efi.c

linux2.6.16版本

			 * 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 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 < (md->num_pages << EFI_PAGE_SHIFT))
			 return md;
	}
	return 0;
}

static int
efi_memmap_has_mmio (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)
			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);

/*
 * Determines whether the memory at phys_addr supports the desired
 * attribute (WB, UC, etc).  If this returns 1, the caller can safely
 * access *size bytes at phys_addr with the specified attribute.
 */
static int
efi_mem_attribute_range (unsigned long phys_addr, unsigned long *size, u64 attr)
{
	efi_memory_desc_t *md = efi_memory_descriptor(phys_addr);
	unsigned long md_end;

	if (!md || (md->attribute & attr) != attr)
		return 0;

	do {
		md_end = efi_md_end(md);
		if (phys_addr + *size <= md_end)
			return 1;

		md = efi_memory_descriptor(md_end);
		if (!md || (md->attribute & attr) != attr) {
			*size = md_end - phys_addr;
			return 1;
		}
	} while (md);
	return 0;
}

/*
 * For /dev/mem, we only allow read & write system calls to access
 * write-back memory, because read & write don't allow the user to
 * control access size.
 */
int
valid_phys_addr_range (unsigned long phys_addr, unsigned long *size)
{
	return efi_mem_attribute_range(phys_addr, size, EFI_MEMORY_WB);
}

/*
 * We allow mmap of anything in the EFI memory map that supports
 * either write-back or uncacheable access.  For uncacheable regions,
 * the supported access sizes are system-dependent, and the user is
 * responsible for using the correct size.
 *
 * Note that this doesn't currently allow access to hot-added memory,
 * because that doesn't appear in the boot-time EFI memory map.
 */
int
valid_mmap_phys_addr_range (unsigned long phys_addr, unsigned long *size)
{
	if (efi_mem_attribute_range(phys_addr, size, EFI_MEMORY_WB))
		return 1;

	if (efi_mem_attribute_range(phys_addr, size, EFI_MEMORY_UC))
		return 1;

	/*
	 * Some firmware doesn't report MMIO regions in the EFI memory map.
	 * The Intel BigSur (a.k.a. HP i2000) has this problem.  In this
	 * case, we can't use the EFI memory map to validate mmap requests.
	 */
	if (!efi_memmap_has_mmio())
		return 1;

	return 0;
}

int __init
efi_uart_console_only(void)
{
	efi_status_t status;
	char *s, name[] = "ConOut";
	efi_guid_t guid = EFI_GLOBAL_VARIABLE_GUID;
	efi_char16_t *utf16, name_utf16[32];
	unsigned char data[1024];
	unsigned long size = sizeof(data);
	struct efi_generic_dev_path *hdr, *end_addr;
	int uart = 0;

	/* Convert to UTF-16 */
	utf16 = name_utf16;
	s = name;
	while (*s)
		*utf16++ = *s++ & 0x7f;
	*utf16 = 0;

	status = efi.get_variable(name_utf16, &guid, NULL, &size, data);
	if (status != EFI_SUCCESS) {
		printk(KERN_ERR "No EFI %s variable?\n", name);
		return 0;
	}

	hdr = (struct efi_generic_dev_path *) data;
	end_addr = (struct efi_generic_dev_path *) ((u8 *) data + size);
	while (hdr < end_addr) {
		if (hdr->type == EFI_DEV_MSG &&
		    hdr->sub_type == EFI_DEV_MSG_UART)
			uart = 1;
		else if (hdr->type == EFI_DEV_END_PATH ||
			  hdr->type == EFI_DEV_END_PATH2) {
			if (!uart)
				return 0;
			if (hdr->sub_type == EFI_DEV_END_ENTIRE)
				return 1;
			uart = 0;
		}
		hdr = (struct efi_generic_dev_path *) ((u8 *) hdr + hdr->length);
	}
	printk(KERN_ERR "Malformed %s value\n", name);
	return 0;
}

/*
 * Look for the first granule aligned memory descriptor memory
 * that is big enough to hold EFI memory map. Make sure this
 * descriptor is atleast granule sized so it does not get trimmed
 */
struct kern_memdesc *
find_memmap_space (void)
{
	u64	contig_low=0, contig_high=0;
	u64	as = 0, ae;
	void *efi_map_start, *efi_map_end, *p, *q;
	efi_memory_desc_t *md, *pmd = NULL, *check_md;
	u64	space_needed, efi_desc_size;
	unsigned long total_mem = 0;

