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

Pull x86 EFI update from Peter Anvin:
 "EFI tree, from Matt Fleming.  Most of the patches are the new efivarfs
  filesystem by Matt Garrett & co.  The balance are support for EFI
  wallclock in the absence of a hardware-specific driver, and various
  fixes and cleanups."

* 'core-efi-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (24 commits)
  efivarfs: Make efivarfs_fill_super() static
  x86, efi: Check table header length in efi_bgrt_init()
  efivarfs: Use query_variable_info() to limit kmalloc()
  efivarfs: Fix return value of efivarfs_file_write()
  efivarfs: Return a consistent error when efivarfs_get_inode() fails
  efivarfs: Make 'datasize' unsigned long
  efivarfs: Add unique magic number
  efivarfs: Replace magic number with sizeof(attributes)
  efivarfs: Return an error if we fail to read a variable
  efi: Clarify GUID length calculations
  efivarfs: Implement exclusive access for {get,set}_variable
  efivarfs: efivarfs_fill_super() ensure we clean up correctly on error
  efivarfs: efivarfs_fill_super() ensure we free our temporary name
  efivarfs: efivarfs_fill_super() fix inode reference counts
  efivarfs: efivarfs_create() ensure we drop our reference on inode on error
  efivarfs: efivarfs_file_read ensure we free data in error paths
  x86-64/efi: Use EFI to deal with platform wall clock (again)
  x86/kernel: remove tboot 1:1 page table creation code
  x86, efi: 1:1 pagetable mapping for virtual EFI calls
  x86, mm: Include the entire kernel memory map in trampoline_pgd
  ...

Documentation/filesystems/00-INDEX

@@ -38,6 +38,8 @@ dnotify_test.c
 	- example program for dnotify
 ecryptfs.txt
 	- docs on eCryptfs: stacked cryptographic filesystem for Linux.
+efivarfs.txt
+	- info for the efivarfs filesystem.
 exofs.txt
 	- info, usage, mount options, design about EXOFS.
 ext2.txt

Documentation/filesystems/efivarfs.txt

+
+efivarfs - a (U)EFI variable filesystem
+
+The efivarfs filesystem was created to address the shortcomings of
+using entries in sysfs to maintain EFI variables. The old sysfs EFI
+variables code only supported variables of up to 1024 bytes. This
+limitation existed in version 0.99 of the EFI specification, but was
+removed before any full releases. Since variables can now be larger
+than a single page, sysfs isn't the best interface for this.
+
+Variables can be created, deleted and modified with the efivarfs
+filesystem.
+
+efivarfs is typically mounted like this,
+
+	mount -t efivarfs none /sys/firmware/efi/efivars

arch/x86/include/asm/efi.h

@@ -69,23 +69,37 @@ extern u64 efi_call6(void *fp, u64 arg1, u64 arg2, u64 arg3,
 	efi_call6((void *)(f), (u64)(a1), (u64)(a2), (u64)(a3),		\
 		  (u64)(a4), (u64)(a5), (u64)(a6))
 
+extern unsigned long efi_call_virt_prelog(void);
+extern void efi_call_virt_epilog(unsigned long);
+
+#define efi_callx(x, func, ...)					\
+	({							\
+		efi_status_t __status;				\
+		unsigned long __pgd;				\
+								\
+		__pgd = efi_call_virt_prelog();			\
+		__status = efi_call##x(func, __VA_ARGS__);	\
+		efi_call_virt_epilog(__pgd);			\
+		__status;					\
+	})
+
 #define efi_call_virt0(f)				\
-	efi_call0((void *)(efi.systab->runtime->f))
+	efi_callx(0, (void *)(efi.systab->runtime->f))
 #define efi_call_virt1(f, a1)					\
-	efi_call1((void *)(efi.systab->runtime->f), (u64)(a1))
+	efi_callx(1, (void *)(efi.systab->runtime->f), (u64)(a1))
 #define efi_call_virt2(f, a1, a2)					\
-	efi_call2((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2))
+	efi_callx(2, (void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2))
 #define efi_call_virt3(f, a1, a2, a3)					\
-	efi_call3((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
+	efi_callx(3, (void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
 		  (u64)(a3))
 #define efi_call_virt4(f, a1, a2, a3, a4)				\
-	efi_call4((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
+	efi_callx(4, (void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
 		  (u64)(a3), (u64)(a4))
 #define efi_call_virt5(f, a1, a2, a3, a4, a5)				\
-	efi_call5((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
+	efi_callx(5, (void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
 		  (u64)(a3), (u64)(a4), (u64)(a5))
 #define efi_call_virt6(f, a1, a2, a3, a4, a5, a6)			\
-	efi_call6((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
+	efi_callx(6, (void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
 		  (u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6))
 
 extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,

arch/x86/kernel/tboot.c

@@ -103,71 +103,13 @@ void __init tboot_probe(void)
 	pr_debug("tboot_size: 0x%x\n", tboot->tboot_size);
 }
 
