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

Pull EFI updates from Ingo Molnar:
"The main changes are:

- Use separate EFI page tables when executing EFI firmware code.
This isolates the EFI context from the rest of the kernel, which
has security and general robustness advantages. (Matt Fleming)

- Run regular UEFI firmware with interrupts enabled. This is already
the status quo under other OSs. (Ard Biesheuvel)

- Various x86 EFI enhancements, such as the use of non-executable
attributes for EFI memory mappings. (Sai Praneeth Prakhya)

- Various arm64 UEFI enhancements. (Ard Biesheuvel)

- ... various fixes and cleanups.

The separate EFI page tables feature got delayed twice already,
because it's an intrusive change and we didn't feel confident about
it - third time's the charm we hope!"

* 'efi-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (37 commits)
x86/mm/pat: Fix boot crash when 1GB pages are not supported by the CPU
x86/efi: Only map kernel text for EFI mixed mode
x86/efi: Map EFI_MEMORY_{XP,RO} memory region bits to EFI page tables
x86/mm/pat: Don't implicitly allow _PAGE_RW in kernel_map_pages_in_pgd()
efi/arm*: Perform hardware compatibility check
efi/arm64: Check for h/w support before booting a >4 KB granular kernel
efi/arm: Check for LPAE support before booting a LPAE kernel
efi/arm-init: Use read-only early mappings
efi/efistub: Prevent __init annotations from being used
arm64/vmlinux.lds.S: Handle .init.rodata.xxx and .init.bss sections
efi/arm64: Drop __init annotation from handle_kernel_image()
x86/mm/pat: Use _PAGE_GLOBAL bit for EFI page table mappings
efi/runtime-wrappers: Run UEFI Runtime Services with interrupts enabled
efi: Reformat GUID tables to follow the format in UEFI spec
efi: Add Persistent Memory type name
efi: Add NV memory attribute
x86/efi: Show actual ending addresses in efi_print_memmap
x86/efi/bgrt: Don't ignore the BGRT if the 'valid' bit is 0
efivars: Use to_efivar_entry
efi: Runtime-wrapper: Get rid of the rtc_lock spinlock
...

Documentation/efi-stub.txt

···
 respectively. For ARM the EFI stub is implemented in
 arch/arm/boot/compressed/efi-header.S and
 arch/arm/boot/compressed/efi-stub.c. EFI stub code that is shared
-between architectures is in drivers/firmware/efi/efi-stub-helper.c.
+between architectures is in drivers/firmware/efi/libstub.
 
 For arm64, there is no compressed kernel support, so the Image itself
 masquerades as a PE/COFF image and the EFI stub is linked into the
 kernel. The arm64 EFI stub lives in arch/arm64/kernel/efi-entry.S
-and arch/arm64/kernel/efi-stub.c.
+and drivers/firmware/efi/libstub/arm64-stub.c.
 
 By using the EFI boot stub it's possible to boot a Linux kernel
 without the use of a conventional EFI boot loader, such as grub or

Documentation/x86/x86_64/mm.txt

···
 ... unused hole ...
 ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
 ... unused hole ...
+ffffffef00000000 - ffffffff00000000 (=64 GB) EFI region mapping space
+... unused hole ...
 ffffffff80000000 - ffffffffa0000000 (=512 MB)  kernel text mapping, from phys 0
 ffffffffa0000000 - ffffffffff5fffff (=1525 MB) module mapping space
 ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls
···
 Current X86-64 implementations only support 40 bits of address space,
 but we support up to 46 bits. This expands into MBZ space in the page tables.
 
-->trampoline_pgd:
-
-We map EFI runtime services in the aforementioned PGD in the virtual
-range of 64Gb (arbitrarily set, can be raised if needed)
-
-0xffffffef00000000 - 0xffffffff00000000
+We map EFI runtime services in the 'efi_pgd' PGD in a 64Gb large virtual
+memory window (this size is arbitrary, it can be raised later if needed).
+The mappings are not part of any other kernel PGD and are only available
+during EFI runtime calls.
 
 -Andi Kleen, Jul 2004

arch/arm64/kernel/vmlinux.lds.S

···
 		CON_INITCALL
 		SECURITY_INITCALL
 		INIT_RAM_FS
+		*(.init.rodata.* .init.bss)	/* from the EFI stub */
 	}
 	.exit.data : {
 		ARM_EXIT_KEEP(EXIT_DATA)

arch/x86/include/asm/efi.h

···
 
 #include <asm/fpu/api.h>
 #include <asm/pgtable.h>
+#include <asm/tlb.h>
 
 /*
  * We map the EFI regions needed for runtime services non-contiguously,
···
 
 #define efi_call_phys(f, args...)		efi_call((f), args)
 
+/*
+ * Scratch space used for switching the pagetable in the EFI stub
+ */
+struct efi_scratch {
+	u64	r15;
+	u64	prev_cr3;
+	pgd_t	*efi_pgt;
+	bool	use_pgd;
+	u64	phys_stack;
+} __packed;
+
 #define efi_call_virt(f, ...)						\
 ({									\
 	efi_status_t __s;						\
···
 	efi_sync_low_kernel_mappings();					\
 	preempt_disable();						\
 	__kernel_fpu_begin();						\
+									\
+	if (efi_scratch.use_pgd) {					\
+		efi_scratch.prev_cr3 = read_cr3();			\
+		write_cr3((unsigned long)efi_scratch.efi_pgt);		\
+		__flush_tlb_all();					\
+	}								\
+									\
 	__s = efi_call((void *)efi.systab->runtime->f, __VA_ARGS__);	\
+									\
+	if (efi_scratch.use_pgd) {					\
+		write_cr3(efi_scratch.prev_cr3);			\
+		__flush_tlb_all();					\
+	}								\
+									\
 	__kernel_fpu_end();						\
 	preempt_enable();						\
 	__s;								\
···
 extern void __init efi_map_region(efi_memory_desc_t *md);
 extern void __init efi_map_region_fixed(efi_memory_desc_t *md);
 extern void efi_sync_low_kernel_mappings(void);
+extern int __init efi_alloc_page_tables(void);
 extern int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages);
 extern void __init efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages);
 extern void __init old_map_region(efi_memory_desc_t *md);
 extern void __init runtime_code_page_mkexec(void);
-extern void __init efi_runtime_mkexec(void);
+extern void __init efi_runtime_update_mappings(void);
 extern void __init efi_dump_pagetable(void);
 extern void __init efi_apply_memmap_quirks(void);
 extern int __init efi_reuse_config(u64 tables, int nr_tables);

arch/x86/kernel/vmlinux.lds.S

···
 		__brk_limit = .;
 	}
 
+	. = ALIGN(PAGE_SIZE);
 	_end = .;
 
         STABS_DEBUG

arch/x86/mm/pageattr.c

···
 
 	pte = pte_offset_kernel(pmd, start);
 
+	/*
+	 * Set the GLOBAL flags only if the PRESENT flag is
+	 * set otherwise pte_present will return true even on
+	 * a non present pte. The canon_pgprot will clear
+	 * _PAGE_GLOBAL for the ancient hardware that doesn't
+	 * support it.
+	 */
+	if (pgprot_val(pgprot) & _PAGE_PRESENT)
+		pgprot_val(pgprot) |= _PAGE_GLOBAL;
+	else
+		pgprot_val(pgprot) &= ~_PAGE_GLOBAL;
+
+	pgprot = canon_pgprot(pgprot);
+
 	while (num_pages-- && start < end) {
-
-		/* deal with the NX bit */
-		if (!(pgprot_val(pgprot) & _PAGE_NX))
-			cpa->pfn &= ~_PAGE_NX;
-
-		set_pte(pte, pfn_pte(cpa->pfn >> PAGE_SHIFT, pgprot));
+		set_pte(pte, pfn_pte(cpa->pfn, pgprot));
 
 		start	 += PAGE_SIZE;
-		cpa->pfn += PAGE_SIZE;
+		cpa->pfn++;
 		pte++;
 	}
 }
···
 
 		pmd = pmd_offset(pud, start);
 
