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

Pull EFI updates from Ingo Molnar:
 "Main changes in this cycle were:

   - Refactor the EFI memory map code into architecture neutral files
     and allow drivers to permanently reserve EFI boot services regions
     on x86, as well as ARM/arm64. (Matt Fleming)

   - Add ARM support for the EFI ESRT driver. (Ard Biesheuvel)

   - Make the EFI runtime services and efivar API interruptible by
     swapping spinlocks for semaphores. (Sylvain Chouleur)

   - Provide the EFI identity mapping for kexec which allows kexec to
     work on SGI/UV platforms with requiring the "noefi" kernel command
     line parameter. (Alex Thorlton)

   - Add debugfs node to dump EFI page tables on arm64. (Ard Biesheuvel)

   - Merge the EFI test driver being carried out of tree until now in
     the FWTS project. (Ivan Hu)

   - Expand the list of flags for classifying EFI regions as "RAM" on
     arm64 so we align with the UEFI spec. (Ard Biesheuvel)

   - Optimise out the EFI mixed mode if it's unsupported (CONFIG_X86_32)
     or disabled (CONFIG_EFI_MIXED=n) and switch the early EFI boot
     services function table for direct calls, alleviating us from
     having to maintain the custom function table. (Lukas Wunner)

   - Miscellaneous cleanups and fixes"

* 'efi-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (30 commits)
  x86/efi: Round EFI memmap reservations to EFI_PAGE_SIZE
  x86/efi: Allow invocation of arbitrary boot services
  x86/efi: Optimize away setup_gop32/64 if unused
  x86/efi: Use kmalloc_array() in efi_call_phys_prolog()
  efi/arm64: Treat regions with WT/WC set but WB cleared as memory
  efi: Add efi_test driver for exporting UEFI runtime service interfaces
  x86/efi: Defer efi_esrt_init until after memblock_x86_fill
  efi/arm64: Add debugfs node to dump UEFI runtime page tables
  x86/efi: Remove unused find_bits() function
  fs/efivarfs: Fix double kfree() in error path
  x86/efi: Map in physical addresses in efi_map_region_fixed
  lib/ucs2_string: Speed up ucs2_utf8size()
  firmware-gsmi: Delete an unnecessary check before the function call "dma_pool_destroy"
  x86/efi: Initialize status to ensure garbage is not returned on small size
  efi: Replace runtime services spinlock with semaphore
  efi: Don't use spinlocks for efi vars
  efi: Use a file local lock for efivars
  efi/arm*: esrt: Add missing call to efi_esrt_init()
  efi/esrt: Use memremap not ioremap to access ESRT table in memory
  x86/efi-bgrt: Use efi_mem_reserve() to avoid copying image data
  ...

MAINTAINERS

@@ -4587,6 +4587,13 @@ M:	Peter Jones <pjones@redhat.com>
 S:	Maintained
 F:	drivers/video/fbdev/efifb.c
 
+EFI TEST DRIVER
+L:	linux-efi@vger.kernel.org
+M:	Ivan Hu <ivan.hu@canonical.com>
+M:	Matt Fleming <matt@codeblueprint.co.uk>
+S:	Maintained
+F:	drivers/firmware/efi/test/
+
 EFS FILESYSTEM
 W:	http://aeschi.ch.eu.org/efs/
 S:	Orphan

arch/x86/boot/compressed/eboot.c

@@ -29,22 +29,11 @@ __pure const struct efi_config *__efi_early(void)
 static void setup_boot_services##bits(struct efi_config *c)		\
 {									\
 	efi_system_table_##bits##_t *table;				\
-	efi_boot_services_##bits##_t *bt;				\
 									\
 	table = (typeof(table))sys_table;				\
 									\
+	c->boot_services = table->boottime;				\
 	c->text_output = table->con_out;				\
-									\
-	bt = (typeof(bt))(unsigned long)(table->boottime);		\
-									\
-	c->allocate_pool = bt->allocate_pool;				\
-	c->allocate_pages = bt->allocate_pages;				\
-	c->get_memory_map = bt->get_memory_map;				\
-	c->free_pool = bt->free_pool;					\
-	c->free_pages = bt->free_pages;					\
-	c->locate_handle = bt->locate_handle;				\
-	c->handle_protocol = bt->handle_protocol;			\
-	c->exit_boot_services = bt->exit_boot_services;			\
 }
 BOOT_SERVICES(32);
 BOOT_SERVICES(64);
@@ -286,29 +275,6 @@ void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str)
 	}
 }
 
-static void find_bits(unsigned long mask, u8 *pos, u8 *size)
-{
-	u8 first, len;
-
-	first = 0;
-	len = 0;
-
-	if (mask) {
-		while (!(mask & 0x1)) {
-			mask = mask >> 1;
-			first++;
-		}
-
-		while (mask & 0x1) {
-			mask = mask >> 1;
-			len++;
-		}
-	}
-
-	*pos = first;
-	*size = len;
-}
-
 static efi_status_t
 __setup_efi_pci32(efi_pci_io_protocol_32 *pci, struct pci_setup_rom **__rom)
 {
@@ -578,7 +544,7 @@ setup_uga32(void **uga_handle, unsigned long size, u32 *width, u32 *height)
 	efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID;
 	unsigned long nr_ugas;
 	u32 *handles = (u32 *)uga_handle;;
-	efi_status_t status;
+	efi_status_t status = EFI_INVALID_PARAMETER;
 	int i;
 
 	first_uga = NULL;
@@ -623,7 +589,7 @@ setup_uga64(void **uga_handle, unsigned long size, u32 *width, u32 *height)
 	efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID;
 	unsigned long nr_ugas;
 	u64 *handles = (u64 *)uga_handle;;
-	efi_status_t status;
+	efi_status_t status = EFI_INVALID_PARAMETER;
 	int i;
 
 	first_uga = NULL;

arch/x86/boot/compressed/head_32.S

@@ -82,7 +82,7 @@ ENTRY(efi_pe_entry)
 
 	/* Relocate efi_config->call() */
 	leal	efi32_config(%esi), %eax
-	add	%esi, 88(%eax)
+	add	%esi, 32(%eax)
 	pushl	%eax
 
 	call	make_boot_params
@@ -108,7 +108,7 @@ ENTRY(efi32_stub_entry)
 
 	/* Relocate efi_config->call() */
 	leal	efi32_config(%esi), %eax
-	add	%esi, 88(%eax)
+	add	%esi, 32(%eax)
 	pushl	%eax
 2:
 	call	efi_main
@@ -264,7 +264,7 @@ relocated:
 #ifdef CONFIG_EFI_STUB
 	.data
 efi32_config:
-	.fill 11,8,0
+	.fill 4,8,0
 	.long efi_call_phys
 	.long 0
 	.byte 0

arch/x86/boot/compressed/head_64.S

@@ -265,7 +265,7 @@ ENTRY(efi_pe_entry)
 	/*
 	 * Relocate efi_config->call().
 	 */
-	addq	%rbp, efi64_config+88(%rip)
+	addq	%rbp, efi64_config+32(%rip)
 
 	movq	%rax, %rdi
 	call	make_boot_params
@@ -285,7 +285,7 @@ handover_entry:
 	 * Relocate efi_config->call().
 	 */
 	movq	efi_config(%rip), %rax
-	addq	%rbp, 88(%rax)
+	addq	%rbp, 32(%rax)
 2:
 	movq	efi_config(%rip), %rdi
 	call	efi_main
@@ -457,14 +457,14 @@ efi_config:
 #ifdef CONFIG_EFI_MIXED
 	.global efi32_config
 efi32_config:
-	.fill	11,8,0
+	.fill	4,8,0
 	.quad	efi64_thunk
 	.byte	0
 #endif
 
 	.global efi64_config
 efi64_config:
-	.fill	11,8,0
+	.fill	4,8,0
 	.quad	efi_call
 	.byte	1
 #endif /* CONFIG_EFI_STUB */

arch/x86/include/asm/efi.h

@@ -117,7 +117,6 @@ extern int __init efi_memblock_x86_reserve_range(void);
 extern pgd_t * __init efi_call_phys_prolog(void);
 extern void __init efi_call_phys_epilog(pgd_t *save_pgd);
 extern void __init efi_print_memmap(void);
-extern void __init efi_unmap_memmap(void);
 extern void __init 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);
@@ -192,14 +191,7 @@ static inline efi_status_t efi_thunk_set_virtual_address_map(
 struct efi_config {
 	u64 image_handle;
 	u64 table;
-	u64 allocate_pool;
-	u64 allocate_pages;
-	u64 get_memory_map;
-	u64 free_pool;
-	u64 free_pages;
-	u64 locate_handle;
-	u64 handle_protocol;
-	u64 exit_boot_services;
+	u64 boot_services;
 	u64 text_output;
 	efi_status_t (*call)(unsigned long, ...);
 	bool is64;
@@ -207,14 +199,27 @@ struct efi_config {
 
 __pure const struct efi_config *__efi_early(void);
 
+static inline bool efi_is_64bit(void)
+{
+	if (!IS_ENABLED(CONFIG_X86_64))
+		return false;
+
+	if (!IS_ENABLED(CONFIG_EFI_MIXED))
+		return true;
+
+	return __efi_early()->is64;
+}
+
 #define efi_call_early(f, ...)						\
-	__efi_early()->call(__efi_early()->f, __VA_ARGS__);
+	__efi_early()->call(efi_is_64bit() ?				\
+		((efi_boot_services_64_t *)(unsigned long)		\
+			__efi_early()->boot_services)->f :		\
+		((efi_boot_services_32_t *)(unsigned long)		\
+			__efi_early()->boot_services)->f, __VA_ARGS__)
 
 #define __efi_call_early(f, ...)					\
 	__efi_early()->call((unsigned long)f, __VA_ARGS__);
 
-#define efi_is_64bit()		__efi_early()->is64
-
 extern bool efi_reboot_required(void);
 
 #else

arch/x86/kernel/setup.c

@@ -1096,19 +1096,19 @@ void __init setup_arch(char **cmdline_p)
 	memblock_set_current_limit(ISA_END_ADDRESS);
 	memblock_x86_fill();
 
-	if (efi_enabled(EFI_BOOT)) {
+	reserve_bios_regions();
+
+	if (efi_enabled(EFI_MEMMAP)) {
 		efi_fake_memmap();
 		efi_find_mirror();
-	}
-
-	reserve_bios_regions();
+		efi_esrt_init();
 
