1 files changed, 199 insertions, 111 deletions

diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 8b24289cc10..56f7fcfe7fa 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>
@@ -108,17 +107,16 @@
 #include <asm/topology.h>
 #include <asm/apicdef.h>
 #include <asm/amd_nb.h>
-#ifdef CONFIG_X86_64
-#include <asm/numa_64.h>
-#endif
 #include <asm/mce.h>
 #include <asm/alternative.h>
 #include <asm/prom.h>
 
 /*
- * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
- * The direct mapping extends to max_pfn_mapped, so that we can directly access
- * apertures, ACPI and other tables without having to play with fixmaps.
+ * max_low_pfn_mapped: highest direct mapped pfn under 4GB
+ * max_pfn_mapped:     highest direct mapped pfn over 4GB
+ *
+ * The direct mapping only covers E820_RAM regions, so the ranges and gaps are
+ * represented by pfn_mapped
  */
 unsigned long max_low_pfn_mapped;
 unsigned long max_pfn_mapped;
@@ -172,9 +170,13 @@ 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 = {0, 0, 0, 0, -1, 1, 0, 0, -1};
+struct cpuinfo_x86 new_cpu_data __cpuinitdata = {
+	.wp_works_ok = -1,
+};
 /* common cpu data for all cpus */
-struct cpuinfo_x86 boot_cpu_data __read_mostly = {0, 0, 0, 0, -1, 1, 0, 0, -1};
+struct cpuinfo_x86 boot_cpu_data __read_mostly = {
+	.wp_works_ok = -1,
+};
 EXPORT_SYMBOL(boot_cpu_data);
 
 unsigned int def_to_bigsmp;
@@ -276,18 +278,7 @@ void * __init extend_brk(size_t size, size_t align)
 	return ret;
 }
 
-#ifdef CONFIG_X86_64
-static void __init init_gbpages(void)
-{
-	if (direct_gbpages && cpu_has_gbpages)
-		printk(KERN_INFO "Using GB pages for direct mapping\n");
-	else
-		direct_gbpages = 0;
-}
-#else
-static inline void init_gbpages(void)
-{
-}
+#ifdef CONFIG_X86_32
 static void __init cleanup_highmap(void)
 {
 }
@@ -296,8 +287,8 @@ static void __init cleanup_highmap(void)
 static void __init reserve_brk(void)
 {
 	if (_brk_end > _brk_start)
-		memblock_reserve(__pa(_brk_start),
-				 __pa(_brk_end) - __pa(_brk_start));
+		memblock_reserve(__pa_symbol(_brk_start),
+				 _brk_end - _brk_start);
 
 	/* Mark brk area as locked down and no longer taking any
 	   new allocations */
@@ -306,27 +297,43 @@ static void __init reserve_brk(void)
 
 #ifdef CONFIG_BLK_DEV_INITRD
 
+static u64 __init get_ramdisk_image(void)
+{
+	u64 ramdisk_image = boot_params.hdr.ramdisk_image;
+
+	ramdisk_image |= (u64)boot_params.ext_ramdisk_image << 32;
+
+	return ramdisk_image;
+}
+static u64 __init get_ramdisk_size(void)
+{
+	u64 ramdisk_size = boot_params.hdr.ramdisk_size;
+
+	ramdisk_size |= (u64)boot_params.ext_ramdisk_size << 32;
+
+	return ramdisk_size;
+}
+
 #define MAX_MAP_CHUNK	(NR_FIX_BTMAPS << PAGE_SHIFT)
 static void __init relocate_initrd(void)
 {
 	/* Assume only end is not page aligned */
-	u64 ramdisk_image = boot_params.hdr.ramdisk_image;
-	u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
+	u64 ramdisk_image = get_ramdisk_image();
+	u64 ramdisk_size  = get_ramdisk_size();
 	u64 area_size     = PAGE_ALIGN(ramdisk_size);
-	u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
 	u64 ramdisk_here;
 	unsigned long slop, clen, mapaddr;
 	char *p, *q;
 
-	/* We need to move the initrd down into lowmem */
-	ramdisk_here = memblock_find_in_range(0, end_of_lowmem, area_size,
-					 PAGE_SIZE);
+	/* 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);
 
 	if (!ramdisk_here)
 		panic("Cannot find place for new RAMDISK of size %lld\n",
 			 ramdisk_size);
 
-	/* Note: this includes all the lowmem currently occupied by
+	/* 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;
@@ -336,17 +343,7 @@ static void __init relocate_initrd(void)
 
 	q = (char *)initrd_start;
 
