efi.c

linux 内核源代码

	/* it's too early to be able to use the standard kernel command line support... */
	for (cp = boot_command_line; *cp; ) {
		if (memcmp(cp, "mem=", 4) == 0) {
			mem_limit = memparse(cp + 4, &cp);
		} else if (memcmp(cp, "max_addr=", 9) == 0) {
			max_addr = GRANULEROUNDDOWN(memparse(cp + 9, &cp));
		} else if (memcmp(cp, "min_addr=", 9) == 0) {
			min_addr = GRANULEROUNDDOWN(memparse(cp + 9, &cp));
		} else {
			while (*cp != ' ' && *cp)
				++cp;
			while (*cp == ' ')
				++cp;
		}
	}
	if (min_addr != 0UL)
		printk(KERN_INFO "Ignoring memory below %luMB\n", min_addr >> 20);
	if (max_addr != ~0UL)
		printk(KERN_INFO "Ignoring memory above %luMB\n", max_addr >> 20);

	efi.systab = __va(ia64_boot_param->efi_systab);

	/*
	 * Verify the EFI Table
	 */
	if (efi.systab == NULL)
		panic("Woah! Can't find EFI system table.\n");
	if (efi.systab->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
		panic("Woah! EFI system table signature incorrect\n");
	if ((efi.systab->hdr.revision >> 16) == 0)
		printk(KERN_WARNING "Warning: EFI system table version "
		       "%d.%02d, expected 1.00 or greater\n",
		       efi.systab->hdr.revision >> 16,
		       efi.systab->hdr.revision & 0xffff);

	config_tables = __va(efi.systab->tables);

	/* Show what we know for posterity */
	c16 = __va(efi.systab->fw_vendor);
	if (c16) {
		for (i = 0;i < (int) sizeof(vendor) - 1 && *c16; ++i)
			vendor[i] = *c16++;
		vendor[i] = '\0';
	}

	printk(KERN_INFO "EFI v%u.%.02u by %s:",
	       efi.systab->hdr.revision >> 16, efi.systab->hdr.revision & 0xffff, vendor);

	efi.mps        = EFI_INVALID_TABLE_ADDR;
	efi.acpi       = EFI_INVALID_TABLE_ADDR;
	efi.acpi20     = EFI_INVALID_TABLE_ADDR;
	efi.smbios     = EFI_INVALID_TABLE_ADDR;
	efi.sal_systab = EFI_INVALID_TABLE_ADDR;
	efi.boot_info  = EFI_INVALID_TABLE_ADDR;
	efi.hcdp       = EFI_INVALID_TABLE_ADDR;
	efi.uga        = EFI_INVALID_TABLE_ADDR;

	for (i = 0; i < (int) efi.systab->nr_tables; i++) {
		if (efi_guidcmp(config_tables[i].guid, MPS_TABLE_GUID) == 0) {
			efi.mps = config_tables[i].table;
			printk(" MPS=0x%lx", config_tables[i].table);
		} else if (efi_guidcmp(config_tables[i].guid, ACPI_20_TABLE_GUID) == 0) {
			efi.acpi20 = config_tables[i].table;
			printk(" ACPI 2.0=0x%lx", config_tables[i].table);
		} else if (efi_guidcmp(config_tables[i].guid, ACPI_TABLE_GUID) == 0) {
			efi.acpi = config_tables[i].table;
			printk(" ACPI=0x%lx", config_tables[i].table);
		} else if (efi_guidcmp(config_tables[i].guid, SMBIOS_TABLE_GUID) == 0) {
			efi.smbios = config_tables[i].table;
			printk(" SMBIOS=0x%lx", config_tables[i].table);
		} else if (efi_guidcmp(config_tables[i].guid, SAL_SYSTEM_TABLE_GUID) == 0) {
			efi.sal_systab = config_tables[i].table;
			printk(" SALsystab=0x%lx", config_tables[i].table);
		} else if (efi_guidcmp(config_tables[i].guid, HCDP_TABLE_GUID) == 0) {
			efi.hcdp = config_tables[i].table;
			printk(" HCDP=0x%lx", config_tables[i].table);
		}
	}
	printk("\n");

