x86, boot: clean up kasl and setup_data handling

index 5903089..51e9e54 100644
@@ -370,10 +370,10 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap,
 				  unsigned char *input_data,
 				  unsigned long input_len,
 				  unsigned char *output,
-				  unsigned long output_len,
-				  unsigned long run_size)
+				  unsigned long output_len)
 {
 	unsigned char *output_orig = output;
+	unsigned long init_size;
 
 	real_mode = rmode;
 

@@ -396,15 +396,14 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap,
 	free_mem_ptr     = heap;	/* Heap */
 	free_mem_end_ptr = heap + BOOT_HEAP_SIZE;
 
+	init_size = real_mode->hdr.init_size;
+
 	/*
-	 * The memory hole needed for the kernel is the larger of either
-	 * the entire decompressed kernel plus relocation table, or the
-	 * entire decompressed kernel plus .bss and .brk sections.
+	 * The memory hole needed for the kernel is init_size for running
+	 * and init_size is bigger than output_len always.
 	 */
 	output = choose_kernel_location(real_mode, input_data, input_len,
-					output,
-					output_len > run_size ? output_len
-							      : run_size);
+					output, init_size);
 
 	/* Validate memory location choices. */
 	if ((unsigned long)output & (MIN_KERNEL_ALIGN - 1))

index d8222f2..b669ab6 100644
@@ -36,13 +36,11 @@ int main(int argc, char *argv[])
 	uint32_t olen;
 	long ilen;
 	unsigned long offs;
-	unsigned long run_size;
 	FILE *f = NULL;
 	int retval = 1;
 
-	if (argc < 3) {
-		fprintf(stderr, "Usage: %s compressed_file run_size\n",
-				argv[0]);
+	if (argc < 2) {
+		fprintf(stderr, "Usage: %s compressed_file\n", argv[0]);
 		goto bail;
 	}
 

@@ -76,7 +74,6 @@ int main(int argc, char *argv[])
 	offs += olen >> 12;	/* Add 8 bytes for each 32K block */
 	offs += 64*1024 + 128;	/* Add 64K + 128 bytes slack */
 	offs = (offs+4095) & ~4095; /* Round to a 4K boundary */
-	run_size = atoi(argv[2]);
 
 	printf(".section \".rodata..compressed\",\"a\",@progbits\n");
 	printf(".globl z_input_len\n");

@@ -88,8 +85,6 @@ int main(int argc, char *argv[])
 	/* z_extract_offset_negative allows simplification of head_32.S */
 	printf(".globl z_extract_offset_negative\n");
 	printf("z_extract_offset_negative = -0x%lx\n", offs);
-	printf(".globl z_run_size\n");
-	printf("z_run_size = %lu\n", run_size);
 
 	printf(".globl input_data, input_data_end\n");
 	printf("input_data:\n");

index b669ab6..652879b 100644
@@ -82,9 +82,6 @@ int main(int argc, char *argv[])
 	printf("z_output_len = %lu\n", (unsigned long)olen);
 	printf(".globl z_extract_offset\n");
 	printf("z_extract_offset = 0x%lx\n", offs);
-	/* z_extract_offset_negative allows simplification of head_32.S */
-	printf(".globl z_extract_offset_negative\n");
-	printf("z_extract_offset_negative = -0x%lx\n", offs);
 
 	printf(".globl input_data, input_data_end\n");
 	printf("input_data:\n");

index 9f6b934..0e8e4f7 100644
@@ -66,6 +66,7 @@ void common(void) {
 	OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch);
 	OFFSET(BP_version, boot_params, hdr.version);
 	OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment);
+	OFFSET(BP_init_size, boot_params, hdr.init_size);
 	OFFSET(BP_pref_address, boot_params, hdr.pref_address);
 	OFFSET(BP_code32_start, boot_params, hdr.code32_start);
 

index 98dc931..05d444f 100644
@@ -429,7 +429,13 @@ static void __init reserve_initrd(void)
 
 static void __init parse_kaslr_setup(u64 pa_data, u32 data_len)
 {
-	kaslr_enabled = (bool)(pa_data + sizeof(struct setup_data));
+	/* kaslr_setup_data is defined in aslr.c */
+	unsigned char *data;
+	unsigned long offset = sizeof(struct setup_data);
+
+	data = early_memremap(pa_data, offset + 1);
+	kaslr_enabled = *(data + offset);
+	early_memunmap(data, offset + 1);
 }
 
 static void __init parse_setup_data(void)

Index: linux-2.6/arch/x86/kernel/setup.c
===================================================================
@@ -429,7 +429,18 @@ static void __init reserve_initrd(void)
 
 static void __init parse_kaslr_setup(u64 pa_data, u32 data_len)
 {
-    kaslr_enabled = (bool)(pa_data + sizeof(struct setup_data));
+    /* kaslr_setup_data is defined in aslr.c */
+    unsigned char *data;
+    unsigned long offset = sizeof(struct setup_data);
+
+    data = early_memremap(pa_data, offset + 1);
+    if (!data) {
+        kaslr_enabled = true;
+        return;
+    }
+
+    kaslr_enabled = *(data + offset);
+    early_memunmap(data, offset + 1);
 }
 
 static void __init parse_setup_data(void)

index 7083c16..e8486a5 100644
@@ -116,7 +116,7 @@ struct mem_vector {
 	unsigned long size;
 };
 