-	/*
-	 * The EFI specification says that boot service code won't be called
-	 * after ExitBootServices(). This is, in fact, a lie.
-	 */
-	if (efi_enabled(EFI_MEMMAP))
+		/*
+		 * The EFI specification says that boot service code won't be
+		 * called after ExitBootServices(). This is, in fact, a lie.
+		 */
 		efi_reserve_boot_services();
+	}
 
 	/* preallocate 4k for mptable mpc */
 	early_reserve_e820_mpc_new();

arch/x86/platform/efi/efi-bgrt.c

@@ -82,21 +82,12 @@ void __init efi_bgrt_init(void)
 	}
 	bgrt_image_size = bmp_header.size;
 
-	bgrt_image = kmalloc(bgrt_image_size, GFP_KERNEL | __GFP_NOWARN);
+	bgrt_image = memremap(bgrt_tab->image_address, bmp_header.size, MEMREMAP_WB);
 	if (!bgrt_image) {
-		pr_notice("Ignoring BGRT: failed to allocate memory for image (wanted %zu bytes)\n",
-		       bgrt_image_size);
-		return;
-	}
-
-	image = memremap(bgrt_tab->image_address, bmp_header.size, MEMREMAP_WB);
-	if (!image) {
 		pr_notice("Ignoring BGRT: failed to map image memory\n");
-		kfree(bgrt_image);
 		bgrt_image = NULL;
 		return;
 	}
 
-	memcpy(bgrt_image, image, bgrt_image_size);
-	memunmap(image);
+	efi_mem_reserve(bgrt_tab->image_address, bgrt_image_size);
 }

arch/x86/platform/efi/efi.c

@@ -172,7 +172,9 @@ static void __init do_add_efi_memmap(void)
 int __init efi_memblock_x86_reserve_range(void)
 {
 	struct efi_info *e = &boot_params.efi_info;
+	struct efi_memory_map_data data;
 	phys_addr_t pmap;
+	int rv;
 
 	if (efi_enabled(EFI_PARAVIRT))
 		return 0;
@@ -187,11 +189,17 @@ int __init efi_memblock_x86_reserve_range(void)
 #else
 	pmap = (e->efi_memmap |	((__u64)e->efi_memmap_hi << 32));
 #endif
-	efi.memmap.phys_map	= pmap;
-	efi.memmap.nr_map	= e->efi_memmap_size /
-				  e->efi_memdesc_size;
-	efi.memmap.desc_size	= e->efi_memdesc_size;
-	efi.memmap.desc_version	= e->efi_memdesc_version;
+	data.phys_map		= pmap;
+	data.size 		= e->efi_memmap_size;
+	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 (add_efi_memmap)
+		do_add_efi_memmap();
 
 	WARN(efi.memmap.desc_version != 1,
 	     "Unexpected EFI_MEMORY_DESCRIPTOR version %ld",
@@ -218,19 +226,6 @@ void __init efi_print_memmap(void)
 	}
 }
 
-void __init efi_unmap_memmap(void)
-{
-	unsigned long size;
-
-	clear_bit(EFI_MEMMAP, &efi.flags);
-
-	size = efi.memmap.nr_map * efi.memmap.desc_size;
-	if (efi.memmap.map) {
-		early_memunmap(efi.memmap.map, size);
-		efi.memmap.map = NULL;
-	}
-}
-
 static int __init efi_systab_init(void *phys)
 {
 	if (efi_enabled(EFI_64BIT)) {
@@ -414,33 +409,6 @@ static int __init efi_runtime_init(void)
 	return 0;
 }
 
-static int __init efi_memmap_init(void)
-{
-	unsigned long addr, size;
-
-	if (efi_enabled(EFI_PARAVIRT))
-		return 0;
-
-	/* Map the EFI memory map */
-	size = efi.memmap.nr_map * efi.memmap.desc_size;
-	addr = (unsigned long)efi.memmap.phys_map;
-
-	efi.memmap.map = early_memremap(addr, size);
-	if (efi.memmap.map == NULL) {
-		pr_err("Could not map the memory map!\n");
-		return -ENOMEM;
-	}
-
-	efi.memmap.map_end = efi.memmap.map + size;
-
-	if (add_efi_memmap)
-		do_add_efi_memmap();
-
-	set_bit(EFI_MEMMAP, &efi.flags);
-
-	return 0;
-}
-
 void __init efi_init(void)
 {
 	efi_char16_t *c16;
@@ -498,16 +466,14 @@ void __init efi_init(void)
 	if (!efi_runtime_supported())
 		pr_info("No EFI runtime due to 32/64-bit mismatch with kernel\n");
 	else {
-		if (efi_runtime_disabled() || efi_runtime_init())
+		if (efi_runtime_disabled() || efi_runtime_init()) {
+			efi_memmap_unmap();
 			return;
+		}
 	}
-	if (efi_memmap_init())
-		return;
 
 	if (efi_enabled(EFI_DBG))
 		efi_print_memmap();
-
-	efi_esrt_init();
 }
 
 void __init efi_late_init(void)
@@ -624,42 +590,6 @@ static void __init get_systab_virt_addr(efi_memory_desc_t *md)
 	}
 }
 
-static void __init save_runtime_map(void)
-{
-#ifdef CONFIG_KEXEC_CORE
-	unsigned long desc_size;
-	efi_memory_desc_t *md;
-	void *tmp, *q = NULL;
-	int count = 0;
-
-	if (efi_enabled(EFI_OLD_MEMMAP))
-		return;
-
-	desc_size = efi.memmap.desc_size;
-
-	for_each_efi_memory_desc(md) {
-		if (!(md->attribute & EFI_MEMORY_RUNTIME) ||
-		    (md->type == EFI_BOOT_SERVICES_CODE) ||
-		    (md->type == EFI_BOOT_SERVICES_DATA))
-			continue;
-		tmp = krealloc(q, (count + 1) * desc_size, GFP_KERNEL);
-		if (!tmp)
-			goto out;
-		q = tmp;
-
-		memcpy(q + count * desc_size, md, desc_size);
-		count++;
-	}
-
-	efi_runtime_map_setup(q, count, desc_size);
-	return;
-
-out:
-	kfree(q);
-	pr_err("Error saving runtime map, efi runtime on kexec non-functional!!\n");
-#endif
-}
-
 static void *realloc_pages(void *old_memmap, int old_shift)
 {
 	void *ret;
@@ -745,6 +675,46 @@ static void *efi_map_next_entry(void *entry)
 	return entry;
 }
 
+static bool should_map_region(efi_memory_desc_t *md)
+{
+	/*
+	 * Runtime regions always require runtime mappings (obviously).
+	 */
+	if (md->attribute & EFI_MEMORY_RUNTIME)
+		return true;
+
+	/*
+	 * 32-bit EFI doesn't suffer from the bug that requires us to
+	 * reserve boot services regions, and mixed mode support
+	 * doesn't exist for 32-bit kernels.
+	 */
+	if (IS_ENABLED(CONFIG_X86_32))
+		return false;
+
+	/*
+	 * Map all of RAM so that we can access arguments in the 1:1
+	 * mapping when making EFI runtime calls.
+	 */
+	if (IS_ENABLED(CONFIG_EFI_MIXED) && !efi_is_native()) {
+		if (md->type == EFI_CONVENTIONAL_MEMORY ||
+		    md->type == EFI_LOADER_DATA ||
+		    md->type == EFI_LOADER_CODE)
+			return true;
+	}
+
+	/*
+	 * Map boot services regions as a workaround for buggy
+	 * firmware that accesses them even when they shouldn't.
+	 *
+	 * See efi_{reserve,free}_boot_services().
+	 */
+	if (md->type == EFI_BOOT_SERVICES_CODE ||
+	    md->type == EFI_BOOT_SERVICES_DATA)
+		return true;
+
+	return false;
+}
+
 /*
  * Map the efi memory ranges of the runtime services and update new_mmap with
  * virtual addresses.
@@ -761,13 +731,9 @@ static void * __init efi_map_regions(int *count, int *pg_shift)
 	p = NULL;
 	while ((p = efi_map_next_entry(p))) {
 		md = p;
-		if (!(md->attribute & EFI_MEMORY_RUNTIME)) {
-#ifdef CONFIG_X86_64
-			if (md->type != EFI_BOOT_SERVICES_CODE &&
-			    md->type != EFI_BOOT_SERVICES_DATA)
-#endif
-				continue;
-		}
+
+		if (!should_map_region(md))
+			continue;
 
 		efi_map_region(md);
 		get_systab_virt_addr(md);
@@ -803,7 +769,7 @@ static void __init kexec_enter_virtual_mode(void)
 	 * non-native EFI
 	 */
 	if (!efi_is_native()) {
-		efi_unmap_memmap();
+		efi_memmap_unmap();
 		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
 		return;
 	}
@@ -823,7 +789,18 @@ static void __init kexec_enter_virtual_mode(void)
 		get_systab_virt_addr(md);
 	}
 
-	save_runtime_map();
+	/*
+	 * Unregister the early EFI memmap from efi_init() and install
+	 * the new EFI memory map.
+	 */
+	efi_memmap_unmap();
+
+	if (efi_memmap_init_late(efi.memmap.phys_map,
+				 efi.memmap.desc_size * efi.memmap.nr_map)) {
+		pr_err("Failed to remap late EFI memory map\n");
+		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+		return;
+	}
 
 	BUG_ON(!efi.systab);
 
@@ -884,6 +861,7 @@ static void __init __efi_enter_virtual_mode(void)
 	int count = 0, pg_shift = 0;
 	void *new_memmap = NULL;
 	efi_status_t status;
+	phys_addr_t pa;
 
 	efi.systab = NULL;
 
@@ -901,11 +879,24 @@ static void __init __efi_enter_virtual_mode(void)
 		return;
 	}
 
-	save_runtime_map();
+	pa = __pa(new_memmap);
+
+	/*
+	 * Unregister the early EFI memmap from efi_init() and install
+	 * the new EFI memory map that we are about to pass to the
+	 * firmware via SetVirtualAddressMap().
+	 */
+	efi_memmap_unmap();
+
+	if (efi_memmap_init_late(pa, efi.memmap.desc_size * count)) {
+		pr_err("Failed to remap late EFI memory map\n");
+		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+		return;
+	}
 
 	BUG_ON(!efi.systab);
 
