1 files changed, 89 insertions, 74 deletions

diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 56f664561754..85104587f849 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -23,12 +23,14 @@
 #include <linux/interrupt.h>
 #include <linux/smp.h>
 #include <linux/fs.h>
+#include <linux/panic_notifier.h>
 #include <linux/proc_fs.h>
 #include <linux/memblock.h>
 #include <linux/of_fdt.h>
 #include <linux/efi.h>
 #include <linux/psci.h>
 #include <linux/sched/task.h>
+#include <linux/scs.h>
 #include <linux/mm.h>
 
 #include <asm/acpi.h>
@@ -41,6 +43,8 @@
 #include <asm/cpu_ops.h>
 #include <asm/kasan.h>
 #include <asm/numa.h>
+#include <asm/rsi.h>
+#include <asm/scs.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
 #include <asm/smp_plat.h>
@@ -55,6 +59,7 @@ static int num_standard_resources;
 static struct resource *standard_resources;
 
 phys_addr_t __fdt_pointer __initdata;
+u64 mmu_enabled_at_boot __initdata;
 
 /*
  * Standard memory resources
@@ -85,14 +90,8 @@ u64 __cacheline_aligned boot_args[4];
 void __init smp_setup_processor_id(void)
 {
 	u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK;
-	cpu_logical_map(0) = mpidr;
+	set_cpu_logical_map(0, mpidr);
 
-	/*
-	 * clear __my_cpu_offset on boot CPU to avoid hang caused by
-	 * using percpu variable early, for example, lockdep will
-	 * access percpu variable inside lock_release
-	 */
-	set_my_cpu_offset(0);
 	pr_info("Booting Linux on physical CPU 0x%010lx [0x%08x]\n",
 		(unsigned long)mpidr, read_cpuid_id());
 }
@@ -177,13 +176,22 @@ static void __init setup_machine_fdt(phys_addr_t dt_phys)
 	if (dt_virt)
 		memblock_reserve(dt_phys, size);
 
-	if (!dt_virt || !early_init_dt_scan(dt_virt)) {
+	/*
+	 * dt_virt is a fixmap address, hence __pa(dt_virt) can't be used.
+	 * Pass dt_phys directly.
+	 */
+	if (!early_init_dt_scan(dt_virt, dt_phys)) {
 		pr_crit("\n"
-			"Error: invalid device tree blob at physical address %pa (virtual address 0x%p)\n"
+			"Error: invalid device tree blob at physical address %pa (virtual address 0x%px)\n"
 			"The dtb must be 8-byte aligned and must not exceed 2 MB in size\n"
 			"\nPlease check your bootloader.",
 			&dt_phys, dt_virt);
 
+		/*
+		 * Note that in this _really_ early stage we cannot even BUG()
+		 * or oops, so the least terrible thing to do is cpu_relax(),
+		 * or else we could end-up printing non-initialized data, etc.
+		 */
 		while (true)
 			cpu_relax();
 	}
@@ -206,43 +214,32 @@ static void __init request_standard_resources(void)
 	unsigned long i = 0;
 	size_t res_size;
 
-	kernel_code.start   = __pa_symbol(_text);
+	kernel_code.start   = __pa_symbol(_stext);
 	kernel_code.end     = __pa_symbol(__init_begin - 1);
 	kernel_data.start   = __pa_symbol(_sdata);
 	kernel_data.end     = __pa_symbol(_end - 1);
+	insert_resource(&iomem_resource, &kernel_code);
+	insert_resource(&iomem_resource, &kernel_data);
 
 	num_standard_resources = memblock.memory.cnt;
 	res_size = num_standard_resources * sizeof(*standard_resources);
-	standard_resources = memblock_alloc(res_size, SMP_CACHE_BYTES);
-	if (!standard_resources)
-		panic("%s: Failed to allocate %zu bytes\n", __func__, res_size);
+	standard_resources = memblock_alloc_or_panic(res_size, SMP_CACHE_BYTES);
 