-static pgd_t *tboot_pg_dir;
-static struct mm_struct tboot_mm = {
-	.mm_rb          = RB_ROOT,
-	.pgd            = swapper_pg_dir,
-	.mm_users       = ATOMIC_INIT(2),
-	.mm_count       = ATOMIC_INIT(1),
-	.mmap_sem       = __RWSEM_INITIALIZER(init_mm.mmap_sem),
-	.page_table_lock =  __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock),
-	.mmlist         = LIST_HEAD_INIT(init_mm.mmlist),
-};
-
 static inline void switch_to_tboot_pt(void)
 {
-	write_cr3(virt_to_phys(tboot_pg_dir));
-}
-
-static int map_tboot_page(unsigned long vaddr, unsigned long pfn,
-			  pgprot_t prot)
-{
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
-
-	pgd = pgd_offset(&tboot_mm, vaddr);
-	pud = pud_alloc(&tboot_mm, pgd, vaddr);
-	if (!pud)
-		return -1;
-	pmd = pmd_alloc(&tboot_mm, pud, vaddr);
-	if (!pmd)
-		return -1;
-	pte = pte_alloc_map(&tboot_mm, NULL, pmd, vaddr);
-	if (!pte)
-		return -1;
-	set_pte_at(&tboot_mm, vaddr, pte, pfn_pte(pfn, prot));
-	pte_unmap(pte);
-	return 0;
-}
-
-static int map_tboot_pages(unsigned long vaddr, unsigned long start_pfn,
-			   unsigned long nr)
-{
-	/* Reuse the original kernel mapping */
-	tboot_pg_dir = pgd_alloc(&tboot_mm);
-	if (!tboot_pg_dir)
-		return -1;
-
-	for (; nr > 0; nr--, vaddr += PAGE_SIZE, start_pfn++) {
-		if (map_tboot_page(vaddr, start_pfn, PAGE_KERNEL_EXEC))
-			return -1;
-	}
-
-	return 0;
-}
-
-static void tboot_create_trampoline(void)
-{
-	u32 map_base, map_size;
-
-	/* Create identity map for tboot shutdown code. */
-	map_base = PFN_DOWN(tboot->tboot_base);
-	map_size = PFN_UP(tboot->tboot_size);
-	if (map_tboot_pages(map_base << PAGE_SHIFT, map_base, map_size))
-		panic("tboot: Error mapping tboot pages (mfns) @ 0x%x, 0x%x\n",
-		      map_base, map_size);
+#ifdef CONFIG_X86_32
+	load_cr3(initial_page_table);
+#else
+	write_cr3(real_mode_header->trampoline_pgd);
+#endif
 }
 
 #ifdef CONFIG_ACPI_SLEEP
@@ -225,14 +167,6 @@ void tboot_shutdown(u32 shutdown_type)
 	if (!tboot_enabled())
 		return;
 
-	/*
-	 * if we're being called before the 1:1 mapping is set up then just
-	 * return and let the normal shutdown happen; this should only be
-	 * due to very early panic()
-	 */
-	if (!tboot_pg_dir)
-		return;
-
 	/* if this is S3 then set regions to MAC */
 	if (shutdown_type == TB_SHUTDOWN_S3)
 		if (tboot_setup_sleep())
@@ -343,8 +277,6 @@ static __init int tboot_late_init(void)
 	if (!tboot_enabled())
 		return 0;
 
