1 files changed, 106 insertions, 55 deletions

diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 90d8cc930f5..78a0e629892 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -82,7 +82,6 @@
 #include <asm/timer.h>
 #include <asm/i8259.h>
 #include <asm/sections.h>
-#include <asm/dmi.h>
 #include <asm/io_apic.h>
 #include <asm/ist.h>
 #include <asm/setup_arch.h>
@@ -171,14 +170,12 @@ static struct resource bss_resource = {
 
 #ifdef CONFIG_X86_32
 /* cpu data as detected by the assembly code in head.S */
-struct cpuinfo_x86 new_cpu_data __cpuinitdata = {
+struct cpuinfo_x86 new_cpu_data = {
 	.wp_works_ok = -1,
-	.fdiv_bug = -1,
 };
 /* common cpu data for all cpus */
 struct cpuinfo_x86 boot_cpu_data __read_mostly = {
 	.wp_works_ok = -1,
-	.fdiv_bug = -1,
 };
 EXPORT_SYMBOL(boot_cpu_data);
 
@@ -209,9 +206,9 @@ EXPORT_SYMBOL(boot_cpu_data);
 
 
 #if !defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64)
-unsigned long mmu_cr4_features;
+__visible unsigned long mmu_cr4_features;
 #else
-unsigned long mmu_cr4_features = X86_CR4_PAE;
+__visible unsigned long mmu_cr4_features = X86_CR4_PAE;
 #endif
 
 /* Boot loader ID and version as integers, for the benefit of proc_dointvec */
@@ -298,6 +295,8 @@ static void __init reserve_brk(void)
 	_brk_start = 0;
 }
 
+u64 relocated_ramdisk;
+
 #ifdef CONFIG_BLK_DEV_INITRD
 
 static u64 __init get_ramdisk_image(void)
@@ -324,25 +323,24 @@ static void __init relocate_initrd(void)
 	u64 ramdisk_image = get_ramdisk_image();
 	u64 ramdisk_size  = get_ramdisk_size();
 	u64 area_size     = PAGE_ALIGN(ramdisk_size);
-	u64 ramdisk_here;
 	unsigned long slop, clen, mapaddr;
 	char *p, *q;
 
 	/* We need to move the initrd down into directly mapped mem */
-	ramdisk_here = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
-						 area_size, PAGE_SIZE);
+	relocated_ramdisk = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
+						   area_size, PAGE_SIZE);
 
-	if (!ramdisk_here)
+	if (!relocated_ramdisk)
 		panic("Cannot find place for new RAMDISK of size %lld\n",
-			 ramdisk_size);
+		      ramdisk_size);
 
 	/* Note: this includes all the mem currently occupied by
 	   the initrd, we rely on that fact to keep the data intact. */
-	memblock_reserve(ramdisk_here, area_size);
-	initrd_start = ramdisk_here + PAGE_OFFSET;
+	memblock_reserve(relocated_ramdisk, area_size);
+	initrd_start = relocated_ramdisk + PAGE_OFFSET;
 	initrd_end   = initrd_start + ramdisk_size;
 	printk(KERN_INFO "Allocated new RAMDISK: [mem %#010llx-%#010llx]\n",
-			 ramdisk_here, ramdisk_here + ramdisk_size - 1);
+	       relocated_ramdisk, relocated_ramdisk + ramdisk_size - 1);
 
 	q = (char *)initrd_start;
 
@@ -366,7 +364,7 @@ static void __init relocate_initrd(void)
 	printk(KERN_INFO "Move RAMDISK from [mem %#010llx-%#010llx] to"
 		" [mem %#010llx-%#010llx]\n",
 		ramdisk_image, ramdisk_image + ramdisk_size - 1,
-		ramdisk_here, ramdisk_here + ramdisk_size - 1);
+		relocated_ramdisk, relocated_ramdisk + ramdisk_size - 1);
 }
 
 static void __init early_reserve_initrd(void)
@@ -429,34 +427,34 @@ static void __init reserve_initrd(void)
 static void __init parse_setup_data(void)
 {
 	struct setup_data *data;
-	u64 pa_data;
+	u64 pa_data, pa_next;
 
 	pa_data = boot_params.hdr.setup_data;
 	while (pa_data) {
-		u32 data_len, map_len;
+		u32 data_len, map_len, data_type;
 
 		map_len = max(PAGE_SIZE - (pa_data & ~PAGE_MASK),
 			      (u64)sizeof(struct setup_data));
 		data = early_memremap(pa_data, map_len);
 		data_len = data->len + sizeof(struct setup_data);
-		if (data_len > map_len) {
-			early_iounmap(data, map_len);
-			data = early_memremap(pa_data, data_len);
-			map_len = data_len;
-		}
+		data_type = data->type;
+		pa_next = data->next;
+		early_iounmap(data, map_len);
 
