_t mem_start = 0;
-	phys_addr_t start, end = 0;
+	phys_addr_t start, dram_end, end = 0;
 	phys_addr_t vmlinux_end = __pa_symbol(&_end);
 	phys_addr_t vmlinux_start = __pa_symbol(&_start);
+	phys_addr_t max_mapped_addr = __pa(~(ulong)0);
 	u64 i;
 
 	/* Find the memory region containing the kernel */
@@ -181,7 +182,18 @@ void __init setup_bootmem(void)
 	/* Reserve from the start of the kernel to the end of the kernel */
 	memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start);
 
-	max_pfn = PFN_DOWN(memblock_end_of_DRAM());
+	dram_end = memblock_end_of_DRAM();
+
+	/*
+	 * memblock allocator is not aware of the fact that last 4K bytes of
+	 * the addressable memory can not be mapped because of IS_ERR_VALUE
+	 * macro. Make sure that last 4k bytes are not usable by memblock
+	 * if end of dram is equal to maximum addressable memory.
+	 */
+	if (max_mapped_addr == (dram_end - 1))
+		memblock_set_current_limit(max_mapped_addr - 4096);
+
+	max_pfn = PFN_DOWN(dram_end);
 	max_low_pfn = max_pfn;
 	dma32_phys_limit = min(4UL * SZ_1G, (unsigned long)PFN_PHYS(max_low_pfn));
 	set_max_mapnr(max_low_pfn);
diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c
index 12ddd1f6bf70..a8a2ffd9114a 100644
--- a/arch/riscv/mm/kasan_init.c
+++ b/arch/riscv/mm/kasan_init.c
@@ -93,8 +93,8 @@ void __init kasan_init(void)
 								VMALLOC_END));
 
 	for_each_mem_range(i, &_start, &_end) {
-		void *start = (void *)_start;
-		void *end = (void *)_end;
+		void *start = (void *)__va(_start);
+		void *end = (void *)__va(_end);
 
 		if (start >= end)
 			break;
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 4638a52d8eae..6375967a8244 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -315,6 +315,25 @@ static struct syscore_ops hv_syscore_ops = {
 	.resume		= hv_resume,
 };
 
+static void (* __initdata old_setup_percpu_clockev)(void);
+
+static void __init hv_stimer_setup_percpu_clockev(void)
+{
+	/*
+	 * Ignore any errors in setting up stimer clockevents
+	 * as we can run with the LAPIC timer as a fallback.
+	 */
+	(void)hv_stimer_alloc();
+
+	/*
+	 * Still register the LAPIC timer, because the direct-mode STIMER is
+	 * not supported by old versions of Hyper-V. This also allows users
+	 * to switch to LAPIC timer via /sys, if they want to.
+	 */
+	if (old_setup_percpu_clockev)
+		old_setup_percpu_clockev();
+}
+
 /*
  * This function is to be invoked early in the boot sequence after the
  * hypervisor has been detected.
@@ -393,10 +412,14 @@ void __init hyperv_init(void)
 	wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
 
 	/*
-	 * Ignore any errors in setting up stimer clockevents
-	 * as we can run with the LAPIC timer as a fallback.
+	 * hyperv_init() is called before LAPIC is initialized: see
+	 * apic_intr_mode_init() -> x86_platform.apic_post_init() and
+	 * apic_bsp_setup() -> setup_local_APIC(). The direct-mode STIMER
+	 * depends on LAPIC, so hv_stimer_alloc() should be called from
+	 * x86_init.timers.setup_percpu_clockev.
 	 */
-	(void)hv_stimer_alloc();
+	old_setup_percpu_clockev = x86_init.timers.setup_percpu_clockev;
+	x86_init.timers.setup_percpu_clockev = hv_stimer_setup_percpu_clockev;
 
 	hv_apic_init();
 
diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c
index 9e87ab010c82..e68ea5f4ad1c 100644
--- a/arch/x86/xen/enlighten_hvm.c
+++ b/arch/x86/xen/enlighten_hvm.c
@@ -164,10 +164,10 @@ static int xen_cpu_up_prepare_hvm(unsigned int cpu)
 	else
 		per_cpu(xen_vcpu_id, cpu) = cpu;
 	rc = xen_vcpu_setup(cpu);
-	if (rc)
+	if (rc || !xen_have_vector_callback)
 		return rc;
 