-#define MEM_AVOID_MAX 5
+#define MEM_AVOID_MAX 4
 static struct mem_vector mem_avoid[MEM_AVOID_MAX];
 
 static bool mem_contains(struct mem_vector *region, struct mem_vector *item)

@@ -142,7 +142,7 @@ static bool mem_overlaps(struct mem_vector *one, struct mem_vector *two)
 }
 
 static void mem_avoid_init(unsigned long input, unsigned long input_size,
-			   unsigned long output, unsigned long output_size)
+			   unsigned long output, unsigned long init_size)
 {
 	u64 initrd_start, initrd_size;
 	u64 cmd_line, cmd_line_size;

@@ -151,10 +151,13 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
 
 	/*
 	 * Avoid the region that is unsafe to overlap during
-	 * decompression (see calculations at top of misc.c).
+	 * decompression.
+	 * As we already move compressed to the end of buffer,
+	 * [input+input_size, output+init_size) has [_text, _end)
+	 * for arch/x86/boot/compressed/vmlinux.
 	 */
-	unsafe_len = (output_size >> 12) + 32768 + 18;
-	unsafe = (unsigned long)input + input_size - unsafe_len;
+	unsafe_len = output + init_size - (input + input_size);
+	unsafe = (unsigned long)input + input_size;
 	mem_avoid[0].start = unsafe;
 	mem_avoid[0].size = unsafe_len;
 

@@ -176,13 +179,9 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
 	mem_avoid[2].start = cmd_line;
 	mem_avoid[2].size = cmd_line_size;
 
-	/* Avoid heap memory. */
-	mem_avoid[3].start = (unsigned long)free_mem_ptr;
-	mem_avoid[3].size = BOOT_HEAP_SIZE;
-
-	/* Avoid stack memory. */
-	mem_avoid[4].start = (unsigned long)free_mem_end_ptr;
-	mem_avoid[4].size = BOOT_STACK_SIZE;
+	/* Avoid params */
+	mem_avoid[3].start = (unsigned long)real_mode;
+	mem_avoid[3].size = sizeof(*real_mode);
 }
 
 /* Does this memory vector overlap a known avoided area? */

@@ -327,7 +326,7 @@ unsigned char *choose_kernel_location(struct boot_params *params,
 				      unsigned char *input,
 				      unsigned long input_size,
 				      unsigned char *output,
-				      unsigned long output_size)
+				      unsigned long init_size)
 {
 	unsigned long choice = (unsigned long)output;
 	unsigned long random;

@@ -349,10 +348,10 @@ unsigned char *choose_kernel_location(struct boot_params *params,
 
 	/* Record the various known unsafe memory ranges. */
 	mem_avoid_init((unsigned long)input, input_size,
-		       (unsigned long)output, output_size);
+		       (unsigned long)output, init_size);
 
 	/* Walk e820 and find a random address. */
-	random = find_random_addr(choice, output_size);
+	random = find_random_addr(choice, init_size);
 	if (!random) {
 		debug_putstr("KASLR could not find suitable E820 region...\n");
 		goto out;

index 802dde3..cf8f619 100644
@@ -37,7 +37,10 @@ static inline void copy_user_page(void *to, void *from, unsigned long vaddr,
 	alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr)
 #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
 
+#ifndef __pa
 #define __pa(x)		__phys_addr((unsigned long)(x))
+#endif
+
 #define __pa_nodebug(x)	__phys_addr_nodebug((unsigned long)(x))
 /* __pa_symbol should be used for C visible symbols.
    This seems to be the official gcc blessed way to do such arithmetic. */

@@ -51,7 +54,9 @@ static inline void copy_user_page(void *to, void *from, unsigned long vaddr,
 #define __pa_symbol(x) \
 	__phys_addr_symbol(__phys_reloc_hide((unsigned long)(x)))
 
+#ifndef __va
 #define __va(x)			((void *)((unsigned long)(x)+PAGE_OFFSET))
+#endif
 
 #define __boot_va(x)		__va(x)
 #define __boot_pa(x)		__pa(x)

74 lines not on this page · raw message

80 lines not on this page · raw message

index e8486a5..10ed3c7 100644
@@ -1,3 +1,8 @@
+#ifdef CONFIG_X86_64
+#define __pa(x)  ((unsigned long)(x))
+#define __va(x)  ((void *)((unsigned long)(x)))
+#endif
+
 #include "misc.h"
 
 #include <asm/msr.h>

@@ -21,6 +26,8 @@ struct kaslr_setup_data {
 	__u8 data[1];
 } kaslr_setup_data;
 
+#include "misc_pgt.c"
+
 #define I8254_PORT_CONTROL	0x43
 #define I8254_PORT_COUNTER0	0x40
 #define I8254_CMD_READBACK	0xC0

@@ -160,6 +167,7 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
 	unsafe = (unsigned long)input + input_size;
 	mem_avoid[0].start = unsafe;
 	mem_avoid[0].size = unsafe_len;
+	fill_linux64_pagetable(output, init_size);
 
 	/* Avoid initrd. */
 	initrd_start  = (u64)real_mode->ext_ramdisk_image << 32;

@@ -168,6 +176,7 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
 	initrd_size |= real_mode->hdr.ramdisk_size;
 	mem_avoid[1].start = initrd_start;
 	mem_avoid[1].size = initrd_size;
+	/* don't need to set mapping for initrd */
 