-		switch (data->type) {
+		switch (data_type) {
 		case SETUP_E820_EXT:
-			parse_e820_ext(data);
+			parse_e820_ext(pa_data, data_len);
 			break;
 		case SETUP_DTB:
 			add_dtb(pa_data);
 			break;
+		case SETUP_EFI:
+			parse_efi_setup(pa_data, data_len);
+			break;
 		default:
 			break;
 		}
-		pa_data = data->next;
-		early_iounmap(data, map_len);
+		pa_data = pa_next;
 	}
 }
 
@@ -507,11 +505,14 @@ static void __init memblock_x86_reserve_range_setup_data(void)
 /*
  * Keep the crash kernel below this limit.  On 32 bits earlier kernels
  * would limit the kernel to the low 512 MiB due to mapping restrictions.
+ * On 64bit, old kexec-tools need to under 896MiB.
  */
 #ifdef CONFIG_X86_32
-# define CRASH_KERNEL_ADDR_MAX	(512 << 20)
+# define CRASH_KERNEL_ADDR_LOW_MAX	(512 << 20)
+# define CRASH_KERNEL_ADDR_HIGH_MAX	(512 << 20)
 #else
-# define CRASH_KERNEL_ADDR_MAX	MAXMEM
+# define CRASH_KERNEL_ADDR_LOW_MAX	(896UL<<20)
+# define CRASH_KERNEL_ADDR_HIGH_MAX	MAXMEM
 #endif
 
 static void __init reserve_crashkernel_low(void)
@@ -521,19 +522,35 @@ static void __init reserve_crashkernel_low(void)
 	unsigned long long low_base = 0, low_size = 0;
 	unsigned long total_low_mem;
 	unsigned long long base;
+	bool auto_set = false;
 	int ret;
 
 	total_low_mem = memblock_mem_size(1UL<<(32-PAGE_SHIFT));
+	/* crashkernel=Y,low */
 	ret = parse_crashkernel_low(boot_command_line, total_low_mem,
 						&low_size, &base);
-	if (ret != 0 || low_size <= 0)
-		return;
+	if (ret != 0) {
+		/*
+		 * two parts from lib/swiotlb.c:
+		 *	swiotlb size: user specified with swiotlb= or default.
+		 *	swiotlb overflow buffer: now is hardcoded to 32k.
+		 *		We round it to 8M for other buffers that
+		 *		may need to stay low too.
+		 */
+		low_size = swiotlb_size_or_default() + (8UL<<20);
+		auto_set = true;
+	} else {
+		/* passed with crashkernel=0,low ? */
+		if (!low_size)
+			return;
+	}
 
 	low_base = memblock_find_in_range(low_size, (1ULL<<32),
 					low_size, alignment);
 
 	if (!low_base) {
-		pr_info("crashkernel low reservation failed - No suitable area found.\n");
+		if (!auto_set)
+			pr_info("crashkernel low reservation failed - No suitable area found.\n");
 
 		return;
 	}
@@ -554,14 +571,22 @@ static void __init reserve_crashkernel(void)
 	const unsigned long long alignment = 16<<20;	/* 16M */
 	unsigned long long total_mem;
 	unsigned long long crash_size, crash_base;
+	bool high = false;
 	int ret;
 
 	total_mem = memblock_phys_mem_size();
 
+	/* crashkernel=XM */
 	ret = parse_crashkernel(boot_command_line, total_mem,
 			&crash_size, &crash_base);
-	if (ret != 0 || crash_size <= 0)
-		return;
+	if (ret != 0 || crash_size <= 0) {
+		/* crashkernel=X,high */
+		ret = parse_crashkernel_high(boot_command_line, total_mem,
+				&crash_size, &crash_base);
+		if (ret != 0 || crash_size <= 0)
+			return;
+		high = true;
+	}
 
 	/* 0 means: find the address automatically */
 	if (crash_base <= 0) {
@@ -569,7 +594,9 @@ static void __init reserve_crashkernel(void)
 		 *  kexec want bzImage is below CRASH_KERNEL_ADDR_MAX
 		 */
 		crash_base = memblock_find_in_range(alignment,
-			       CRASH_KERNEL_ADDR_MAX, crash_size, alignment);
+					high ? CRASH_KERNEL_ADDR_HIGH_MAX :
+					       CRASH_KERNEL_ADDR_LOW_MAX,
+					crash_size, alignment);
 
 		if (!crash_base) {
 			pr_info("crashkernel reservation failed - No suitable area found.\n");
@@ -801,6 +828,20 @@ static void __init trim_low_memory_range(void)
 }
 	
 /*
+ * Dump out kernel offset information on panic.
+ */
+static int
+dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p)
+{
+	pr_emerg("Kernel Offset: 0x%lx from 0x%lx "
+		 "(relocation range: 0x%lx-0x%lx)\n",
+		 (unsigned long)&_text - __START_KERNEL, __START_KERNEL,
+		 __START_KERNEL_map, MODULES_VADDR-1);
+
+	return 0;
+}
+
+/*
  * Determine if we were loaded by an EFI loader.  If so, then we have also been
  * passed the efi memmap, systab, etc., so we should use these data structures
  * for initialization.  Note, the efi init code path is determined by the
@@ -828,7 +869,6 @@ void __init setup_arch(char **cmdline_p)
 