-		set_pmd(pmd, __pmd(cpa->pfn | _PAGE_PSE |
+		set_pmd(pmd, __pmd(cpa->pfn << PAGE_SHIFT | _PAGE_PSE |
 				   massage_pgprot(pmd_pgprot)));
 
 		start	  += PMD_SIZE;
-		cpa->pfn  += PMD_SIZE;
+		cpa->pfn  += PMD_SIZE >> PAGE_SHIFT;
 		cur_pages += PMD_SIZE >> PAGE_SHIFT;
 	}
 
···
 	/*
 	 * Map everything starting from the Gb boundary, possibly with 1G pages
 	 */
-	while (end - start >= PUD_SIZE) {
-		set_pud(pud, __pud(cpa->pfn | _PAGE_PSE |
+	while (cpu_has_gbpages && end - start >= PUD_SIZE) {
+		set_pud(pud, __pud(cpa->pfn << PAGE_SHIFT | _PAGE_PSE |
 				   massage_pgprot(pud_pgprot)));
 
 		start	  += PUD_SIZE;
-		cpa->pfn  += PUD_SIZE;
+		cpa->pfn  += PUD_SIZE >> PAGE_SHIFT;
 		cur_pages += PUD_SIZE >> PAGE_SHIFT;
 		pud++;
 	}
···
 
 	if (!(page_flags & _PAGE_NX))
 		cpa.mask_clr = __pgprot(_PAGE_NX);
+
+	if (!(page_flags & _PAGE_RW))
+		cpa.mask_clr = __pgprot(_PAGE_RW);
 
 	cpa.mask_set = __pgprot(_PAGE_PRESENT | page_flags);
 

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

···
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/acpi.h>
···
 void __init efi_bgrt_init(void)
 {
 	acpi_status status;
-	void __iomem *image;
-	bool ioremapped = false;
+	void *image;
 	struct bmp_header bmp_header;
 
 	if (acpi_disabled)
···
 		       bgrt_tab->status);
 		return;
 	}
-	if (bgrt_tab->status != 1) {
-		pr_debug("Ignoring BGRT: invalid status %u (expected 1)\n",
-			 bgrt_tab->status);
-		return;
-	}
 	if (bgrt_tab->image_type != 0) {
 		pr_err("Ignoring BGRT: invalid image type %u (expected 0)\n",
 		       bgrt_tab->image_type);
···
 		return;
 	}
 
-	image = efi_lookup_mapped_addr(bgrt_tab->image_address);
+	image = memremap(bgrt_tab->image_address, sizeof(bmp_header), MEMREMAP_WB);
 	if (!image) {
-		image = early_ioremap(bgrt_tab->image_address,
-				       sizeof(bmp_header));
-		ioremapped = true;
-		if (!image) {
-			pr_err("Ignoring BGRT: failed to map image header memory\n");
-			return;
-		}
+		pr_err("Ignoring BGRT: failed to map image header memory\n");
+		return;
 	}
 
-	memcpy_fromio(&bmp_header, image, sizeof(bmp_header));
-	if (ioremapped)
-		early_iounmap(image, sizeof(bmp_header));
+	memcpy(&bmp_header, image, sizeof(bmp_header));
+	memunmap(image);
+	if (bmp_header.id != 0x4d42) {
+		pr_err("Ignoring BGRT: Incorrect BMP magic number 0x%x (expected 0x4d42)\n",
+			bmp_header.id);
+		return;
+	}
 	bgrt_image_size = bmp_header.size;
 
 	bgrt_image = kmalloc(bgrt_image_size, GFP_KERNEL | __GFP_NOWARN);
···
 		return;
 	}
 
-	if (ioremapped) {
-		image = early_ioremap(bgrt_tab->image_address,
-				       bmp_header.size);
-		if (!image) {
-			pr_err("Ignoring BGRT: failed to map image memory\n");
-			kfree(bgrt_image);
-			bgrt_image = NULL;
-			return;
-		}
+	image = memremap(bgrt_tab->image_address, bmp_header.size, MEMREMAP_WB);
+	if (!image) {
+		pr_err("Ignoring BGRT: failed to map image memory\n");
+		kfree(bgrt_image);
+		bgrt_image = NULL;
+		return;
 	}
 
-	memcpy_fromio(bgrt_image, image, bgrt_image_size);
-	if (ioremapped)
-		early_iounmap(image, bmp_header.size);
+	memcpy(bgrt_image, image, bgrt_image_size);
+	memunmap(image);
 }

arch/x86/platform/efi/efi.c

···
 		char buf[64];
 
 		md = p;
-		pr_info("mem%02u: %s range=[0x%016llx-0x%016llx) (%lluMB)\n",
+		pr_info("mem%02u: %s range=[0x%016llx-0x%016llx] (%lluMB)\n",
 			i, efi_md_typeattr_format(buf, sizeof(buf), md),
 			md->phys_addr,
-			md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT),
+			md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT) - 1,
 			(md->num_pages >> (20 - EFI_PAGE_SHIFT)));
 	}
 #endif  /*  EFI_DEBUG  */
···
 {
 #ifdef CONFIG_KEXEC_CORE
 	efi_memory_desc_t *md;
+	unsigned int num_pages;
 	void *p;
 
 	efi.systab = NULL;
···
 	 */
 	if (!efi_is_native()) {
 		efi_unmap_memmap();
+		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+		return;
+	}
+
+	if (efi_alloc_page_tables()) {
+		pr_err("Failed to allocate EFI page tables\n");
 		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
 		return;
 	}
···
 	save_runtime_map();
 
 	BUG_ON(!efi.systab);
+
+	num_pages = ALIGN(memmap.nr_map * memmap.desc_size, PAGE_SIZE);
+	num_pages >>= PAGE_SHIFT;
+
+	if (efi_setup_page_tables(memmap.phys_map, num_pages)) {
+		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+		return;
+	}
 
 	efi_sync_low_kernel_mappings();
 
···
  * This function will switch the EFI runtime services to virtual mode.
  * Essentially, we look through the EFI memmap and map every region that
  * has the runtime attribute bit set in its memory descriptor into the
- * ->trampoline_pgd page table using a top-down VA allocation scheme.
+ * efi_pgd page table.
  *
  * The old method which used to update that memory descriptor with the
  * virtual address obtained from ioremap() is still supported when the
···
  *
  * The new method does a pagetable switch in a preemption-safe manner
  * so that we're in a different address space when calling a runtime
- * function. For function arguments passing we do copy the PGDs of the
- * kernel page table into ->trampoline_pgd prior to each call.
+ * function. For function arguments passing we do copy the PUDs of the
+ * kernel page table into efi_pgd prior to each call.
  *
  * Specially for kexec boot, efi runtime maps in previous kernel should
  * be passed in via setup_data. In that case runtime ranges will be mapped
···
 	efi_status_t status;
 
 	efi.systab = NULL;
+
+	if (efi_alloc_page_tables()) {
+		pr_err("Failed to allocate EFI page tables\n");
+		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+		return;
+	}
 
 	efi_merge_regions();
 	new_memmap = efi_map_regions(&count, &pg_shift);
···
 	}
 
 	efi_sync_low_kernel_mappings();
-	efi_dump_pagetable();
 
 	if (efi_is_native()) {
 		status = phys_efi_set_virtual_address_map(
···
 
 	efi.set_virtual_address_map = NULL;
 
-	efi_runtime_mkexec();
+	/*
+	 * Apply more restrictive page table mapping attributes now that
+	 * SVAM() has been called and the firmware has performed all
+	 * necessary relocation fixups for the new virtual addresses.
+	 */
+	efi_runtime_update_mappings();
+	efi_dump_pagetable();
 