 	/* Avoid kernel command line. */
 	cmd_line  = (u64)real_mode->ext_cmd_line_ptr << 32;

@@ -178,10 +187,25 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
 		;
 	mem_avoid[2].start = cmd_line;
 	mem_avoid[2].size = cmd_line_size;
+	fill_linux64_pagetable(cmd_line, cmd_line_size);
 
 	/* Avoid params */
 	mem_avoid[3].start = (unsigned long)real_mode;
 	mem_avoid[3].size = sizeof(*real_mode);
+	fill_linux64_pagetable((unsigned long)real_mode, sizeof(*real_mode));
+}
+
+static void init_linux64_pagetable(void)
+{
+	struct setup_data *ptr;
+
+	ptr = (struct setup_data *)(unsigned long)real_mode->hdr.setup_data;
+	while (ptr) {
+		fill_linux64_pagetable((unsigned long)ptr,
+				       sizeof(*ptr) + ptr->len);
+
+		ptr = (struct setup_data *)(unsigned long)ptr->next;
+	}
 }
 
 /* Does this memory vector overlap a known avoided area? */

@@ -346,6 +370,7 @@ unsigned char *choose_kernel_location(struct boot_params *params,
 #endif
 	add_kaslr_setup_data(params, 1);
 
+	init_linux64_pagetable();
 	/* Record the various known unsafe memory ranges. */
 	mem_avoid_init((unsigned long)input, input_size,
 		       (unsigned long)output, init_size);

@@ -362,6 +387,9 @@ unsigned char *choose_kernel_location(struct boot_params *params,
 		goto out;
 
 	choice = random;
+
+	fill_linux64_pagetable(choice, init_size);
+	switch_linux64_pagetable();
 out:
 	return (unsigned char *)choice;
 }

96 lines not on this page · raw message

index 4fa687a..3795a77 100644
@@ -32,7 +32,20 @@
 #endif /* !CONFIG_KERNEL_BZIP2 */
 
 #ifdef CONFIG_X86_64
+
 #define BOOT_STACK_SIZE	0x4000
+
+#define BOOT_INIT_PGT_SIZE (6*4096)
+#ifdef CONFIG_RANDOMIZE_BASE
+/*
+ * 17 pages to cover for kernel, param, cmd_line, random kernel
+ * if all cross 512G boundary.
+ */
+#define BOOT_PGT_SIZE (BOOT_INIT_PGT_SIZE + (11*4096))
+#else
+#define BOOT_PGT_SIZE BOOT_INIT_PGT_SIZE
+#endif
+
 #else
 #define BOOT_STACK_SIZE	0x1000
 #endif

index d993e33..edc8a71 100644
@@ -33,15 +33,6 @@
 #define E820_NVS	4
 #define E820_UNUSABLE	5
 
-
-/*
- * reserved RAM used by kernel itself
- * if CONFIG_INTEL_TXT is enabled, memory of this type will be
- * included in the S3 integrity calculation and so should not include
- * any memory that BIOS might alter over the S3 transition
- */
-#define E820_RESERVED_KERN        128
-
 #ifndef __ASSEMBLY__
 #include <linux/types.h>
 struct e820entry {

index 46201de..2a6bed9 100644
@@ -134,7 +134,6 @@ static void __init e820_print_type(u32 type)
 {
 	switch (type) {
 	case E820_RAM:
-	case E820_RESERVED_KERN:
 		printk(KERN_CONT "usable");
 		break;
 	case E820_RESERVED:

@@ -688,7 +687,7 @@ void __init e820_mark_nosave_regions(unsigned long limit_pfn)
 			register_nosave_region(pfn, PFN_UP(ei->addr));
 
 		pfn = PFN_DOWN(ei->addr + ei->size);
-		if (ei->type != E820_RAM && ei->type != E820_RESERVED_KERN)
+		if (ei->type != E820_RAM)
 			register_nosave_region(PFN_UP(ei->addr), pfn);
 
 		if (pfn >= limit_pfn)

@@ -902,7 +901,6 @@ void __init finish_e820_parsing(void)
 static inline const char *e820_type_to_string(int e820_type)
 {
 	switch (e820_type) {
-	case E820_RESERVED_KERN:
 	case E820_RAM:	return "System RAM";
 	case E820_ACPI:	return "ACPI Tables";
 	case E820_NVS:	return "ACPI Non-volatile Storage";

@@ -1077,7 +1075,7 @@ void __init memblock_x86_fill(void)
 		if (end != (resource_size_t)end)
 			continue;
 
-		if (ei->type != E820_RAM && ei->type != E820_RESERVED_KERN)
+		if (ei->type != E820_RAM)
 			continue;
 
 		memblock_add(ei->addr, ei->size);

index 05d444f..c9b3e2f 100644
@@ -473,30 +473,6 @@ static void __init parse_setup_data(void)
 	}
 }
 
-static void __init e820_reserve_setup_data(void)
-{
-	struct setup_data *data;
-	u64 pa_data;
-	int found = 0;
-
-	pa_data = boot_params.hdr.setup_data;
-	while (pa_data) {
-		data = early_memremap(pa_data, sizeof(*data));
-		e820_update_range(pa_data, sizeof(*data)+data->len,
-			 E820_RAM, E820_RESERVED_KERN);
-		found = 1;
-		pa_data = data->next;
-		early_iounmap(data, sizeof(*data));
-	}
-	if (!found)
-		return;
-
-	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
-	memcpy(&e820_saved, &e820, sizeof(struct e820map));
-	printk(KERN_INFO "extended physical RAM map:\n");
-	e820_print_map("reserve setup_data");
-}
-
 static void __init memblock_x86_reserve_range_setup_data(void)
 {
 	struct setup_data *data;

