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
  ...

23 files changed, 1689 insertions, 116 deletions

diff --git a/Documentation/ABI/testing/sysfs-firmware-efi b/Documentation/ABI/testing/sysfs-firmware-efi
new file mode 100644
index 00000000000..05874da7ce8
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-firmware-efi
@@ -0,0 +1,20 @@
+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
diff --git a/Documentation/ABI/testing/sysfs-firmware-efi-runtime-map b/Documentation/ABI/testing/sysfs-firmware-efi-runtime-map
new file mode 100644
index 00000000000..c61b9b348e9
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-firmware-efi-runtime-map
@@ -0,0 +1,34 @@
+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
diff --git a/Documentation/ABI/testing/sysfs-kernel-boot_params b/Documentation/ABI/testing/sysfs-kernel-boot_params
new file mode 100644
index 00000000000..eca38ce2852
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-kernel-boot_params
@@ -0,0 +1,38 @@
+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
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 3b8e262c365..4eb5fff022b 100644
--- a/Documentation/kernel-parameters.txt
+++ b/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
diff --git a/Documentation/x86/boot.txt b/Documentation/x86/boot.txt
index f4f268c2b82..cb81741d3b0 100644
--- a/Documentation/x86/boot.txt
+++ b/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
diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index 881582f75c9..c584a51add1 100644
--- a/Documentation/x86/x86_64/mm.txt
+++ b/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
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index 9ec06a1f6d6..ec3b8ba6809 100644
--- a/arch/x86/boot/header.S
+++ b/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
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 65c6e6e3a55..3b978c472d0 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -1,6 +1,24 @@
 #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 */
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 0ecac257fb2..a83aa44bb1f 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/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 */
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index 9c3733c5f8f..225b0988043 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/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__
 
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 9b0a34e2cd7..510cca5c539 100644
--- a/arch/x86/kernel/Makefile
+++ b/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
diff --git a/arch/x86/kernel/ksysfs.c b/arch/x86/kernel/ksysfs.c
new file mode 100644
index 00000000000..c2bedaea11f
--- /dev/null
+++ b/arch/x86/kernel/ksysfs.c
@@ -0,0 +1,340 @@
+/*
+ * 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);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index cb233bc9dee..be4b456e444 100644
--- a/arch/x86/kernel/setup.c
+++ b/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))
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index bb32480c2d7..b3b19f46c01 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -30,6 +30,7 @@
  */
 struct cpa_data {
 	unsigned long	*vaddr;
+	pgd_t		*pgd;
 	pgprot_t	mask_set;
 	pgprot_t	mask_clr;
 	int		numpages;
@@ -322,17 +323,9 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
 	return prot;
 }
 
-/*
- * Lookup the page table entry for a virtual address. Return a pointer
- * to the entry and the level of the mapping.
- *
- * Note: We return pud and pmd either when the entry is marked large
- * or when the present bit is not set. Otherwise we would return a
- * pointer to a nonexisting mapping.
- */
-pte_t *lookup_address(unsigned long address, unsigned int *level)
+static pte_t *__lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
+				      unsigned int *level)
 {
-	pgd_t *pgd = pgd_offset_k(address);
 	pud_t *pud;
 	pmd_t *pmd;
 
@@ -361,8 +354,31 @@ pte_t *lookup_address(unsigned long address, unsigned int *level)
 
 	return pte_offset_kernel(pmd, address);
 }
+
+/*
+ * Lookup the page table entry for a virtual address. Return a pointer
+ * to the entry and the level of the mapping.
+ *
+ * Note: We return pud and pmd either when the entry is marked large
+ * or when the present bit is not set. Otherwise we would return a
+ * pointer to a nonexisting mapping.
+ */
+pte_t *lookup_address(unsigned long address, unsigned int *level)
+{
+        return __lookup_address_in_pgd(pgd_offset_k(address), address, level);
+}
 EXPORT_SYMBOL_GPL(lookup_address);
 