 	/*
-	 * We mapped the descriptor array into the EFI pagetable above but we're
-	 * not unmapping it here. Here's why:
-	 *
-	 * We're copying select PGDs from the kernel page table to the EFI page
-	 * table and when we do so and make changes to those PGDs like unmapping
-	 * stuff from them, those changes appear in the kernel page table and we
-	 * go boom.
-	 *
-	 * From setup_real_mode():
-	 *
-	 * ...
-	 * trampoline_pgd[0] = init_level4_pgt[pgd_index(__PAGE_OFFSET)].pgd;
-	 *
-	 * In this particular case, our allocation is in PGD 0 of the EFI page
-	 * table but we've copied that PGD from PGD[272] of the EFI page table:
-	 *
-	 *	pgd_index(__PAGE_OFFSET = 0xffff880000000000) = 272
-	 *
-	 * where the direct memory mapping in kernel space is.
-	 *
-	 * new_memmap's VA comes from that direct mapping and thus clearing it,
-	 * it would get cleared in the kernel page table too.
+	 * 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.
 	 *
 	 * efi_cleanup_page_tables(__pa(new_memmap), 1 << pg_shift);
 	 */

arch/x86/platform/efi/efi_32.c

···
  * say 0 - 3G.
  */
 
+int __init efi_alloc_page_tables(void)
+{
+	return 0;
+}
+
 void efi_sync_low_kernel_mappings(void) {}
 void __init efi_dump_pagetable(void) {}
 int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
···
 	__flush_tlb_all();
 }
 
-void __init efi_runtime_mkexec(void)
+void __init efi_runtime_update_mappings(void)
 {
 	if (__supported_pte_mask & _PAGE_NX)
 		runtime_code_page_mkexec();

arch/x86/platform/efi/efi_64.c

···
  *
  */
 
+#define pr_fmt(fmt) "efi: " fmt
+
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/mm.h>
···
 #include <asm/fixmap.h>
 #include <asm/realmode.h>
 #include <asm/time.h>
+#include <asm/pgalloc.h>
 
 /*
  * We allocate runtime services regions bottom-up, starting from -4G, i.e.
···
  */
 static u64 efi_va = EFI_VA_START;
 
-/*
- * Scratch space used for switching the pagetable in the EFI stub
- */
-struct efi_scratch {
-	u64 r15;
-	u64 prev_cr3;
-	pgd_t *efi_pgt;
-	bool use_pgd;
-	u64 phys_stack;
-} __packed;
+struct efi_scratch efi_scratch;
 
 static void __init early_code_mapping_set_exec(int executable)
 {
···
 	int pgd;
 	int n_pgds;
 
-	if (!efi_enabled(EFI_OLD_MEMMAP))
-		return NULL;
+	if (!efi_enabled(EFI_OLD_MEMMAP)) {
+		save_pgd = (pgd_t *)read_cr3();
+		write_cr3((unsigned long)efi_scratch.efi_pgt);
+		goto out;
+	}
 
 	early_code_mapping_set_exec(1);
 
···
 		vaddress = (unsigned long)__va(pgd * PGDIR_SIZE);
 		set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), *pgd_offset_k(vaddress));
 	}
+out:
 	__flush_tlb_all();
 
 	return save_pgd;
···
 	int pgd_idx;
 	int nr_pgds;
 
-	if (!save_pgd)
+	if (!efi_enabled(EFI_OLD_MEMMAP)) {
+		write_cr3((unsigned long)save_pgd);
+		__flush_tlb_all();
 		return;
+	}
 
 	nr_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE);
 
···
 	early_code_mapping_set_exec(0);
 }
 
+static pgd_t *efi_pgd;
+
+/*
+ * We need our own copy of the higher levels of the page tables
+ * because we want to avoid inserting EFI region mappings (EFI_VA_END
+ * to EFI_VA_START) into the standard kernel page tables. Everything
+ * else can be shared, see efi_sync_low_kernel_mappings().
+ */
+int __init efi_alloc_page_tables(void)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	gfp_t gfp_mask;
+
+	if (efi_enabled(EFI_OLD_MEMMAP))
+		return 0;
+
+	gfp_mask = GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO;
+	efi_pgd = (pgd_t *)__get_free_page(gfp_mask);
+	if (!efi_pgd)
+		return -ENOMEM;
+
+	pgd = efi_pgd + pgd_index(EFI_VA_END);
+
+	pud = pud_alloc_one(NULL, 0);
+	if (!pud) {
+		free_page((unsigned long)efi_pgd);
+		return -ENOMEM;
+	}
+
+	pgd_populate(NULL, pgd, pud);
+
+	return 0;
+}
+
 /*
  * Add low kernel mappings for passing arguments to EFI functions.
  */
 void efi_sync_low_kernel_mappings(void)
 {
-	unsigned num_pgds;
-	pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
+	unsigned num_entries;
+	pgd_t *pgd_k, *pgd_efi;
+	pud_t *pud_k, *pud_efi;
 
 	if (efi_enabled(EFI_OLD_MEMMAP))
 		return;
 
-	num_pgds = pgd_index(MODULES_END - 1) - pgd_index(PAGE_OFFSET);
+	/*
+	 * We can share all PGD entries apart from the one entry that
+	 * covers the EFI runtime mapping space.
+	 *
+	 * Make sure the EFI runtime region mappings are guaranteed to
+	 * only span a single PGD entry and that the entry also maps
+	 * other important kernel regions.
+	 */
+	BUILD_BUG_ON(pgd_index(EFI_VA_END) != pgd_index(MODULES_END));
+	BUILD_BUG_ON((EFI_VA_START & PGDIR_MASK) !=
+			(EFI_VA_END & PGDIR_MASK));
 
-	memcpy(pgd + pgd_index(PAGE_OFFSET),
-		init_mm.pgd + pgd_index(PAGE_OFFSET),
-		sizeof(pgd_t) * num_pgds);
+	pgd_efi = efi_pgd + pgd_index(PAGE_OFFSET);
+	pgd_k = pgd_offset_k(PAGE_OFFSET);
+
+	num_entries = pgd_index(EFI_VA_END) - pgd_index(PAGE_OFFSET);
+	memcpy(pgd_efi, pgd_k, sizeof(pgd_t) * num_entries);
+
+	/*
+	 * We share all the PUD entries apart from those that map the
+	 * EFI regions. Copy around them.
+	 */
+	BUILD_BUG_ON((EFI_VA_START & ~PUD_MASK) != 0);
+	BUILD_BUG_ON((EFI_VA_END & ~PUD_MASK) != 0);
+
+	pgd_efi = efi_pgd + pgd_index(EFI_VA_END);
+	pud_efi = pud_offset(pgd_efi, 0);
+
+	pgd_k = pgd_offset_k(EFI_VA_END);
+	pud_k = pud_offset(pgd_k, 0);
+
+	num_entries = pud_index(EFI_VA_END);
+	memcpy(pud_efi, pud_k, sizeof(pud_t) * num_entries);
+
+	pud_efi = pud_offset(pgd_efi, EFI_VA_START);
+	pud_k = pud_offset(pgd_k, EFI_VA_START);
+
+	num_entries = PTRS_PER_PUD - pud_index(EFI_VA_START);
+	memcpy(pud_efi, pud_k, sizeof(pud_t) * num_entries);
 }
 
 int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 {
-	unsigned long text;
+	unsigned long pfn, text;
+	efi_memory_desc_t *md;
 	struct page *page;
 	unsigned npages;
 	pgd_t *pgd;
···
 	if (efi_enabled(EFI_OLD_MEMMAP))
 		return 0;
 
-	efi_scratch.efi_pgt = (pgd_t *)(unsigned long)real_mode_header->trampoline_pgd;
-	pgd = __va(efi_scratch.efi_pgt);
+	efi_scratch.efi_pgt = (pgd_t *)__pa(efi_pgd);
+	pgd = efi_pgd;
 
 	/*
 	 * It can happen that the physical address of new_memmap lands in memory
···
 	 * and ident-map those pages containing the map before calling
 	 * phys_efi_set_virtual_address_map().
 	 */
-	if (kernel_map_pages_in_pgd(pgd, pa_memmap, pa_memmap, num_pages, _PAGE_NX)) {
+	pfn = pa_memmap >> PAGE_SHIFT;
+	if (kernel_map_pages_in_pgd(pgd, pfn, pa_memmap, num_pages, _PAGE_NX | _PAGE_RW)) {
 		pr_err("Error ident-mapping new memmap (0x%lx)!\n", pa_memmap);
 		return 1;
 	}
···
 	if (!IS_ENABLED(CONFIG_EFI_MIXED))
 		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(&memmap, 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");
···
 	efi_scratch.phys_stack = virt_to_phys(page_address(page));
 	efi_scratch.phys_stack += PAGE_SIZE; /* stack grows down */
 
