Merge tag 'efi-next-for-v6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/efi/efi

Pull EFI updates from Ard Biesheuvel:
 "Another fairly sizable pull request, by EFI subsystem standards.

  Most of the work was done by me, some of it in collaboration with the
  distro and bootloader folks (GRUB, systemd-boot), where the main focus
  has been on removing pointless per-arch differences in the way EFI
  boots a Linux kernel.

   - Refactor the zboot code so that it incorporates all the EFI stub
     logic, rather than calling the decompressed kernel as a EFI app.

   - Add support for initrd= command line option to x86 mixed mode.

   - Allow initrd= to be used with arbitrary EFI accessible file systems
     instead of just the one the kernel itself was loaded from.

   - Move some x86-only handling and manipulation of the EFI memory map
     into arch/x86, as it is not used anywhere else.

   - More flexible handling of any random seeds provided by the boot
     environment (i.e., systemd-boot) so that it becomes available much
     earlier during the boot.

   - Allow improved arch-agnostic EFI support in loaders, by setting a
     uniform baseline of supported features, and adding a generic magic
     number to the DOS/PE header. This should allow loaders such as GRUB
     or systemd-boot to reduce the amount of arch-specific handling
     substantially.

   - (arm64) Run EFI runtime services from a dedicated stack, and use it
     to recover from synchronous exceptions that might occur in the
     firmware code.

   - (arm64) Ensure that we don't allocate memory outside of the 48-bit
     addressable physical range.

   - Make EFI pstore record size configurable

   - Add support for decoding CXL specific CPER records"

* tag 'efi-next-for-v6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/efi/efi: (43 commits)
  arm64: efi: Recover from synchronous exceptions occurring in firmware
  arm64: efi: Execute runtime services from a dedicated stack
  arm64: efi: Limit allocations to 48-bit addressable physical region
  efi: Put Linux specific magic number in the DOS header
  efi: libstub: Always enable initrd command line loader and bump version
  efi: stub: use random seed from EFI variable
  efi: vars: prohibit reading random seed variables
  efi: random: combine bootloader provided RNG seed with RNG protocol output
  efi/cper, cxl: Decode CXL Error Log
  efi/cper, cxl: Decode CXL Protocol Error Section
  efi: libstub: fix efi_load_initrd_dev_path() kernel-doc comment
  efi: x86: Move EFI runtime map sysfs code to arch/x86
  efi: runtime-maps: Clarify purpose and enable by default for kexec
  efi: pstore: Add module parameter for setting the record size
  efi: xen: Set EFI_PARAVIRT for Xen dom0 boot on all architectures
  efi: memmap: Move manipulation routines into x86 arch tree
  efi: memmap: Move EFI fake memmap support into x86 arch tree
  efi: libstub: Undeprecate the command line initrd loader
  efi: libstub: Add mixed mode support to command line initrd loader
  efi: libstub: Permit mixed mode return types other than efi_status_t
  ...

10 files changed, 750 insertions, 43 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 276b3baf1c50..e9ede4c4c27f 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1995,6 +1995,37 @@ config EFI_MIXED
 
 	  If unsure, say N.
 
+config EFI_FAKE_MEMMAP
+	bool "Enable EFI fake memory map"
+	depends on EFI
+	help
+	  Saying Y here will enable "efi_fake_mem" boot option.  By specifying
+	  this parameter, you can add arbitrary attribute to specific memory
+	  range by updating original (firmware provided) EFI memmap.  This is
+	  useful for debugging of EFI memmap related feature, e.g., Address
+	  Range Mirroring feature.
+
+config EFI_MAX_FAKE_MEM
+	int "maximum allowable number of ranges in efi_fake_mem boot option"
+	depends on EFI_FAKE_MEMMAP
+	range 1 128
+	default 8
+	help
+	  Maximum allowable number of ranges in efi_fake_mem boot option.
+	  Ranges can be set up to this value using comma-separated list.
+	  The default value is 8.
+
+config EFI_RUNTIME_MAP
+	bool "Export EFI runtime maps to sysfs" if EXPERT
+	depends on EFI
+	default KEXEC_CORE
+	help
+	  Export EFI runtime memory regions to /sys/firmware/efi/runtime-map.
+	  That memory map is required by the 2nd kernel to set up EFI virtual
+	  mappings after kexec, but can also be used for debugging purposes.
+
+	  See also Documentation/ABI/testing/sysfs-firmware-efi-runtime-map.
+
 source "kernel/Kconfig.hz"
 