-	if (efi_setup_page_tables(__pa(new_memmap), 1 << pg_shift)) {
+	if (efi_setup_page_tables(pa, 1 << pg_shift)) {
 		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
 		return;
 	}
@@ -917,14 +908,14 @@ static void __init __efi_enter_virtual_mode(void)
 				efi.memmap.desc_size * count,
 				efi.memmap.desc_size,
 				efi.memmap.desc_version,
-				(efi_memory_desc_t *)__pa(new_memmap));
+				(efi_memory_desc_t *)pa);
 	} else {
 		status = efi_thunk_set_virtual_address_map(
 				efi_phys.set_virtual_address_map,
 				efi.memmap.desc_size * count,
 				efi.memmap.desc_size,
 				efi.memmap.desc_version,
-				(efi_memory_desc_t *)__pa(new_memmap));
+				(efi_memory_desc_t *)pa);
 	}
 
 	if (status != EFI_SUCCESS) {
@@ -956,15 +947,6 @@ static void __init __efi_enter_virtual_mode(void)
 	efi_runtime_update_mappings();
 	efi_dump_pagetable();
 
-	/*
-	 * We mapped the descriptor array into the EFI pagetable above
-	 * but we're not unmapping it here because if we're running in
-	 * EFI mixed mode we need all of memory to be accessible when
-	 * we pass parameters to the EFI runtime services in the
-	 * thunking code.
-	 */
-	free_pages((unsigned long)new_memmap, pg_shift);
-
 	/* clean DUMMY object */
 	efi_delete_dummy_variable();
 }

arch/x86/platform/efi/efi_64.c

@@ -85,7 +85,7 @@ pgd_t * __init efi_call_phys_prolog(void)
 	early_code_mapping_set_exec(1);
 
 	n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT), PGDIR_SIZE);
-	save_pgd = kmalloc(n_pgds * sizeof(pgd_t), GFP_KERNEL);
+	save_pgd = kmalloc_array(n_pgds, sizeof(*save_pgd), GFP_KERNEL);
 
 	for (pgd = 0; pgd < n_pgds; pgd++) {
 		save_pgd[pgd] = *pgd_offset_k(pgd * PGDIR_SIZE);
@@ -214,7 +214,6 @@ void efi_sync_low_kernel_mappings(void)
 int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 {
 	unsigned long pfn, text;
-	efi_memory_desc_t *md;
 	struct page *page;
 	unsigned npages;
 	pgd_t *pgd;
@@ -248,25 +247,6 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 	if (!IS_ENABLED(CONFIG_EFI_MIXED) || efi_is_native())
 		return 0;
 
-	/*
-	 * Map all of RAM so that we can access arguments in the 1:1
-	 * mapping when making EFI runtime calls.
-	 */
-	for_each_efi_memory_desc(md) {
-		if (md->type != EFI_CONVENTIONAL_MEMORY &&
-		    md->type != EFI_LOADER_DATA &&
-		    md->type != EFI_LOADER_CODE)
-			continue;
-
-		pfn = md->phys_addr >> PAGE_SHIFT;
-		npages = md->num_pages;
-
-		if (kernel_map_pages_in_pgd(pgd, pfn, md->phys_addr, npages, _PAGE_RW)) {
-			pr_err("Failed to map 1:1 memory\n");
-			return 1;
-		}
-	}
-
 	page = alloc_page(GFP_KERNEL|__GFP_DMA32);
 	if (!page)
 		panic("Unable to allocate EFI runtime stack < 4GB\n");
@@ -359,6 +339,7 @@ void __init efi_map_region(efi_memory_desc_t *md)
  */
 void __init efi_map_region_fixed(efi_memory_desc_t *md)
 {
+	__map_region(md, md->phys_addr);
 	__map_region(md, md->virt_addr);
 }
 

arch/x86/platform/efi/quirks.c

@@ -163,6 +163,75 @@ efi_status_t efi_query_variable_store(u32 attributes, unsigned long size,
 }
 EXPORT_SYMBOL_GPL(efi_query_variable_store);
 
+/*
+ * The UEFI specification makes it clear that the operating system is
+ * free to do whatever it wants with boot services code after
+ * ExitBootServices() has been called. Ignoring this recommendation a
+ * significant bunch of EFI implementations continue calling into boot
+ * services code (SetVirtualAddressMap). In order to work around such
+ * buggy implementations we reserve boot services region during EFI
+ * init and make sure it stays executable. Then, after
+ * SetVirtualAddressMap(), it is discarded.
+ *
+ * However, some boot services regions contain data that is required
+ * by drivers, so we need to track which memory ranges can never be
+ * freed. This is done by tagging those regions with the
+ * EFI_MEMORY_RUNTIME attribute.
+ *
+ * Any driver that wants to mark a region as reserved must use
+ * efi_mem_reserve() which will insert a new EFI memory descriptor
+ * into efi.memmap (splitting existing regions if necessary) and tag
+ * it with EFI_MEMORY_RUNTIME.
+ */
+void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size)
+{
+	phys_addr_t new_phys, new_size;
+	struct efi_mem_range mr;
+	efi_memory_desc_t md;
+	int num_entries;
+	void *new;
+
+	if (efi_mem_desc_lookup(addr, &md)) {
+		pr_err("Failed to lookup EFI memory descriptor for %pa\n", &addr);
+		return;
+	}
+
+	if (addr + size > md.phys_addr + (md.num_pages << EFI_PAGE_SHIFT)) {
+		pr_err("Region spans EFI memory descriptors, %pa\n", &addr);
+		return;
+	}
+
+	size += addr % EFI_PAGE_SIZE;
+	size = round_up(size, EFI_PAGE_SIZE);
+	addr = round_down(addr, EFI_PAGE_SIZE);
+
+	mr.range.start = addr;
+	mr.range.end = addr + size - 1;
+	mr.attribute = md.attribute | EFI_MEMORY_RUNTIME;
+
+	num_entries = efi_memmap_split_count(&md, &mr.range);
+	num_entries += efi.memmap.nr_map;
+
+	new_size = efi.memmap.desc_size * num_entries;
+
+	new_phys = memblock_alloc(new_size, 0);
+	if (!new_phys) {
+		pr_err("Could not allocate boot services memmap\n");
+		return;
+	}
+
+	new = early_memremap(new_phys, new_size);
+	if (!new) {
+		pr_err("Failed to map new boot services memmap\n");
+		return;
+	}
+
+	efi_memmap_insert(&efi.memmap, new, &mr);
+	early_memunmap(new, new_size);
+
+	efi_memmap_install(new_phys, num_entries);
+}
+
 /*
  * Helper function for efi_reserve_boot_services() to figure out if we
  * can free regions in efi_free_boot_services().
@@ -184,15 +253,6 @@ static bool can_free_region(u64 start, u64 size)
 	return true;
 }
 
-/*
- * The UEFI specification makes it clear that the operating system is free to do
- * whatever it wants with boot services code after ExitBootServices() has been
- * called. Ignoring this recommendation a significant bunch of EFI implementations 
- * continue calling into boot services code (SetVirtualAddressMap). In order to 
- * work around such buggy implementations we reserve boot services region during 
- * EFI init and make sure it stays executable. Then, after SetVirtualAddressMap(), it
-* is discarded.
-*/
 void __init efi_reserve_boot_services(void)
 {
 	efi_memory_desc_t *md;
@@ -249,7 +309,10 @@ void __init efi_reserve_boot_services(void)
 
 void __init efi_free_boot_services(void)
 {
+	phys_addr_t new_phys, new_size;
 	efi_memory_desc_t *md;
+	int num_entries = 0;
+	void *new, *new_md;
 
 	for_each_efi_memory_desc(md) {
 		unsigned long long start = md->phys_addr;
@@ -257,12 +320,16 @@ void __init efi_free_boot_services(void)
 		size_t rm_size;
 
 		if (md->type != EFI_BOOT_SERVICES_CODE &&
-		    md->type != EFI_BOOT_SERVICES_DATA)
+		    md->type != EFI_BOOT_SERVICES_DATA) {
+			num_entries++;
 			continue;
+		}
 
 		/* Do not free, someone else owns it: */
-		if (md->attribute & EFI_MEMORY_RUNTIME)
+		if (md->attribute & EFI_MEMORY_RUNTIME) {
+			num_entries++;
 			continue;
+		}
 
 		/*
 		 * Nasty quirk: if all sub-1MB memory is used for boot
@@ -287,7 +354,41 @@ void __init efi_free_boot_services(void)
 		free_bootmem_late(start, size);
 	}
 
-	efi_unmap_memmap();
+	new_size = efi.memmap.desc_size * num_entries;
+	new_phys = memblock_alloc(new_size, 0);
+	if (!new_phys) {
+		pr_err("Failed to allocate new EFI memmap\n");
+		return;
+	}
+
+	new = memremap(new_phys, new_size, MEMREMAP_WB);
+	if (!new) {
+		pr_err("Failed to map new EFI memmap\n");
+		return;
+	}
+
+	/*
+	 * Build a new EFI memmap that excludes any boot services
+	 * regions that are not tagged EFI_MEMORY_RUNTIME, since those
+	 * regions have now been freed.
+	 */
+	new_md = new;
+	for_each_efi_memory_desc(md) {
+		if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
+		    (md->type == EFI_BOOT_SERVICES_CODE ||
+		     md->type == EFI_BOOT_SERVICES_DATA))
+			continue;
+
+		memcpy(new_md, md, efi.memmap.desc_size);
+		new_md += efi.memmap.desc_size;
+	}
+
+	memunmap(new);
+
+	if (efi_memmap_install(new_phys, num_entries)) {
+		pr_err("Could not install new EFI memmap\n");
+		return;
+	}
 }
 
 /*
@@ -365,7 +466,7 @@ void __init efi_apply_memmap_quirks(void)
 	 */
 	if (!efi_runtime_supported()) {
 		pr_info("Setup done, disabling due to 32/64-bit mismatch\n");
-		efi_unmap_memmap();
+		efi_memmap_unmap();
 	}
 
 	/* UV2+ BIOS has a fix for this issue.  UV1 still needs the quirk. */

drivers/firmware/efi/Kconfig

@@ -112,6 +112,23 @@ config EFI_CAPSULE_LOADER
 
 	  Most users should say N.
 