@@ -1032,8 +1008,6 @@ 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))

index 91a4496..3c2752a 100644
@@ -195,8 +195,7 @@ static int tboot_setup_sleep(void)
 	tboot->num_mac_regions = 0;
 
 	for (i = 0; i < e820.nr_map; i++) {
-		if ((e820.map[i].type != E820_RAM)
-		 && (e820.map[i].type != E820_RESERVED_KERN))
+		if (e820.map[i].type != E820_RAM)
 			continue;
 
 		add_mac_region(e820.map[i].addr, e820.map[i].size);

index c30efb6..63520ec 100644
@@ -354,8 +354,7 @@ phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end,
 		next = (addr & PAGE_MASK) + PAGE_SIZE;
 		if (addr >= end) {
 			if (!after_bootmem &&
-			    !e820_any_mapped(addr & PAGE_MASK, next, E820_RAM) &&
-			    !e820_any_mapped(addr & PAGE_MASK, next, E820_RESERVED_KERN))
+			    !e820_any_mapped(addr & PAGE_MASK, next, E820_RAM))
 				set_pte(pte, __pte(0));
 			continue;
 		}

@@ -401,9 +400,8 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
 
 		next = (address & PMD_MASK) + PMD_SIZE;
 		if (address >= end) {
-			if (!after_bootmem &&
-			    !e820_any_mapped(address & PMD_MASK, next, E820_RAM) &&
-			    !e820_any_mapped(address & PMD_MASK, next, E820_RESERVED_KERN))
+			if (!after_bootmem && !e820_any_mapped(
+					address & PMD_MASK, next, E820_RAM))
 				set_pmd(pmd, __pmd(0));
 			continue;
 		}

@@ -476,8 +474,7 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
 		next = (addr & PUD_MASK) + PUD_SIZE;
 		if (addr >= end) {
 			if (!after_bootmem &&
-			    !e820_any_mapped(addr & PUD_MASK, next, E820_RAM) &&
-			    !e820_any_mapped(addr & PUD_MASK, next, E820_RESERVED_KERN))
+			    !e820_any_mapped(addr & PUD_MASK, next, E820_RAM))
 				set_pud(pud, __pud(0));
 			continue;
 		}

index 25bce45..edbecd6 100644
@@ -114,7 +114,7 @@ struct efi_setup_data {
 	u64 reserved[8];
 };
 
-extern u64 efi_setup;
+extern struct efi_setup_data *efi_setup;
 
 #ifdef CONFIG_EFI
 

index dbc8627..1cd38e8 100644
@@ -68,7 +68,7 @@ static efi_config_table_type_t arch_tables[] __initdata = {
 	{NULL_GUID, NULL, NULL},
 };
 
-u64 efi_setup;		/* efi setup_data physical address */
+struct efi_setup_data *efi_setup __initdata; /* cached efi setup_data pointer */
 
 static int add_efi_memmap __initdata;
 static int __init setup_add_efi_memmap(char *arg)

@@ -225,20 +225,13 @@ static int __init efi_systab_init(void *phys)
 {
 	if (efi_enabled(EFI_64BIT)) {
 		efi_system_table_64_t *systab64;
-		struct efi_setup_data *data = NULL;
+		struct efi_setup_data *data = efi_setup;
 		u64 tmp = 0;
 
-		if (efi_setup) {
-			data = early_memremap(efi_setup, sizeof(*data));
-			if (!data)
-				return -ENOMEM;
-		}
 		systab64 = early_memremap((unsigned long)phys,
 					 sizeof(*systab64));
 		if (systab64 == NULL) {
 			pr_err("Couldn't map the system table!\n");
-			if (data)
-				early_memunmap(data, sizeof(*data));
 			return -ENOMEM;
 		}
 

@@ -271,8 +264,6 @@ static int __init efi_systab_init(void *phys)
 		tmp |= data ? data->tables : systab64->tables;
 
 		early_memunmap(systab64, sizeof(*systab64));
-		if (data)
-			early_memunmap(data, sizeof(*data));
 #ifdef CONFIG_X86_32
 		if (tmp >> 32) {
 			pr_err("EFI data located above 4GB, disabling EFI.\n");

index 17e80d8..a541c6c 100644
@@ -292,9 +292,20 @@ void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size,
 	return (void __iomem *)__va(phys_addr);
 }
 
+static struct efi_setup_data efi_setup_data __initdata;
+
 void __init parse_efi_setup(u64 phys_addr, u32 data_len)
 {
-	efi_setup = phys_addr + sizeof(struct setup_data);
+	struct efi_setup_data *data;
+
+	data = early_memremap(phys_addr + sizeof(struct setup_data),
+			      sizeof(*data));
+	if (!data)
+		return;
+
+	efi_setup_data = *data;
+	early_memunmap(data, sizeof(*data));
+	efi_setup = &efi_setup_data;
 }
 
 void __init efi_runtime_mkexec(void)

index 1c7380d..45fec7d 100644
@@ -203,9 +203,8 @@ void __init efi_free_boot_services(void)
  */
 int __init efi_reuse_config(u64 tables, int nr_tables)
 {
-	int i, sz, ret = 0;
+	int i, sz;
 	void *p, *tablep;
-	struct efi_setup_data *data;
 
 	if (!efi_setup)
 		return 0;