	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;

	/*
	 * Worst case: we need 3 kernel descriptors for each efi descriptor
	 * (if every entry has a WB part in the middle, and UC head and tail),
	 * plus one for the end marker.
	 */
	space_needed = sizeof(kern_memdesc_t) *
		(3 * (ia64_boot_param->efi_memmap_size/efi_desc_size) + 1);

	for (p = efi_map_start; p < efi_map_end; pmd = md, p += efi_desc_size) {
		md = p;
		if (!efi_wb(md)) {
			continue;
		}
		if (pmd == NULL || !efi_wb(pmd) || efi_md_end(pmd) != md->phys_addr) {
			contig_low = GRANULEROUNDUP(md->phys_addr);
			contig_high = efi_md_end(md);
			for (q = p + efi_desc_size; q < efi_map_end; q += efi_desc_size) {
				check_md = q;
				if (!efi_wb(check_md))
					break;
				if (contig_high != check_md->phys_addr)
					break;
				contig_high = efi_md_end(check_md);
			}
			contig_high = GRANULEROUNDDOWN(contig_high);
		}
		if (!is_available_memory(md) || md->type == EFI_LOADER_DATA)
			continue;

		/* Round ends inward to granule boundaries */
		as = max(contig_low, md->phys_addr);
		ae = min(contig_high, efi_md_end(md));

		/* keep within max_addr= command line arg */
		ae = min(ae, max_addr);
		if (ae <= as)
			continue;

		/* avoid going over mem= command line arg */
		if (total_mem + (ae - as) > mem_limit)
			ae -= total_mem + (ae - as) - mem_limit;

		if (ae <= as)
			continue;

		if (ae - as > space_needed)
			break;
	}
	if (p >= efi_map_end)
		panic("Can't allocate space for kernel memory descriptors");

	return __va(as);
}

/*
 * Walk the EFI memory map and gather all memory available for kernel
 * to use.  We can allocate partial granules only if the unavailable
 * parts exist, and are WB.
 */
void
efi_memmap_init(unsigned long *s, unsigned long *e)
{
	struct kern_memdesc *k, *prev = 0;
	u64	contig_low=0, contig_high=0;
	u64	as, ae, lim;
	void *efi_map_start, *efi_map_end, *p, *q;
	efi_memory_desc_t *md, *pmd = NULL, *check_md;
	u64	efi_desc_size;
	unsigned long total_mem = 0;

	k = kern_memmap = find_memmap_space();

	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; pmd = md, p += efi_desc_size) {
		md = p;
		if (!efi_wb(md)) {
			if (efi_uc(md) && (md->type == EFI_CONVENTIONAL_MEMORY ||
				    	   md->type == EFI_BOOT_SERVICES_DATA)) {
				k->attribute = EFI_MEMORY_UC;
				k->start = md->phys_addr;
				k->num_pages = md->num_pages;
				k++;
			}
			continue;
		}
		if (pmd == NULL || !efi_wb(pmd) || efi_md_end(pmd) != md->phys_addr) {
			contig_low = GRANULEROUNDUP(md->phys_addr);
			contig_high = efi_md_end(md);
			for (q = p + efi_desc_size; q < efi_map_end; q += efi_desc_size) {
				check_md = q;
				if (!efi_wb(check_md))
					break;
				if (contig_high != check_md->phys_addr)
					break;
				contig_high = efi_md_end(check_md);
			}
			contig_high = GRANULEROUNDDOWN(contig_high);
		}
		if (!is_available_memory(md))
			continue;