	runtime = __va(efi.systab->runtime);
	efi.get_time = phys_get_time;
	efi.set_time = phys_set_time;
	efi.get_wakeup_time = phys_get_wakeup_time;
	efi.set_wakeup_time = phys_set_wakeup_time;
	efi.get_variable = phys_get_variable;
	efi.get_next_variable = phys_get_next_variable;
	efi.set_variable = phys_set_variable;
	efi.get_next_high_mono_count = phys_get_next_high_mono_count;
	efi.reset_system = phys_reset_system;

	efi_map_start = __va(ia64_boot_param->efi_memmap);
	efi_map_end   = efi_map_start + ia64_boot_param->efi_memmap_size;
	efi_desc_size = ia64_boot_param->efi_memdesc_size;

#if EFI_DEBUG
	/* print EFI memory map: */
	{
		efi_memory_desc_t *md;
		void *p;

		for (i = 0, p = efi_map_start; p < efi_map_end; ++i, p += efi_desc_size) {
			md = p;
			printk("mem%02u: type=%u, attr=0x%lx, range=[0x%016lx-0x%016lx) (%luMB)\n",
			       i, md->type, md->attribute, md->phys_addr,
			       md->phys_addr + efi_md_size(md),
			       md->num_pages >> (20 - EFI_PAGE_SHIFT));
		}
	}
#endif

	efi_map_pal_code();
	efi_enter_virtual_mode();
}

void
efi_enter_virtual_mode (void)
{
	void *efi_map_start, *efi_map_end, *p;
	efi_memory_desc_t *md;
	efi_status_t status;
	u64 efi_desc_size;

	efi_map_start = __va(ia64_boot_param->efi_memmap);
	efi_map_end   = efi_map_start + ia64_boot_param->efi_memmap_size;
	efi_desc_size = ia64_boot_param->efi_memdesc_size;

	for (p = efi_map_start; p < efi_map_end; p += efi_desc_size) {
		md = p;
		if (md->attribute & EFI_MEMORY_RUNTIME) {
			/*
			 * Some descriptors have multiple bits set, so the order of
			 * the tests is relevant.
			 */
			if (md->attribute & EFI_MEMORY_WB) {
				md->virt_addr = (u64) __va(md->phys_addr);
			} else if (md->attribute & EFI_MEMORY_UC) {
				md->virt_addr = (u64) ioremap(md->phys_addr, 0);
			} else if (md->attribute & EFI_MEMORY_WC) {
#if 0
				md->virt_addr = ia64_remap(md->phys_addr, (_PAGE_A | _PAGE_P
									   | _PAGE_D
									   | _PAGE_MA_WC
									   | _PAGE_PL_0
									   | _PAGE_AR_RW));
#else
				printk(KERN_INFO "EFI_MEMORY_WC mapping\n");
				md->virt_addr = (u64) ioremap(md->phys_addr, 0);
#endif
			} else if (md->attribute & EFI_MEMORY_WT) {
#if 0
				md->virt_addr = ia64_remap(md->phys_addr, (_PAGE_A | _PAGE_P
									   | _PAGE_D | _PAGE_MA_WT
									   | _PAGE_PL_0
									   | _PAGE_AR_RW));
#else
				printk(KERN_INFO "EFI_MEMORY_WT mapping\n");
				md->virt_addr = (u64) ioremap(md->phys_addr, 0);
#endif
			}
		}
	}

	status = efi_call_phys(__va(runtime->set_virtual_address_map),
			       ia64_boot_param->efi_memmap_size,
			       efi_desc_size, ia64_boot_param->efi_memdesc_version,
			       ia64_boot_param->efi_memmap);
	if (status != EFI_SUCCESS) {
		printk(KERN_WARNING "warning: unable to switch EFI into virtual mode "
		       "(status=%lu)\n", status);
		return;
	}