 #ifdef CONFIG_X86_32
 	memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data));
-	visws_early_detect();
 
 	/*
 	 * copy kernel address range established so far and switch
@@ -885,11 +925,11 @@ void __init setup_arch(char **cmdline_p)
 #ifdef CONFIG_EFI
 	if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
 		     "EL32", 4)) {
-		set_bit(EFI_BOOT, &x86_efi_facility);
+		set_bit(EFI_BOOT, &efi.flags);
 	} else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
 		     "EL64", 4)) {
-		set_bit(EFI_BOOT, &x86_efi_facility);
-		set_bit(EFI_64BIT, &x86_efi_facility);
+		set_bit(EFI_BOOT, &efi.flags);
+		set_bit(EFI_64BIT, &efi.flags);
 	}
 
 	if (efi_enabled(EFI_BOOT))
@@ -901,8 +941,6 @@ void __init setup_arch(char **cmdline_p)
 	iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1;
 	setup_memory_map();
 	parse_setup_data();
-	/* update the e820_saved too */
-	e820_reserve_setup_data();
 
 	copy_edd();
 
@@ -964,12 +1002,16 @@ void __init setup_arch(char **cmdline_p)
 		early_dump_pci_devices();
 #endif
 
+	/* update the e820_saved too */
+	e820_reserve_setup_data();
 	finish_e820_parsing();
 
 	if (efi_enabled(EFI_BOOT))
 		efi_init();
 
 	dmi_scan_machine();
+	dmi_memdev_walk();
+	dmi_set_dump_stack_arch_desc();
 
 	/*
 	 * VMware detection requires dmi to be available, so this
@@ -1013,8 +1055,6 @@ void __init setup_arch(char **cmdline_p)
 	/* max_low_pfn get updated here */
 	find_low_pfn_range();
 #else
-	num_physpages = max_pfn;
-
 	check_x2apic();
 
 	/* How many end-of-memory variables you have, grandma! */
@@ -1045,7 +1085,7 @@ void __init setup_arch(char **cmdline_p)
 
 	cleanup_highmap();
 
-	memblock.current_limit = ISA_END_ADDRESS;
+	memblock_set_current_limit(ISA_END_ADDRESS);
 	memblock_x86_fill();
 
 	/*
@@ -1078,8 +1118,8 @@ void __init setup_arch(char **cmdline_p)
 
 	setup_real_mode();
 
-	memblock.current_limit = get_max_mapped();
-	dma_contiguous_reserve(0);
+	memblock_set_current_limit(get_max_mapped());
+	dma_contiguous_reserve(max_pfn_mapped << PAGE_SHIFT);
 
 	/*
 	 * NOTE: On x86-32, only from this point on, fixmaps are ready for use.
@@ -1098,8 +1138,6 @@ void __init setup_arch(char **cmdline_p)
 	acpi_initrd_override((void *)initrd_start, initrd_end - initrd_start);
 #endif
 
-	reserve_crashkernel();
-
 	vsmp_init();
 
 	io_delay_init();
@@ -1112,6 +1150,13 @@ void __init setup_arch(char **cmdline_p)
 	early_acpi_boot_init();
 
 	initmem_init();
+
+	/*
+	 * Reserve memory for crash kernel after SRAT is parsed so that it
+	 * won't consume hotpluggable memory.
+	 */
+	reserve_crashkernel();
+
 	memblock_find_dma_reserve();
 
 #ifdef CONFIG_KVM_GUEST
@@ -1193,14 +1238,8 @@ void __init setup_arch(char **cmdline_p)
 	register_refined_jiffies(CLOCK_TICK_RATE);
 
 #ifdef CONFIG_EFI
-	/* Once setup is done above, unmap the EFI memory map on
-	 * mismatched firmware/kernel archtectures since there is no
-	 * support for runtime services.
-	 */
-	if (efi_enabled(EFI_BOOT) && !efi_is_native()) {
-		pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n");
-		efi_unmap_memmap();
-	}
+	if (efi_enabled(EFI_BOOT))
+		efi_apply_memmap_quirks();
 #endif
 }
 
@@ -1220,3 +1259,15 @@ void __init i386_reserve_resources(void)
 }
 
 #endif /* CONFIG_X86_32 */
+
+static struct notifier_block kernel_offset_notifier = {
+	.notifier_call = dump_kernel_offset
+};
+
+static int __init register_kernel_offset_dumper(void)
+{
+	atomic_notifier_chain_register(&panic_notifier_list,
+					&kernel_offset_notifier);
+	return 0;
+}
+__initcall(register_kernel_offset_dumper);