-	for_each_memblock(memory, region) {
+	for_each_mem_region(region) {
 		res = &standard_resources[i++];
 		if (memblock_is_nomap(region)) {
 			res->name  = "reserved";
 			res->flags = IORESOURCE_MEM;
+			res->start = __pfn_to_phys(memblock_region_reserved_base_pfn(region));
+			res->end = __pfn_to_phys(memblock_region_reserved_end_pfn(region)) - 1;
 		} else {
 			res->name  = "System RAM";
 			res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+			res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region));
+			res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1;
 		}
-		res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region));
-		res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1;
-
-		request_resource(&iomem_resource, res);
-
-		if (kernel_code.start >= res->start &&
-		    kernel_code.end <= res->end)
-			request_resource(res, &kernel_code);
-		if (kernel_data.start >= res->start &&
-		    kernel_data.end <= res->end)
-			request_resource(res, &kernel_data);
-#ifdef CONFIG_KEXEC_CORE
-		/* Userspace will find "Crash kernel" region in /proc/iomem. */
-		if (crashk_res.end && crashk_res.start >= res->start &&
-		    crashk_res.end <= res->end)
-			request_resource(res, &crashk_res);
-#endif
+
+		insert_resource(&iomem_resource, res);
 	}
 }
 
@@ -257,7 +254,7 @@ static int __init reserve_memblock_reserved_regions(void)
 		if (!memblock_is_region_reserved(mem->start, mem_size))
 			continue;
 
-		for_each_reserved_mem_region(j, &r_start, &r_end) {
+		for_each_reserved_mem_range(j, &r_start, &r_end) {
 			resource_size_t start, end;
 
 			start = max(PFN_PHYS(PFN_DOWN(r_start)), mem->start);
@@ -276,15 +273,19 @@ arch_initcall(reserve_memblock_reserved_regions);
 
 u64 __cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = INVALID_HWID };
 
-void __init setup_arch(char **cmdline_p)
+u64 cpu_logical_map(unsigned int cpu)
 {
-	init_mm.start_code = (unsigned long) _text;
-	init_mm.end_code   = (unsigned long) _etext;
-	init_mm.end_data   = (unsigned long) _edata;
-	init_mm.brk	   = (unsigned long) _end;
+	return __cpu_logical_map[cpu];
+}
+
+void __init __no_sanitize_address setup_arch(char **cmdline_p)
+{
+	setup_initial_init_mm(_stext, _etext, _edata, _end);
 
 	*cmdline_p = boot_command_line;
 
+	kaslr_init();
+
 	early_fixmap_init();
 	early_ioremap_init();
 
@@ -297,10 +298,18 @@ void __init setup_arch(char **cmdline_p)
 	jump_label_init();
 	parse_early_param();
 
+	dynamic_scs_init();
+
 	/*
-	 * Unmask asynchronous aborts and fiq after bringing up possible
-	 * earlycon. (Report possible System Errors once we can report this
-	 * occurred).
+	 * The primary CPU enters the kernel with all DAIF exceptions masked.
+	 *
+	 * We must unmask Debug and SError before preemption or scheduling is
+	 * possible to ensure that these are consistently unmasked across
+	 * threads, and we want to unmask SError as soon as possible after
+	 * initializing earlycon so that we can report any SErrors immediately.
+	 *
+	 * IRQ and FIQ will be unmasked after the root irqchip has been
+	 * detected and initialized.
 	 */
 	local_daif_restore(DAIF_PROCCTX_NOIRQ);
 
@@ -312,6 +321,14 @@ void __init setup_arch(char **cmdline_p)
 
 	xen_early_init();
 	efi_init();
+
+	if (!efi_enabled(EFI_BOOT)) {
+		if ((u64)_text % MIN_KIMG_ALIGN)
+			pr_warn(FW_BUG "Kernel image misaligned at boot, please fix your bootloader!");
+		WARN_TAINT(mmu_enabled_at_boot, TAINT_FIRMWARE_WORKAROUND,
+			   FW_BUG "Booted with MMU enabled!");
+	}
+
 	arm64_memblock_init();
 
 	paging_init();
@@ -337,25 +354,21 @@ void __init setup_arch(char **cmdline_p)
 	else
 		psci_acpi_init();
 