	/*
	 * Now that EFI is in virtual mode, we call the EFI functions more efficiently:
	 */
	efi.get_time = virt_get_time;
	efi.set_time = virt_set_time;
	efi.get_wakeup_time = virt_get_wakeup_time;
	efi.set_wakeup_time = virt_set_wakeup_time;
	efi.get_variable = virt_get_variable;
	efi.get_next_variable = virt_get_next_variable;
	efi.set_variable = virt_set_variable;
	efi.get_next_high_mono_count = virt_get_next_high_mono_count;
	efi.reset_system = virt_reset_system;
}

/*
 * Walk the EFI memory map looking for the I/O port range.  There can only be one entry of
 * this type, other I/O port ranges should be described via ACPI.
 */
u64
efi_get_iobase (void)
{
	void *efi_map_start, *efi_map_end, *p;
	efi_memory_desc_t *md;
	u64 efi_desc_size;

	efi_map_start = __va(ia64_boot_param->efi_memmap);
	efi_map_end   = efi_map_start + ia64_boot_param->efi_memmap_size;
	efi_desc_size = ia64_boot_param->efi_memdesc_size;

	for (p = efi_map_start; p < efi_map_end; p += efi_desc_size) {
		md = p;
		if (md->type == EFI_MEMORY_MAPPED_IO_PORT_SPACE) {
			if (md->attribute & EFI_MEMORY_UC)
				return md->phys_addr;
		}
	}
	return 0;
}

static struct kern_memdesc *
kern_memory_descriptor (unsigned long phys_addr)
{
	struct kern_memdesc *md;

	for (md = kern_memmap; md->start != ~0UL; md++) {
		if (phys_addr - md->start < (md->num_pages << EFI_PAGE_SHIFT))
			 return md;
	}
	return NULL;
}

static efi_memory_desc_t *
efi_memory_descriptor (unsigned long phys_addr)
{
	void *efi_map_start, *efi_map_end, *p;
	efi_memory_desc_t *md;
	u64 efi_desc_size;

	efi_map_start = __va(ia64_boot_param->efi_memmap);
	efi_map_end   = efi_map_start + ia64_boot_param->efi_memmap_size;
	efi_desc_size = ia64_boot_param->efi_memdesc_size;

	for (p = efi_map_start; p < efi_map_end; p += efi_desc_size) {
		md = p;

		if (phys_addr - md->phys_addr < efi_md_size(md))
			 return md;
	}
	return NULL;
}

static int
efi_memmap_intersects (unsigned long phys_addr, unsigned long size)
{
	void *efi_map_start, *efi_map_end, *p;
	efi_memory_desc_t *md;
	u64 efi_desc_size;
	unsigned long end;

	efi_map_start = __va(ia64_boot_param->efi_memmap);
	efi_map_end   = efi_map_start + ia64_boot_param->efi_memmap_size;
	efi_desc_size = ia64_boot_param->efi_memdesc_size;

	end = phys_addr + size;

	for (p = efi_map_start; p < efi_map_end; p += efi_desc_size) {
		md = p;

		if (md->phys_addr < end && efi_md_end(md) > phys_addr)
			return 1;
	}
	return 0;
}

u32
efi_mem_type (unsigned long phys_addr)
{
	efi_memory_desc_t *md = efi_memory_descriptor(phys_addr);

	if (md)
		return md->type;
	return 0;
}

u64
efi_mem_attributes (unsigned long phys_addr)
{
	efi_memory_desc_t *md = efi_memory_descriptor(phys_addr);

	if (md)
		return md->attribute;
	return 0;
}
EXPORT_SYMBOL(efi_mem_attributes);

u64
efi_mem_attribute (unsigned long phys_addr, unsigned long size)
{
	unsigned long end = phys_addr + size;
	efi_memory_desc_t *md = efi_memory_descriptor(phys_addr);
	u64 attr;

	if (!md)
		return 0;