 config KEXEC
diff --git a/arch/x86/boot/compressed/efi_thunk_64.S b/arch/x86/boot/compressed/efi_thunk_64.S
index 67e7edcdfea8..0c988f2a1243 100644
--- a/arch/x86/boot/compressed/efi_thunk_64.S
+++ b/arch/x86/boot/compressed/efi_thunk_64.S
@@ -93,12 +93,6 @@ SYM_FUNC_START(__efi64_thunk)
 	movl	%ebx, %fs
 	movl	%ebx, %gs
 
-	/*
-	 * Convert 32-bit status code into 64-bit.
-	 */
-	roll	$1, %eax
-	rorq	$1, %rax
-
 	pop	%rbx
 	pop	%rbp
 	RET
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index f912d7770130..be8f78a7ee32 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -80,10 +80,11 @@ bs_die:
 	ljmp	$0xf000,$0xfff0
 
 #ifdef CONFIG_EFI_STUB
-	.org	0x3c
+	.org	0x38
 	#
 	# Offset to the PE header.
 	#
+	.long	LINUX_PE_MAGIC
 	.long	pe_header
 #endif /* CONFIG_EFI_STUB */
 
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 233ae6986d6f..a63154e049d7 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -178,7 +178,7 @@ struct efi_setup_data {
 extern u64 efi_setup;
 
 #ifdef CONFIG_EFI
-extern efi_status_t __efi64_thunk(u32, ...);
+extern u64 __efi64_thunk(u32, ...);
 
 #define efi64_thunk(...) ({						\
 	u64 __pad[3]; /* must have space for 3 args on the stack */	\
@@ -228,16 +228,15 @@ static inline bool efi_is_native(void)
 	return efi_is_64bit();
 }
 
-#define efi_mixed_mode_cast(attr)					\
-	__builtin_choose_expr(						\
-		__builtin_types_compatible_p(u32, __typeof__(attr)),	\
-			(unsigned long)(attr), (attr))
-
 #define efi_table_attr(inst, attr)					\
-	(efi_is_native()						\
-		? inst->attr						\
-		: (__typeof__(inst->attr))				\
-			efi_mixed_mode_cast(inst->mixed_mode.attr))
+	(efi_is_native() ? (inst)->attr					\
+			 : efi_mixed_table_attr((inst), attr))
+
+#define efi_mixed_table_attr(inst, attr)				\
+	(__typeof__(inst->attr))					\
+		_Generic(inst->mixed_mode.attr,				\
+		u32:		(unsigned long)(inst->mixed_mode.attr),	\
+		default:	(inst->mixed_mode.attr))
 
 /*
  * The following macros allow translating arguments if necessary from native to
@@ -325,6 +324,17 @@ static inline u32 efi64_convert_status(efi_status_t status)
 #define __efi64_argmap_set_memory_space_attributes(phys, size, flags) \
 	(__efi64_split(phys), __efi64_split(size), __efi64_split(flags))
 
+/* file protocol */
+#define __efi64_argmap_open(prot, newh, fname, mode, attr) \
+	((prot), efi64_zero_upper(newh), (fname), __efi64_split(mode), \
+	 __efi64_split(attr))
+
+#define __efi64_argmap_set_position(pos) (__efi64_split(pos))
+
+/* file system protocol */
+#define __efi64_argmap_open_volume(prot, file) \
+	((prot), efi64_zero_upper(file))
+
 /*
  * The macros below handle the plumbing for the argument mapping. To add a
  * mapping for a specific EFI method, simply define a macro
@@ -344,31 +354,27 @@ static inline u32 efi64_convert_status(efi_status_t status)
 #define __efi_eat(...)
 #define __efi_eval(...) __VA_ARGS__
 