-	npages = (_end - _text) >> PAGE_SHIFT;
+	npages = (_etext - _text) >> PAGE_SHIFT;
 	text = __pa(_text);
+	pfn = text >> PAGE_SHIFT;
 
-	if (kernel_map_pages_in_pgd(pgd, text >> PAGE_SHIFT, text, npages, 0)) {
+	if (kernel_map_pages_in_pgd(pgd, pfn, text, npages, _PAGE_RW)) {
 		pr_err("Failed to map kernel text 1:1\n");
 		return 1;
 	}
···
 
 void __init efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 {
-	pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
-
-	kernel_unmap_pages_in_pgd(pgd, pa_memmap, num_pages);
+	kernel_unmap_pages_in_pgd(efi_pgd, pa_memmap, num_pages);
 }
 
 static void __init __map_region(efi_memory_desc_t *md, u64 va)
 {
-	pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
-	unsigned long pf = 0;
+	unsigned long flags = _PAGE_RW;
+	unsigned long pfn;
+	pgd_t *pgd = efi_pgd;
 
 	if (!(md->attribute & EFI_MEMORY_WB))
-		pf |= _PAGE_PCD;
+		flags |= _PAGE_PCD;
 
-	if (kernel_map_pages_in_pgd(pgd, md->phys_addr, va, md->num_pages, pf))
+	pfn = md->phys_addr >> PAGE_SHIFT;
+	if (kernel_map_pages_in_pgd(pgd, pfn, va, md->num_pages, flags))
 		pr_warn("Error mapping PA 0x%llx -> VA 0x%llx!\n",
 			   md->phys_addr, va);
 }
···
 	efi_setup = phys_addr + sizeof(struct setup_data);
 }
 
-void __init efi_runtime_mkexec(void)
+void __init efi_runtime_update_mappings(void)
 {
-	if (!efi_enabled(EFI_OLD_MEMMAP))
+	unsigned long pfn;
+	pgd_t *pgd = efi_pgd;
+	efi_memory_desc_t *md;
+	void *p;
+
+	if (efi_enabled(EFI_OLD_MEMMAP)) {
+		if (__supported_pte_mask & _PAGE_NX)
+			runtime_code_page_mkexec();
+		return;
+	}
+
+	if (!efi_enabled(EFI_NX_PE_DATA))
 		return;
 
-	if (__supported_pte_mask & _PAGE_NX)
-		runtime_code_page_mkexec();
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		unsigned long pf = 0;
+		md = p;
+
+		if (!(md->attribute & EFI_MEMORY_RUNTIME))
+			continue;
+
+		if (!(md->attribute & EFI_MEMORY_WB))
+			pf |= _PAGE_PCD;
+
+		if ((md->attribute & EFI_MEMORY_XP) ||
+			(md->type == EFI_RUNTIME_SERVICES_DATA))
+			pf |= _PAGE_NX;
+
+		if (!(md->attribute & EFI_MEMORY_RO) &&
+			(md->type != EFI_RUNTIME_SERVICES_CODE))
+			pf |= _PAGE_RW;
+
+		/* Update the 1:1 mapping */
+		pfn = md->phys_addr >> PAGE_SHIFT;
+		if (kernel_map_pages_in_pgd(pgd, pfn, md->phys_addr, md->num_pages, pf))
+			pr_warn("Error mapping PA 0x%llx -> VA 0x%llx!\n",
+				   md->phys_addr, md->virt_addr);
+
+		if (kernel_map_pages_in_pgd(pgd, pfn, md->virt_addr, md->num_pages, pf))
+			pr_warn("Error mapping PA 0x%llx -> VA 0x%llx!\n",
+				   md->phys_addr, md->virt_addr);
+	}
 }
 
 void __init efi_dump_pagetable(void)
 {
 #ifdef CONFIG_EFI_PGT_DUMP
-	pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
-
-	ptdump_walk_pgd_level(NULL, pgd);
+	ptdump_walk_pgd_level(NULL, efi_pgd);
 #endif
 }
 

arch/x86/platform/efi/efi_stub_64.S

···
 	mov %rsi, %cr0;			\
 	mov (%rsp), %rsp
 
-	/* stolen from gcc */
-	.macro FLUSH_TLB_ALL
-	movq %r15, efi_scratch(%rip)
-	movq %r14, efi_scratch+8(%rip)
-	movq %cr4, %r15
-	movq %r15, %r14
-	andb $0x7f, %r14b
-	movq %r14, %cr4
-	movq %r15, %cr4
-	movq efi_scratch+8(%rip), %r14
-	movq efi_scratch(%rip), %r15
-	.endm
-
-	.macro SWITCH_PGT
-	cmpb $0, efi_scratch+24(%rip)
-	je 1f
-	movq %r15, efi_scratch(%rip)		# r15
-	# save previous CR3
-	movq %cr3, %r15
-	movq %r15, efi_scratch+8(%rip)		# prev_cr3
-	movq efi_scratch+16(%rip), %r15		# EFI pgt
-	movq %r15, %cr3
-	1:
-	.endm
-
-	.macro RESTORE_PGT
-	cmpb $0, efi_scratch+24(%rip)
-	je 2f
-	movq efi_scratch+8(%rip), %r15
-	movq %r15, %cr3
-	movq efi_scratch(%rip), %r15
-	FLUSH_TLB_ALL
-	2:
-	.endm
-
 ENTRY(efi_call)
 	FRAME_BEGIN
 	SAVE_XMM
···
 	mov %r8, %r9
 	mov %rcx, %r8
 	mov %rsi, %rcx
-	SWITCH_PGT
 	call *%rdi
-	RESTORE_PGT
 	addq $48, %rsp
 	RESTORE_XMM
 	FRAME_END
 	ret
 ENDPROC(efi_call)
-
-	.data
-ENTRY(efi_scratch)
-	.fill 3,8,0
-	.byte 0
-	.quad 0

arch/x86/platform/efi/quirks.c

···
+#define pr_fmt(fmt) "efi: " fmt
+
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
···
 }
 
 /*
+ * In the nonblocking case we do not attempt to perform garbage
+ * collection if we do not have enough free space. Rather, we do the
+ * bare minimum check and give up immediately if the available space
+ * is below EFI_MIN_RESERVE.
+ *
+ * This function is intended to be small and simple because it is
+ * invoked from crash handler paths.
+ */
+static efi_status_t
+query_variable_store_nonblocking(u32 attributes, unsigned long size)
+{
+	efi_status_t status;
+	u64 storage_size, remaining_size, max_size;
+
+	status = efi.query_variable_info_nonblocking(attributes, &storage_size,
+						     &remaining_size,
+						     &max_size);
+	if (status != EFI_SUCCESS)
+		return status;
+
+	if (remaining_size - size < EFI_MIN_RESERVE)
+		return EFI_OUT_OF_RESOURCES;
+
+	return EFI_SUCCESS;
+}
+
+/*
  * Some firmware implementations refuse to boot if there's insufficient space
  * in the variable store. Ensure that we never use more than a safe limit.
  *
  * Return EFI_SUCCESS if it is safe to write 'size' bytes to the variable
  * store.
  */
-efi_status_t efi_query_variable_store(u32 attributes, unsigned long size)
+efi_status_t efi_query_variable_store(u32 attributes, unsigned long size,
+				      bool nonblocking)
 {
 	efi_status_t status;
 	u64 storage_size, remaining_size, max_size;
 
 	if (!(attributes & EFI_VARIABLE_NON_VOLATILE))
 		return 0;
+
+	if (nonblocking)
+		return query_variable_store_nonblocking(attributes, size);
 
 	status = efi.query_variable_info(attributes, &storage_size,
 					 &remaining_size, &max_size);
···
 	 * services.
 	 */
 	if (!efi_runtime_supported()) {
-		pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n");
+		pr_info("Setup done, disabling due to 32/64-bit mismatch\n");
 		efi_unmap_memmap();
 	}
 

drivers/firmware/efi/arm-init.c

···
 	char vendor[100] = "unknown";
 	int i, retval;
 