-	/* Copy any lowmem portion of the initrd */
-	if (ramdisk_image < end_of_lowmem) {
-		clen = end_of_lowmem - ramdisk_image;
-		p = (char *)__va(ramdisk_image);
-		memcpy(q, p, clen);
-		q += clen;
-		ramdisk_image += clen;
-		ramdisk_size  -= clen;
-	}
-
-	/* Copy the highmem portion of the initrd */
+	/* Copy the initrd */
 	while (ramdisk_size) {
 		slop = ramdisk_image & ~PAGE_MASK;
 		clen = ramdisk_size;
@@ -360,22 +357,35 @@ static void __init relocate_initrd(void)
 		ramdisk_image += clen;
 		ramdisk_size  -= clen;
 	}
-	/* high pages is not converted by early_res_to_bootmem */
-	ramdisk_image = boot_params.hdr.ramdisk_image;
-	ramdisk_size  = boot_params.hdr.ramdisk_size;
+
+	ramdisk_image = get_ramdisk_image();
+	ramdisk_size  = get_ramdisk_size();
 	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);
 }
 
+static void __init early_reserve_initrd(void)
+{
+	/* Assume only end is not page aligned */
+	u64 ramdisk_image = get_ramdisk_image();
+	u64 ramdisk_size  = get_ramdisk_size();
+	u64 ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
+
+	if (!boot_params.hdr.type_of_loader ||
+	    !ramdisk_image || !ramdisk_size)
+		return;		/* No initrd provided by bootloader */
+
+	memblock_reserve(ramdisk_image, ramdisk_end - ramdisk_image);
+}
 static void __init reserve_initrd(void)
 {
 	/* Assume only end is not page aligned */
-	u64 ramdisk_image = boot_params.hdr.ramdisk_image;
-	u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
+	u64 ramdisk_image = get_ramdisk_image();
+	u64 ramdisk_size  = get_ramdisk_size();
 	u64 ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
-	u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
+	u64 mapped_size;
 
 	if (!boot_params.hdr.type_of_loader ||
 	    !ramdisk_image || !ramdisk_size)
@@ -383,22 +393,18 @@ static void __init reserve_initrd(void)
 
 	initrd_start = 0;
 
-	if (ramdisk_size >= (end_of_lowmem>>1)) {
+	mapped_size = memblock_mem_size(max_pfn_mapped);
+	if (ramdisk_size >= (mapped_size>>1))
 		panic("initrd too large to handle, "
 		       "disabling initrd (%lld needed, %lld available)\n",
-		       ramdisk_size, end_of_lowmem>>1);
-	}
+		       ramdisk_size, mapped_size>>1);
 
 	printk(KERN_INFO "RAMDISK: [mem %#010llx-%#010llx]\n", ramdisk_image,
 			ramdisk_end - 1);
 
-
-	if (ramdisk_end <= end_of_lowmem) {
-		/* All in lowmem, easy case */
-		/*
-		 * don't need to reserve again, already reserved early
-		 * in i386_start_kernel
-		 */
+	if (pfn_range_is_mapped(PFN_DOWN(ramdisk_image),
+				PFN_DOWN(ramdisk_end))) {
+		/* All are mapped, easy case */
 		initrd_start = ramdisk_image + PAGE_OFFSET;
 		initrd_end = initrd_start + ramdisk_size;
 		return;
@@ -409,6 +415,9 @@ static void __init reserve_initrd(void)
 	memblock_free(ramdisk_image, ramdisk_end - ramdisk_image);
 }
 #else
+static void __init early_reserve_initrd(void)
+{
+}
 static void __init reserve_initrd(void)
 {
 }
@@ -419,8 +428,6 @@ static void __init parse_setup_data(void)
 	struct setup_data *data;
 	u64 pa_data;
 
-	if (boot_params.hdr.version < 0x0209)
-		return;
 	pa_data = boot_params.hdr.setup_data;
 	while (pa_data) {
 		u32 data_len, map_len;
@@ -456,8 +463,6 @@ static void __init e820_reserve_setup_data(void)
 	u64 pa_data;
 	int found = 0;
 
-	if (boot_params.hdr.version < 0x0209)
-		return;
 	pa_data = boot_params.hdr.setup_data;
 	while (pa_data) {
 		data = early_memremap(pa_data, sizeof(*data));
@@ -481,8 +486,6 @@ static void __init memblock_x86_reserve_range_setup_data(void)
 	struct setup_data *data;
 	u64 pa_data;
 