-/* The three macros below handle dispatching via the thunk if needed */
-
-#define efi_call_proto(inst, func, ...)					\
-	(efi_is_native()						\
-		? inst->func(inst, ##__VA_ARGS__)			\
-		: __efi64_thunk_map(inst, func, inst, ##__VA_ARGS__))
+static inline efi_status_t __efi64_widen_efi_status(u64 status)
+{
+	/* use rotate to move the value of bit #31 into position #63 */
+	return ror64(rol32(status, 1), 1);
+}
 
-#define efi_bs_call(func, ...)						\
-	(efi_is_native()						\
-		? efi_system_table->boottime->func(__VA_ARGS__)		\
-		: __efi64_thunk_map(efi_table_attr(efi_system_table,	\
-						   boottime),		\
-				    func, __VA_ARGS__))
+/* The macro below handles dispatching via the thunk if needed */
 
-#define efi_rt_call(func, ...)						\
-	(efi_is_native()						\
-		? efi_system_table->runtime->func(__VA_ARGS__)		\
-		: __efi64_thunk_map(efi_table_attr(efi_system_table,	\
-						   runtime),		\
-				    func, __VA_ARGS__))
+#define efi_fn_call(inst, func, ...)					\
+	(efi_is_native() ? (inst)->func(__VA_ARGS__)			\
+			 : efi_mixed_call((inst), func, ##__VA_ARGS__))
 
-#define efi_dxe_call(func, ...)						\
-	(efi_is_native()						\
-		? efi_dxe_table->func(__VA_ARGS__)			\
-		: __efi64_thunk_map(efi_dxe_table, func, __VA_ARGS__))
+#define efi_mixed_call(inst, func, ...)					\
+	_Generic(inst->func(__VA_ARGS__),				\
+	efi_status_t:							\
+		__efi64_widen_efi_status(				\
+			__efi64_thunk_map(inst, func, ##__VA_ARGS__)),	\
+	u64: ({ BUILD_BUG(); ULONG_MAX; }),				\
+	default:							\
+		(__typeof__(inst->func(__VA_ARGS__)))			\
+			__efi64_thunk_map(inst, func, ##__VA_ARGS__))
 
 #else /* CONFIG_EFI_MIXED */
 
@@ -400,13 +406,52 @@ static inline void efi_reserve_boot_services(void)
 
 #ifdef CONFIG_EFI_FAKE_MEMMAP
 extern void __init efi_fake_memmap_early(void);
+extern void __init efi_fake_memmap(void);
 #else
 static inline void efi_fake_memmap_early(void)
 {
 }
+
+static inline void efi_fake_memmap(void)
+{
+}
 #endif
 
+extern int __init efi_memmap_alloc(unsigned int num_entries,
+				   struct efi_memory_map_data *data);
+extern void __efi_memmap_free(u64 phys, unsigned long size,
+			      unsigned long flags);
+#define __efi_memmap_free __efi_memmap_free
+
+extern int __init efi_memmap_install(struct efi_memory_map_data *data);
+extern int __init efi_memmap_split_count(efi_memory_desc_t *md,
+					 struct range *range);
+extern void __init efi_memmap_insert(struct efi_memory_map *old_memmap,
+				     void *buf, struct efi_mem_range *mem);
+
 #define arch_ima_efi_boot_mode	\
 	({ extern struct boot_params boot_params; boot_params.secure_boot; })
 
+#ifdef CONFIG_EFI_RUNTIME_MAP
+int efi_get_runtime_map_size(void);
+int efi_get_runtime_map_desc_size(void);
+int efi_runtime_map_copy(void *buf, size_t bufsz);
+#else
+static inline int efi_get_runtime_map_size(void)
+{
+	return 0;
+}
+
+static inline int efi_get_runtime_map_desc_size(void)
+{
+	return 0;
+}
+
+static inline int efi_runtime_map_copy(void *buf, size_t bufsz)
+{
+	return 0;
+}
+
+#endif
+
 #endif /* _ASM_X86_EFI_H */
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 216fee7144ee..41ec3a69f3c7 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -31,6 +31,7 @@
 #include <xen/xen.h>
 