-	efi.systab = early_memremap(efi_system_table,
-				    sizeof(efi_system_table_t));
+	efi.systab = early_memremap_ro(efi_system_table,
+				       sizeof(efi_system_table_t));
 	if (efi.systab == NULL) {
 		pr_warn("Unable to map EFI system table.\n");
 		return -ENOMEM;
···
 			efi.systab->hdr.revision & 0xffff);
 
 	/* Show what we know for posterity */
-	c16 = early_memremap(efi_to_phys(efi.systab->fw_vendor),
-			     sizeof(vendor) * sizeof(efi_char16_t));
+	c16 = early_memremap_ro(efi_to_phys(efi.systab->fw_vendor),
+				sizeof(vendor) * sizeof(efi_char16_t));
 	if (c16) {
 		for (i = 0; i < (int) sizeof(vendor) - 1 && *c16; ++i)
 			vendor[i] = c16[i];
···
 		efi.systab->hdr.revision & 0xffff, vendor);
 
 	table_size = sizeof(efi_config_table_64_t) * efi.systab->nr_tables;
-	config_tables = early_memremap(efi_to_phys(efi.systab->tables),
-				       table_size);
+	config_tables = early_memremap_ro(efi_to_phys(efi.systab->tables),
+					  table_size);
 	if (config_tables == NULL) {
 		pr_warn("Unable to map EFI config table array.\n");
 		retval = -ENOMEM;
···
 	efi_system_table = params.system_table;
 
 	memmap.phys_map = params.mmap;
-	memmap.map = early_memremap(params.mmap, params.mmap_size);
+	memmap.map = early_memremap_ro(params.mmap, params.mmap_size);
 	if (memmap.map == NULL) {
 		/*
 		* If we are booting via UEFI, the UEFI memory map is the only

drivers/firmware/efi/efi.c

···
 {
 	generic_ops.get_variable = efi.get_variable;
 	generic_ops.set_variable = efi.set_variable;
+	generic_ops.set_variable_nonblocking = efi.set_variable_nonblocking;
 	generic_ops.get_next_variable = efi.get_next_variable;
 	generic_ops.query_variable_store = efi_query_variable_store;
 
···
 	u64 size = md->num_pages << EFI_PAGE_SHIFT;
 	u64 end = md->phys_addr + size;
 	return end;
-}
-
-/*
- * We can't ioremap data in EFI boot services RAM, because we've already mapped
- * it as RAM.  So, look it up in the existing EFI memory map instead.  Only
- * callable after efi_enter_virtual_mode and before efi_free_boot_services.
- */
-void __iomem *efi_lookup_mapped_addr(u64 phys_addr)
-{
-	struct efi_memory_map *map;
-	void *p;
-	map = efi.memmap;
-	if (!map)
-		return NULL;
-	if (WARN_ON(!map->map))
-		return NULL;
-	for (p = map->map; p < map->map_end; p += map->desc_size) {
-		efi_memory_desc_t *md = p;
-		u64 size = md->num_pages << EFI_PAGE_SHIFT;
-		u64 end = md->phys_addr + size;
-		if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
-		    md->type != EFI_BOOT_SERVICES_CODE &&
-		    md->type != EFI_BOOT_SERVICES_DATA)
-			continue;
-		if (!md->virt_addr)
-			continue;
-		if (phys_addr >= md->phys_addr && phys_addr < end) {
-			phys_addr += md->virt_addr - md->phys_addr;
-			return (__force void __iomem *)(unsigned long)phys_addr;
-		}
-	}
-	return NULL;
 }
 
 static __initdata efi_config_table_type_t common_tables[] = {
···
 	"ACPI Memory NVS",
 	"Memory Mapped I/O",
 	"MMIO Port Space",
-	"PAL Code"
+	"PAL Code",
+	"Persistent Memory",
 };
 
 char * __init efi_md_typeattr_format(char *buf, size_t size,
···
 	if (attr & ~(EFI_MEMORY_UC | EFI_MEMORY_WC | EFI_MEMORY_WT |
 		     EFI_MEMORY_WB | EFI_MEMORY_UCE | EFI_MEMORY_RO |
 		     EFI_MEMORY_WP | EFI_MEMORY_RP | EFI_MEMORY_XP |
+		     EFI_MEMORY_NV |
 		     EFI_MEMORY_RUNTIME | EFI_MEMORY_MORE_RELIABLE))
 		snprintf(pos, size, "|attr=0x%016llx]",
 			 (unsigned long long)attr);
 	else
-		snprintf(pos, size, "|%3s|%2s|%2s|%2s|%2s|%2s|%3s|%2s|%2s|%2s|%2s]",
+		snprintf(pos, size,
+			 "|%3s|%2s|%2s|%2s|%2s|%2s|%2s|%3s|%2s|%2s|%2s|%2s]",
 			 attr & EFI_MEMORY_RUNTIME ? "RUN" : "",
 			 attr & EFI_MEMORY_MORE_RELIABLE ? "MR" : "",
+			 attr & EFI_MEMORY_NV      ? "NV"  : "",
 			 attr & EFI_MEMORY_XP      ? "XP"  : "",
 			 attr & EFI_MEMORY_RP      ? "RP"  : "",
 			 attr & EFI_MEMORY_WP      ? "WP"  : "",

drivers/firmware/efi/efivars.c

···
 
 static void efivar_release(struct kobject *kobj)
 {
-	struct efivar_entry *var = container_of(kobj, struct efivar_entry, kobj);
+	struct efivar_entry *var = to_efivar_entry(kobj);
 	kfree(var);
 }
 

drivers/firmware/efi/esrt.c

···
 static int esre_create_sysfs_entry(void *esre, int entry_num)
 {
 	struct esre_entry *entry;
-	char name[20];
 
 	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
 	if (!entry)
 		return -ENOMEM;
-
-	sprintf(name, "entry%d", entry_num);
 
 	entry->kobj.kset = esrt_kset;
 
···
 
 		entry->esre.esre1 = esre;
 		rc = kobject_init_and_add(&entry->kobj, &esre1_ktype, NULL,
-					  "%s", name);
+					  "entry%d", entry_num);
 		if (rc) {
 			kfree(entry);
 			return rc;

drivers/firmware/efi/libstub/arm-stub.c

···
 
 	pr_efi(sys_table, "Booting Linux Kernel...\n");
 
+	status = check_platform_features(sys_table);
+	if (status != EFI_SUCCESS)
+		goto fail;
+
 	/*
 	 * Get a handle to the loaded image protocol.  This is used to get
 	 * information about the running image, such as size and the command

drivers/firmware/efi/libstub/arm32-stub.c

···
 #include <linux/efi.h>
 #include <asm/efi.h>
 
+efi_status_t check_platform_features(efi_system_table_t *sys_table_arg)
+{
+	int block;
+
+	/* non-LPAE kernels can run anywhere */
+	if (!IS_ENABLED(CONFIG_ARM_LPAE))
+		return EFI_SUCCESS;
+
+	/* LPAE kernels need compatible hardware */
+	block = cpuid_feature_extract(CPUID_EXT_MMFR0, 0);
+	if (block < 5) {
+		pr_efi_err(sys_table_arg, "This LPAE kernel is not supported by your CPU\n");
+		return EFI_UNSUPPORTED;
+	}
+	return EFI_SUCCESS;
+}
+
 efi_status_t handle_kernel_image(efi_system_table_t *sys_table,
 				 unsigned long *image_addr,
 				 unsigned long *image_size,

drivers/firmware/efi/libstub/arm64-stub.c

···
 #include <linux/efi.h>
 #include <asm/efi.h>
 #include <asm/sections.h>
+#include <asm/sysreg.h>
 
 #include "efistub.h"
 
 extern bool __nokaslr;
 
