Merge branch 'x86-efi-kexec-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 EFI changes from Ingo Molnar:
 "This consists of two main parts:

   - New static EFI runtime services virtual mapping layout which is
     groundwork for kexec support on EFI (Borislav Petkov)

   - EFI kexec support itself (Dave Young)"

* 'x86-efi-kexec-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (24 commits)
  x86/efi: parse_efi_setup() build fix
  x86: ksysfs.c build fix
  x86/efi: Delete superfluous global variables
  x86: Reserve setup_data ranges late after parsing memmap cmdline
  x86: Export x86 boot_params to sysfs
  x86: Add xloadflags bit for EFI runtime support on kexec
  x86/efi: Pass necessary EFI data for kexec via setup_data
  efi: Export EFI runtime memory mapping to sysfs
  efi: Export more EFI table variables to sysfs
  x86/efi: Cleanup efi_enter_virtual_mode() function
  x86/efi: Fix off-by-one bug in EFI Boot Services reservation
  x86/efi: Add a wrapper function efi_map_region_fixed()
  x86/efi: Remove unused variables in __map_region()
  x86/efi: Check krealloc return value
  x86/efi: Runtime services virtual mapping
  x86/mm/cpa: Map in an arbitrary pgd
  x86/mm/pageattr: Add last levels of error path
  x86/mm/pageattr: Add a PUD error unwinding path
  x86/mm/pageattr: Add a PTE pagetable populating function
  x86/mm/pageattr: Add a PMD pagetable populating function
  ...

Documentation/ABI/testing/sysfs-firmware-efi

+What:		/sys/firmware/efi/fw_vendor
+Date:		December 2013
+Contact:	Dave Young <dyoung@redhat.com>
+Description:	It shows the physical address of firmware vendor field in the
+		EFI system table.
+Users:		Kexec
+
+What:		/sys/firmware/efi/runtime
+Date:		December 2013
+Contact:	Dave Young <dyoung@redhat.com>
+Description:	It shows the physical address of runtime service table entry in
+		the EFI system table.
+Users:		Kexec
+
+What:		/sys/firmware/efi/config_table
+Date:		December 2013
+Contact:	Dave Young <dyoung@redhat.com>
+Description:	It shows the physical address of config table entry in the EFI
+		system table.
+Users:		Kexec

Documentation/ABI/testing/sysfs-firmware-efi-runtime-map

+What:		/sys/firmware/efi/runtime-map/
+Date:		December 2013
+Contact:	Dave Young <dyoung@redhat.com>
+Description:	Switching efi runtime services to virtual mode requires
+		that all efi memory ranges which have the runtime attribute
+		bit set to be mapped to virtual addresses.
+
+		The efi runtime services can only be switched to virtual
+		mode once without rebooting. The kexec kernel must maintain
+		the same physical to virtual address mappings as the first
+		kernel. The mappings are exported to sysfs so userspace tools
+		can reassemble them and pass them into the kexec kernel.
+
+		/sys/firmware/efi/runtime-map/ is the directory the kernel
+		exports that information in.
+
+		subdirectories are named with the number of the memory range:
+
+			/sys/firmware/efi/runtime-map/0
+			/sys/firmware/efi/runtime-map/1
+			/sys/firmware/efi/runtime-map/2
+			/sys/firmware/efi/runtime-map/3
+			...
+
+		Each subdirectory contains five files:
+
+		attribute : The attributes of the memory range.
+		num_pages : The size of the memory range in pages.
+		phys_addr : The physical address of the memory range.
+		type      : The type of the memory range.
+		virt_addr : The virtual address of the memory range.
+
+		Above values are all hexadecimal numbers with the '0x' prefix.
+Users:		Kexec

Documentation/ABI/testing/sysfs-kernel-boot_params

+What:		/sys/kernel/boot_params
+Date:		December 2013
+Contact:	Dave Young <dyoung@redhat.com>
+Description:	The /sys/kernel/boot_params directory contains two
+		files: "data" and "version" and one subdirectory "setup_data".
+		It is used to export the kernel boot parameters of an x86
+		platform to userspace for kexec and debugging purpose.
+
+		If there's no setup_data in boot_params the subdirectory will
+		not be created.
+
+		"data" file is the binary representation of struct boot_params.
+
+		"version" file is the string representation of boot
+		protocol version.
+
+		"setup_data" subdirectory contains the setup_data data
+		structure in boot_params. setup_data is maintained in kernel
+		as a link list. In "setup_data" subdirectory there's one
+		subdirectory for each link list node named with the number
+		of the list nodes. The list node subdirectory contains two
+		files "type" and "data". "type" file is the string
+		representation of setup_data type. "data" file is the binary
+		representation of setup_data payload.
+
+		The whole boot_params directory structure is like below:
+		/sys/kernel/boot_params
+		|__ data
+		|__ setup_data
+		|   |__ 0
+		|   |   |__ data
+		|   |   |__ type
+		|   |__ 1
+		|       |__ data
+		|       |__ type
+		|__ version
+
+Users:		Kexec

Documentation/kernel-parameters.txt

@@ -899,6 +899,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	edd=		[EDD]
 			Format: {"off" | "on" | "skip[mbr]"}
 
+	efi=		[EFI]
+			Format: { "old_map" }
+			old_map [X86-64]: switch to the old ioremap-based EFI
+			runtime services mapping. 32-bit still uses this one by
+			default.
+
 	efi_no_storage_paranoia [EFI; X86]
 			Using this parameter you can use more than 50% of
 			your efi variable storage. Use this parameter only if

Documentation/x86/boot.txt

@@ -608,6 +608,9 @@ Protocol:       2.12+
 	- If 1, the kernel supports the 64-bit EFI handoff entry point
           given at handover_offset + 0x200.
 