 #include <asm/apic.h>
+#include <asm/efi.h>
 #include <asm/numa.h>
 #include <asm/bios_ebda.h>
 #include <asm/bugs.h>
diff --git a/arch/x86/platform/efi/Makefile b/arch/x86/platform/efi/Makefile
index a50245157685..543df9a1379d 100644
--- a/arch/x86/platform/efi/Makefile
+++ b/arch/x86/platform/efi/Makefile
@@ -2,5 +2,8 @@
 KASAN_SANITIZE := n
 GCOV_PROFILE := n
 
-obj-$(CONFIG_EFI) 		+= quirks.o efi.o efi_$(BITS).o efi_stub_$(BITS).o
+obj-$(CONFIG_EFI) 		+= memmap.o quirks.o efi.o efi_$(BITS).o \
+				   efi_stub_$(BITS).o
 obj-$(CONFIG_EFI_MIXED)		+= efi_thunk_$(BITS).o
+obj-$(CONFIG_EFI_FAKE_MEMMAP)	+= fake_mem.o
+obj-$(CONFIG_EFI_RUNTIME_MAP)	+= runtime-map.o
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index ebc98a68c400..7e51c14a1ef0 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -214,9 +214,11 @@ int __init efi_memblock_x86_reserve_range(void)
 	data.desc_size		= e->efi_memdesc_size;
 	data.desc_version	= e->efi_memdesc_version;
 
-	rv = efi_memmap_init_early(&data);
-	if (rv)
-		return rv;
+	if (!efi_enabled(EFI_PARAVIRT)) {
+		rv = efi_memmap_init_early(&data);
+		if (rv)
+			return rv;
+	}
 