-efi_status_t __init handle_kernel_image(efi_system_table_t *sys_table_arg,
-					unsigned long *image_addr,
-					unsigned long *image_size,
-					unsigned long *reserve_addr,
-					unsigned long *reserve_size,
-					unsigned long dram_base,
-					efi_loaded_image_t *image)
+efi_status_t check_platform_features(efi_system_table_t *sys_table_arg)
+{
+	u64 tg;
+
+	/* UEFI mandates support for 4 KB granularity, no need to check */
+	if (IS_ENABLED(CONFIG_ARM64_4K_PAGES))
+		return EFI_SUCCESS;
+
+	tg = (read_cpuid(ID_AA64MMFR0_EL1) >> ID_AA64MMFR0_TGRAN_SHIFT) & 0xf;
+	if (tg != ID_AA64MMFR0_TGRAN_SUPPORTED) {
+		if (IS_ENABLED(CONFIG_ARM64_64K_PAGES))
+			pr_efi_err(sys_table_arg, "This 64 KB granular kernel is not supported by your CPU\n");
+		else
+			pr_efi_err(sys_table_arg, "This 16 KB granular kernel is not supported by your CPU\n");
+		return EFI_UNSUPPORTED;
+	}
+	return EFI_SUCCESS;
+}
+
+efi_status_t handle_kernel_image(efi_system_table_t *sys_table_arg,
+				 unsigned long *image_addr,
+				 unsigned long *image_size,
+				 unsigned long *reserve_addr,
+				 unsigned long *reserve_size,
+				 unsigned long dram_base,
+				 efi_loaded_image_t *image)
 {
 	efi_status_t status;
 	unsigned long kernel_size, kernel_memsize = 0;

drivers/firmware/efi/libstub/efistub.h

···
 /* error code which can't be mistaken for valid address */
 #define EFI_ERROR	(~0UL)
 
+/*
+ * __init annotations should not be used in the EFI stub, since the code is
+ * either included in the decompressor (x86, ARM) where they have no effect,
+ * or the whole stub is __init annotated at the section level (arm64), by
+ * renaming the sections, in which case the __init annotation will be
+ * redundant, and will result in section names like .init.init.text, and our
+ * linker script does not expect that.
+ */
+#undef __init
+
 void efi_char16_printk(efi_system_table_t *, efi_char16_t *);
 
 efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg, void *__image,
···
 efi_status_t efi_random_alloc(efi_system_table_t *sys_table_arg,
 			      unsigned long size, unsigned long align,
 			      unsigned long *addr, unsigned long random_seed);
+
+efi_status_t check_platform_features(efi_system_table_t *sys_table_arg);
 
 #endif

drivers/firmware/efi/runtime-wrappers.c

···
  */
 static DEFINE_SPINLOCK(efi_runtime_lock);
 
-/*
- * Some runtime services calls can be reentrant under NMI, even if the table
- * above says they are not. (source: UEFI Specification v2.4A)
- *
- * Table 32. Functions that may be called after Machine Check, INIT and NMI
- * +----------------------------+------------------------------------------+
- * | Function			| Called after Machine Check, INIT and NMI |
- * +----------------------------+------------------------------------------+
- * | GetTime()			| Yes, even if previously busy.		   |
- * | GetVariable()		| Yes, even if previously busy		   |
- * | GetNextVariableName()	| Yes, even if previously busy		   |
- * | QueryVariableInfo()	| Yes, even if previously busy		   |
- * | SetVariable()		| Yes, even if previously busy		   |
- * | UpdateCapsule()		| Yes, even if previously busy		   |
- * | QueryCapsuleCapabilities()	| Yes, even if previously busy		   |
- * | ResetSystem()		| Yes, even if previously busy		   |
- * +----------------------------+------------------------------------------+
- *
- * In order to prevent deadlocks under NMI, the wrappers for these functions
- * may only grab the efi_runtime_lock or rtc_lock spinlocks if !efi_in_nmi().
- * However, not all of the services listed are reachable through NMI code paths,
- * so the the special handling as suggested by the UEFI spec is only implemented
- * for QueryVariableInfo() and SetVariable(), as these can be reached in NMI
- * context through efi_pstore_write().
- */
-
-/*
- * As per commit ef68c8f87ed1 ("x86: Serialize EFI time accesses on rtc_lock"),
- * the EFI specification requires that callers of the time related runtime
- * functions serialize with other CMOS accesses in the kernel, as the EFI time
- * functions may choose to also use the legacy CMOS RTC.
- */
-__weak DEFINE_SPINLOCK(rtc_lock);
-
 static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc)
 {
-	unsigned long flags;
 	efi_status_t status;
 
-	spin_lock_irqsave(&rtc_lock, flags);
 	spin_lock(&efi_runtime_lock);
 	status = efi_call_virt(get_time, tm, tc);
 	spin_unlock(&efi_runtime_lock);
-	spin_unlock_irqrestore(&rtc_lock, flags);
 	return status;
 }
 
 static efi_status_t virt_efi_set_time(efi_time_t *tm)
 {
-	unsigned long flags;
 	efi_status_t status;
 
-	spin_lock_irqsave(&rtc_lock, flags);
 	spin_lock(&efi_runtime_lock);
 	status = efi_call_virt(set_time, tm);
 	spin_unlock(&efi_runtime_lock);
-	spin_unlock_irqrestore(&rtc_lock, flags);
 	return status;
 }
 
···
 					     efi_bool_t *pending,
 					     efi_time_t *tm)
 {
-	unsigned long flags;
 	efi_status_t status;
 
-	spin_lock_irqsave(&rtc_lock, flags);
 	spin_lock(&efi_runtime_lock);
 	status = efi_call_virt(get_wakeup_time, enabled, pending, tm);
 	spin_unlock(&efi_runtime_lock);
-	spin_unlock_irqrestore(&rtc_lock, flags);
 	return status;
 }
 
 static efi_status_t virt_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
 {
-	unsigned long flags;
 	efi_status_t status;
 
-	spin_lock_irqsave(&rtc_lock, flags);
 	spin_lock(&efi_runtime_lock);
 	status = efi_call_virt(set_wakeup_time, enabled, tm);
 	spin_unlock(&efi_runtime_lock);
-	spin_unlock_irqrestore(&rtc_lock, flags);
 	return status;
 }
 
···
 					  unsigned long *data_size,
 					  void *data)
 {
-	unsigned long flags;
 	efi_status_t status;
 
-	spin_lock_irqsave(&efi_runtime_lock, flags);
+	spin_lock(&efi_runtime_lock);
 	status = efi_call_virt(get_variable, name, vendor, attr, data_size,
 			       data);
-	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+	spin_unlock(&efi_runtime_lock);
 	return status;
 }
 
···
 					       efi_char16_t *name,
 					       efi_guid_t *vendor)
 {
-	unsigned long flags;
 	efi_status_t status;
 
-	spin_lock_irqsave(&efi_runtime_lock, flags);
+	spin_lock(&efi_runtime_lock);
 	status = efi_call_virt(get_next_variable, name_size, name, vendor);
-	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+	spin_unlock(&efi_runtime_lock);
 	return status;
 }
 
···
 					  unsigned long data_size,
 					  void *data)
 {
-	unsigned long flags;
 	efi_status_t status;
 
-	spin_lock_irqsave(&efi_runtime_lock, flags);
+	spin_lock(&efi_runtime_lock);
 	status = efi_call_virt(set_variable, name, vendor, attr, data_size,
 			       data);
-	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+	spin_unlock(&efi_runtime_lock);
 	return status;
 }
 
···
 				  u32 attr, unsigned long data_size,
 				  void *data)
 {
-	unsigned long flags;
 	efi_status_t status;
 
-	if (!spin_trylock_irqsave(&efi_runtime_lock, flags))
+	if (!spin_trylock(&efi_runtime_lock))
 		return EFI_NOT_READY;
 
 	status = efi_call_virt(set_variable, name, vendor, attr, data_size,
 			       data);
-	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+	spin_unlock(&efi_runtime_lock);
 	return status;
 }
 
···
 						 u64 *remaining_space,
 						 u64 *max_variable_size)
 {
-	unsigned long flags;
 	efi_status_t status;
 
 	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
 		return EFI_UNSUPPORTED;
 