+  Bit 4 (read): XLF_EFI_KEXEC
+	- If 1, the kernel supports kexec EFI boot with EFI runtime support.
+
 Field name:	cmdline_size
 Type:		read
 Offset/size:	0x238/4

Documentation/x86/x86_64/mm.txt

@@ -28,4 +28,11 @@ reference.
 Current X86-64 implementations only support 40 bits of address space,
 but we support up to 46 bits. This expands into MBZ space in the page tables.
 
+->trampoline_pgd:
+
+We map EFI runtime services in the aforementioned PGD in the virtual
+range of 64Gb (arbitrarily set, can be raised if needed)
+
+0xffffffef00000000 - 0xffffffff00000000
+
 -Andi Kleen, Jul 2004

arch/x86/boot/header.S

@@ -391,7 +391,14 @@ xloadflags:
 #else
 # define XLF23 0
 #endif
-			.word XLF0 | XLF1 | XLF23
+
+#if defined(CONFIG_X86_64) && defined(CONFIG_EFI) && defined(CONFIG_KEXEC)
+# define XLF4 XLF_EFI_KEXEC
+#else
+# define XLF4 0
+#endif
+
+			.word XLF0 | XLF1 | XLF23 | XLF4
 
 cmdline_size:   .long   COMMAND_LINE_SIZE-1     #length of the command line,
                                                 #added with boot protocol

arch/x86/include/asm/efi.h

 #ifndef _ASM_X86_EFI_H
 #define _ASM_X86_EFI_H
 
+/*
+ * We map the EFI regions needed for runtime services non-contiguously,
+ * with preserved alignment on virtual addresses starting from -4G down
+ * for a total max space of 64G. This way, we provide for stable runtime
+ * services addresses across kernels so that a kexec'd kernel can still
+ * use them.
+ *
+ * This is the main reason why we're doing stable VA mappings for RT
+ * services.
+ *
+ * This flag is used in conjuction with a chicken bit called
+ * "efi=old_map" which can be used as a fallback to the old runtime
+ * services mapping method in case there's some b0rkage with a
+ * particular EFI implementation (haha, it is hard to hold up the
+ * sarcasm here...).
+ */
+#define EFI_OLD_MEMMAP		EFI_ARCH_1
+
 #ifdef CONFIG_X86_32
 
 #define EFI_LOADER_SIGNATURE	"EL32"
@@ -69,24 +87,31 @@ extern u64 efi_call6(void *fp, u64 arg1, u64 arg2, u64 arg3,
 	efi_call6((f), (u64)(a1), (u64)(a2), (u64)(a3),		\
 		  (u64)(a4), (u64)(a5), (u64)(a6))
 
+#define _efi_call_virtX(x, f, ...)					\
+({									\
+	efi_status_t __s;						\
+									\
+	efi_sync_low_kernel_mappings();					\
+	preempt_disable();						\
+	__s = efi_call##x((void *)efi.systab->runtime->f, __VA_ARGS__);	\
+	preempt_enable();						\
+	__s;								\
+})
+
 #define efi_call_virt0(f)				\
-	efi_call0((efi.systab->runtime->f))
-#define efi_call_virt1(f, a1)					\
-	efi_call1((efi.systab->runtime->f), (u64)(a1))
-#define efi_call_virt2(f, a1, a2)					\
-	efi_call2((efi.systab->runtime->f), (u64)(a1), (u64)(a2))
-#define efi_call_virt3(f, a1, a2, a3)					\
-	efi_call3((efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
-		  (u64)(a3))
-#define efi_call_virt4(f, a1, a2, a3, a4)				\
-	efi_call4((efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
-		  (u64)(a3), (u64)(a4))
-#define efi_call_virt5(f, a1, a2, a3, a4, a5)				\
-	efi_call5((efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
-		  (u64)(a3), (u64)(a4), (u64)(a5))
-#define efi_call_virt6(f, a1, a2, a3, a4, a5, a6)			\
-	efi_call6((efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
-		  (u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6))
+	_efi_call_virtX(0, f)
+#define efi_call_virt1(f, a1)				\
+	_efi_call_virtX(1, f, (u64)(a1))
+#define efi_call_virt2(f, a1, a2)			\
+	_efi_call_virtX(2, f, (u64)(a1), (u64)(a2))
+#define efi_call_virt3(f, a1, a2, a3)			\
+	_efi_call_virtX(3, f, (u64)(a1), (u64)(a2), (u64)(a3))
+#define efi_call_virt4(f, a1, a2, a3, a4)		\
+	_efi_call_virtX(4, f, (u64)(a1), (u64)(a2), (u64)(a3), (u64)(a4))
+#define efi_call_virt5(f, a1, a2, a3, a4, a5)		\
+	_efi_call_virtX(5, f, (u64)(a1), (u64)(a2), (u64)(a3), (u64)(a4), (u64)(a5))
+#define efi_call_virt6(f, a1, a2, a3, a4, a5, a6)	\
+	_efi_call_virtX(6, f, (u64)(a1), (u64)(a2), (u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6))
 
 extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,
 				 u32 type, u64 attribute);
@@ -95,12 +120,28 @@ extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,
 
 extern int add_efi_memmap;
 extern unsigned long x86_efi_facility;
+extern struct efi_scratch efi_scratch;
 extern void efi_set_executable(efi_memory_desc_t *md, bool executable);
 extern int efi_memblock_x86_reserve_range(void);
 extern void efi_call_phys_prelog(void);
 extern void efi_call_phys_epilog(void);
 extern void efi_unmap_memmap(void);
 extern void efi_memory_uc(u64 addr, unsigned long size);
+extern void __init efi_map_region(efi_memory_desc_t *md);
+extern void __init efi_map_region_fixed(efi_memory_desc_t *md);
+extern void efi_sync_low_kernel_mappings(void);
+extern void efi_setup_page_tables(void);
+extern void __init old_map_region(efi_memory_desc_t *md);
+
+struct efi_setup_data {
+	u64 fw_vendor;
+	u64 runtime;
+	u64 tables;
+	u64 smbios;
+	u64 reserved[8];
+};
+
+extern u64 efi_setup;
 