@@ -213,22 +212,15 @@ int __init efi_reuse_config(u64 tables, int nr_tables)
 	if (!efi_enabled(EFI_64BIT))
 		return 0;
 
-	data = early_memremap(efi_setup, sizeof(*data));
-	if (!data) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	if (!data->smbios)
-		goto out_memremap;
+	if (!efi_setup->smbios)
+		return 0;
 
 	sz = sizeof(efi_config_table_64_t);
 
 	p = tablep = early_memremap(tables, nr_tables * sz);
 	if (!p) {
 		pr_err("Could not map Configuration table!\n");
-		ret = -ENOMEM;
-		goto out_memremap;
+		return -ENOMEM;
 	}
 
 	for (i = 0; i < efi.systab->nr_tables; i++) {

@@ -237,15 +229,12 @@ int __init efi_reuse_config(u64 tables, int nr_tables)
 		guid = ((efi_config_table_64_t *)p)->guid;
 
 		if (!efi_guidcmp(guid, SMBIOS_TABLE_GUID))
-			((efi_config_table_64_t *)p)->table = data->smbios;
+			((efi_config_table_64_t *)p)->table = efi_setup->smbios;
 		p += sz;
 	}
 	early_memunmap(tablep, nr_tables * sz);
 
-out_memremap:
-	early_memunmap(data, sizeof(*data));
-out:
-	return ret;
+	return 0;
 }
 
 void __init efi_apply_memmap_quirks(void)

index 1d081ac..fb716eddc 100644
@@ -24,17 +24,20 @@
 
 #ifdef CONFIG_OF
 extern int of_ioapic;
-extern u64 initial_dtb;
-extern void add_dtb(u64 data);
 void x86_of_pci_init(void);
 void x86_dtb_init(void);
 #else
-static inline void add_dtb(u64 data) { }
 static inline void x86_of_pci_init(void) { }
 static inline void x86_dtb_init(void) { }
 #define of_ioapic 0
 #endif
 
+#ifdef CONFIG_OF_FLATTREE
+extern void add_dtb(u64 data);
+#else
+static inline void add_dtb(u64 data) { }
+#endif
+
 extern char cmd_line[COMMAND_LINE_SIZE];
 
 #endif /* __ASSEMBLY__ */

index 3d35033..cc2fb61 100644
@@ -2,6 +2,7 @@
  * Architecture specific OF callbacks.
  */
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/export.h>
 #include <linux/io.h>
 #include <linux/irqdomain.h>

@@ -23,7 +24,6 @@
 #include <asm/setup.h>
 #include <asm/i8259.h>
 
-__initdata u64 initial_dtb;
 char __initdata cmd_line[COMMAND_LINE_SIZE];
 
 int __initdata of_ioapic;

@@ -43,11 +43,23 @@ void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
 	return __alloc_bootmem(size, align, __pa(MAX_DMA_ADDRESS));
 }
 
+#ifdef CONFIG_OF_FLATTREE
+static u64 initial_dtb __initdata;
+static u32 initial_dtb_size __initdata;
 void __init add_dtb(u64 data)
 {
+	u32 map_len;
+
 	initial_dtb = data + offsetof(struct setup_data, data);
-}
 
+	map_len = max(PAGE_SIZE - (initial_dtb & ~PAGE_MASK), (u64)128);
+	initial_boot_params = early_memremap(initial_dtb, map_len);
+	initial_dtb_size = of_get_flat_dt_size();
+	early_memunmap(initial_boot_params, map_len);
+	initial_boot_params = NULL;
+	memblock_reserve(initial_dtb, initial_dtb_size);
+}
+#endif
 /*
  * CE4100 ids. Will be moved to machine_device_initcall() once we have it.
  */

@@ -272,31 +284,22 @@ static void __init dtb_apic_setup(void)
 	dtb_ioapic_setup();
 }
 
-#ifdef CONFIG_OF_FLATTREE
 static void __init x86_flattree_get_config(void)
 {
-	u32 size, map_len;
+#ifdef CONFIG_OF_FLATTREE
 	void *dt;
 
 	if (!initial_dtb)
 		return;
 
-	map_len = max(PAGE_SIZE - (initial_dtb & ~PAGE_MASK), (u64)128);
-
-	initial_boot_params = dt = early_memremap(initial_dtb, map_len);
-	size = of_get_flat_dt_size();
-	if (map_len < size) {
-		early_iounmap(dt, map_len);
-		initial_boot_params = dt = early_memremap(initial_dtb, size);
-		map_len = size;
-	}
-
+	initial_boot_params = dt = early_memremap(initial_dtb,
+						  initial_dtb_size);
 	unflatten_and_copy_device_tree();
-	early_iounmap(dt, map_len);
-}
-#else
-static inline void x86_flattree_get_config(void) { }
+	early_memunmap(dt, initial_dtb_size);
+
+	memblock_free(initial_dtb, initial_dtb_size);
 #endif
+}
 
 void __init x86_dtb_init(void)
 {

index 4e370a5..7fbd5f3 100644
@@ -87,8 +87,10 @@ static inline void pci_dma_burst_advice(struct pci_dev *pdev,
 	*strat = PCI_DMA_BURST_INFINITY;
 	*strategy_parameter = ~0UL;
 }
+void add_pci(u64 pa_data);
 #else
 static inline void early_quirks(void) { }
+static inline void add_pci(u64 pa_data) { }
 #endif
 
 extern void pci_iommu_alloc(void);

index c9b3e2f..b1296d3 100644
@@ -453,6 +453,8 @@ static void __init parse_setup_data(void)
 		pa_next = data->next;
 		early_iounmap(data, sizeof(*data));
 