 	if (add_efi_memmap || do_efi_soft_reserve())
 		do_add_efi_memmap();
diff --git a/arch/x86/platform/efi/fake_mem.c b/arch/x86/platform/efi/fake_mem.c
new file mode 100644
index 000000000000..41d57cad3d84
--- /dev/null
+++ b/arch/x86/platform/efi/fake_mem.c
@@ -0,0 +1,197 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * fake_mem.c
+ *
+ * Copyright (C) 2015 FUJITSU LIMITED
+ * Author: Taku Izumi <izumi.taku@jp.fujitsu.com>
+ *
+ * This code introduces new boot option named "efi_fake_mem"
+ * By specifying this parameter, you can add arbitrary attribute to
+ * specific memory range by updating original (firmware provided) EFI
+ * memmap.
+ */
+
+#include <linux/kernel.h>
+#include <linux/efi.h>
+#include <linux/init.h>
+#include <linux/memblock.h>
+#include <linux/types.h>
+#include <linux/sort.h>
+#include <asm/e820/api.h>
+#include <asm/efi.h>
+
+#define EFI_MAX_FAKEMEM CONFIG_EFI_MAX_FAKE_MEM
+
+static struct efi_mem_range efi_fake_mems[EFI_MAX_FAKEMEM];
+static int nr_fake_mem;
+
+static int __init cmp_fake_mem(const void *x1, const void *x2)
+{
+	const struct efi_mem_range *m1 = x1;
+	const struct efi_mem_range *m2 = x2;
+
+	if (m1->range.start < m2->range.start)
+		return -1;
+	if (m1->range.start > m2->range.start)
+		return 1;
+	return 0;
+}
+
+static void __init efi_fake_range(struct efi_mem_range *efi_range)
+{
+	struct efi_memory_map_data data = { 0 };
+	int new_nr_map = efi.memmap.nr_map;
+	efi_memory_desc_t *md;
+	void *new_memmap;
+
+	/* count up the number of EFI memory descriptor */
+	for_each_efi_memory_desc(md)
+		new_nr_map += efi_memmap_split_count(md, &efi_range->range);
+
+	/* allocate memory for new EFI memmap */
+	if (efi_memmap_alloc(new_nr_map, &data) != 0)
+		return;
+
+	/* create new EFI memmap */
+	new_memmap = early_memremap(data.phys_map, data.size);
+	if (!new_memmap) {
+		__efi_memmap_free(data.phys_map, data.size, data.flags);
+		return;
+	}
+
+	efi_memmap_insert(&efi.memmap, new_memmap, efi_range);
+
+	/* swap into new EFI memmap */
+	early_memunmap(new_memmap, data.size);
+
+	efi_memmap_install(&data);
+}
+
+void __init efi_fake_memmap(void)
+{
+	int i;
+
+	if (!efi_enabled(EFI_MEMMAP) || !nr_fake_mem)
+		return;
+
+	for (i = 0; i < nr_fake_mem; i++)
+		efi_fake_range(&efi_fake_mems[i]);
+
+	/* print new EFI memmap */
+	efi_print_memmap();
+}
+
+static int __init setup_fake_mem(char *p)
+{
+	u64 start = 0, mem_size = 0, attribute = 0;
+	int i;
+
+	if (!p)
+		return -EINVAL;
+
+	while (*p != '\0') {
+		mem_size = memparse(p, &p);
+		if (*p == '@')
+			start = memparse(p+1, &p);
+		else
+			break;
+
+		if (*p == ':')
+			attribute = simple_strtoull(p+1, &p, 0);
+		else
+			break;
+
+		if (nr_fake_mem >= EFI_MAX_FAKEMEM)
+			break;
+
+		efi_fake_mems[nr_fake_mem].range.start = start;
+		efi_fake_mems[nr_fake_mem].range.end = start + mem_size - 1;
+		efi_fake_mems[nr_fake_mem].attribute = attribute;
+		nr_fake_mem++;
+
+		if (*p == ',')
+			p++;
+	}
+
+	sort(efi_fake_mems, nr_fake_mem, sizeof(struct efi_mem_range),
+	     cmp_fake_mem, NULL);
+
+	for (i = 0; i < nr_fake_mem; i++)
+		pr_info("efi_fake_mem: add attr=0x%016llx to [mem 0x%016llx-0x%016llx]",
+			efi_fake_mems[i].attribute, efi_fake_mems[i].range.start,
+			efi_fake_mems[i].range.end);
+
+	return *p == '\0' ? 0 : -EINVAL;
+}
+
+early_param("efi_fake_mem", setup_fake_mem);
+
+void __init efi_fake_memmap_early(void)
+{
+	int i;
+
+	/*
+	 * The late efi_fake_mem() call can handle all requests if
+	 * EFI_MEMORY_SP support is disabled.
+	 */
+	if (!efi_soft_reserve_enabled())
+		return;