-	spin_lock_irqsave(&efi_runtime_lock, flags);
+	spin_lock(&efi_runtime_lock);
 	status = efi_call_virt(query_variable_info, attr, storage_space,
 			       remaining_space, max_variable_size);
-	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+	spin_unlock(&efi_runtime_lock);
+	return status;
+}
+
+static efi_status_t
+virt_efi_query_variable_info_nonblocking(u32 attr,
+					 u64 *storage_space,
+					 u64 *remaining_space,
+					 u64 *max_variable_size)
+{
+	efi_status_t status;
+
+	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
+		return EFI_UNSUPPORTED;
+
+	if (!spin_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);
 	return status;
 }
 
 static efi_status_t virt_efi_get_next_high_mono_count(u32 *count)
 {
-	unsigned long flags;
 	efi_status_t status;
 
-	spin_lock_irqsave(&efi_runtime_lock, flags);
+	spin_lock(&efi_runtime_lock);
 	status = efi_call_virt(get_next_high_mono_count, count);
-	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+	spin_unlock(&efi_runtime_lock);
 	return status;
 }
 
···
 				  unsigned long data_size,
 				  efi_char16_t *data)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&efi_runtime_lock, flags);
+	spin_lock(&efi_runtime_lock);
 	__efi_call_virt(reset_system, reset_type, status, data_size, data);
-	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+	spin_unlock(&efi_runtime_lock);
 }
 
 static efi_status_t virt_efi_update_capsule(efi_capsule_header_t **capsules,
 					    unsigned long count,
 					    unsigned long sg_list)
 {
-	unsigned long flags;
 	efi_status_t status;
 
 	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
 		return EFI_UNSUPPORTED;
 
-	spin_lock_irqsave(&efi_runtime_lock, flags);
+	spin_lock(&efi_runtime_lock);
 	status = efi_call_virt(update_capsule, capsules, count, sg_list);
-	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+	spin_unlock(&efi_runtime_lock);
 	return status;
 }
 
···
 						u64 *max_size,
 						int *reset_type)
 {
-	unsigned long flags;
 	efi_status_t status;
 
 	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
 		return EFI_UNSUPPORTED;
 
-	spin_lock_irqsave(&efi_runtime_lock, flags);
+	spin_lock(&efi_runtime_lock);
 	status = efi_call_virt(query_capsule_caps, capsules, count, max_size,
 			       reset_type);
-	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+	spin_unlock(&efi_runtime_lock);
 	return status;
 }
 
···
 	efi.get_next_high_mono_count = virt_efi_get_next_high_mono_count;
 	efi.reset_system = virt_efi_reset_system;
 	efi.query_variable_info = virt_efi_query_variable_info;
+	efi.query_variable_info_nonblocking = virt_efi_query_variable_info_nonblocking;
 	efi.update_capsule = virt_efi_update_capsule;
 	efi.query_capsule_caps = virt_efi_query_capsule_caps;
 }

drivers/firmware/efi/vars.c

···
 	if (!fops->query_variable_store)
 		return EFI_UNSUPPORTED;
 
-	return fops->query_variable_store(attributes, size);
+	return fops->query_variable_store(attributes, size, false);
+}
+
+static efi_status_t
+check_var_size_nonblocking(u32 attributes, unsigned long size)
+{
+	const struct efivar_operations *fops = __efivars->ops;
+
+	if (!fops->query_variable_store)
+		return EFI_UNSUPPORTED;
+
+	return fops->query_variable_store(attributes, size, true);
 }
 
 static int efi_status_to_err(efi_status_t status)
···
 	if (!spin_trylock_irqsave(&__efivars->lock, flags))
 		return -EBUSY;
 
-	status = check_var_size(attributes, size + ucs2_strsize(name, 1024));
+	status = check_var_size_nonblocking(attributes,
+					    size + ucs2_strsize(name, 1024));
 	if (status != EFI_SUCCESS) {
 		spin_unlock_irqrestore(&__efivars->lock, flags);
 		return -ENOSPC;

include/linux/efi.h

···
 #define EFI_MEMORY_WP		((u64)0x0000000000001000ULL)	/* write-protect */
 #define EFI_MEMORY_RP		((u64)0x0000000000002000ULL)	/* read-protect */
 #define EFI_MEMORY_XP		((u64)0x0000000000004000ULL)	/* execute-protect */
+#define EFI_MEMORY_NV		((u64)0x0000000000008000ULL)	/* non-volatile */
 #define EFI_MEMORY_MORE_RELIABLE \
 				((u64)0x0000000000010000ULL)	/* higher reliability */
 #define EFI_MEMORY_RO		((u64)0x0000000000020000ULL)	/* read-only */
···
 typedef efi_status_t efi_set_variable_t (efi_char16_t *name, efi_guid_t *vendor, 
 					 u32 attr, unsigned long data_size,
 					 void *data);
-typedef efi_status_t
-efi_set_variable_nonblocking_t(efi_char16_t *name, efi_guid_t *vendor,
-			       u32 attr, unsigned long data_size, void *data);
-
 typedef efi_status_t efi_get_next_high_mono_count_t (u32 *count);
 typedef void efi_reset_system_t (int reset_type, efi_status_t status,
 				 unsigned long data_size, efi_char16_t *data);
···
 					      unsigned long count,
 					      u64 *max_size,
 					      int *reset_type);
-typedef efi_status_t efi_query_variable_store_t(u32 attributes, unsigned long size);
+typedef efi_status_t efi_query_variable_store_t(u32 attributes,
+						unsigned long size,
+						bool nonblocking);
 
 void efi_native_runtime_setup(void);
 
···
  *  EFI Configuration Table and GUID definitions
  */
 #define NULL_GUID \
-    EFI_GUID(  0x00000000, 0x0000, 0x0000, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 )
+	EFI_GUID(0x00000000, 0x0000, 0x0000, \
+		 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00)
 
 #define MPS_TABLE_GUID    \
-    EFI_GUID(  0xeb9d2d2f, 0x2d88, 0x11d3, 0x9a, 0x16, 0x0, 0x90, 0x27, 0x3f, 0xc1, 0x4d )
+	EFI_GUID(0xeb9d2d2f, 0x2d88, 0x11d3, \
+		 0x9a, 0x16, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d)
 
 #define ACPI_TABLE_GUID    \
-    EFI_GUID(  0xeb9d2d30, 0x2d88, 0x11d3, 0x9a, 0x16, 0x0, 0x90, 0x27, 0x3f, 0xc1, 0x4d )
+	EFI_GUID(0xeb9d2d30, 0x2d88, 0x11d3, \
+		 0x9a, 0x16, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d)
 
 #define ACPI_20_TABLE_GUID    \
-    EFI_GUID(  0x8868e871, 0xe4f1, 0x11d3, 0xbc, 0x22, 0x0, 0x80, 0xc7, 0x3c, 0x88, 0x81 )
+	EFI_GUID(0x8868e871, 0xe4f1, 0x11d3, \
+		 0xbc, 0x22, 0x00, 0x80, 0xc7, 0x3c, 0x88, 0x81)
 
 #define SMBIOS_TABLE_GUID    \
-    EFI_GUID(  0xeb9d2d31, 0x2d88, 0x11d3, 0x9a, 0x16, 0x0, 0x90, 0x27, 0x3f, 0xc1, 0x4d )
+	EFI_GUID(0xeb9d2d31, 0x2d88, 0x11d3, \
+		 0x9a, 0x16, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d)
 
 #define SMBIOS3_TABLE_GUID    \
-    EFI_GUID(  0xf2fd1544, 0x9794, 0x4a2c, 0x99, 0x2e, 0xe5, 0xbb, 0xcf, 0x20, 0xe3, 0x94 )
+	EFI_GUID(0xf2fd1544, 0x9794, 0x4a2c, \
+		 0x99, 0x2e, 0xe5, 0xbb, 0xcf, 0x20, 0xe3, 0x94)
 