+		printk(KERN_DEBUG "setup_data type: %d @ %#010llx\n",
+				data_type, pa_data);
 		switch (data_type) {
 		case SETUP_E820_EXT:
 			parse_e820_ext(pa_data, data_len);

@@ -460,6 +462,9 @@ static void __init parse_setup_data(void)
 		case SETUP_DTB:
 			add_dtb(pa_data);
 			break;
+		case SETUP_PCI:
+			add_pci(pa_data);
+			break;
 		case SETUP_EFI:
 			parse_efi_setup(pa_data, data_len);
 			break;

@@ -467,10 +472,13 @@ static void __init parse_setup_data(void)
 			parse_kaslr_setup(pa_data, data_len);
 			break;
 		default:
+			pr_warn("Unknown setup_data type: %d @ %#010llx ignored!\n",
+				data_type, pa_data);
 			break;
 		}
 		pa_data = pa_next;
 	}
+	boot_params.hdr.setup_data = 0; /* all done */
 }
 
 static void __init memblock_x86_reserve_range_setup_data(void)

65 lines not on this page · raw message

index dc1404b..c8ca86c 100644
@@ -21,142 +21,6 @@ struct dentry *arch_debugfs_dir;
 EXPORT_SYMBOL(arch_debugfs_dir);
 
 #ifdef CONFIG_DEBUG_BOOT_PARAMS
-struct setup_data_node {
-	u64 paddr;
-	u32 type;
-	u32 len;
-};
-
-static ssize_t setup_data_read(struct file *file, char __user *user_buf,
-			       size_t count, loff_t *ppos)
-{
-	struct setup_data_node *node = file->private_data;
-	unsigned long remain;
-	loff_t pos = *ppos;
-	struct page *pg;
-	void *p;
-	u64 pa;
-
-	if (pos < 0)
-		return -EINVAL;
-
-	if (pos >= node->len)
-		return 0;
-
-	if (count > node->len - pos)
-		count = node->len - pos;
-
-	pa = node->paddr + sizeof(struct setup_data) + pos;
-	pg = pfn_to_page((pa + count - 1) >> PAGE_SHIFT);
-	if (PageHighMem(pg)) {
-		p = ioremap_cache(pa, count);
-		if (!p)
-			return -ENXIO;
-	} else
-		p = __va(pa);
-
-	remain = copy_to_user(user_buf, p, count);
-
-	if (PageHighMem(pg))
-		iounmap(p);
-
-	if (remain)
-		return -EFAULT;
-
-	*ppos = pos + count;
-
-	return count;
-}
-
-static const struct file_operations fops_setup_data = {
-	.read		= setup_data_read,
-	.open		= simple_open,
-	.llseek		= default_llseek,
-};
-
-static int __init
-create_setup_data_node(struct dentry *parent, int no,
-		       struct setup_data_node *node)
-{
-	struct dentry *d, *type, *data;
-	char buf[16];
-
-	sprintf(buf, "%d", no);
-	d = debugfs_create_dir(buf, parent);
-	if (!d)
-		return -ENOMEM;
-
-	type = debugfs_create_x32("type", S_IRUGO, d, &node->type);
-	if (!type)
-		goto err_dir;
-
-	data = debugfs_create_file("data", S_IRUGO, d, node, &fops_setup_data);
-	if (!data)
-		goto err_type;
-
-	return 0;
-
-err_type:
-	debugfs_remove(type);
-err_dir:
-	debugfs_remove(d);
-	return -ENOMEM;
-}
-
-static int __init create_setup_data_nodes(struct dentry *parent)
-{
-	struct setup_data_node *node;
-	struct setup_data *data;
-	int error;
-	struct dentry *d;
-	struct page *pg;
-	u64 pa_data;
-	int no = 0;
-
-	d = debugfs_create_dir("setup_data", parent);
-	if (!d)
-		return -ENOMEM;
-
-	pa_data = boot_params.hdr.setup_data;
-
-	while (pa_data) {
-		node = kmalloc(sizeof(*node), GFP_KERNEL);
-		if (!node) {
-			error = -ENOMEM;
-			goto err_dir;
-		}
-
-		pg = pfn_to_page((pa_data+sizeof(*data)-1) >> PAGE_SHIFT);
-		if (PageHighMem(pg)) {
-			data = ioremap_cache(pa_data, sizeof(*data));
-			if (!data) {
-				kfree(node);
-				error = -ENXIO;
-				goto err_dir;
-			}
-		} else
-			data = __va(pa_data);
-
-		node->paddr = pa_data;
-		node->type = data->type;
-		node->len = data->len;
-		error = create_setup_data_node(d, no, node);
-		pa_data = data->next;
-
-		if (PageHighMem(pg))
-			iounmap(data);
-		if (error)
-			goto err_dir;
-		no++;
-	}
-
-	return 0;
-
-err_dir:
-	debugfs_remove(d);
-	return error;
-}
-
 static struct debugfs_blob_wrapper boot_params_blob = {
 	.data		= &boot_params,
 	.size		= sizeof(boot_params),