 #ifdef CONFIG_EFI
 
@@ -110,7 +151,7 @@ static inline bool efi_is_native(void)
 }
 
 extern struct console early_efi_console;
-
+extern void parse_efi_setup(u64 phys_addr, u32 data_len);
 #else
 /*
  * IF EFI is not configured, have the EFI calls return -ENOSYS.
@@ -122,6 +163,7 @@ extern struct console early_efi_console;
 #define efi_call4(_f, _a1, _a2, _a3, _a4)		(-ENOSYS)
 #define efi_call5(_f, _a1, _a2, _a3, _a4, _a5)		(-ENOSYS)
 #define efi_call6(_f, _a1, _a2, _a3, _a4, _a5, _a6)	(-ENOSYS)
+static inline void parse_efi_setup(u64 phys_addr, u32 data_len) {}
 #endif /* CONFIG_EFI */
 
 #endif /* _ASM_X86_EFI_H */

arch/x86/include/asm/pgtable_types.h

@@ -382,7 +382,8 @@ static inline void update_page_count(int level, unsigned long pages) { }
  */
 extern pte_t *lookup_address(unsigned long address, unsigned int *level);
 extern phys_addr_t slow_virt_to_phys(void *__address);
-
+extern int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
+				   unsigned numpages, unsigned long page_flags);
 #endif	/* !__ASSEMBLY__ */
 
 #endif /* _ASM_X86_PGTABLE_DEFS_H */

arch/x86/include/uapi/asm/bootparam.h

@@ -6,6 +6,7 @@
 #define SETUP_E820_EXT			1
 #define SETUP_DTB			2
 #define SETUP_PCI			3
+#define SETUP_EFI			4
 
 /* ram_size flags */
 #define RAMDISK_IMAGE_START_MASK	0x07FF
@@ -23,6 +24,7 @@
 #define XLF_CAN_BE_LOADED_ABOVE_4G	(1<<1)
 #define XLF_EFI_HANDOVER_32		(1<<2)
 #define XLF_EFI_HANDOVER_64		(1<<3)
+#define XLF_EFI_KEXEC			(1<<4)
 
 #ifndef __ASSEMBLY__
 

arch/x86/kernel/Makefile

@@ -29,6 +29,7 @@ obj-$(CONFIG_X86_64)	+= sys_x86_64.o x8664_ksyms_64.o
 obj-y			+= syscall_$(BITS).o
 obj-$(CONFIG_X86_64)	+= vsyscall_64.o
 obj-$(CONFIG_X86_64)	+= vsyscall_emu_64.o
+obj-$(CONFIG_SYSFS)	+= ksysfs.o
 obj-y			+= bootflag.o e820.o
 obj-y			+= pci-dma.o quirks.o topology.o kdebugfs.o
 obj-y			+= alternative.o i8253.o pci-nommu.o hw_breakpoint.o