-	if (boot_params.hdr.version < 0x0209)
-		return;
 	pa_data = boot_params.hdr.setup_data;
 	while (pa_data) {
 		data = early_memremap(pa_data, sizeof(*data));
@@ -501,42 +504,104 @@ 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 64 bits, kexec-tools currently limits us to 896 MiB; increase this
- * limit once kexec-tools are fixed.
+ * 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	(896 << 20)
+# define CRASH_KERNEL_ADDR_LOW_MAX	(896UL<<20)
+# define CRASH_KERNEL_ADDR_HIGH_MAX	MAXMEM
+#endif
+
+static void __init reserve_crashkernel_low(void)
+{
+#ifdef CONFIG_X86_64
+	const unsigned long long alignment = 16<<20;	/* 16M */
+	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) {
+		/*
+		 * 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) {
+		if (!auto_set)
+			pr_info("crashkernel low reservation failed - No suitable area found.\n");
+
+		return;
+	}
+
+	memblock_reserve(low_base, low_size);
+	pr_info("Reserving %ldMB of low memory at %ldMB for crashkernel (System low RAM: %ldMB)\n",
+			(unsigned long)(low_size >> 20),
+			(unsigned long)(low_base >> 20),
+			(unsigned long)(total_low_mem >> 20));
+	crashk_low_res.start = low_base;
+	crashk_low_res.end   = low_base + low_size - 1;
+	insert_resource(&iomem_resource, &crashk_low_res);
 #endif
+}
 
 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) {
-		const unsigned long long alignment = 16<<20;	/* 16M */
-
 		/*
 		 *  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");
 			return;
 		}
+
 	} else {
 		unsigned long long start;
 
@@ -558,6 +623,9 @@ static void __init reserve_crashkernel(void)
 	crashk_res.start = crash_base;
 	crashk_res.end   = crash_base + crash_size - 1;
 	insert_resource(&iomem_resource, &crashk_res);
+
+	if (crash_base >= (1ULL<<32))
+		reserve_crashkernel_low();
 }
 #else
 static void __init reserve_crashkernel(void)
@@ -608,8 +676,6 @@ static __init void reserve_ibft_region(void)
 		memblock_reserve(addr, size);
 }
 
-static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10;
-
 static bool __init snb_gfx_workaround_needed(void)
 {
 #ifdef CONFIG_PCI
@@ -698,8 +764,7 @@ static void __init trim_bios_range(void)
 	 * since some BIOSes are known to corrupt low memory.  See the
 	 * Kconfig help text for X86_RESERVE_LOW.
 	 */
-	e820_update_range(0, ALIGN(reserve_low, PAGE_SIZE),
-			  E820_RAM, E820_RESERVED);
+	e820_update_range(0, PAGE_SIZE, E820_RAM, E820_RESERVED);
 
 	/*
 	 * special case: Some BIOSen report the PC BIOS
@@ -711,6 +776,29 @@ static void __init trim_bios_range(void)
 	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
 }
 
+/* called before trim_bios_range() to spare extra sanitize */
+static void __init e820_add_kernel_range(void)
+{
+	u64 start = __pa_symbol(_text);
+	u64 size = __pa_symbol(_end) - start;
+
+	/*
+	 * Complain if .text .data and .bss are not marked as E820_RAM and
+	 * attempt to fix it by adding the range. We may have a confused BIOS,
+	 * or the user may have used memmap=exactmap or memmap=xxM$yyM to
+	 * exclude kernel range. If we really are running on top non-RAM,
+	 * we will crash later anyways.
+	 */
+	if (e820_all_mapped(start, start + size, E820_RAM))
+		return;
+
+	pr_warn(".text .data .bss are not marked as E820_RAM!\n");
+	e820_remove_range(start, size, E820_RAM, 0);
+	e820_add_region(start, size, E820_RAM);
+}
+
+static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10;
+
 static int __init parse_reservelow(char *p)
 {
 	unsigned long long size;
@@ -733,6 +821,11 @@ static int __init parse_reservelow(char *p)
 
 early_param("reservelow", parse_reservelow);
 
+static void __init trim_low_memory_range(void)
+{
+	memblock_reserve(0, ALIGN(reserve_low, PAGE_SIZE));
+}
+	
 /*
  * 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
@@ -748,6 +841,17 @@ early_param("reservelow", parse_reservelow);
 
 void __init setup_arch(char **cmdline_p)
 {
+	memblock_reserve(__pa_symbol(_text),
+			 (unsigned long)__bss_stop - (unsigned long)_text);
+
+	early_reserve_initrd();
+
+	/*
+	 * At this point everything still needed from the boot loader
+	 * or BIOS or kernel text should be early reserved or marked not
+	 * RAM in e820. All other memory is free game.
+	 */
+
 #ifdef CONFIG_X86_32
 	memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data));
 	visws_early_detect();
@@ -835,12 +939,12 @@ void __init setup_arch(char **cmdline_p)
 	init_mm.end_data = (unsigned long) _edata;
 	init_mm.brk = _brk_end;
 