 #define SAL_SYSTEM_TABLE_GUID    \
-    EFI_GUID(  0xeb9d2d32, 0x2d88, 0x11d3, 0x9a, 0x16, 0x0, 0x90, 0x27, 0x3f, 0xc1, 0x4d )
+	EFI_GUID(0xeb9d2d32, 0x2d88, 0x11d3, \
+		 0x9a, 0x16, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d)
 
 #define HCDP_TABLE_GUID	\
-    EFI_GUID(  0xf951938d, 0x620b, 0x42ef, 0x82, 0x79, 0xa8, 0x4b, 0x79, 0x61, 0x78, 0x98 )
+	EFI_GUID(0xf951938d, 0x620b, 0x42ef, \
+		 0x82, 0x79, 0xa8, 0x4b, 0x79, 0x61, 0x78, 0x98)
 
 #define UGA_IO_PROTOCOL_GUID \
-    EFI_GUID(  0x61a4d49e, 0x6f68, 0x4f1b, 0xb9, 0x22, 0xa8, 0x6e, 0xed, 0xb, 0x7, 0xa2 )
+	EFI_GUID(0x61a4d49e, 0x6f68, 0x4f1b, \
+		 0xb9, 0x22, 0xa8, 0x6e, 0xed, 0x0b, 0x07, 0xa2)
 
 #define EFI_GLOBAL_VARIABLE_GUID \
-    EFI_GUID(  0x8be4df61, 0x93ca, 0x11d2, 0xaa, 0x0d, 0x00, 0xe0, 0x98, 0x03, 0x2b, 0x8c )
+	EFI_GUID(0x8be4df61, 0x93ca, 0x11d2, \
+		 0xaa, 0x0d, 0x00, 0xe0, 0x98, 0x03, 0x2b, 0x8c)
 
 #define UV_SYSTEM_TABLE_GUID \
-    EFI_GUID(  0x3b13a7d4, 0x633e, 0x11dd, 0x93, 0xec, 0xda, 0x25, 0x56, 0xd8, 0x95, 0x93 )
+	EFI_GUID(0x3b13a7d4, 0x633e, 0x11dd, \
+		 0x93, 0xec, 0xda, 0x25, 0x56, 0xd8, 0x95, 0x93)
 
 #define LINUX_EFI_CRASH_GUID \
-    EFI_GUID(  0xcfc8fc79, 0xbe2e, 0x4ddc, 0x97, 0xf0, 0x9f, 0x98, 0xbf, 0xe2, 0x98, 0xa0 )
+	EFI_GUID(0xcfc8fc79, 0xbe2e, 0x4ddc, \
+		 0x97, 0xf0, 0x9f, 0x98, 0xbf, 0xe2, 0x98, 0xa0)
 
 #define LOADED_IMAGE_PROTOCOL_GUID \
-    EFI_GUID(  0x5b1b31a1, 0x9562, 0x11d2, 0x8e, 0x3f, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b )
+	EFI_GUID(0x5b1b31a1, 0x9562, 0x11d2, \
+		 0x8e, 0x3f, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b)
 
 #define EFI_GRAPHICS_OUTPUT_PROTOCOL_GUID \
-    EFI_GUID(  0x9042a9de, 0x23dc, 0x4a38, 0x96, 0xfb, 0x7a, 0xde, 0xd0, 0x80, 0x51, 0x6a )
+	EFI_GUID(0x9042a9de, 0x23dc, 0x4a38, \
+		 0x96, 0xfb, 0x7a, 0xde, 0xd0, 0x80, 0x51, 0x6a)
 
 #define EFI_UGA_PROTOCOL_GUID \
-    EFI_GUID(  0x982c298b, 0xf4fa, 0x41cb, 0xb8, 0x38, 0x77, 0xaa, 0x68, 0x8f, 0xb8, 0x39 )
+	EFI_GUID(0x982c298b, 0xf4fa, 0x41cb, \
+		 0xb8, 0x38, 0x77, 0xaa, 0x68, 0x8f, 0xb8, 0x39)
 
 #define EFI_PCI_IO_PROTOCOL_GUID \
-    EFI_GUID(  0x4cf5b200, 0x68b8, 0x4ca5, 0x9e, 0xec, 0xb2, 0x3e, 0x3f, 0x50, 0x2, 0x9a )
+	EFI_GUID(0x4cf5b200, 0x68b8, 0x4ca5, \
+		 0x9e, 0xec, 0xb2, 0x3e, 0x3f, 0x50, 0x02, 0x9a)
 
 #define EFI_FILE_INFO_ID \
-    EFI_GUID(  0x9576e92, 0x6d3f, 0x11d2, 0x8e, 0x39, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b )
+	EFI_GUID(0x9576e92, 0x6d3f, 0x11d2, \
+		 0x8e, 0x39, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b)
 
 #define EFI_SYSTEM_RESOURCE_TABLE_GUID \
-    EFI_GUID(  0xb122a263, 0x3661, 0x4f68, 0x99, 0x29, 0x78, 0xf8, 0xb0, 0xd6, 0x21, 0x80 )
+	EFI_GUID(0xb122a263, 0x3661, 0x4f68, \
+		 0x99, 0x29, 0x78, 0xf8, 0xb0, 0xd6, 0x21, 0x80)
 
 #define EFI_FILE_SYSTEM_GUID \
-    EFI_GUID(  0x964e5b22, 0x6459, 0x11d2, 0x8e, 0x39, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b )
+	EFI_GUID(0x964e5b22, 0x6459, 0x11d2, \
+		 0x8e, 0x39, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b)
 
 #define DEVICE_TREE_GUID \
-    EFI_GUID(  0xb1b621d5, 0xf19c, 0x41a5, 0x83, 0x0b, 0xd9, 0x15, 0x2c, 0x69, 0xaa, 0xe0 )
+	EFI_GUID(0xb1b621d5, 0xf19c, 0x41a5, \
+		 0x83, 0x0b, 0xd9, 0x15, 0x2c, 0x69, 0xaa, 0xe0)
 
 #define EFI_PROPERTIES_TABLE_GUID \
-    EFI_GUID(  0x880aaca3, 0x4adc, 0x4a04, 0x90, 0x79, 0xb7, 0x47, 0x34, 0x08, 0x25, 0xe5 )
+	EFI_GUID(0x880aaca3, 0x4adc, 0x4a04, \
+		 0x90, 0x79, 0xb7, 0x47, 0x34, 0x08, 0x25, 0xe5)
 
 #define EFI_RNG_PROTOCOL_GUID \
 	EFI_GUID(0x3152bca5, 0xeade, 0x433d, \
···
 	efi_get_variable_t *get_variable;
 	efi_get_next_variable_t *get_next_variable;
 	efi_set_variable_t *set_variable;
-	efi_set_variable_nonblocking_t *set_variable_nonblocking;
+	efi_set_variable_t *set_variable_nonblocking;
 	efi_query_variable_info_t *query_variable_info;
+	efi_query_variable_info_t *query_variable_info_nonblocking;
 	efi_update_capsule_t *update_capsule;
 	efi_query_capsule_caps_t *query_capsule_caps;
 	efi_get_next_high_mono_count_t *get_next_high_mono_count;
···
 #ifdef CONFIG_X86
 extern void efi_late_init(void);
 extern void efi_free_boot_services(void);
-extern efi_status_t efi_query_variable_store(u32 attributes, unsigned long size);
+extern efi_status_t efi_query_variable_store(u32 attributes,
+					     unsigned long size,
+					     bool nonblocking);
 extern void efi_find_mirror(void);
 #else
 static inline void efi_late_init(void) {}
 static inline void efi_free_boot_services(void) {}
 
-static inline efi_status_t efi_query_variable_store(u32 attributes, unsigned long size)
+static inline efi_status_t efi_query_variable_store(u32 attributes,
+						    unsigned long size,
+						    bool nonblocking)
 {
 	return EFI_SUCCESS;
 }
···
 	efi_get_variable_t *get_variable;
 	efi_get_next_variable_t *get_next_variable;
 	efi_set_variable_t *set_variable;
-	efi_set_variable_nonblocking_t *set_variable_nonblocking;
+	efi_set_variable_t *set_variable_nonblocking;
 	efi_query_variable_store_t *query_variable_store;
 };