+
+	if (!efi_enabled(EFI_MEMMAP) || !nr_fake_mem)
+		return;
+
+	/*
+	 * Given that efi_fake_memmap() needs to perform memblock
+	 * allocations it needs to run after e820__memblock_setup().
+	 * However, if efi_fake_mem specifies EFI_MEMORY_SP for a given
+	 * address range that potentially needs to mark the memory as
+	 * reserved prior to e820__memblock_setup(). Update e820
+	 * directly if EFI_MEMORY_SP is specified for an
+	 * EFI_CONVENTIONAL_MEMORY descriptor.
+	 */
+	for (i = 0; i < nr_fake_mem; i++) {
+		struct efi_mem_range *mem = &efi_fake_mems[i];
+		efi_memory_desc_t *md;
+		u64 m_start, m_end;
+
+		if ((mem->attribute & EFI_MEMORY_SP) == 0)
+			continue;
+
+		m_start = mem->range.start;
+		m_end = mem->range.end;
+		for_each_efi_memory_desc(md) {
+			u64 start, end, size;
+
+			if (md->type != EFI_CONVENTIONAL_MEMORY)
+				continue;
+
+			start = md->phys_addr;
+			end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT) - 1;
+
+			if (m_start <= end && m_end >= start)
+				/* fake range overlaps descriptor */;
+			else
+				continue;
+
+			/*
+			 * Trim the boundary of the e820 update to the
+			 * descriptor in case the fake range overlaps
+			 * !EFI_CONVENTIONAL_MEMORY
+			 */
+			start = max(start, m_start);
+			end = min(end, m_end);
+			size = end - start + 1;
+
+			if (end <= start)
+				continue;
+
+			/*
+			 * Ensure each efi_fake_mem instance results in
+			 * a unique e820 resource
+			 */
+			e820__range_remove(start, size, E820_TYPE_RAM, 1);
+			e820__range_add(start, size, E820_TYPE_SOFT_RESERVED);
+			e820__update_table(e820_table);
+		}
+	}
+}
diff --git a/arch/x86/platform/efi/memmap.c b/arch/x86/platform/efi/memmap.c
new file mode 100644
index 000000000000..c69f8471e6d0
--- /dev/null
+++ b/arch/x86/platform/efi/memmap.c
@@ -0,0 +1,239 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Common EFI memory map functions.
+ */
+
+#define pr_fmt(fmt) "efi: " fmt
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/efi.h>
+#include <linux/io.h>
+#include <asm/early_ioremap.h>
+#include <asm/efi.h>
+#include <linux/memblock.h>
+#include <linux/slab.h>
+
+static phys_addr_t __init __efi_memmap_alloc_early(unsigned long size)
+{
+	return memblock_phys_alloc(size, SMP_CACHE_BYTES);
+}
+
+static phys_addr_t __init __efi_memmap_alloc_late(unsigned long size)
+{
+	unsigned int order = get_order(size);
+	struct page *p = alloc_pages(GFP_KERNEL, order);
+
+	if (!p)
+		return 0;
+
+	return PFN_PHYS(page_to_pfn(p));
+}
+
+void __init __efi_memmap_free(u64 phys, unsigned long size, unsigned long flags)
+{
+	if (flags & EFI_MEMMAP_MEMBLOCK) {
+		if (slab_is_available())
+			memblock_free_late(phys, size);
+		else
+			memblock_phys_free(phys, size);
+	} else if (flags & EFI_MEMMAP_SLAB) {
+		struct page *p = pfn_to_page(PHYS_PFN(phys));
+		unsigned int order = get_order(size);
+
+		free_pages((unsigned long) page_address(p), order);
+	}
+}
+
+/**
+ * efi_memmap_alloc - Allocate memory for the EFI memory map
+ * @num_entries: Number of entries in the allocated map.
+ * @data: efi memmap installation parameters
+ *
+ * Depending on whether mm_init() has already been invoked or not,
+ * either memblock or "normal" page allocation is used.
+ *
+ * Returns zero on success, a negative error code on failure.
+ */
+int __init efi_memmap_alloc(unsigned int num_entries,
+		struct efi_memory_map_data *data)
+{
+	/* Expect allocation parameters are zero initialized */
+	WARN_ON(data->phys_map || data->size);
+
+	data->size = num_entries * efi.memmap.desc_size;