+static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address,
+				  unsigned int *level)
+{
+        if (cpa->pgd)
+		return __lookup_address_in_pgd(cpa->pgd + pgd_index(address),
+					       address, level);
+
+        return lookup_address(address, level);
+}
+
 /*
  * This is necessary because __pa() does not work on some
  * kinds of memory, like vmalloc() or the alloc_remap()
@@ -437,7 +453,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
 	 * Check for races, another CPU might have split this page
 	 * up already:
 	 */
-	tmp = lookup_address(address, &level);
+	tmp = _lookup_address_cpa(cpa, address, &level);
 	if (tmp != kpte)
 		goto out_unlock;
 
@@ -543,7 +559,8 @@ out_unlock:
 }
 
 static int
-__split_large_page(pte_t *kpte, unsigned long address, struct page *base)
+__split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address,
+		   struct page *base)
 {
 	pte_t *pbase = (pte_t *)page_address(base);
 	unsigned long pfn, pfninc = 1;
@@ -556,7 +573,7 @@ __split_large_page(pte_t *kpte, unsigned long address, struct page *base)
 	 * Check for races, another CPU might have split this page
 	 * up for us already:
 	 */
-	tmp = lookup_address(address, &level);
+	tmp = _lookup_address_cpa(cpa, address, &level);
 	if (tmp != kpte) {
 		spin_unlock(&pgd_lock);
 		return 1;
@@ -632,7 +649,8 @@ __split_large_page(pte_t *kpte, unsigned long address, struct page *base)
 	return 0;
 }
 
-static int split_large_page(pte_t *kpte, unsigned long address)
+static int split_large_page(struct cpa_data *cpa, pte_t *kpte,
+			    unsigned long address)
 {
 	struct page *base;
 
@@ -644,15 +662,390 @@ static int split_large_page(pte_t *kpte, unsigned long address)
 	if (!base)
 		return -ENOMEM;
 
-	if (__split_large_page(kpte, address, base))
+	if (__split_large_page(cpa, kpte, address, base))
 		__free_page(base);
 
 	return 0;
 }
 
+static bool try_to_free_pte_page(pte_t *pte)
+{
+	int i;
+
+	for (i = 0; i < PTRS_PER_PTE; i++)
+		if (!pte_none(pte[i]))
+			return false;
+
+	free_page((unsigned long)pte);
+	return true;
+}
+
+static bool try_to_free_pmd_page(pmd_t *pmd)
+{
+	int i;
+
+	for (i = 0; i < PTRS_PER_PMD; i++)
+		if (!pmd_none(pmd[i]))
+			return false;
+
+	free_page((unsigned long)pmd);
+	return true;
+}
+
+static bool unmap_pte_range(pmd_t *pmd, unsigned long start, unsigned long end)
+{
+	pte_t *pte = pte_offset_kernel(pmd, start);
+
+	while (start < end) {
+		set_pte(pte, __pte(0));
+
+		start += PAGE_SIZE;
+		pte++;
+	}
+
+	if (try_to_free_pte_page((pte_t *)pmd_page_vaddr(*pmd))) {
+		pmd_clear(pmd);
+		return true;
+	}
+	return false;
+}
+
+static void __unmap_pmd_range(pud_t *pud, pmd_t *pmd,
+			      unsigned long start, unsigned long end)
+{
+	if (unmap_pte_range(pmd, start, end))
+		if (try_to_free_pmd_page((pmd_t *)pud_page_vaddr(*pud)))
+			pud_clear(pud);
+}
+
+static void unmap_pmd_range(pud_t *pud, unsigned long start, unsigned long end)
+{
+	pmd_t *pmd = pmd_offset(pud, start);
+
+	/*
+	 * Not on a 2MB page boundary?
+	 */
+	if (start & (PMD_SIZE - 1)) {
+		unsigned long next_page = (start + PMD_SIZE) & PMD_MASK;
+		unsigned long pre_end = min_t(unsigned long, end, next_page);
+
+		__unmap_pmd_range(pud, pmd, start, pre_end);
+
+		start = pre_end;
+		pmd++;
+	}
+
+	/*
+	 * Try to unmap in 2M chunks.
+	 */
+	while (end - start >= PMD_SIZE) {
+		if (pmd_large(*pmd))
+			pmd_clear(pmd);
+		else
+			__unmap_pmd_range(pud, pmd, start, start + PMD_SIZE);
+
+		start += PMD_SIZE;
+		pmd++;
+	}
+
+	/*
+	 * 4K leftovers?