+config EFI_TEST
+	tristate "EFI Runtime Service Tests Support"
+	depends on EFI
+	default n
+	help
+	  This driver uses the efi.<service> function pointers directly instead
+	  of going through the efivar API, because it is not trying to test the
+	  kernel subsystem, just for testing the UEFI runtime service
+	  interfaces which are provided by the firmware. This driver is used
+	  by the Firmware Test Suite (FWTS) for testing the UEFI runtime
+	  interfaces readiness of the firmware.
+	  Details for FWTS are available from:
+	  <https://wiki.ubuntu.com/FirmwareTestSuite>
+
+	  Say Y here to enable the runtime services support via /dev/efi_test.
+	  If unsure, say N.
+
 endmenu
 
 config UEFI_CPER

drivers/firmware/efi/Makefile

@@ -10,7 +10,7 @@
 KASAN_SANITIZE_runtime-wrappers.o	:= n
 
 obj-$(CONFIG_EFI)			+= efi.o vars.o reboot.o memattr.o
-obj-$(CONFIG_EFI)			+= capsule.o
+obj-$(CONFIG_EFI)			+= capsule.o memmap.o
 obj-$(CONFIG_EFI_VARS)			+= efivars.o
 obj-$(CONFIG_EFI_ESRT)			+= esrt.o
 obj-$(CONFIG_EFI_VARS_PSTORE)		+= efi-pstore.o
@@ -20,6 +20,7 @@ obj-$(CONFIG_EFI_RUNTIME_WRAPPERS)	+= runtime-wrappers.o
 obj-$(CONFIG_EFI_STUB)			+= libstub/
 obj-$(CONFIG_EFI_FAKE_MEMMAP)		+= fake_mem.o
 obj-$(CONFIG_EFI_BOOTLOADER_CONTROL)	+= efibc.o
+obj-$(CONFIG_EFI_TEST)			+= test/
 
 arm-obj-$(CONFIG_EFI)			:= arm-init.o arm-runtime.o
 obj-$(CONFIG_ARM)			+= $(arm-obj-y)

drivers/firmware/efi/arm-init.c

@@ -26,9 +26,9 @@
 
 u64 efi_system_table;
 
-static int __init is_normal_ram(efi_memory_desc_t *md)
+static int __init is_memory(efi_memory_desc_t *md)
 {
-	if (md->attribute & EFI_MEMORY_WB)
+	if (md->attribute & (EFI_MEMORY_WB|EFI_MEMORY_WT|EFI_MEMORY_WC))
 		return 1;
 	return 0;
 }
@@ -152,9 +152,9 @@ static int __init uefi_init(void)
 }
 
 /*
- * Return true for RAM regions we want to permanently reserve.
+ * Return true for regions that can be used as System RAM.
  */
-static __init int is_reserve_region(efi_memory_desc_t *md)
+static __init int is_usable_memory(efi_memory_desc_t *md)
 {
 	switch (md->type) {
 	case EFI_LOADER_CODE:
@@ -163,18 +163,22 @@ static __init int is_reserve_region(efi_memory_desc_t *md)
 	case EFI_BOOT_SERVICES_DATA:
 	case EFI_CONVENTIONAL_MEMORY:
 	case EFI_PERSISTENT_MEMORY:
-		return 0;
+		/*
+		 * According to the spec, these regions are no longer reserved
+		 * after calling ExitBootServices(). However, we can only use
+		 * them as System RAM if they can be mapped writeback cacheable.
+		 */
+		return (md->attribute & EFI_MEMORY_WB);
 	default:
 		break;
 	}
-	return is_normal_ram(md);
+	return false;
 }
 
 static __init void reserve_regions(void)
 {
 	efi_memory_desc_t *md;
 	u64 paddr, npages, size;
-	int resv;
 
 	if (efi_enabled(EFI_DBG))
 		pr_info("Processing EFI memory map:\n");
@@ -191,32 +195,29 @@ static __init void reserve_regions(void)
 		paddr = md->phys_addr;
 		npages = md->num_pages;
 
-		resv = is_reserve_region(md);
 		if (efi_enabled(EFI_DBG)) {
 			char buf[64];
 
-			pr_info("  0x%012llx-0x%012llx %s%s\n",
+			pr_info("  0x%012llx-0x%012llx %s\n",
 				paddr, paddr + (npages << EFI_PAGE_SHIFT) - 1,
-				efi_md_typeattr_format(buf, sizeof(buf), md),
-				resv ? "*" : "");
+				efi_md_typeattr_format(buf, sizeof(buf), md));
 		}
 
 		memrange_efi_to_native(&paddr, &npages);
 		size = npages << PAGE_SHIFT;
 
-		if (is_normal_ram(md))
+		if (is_memory(md)) {
 			early_init_dt_add_memory_arch(paddr, size);
 
-		if (resv)
-			memblock_mark_nomap(paddr, size);
-
+			if (!is_usable_memory(md))
+				memblock_mark_nomap(paddr, size);
+		}
 	}
-
-	set_bit(EFI_MEMMAP, &efi.flags);
 }
 
 void __init efi_init(void)
 {
+	struct efi_memory_map_data data;
 	struct efi_fdt_params params;
 
 	/* Grab UEFI information placed in FDT by stub */
@@ -225,9 +226,12 @@ void __init efi_init(void)
 
 	efi_system_table = params.system_table;
 
-	efi.memmap.phys_map = params.mmap;
-	efi.memmap.map = early_memremap_ro(params.mmap, params.mmap_size);
-	if (efi.memmap.map == NULL) {
+	data.desc_version = params.desc_ver;
+	data.desc_size = params.desc_size;
+	data.size = params.mmap_size;
+	data.phys_map = params.mmap;
+
+	if (efi_memmap_init_early(&data) < 0) {
 		/*
 		* If we are booting via UEFI, the UEFI memory map is the only
 		* description of memory we have, so there is little point in
@@ -235,9 +239,6 @@ void __init efi_init(void)
 		*/
 		panic("Unable to map EFI memory map.\n");
 	}
-	efi.memmap.map_end = efi.memmap.map + params.mmap_size;
-	efi.memmap.desc_size = params.desc_size;
-	efi.memmap.desc_version = params.desc_ver;
 
 	WARN(efi.memmap.desc_version != 1,
 	     "Unexpected EFI_MEMORY_DESCRIPTOR version %ld",
@@ -248,7 +249,8 @@ void __init efi_init(void)
 
 	reserve_regions();
 	efi_memattr_init();
-	early_memunmap(efi.memmap.map, params.mmap_size);
+	efi_esrt_init();
+	efi_memmap_unmap();
 
 	memblock_reserve(params.mmap & PAGE_MASK,
 			 PAGE_ALIGN(params.mmap_size +

drivers/firmware/efi/arm-runtime.c

@@ -39,6 +39,26 @@ static struct mm_struct efi_mm = {
 	.mmlist			= LIST_HEAD_INIT(efi_mm.mmlist),
 };
 
+#ifdef CONFIG_ARM64_PTDUMP
+#include <asm/ptdump.h>
+
+static struct ptdump_info efi_ptdump_info = {
+	.mm		= &efi_mm,
+	.markers	= (struct addr_marker[]){
+		{ 0,		"UEFI runtime start" },
+		{ TASK_SIZE_64,	"UEFI runtime end" }
+	},
+	.base_addr	= 0,
+};
+
+static int __init ptdump_init(void)
+{
+	return ptdump_register(&efi_ptdump_info, "efi_page_tables");
+}
+device_initcall(ptdump_init);
+
+#endif
+
 static bool __init efi_virtmap_init(void)
 {
 	efi_memory_desc_t *md;
@@ -114,14 +134,12 @@ static int __init arm_enable_runtime_services(void)
 
 	pr_info("Remapping and enabling EFI services.\n");
 
-	mapsize = efi.memmap.map_end - efi.memmap.map;
+	mapsize = efi.memmap.desc_size * efi.memmap.nr_map;
 
-	efi.memmap.map = memremap(efi.memmap.phys_map, mapsize, MEMREMAP_WB);
-	if (!efi.memmap.map) {
+	if (efi_memmap_init_late(efi.memmap.phys_map, mapsize)) {
 		pr_err("Failed to remap EFI memory map\n");
 		return -ENOMEM;
 	}
-	efi.memmap.map_end = efi.memmap.map + mapsize;
 
 	if (!efi_virtmap_init()) {
 		pr_err("UEFI virtual mapping missing or invalid -- runtime services will not be available\n");

drivers/firmware/efi/efi-pstore.c

@@ -125,16 +125,19 @@ static void efi_pstore_scan_sysfs_enter(struct efivar_entry *pos,
  * @entry: deleting entry
  * @turn_off_scanning: Check if a scanning flag should be turned off
  */
-static inline void __efi_pstore_scan_sysfs_exit(struct efivar_entry *entry,
+static inline int __efi_pstore_scan_sysfs_exit(struct efivar_entry *entry,
 						bool turn_off_scanning)
 {
 	if (entry->deleting) {
 		list_del(&entry->list);
 		efivar_entry_iter_end();
 		efivar_unregister(entry);
-		efivar_entry_iter_begin();
+		if (efivar_entry_iter_begin())
+			return -EINTR;
 	} else if (turn_off_scanning)
 		entry->scanning = false;
+
+	return 0;
 }
 
 /**
@@ -144,13 +147,18 @@ static inline void __efi_pstore_scan_sysfs_exit(struct efivar_entry *entry,
  * @head: list head
  * @stop: a flag checking if scanning will stop
  */
-static void efi_pstore_scan_sysfs_exit(struct efivar_entry *pos,
+static int efi_pstore_scan_sysfs_exit(struct efivar_entry *pos,
 				       struct efivar_entry *next,
 				       struct list_head *head, bool stop)
 {
-	__efi_pstore_scan_sysfs_exit(pos, true);
+	int ret = __efi_pstore_scan_sysfs_exit(pos, true);
+
+	if (ret)
+		return ret;
+
 	if (stop)
-		__efi_pstore_scan_sysfs_exit(next, &next->list != head);
+		ret = __efi_pstore_scan_sysfs_exit(next, &next->list != head);
+	return ret;
 }
 
 /**
@@ -172,13 +180,17 @@ static int efi_pstore_sysfs_entry_iter(void *data, struct efivar_entry **pos)
 	struct efivar_entry *entry, *n;
 	struct list_head *head = &efivar_sysfs_list;
 	int size = 0;
+	int ret;
 
 	if (!*pos) {
 		list_for_each_entry_safe(entry, n, head, list) {
 			efi_pstore_scan_sysfs_enter(entry, n, head);
 
 			size = efi_pstore_read_func(entry, data);
-			efi_pstore_scan_sysfs_exit(entry, n, head, size < 0);
+			ret = efi_pstore_scan_sysfs_exit(entry, n, head,
+							 size < 0);
+			if (ret)
+				return ret;
 			if (size)
 				break;
 		}
@@ -190,7 +202,9 @@ static int efi_pstore_sysfs_entry_iter(void *data, struct efivar_entry **pos)
 		efi_pstore_scan_sysfs_enter((*pos), n, head);
 
 		size = efi_pstore_read_func((*pos), data);
-		efi_pstore_scan_sysfs_exit((*pos), n, head, size < 0);
+		ret = efi_pstore_scan_sysfs_exit((*pos), n, head, size < 0);
+		if (ret)
+			return ret;
 		if (size)
 			break;
 	}
@@ -232,7 +246,10 @@ static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type,
 	if (!*data.buf)
 		return -ENOMEM;
 