@@ -181,14 +45,8 @@ static int __init boot_params_kdebugfs_init(void)
 	if (!data)
 		goto err_version;
 
-	error = create_setup_data_nodes(dbp);
-	if (error)
-		goto err_data;
-
 	return 0;
 
-err_data:
-	debugfs_remove(data);
 err_version:
 	debugfs_remove(version);
 err_dir:

index b1296d3..9a18078 100644
@@ -481,20 +481,6 @@ static void __init parse_setup_data(void)
 	boot_params.hdr.setup_data = 0; /* all done */
 }
 
-static void __init memblock_x86_reserve_range_setup_data(void)
-{
-	struct setup_data *data;
-	u64 pa_data;
-
-	pa_data = boot_params.hdr.setup_data;
-	while (pa_data) {
-		data = early_memremap(pa_data, sizeof(*data));
-		memblock_reserve(pa_data, sizeof(*data) + data->len);
-		pa_data = data->next;
-		early_iounmap(data, sizeof(*data));
-	}
-}
-
 /*
  * --------- Crashkernel reservation ------------------------------
  */

@@ -1001,9 +987,6 @@ void __init setup_arch(char **cmdline_p)
 
 	x86_report_nx();
 
-	/* after early param, so could get panic from serial */
-	memblock_x86_reserve_range_setup_data();
-
 	if (acpi_mps_check()) {
 #ifdef CONFIG_X86_LOCAL_APIC
 		disable_apic = 1;

index 7fbd5f3..99b261f 100644
@@ -88,9 +88,11 @@ static inline void pci_dma_burst_advice(struct pci_dev *pdev,
 	*strategy_parameter = ~0UL;
 }
 void add_pci(u64 pa_data);
+int fill_setup_pci_entries(void);
 #else
 static inline void early_quirks(void) { }
 static inline void add_pci(u64 pa_data) { }
+static inline int fill_setup_pci_entries(void) { }
 #endif
 
 extern void pci_iommu_alloc(void);

index 9a18078..215bea8 100644
@@ -1190,6 +1190,7 @@ void __init setup_arch(char **cmdline_p)
 	acpi_boot_init();
 	sfi_init();
 	x86_dtb_init();
+	fill_setup_pci_entries();
 
 	/*
 	 * get boot-time SMP configuration:

105 lines not on this page · raw message

index 93577fb..a5de331 100644
@@ -694,6 +694,48 @@ struct firmware_setup_pci_entry {
 
 static LIST_HEAD(setup_pci_entries);
 
+static phys_addr_t check_copy(phys_addr_t start, unsigned long size)
+{
+	unsigned long start_pfn = PFN_DOWN(start);
+	unsigned long end_pfn = PFN_UP(start + size);
+	unsigned char *p, *q;
+	phys_addr_t pa_p, pa_q;
+	long sz = size;
+
+	if (pfn_range_is_mapped(start_pfn, end_pfn))
+		return start;
+
+	/* allocate and copy */
+	pa_p = memblock_alloc(size, PAGE_SIZE);
+	if (!pa_p)
+		return start;
+
+	p = phys_to_virt(pa_p);
+
+	pa_q = start;
+	while (sz > 0) {
+		long chunk_size = 64<<10;
+
+		if (chunk_size > sz)
+			chunk_size = sz;
+
+		q = early_memremap(pa_q, chunk_size);
+		if (!q) {
+			memblock_free(pa_p, size);
+			return start;
+		}
+		memcpy(p, q, chunk_size);
+		early_memunmap(q, chunk_size);
+		p += chunk_size;
+		pa_q += chunk_size;
+		sz -= chunk_size;
+	}
+
+	early_memunmap(start, size);
+
+	return pa_p;
+}
+
 int __init fill_setup_pci_entries(void)
 {
 	struct setup_data *data;

@@ -723,8 +765,9 @@ int __init fill_setup_pci_entries(void)
 		entry->vendor = rom->vendor;
 		entry->devid = rom->devid;
 		entry->pcilen = rom->pcilen;
-		entry->romdata = pa_data +
-				 offsetof(struct pci_setup_rom, romdata);
+		entry->romdata = check_copy(pa_data +
+				      offsetof(struct pci_setup_rom, romdata),
+				      rom->pcilen);
 
 		list_add(&entry->list, &setup_pci_entries);
 

index a5de331..fb4765b 100644
@@ -682,6 +682,8 @@ void __init add_pci(u64 pa_data)
 
 struct firmware_setup_pci_entry {
 	struct list_head list;
+	struct kobject kobj;
+	struct bin_attribute *rom_attr;
 	uint16_t vendor;
 	uint16_t devid;
 	uint64_t pcilen;