arch/x86/kernel/ksysfs.c

+/*
+ * Architecture specific sysfs attributes in /sys/kernel
+ *
+ * Copyright (C) 2007, Intel Corp.
+ *      Huang Ying <ying.huang@intel.com>
+ * Copyright (C) 2013, 2013 Red Hat, Inc.
+ *      Dave Young <dyoung@redhat.com>
+ *
+ * This file is released under the GPLv2
+ */
+
+#include <linux/kobject.h>
+#include <linux/string.h>
+#include <linux/sysfs.h>
+#include <linux/init.h>
+#include <linux/stat.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+
+#include <asm/io.h>
+#include <asm/setup.h>
+
+static ssize_t version_show(struct kobject *kobj,
+			    struct kobj_attribute *attr, char *buf)
+{
+	return sprintf(buf, "0x%04x\n", boot_params.hdr.version);
+}
+
+static struct kobj_attribute boot_params_version_attr = __ATTR_RO(version);
+
+static ssize_t boot_params_data_read(struct file *fp, struct kobject *kobj,
+				     struct bin_attribute *bin_attr,
+				     char *buf, loff_t off, size_t count)
+{
+	memcpy(buf, (void *)&boot_params + off, count);
+	return count;
+}
+
+static struct bin_attribute boot_params_data_attr = {
+	.attr = {
+		.name = "data",
+		.mode = S_IRUGO,
+	},
+	.read = boot_params_data_read,
+	.size = sizeof(boot_params),
+};
+
+static struct attribute *boot_params_version_attrs[] = {
+	&boot_params_version_attr.attr,
+	NULL,
+};
+
+static struct bin_attribute *boot_params_data_attrs[] = {
+	&boot_params_data_attr,
+	NULL,
+};
+
+static struct attribute_group boot_params_attr_group = {
+	.attrs = boot_params_version_attrs,
+	.bin_attrs = boot_params_data_attrs,
+};
+
+static int kobj_to_setup_data_nr(struct kobject *kobj, int *nr)
+{
+	const char *name;
+
+	name = kobject_name(kobj);
+	return kstrtoint(name, 10, nr);
+}
+
+static int get_setup_data_paddr(int nr, u64 *paddr)
+{
+	int i = 0;
+	struct setup_data *data;
+	u64 pa_data = boot_params.hdr.setup_data;
+
+	while (pa_data) {
+		if (nr == i) {
+			*paddr = pa_data;
+			return 0;
+		}
+		data = ioremap_cache(pa_data, sizeof(*data));
+		if (!data)
+			return -ENOMEM;
+
+		pa_data = data->next;
+		iounmap(data);
+		i++;
+	}
+	return -EINVAL;
+}
+
+static int __init get_setup_data_size(int nr, size_t *size)
+{
+	int i = 0;
+	struct setup_data *data;
+	u64 pa_data = boot_params.hdr.setup_data;
+
+	while (pa_data) {
+		data = ioremap_cache(pa_data, sizeof(*data));
+		if (!data)
+			return -ENOMEM;
+		if (nr == i) {
+			*size = data->len;
+			iounmap(data);
+			return 0;
+		}
+
+		pa_data = data->next;
+		iounmap(data);
+		i++;
+	}
+	return -EINVAL;
+}
+
+static ssize_t type_show(struct kobject *kobj,
+			 struct kobj_attribute *attr, char *buf)
+{
+	int nr, ret;
+	u64 paddr;
+	struct setup_data *data;
+
+	ret = kobj_to_setup_data_nr(kobj, &nr);
+	if (ret)
+		return ret;
+
+	ret = get_setup_data_paddr(nr, &paddr);
+	if (ret)
+		return ret;
+	data = ioremap_cache(paddr, sizeof(*data));
+	if (!data)
+		return -ENOMEM;
+
+	ret = sprintf(buf, "0x%x\n", data->type);
+	iounmap(data);
+	return ret;
+}
+
+static ssize_t setup_data_data_read(struct file *fp,
+				    struct kobject *kobj,
+				    struct bin_attribute *bin_attr,
+				    char *buf,
+				    loff_t off, size_t count)
+{
+	int nr, ret = 0;
+	u64 paddr;
+	struct setup_data *data;
+	void *p;
+
+	ret = kobj_to_setup_data_nr(kobj, &nr);
+	if (ret)
+		return ret;
+
+	ret = get_setup_data_paddr(nr, &paddr);
+	if (ret)
+		return ret;
+	data = ioremap_cache(paddr, sizeof(*data));
+	if (!data)
+		return -ENOMEM;
+
+	if (off > data->len) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (count > data->len - off)
+		count = data->len - off;
+
+	if (!count)
+		goto out;
+
+	ret = count;
+	p = ioremap_cache(paddr + sizeof(*data), data->len);
+	if (!p) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	memcpy(buf, p + off, count);
+	iounmap(p);
+out:
+	iounmap(data);
+	return ret;
+}
+
+static struct kobj_attribute type_attr = __ATTR_RO(type);
+
+static struct bin_attribute data_attr = {
+	.attr = {
+		.name = "data",
+		.mode = S_IRUGO,
+	},
+	.read = setup_data_data_read,
+};
+
+static struct attribute *setup_data_type_attrs[] = {
+	&type_attr.attr,
+	NULL,
+};
+
+static struct bin_attribute *setup_data_data_attrs[] = {
+	&data_attr,
+	NULL,
+};
+
+static struct attribute_group setup_data_attr_group = {
+	.attrs = setup_data_type_attrs,
+	.bin_attrs = setup_data_data_attrs,
+};
+
+static int __init create_setup_data_node(struct kobject *parent,
+					 struct kobject **kobjp, int nr)
+{
+	int ret = 0;
+	size_t size;
+	struct kobject *kobj;
+	char name[16]; /* should be enough for setup_data nodes numbers */
+	snprintf(name, 16, "%d", nr);
+
+	kobj = kobject_create_and_add(name, parent);
+	if (!kobj)
+		return -ENOMEM;
+
+	ret = get_setup_data_size(nr, &size);
+	if (ret)
+		goto out_kobj;
+
+	data_attr.size = size;
+	ret = sysfs_create_group(kobj, &setup_data_attr_group);
+	if (ret)
+		goto out_kobj;
+	*kobjp = kobj;
+
+	return 0;
+out_kobj:
+	kobject_put(kobj);
+	return ret;
+}
+
+static void __init cleanup_setup_data_node(struct kobject *kobj)
+{
+	sysfs_remove_group(kobj, &setup_data_attr_group);
+	kobject_put(kobj);
+}
+
+static int __init get_setup_data_total_num(u64 pa_data, int *nr)
+{
+	int ret = 0;
+	struct setup_data *data;
+
+	*nr = 0;
+	while (pa_data) {
+		*nr += 1;
+		data = ioremap_cache(pa_data, sizeof(*data));
+		if (!data) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		pa_data = data->next;
+		iounmap(data);
+	}
+
+out:
+	return ret;
+}
+
+static int __init create_setup_data_nodes(struct kobject *parent)
+{
+	struct kobject *setup_data_kobj, **kobjp;
+	u64 pa_data;
+	int i, j, nr, ret = 0;
+
+	pa_data = boot_params.hdr.setup_data;
+	if (!pa_data)
+		return 0;
+
+	setup_data_kobj = kobject_create_and_add("setup_data", parent);
+	if (!setup_data_kobj) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = get_setup_data_total_num(pa_data, &nr);
+	if (ret)
+		goto out_setup_data_kobj;
+
+	kobjp = kmalloc(sizeof(*kobjp) * nr, GFP_KERNEL);
+	if (!kobjp) {
+		ret = -ENOMEM;
+		goto out_setup_data_kobj;
+	}
+
+	for (i = 0; i < nr; i++) {
+		ret = create_setup_data_node(setup_data_kobj, kobjp + i, i);
+		if (ret)
+			goto out_clean_nodes;
+	}
+
+	kfree(kobjp);
+	return 0;
+
+out_clean_nodes:
+	for (j = i - 1; j > 0; j--)
+		cleanup_setup_data_node(*(kobjp + j));
+	kfree(kobjp);
+out_setup_data_kobj:
+	kobject_put(setup_data_kobj);
+out:
+	return ret;
+}
+
+static int __init boot_params_ksysfs_init(void)
+{
+	int ret;
+	struct kobject *boot_params_kobj;
+
+	boot_params_kobj = kobject_create_and_add("boot_params",
+						  kernel_kobj);
+	if (!boot_params_kobj) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = sysfs_create_group(boot_params_kobj, &boot_params_attr_group);
+	if (ret)
+		goto out_boot_params_kobj;
+
+	ret = create_setup_data_nodes(boot_params_kobj);
+	if (ret)
+		goto out_create_group;
+
+	return 0;
+out_create_group:
+	sysfs_remove_group(boot_params_kobj, &boot_params_attr_group);
+out_boot_params_kobj:
+	kobject_put(boot_params_kobj);
+out:
+	return ret;
+}
+
+arch_initcall(boot_params_ksysfs_init);