-	efivar_entry_iter_begin();
+	if (efivar_entry_iter_begin()) {
+		kfree(*data.buf);
+		return -EINTR;
+	}
 	size = efi_pstore_sysfs_entry_iter(&data,
 					   (struct efivar_entry **)&psi->data);
 	efivar_entry_iter_end();
@@ -347,7 +364,8 @@ static int efi_pstore_erase(enum pstore_type_id type, u64 id, int count,
 	edata.time = time;
 	edata.name = efi_name;
 
-	efivar_entry_iter_begin();
+	if (efivar_entry_iter_begin())
+		return -EINTR;
 	found = __efivar_entry_iter(efi_pstore_erase_func, &efivar_sysfs_list, &edata, &entry);
 
 	if (found && !entry->scanning) {

drivers/firmware/efi/efi.c

@@ -27,6 +27,7 @@
 #include <linux/slab.h>
 #include <linux/acpi.h>
 #include <linux/ucs2_string.h>
+#include <linux/memblock.h>
 
 #include <asm/early_ioremap.h>
 
@@ -347,56 +348,31 @@ subsys_initcall(efisubsys_init);
 
 /*
  * Find the efi memory descriptor for a given physical address.  Given a
- * physicall address, determine if it exists within an EFI Memory Map entry,
+ * physical address, determine if it exists within an EFI Memory Map entry,
  * and if so, populate the supplied memory descriptor with the appropriate
  * data.
  */
 int __init efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md)
 {
-	struct efi_memory_map *map = &efi.memmap;
-	phys_addr_t p, e;
+	efi_memory_desc_t *md;
 
 	if (!efi_enabled(EFI_MEMMAP)) {
 		pr_err_once("EFI_MEMMAP is not enabled.\n");
 		return -EINVAL;
 	}
 
-	if (!map) {
-		pr_err_once("efi.memmap is not set.\n");
-		return -EINVAL;
-	}
 	if (!out_md) {
 		pr_err_once("out_md is null.\n");
 		return -EINVAL;
         }
-	if (WARN_ON_ONCE(!map->phys_map))
-		return -EINVAL;
-	if (WARN_ON_ONCE(map->nr_map == 0) || WARN_ON_ONCE(map->desc_size == 0))
-		return -EINVAL;
 
-	e = map->phys_map + map->nr_map * map->desc_size;
-	for (p = map->phys_map; p < e; p += map->desc_size) {
-		efi_memory_desc_t *md;
+	for_each_efi_memory_desc(md) {
 		u64 size;
 		u64 end;
 
-		/*
-		 * If a driver calls this after efi_free_boot_services,
-		 * ->map will be NULL, and the target may also not be mapped.
-		 * So just always get our own virtual map on the CPU.
-		 *
-		 */
-		md = early_memremap(p, sizeof (*md));
-		if (!md) {
-			pr_err_once("early_memremap(%pa, %zu) failed.\n",
-				    &p, sizeof (*md));
-			return -ENOMEM;
-		}
-
 		if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
 		    md->type != EFI_BOOT_SERVICES_DATA &&
 		    md->type != EFI_RUNTIME_SERVICES_DATA) {
-			early_memunmap(md, sizeof (*md));
 			continue;
 		}
 
@@ -404,11 +380,8 @@ int __init efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md)
 		end = md->phys_addr + size;
 		if (phys_addr >= md->phys_addr && phys_addr < end) {
 			memcpy(out_md, md, sizeof(*out_md));
-			early_memunmap(md, sizeof (*md));
 			return 0;
 		}
-
-		early_memunmap(md, sizeof (*md));
 	}
 	pr_err_once("requested map not found.\n");
 	return -ENOENT;
@@ -424,6 +397,35 @@ u64 __init efi_mem_desc_end(efi_memory_desc_t *md)
 	return end;
 }
 
+void __init __weak efi_arch_mem_reserve(phys_addr_t addr, u64 size) {}
+
+/**
+ * efi_mem_reserve - Reserve an EFI memory region
+ * @addr: Physical address to reserve
+ * @size: Size of reservation
+ *
+ * Mark a region as reserved from general kernel allocation and
+ * prevent it being released by efi_free_boot_services().
+ *
+ * This function should be called drivers once they've parsed EFI
+ * configuration tables to figure out where their data lives, e.g.
+ * efi_esrt_init().
+ */
+void __init efi_mem_reserve(phys_addr_t addr, u64 size)
+{
+	if (!memblock_is_region_reserved(addr, size))
+		memblock_reserve(addr, size);
+
+	/*
+	 * Some architectures (x86) reserve all boot services ranges
+	 * until efi_free_boot_services() because of buggy firmware
+	 * implementations. This means the above memblock_reserve() is
+	 * superfluous on x86 and instead what it needs to do is
+	 * ensure the @start, @size is not freed.
+	 */
+	efi_arch_mem_reserve(addr, size);
+}
+
 static __initdata efi_config_table_type_t common_tables[] = {
 	{ACPI_20_TABLE_GUID, "ACPI 2.0", &efi.acpi20},
 	{ACPI_TABLE_GUID, "ACPI", &efi.acpi},
@@ -811,6 +813,9 @@ int efi_status_to_err(efi_status_t status)
 	case EFI_NOT_FOUND:
 		err = -ENOENT;
 		break;
+	case EFI_ABORTED:
+		err = -EINTR;
+		break;
 	default:
 		err = -EINVAL;
 	}

drivers/firmware/efi/efivars.c

@@ -510,7 +510,8 @@ static ssize_t efivar_delete(struct file *filp, struct kobject *kobj,
 		vendor = del_var->VendorGuid;
 	}
 
-	efivar_entry_iter_begin();
+	if (efivar_entry_iter_begin())
+		return -EINTR;
 	entry = efivar_entry_find(name, vendor, &efivar_sysfs_list, true);
 	if (!entry)
 		err = -EINVAL;
@@ -575,7 +576,10 @@ efivar_create_sysfs_entry(struct efivar_entry *new_var)
 		return ret;
 
 	kobject_uevent(&new_var->kobj, KOBJ_ADD);
-	efivar_entry_add(new_var, &efivar_sysfs_list);
+	if (efivar_entry_add(new_var, &efivar_sysfs_list)) {
+		efivar_unregister(new_var);
+		return -EINTR;
+	}
 
 	return 0;
 }
@@ -690,7 +694,10 @@ static int efivars_sysfs_callback(efi_char16_t *name, efi_guid_t vendor,
 
 static int efivar_sysfs_destroy(struct efivar_entry *entry, void *data)
 {
-	efivar_entry_remove(entry);
+	int err = efivar_entry_remove(entry);
+
+	if (err)
+		return err;
 	efivar_unregister(entry);
 	return 0;
 }
@@ -698,7 +705,14 @@ static int efivar_sysfs_destroy(struct efivar_entry *entry, void *data)
 static void efivars_sysfs_exit(void)
 {
 	/* Remove all entries and destroy */
-	__efivar_entry_iter(efivar_sysfs_destroy, &efivar_sysfs_list, NULL, NULL);
+	int err;
+
+	err = __efivar_entry_iter(efivar_sysfs_destroy, &efivar_sysfs_list,
+				  NULL, NULL);
+	if (err) {
+		pr_err("efivars: Failed to destroy sysfs entries\n");
+		return;
+	}
 
 	if (efivars_new_var)
 		sysfs_remove_bin_file(&efivars_kset->kobj, efivars_new_var);

drivers/firmware/efi/esrt.c

@@ -16,6 +16,7 @@
 #include <linux/device.h>
 #include <linux/efi.h>
 #include <linux/init.h>
+#include <linux/io.h>
 #include <linux/kernel.h>
 #include <linux/kobject.h>
 #include <linux/list.h>
@@ -235,7 +236,7 @@ static struct attribute_group esrt_attr_group = {
 };
 
 /*
- * remap the table, copy it to kmalloced pages, and unmap it.
+ * remap the table, validate it, mark it reserved and unmap it.
  */
 void __init efi_esrt_init(void)
 {
@@ -335,7 +336,7 @@ void __init efi_esrt_init(void)
 
 	end = esrt_data + size;
 	pr_info("Reserving ESRT space from %pa to %pa.\n", &esrt_data, &end);
-	memblock_reserve(esrt_data, esrt_data_size);
+	efi_mem_reserve(esrt_data, esrt_data_size);
 
 	pr_debug("esrt-init: loaded.\n");
 err_memunmap:
@@ -382,28 +383,18 @@ static void cleanup_entry_list(void)
 static int __init esrt_sysfs_init(void)
 {
 	int error;
-	struct efi_system_resource_table __iomem *ioesrt;
 
 	pr_debug("esrt-sysfs: loading.\n");
 	if (!esrt_data || !esrt_data_size)
 		return -ENOSYS;
 
-	ioesrt = ioremap(esrt_data, esrt_data_size);
-	if (!ioesrt) {
-		pr_err("ioremap(%pa, %zu) failed.\n", &esrt_data,
-		       esrt_data_size);
-		return -ENOMEM;
-	}
-
-	esrt = kmalloc(esrt_data_size, GFP_KERNEL);
+	esrt = memremap(esrt_data, esrt_data_size, MEMREMAP_WB);
 	if (!esrt) {
-		pr_err("kmalloc failed. (wanted %zu bytes)\n", esrt_data_size);
-		iounmap(ioesrt);
+		pr_err("memremap(%pa, %zu) failed.\n", &esrt_data,
+		       esrt_data_size);
 		return -ENOMEM;
 	}
 
-	memcpy_fromio(esrt, ioesrt, esrt_data_size);
-
 	esrt_kobj = kobject_create_and_add("esrt", efi_kobj);
 	if (!esrt_kobj) {
 		pr_err("Firmware table registration failed.\n");
@@ -429,8 +420,6 @@ static int __init esrt_sysfs_init(void)
 	if (error)
 		goto err_cleanup_list;
 