+	data->desc_version = efi.memmap.desc_version;
+	data->desc_size = efi.memmap.desc_size;
+	data->flags &= ~(EFI_MEMMAP_SLAB | EFI_MEMMAP_MEMBLOCK);
+	data->flags |= efi.memmap.flags & EFI_MEMMAP_LATE;
+
+	if (slab_is_available()) {
+		data->flags |= EFI_MEMMAP_SLAB;
+		data->phys_map = __efi_memmap_alloc_late(data->size);
+	} else {
+		data->flags |= EFI_MEMMAP_MEMBLOCK;
+		data->phys_map = __efi_memmap_alloc_early(data->size);
+	}
+
+	if (!data->phys_map)
+		return -ENOMEM;
+	return 0;
+}
+
+/**
+ * efi_memmap_install - Install a new EFI memory map in efi.memmap
+ * @ctx: map allocation parameters (address, size, flags)
+ *
+ * Unlike efi_memmap_init_*(), this function does not allow the caller
+ * to switch from early to late mappings. It simply uses the existing
+ * mapping function and installs the new memmap.
+ *
+ * Returns zero on success, a negative error code on failure.
+ */
+int __init efi_memmap_install(struct efi_memory_map_data *data)
+{
+	efi_memmap_unmap();
+
+	if (efi_enabled(EFI_PARAVIRT))
+		return 0;
+
+	return __efi_memmap_init(data);
+}
+
+/**
+ * efi_memmap_split_count - Count number of additional EFI memmap entries
+ * @md: EFI memory descriptor to split
+ * @range: Address range (start, end) to split around
+ *
+ * Returns the number of additional EFI memmap entries required to
+ * accommodate @range.
+ */
+int __init efi_memmap_split_count(efi_memory_desc_t *md, struct range *range)
+{
+	u64 m_start, m_end;
+	u64 start, end;
+	int count = 0;
+
+	start = md->phys_addr;
+	end = start + (md->num_pages << EFI_PAGE_SHIFT) - 1;
+
+	/* modifying range */
+	m_start = range->start;
+	m_end = range->end;
+
+	if (m_start <= start) {
+		/* split into 2 parts */
+		if (start < m_end && m_end < end)
+			count++;
+	}
+
+	if (start < m_start && m_start < end) {
+		/* split into 3 parts */
+		if (m_end < end)
+			count += 2;
+		/* split into 2 parts */
+		if (end <= m_end)
+			count++;
+	}
+
+	return count;
+}
+
+/**
+ * efi_memmap_insert - Insert a memory region in an EFI memmap
+ * @old_memmap: The existing EFI memory map structure
+ * @buf: Address of buffer to store new map
+ * @mem: Memory map entry to insert
+ *
+ * It is suggested that you call efi_memmap_split_count() first
+ * to see how large @buf needs to be.
+ */
+void __init efi_memmap_insert(struct efi_memory_map *old_memmap, void *buf,
+			      struct efi_mem_range *mem)
+{
+	u64 m_start, m_end, m_attr;
+	efi_memory_desc_t *md;
+	u64 start, end;
+	void *old, *new;
+
+	/* modifying range */
+	m_start = mem->range.start;
+	m_end = mem->range.end;
+	m_attr = mem->attribute;
+
+	/*
+	 * The EFI memory map deals with regions in EFI_PAGE_SIZE
+	 * units. Ensure that the region described by 'mem' is aligned
+	 * correctly.
+	 */
+	if (!IS_ALIGNED(m_start, EFI_PAGE_SIZE) ||
+	    !IS_ALIGNED(m_end + 1, EFI_PAGE_SIZE)) {
+		WARN_ON(1);
+		return;
+	}
+
+	for (old = old_memmap->map, new = buf;
+	     old < old_memmap->map_end;
+	     old += old_memmap->desc_size, new += old_memmap->desc_size) {
+
+		/* copy original EFI memory descriptor */
+		memcpy(new, old, old_memmap->desc_size);
+		md = new;
+		start = md->phys_addr;
+		end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT) - 1;
+
+		if (m_start <= start && end <= m_end)
+			md->attribute |= m_attr;
+
+		if (m_start <= start &&
+		    (start < m_end && m_end < end)) {
+			/* first part */
+			md->attribute |= m_attr;
+			md->num_pages = (m_end - md->phys_addr + 1) >>
+				EFI_PAGE_SHIFT;
+			/* latter part */
+			new += old_memmap->desc_size;