arch/x86/kernel/setup.c

@@ -447,6 +447,9 @@ static void __init parse_setup_data(void)
 		case SETUP_DTB:
 			add_dtb(pa_data);
 			break;
+		case SETUP_EFI:
+			parse_efi_setup(pa_data, data_len);
+			break;
 		default:
 			break;
 		}
@@ -924,8 +927,6 @@ 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();
 
@@ -987,6 +988,8 @@ 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))

arch/x86/platform/efi/efi_32.c

@@ -37,9 +37,19 @@
  * claim EFI runtime service handler exclusively and to duplicate a memory in
  * low memory space say 0 - 3G.
  */
-
 static unsigned long efi_rt_eflags;
 
+void efi_sync_low_kernel_mappings(void) {}
+void efi_setup_page_tables(void) {}
+
+void __init efi_map_region(efi_memory_desc_t *md)
+{
+	old_map_region(md);
+}
+
+void __init efi_map_region_fixed(efi_memory_desc_t *md) {}
+void __init parse_efi_setup(u64 phys_addr, u32 data_len) {}
+
 void efi_call_phys_prelog(void)
 {
 	struct desc_ptr gdt_descr;

arch/x86/platform/efi/efi_64.c

@@ -38,10 +38,28 @@
 #include <asm/efi.h>
 #include <asm/cacheflush.h>
 #include <asm/fixmap.h>
+#include <asm/realmode.h>
 
 static pgd_t *save_pgd __initdata;
 static unsigned long efi_flags __initdata;
 
+/*
+ * We allocate runtime services regions bottom-up, starting from -4G, i.e.
+ * 0xffff_ffff_0000_0000 and limit EFI VA mapping space to 64G.
+ */
+static u64 efi_va	= -4 * (1UL << 30);
+#define EFI_VA_END	(-68 * (1UL << 30))
+
+/*
+ * Scratch space used for switching the pagetable in the EFI stub
+ */
+struct efi_scratch {
+	u64 r15;
+	u64 prev_cr3;
+	pgd_t *efi_pgt;
+	bool use_pgd;
+};
+
 static void __init early_code_mapping_set_exec(int executable)
 {
 	efi_memory_desc_t *md;
@@ -65,6 +83,9 @@ void __init efi_call_phys_prelog(void)
 	int pgd;
 	int n_pgds;
 
+	if (!efi_enabled(EFI_OLD_MEMMAP))
+		return;
+
 	early_code_mapping_set_exec(1);
 	local_irq_save(efi_flags);
 
@@ -86,6 +107,10 @@ void __init efi_call_phys_epilog(void)
 	 */
 	int pgd;
 	int n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE);
+
+	if (!efi_enabled(EFI_OLD_MEMMAP))
+		return;
+
 	for (pgd = 0; pgd < n_pgds; pgd++)
 		set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), save_pgd[pgd]);
 	kfree(save_pgd);
@@ -94,6 +119,96 @@ void __init efi_call_phys_epilog(void)
 	early_code_mapping_set_exec(0);
 }
 
+/*
+ * Add low kernel mappings for passing arguments to EFI functions.
+ */
+void efi_sync_low_kernel_mappings(void)
+{
+	unsigned num_pgds;
+	pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
+
+	if (efi_enabled(EFI_OLD_MEMMAP))
+		return;
+
+	num_pgds = pgd_index(MODULES_END - 1) - pgd_index(PAGE_OFFSET);
+
+	memcpy(pgd + pgd_index(PAGE_OFFSET),
+		init_mm.pgd + pgd_index(PAGE_OFFSET),
+		sizeof(pgd_t) * num_pgds);
+}
+
+void efi_setup_page_tables(void)
+{
+	efi_scratch.efi_pgt = (pgd_t *)(unsigned long)real_mode_header->trampoline_pgd;
+
+	if (!efi_enabled(EFI_OLD_MEMMAP))
+		efi_scratch.use_pgd = true;
+}
+
+static void __init __map_region(efi_memory_desc_t *md, u64 va)
+{
+	pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
+	unsigned long pf = 0;
+
+	if (!(md->attribute & EFI_MEMORY_WB))
+		pf |= _PAGE_PCD;
+
+	if (kernel_map_pages_in_pgd(pgd, md->phys_addr, va, md->num_pages, pf))
+		pr_warn("Error mapping PA 0x%llx -> VA 0x%llx!\n",
+			   md->phys_addr, va);
+}
+
+void __init efi_map_region(efi_memory_desc_t *md)
+{
+	unsigned long size = md->num_pages << PAGE_SHIFT;
+	u64 pa = md->phys_addr;
+
+	if (efi_enabled(EFI_OLD_MEMMAP))
+		return old_map_region(md);
+
+	/*
+	 * Make sure the 1:1 mappings are present as a catch-all for b0rked
+	 * firmware which doesn't update all internal pointers after switching
+	 * to virtual mode and would otherwise crap on us.
+	 */
+	__map_region(md, md->phys_addr);
+
+	efi_va -= size;
+
+	/* Is PA 2M-aligned? */
+	if (!(pa & (PMD_SIZE - 1))) {
+		efi_va &= PMD_MASK;
+	} else {
+		u64 pa_offset = pa & (PMD_SIZE - 1);
+		u64 prev_va = efi_va;
+
+		/* get us the same offset within this 2M page */
+		efi_va = (efi_va & PMD_MASK) + pa_offset;
+
+		if (efi_va > prev_va)
+			efi_va -= PMD_SIZE;
+	}
+
+	if (efi_va < EFI_VA_END) {
+		pr_warn(FW_WARN "VA address range overflow!\n");
+		return;
+	}
+
+	/* Do the VA map */
+	__map_region(md, efi_va);
+	md->virt_addr = efi_va;
+}
+
+/*
+ * kexec kernel will use efi_map_region_fixed to map efi runtime memory ranges.
+ * md->virt_addr is the original virtual address which had been mapped in kexec
+ * 1st kernel.
+ */
+void __init efi_map_region_fixed(efi_memory_desc_t *md)
+{
+	__map_region(md, md->virt_addr);
+}
+
 void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size,
 				 u32 type, u64 attribute)
 {
@@ -113,3 +228,8 @@ void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size,
 
