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

…ux/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

@@ -10,12 +10,12 @@ arch/x86/boot/header.S and arch/x86/boot/compressed/eboot.c,
 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

@@ -16,6 +16,8 @@ ffffec0000000000 - fffffc0000000000 (=44 bits) kasan shadow memory (16TB)
 ... 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
@@ -32,11 +34,9 @@ reference.
 Current X86-64 implementations only support 40 bits of address space,
 but we support up to 46 bits. This expands into MBZ space in the page tables.
 
-->trampoline_pgd:
-
-We map EFI runtime services in the aforementioned PGD in the virtual
-range of 64Gb (arbitrarily set, can be raised if needed)
-
-0xffffffef00000000 - 0xffffffff00000000
+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

@@ -135,6 +135,7 @@ SECTIONS
 		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

@@ -3,6 +3,7 @@
 
 #include <asm/fpu/api.h>
 #include <asm/pgtable.h>
+#include <asm/tlb.h>
 
 /*
  * We map the EFI regions needed for runtime services non-contiguously,
@@ -66,14 +67,38 @@ extern u64 asmlinkage efi_call(void *fp, ...);
 
 #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;								\
@@ -113,11 +138,12 @@ 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);
 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

@@ -333,6 +333,7 @@ SECTIONS
 		__brk_limit = .;
 	}
 
+	. = ALIGN(PAGE_SIZE);
 	_end = .;
 
         STABS_DEBUG

arch/x86/mm/pageattr.c

@@ -909,16 +909,25 @@ static void populate_pte(struct cpa_data *cpa,
 
 	pte = pte_offset_kernel(pmd, start);
 
-	while (num_pages-- && start < end) {
+	/*
+	 * 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;
 
-		/* deal with the NX bit */
-		if (!(pgprot_val(pgprot) & _PAGE_NX))
-			cpa->pfn &= ~_PAGE_NX;
+	pgprot = canon_pgprot(pgprot);
 
-		set_pte(pte, pfn_pte(cpa->pfn >> PAGE_SHIFT, pgprot));
+	while (num_pages-- && start < end) {
+		set_pte(pte, pfn_pte(cpa->pfn, pgprot));
 
 		start	 += PAGE_SIZE;
-		cpa->pfn += PAGE_SIZE;
+		cpa->pfn++;
 		pte++;
 	}
 }
@@ -974,11 +983,11 @@ static int populate_pmd(struct cpa_data *cpa,
 
 		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;
 	}
 
@@ -1046,12 +1055,12 @@ static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
 	/*
 	 * 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++;
 	}
@@ -1964,6 +1973,9 @@ int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
 	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);
 
 	retval = __change_page_attr_set_clr(&cpa, 0);

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

@@ -10,6 +10,9 @@
  * 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>
@@ -28,8 +31,7 @@ struct bmp_header {
 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)
@@ -55,11 +57,6 @@ void __init efi_bgrt_init(void)
 		       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);
@@ -70,20 +67,19 @@ void __init efi_bgrt_init(void)
 		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);
@@ -93,18 +89,14 @@ void __init efi_bgrt_init(void)
 		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);
 }