-	cpu_read_bootcpu_ops();
+	arm64_rsi_init();
+
+	init_bootcpu_ops();
 	smp_init_cpus();
 	smp_build_mpidr_hash();
 
-	/* Init percpu seeds for random tags after cpus are set up. */
-	kasan_init_tags();
-
 #ifdef CONFIG_ARM64_SW_TTBR0_PAN
 	/*
 	 * Make sure init_thread_info.ttbr0 always generates translation
 	 * faults in case uaccess_enable() is inadvertently called by the init
 	 * thread.
 	 */
-	init_task.thread_info.ttbr0 = __pa_symbol(empty_zero_page);
+	init_task.thread_info.ttbr0 = phys_to_ttbr(__pa_symbol(reserved_pg_dir));
 #endif
 
-#ifdef CONFIG_VT
-	conswitchp = &dummy_con;
-#endif
 	if (boot_args[1] || boot_args[2] || boot_args[3]) {
 		pr_err("WARNING: x1-x3 nonzero in violation of boot protocol:\n"
 			"\tx1: %016llx\n\tx2: %016llx\n\tx3: %016llx\n"
@@ -367,34 +380,20 @@ void __init setup_arch(char **cmdline_p)
 static inline bool cpu_can_disable(unsigned int cpu)
 {
 #ifdef CONFIG_HOTPLUG_CPU
-	if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_can_disable)
-		return cpu_ops[cpu]->cpu_can_disable(cpu);
+	const struct cpu_operations *ops = get_cpu_ops(cpu);
+
+	if (ops && ops->cpu_can_disable)
+		return ops->cpu_can_disable(cpu);
 #endif
 	return false;
 }
 
-static int __init topology_init(void)
+bool arch_cpu_is_hotpluggable(int num)
 {
-	int i;
-
-	for_each_online_node(i)
-		register_one_node(i);
-
-	for_each_possible_cpu(i) {
-		struct cpu *cpu = &per_cpu(cpu_data.cpu, i);
-		cpu->hotpluggable = cpu_can_disable(i);
-		register_cpu(cpu, i);
-	}
-
-	return 0;
+	return cpu_can_disable(num);
 }
-subsys_initcall(topology_init);
 
-/*
- * Dump out kernel offset information on panic.
- */
-static int dump_kernel_offset(struct notifier_block *self, unsigned long v,
-			      void *p)
+static void dump_kernel_offset(void)
 {
 	const unsigned long offset = kaslr_offset();
 
@@ -405,17 +404,33 @@ static int dump_kernel_offset(struct notifier_block *self, unsigned long v,
 	} else {
 		pr_emerg("Kernel Offset: disabled\n");
 	}
+}
+
+static int arm64_panic_block_dump(struct notifier_block *self,
+				  unsigned long v, void *p)
+{
+	dump_kernel_offset();
+	dump_cpu_features();
+	dump_mem_limit();
 	return 0;
 }
 
-static struct notifier_block kernel_offset_notifier = {
-	.notifier_call = dump_kernel_offset
+static struct notifier_block arm64_panic_block = {
+	.notifier_call = arm64_panic_block_dump
 };
 
-static int __init register_kernel_offset_dumper(void)
+static int __init register_arm64_panic_block(void)
 {
 	atomic_notifier_chain_register(&panic_notifier_list,
-				       &kernel_offset_notifier);
+				       &arm64_panic_block);
+	return 0;
+}
+device_initcall(register_arm64_panic_block);
+
+static int __init check_mmu_enabled_at_boot(void)
+{
+	if (!efi_enabled(EFI_BOOT) && mmu_enabled_at_boot)
+		panic("Non-EFI boot detected with MMU and caches enabled");
 	return 0;
 }
-__initcall(register_kernel_offset_dumper);
+device_initcall_sync(check_mmu_enabled_at_boot);