		/*
		 * Round ends inward to granule boundaries
		 * Give trimmings to uncached allocator
		 */
		if (md->phys_addr < contig_low) {
			lim = min(efi_md_end(md), contig_low);
			if (efi_uc(md)) {
				if (k > kern_memmap && (k-1)->attribute == EFI_MEMORY_UC &&
				    kmd_end(k-1) == md->phys_addr) {
					(k-1)->num_pages += (lim - md->phys_addr) >> EFI_PAGE_SHIFT;
				} else {
					k->attribute = EFI_MEMORY_UC;
					k->start = md->phys_addr;
					k->num_pages = (lim - md->phys_addr) >> EFI_PAGE_SHIFT;
					k++;
				}
			}
			as = contig_low;
		} else
			as = md->phys_addr;

		if (efi_md_end(md) > contig_high) {
			lim = max(md->phys_addr, contig_high);
			if (efi_uc(md)) {
				if (lim == md->phys_addr && k > kern_memmap &&
				    (k-1)->attribute == EFI_MEMORY_UC &&
				    kmd_end(k-1) == md->phys_addr) {
					(k-1)->num_pages += md->num_pages;
				} else {
					k->attribute = EFI_MEMORY_UC;
					k->start = lim;
					k->num_pages = (efi_md_end(md) - lim) >> EFI_PAGE_SHIFT;
					k++;
				}
			}
			ae = contig_high;
		} else
			ae = efi_md_end(md);

		/* keep within max_addr= command line arg */
		ae = min(ae, max_addr);
		if (ae <= as)
			continue;

		/* avoid going over mem= command line arg */
		if (total_mem + (ae - as) > mem_limit)
			ae -= total_mem + (ae - as) - mem_limit;

		if (ae <= as)
			continue;
		if (prev && kmd_end(prev) == md->phys_addr) {
			prev->num_pages += (ae - as) >> EFI_PAGE_SHIFT;
			total_mem += ae - as;
			continue;
		}
		k->attribute = EFI_MEMORY_WB;
		k->start = as;
		k->num_pages = (ae - as) >> EFI_PAGE_SHIFT;
		total_mem += ae - as;
		prev = k++;
	}
	k->start = ~0L; /* end-marker */

	/* reserve the memory we are using for kern_memmap */
	*s = (u64)kern_memmap;
	*e = (u64)++k;
}

void
efi_initialize_iomem_resources(struct resource *code_resource,
			       struct resource *data_resource)
{
	struct resource *res;
	void *efi_map_start, *efi_map_end, *p;
	efi_memory_desc_t *md;
	u64 efi_desc_size;
	char *name;
	unsigned long flags;

	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;

	res = NULL;

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

		if (md->num_pages == 0) /* should not happen */
			continue;

		flags = IORESOURCE_MEM;
		switch (md->type) {

			case EFI_MEMORY_MAPPED_IO:
			case EFI_MEMORY_MAPPED_IO_PORT_SPACE:
				continue;

			case EFI_LOADER_CODE:
			case EFI_LOADER_DATA:
			case EFI_BOOT_SERVICES_DATA:
			case EFI_BOOT_SERVICES_CODE:
			case EFI_CONVENTIONAL_MEMORY:
				if (md->attribute & EFI_MEMORY_WP) {
					name = "System ROM";
					flags |= IORESOURCE_READONLY;
				} else {
					name = "System RAM";
				}
				break;

			case EFI_ACPI_MEMORY_NVS:
				name = "ACPI Non-volatile Storage";
				flags |= IORESOURCE_BUSY;
				break;

			case EFI_UNUSABLE_MEMORY:
				name = "reserved";
				flags |= IORESOURCE_BUSY | IORESOURCE_DISABLED;
				break;

			case EFI_RESERVED_TYPE:
			case EFI_RUNTIME_SERVICES_CODE:
			case EFI_RUNTIME_SERVICES_DATA:
			case EFI_ACPI_RECLAIM_MEMORY:
			default:
				name = "reserved";
				flags |= IORESOURCE_BUSY;
				break;
		}

		if ((res = kzalloc(sizeof(struct resource), GFP_KERNEL)) == NULL) {
			printk(KERN_ERR "failed to alocate resource for iomem\n");
			return;
		}

		res->name = name;
		res->start = md->phys_addr;
		res->end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT) - 1;
		res->flags = flags;

		if (insert_resource(&iomem_resource, res) < 0)
			kfree(res);
		else {
			/*
			 * We don't know which region contains
			 * kernel data so we try it repeatedly and
			 * let the resource manager test it.
			 */
			insert_resource(res, code_resource);
			insert_resource(res, data_resource);
		}
	}
}