 	return (void __iomem *)__va(phys_addr);
 }
+
+void __init parse_efi_setup(u64 phys_addr, u32 data_len)
+{
+	efi_setup = phys_addr + sizeof(struct setup_data);
+}

arch/x86/platform/efi/efi_stub_64.S

@@ -34,10 +34,47 @@
 	mov %rsi, %cr0;			\
 	mov (%rsp), %rsp
 
+	/* stolen from gcc */
+	.macro FLUSH_TLB_ALL
+	movq %r15, efi_scratch(%rip)
+	movq %r14, efi_scratch+8(%rip)
+	movq %cr4, %r15
+	movq %r15, %r14
+	andb $0x7f, %r14b
+	movq %r14, %cr4
+	movq %r15, %cr4
+	movq efi_scratch+8(%rip), %r14
+	movq efi_scratch(%rip), %r15
+	.endm
+
+	.macro SWITCH_PGT
+	cmpb $0, efi_scratch+24(%rip)
+	je 1f
+	movq %r15, efi_scratch(%rip)		# r15
+	# save previous CR3
+	movq %cr3, %r15
+	movq %r15, efi_scratch+8(%rip)		# prev_cr3
+	movq efi_scratch+16(%rip), %r15		# EFI pgt
+	movq %r15, %cr3
+	1:
+	.endm
+
+	.macro RESTORE_PGT
+	cmpb $0, efi_scratch+24(%rip)
+	je 2f
+	movq efi_scratch+8(%rip), %r15
+	movq %r15, %cr3
+	movq efi_scratch(%rip), %r15
+	FLUSH_TLB_ALL
+	2:
+	.endm
+
 ENTRY(efi_call0)
 	SAVE_XMM
 	subq $32, %rsp
+	SWITCH_PGT
 	call *%rdi
+	RESTORE_PGT
 	addq $32, %rsp
 	RESTORE_XMM
 	ret
@@ -47,7 +84,9 @@ ENTRY(efi_call1)
 	SAVE_XMM
 	subq $32, %rsp
 	mov  %rsi, %rcx
+	SWITCH_PGT
 	call *%rdi
+	RESTORE_PGT
 	addq $32, %rsp
 	RESTORE_XMM
 	ret
@@ -57,7 +96,9 @@ ENTRY(efi_call2)
 	SAVE_XMM
 	subq $32, %rsp
 	mov  %rsi, %rcx
+	SWITCH_PGT
 	call *%rdi
+	RESTORE_PGT
 	addq $32, %rsp
 	RESTORE_XMM
 	ret
@@ -68,7 +109,9 @@ ENTRY(efi_call3)
 	subq $32, %rsp
 	mov  %rcx, %r8
 	mov  %rsi, %rcx
+	SWITCH_PGT
 	call *%rdi
+	RESTORE_PGT
 	addq $32, %rsp
 	RESTORE_XMM
 	ret
@@ -80,7 +123,9 @@ ENTRY(efi_call4)
 	mov %r8, %r9
 	mov %rcx, %r8
 	mov %rsi, %rcx
+	SWITCH_PGT
 	call *%rdi
+	RESTORE_PGT
 	addq $32, %rsp
 	RESTORE_XMM
 	ret
@@ -93,7 +138,9 @@ ENTRY(efi_call5)
 	mov %r8, %r9
 	mov %rcx, %r8
 	mov %rsi, %rcx
+	SWITCH_PGT
 	call *%rdi
+	RESTORE_PGT
 	addq $48, %rsp
 	RESTORE_XMM
 	ret
@@ -109,8 +156,15 @@ ENTRY(efi_call6)
 	mov %r8, %r9
 	mov %rcx, %r8
 	mov %rsi, %rcx
+	SWITCH_PGT
 	call *%rdi
+	RESTORE_PGT
 	addq $48, %rsp
 	RESTORE_XMM
 	ret
 ENDPROC(efi_call6)
+
+	.data
+ENTRY(efi_scratch)
+	.fill 3,8,0
+	.byte 0

drivers/firmware/efi/Kconfig

@@ -36,6 +36,17 @@ config EFI_VARS_PSTORE_DEFAULT_DISABLE
 	  backend for pstore by default. This setting can be overridden
 	  using the efivars module's pstore_disable parameter.
 