-	memblock_remove(esrt_data, esrt_data_size);
-
 	pr_debug("esrt-sysfs: loaded.\n");
 
 	return 0;

drivers/firmware/efi/fake_mem.c

@@ -35,17 +35,13 @@
 
 #define EFI_MAX_FAKEMEM CONFIG_EFI_MAX_FAKE_MEM
 
-struct fake_mem {
-	struct range range;
-	u64 attribute;
-};
-static struct fake_mem fake_mems[EFI_MAX_FAKEMEM];
+static struct efi_mem_range fake_mems[EFI_MAX_FAKEMEM];
 static int nr_fake_mem;
 
 static int __init cmp_fake_mem(const void *x1, const void *x2)
 {
-	const struct fake_mem *m1 = x1;
-	const struct fake_mem *m2 = x2;
+	const struct efi_mem_range *m1 = x1;
+	const struct efi_mem_range *m2 = x2;
 
 	if (m1->range.start < m2->range.start)
 		return -1;
@@ -56,40 +52,21 @@ static int __init cmp_fake_mem(const void *x1, const void *x2)
 
 void __init efi_fake_memmap(void)
 {
-	u64 start, end, m_start, m_end, m_attr;
 	int new_nr_map = efi.memmap.nr_map;
 	efi_memory_desc_t *md;
 	phys_addr_t new_memmap_phy;
 	void *new_memmap;
-	void *old, *new;
 	int i;
 
-	if (!nr_fake_mem || !efi_enabled(EFI_MEMMAP))
+	if (!nr_fake_mem)
 		return;
 
 	/* count up the number of EFI memory descriptor */
-	for_each_efi_memory_desc(md) {
-		start = md->phys_addr;
-		end = start + (md->num_pages << EFI_PAGE_SHIFT) - 1;
-
-		for (i = 0; i < nr_fake_mem; i++) {
-			/* modifying range */
-			m_start = fake_mems[i].range.start;
-			m_end = fake_mems[i].range.end;
-
-			if (m_start <= start) {
-				/* split into 2 parts */
-				if (start < m_end && m_end < end)
-					new_nr_map++;
-			}
-			if (start < m_start && m_start < end) {
-				/* split into 3 parts */
-				if (m_end < end)
-					new_nr_map += 2;
-				/* split into 2 parts */
-				if (end <= m_end)
-					new_nr_map++;
-			}
+	for (i = 0; i < nr_fake_mem; i++) {
+		for_each_efi_memory_desc(md) {
+			struct range *r = &fake_mems[i].range;
+
+			new_nr_map += efi_memmap_split_count(md, r);
 		}
 	}
 
@@ -107,85 +84,13 @@ void __init efi_fake_memmap(void)
 		return;
 	}
 
-	for (old = efi.memmap.map, new = new_memmap;
-	     old < efi.memmap.map_end;
-	     old += efi.memmap.desc_size, new += efi.memmap.desc_size) {
-
-		/* copy original EFI memory descriptor */
-		memcpy(new, old, efi.memmap.desc_size);
-		md = new;
-		start = md->phys_addr;
-		end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT) - 1;
-
-		for (i = 0; i < nr_fake_mem; i++) {
-			/* modifying range */
-			m_start = fake_mems[i].range.start;
-			m_end = fake_mems[i].range.end;
-			m_attr = fake_mems[i].attribute;
-
-			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 += efi.memmap.desc_size;
-				memcpy(new, old, efi.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 += efi.memmap.desc_size;
-				memcpy(new, old, efi.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 += efi.memmap.desc_size;
-				memcpy(new, old, efi.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 += efi.memmap.desc_size;
-				memcpy(new, old, efi.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;
-			}
-		}
-	}
+	for (i = 0; i < nr_fake_mem; i++)
+		efi_memmap_insert(&efi.memmap, new_memmap, &fake_mems[i]);
 
 	/* swap into new EFI memmap */
-	efi_unmap_memmap();
-	efi.memmap.map = new_memmap;
-	efi.memmap.phys_map = new_memmap_phy;
-	efi.memmap.nr_map = new_nr_map;
-	efi.memmap.map_end = efi.memmap.map + efi.memmap.nr_map * efi.memmap.desc_size;
-	set_bit(EFI_MEMMAP, &efi.flags);
+	early_memunmap(new_memmap, efi.memmap.desc_size * new_nr_map);
+
+	efi_memmap_install(new_memmap_phy, new_nr_map);
 
 	/* print new EFI memmap */
 	efi_print_memmap();
@@ -223,7 +128,7 @@ static int __init setup_fake_mem(char *p)
 			p++;
 	}
 
-	sort(fake_mems, nr_fake_mem, sizeof(struct fake_mem),
+	sort(fake_mems, nr_fake_mem, sizeof(struct efi_mem_range),
 	     cmp_fake_mem, NULL);
 
 	for (i = 0; i < nr_fake_mem; i++)

drivers/firmware/efi/memmap.c

+/*
+ * 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>
+
+/**
+ * __efi_memmap_init - Common code for mapping the EFI memory map
+ * @data: EFI memory map data
+ * @late: Use early or late mapping function?
+ *
+ * This function takes care of figuring out which function to use to
+ * map the EFI memory map in efi.memmap based on how far into the boot
+ * we are.
+ *
+ * During bootup @late should be %false since we only have access to
+ * the early_memremap*() functions as the vmalloc space isn't setup.
+ * Once the kernel is fully booted we can fallback to the more robust
+ * memremap*() API.
+ *
+ * Returns zero on success, a negative error code on failure.
+ */
+static int __init
+__efi_memmap_init(struct efi_memory_map_data *data, bool late)
+{
+	struct efi_memory_map map;
+	phys_addr_t phys_map;
+
+	if (efi_enabled(EFI_PARAVIRT))
+		return 0;
+
+	phys_map = data->phys_map;
+
+	if (late)
+		map.map = memremap(phys_map, data->size, MEMREMAP_WB);
+	else
+		map.map = early_memremap(phys_map, data->size);
+
+	if (!map.map) {
+		pr_err("Could not map the memory map!\n");
+		return -ENOMEM;
+	}
+
+	map.phys_map = data->phys_map;
+	map.nr_map = data->size / data->desc_size;
+	map.map_end = map.map + data->size;
+
+	map.desc_version = data->desc_version;
+	map.desc_size = data->desc_size;
+	map.late = late;
+
+	set_bit(EFI_MEMMAP, &efi.flags);
+
+	efi.memmap = map;
+
+	return 0;
+}
+
+/**
+ * efi_memmap_init_early - Map the EFI memory map data structure
+ * @data: EFI memory map data
+ *
+ * Use early_memremap() to map the passed in EFI memory map and assign
+ * it to efi.memmap.
+ */
+int __init efi_memmap_init_early(struct efi_memory_map_data *data)
+{
+	/* Cannot go backwards */
+	WARN_ON(efi.memmap.late);
+
+	return __efi_memmap_init(data, false);
+}
+
+void __init efi_memmap_unmap(void)
+{
+	if (!efi.memmap.late) {
+		unsigned long size;
+
+		size = efi.memmap.desc_size * efi.memmap.nr_map;
+		early_memunmap(efi.memmap.map, size);
+	} else {
+		memunmap(efi.memmap.map);
+	}
+
+	efi.memmap.map = NULL;
+	clear_bit(EFI_MEMMAP, &efi.flags);
+}
+
+/**
+ * efi_memmap_init_late - Map efi.memmap with memremap()
+ * @phys_addr: Physical address of the new EFI memory map
+ * @size: Size in bytes of the new EFI memory map
+ *
+ * Setup a mapping of the EFI memory map using ioremap_cache(). This
+ * function should only be called once the vmalloc space has been
+ * setup and is therefore not suitable for calling during early EFI
+ * initialise, e.g. in efi_init(). Additionally, it expects
+ * efi_memmap_init_early() to have already been called.
+ *
+ * The reason there are two EFI memmap initialisation
+ * (efi_memmap_init_early() and this late version) is because the
+ * early EFI memmap should be explicitly unmapped once EFI
+ * initialisation is complete as the fixmap space used to map the EFI
+ * memmap (via early_memremap()) is a scarce resource.
+ *
+ * This late mapping is intended to persist for the duration of
+ * runtime so that things like efi_mem_desc_lookup() and
+ * efi_mem_attributes() always work.
+ *
+ * Returns zero on success, a negative error code on failure.
+ */
+int __init efi_memmap_init_late(phys_addr_t addr, unsigned long size)
+{
+	struct efi_memory_map_data data = {
+		.phys_map = addr,
+		.size = size,
+	};
+
+	/* Did we forget to unmap the early EFI memmap? */
+	WARN_ON(efi.memmap.map);
+
+	/* Were we already called? */
+	WARN_ON(efi.memmap.late);
+
+	/*
+	 * It makes no sense to allow callers to register different
+	 * values for the following fields. Copy them out of the
+	 * existing early EFI memmap.
+	 */
+	data.desc_version = efi.memmap.desc_version;
+	data.desc_size = efi.memmap.desc_size;
+
+	return __efi_memmap_init(&data, true);
+}
+
+/**
+ * efi_memmap_install - Install a new EFI memory map in efi.memmap
+ * @addr: Physical address of the memory map
+ * @nr_map: Number of entries in the memory map
+ *
+ * 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(phys_addr_t addr, unsigned int nr_map)
+{
+	struct efi_memory_map_data data;
+
+	efi_memmap_unmap();
+
+	data.phys_map = addr;
+	data.size = efi.memmap.desc_size * nr_map;
+	data.desc_version = efi.memmap.desc_version;
+	data.desc_size = efi.memmap.desc_size;
+
+	return __efi_memmap_init(&data, efi.memmap.late);
+}
+
+/**
+ * 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
+ * accomodate @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;
+		}
+	}
+}

drivers/firmware/efi/runtime-map.c

@@ -14,10 +14,6 @@
 
 #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 */
@@ -106,7 +102,8 @@ static struct kobj_type __refdata map_ktype = {
 static struct kset *map_kset;
 
 static struct efi_runtime_map_entry *
-add_sysfs_runtime_map_entry(struct kobject *kobj, int nr)
+add_sysfs_runtime_map_entry(struct kobject *kobj, int nr,
+			    efi_memory_desc_t *md)
 {
 	int ret;
 	struct efi_runtime_map_entry *entry;
@@ -124,8 +121,7 @@ add_sysfs_runtime_map_entry(struct kobject *kobj, int nr)
 		return ERR_PTR(-ENOMEM);
 	}
 