-	tboot_create_trampoline();
-
 	atomic_set(&ap_wfs_count, 0);
 	register_hotcpu_notifier(&tboot_cpu_notifier);
 

arch/x86/mm/init_64.c

@@ -108,13 +108,13 @@ void sync_global_pgds(unsigned long start, unsigned long end)
 	for (address = start; address <= end; address += PGDIR_SIZE) {
 		const pgd_t *pgd_ref = pgd_offset_k(address);
 		struct page *page;
+		pgd_t *pgd;
 
 		if (pgd_none(*pgd_ref))
 			continue;
 
 		spin_lock(&pgd_lock);
 		list_for_each_entry(page, &pgd_list, lru) {
-			pgd_t *pgd;
 			spinlock_t *pgt_lock;
 
 			pgd = (pgd_t *)page_address(page) + pgd_index(address);
@@ -130,6 +130,13 @@ void sync_global_pgds(unsigned long start, unsigned long end)
 
 			spin_unlock(pgt_lock);
 		}
+
+		pgd = __va(real_mode_header->trampoline_pgd);
+		pgd += pgd_index(address);
+
+		if (pgd_none(*pgd))
+			set_pgd(pgd, *pgd_ref);
+
 		spin_unlock(&pgd_lock);
 	}
 }

arch/x86/mm/ioremap.c

@@ -50,6 +50,107 @@ int ioremap_change_attr(unsigned long vaddr, unsigned long size,
 	return err;
 }
 
+#ifdef CONFIG_X86_64
+static void ident_pte_range(unsigned long paddr, unsigned long vaddr,
+			    pmd_t *ppmd, pmd_t *vpmd, unsigned long end)
+{
+	pte_t *ppte = pte_offset_kernel(ppmd, paddr);
+	pte_t *vpte = pte_offset_kernel(vpmd, vaddr);
+
+	do {
+		set_pte(ppte, *vpte);
+	} while (ppte++, vpte++, vaddr += PAGE_SIZE, vaddr != end);
+}
+
+static int ident_pmd_range(unsigned long paddr, unsigned long vaddr,
+			    pud_t *ppud, pud_t *vpud, unsigned long end)
+{
+	pmd_t *ppmd = pmd_offset(ppud, paddr);
+	pmd_t *vpmd = pmd_offset(vpud, vaddr);
+	unsigned long next;
+
+	do {
+		next = pmd_addr_end(vaddr, end);
+
+		if (!pmd_present(*ppmd)) {
+			pte_t *ppte = (pte_t *)get_zeroed_page(GFP_KERNEL);
+			if (!ppte)
+				return 1;
+
+			set_pmd(ppmd, __pmd(_KERNPG_TABLE | __pa(ppte)));
+		}
+
+		ident_pte_range(paddr, vaddr, ppmd, vpmd, next);
+	} while (ppmd++, vpmd++, vaddr = next, vaddr != end);
+
+	return 0;
+}
+
+static int ident_pud_range(unsigned long paddr, unsigned long vaddr,
+			    pgd_t *ppgd, pgd_t *vpgd, unsigned long end)
+{
+	pud_t *ppud = pud_offset(ppgd, paddr);
+	pud_t *vpud = pud_offset(vpgd, vaddr);
+	unsigned long next;
+
+	do {
+		next = pud_addr_end(vaddr, end);
+
+		if (!pud_present(*ppud)) {
+			pmd_t *ppmd = (pmd_t *)get_zeroed_page(GFP_KERNEL);
+			if (!ppmd)
+				return 1;
+
+			set_pud(ppud, __pud(_KERNPG_TABLE | __pa(ppmd)));
+		}
+
+		if (ident_pmd_range(paddr, vaddr, ppud, vpud, next))
+			return 1;
+	} while (ppud++, vpud++, vaddr = next, vaddr != end);
+
+	return 0;
+}
+
+static int insert_identity_mapping(resource_size_t paddr, unsigned long vaddr,
+				    unsigned long size)
+{
+	unsigned long end = vaddr + size;
+	unsigned long next;
+	pgd_t *vpgd, *ppgd;
+
+	/* Don't map over the guard hole. */
+	if (paddr >= 0x800000000000 || paddr + size > 0x800000000000)
+		return 1;
+
+	ppgd = __va(real_mode_header->trampoline_pgd) + pgd_index(paddr);
+
+	vpgd = pgd_offset_k(vaddr);
+	do {
+		next = pgd_addr_end(vaddr, end);
+
+		if (!pgd_present(*ppgd)) {
+			pud_t *ppud = (pud_t *)get_zeroed_page(GFP_KERNEL);
+			if (!ppud)
+				return 1;
+
+			set_pgd(ppgd, __pgd(_KERNPG_TABLE | __pa(ppud)));
+		}
+
+		if (ident_pud_range(paddr, vaddr, ppgd, vpgd, next))
+			return 1;
+	} while (ppgd++, vpgd++, vaddr = next, vaddr != end);
+
+	return 0;
+}
+#else
+static inline int insert_identity_mapping(resource_size_t paddr,
+					  unsigned long vaddr,
+					  unsigned long size)
+{
+	return 0;
+}
+#endif /* CONFIG_X86_64 */
+
 /*
  * Remap an arbitrary physical address space into the kernel virtual
  * address space. Needed when the kernel wants to access high addresses
@@ -163,6 +264,10 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 	ret_addr = (void __iomem *) (vaddr + offset);
 	mmiotrace_ioremap(unaligned_phys_addr, unaligned_size, ret_addr);
 