-	if (xen_have_vector_callback && xen_feature(XENFEAT_hvm_safe_pvclock))
+	if (xen_feature(XENFEAT_hvm_safe_pvclock))
 		xen_setup_timer(cpu);
 
 	rc = xen_smp_intr_init(cpu);
@@ -188,6 +188,8 @@ static int xen_cpu_dead_hvm(unsigned int cpu)
        return 0;
 }
 
+static bool no_vector_callback __initdata;
+
 static void __init xen_hvm_guest_init(void)
 {
 	if (xen_pv_domain())
@@ -207,7 +209,7 @@ static void __init xen_hvm_guest_init(void)
 
 	xen_panic_handler_init();
 
-	if (xen_feature(XENFEAT_hvm_callback_vector))
+	if (!no_vector_callback && xen_feature(XENFEAT_hvm_callback_vector))
 		xen_have_vector_callback = 1;
 
 	xen_hvm_smp_init();
@@ -233,6 +235,13 @@ static __init int xen_parse_nopv(char *arg)
 }
 early_param("xen_nopv", xen_parse_nopv);
 
+static __init int xen_parse_no_vector_callback(char *arg)
+{
+	no_vector_callback = true;
+	return 0;
+}
+early_param("xen_no_vector_callback", xen_parse_no_vector_callback);
+
 bool __init xen_hvm_need_lapic(void)
 {
 	if (xen_pv_domain())
diff --git a/arch/x86/xen/smp_hvm.c b/arch/x86/xen/smp_hvm.c
index f5e7db4f82ab..6ff3c887e0b9 100644
--- a/arch/x86/xen/smp_hvm.c
+++ b/arch/x86/xen/smp_hvm.c
@@ -33,9 +33,11 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus)
 	int cpu;
 
 	native_smp_prepare_cpus(max_cpus);
-	WARN_ON(xen_smp_intr_init(0));
 
-	xen_init_lock_cpu(0);
+	if (xen_have_vector_callback) {
+		WARN_ON(xen_smp_intr_init(0));
+		xen_init_lock_cpu(0);
+	}
 
 	for_each_possible_cpu(cpu) {
 		if (cpu == 0)
@@ -50,9 +52,11 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus)
 static void xen_hvm_cpu_die(unsigned int cpu)
 {
 	if (common_cpu_die(cpu) == 0) {
-		xen_smp_intr_free(cpu);
-		xen_uninit_lock_cpu(cpu);
-		xen_teardown_timer(cpu);
+		if (xen_have_vector_callback) {
+			xen_smp_intr_free(cpu);
+			xen_uninit_lock_cpu(cpu);
+			xen_teardown_timer(cpu);
+		}
 	}
 }
 #else
@@ -64,14 +68,19 @@ static void xen_hvm_cpu_die(unsigned int cpu)
 
 void __init xen_hvm_smp_init(void)
 {
-	if (!xen_have_vector_callback)
+	smp_ops.smp_prepare_boot_cpu = xen_hvm_smp_prepare_boot_cpu;
+	smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus;
+	smp_ops.smp_cpus_done = xen_smp_cpus_done;
+	smp_ops.cpu_die = xen_hvm_cpu_die;
+
+	if (!xen_have_vector_callback) {
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+		nopvspin = true;
+#endif
 		return;
+	}
 
-	smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus;
 	smp_ops.smp_send_reschedule = xen_smp_send_reschedule;
-	smp_ops.cpu_die = xen_hvm_cpu_die;
 	smp_ops.send_call_func_ipi = xen_smp_send_call_function_ipi;
 	smp_ops.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi;
-	smp_ops.smp_prepare_boot_cpu = xen_hvm_smp_prepare_boot_cpu;
-	smp_ops.smp_cpus_done = xen_smp_cpus_done;
 }