-	memcpy(&entry->md, efi_runtime_map + nr * efi_memdesc_size,
-	       sizeof(efi_memory_desc_t));
+	memcpy(&entry->md, md, sizeof(efi_memory_desc_t));
 
 	kobject_init(&entry->kobj, &map_ktype);
 	entry->kobj.kset = map_kset;
@@ -142,12 +138,12 @@ add_sysfs_runtime_map_entry(struct kobject *kobj, int nr)
 
 int efi_get_runtime_map_size(void)
 {
-	return nr_efi_runtime_map * efi_memdesc_size;
+	return efi.memmap.nr_map * efi.memmap.desc_size;
 }
 
 int efi_get_runtime_map_desc_size(void)
 {
-	return efi_memdesc_size;
+	return efi.memmap.desc_size;
 }
 
 int efi_runtime_map_copy(void *buf, size_t bufsz)
@@ -157,38 +153,33 @@ int efi_runtime_map_copy(void *buf, size_t bufsz)
 	if (sz > bufsz)
 		sz = bufsz;
 
-	memcpy(buf, efi_runtime_map, sz);
+	memcpy(buf, efi.memmap.map, sz);
 	return 0;
 }
 
-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;
+	efi_memory_desc_t *md;
 
-	if (!efi_runtime_map)
+	if (!efi_enabled(EFI_MEMMAP))
 		return 0;
 
-	map_entries = kzalloc(nr_efi_runtime_map * sizeof(entry), GFP_KERNEL);
+	map_entries = kzalloc(efi.memmap.nr_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);
+	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;
+		*(map_entries + i++) = entry;
 	}
 
 	return 0;

drivers/firmware/efi/runtime-wrappers.c

@@ -14,11 +14,13 @@
  * This file is released under the GPLv2.
  */
 
+#define pr_fmt(fmt)	"efi: " fmt
+
 #include <linux/bug.h>
 #include <linux/efi.h>
 #include <linux/irqflags.h>
 #include <linux/mutex.h>
-#include <linux/spinlock.h>
+#include <linux/semaphore.h>
 #include <linux/stringify.h>
 #include <asm/efi.h>
 
@@ -81,20 +83,21 @@ void efi_call_virt_check_flags(unsigned long flags, const char *call)
  * +------------------------------------+-------------------------------+
  *
  * Due to the fact that the EFI pstore may write to the variable store in
- * interrupt context, we need to use a spinlock for at least the groups that
+ * interrupt context, we need to use a lock for at least the groups that
  * contain SetVariable() and QueryVariableInfo(). That leaves little else, as
  * none of the remaining functions are actually ever called at runtime.
- * So let's just use a single spinlock to serialize all Runtime Services calls.
+ * So let's just use a single lock to serialize all Runtime Services calls.
  */
-static DEFINE_SPINLOCK(efi_runtime_lock);
+static DEFINE_SEMAPHORE(efi_runtime_lock);
 
 static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc)
 {
 	efi_status_t status;
 
-	spin_lock(&efi_runtime_lock);
+	if (down_interruptible(&efi_runtime_lock))
+		return EFI_ABORTED;
 	status = efi_call_virt(get_time, tm, tc);
-	spin_unlock(&efi_runtime_lock);
+	up(&efi_runtime_lock);
 	return status;
 }
 
@@ -102,9 +105,10 @@ static efi_status_t virt_efi_set_time(efi_time_t *tm)
 {
 	efi_status_t status;
 
-	spin_lock(&efi_runtime_lock);
+	if (down_interruptible(&efi_runtime_lock))
+		return EFI_ABORTED;
 	status = efi_call_virt(set_time, tm);
-	spin_unlock(&efi_runtime_lock);
+	up(&efi_runtime_lock);
 	return status;
 }
 
@@ -114,9 +118,10 @@ static efi_status_t virt_efi_get_wakeup_time(efi_bool_t *enabled,
 {
 	efi_status_t status;
 
-	spin_lock(&efi_runtime_lock);
+	if (down_interruptible(&efi_runtime_lock))
+		return EFI_ABORTED;
 	status = efi_call_virt(get_wakeup_time, enabled, pending, tm);
-	spin_unlock(&efi_runtime_lock);
+	up(&efi_runtime_lock);
 	return status;
 }
 
@@ -124,9 +129,10 @@ static efi_status_t virt_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
 {
 	efi_status_t status;
 
-	spin_lock(&efi_runtime_lock);
+	if (down_interruptible(&efi_runtime_lock))
+		return EFI_ABORTED;
 	status = efi_call_virt(set_wakeup_time, enabled, tm);
-	spin_unlock(&efi_runtime_lock);
+	up(&efi_runtime_lock);
 	return status;
 }
 
@@ -138,10 +144,11 @@ static efi_status_t virt_efi_get_variable(efi_char16_t *name,
 {
 	efi_status_t status;
 
-	spin_lock(&efi_runtime_lock);
+	if (down_interruptible(&efi_runtime_lock))
+		return EFI_ABORTED;
 	status = efi_call_virt(get_variable, name, vendor, attr, data_size,
 			       data);
-	spin_unlock(&efi_runtime_lock);
+	up(&efi_runtime_lock);
 	return status;
 }
 
@@ -151,9 +158,10 @@ static efi_status_t virt_efi_get_next_variable(unsigned long *name_size,
 {
 	efi_status_t status;
 
-	spin_lock(&efi_runtime_lock);
+	if (down_interruptible(&efi_runtime_lock))
+		return EFI_ABORTED;
 	status = efi_call_virt(get_next_variable, name_size, name, vendor);
-	spin_unlock(&efi_runtime_lock);
+	up(&efi_runtime_lock);
 	return status;
 }
 
@@ -165,10 +173,11 @@ static efi_status_t virt_efi_set_variable(efi_char16_t *name,
 {
 	efi_status_t status;
 
-	spin_lock(&efi_runtime_lock);
+	if (down_interruptible(&efi_runtime_lock))
+		return EFI_ABORTED;
 	status = efi_call_virt(set_variable, name, vendor, attr, data_size,
 			       data);
-	spin_unlock(&efi_runtime_lock);
+	up(&efi_runtime_lock);
 	return status;
 }
 
@@ -179,12 +188,12 @@ virt_efi_set_variable_nonblocking(efi_char16_t *name, efi_guid_t *vendor,
 {
 	efi_status_t status;
 
-	if (!spin_trylock(&efi_runtime_lock))
+	if (down_trylock(&efi_runtime_lock))
 		return EFI_NOT_READY;
 
 	status = efi_call_virt(set_variable, name, vendor, attr, data_size,
 			       data);
-	spin_unlock(&efi_runtime_lock);
+	up(&efi_runtime_lock);
 	return status;
 }
 
@@ -199,10 +208,11 @@ static efi_status_t virt_efi_query_variable_info(u32 attr,
 	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
 		return EFI_UNSUPPORTED;
 
-	spin_lock(&efi_runtime_lock);
+	if (down_interruptible(&efi_runtime_lock))
+		return EFI_ABORTED;
 	status = efi_call_virt(query_variable_info, attr, storage_space,
 			       remaining_space, max_variable_size);
-	spin_unlock(&efi_runtime_lock);
+	up(&efi_runtime_lock);
 	return status;
 }
 
@@ -217,12 +227,12 @@ virt_efi_query_variable_info_nonblocking(u32 attr,
 	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
 		return EFI_UNSUPPORTED;
 
-	if (!spin_trylock(&efi_runtime_lock))
+	if (down_trylock(&efi_runtime_lock))
 		return EFI_NOT_READY;
 
 	status = efi_call_virt(query_variable_info, attr, storage_space,
 			       remaining_space, max_variable_size);
-	spin_unlock(&efi_runtime_lock);
+	up(&efi_runtime_lock);
 	return status;
 }
 
@@ -230,9 +240,10 @@ static efi_status_t virt_efi_get_next_high_mono_count(u32 *count)
 {
 	efi_status_t status;
 
-	spin_lock(&efi_runtime_lock);
+	if (down_interruptible(&efi_runtime_lock))
+		return EFI_ABORTED;
 	status = efi_call_virt(get_next_high_mono_count, count);
-	spin_unlock(&efi_runtime_lock);
+	up(&efi_runtime_lock);
 	return status;
 }
 
@@ -241,9 +252,13 @@ static void virt_efi_reset_system(int reset_type,
 				  unsigned long data_size,
 				  efi_char16_t *data)
 {
-	spin_lock(&efi_runtime_lock);
+	if (down_interruptible(&efi_runtime_lock)) {
+		pr_warn("failed to invoke the reset_system() runtime service:\n"
+			"could not get exclusive access to the firmware\n");
+		return;
+	}
 	__efi_call_virt(reset_system, reset_type, status, data_size, data);
-	spin_unlock(&efi_runtime_lock);
+	up(&efi_runtime_lock);
 }
 
 static efi_status_t virt_efi_update_capsule(efi_capsule_header_t **capsules,
@@ -255,9 +270,10 @@ static efi_status_t virt_efi_update_capsule(efi_capsule_header_t **capsules,
 	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
 		return EFI_UNSUPPORTED;
 
-	spin_lock(&efi_runtime_lock);
+	if (down_interruptible(&efi_runtime_lock))
+		return EFI_ABORTED;
 	status = efi_call_virt(update_capsule, capsules, count, sg_list);
-	spin_unlock(&efi_runtime_lock);
+	up(&efi_runtime_lock);
 	return status;
 }
 
@@ -271,10 +287,11 @@ static efi_status_t virt_efi_query_capsule_caps(efi_capsule_header_t **capsules,
 	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
 		return EFI_UNSUPPORTED;
 