+			memcpy(new, old, old_memmap->desc_size);
+			md = new;
+			md->phys_addr = m_end + 1;
+			md->num_pages = (end - md->phys_addr + 1) >>
+				EFI_PAGE_SHIFT;
+		}
+
+		if ((start < m_start && m_start < end) && m_end < end) {
+			/* first part */
+			md->num_pages = (m_start - md->phys_addr) >>
+				EFI_PAGE_SHIFT;
+			/* middle part */
+			new += old_memmap->desc_size;
+			memcpy(new, old, old_memmap->desc_size);
+			md = new;
+			md->attribute |= m_attr;
+			md->phys_addr = m_start;
+			md->num_pages = (m_end - m_start + 1) >>
+				EFI_PAGE_SHIFT;
+			/* last part */
+			new += old_memmap->desc_size;
+			memcpy(new, old, old_memmap->desc_size);
+			md = new;
+			md->phys_addr = m_end + 1;
+			md->num_pages = (end - m_end) >>
+				EFI_PAGE_SHIFT;
+		}
+
+		if ((start < m_start && m_start < end) &&
+		    (end <= m_end)) {
+			/* first part */
+			md->num_pages = (m_start - md->phys_addr) >>
+				EFI_PAGE_SHIFT;
+			/* latter part */
+			new += old_memmap->desc_size;
+			memcpy(new, old, old_memmap->desc_size);
+			md = new;
+			md->phys_addr = m_start;
+			md->num_pages = (end - md->phys_addr + 1) >>
+				EFI_PAGE_SHIFT;
+			md->attribute |= m_attr;
+		}
+	}
+}
diff --git a/arch/x86/platform/efi/runtime-map.c b/arch/x86/platform/efi/runtime-map.c
new file mode 100644
index 000000000000..bbee682ef8cd
--- /dev/null
+++ b/arch/x86/platform/efi/runtime-map.c
@@ -0,0 +1,194 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2013 Red Hat, Inc., Dave Young <dyoung@redhat.com>
+ */
+
+#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/efi.h>
+#include <asm/setup.h>
+
+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_MODE(type, 0400);
+static struct map_attribute map_phys_addr_attr = __ATTR_RO_MODE(phys_addr, 0400);
+static struct map_attribute map_virt_addr_attr = __ATTR_RO_MODE(virt_addr, 0400);
+static struct map_attribute map_num_pages_attr = __ATTR_RO_MODE(num_pages, 0400);
+static struct map_attribute map_attribute_attr = __ATTR_RO_MODE(attribute, 0400);
+
+/*
+ * 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
+};
+ATTRIBUTE_GROUPS(def);
+
+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_groups	= def_groups,
+	.release	= map_release,
+};
+
+static struct kset *map_kset;
+
+static struct efi_runtime_map_entry *
+add_sysfs_runtime_map_entry(struct kobject *kobj, int nr,
+			    efi_memory_desc_t *md)
+{
+	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);
+		map_kset = NULL;
+		return ERR_PTR(-ENOMEM);
+	}
+
+	memcpy(&entry->md, md, 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);
+		map_kset = NULL;
+		return ERR_PTR(ret);
+	}
+
+	return entry;
+}
+
+int efi_get_runtime_map_size(void)
+{
+	return efi.memmap.nr_map * efi.memmap.desc_size;
+}
+
+int efi_get_runtime_map_desc_size(void)
+{
+	return efi.memmap.desc_size;
+}
+
+int efi_runtime_map_copy(void *buf, size_t bufsz)
+{
+	size_t sz = efi_get_runtime_map_size();
+
+	if (sz > bufsz)
+		sz = bufsz;
+
+	memcpy(buf, efi.memmap.map, sz);
+	return 0;
+}
+
+static int __init efi_runtime_map_init(void)
+{
+	int i, j, ret = 0;
+	struct efi_runtime_map_entry *entry;
+	efi_memory_desc_t *md;
+
+	if (!efi_enabled(EFI_MEMMAP) || !efi_kobj)
+		return 0;
+
+	map_entries = kcalloc(efi.memmap.nr_map, sizeof(entry), GFP_KERNEL);
+	if (!map_entries) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	i = 0;
+	for_each_efi_memory_desc(md) {
+		entry = add_sysfs_runtime_map_entry(efi_kobj, i, md);
+		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);
+	}
+out:
+	return ret;
+}
+subsys_initcall_sync(efi_runtime_map_init);