+config EFI_RUNTIME_MAP
+	bool "Export efi runtime maps to sysfs"
+	depends on X86 && EFI && KEXEC
+	default y
+	help
+	  Export efi runtime memory maps to /sys/firmware/efi/runtime-map.
+	  That memory map is used for example by kexec to set up efi virtual
+	  mapping the 2nd kernel, but can also be used for debugging purposes.
+
+	  See also Documentation/ABI/testing/sysfs-firmware-efi-runtime-map.
+
 endmenu
 
 config UEFI_CPER

drivers/firmware/efi/Makefile

@@ -5,3 +5,4 @@ obj-$(CONFIG_EFI)			+= efi.o vars.o
 obj-$(CONFIG_EFI_VARS)			+= efivars.o
 obj-$(CONFIG_EFI_VARS_PSTORE)		+= efi-pstore.o
 obj-$(CONFIG_UEFI_CPER)			+= cper.o
+obj-$(CONFIG_EFI_RUNTIME_MAP)		+= runtime-map.o

drivers/firmware/efi/efi.c

@@ -32,6 +32,9 @@ struct efi __read_mostly efi = {
 	.hcdp       = EFI_INVALID_TABLE_ADDR,
 	.uga        = EFI_INVALID_TABLE_ADDR,
 	.uv_systab  = EFI_INVALID_TABLE_ADDR,
+	.fw_vendor  = EFI_INVALID_TABLE_ADDR,
+	.runtime    = EFI_INVALID_TABLE_ADDR,
+	.config_table  = EFI_INVALID_TABLE_ADDR,
 };
 EXPORT_SYMBOL(efi);
 
@@ -71,13 +74,49 @@ static ssize_t systab_show(struct kobject *kobj,
 static struct kobj_attribute efi_attr_systab =
 			__ATTR(systab, 0400, systab_show, NULL);
 
+#define EFI_FIELD(var) efi.var
+
+#define EFI_ATTR_SHOW(name) \
+static ssize_t name##_show(struct kobject *kobj, \
+				struct kobj_attribute *attr, char *buf) \
+{ \
+	return sprintf(buf, "0x%lx\n", EFI_FIELD(name)); \
+}
+
+EFI_ATTR_SHOW(fw_vendor);
+EFI_ATTR_SHOW(runtime);
+EFI_ATTR_SHOW(config_table);
+
+static struct kobj_attribute efi_attr_fw_vendor = __ATTR_RO(fw_vendor);
+static struct kobj_attribute efi_attr_runtime = __ATTR_RO(runtime);
+static struct kobj_attribute efi_attr_config_table = __ATTR_RO(config_table);
+
 static struct attribute *efi_subsys_attrs[] = {
 	&efi_attr_systab.attr,
-	NULL,	/* maybe more in the future? */
+	&efi_attr_fw_vendor.attr,
+	&efi_attr_runtime.attr,
+	&efi_attr_config_table.attr,
+	NULL,
 };
 
+static umode_t efi_attr_is_visible(struct kobject *kobj,
+				   struct attribute *attr, int n)
+{
+	umode_t mode = attr->mode;
+
+	if (attr == &efi_attr_fw_vendor.attr)
+		return (efi.fw_vendor == EFI_INVALID_TABLE_ADDR) ? 0 : mode;
+	else if (attr == &efi_attr_runtime.attr)
+		return (efi.runtime == EFI_INVALID_TABLE_ADDR) ? 0 : mode;
+	else if (attr == &efi_attr_config_table.attr)
+		return (efi.config_table == EFI_INVALID_TABLE_ADDR) ? 0 : mode;
+
+	return mode;
+}
+
 static struct attribute_group efi_subsys_attr_group = {
 	.attrs = efi_subsys_attrs,
+	.is_visible = efi_attr_is_visible,
 };
 
 static struct efivars generic_efivars;
@@ -128,6 +167,10 @@ static int __init efisubsys_init(void)
 		goto err_unregister;
 	}
 
+	error = efi_runtime_map_init(efi_kobj);
+	if (error)
+		goto err_remove_group;
+
 	/* and the standard mountpoint for efivarfs */
 	efivars_kobj = kobject_create_and_add("efivars", efi_kobj);
 	if (!efivars_kobj) {