-	spin_lock(&efi_runtime_lock);
+	if (down_interruptible(&efi_runtime_lock))
+		return EFI_ABORTED;
 	status = efi_call_virt(query_capsule_caps, capsules, count, max_size,
 			       reset_type);
-	spin_unlock(&efi_runtime_lock);
+	up(&efi_runtime_lock);
 	return status;
 }
 

drivers/firmware/efi/test/Makefile

+obj-$(CONFIG_EFI_TEST)			+= efi_test.o

drivers/firmware/efi/test/efi_test.h

+/*
+ * EFI Test driver Header
+ *
+ * Copyright(C) 2012-2016 Canonical Ltd.
+ *
+ */
+
+#ifndef _DRIVERS_FIRMWARE_EFI_TEST_H_
+#define _DRIVERS_FIRMWARE_EFI_TEST_H_
+
+#include <linux/efi.h>
+
+struct efi_getvariable {
+	efi_char16_t	*variable_name;
+	efi_guid_t	*vendor_guid;
+	u32		*attributes;
+	unsigned long	*data_size;
+	void		*data;
+	efi_status_t	*status;
+} __packed;
+
+struct efi_setvariable {
+	efi_char16_t	*variable_name;
+	efi_guid_t	*vendor_guid;
+	u32		attributes;
+	unsigned long	data_size;
+	void		*data;
+	efi_status_t	*status;
+} __packed;
+
+struct efi_getnextvariablename {
+	unsigned long	*variable_name_size;
+	efi_char16_t	*variable_name;
+	efi_guid_t	*vendor_guid;
+	efi_status_t	*status;
+} __packed;
+
+struct efi_queryvariableinfo {
+	u32		attributes;
+	u64		*maximum_variable_storage_size;
+	u64		*remaining_variable_storage_size;
+	u64		*maximum_variable_size;
+	efi_status_t	*status;
+} __packed;
+
+struct efi_gettime {
+	efi_time_t	*time;
+	efi_time_cap_t	*capabilities;
+	efi_status_t	*status;
+} __packed;
+
+struct efi_settime {
+	efi_time_t	*time;
+	efi_status_t	*status;
+} __packed;
+
+struct efi_getwakeuptime {
+	efi_bool_t	*enabled;
+	efi_bool_t	*pending;
+	efi_time_t	*time;
+	efi_status_t	*status;
+} __packed;
+
+struct efi_setwakeuptime {
+	efi_bool_t	enabled;
+	efi_time_t	*time;
+	efi_status_t	*status;
+} __packed;
+
+struct efi_getnexthighmonotoniccount {
+	u32		*high_count;
+	efi_status_t	*status;
+} __packed;
+
+struct efi_querycapsulecapabilities {
+	efi_capsule_header_t	**capsule_header_array;
+	unsigned long		capsule_count;
+	u64			*maximum_capsule_size;
+	int			*reset_type;
+	efi_status_t		*status;
+} __packed;
+
+#define EFI_RUNTIME_GET_VARIABLE \
+	_IOWR('p', 0x01, struct efi_getvariable)
+#define EFI_RUNTIME_SET_VARIABLE \
+	_IOW('p', 0x02, struct efi_setvariable)
+
+#define EFI_RUNTIME_GET_TIME \
+	_IOR('p', 0x03, struct efi_gettime)
+#define EFI_RUNTIME_SET_TIME \
+	_IOW('p', 0x04, struct efi_settime)
+
+#define EFI_RUNTIME_GET_WAKETIME \
+	_IOR('p', 0x05, struct efi_getwakeuptime)
+#define EFI_RUNTIME_SET_WAKETIME \
+	_IOW('p', 0x06, struct efi_setwakeuptime)
+
+#define EFI_RUNTIME_GET_NEXTVARIABLENAME \
+	_IOWR('p', 0x07, struct efi_getnextvariablename)
+
+#define EFI_RUNTIME_QUERY_VARIABLEINFO \
+	_IOR('p', 0x08, struct efi_queryvariableinfo)
+
+#define EFI_RUNTIME_GET_NEXTHIGHMONOTONICCOUNT \
+	_IOR('p', 0x09, struct efi_getnexthighmonotoniccount)
+
+#define EFI_RUNTIME_QUERY_CAPSULECAPABILITIES \
+	_IOR('p', 0x0A, struct efi_querycapsulecapabilities)
+
+#endif /* _DRIVERS_FIRMWARE_EFI_TEST_H_ */

drivers/firmware/google/gsmi.c

@@ -910,8 +910,7 @@ static __init int gsmi_init(void)
 	gsmi_buf_free(gsmi_dev.param_buf);
 	gsmi_buf_free(gsmi_dev.data_buf);
 	gsmi_buf_free(gsmi_dev.name_buf);
-	if (gsmi_dev.dma_pool)
-		dma_pool_destroy(gsmi_dev.dma_pool);
+	dma_pool_destroy(gsmi_dev.dma_pool);
 	platform_device_unregister(gsmi_dev.pdev);
 	pr_info("gsmi: failed to load: %d\n", ret);
 	return ret;

fs/efivarfs/inode.c

@@ -105,7 +105,10 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry,
 
 	inode->i_private = var;
 
-	efivar_entry_add(var, &efivarfs_list);
+	err = efivar_entry_add(var, &efivarfs_list);
+	if (err)
+		goto out;
+
 	d_instantiate(dentry, inode);
 	dget(dentry);
 out:

fs/efivarfs/super.c

@@ -157,12 +157,14 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
 		goto fail_inode;
 	}
 
+	efivar_entry_size(entry, &size);
+	err = efivar_entry_add(entry, &efivarfs_list);
+	if (err)
+		goto fail_inode;
+
 	/* copied by the above to local storage in the dentry. */
 	kfree(name);
 
-	efivar_entry_size(entry, &size);
-	efivar_entry_add(entry, &efivarfs_list);
-
 	inode_lock(inode);
 	inode->i_private = entry;
 	i_size_write(inode, size + sizeof(entry->var.Attributes));
@@ -182,7 +184,10 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
 
 static int efivarfs_destroy(struct efivar_entry *entry, void *data)
 {
-	efivar_entry_remove(entry);
+	int err = efivar_entry_remove(entry);
+
+	if (err)
+		return err;
 	kfree(entry);
 	return 0;
 }

include/linux/efi.h

@@ -20,6 +20,7 @@
 #include <linux/ioport.h>
 #include <linux/pfn.h>
 #include <linux/pstore.h>
+#include <linux/range.h>
 #include <linux/reboot.h>
 #include <linux/uuid.h>
 #include <linux/screen_info.h>
@@ -37,6 +38,7 @@
 #define EFI_WRITE_PROTECTED	( 8 | (1UL << (BITS_PER_LONG-1)))
 #define EFI_OUT_OF_RESOURCES	( 9 | (1UL << (BITS_PER_LONG-1)))
 #define EFI_NOT_FOUND		(14 | (1UL << (BITS_PER_LONG-1)))
+#define EFI_ABORTED		(21 | (1UL << (BITS_PER_LONG-1)))
 #define EFI_SECURITY_VIOLATION	(26 | (1UL << (BITS_PER_LONG-1)))
 
 typedef unsigned long efi_status_t;
@@ -678,6 +680,18 @@ typedef struct {
 	unsigned long tables;
 } efi_system_table_t;
 
+/*
+ * Architecture independent structure for describing a memory map for the
+ * benefit of efi_memmap_init_early(), saving us the need to pass four
+ * parameters.
+ */
+struct efi_memory_map_data {
+	phys_addr_t phys_map;
+	unsigned long size;
+	unsigned long desc_version;
+	unsigned long desc_size;
+};
+
 struct efi_memory_map {
 	phys_addr_t phys_map;
 	void *map;
@@ -685,6 +699,12 @@ struct efi_memory_map {
 	int nr_map;
 	unsigned long desc_version;
 	unsigned long desc_size;
+	bool late;
+};
+
+struct efi_mem_range {
+	struct range range;
+	u64 attribute;
 };
 
 struct efi_fdt_params {
@@ -909,6 +929,16 @@ static inline efi_status_t efi_query_variable_store(u32 attributes,
 }
 #endif
 extern void __iomem *efi_lookup_mapped_addr(u64 phys_addr);
+
+extern int __init efi_memmap_init_early(struct efi_memory_map_data *data);
+extern int __init efi_memmap_init_late(phys_addr_t addr, unsigned long size);
+extern void __init efi_memmap_unmap(void);
+extern int __init efi_memmap_install(phys_addr_t addr, unsigned int nr_map);
+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);
+
 extern int efi_config_init(efi_config_table_type_t *arch_tables);
 #ifdef CONFIG_EFI_ESRT
 extern void __init efi_esrt_init(void);
@@ -924,6 +954,7 @@ extern u64 efi_mem_attribute (unsigned long phys_addr, unsigned long size);
 extern int __init efi_uart_console_only (void);
 extern u64 efi_mem_desc_end(efi_memory_desc_t *md);
 extern int efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md);
+extern void efi_mem_reserve(phys_addr_t addr, u64 size);
 extern void efi_initialize_iomem_resources(struct resource *code_resource,
 		struct resource *data_resource, struct resource *bss_resource);
 extern void efi_reserve_boot_services(void);
@@ -1136,12 +1167,6 @@ struct efivar_operations {
 };
 
 struct efivars {
-	/*
-	 * ->lock protects two things:
-	 * 1) efivarfs_list and efivars_sysfs_list
-	 * 2) ->ops calls
-	 */
-	spinlock_t lock;
 	struct kset *kset;
 	struct kobject *kobject;
 	const struct efivar_operations *ops;
@@ -1282,8 +1307,8 @@ struct kobject *efivars_kobject(void);
 int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *),
 		void *data, bool duplicates, struct list_head *head);
 
-void efivar_entry_add(struct efivar_entry *entry, struct list_head *head);
-void efivar_entry_remove(struct efivar_entry *entry);
+int efivar_entry_add(struct efivar_entry *entry, struct list_head *head);
+int efivar_entry_remove(struct efivar_entry *entry);
 
 int __efivar_entry_delete(struct efivar_entry *entry);
 int efivar_entry_delete(struct efivar_entry *entry);
@@ -1300,7 +1325,7 @@ int efivar_entry_set_get_size(struct efivar_entry *entry, u32 attributes,
 int efivar_entry_set_safe(efi_char16_t *name, efi_guid_t vendor, u32 attributes,
 			  bool block, unsigned long size, void *data);
 
-void efivar_entry_iter_begin(void);
+int efivar_entry_iter_begin(void);
 void efivar_entry_iter_end(void);
 
 int __efivar_entry_iter(int (*func)(struct efivar_entry *, void *),
@@ -1336,7 +1361,6 @@ extern int efi_capsule_update(efi_capsule_header_t *capsule,
 
 #ifdef CONFIG_EFI_RUNTIME_MAP
 int efi_runtime_map_init(struct kobject *);
-void efi_runtime_map_setup(void *, int, u32);
 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);
@@ -1346,9 +1370,6 @@ 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) {}
-
 static inline int efi_get_runtime_map_size(void)
 {
 	return 0;

lib/ucs2_string.c

@@ -56,7 +56,7 @@ ucs2_utf8size(const ucs2_char_t *src)
 	unsigned long i;
 	unsigned long j = 0;
 
-	for (i = 0; i < ucs2_strlen(src); i++) {
+	for (i = 0; src[i]; i++) {
 		u16 c = src[i];
 
 		if (c >= 0x800)