-	code_resource.start = virt_to_phys(_text);
-	code_resource.end = virt_to_phys(_etext)-1;
-	data_resource.start = virt_to_phys(_etext);
-	data_resource.end = virt_to_phys(_edata)-1;
-	bss_resource.start = virt_to_phys(&__bss_start);
-	bss_resource.end = virt_to_phys(&__bss_stop)-1;
+	code_resource.start = __pa_symbol(_text);
+	code_resource.end = __pa_symbol(_etext)-1;
+	data_resource.start = __pa_symbol(_etext);
+	data_resource.end = __pa_symbol(_edata)-1;
+	bss_resource.start = __pa_symbol(__bss_start);
+	bss_resource.end = __pa_symbol(__bss_stop)-1;
 
 #ifdef CONFIG_CMDLINE_BOOL
 #ifdef CONFIG_CMDLINE_OVERRIDE
@@ -892,6 +996,7 @@ void __init setup_arch(char **cmdline_p)
 		efi_init();
 
 	dmi_scan_machine();
+	dmi_set_dump_stack_arch_desc();
 
 	/*
 	 * VMware detection requires dmi to be available, so this
@@ -906,6 +1011,7 @@ void __init setup_arch(char **cmdline_p)
 	insert_resource(&iomem_resource, &data_resource);
 	insert_resource(&iomem_resource, &bss_resource);
 
+	e820_add_kernel_range();
 	trim_bios_range();
 #ifdef CONFIG_X86_32
 	if (ppro_with_ram_bug()) {
@@ -955,6 +1061,8 @@ void __init setup_arch(char **cmdline_p)
 
 	reserve_ibft_region();
 
+	early_alloc_pgt_buf();
+
 	/*
 	 * Need to conclude brk, before memblock_x86_fill()
 	 *  it could use memblock_find_in_range, could overlap with
@@ -964,7 +1072,7 @@ void __init setup_arch(char **cmdline_p)
 
 	cleanup_highmap();
 
-	memblock.current_limit = get_max_mapped();
+	memblock.current_limit = ISA_END_ADDRESS;
 	memblock_x86_fill();
 
 	/*
@@ -981,41 +1089,22 @@ void __init setup_arch(char **cmdline_p)
 	setup_bios_corruption_check();
 #endif
 
+#ifdef CONFIG_X86_32
 	printk(KERN_DEBUG "initial memory mapped: [mem 0x00000000-%#010lx]\n",
 			(max_pfn_mapped<<PAGE_SHIFT) - 1);
+#endif
 
-	setup_real_mode();
+	reserve_real_mode();
 
 	trim_platform_memory_ranges();
+	trim_low_memory_range();
 
-	init_gbpages();
-
-	/* max_pfn_mapped is updated here */
-	max_low_pfn_mapped = init_memory_mapping(0, max_low_pfn<<PAGE_SHIFT);
-	max_pfn_mapped = max_low_pfn_mapped;
-
-#ifdef CONFIG_X86_64
-	if (max_pfn > max_low_pfn) {
-		int i;
-		unsigned long start, end;
-		unsigned long start_pfn, end_pfn;
+	init_mem_mapping();
 
-		for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn,
-							 NULL) {
+	early_trap_pf_init();
 
-			end = PFN_PHYS(end_pfn);
-			if (end <= (1UL<<32))
-				continue;
-
-			start = PFN_PHYS(start_pfn);
-			max_pfn_mapped = init_memory_mapping(
-						max((1UL<<32), start), end);
-		}
+	setup_real_mode();
 
-		/* can we preseve max_low_pfn ?*/
-		max_low_pfn = max_pfn;
-	}
-#endif
 	memblock.current_limit = get_max_mapped();
 	dma_contiguous_reserve(0);
 
@@ -1135,8 +1224,7 @@ void __init setup_arch(char **cmdline_p)
 	 * mismatched firmware/kernel archtectures since there is no
 	 * support for runtime services.
 	 */
-	if (efi_enabled(EFI_BOOT) &&
-	    IS_ENABLED(CONFIG_X86_64) != efi_enabled(EFI_64BIT)) {
+	if (efi_enabled(EFI_BOOT) && !efi_is_native()) {
 		pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n");
 		efi_unmap_memmap();
 	}