	/*
	 * EFI_MEMORY_RUNTIME is not a memory attribute; it just tells
	 * the kernel that firmware needs this region mapped.
	 */
	attr = md->attribute & ~EFI_MEMORY_RUNTIME;
	do {
		unsigned long md_end = efi_md_end(md);

		if (end <= md_end)
			return attr;

		md = efi_memory_descriptor(md_end);
		if (!md || (md->attribute & ~EFI_MEMORY_RUNTIME) != attr)
			return 0;
	} while (md);
	return 0;
}

u64
kern_mem_attribute (unsigned long phys_addr, unsigned long size)
{
	unsigned long end = phys_addr + size;
	struct kern_memdesc *md;
	u64 attr;

	/*
	 * This is a hack for ioremap calls before we set up kern_memmap.
	 * Maybe we should do efi_memmap_init() earlier instead.
	 */
	if (!kern_memmap) {
		attr = efi_mem_attribute(phys_addr, size);
		if (attr & EFI_MEMORY_WB)
			return EFI_MEMORY_WB;
		return 0;
	}

	md = kern_memory_descriptor(phys_addr);
	if (!md)
		return 0;

	attr = md->attribute;
	do {
		unsigned long md_end = kmd_end(md);

		if (end <= md_end)
			return attr;

		md = kern_memory_descriptor(md_end);
		if (!md || md->attribute != attr)
			return 0;
	} while (md);
	return 0;
}
EXPORT_SYMBOL(kern_mem_attribute);

int
valid_phys_addr_range (unsigned long phys_addr, unsigned long size)
{
	u64 attr;

	/*
	 * /dev/mem reads and writes use copy_to_user(), which implicitly
	 * uses a granule-sized kernel identity mapping.  It's really
	 * only safe to do this for regions in kern_memmap.  For more
	 * details, see Documentation/ia64/aliasing.txt.
	 */
	attr = kern_mem_attribute(phys_addr, size);
	if (attr & EFI_MEMORY_WB || attr & EFI_MEMORY_UC)
		return 1;
	return 0;
}

int
valid_mmap_phys_addr_range (unsigned long pfn, unsigned long size)
{
	unsigned long phys_addr = pfn << PAGE_SHIFT;
	u64 attr;

	attr = efi_mem_attribute(phys_addr, size);

	/*
	 * /dev/mem mmap uses normal user pages, so we don't need the entire
	 * granule, but the entire region we're mapping must support the same
	 * attribute.
	 */
	if (attr & EFI_MEMORY_WB || attr & EFI_MEMORY_UC)
		return 1;

	/*
	 * Intel firmware doesn't tell us about all the MMIO regions, so
	 * in general we have to allow mmap requests.  But if EFI *does*
	 * tell us about anything inside this region, we should deny it.
	 * The user can always map a smaller region to avoid the overlap.
	 */
	if (efi_memmap_intersects(phys_addr, size))
		return 0;

	return 1;
}

pgprot_t
phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size,
		     pgprot_t vma_prot)
{
	unsigned long phys_addr = pfn << PAGE_SHIFT;
	u64 attr;

	/*
	 * For /dev/mem mmap, we use user mappings, but if the region is
	 * in kern_memmap (and hence may be covered by a kernel mapping),
	 * we must use the same attribute as the kernel mapping.
	 */
	attr = kern_mem_attribute(phys_addr, size);
	if (attr & EFI_MEMORY_WB)
		return pgprot_cacheable(vma_prot);
	else if (attr & EFI_MEMORY_UC)
		return pgprot_noncached(vma_prot);

	/*
	 * Some chipsets don't support UC access to memory.  If
	 * WB is supported, we prefer that.
	 */