+	if (insert_identity_mapping(phys_addr, vaddr, size))
+		printk(KERN_WARNING "ioremap: unable to map 0x%llx in identity pagetable\n",
+					(unsigned long long)phys_addr);
+
 	/*
 	 * Check if the request spans more than any BAR in the iomem resource
 	 * tree.

arch/x86/mm/pageattr.c

@@ -919,11 +919,13 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 
 	/*
 	 * On success we use clflush, when the CPU supports it to
-	 * avoid the wbindv. If the CPU does not support it and in the
-	 * error case we fall back to cpa_flush_all (which uses
-	 * wbindv):
+	 * avoid the wbindv. If the CPU does not support it, in the
+	 * error case, and during early boot (for EFI) we fall back
+	 * to cpa_flush_all (which uses wbinvd):
 	 */
-	if (!ret && cpu_has_clflush) {
+	if (early_boot_irqs_disabled)
+		__cpa_flush_all((void *)(long)cache);
+	else if (!ret && cpu_has_clflush) {
 		if (cpa.flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) {
 			cpa_flush_array(addr, numpages, cache,
 					cpa.flags, pages);

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

@@ -39,6 +39,8 @@ void efi_bgrt_init(void)
 	if (ACPI_FAILURE(status))
 		return;
 
+	if (bgrt_tab->header.length < sizeof(*bgrt_tab))
+		return;
 	if (bgrt_tab->version != 1)
 		return;
 	if (bgrt_tab->image_type != 0 || !bgrt_tab->image_address)

arch/x86/platform/efi/efi.c

@@ -239,22 +239,7 @@ static efi_status_t __init phys_efi_set_virtual_address_map(
 	return status;
 }
 
-static efi_status_t __init phys_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);
-	efi_call_phys_prelog();
-	status = efi_call_phys2(efi_phys.get_time, virt_to_phys(tm),
-				virt_to_phys(tc));
-	efi_call_phys_epilog();
-	spin_unlock_irqrestore(&rtc_lock, flags);
-	return status;
-}
-
-int efi_set_rtc_mmss(unsigned long nowtime)
+static int efi_set_rtc_mmss(unsigned long nowtime)
 {
 	int real_seconds, real_minutes;
 	efi_status_t 	status;
@@ -283,7 +268,7 @@ int efi_set_rtc_mmss(unsigned long nowtime)
 	return 0;
 }
 
-unsigned long efi_get_time(void)
+static unsigned long efi_get_time(void)
 {
 	efi_status_t status;
 	efi_time_t eft;
@@ -639,18 +624,13 @@ static int __init efi_runtime_init(void)
 	}
 	/*
 	 * We will only need *early* access to the following
-	 * two EFI runtime services before set_virtual_address_map
+	 * EFI runtime service before set_virtual_address_map
 	 * is invoked.
 	 */
-	efi_phys.get_time = (efi_get_time_t *)runtime->get_time;
 	efi_phys.set_virtual_address_map =
 		(efi_set_virtual_address_map_t *)
 		runtime->set_virtual_address_map;
-	/*
-	 * Make efi_get_time can be called before entering
-	 * virtual mode.
-	 */
-	efi.get_time = phys_efi_get_time;
+
 	early_iounmap(runtime, sizeof(efi_runtime_services_t));
 
 	return 0;
@@ -736,12 +716,10 @@ void __init efi_init(void)
 		efi_enabled = 0;
 		return;
 	}
-#ifdef CONFIG_X86_32
 	if (efi_is_native()) {
 		x86_platform.get_wallclock = efi_get_time;
 		x86_platform.set_wallclock = efi_set_rtc_mmss;
 	}
-#endif
 
 #if EFI_DEBUG
 	print_efi_memmap();

arch/x86/platform/efi/efi_64.c

@@ -58,6 +58,21 @@ static void __init early_code_mapping_set_exec(int executable)
 	}
 }
 