drivers/firmware/efi/runtime-map.c

+/*
+ * linux/drivers/efi/runtime-map.c
+ * Copyright (C) 2013 Red Hat, Inc., Dave Young <dyoung@redhat.com>
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/efi.h>
+#include <linux/slab.h>
+
+#include <asm/setup.h>
+
+static void *efi_runtime_map;
+static int nr_efi_runtime_map;
+static u32 efi_memdesc_size;
+
+struct efi_runtime_map_entry {
+	efi_memory_desc_t md;
+	struct kobject kobj;   /* kobject for each entry */
+};
+
+static struct efi_runtime_map_entry **map_entries;
+
+struct map_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct efi_runtime_map_entry *entry, char *buf);
+};
+
+static inline struct map_attribute *to_map_attr(struct attribute *attr)
+{
+	return container_of(attr, struct map_attribute, attr);
+}
+
+static ssize_t type_show(struct efi_runtime_map_entry *entry, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "0x%x\n", entry->md.type);
+}
+
+#define EFI_RUNTIME_FIELD(var) entry->md.var
+
+#define EFI_RUNTIME_U64_ATTR_SHOW(name) \
+static ssize_t name##_show(struct efi_runtime_map_entry *entry, char *buf) \
+{ \
+	return snprintf(buf, PAGE_SIZE, "0x%llx\n", EFI_RUNTIME_FIELD(name)); \
+}
+
+EFI_RUNTIME_U64_ATTR_SHOW(phys_addr);
+EFI_RUNTIME_U64_ATTR_SHOW(virt_addr);
+EFI_RUNTIME_U64_ATTR_SHOW(num_pages);
+EFI_RUNTIME_U64_ATTR_SHOW(attribute);
+
+static inline struct efi_runtime_map_entry *to_map_entry(struct kobject *kobj)
+{
+	return container_of(kobj, struct efi_runtime_map_entry, kobj);
+}
+
+static ssize_t map_attr_show(struct kobject *kobj, struct attribute *attr,
+			      char *buf)
+{
+	struct efi_runtime_map_entry *entry = to_map_entry(kobj);
+	struct map_attribute *map_attr = to_map_attr(attr);
+
+	return map_attr->show(entry, buf);
+}
+
+static struct map_attribute map_type_attr = __ATTR_RO(type);
+static struct map_attribute map_phys_addr_attr   = __ATTR_RO(phys_addr);
+static struct map_attribute map_virt_addr_attr  = __ATTR_RO(virt_addr);
+static struct map_attribute map_num_pages_attr  = __ATTR_RO(num_pages);
+static struct map_attribute map_attribute_attr  = __ATTR_RO(attribute);
+
+/*
+ * These are default attributes that are added for every memmap entry.
+ */
+static struct attribute *def_attrs[] = {
+	&map_type_attr.attr,
+	&map_phys_addr_attr.attr,
+	&map_virt_addr_attr.attr,
+	&map_num_pages_attr.attr,
+	&map_attribute_attr.attr,
+	NULL
+};
+
+static const struct sysfs_ops map_attr_ops = {
+	.show = map_attr_show,
+};
+
+static void map_release(struct kobject *kobj)
+{
+	struct efi_runtime_map_entry *entry;
+
+	entry = to_map_entry(kobj);
+	kfree(entry);
+}
+
+static struct kobj_type __refdata map_ktype = {
+	.sysfs_ops	= &map_attr_ops,
+	.default_attrs	= def_attrs,
+	.release	= map_release,
+};
+
+static struct kset *map_kset;
+
+static struct efi_runtime_map_entry *
+add_sysfs_runtime_map_entry(struct kobject *kobj, int nr)
+{
+	int ret;
+	struct efi_runtime_map_entry *entry;
+
+	if (!map_kset) {
+		map_kset = kset_create_and_add("runtime-map", NULL, kobj);
+		if (!map_kset)
+			return ERR_PTR(-ENOMEM);
+	}
+
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry) {
+		kset_unregister(map_kset);
+		return entry;
+	}
+
+	memcpy(&entry->md, efi_runtime_map + nr * efi_memdesc_size,
+	       sizeof(efi_memory_desc_t));
+
+	kobject_init(&entry->kobj, &map_ktype);
+	entry->kobj.kset = map_kset;
+	ret = kobject_add(&entry->kobj, NULL, "%d", nr);
+	if (ret) {
+		kobject_put(&entry->kobj);
+		kset_unregister(map_kset);
+		return ERR_PTR(ret);
+	}
+
+	return entry;
+}
+
+void efi_runtime_map_setup(void *map, int nr_entries, u32 desc_size)
+{
+	efi_runtime_map = map;
+	nr_efi_runtime_map = nr_entries;
+	efi_memdesc_size = desc_size;
+}
+
+int __init efi_runtime_map_init(struct kobject *efi_kobj)
+{
+	int i, j, ret = 0;
+	struct efi_runtime_map_entry *entry;
+
+	if (!efi_runtime_map)
+		return 0;
+
+	map_entries = kzalloc(nr_efi_runtime_map * sizeof(entry), GFP_KERNEL);
+	if (!map_entries) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	for (i = 0; i < nr_efi_runtime_map; i++) {
+		entry = add_sysfs_runtime_map_entry(efi_kobj, i);
+		if (IS_ERR(entry)) {
+			ret = PTR_ERR(entry);
+			goto out_add_entry;
+		}
+		*(map_entries + i) = entry;
+	}
+
+	return 0;
+out_add_entry:
+	for (j = i - 1; j > 0; j--) {
+		entry = *(map_entries + j);
+		kobject_put(&entry->kobj);
+	}
+	if (map_kset)
+		kset_unregister(map_kset);
+out:
+	return ret;
+}

include/linux/efi.h

@@ -556,6 +556,9 @@ extern struct efi {
 	unsigned long hcdp;		/* HCDP table */
 	unsigned long uga;		/* UGA table */
 	unsigned long uv_systab;	/* UV system table */
+	unsigned long fw_vendor;	/* fw_vendor */
+	unsigned long runtime;		/* runtime table */
+	unsigned long config_table;	/* config tables */
 	efi_get_time_t *get_time;
 	efi_set_time_t *set_time;
 	efi_get_wakeup_time_t *get_wakeup_time;
@@ -653,6 +656,7 @@ extern int __init efi_setup_pcdp_console(char *);
 #define EFI_RUNTIME_SERVICES	3	/* Can we use runtime services? */
 #define EFI_MEMMAP		4	/* Can we use EFI memory map? */
 #define EFI_64BIT		5	/* Is the firmware 64-bit? */
+#define EFI_ARCH_1		6	/* First arch-specific bit */
 
 #ifdef CONFIG_EFI
 # ifdef CONFIG_X86
@@ -872,4 +876,17 @@ int efivars_sysfs_init(void);
 
 #endif /* CONFIG_EFI_VARS */
 
+#ifdef CONFIG_EFI_RUNTIME_MAP
+int efi_runtime_map_init(struct kobject *);
+void efi_runtime_map_setup(void *, int, u32);
+#else
+static inline int efi_runtime_map_init(struct kobject *kobj)
+{
+	return 0;
+}
+
+static inline void
+efi_runtime_map_setup(void *map, int nr_entries, u32 desc_size) {}
+#endif
+
 #endif /* _LINUX_EFI_H */