@@ -803,6 +805,179 @@ int pcibios_add_device(struct pci_dev *dev)
 	return 0;
 }
 
+#ifdef CONFIG_SYSFS
+static inline struct firmware_setup_pci_entry *
+to_setup_pci_entry(struct kobject *kobj)
+{
+	return container_of(kobj, struct firmware_setup_pci_entry, kobj);
+}
+
+static ssize_t vendor_show(struct firmware_setup_pci_entry *entry, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "0x%04llx\n",
+			(unsigned long long)entry->vendor);
+}
+
+static ssize_t devid_show(struct firmware_setup_pci_entry *entry, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "0x%04llx\n",
+			(unsigned long long)entry->devid);
+}
+
+static ssize_t pcilen_show(struct firmware_setup_pci_entry *entry, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "0x%llx\n",
+			(unsigned long long)entry->pcilen);
+}
+
+static ssize_t segment_show(struct firmware_setup_pci_entry *entry, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "0x%04llx\n",
+			(unsigned long long)entry->segment);
+}
+
+static ssize_t bus_show(struct firmware_setup_pci_entry *entry, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "0x%02llx\n",
+			(unsigned long long)entry->bus);
+}
+
+static ssize_t device_show(struct firmware_setup_pci_entry *entry, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "0x%02llx\n",
+			(unsigned long long)entry->device);
+}
+
+static ssize_t function_show(struct firmware_setup_pci_entry *entry, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "0x%1llx\n",
+			(unsigned long long)entry->function);
+}
+
+struct setup_pci_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct firmware_setup_pci_entry *entry, char *buf);
+};
+
+static inline struct setup_pci_attribute *to_setup_pci_attr(
+							struct attribute *attr)
+{
+	return container_of(attr, struct setup_pci_attribute, attr);
+}
+
+static ssize_t setup_pci_attr_show(struct kobject *kobj,
+				   struct attribute *attr, char *buf)
+{
+	struct firmware_setup_pci_entry *entry = to_setup_pci_entry(kobj);
+	struct setup_pci_attribute *setup_pci_attr = to_setup_pci_attr(attr);
+
+	return setup_pci_attr->show(entry, buf);
+}
+
+static struct setup_pci_attribute setup_pci_vendor_attr = __ATTR_RO(vendor);
+static struct setup_pci_attribute setup_pci_devid_attr = __ATTR_RO(devid);
+static struct setup_pci_attribute setup_pci_pcilen_attr = __ATTR_RO(pcilen);
+static struct setup_pci_attribute setup_pci_segment_attr = __ATTR_RO(segment);
+static struct setup_pci_attribute setup_pci_bus_attr = __ATTR_RO(bus);
+static struct setup_pci_attribute setup_pci_device_attr = __ATTR_RO(device);
+static struct setup_pci_attribute setup_pci_function_attr = __ATTR_RO(function);
+
+/*
+ * These are default attributes that are added for every memmap entry.
+ */
+static struct attribute *def_attrs[] = {
+	&setup_pci_vendor_attr.attr,
+	&setup_pci_devid_attr.attr,
+	&setup_pci_pcilen_attr.attr,
+	&setup_pci_segment_attr.attr,
+	&setup_pci_bus_attr.attr,
+	&setup_pci_device_attr.attr,
+	&setup_pci_function_attr.attr,
+	NULL
+};
+
+static const struct sysfs_ops setup_pci_attr_ops = {
+	.show = setup_pci_attr_show,
+};
+
+static struct kobj_type __refdata setup_pci_ktype = {
+	.sysfs_ops      = &setup_pci_attr_ops,
+	.default_attrs  = def_attrs,
+};
+
+static ssize_t setup_pci_rom_read(struct file *filp, struct kobject *kobj,
+				  struct bin_attribute *bin_attr, char *buf,
+				  loff_t off, size_t count)
+{
+	struct firmware_setup_pci_entry *entry = to_setup_pci_entry(kobj);
+
+	if (off >= entry->pcilen)
+		count = 0;
+	else {
+		unsigned char *rom = phys_to_virt(entry->romdata);
+
+		if (off + count > entry->pcilen)
+			count = entry->pcilen - off;
+
+		memcpy(buf, rom + off, count);
+	}
+
+	return count;
+}
+
+static int __init add_sysfs_fw_setup_pci_entry(
+					struct firmware_setup_pci_entry *entry)
+{
+	int retval = 0;
+	static int setup_pci_entries_nr;
+	static struct kset *setup_pci_kset;
+	struct bin_attribute *attr;
+
+	kobject_init(&entry->kobj, &setup_pci_ktype);
+
+	if (!setup_pci_kset) {
+		setup_pci_kset = kset_create_and_add("setup_pci", NULL,
+						     firmware_kobj);
+		if (!setup_pci_kset)
+			return -ENOMEM;
+	}
+
+	entry->kobj.kset = setup_pci_kset;
+	retval = kobject_add(&entry->kobj, NULL, "%d", setup_pci_entries_nr++);
+	if (retval) {
+		kobject_put(&entry->kobj);
+		return retval;
+	}
+
+	attr = kzalloc(sizeof(*attr), GFP_ATOMIC);
+	if (!attr)
+		return -ENOMEM;
+
+	sysfs_bin_attr_init(attr);
+	attr->size = entry->pcilen;
+	attr->attr.name = "rom";
+	attr->attr.mode = S_IRUSR;
+	attr->read = setup_pci_rom_read;
+	retval = sysfs_create_bin_file(&entry->kobj, attr);
+	if (retval)
+		kfree(attr);
+	entry->rom_attr = attr;
+
+	return retval;
+}
+
+static int __init firmware_setup_pci_init(void)
+{
+	struct firmware_setup_pci_entry *entry;
+
+	list_for_each_entry(entry, &setup_pci_entries, list)
+		add_sysfs_fw_setup_pci_entry(entry);
+
+	return 0;
+}
+late_initcall(firmware_setup_pci_init);
+#endif
+
 int pcibios_enable_device(struct pci_dev *dev, int mask)
 {
 	int err;