+unsigned long efi_call_virt_prelog(void)
+{
+	unsigned long saved;
+
+	saved = read_cr3();
+	write_cr3(real_mode_header->trampoline_pgd);
+
+	return saved;
+}
+
+void efi_call_virt_epilog(unsigned long saved)
+{
+	write_cr3(saved);
+}
+
 void __init efi_call_phys_prelog(void)
 {
 	unsigned long vaddress;

arch/x86/realmode/init.c

@@ -78,8 +78,21 @@ void __init setup_real_mode(void)
 	*trampoline_cr4_features = read_cr4();
 
 	trampoline_pgd = (u64 *) __va(real_mode_header->trampoline_pgd);
-	trampoline_pgd[0] = __pa(level3_ident_pgt) + _KERNPG_TABLE;
-	trampoline_pgd[511] = __pa(level3_kernel_pgt) + _KERNPG_TABLE;
+
+	/*
+	 * Create an identity mapping for all of physical memory.
+	 */
+	for (i = 0; i <= pgd_index(max_pfn << PAGE_SHIFT); i++) {
+		int index = pgd_index(PAGE_OFFSET) + i;
+
+		trampoline_pgd[i] = (u64)pgd_val(swapper_pg_dir[index]);
+	}
+
+	/*
+	 * Copy the upper-half of the kernel pages tables.
+	 */
+	for (i = pgd_index(PAGE_OFFSET); i < PTRS_PER_PGD; i++)
+		trampoline_pgd[i] = (u64)pgd_val(swapper_pg_dir[i]);
 #endif
 }
 

include/linux/efi.h

@@ -29,7 +29,12 @@
 #define EFI_UNSUPPORTED		( 3 | (1UL << (BITS_PER_LONG-1)))
 #define EFI_BAD_BUFFER_SIZE     ( 4 | (1UL << (BITS_PER_LONG-1)))
 #define EFI_BUFFER_TOO_SMALL	( 5 | (1UL << (BITS_PER_LONG-1)))
+#define EFI_NOT_READY		( 6 | (1UL << (BITS_PER_LONG-1)))
+#define EFI_DEVICE_ERROR	( 7 | (1UL << (BITS_PER_LONG-1)))
+#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_SECURITY_VIOLATION	(26 | (1UL << (BITS_PER_LONG-1)))
 
 typedef unsigned long efi_status_t;
 typedef u8 efi_bool_t;
@@ -582,8 +587,6 @@ extern u64 efi_mem_attribute (unsigned long phys_addr, unsigned long size);
 extern int __init efi_uart_console_only (void);
 extern void efi_initialize_iomem_resources(struct resource *code_resource,
 		struct resource *data_resource, struct resource *bss_resource);
-extern unsigned long efi_get_time(void);
-extern int efi_set_rtc_mmss(unsigned long nowtime);
 extern void efi_reserve_boot_services(void);
 extern struct efi_memory_map memmap;
 
@@ -729,6 +732,7 @@ struct efivars {
 	spinlock_t lock;
 	struct list_head list;
 	struct kset *kset;
+	struct kobject *kobject;
 	struct bin_attribute *new_var, *del_var;
 	const struct efivar_operations *ops;
 	struct efivar_entry *walk_entry;

include/uapi/linux/magic.h

@@ -27,6 +27,7 @@
 #define ISOFS_SUPER_MAGIC	0x9660
 #define JFFS2_SUPER_MAGIC	0x72b6
 #define PSTOREFS_MAGIC		0x6165676C
+#define EFIVARFS_MAGIC		0xde5e81e4
 
 #define MINIX_SUPER_MAGIC	0x137F		/* minix v1 fs, 14 char names */
 #define MINIX_SUPER_MAGIC2	0x138F		/* minix v1 fs, 30 char names */

init/main.c

@@ -463,6 +463,10 @@ static void __init mm_init(void)
 	percpu_init_late();
 	pgtable_cache_init();
 	vmalloc_init();
+#ifdef CONFIG_X86
+	if (efi_enabled)
+		efi_enter_virtual_mode();
+#endif
 }
 
 asmlinkage void __init start_kernel(void)
@@ -603,10 +607,6 @@ asmlinkage void __init start_kernel(void)
 	calibrate_delay();
 	pidmap_init();
 	anon_vma_init();
-#ifdef CONFIG_X86
-	if (efi_enabled)
-		efi_enter_virtual_mode();
-#endif
 	thread_info_cache_init();
 	cred_init();
 	fork_init(totalram_pages);